Showing 1–50 of 70 results for author: Das, S K

Receding-Horizon Next-Best-View Planner for Autonomous Leaf Surface Reconstruction

Authors: Arif Ahmed, Sajal K. Das, Parikshit Maini

Abstract: Accurate plant leaf modeling is fundamental to downstream tasks such as plant growth monitoring, and phenotyping for yield estimation. Autonomous robotic reconstruction for large-scale field deployment must address limitations on robot planning budget and computation resources while optimizing viewpoint utility for leaf surface reconstruction. Existing approaches either focus on rigid objects, poi… ▽ More Accurate plant leaf modeling is fundamental to downstream tasks such as plant growth monitoring, and phenotyping for yield estimation. Autonomous robotic reconstruction for large-scale field deployment must address limitations on robot planning budget and computation resources while optimizing viewpoint utility for leaf surface reconstruction. Existing approaches either focus on rigid objects, point-cloud coverage or plant reconstruction without fully addressing the system limitations or exploiting task-driven point cloud utility. In this work, we study next-best-view (NBV) planning for leaf surface reconstruction under travel constraints. We develop a novel Centroid-based Information Gain (CIG) function that measures the spatial distribution of observed points relative to the centroid of the existing point cloud to compute viewpoint utility. We also develop a receding-horizon variant that reasons over future viewpoints. To benchmark our work, we use the LAST-STRAW [1] public dataset that includes point clouds of strawberry plants over different growth stages and compare our method with attention-driven NBV [2] that uses a visibility-based information gain approach. The proposed receding-horizon approach consistently reduces surface reconstruction error and improves geometric fidelity across multiple growth stages, especially under increased inter-leaf occlusion. Results demonstrate that our approach is able to visit viewpoints that reduce surface reconstruction error and improves reconstruc-tion accuracy as compared to the baseline by upto 10%. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Comments: Accepted at IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)

A method of Risk Analysis and threat management using analytic hierarchy process

Authors: Manvi Sahni, Sumanta Kumar Das

Abstract: Efficient risk analysis and threat management are essential requirements of modern air defense (AD) systems. The paper is halfway between the analytic hierarchy process (AHP) and practical reasoning to model and analyze the risks and threats associated with military AD applications. The models are applied for decision-making tasks of AD command and control (C2) for assessing and prioritizing the t… ▽ More Efficient risk analysis and threat management are essential requirements of modern air defense (AD) systems. The paper is halfway between the analytic hierarchy process (AHP) and practical reasoning to model and analyze the risks and threats associated with military AD applications. The models are applied for decision-making tasks of AD command and control (C2) for assessing and prioritizing the threat from hostile targets for efficient risk management. The paper presents a method for threat assessment using fuzzy set theory, the AHP, and the technique for order preference by similarity to ideal solution (TOPSIS). The target threat attributes are first represented using fuzzy set theory. The experts' subjective opinions on different alternatives are quantified and ranked using the AHP process. These AHP solutions are obtained through the TOPSIS for prioritization. The models are implemented in a simulated environment. The simulated system runs without any human intervention and represents the state-of-the-art model for the C2 system. The use of fuzzy set theory, AHP, and TOPSIS for decision-making tasks is particularly useful from the point of view of futuristic risk and threat management in the battlefield. This method is easy to implement in practice and good for real-time applications. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Comments: 8 pages, 2 figures

Journal ref: Journal of Battlefield Technology,2015

Demographic Prompting at Scale: When More Attributes Hurt LLM--Human Agreement

Authors: Mahammed Kamruzzaman, Shrabon Kumar Das, Gene Louis Kim

Abstract: We investigate how annotator demographic attributes, supplied as prompt cues, shape the alignment between large language model (LLM) predictions and human annotations across five tasks. Using five open-source LLMs, we systematically vary the number and composition of demographic components in the prompt, spanning every combination from single-attribute through full-attribute configurations. Our ex… ▽ More We investigate how annotator demographic attributes, supplied as prompt cues, shape the alignment between large language model (LLM) predictions and human annotations across five tasks. Using five open-source LLMs, we systematically vary the number and composition of demographic components in the prompt, spanning every combination from single-attribute through full-attribute configurations. Our experiments reveal three principal findings. First, alignment consistently peaks with one to three high-signal attributes and degrades under the full attribute set, establishing a clear over-specification threshold. Second, the overall magnitude of demographic influence on human annotations does not predict which attributes improve LLM alignment; instead, both the learnability and the directional coherence of each attribute's annotation signal need to be considered jointly. Third, neuron probing reveals that specialized activation correlates with alignment gains only under coherent annotation signals, and that activation volume alone does not imply steerability. Together, these results demonstrate that demographic prompting is not a monolithic intervention: its utility is highly context-dependent, shaped by attribute signal quality, task characteristics, and model architecture. △ Less

Submitted 12 July, 2026; originally announced July 2026.

Bit-ViP: Leveraging Bit-planes to Preserve Visual Privacy in Images through Obfuscation

Authors: Vishesh Kumar Tanwar, Ashish Gupta, Sanjay Madria, Sajal K. Das

Abstract: The unprecedented growth of computer vision applications, such as surveillance systems and social media, raises security and visual privacy concerns, especially when data is stored on cloud servers. Image obfuscation offers a way to preserve visual privacy while maintaining an adequate level of usability; thus, it has been a topic of great interest in recent years. However, prior obfuscation schem… ▽ More The unprecedented growth of computer vision applications, such as surveillance systems and social media, raises security and visual privacy concerns, especially when data is stored on cloud servers. Image obfuscation offers a way to preserve visual privacy while maintaining an adequate level of usability; thus, it has been a topic of great interest in recent years. However, prior obfuscation schemes are either vulnerable to malicious attacks, such as model inversion to reconstruct original images from obfuscated images, or generate non-trainable obfuscated images, making them unusable for achieving reasonable accuracy. This paper proposes a novel bit-plane-based image obfuscation scheme, {\em Bit-ViP}, to preserve visual privacy for image-based recognition tasks. The Bit-ViP scheme produces secure, usable images by incorporating an innovative end-to-end obfuscation function. While doing so, the obfuscated image would contain non-invertible noise (generated by Lorenz's chaotic system and differential privacy), making it hard for an adversary to reconstruct the original image. We conduct extensive experiments on two popular activity recognition datasets, namely UCF101 and HMDB51, to validate the effectiveness of Bit-ViP. In the face of attacks on reconstruction, pixel frequency, information entropy, and pixel inter-correlation, we present a rigorous security analysis demonstrating tangible improvements over existing schemes. △ Less

Submitted 28 June, 2026; originally announced June 2026.

DynLP: Parallel Dynamic Batch Update for Label Propagation in Semi-Supervised Learning

Authors: S M Shovan, Arindam Khanda, S M Ferdous, Sajal K. Das, Mahantesh Halappanavar

Abstract: Semi-supervised learning aims to infer class labels using only a small fraction of labeled data. In graph-based semi-supervised learning, this is typically achieved through label propagation to predict labels of unlabeled nodes. However, in real-world applications, data often arrive incrementally in batches. Each time a new batch appears, reapplying the traditional label propagation algorithm to r… ▽ More Semi-supervised learning aims to infer class labels using only a small fraction of labeled data. In graph-based semi-supervised learning, this is typically achieved through label propagation to predict labels of unlabeled nodes. However, in real-world applications, data often arrive incrementally in batches. Each time a new batch appears, reapplying the traditional label propagation algorithm to recompute all labels is redundant, computationally intensive, and inefficient. To address the absence of an efficient label propagation update method, we propose DynLP, a novel GPU-centric Dynamic Batched Parallel Label Propagation algorithm that performs only the necessary updates, propagating changes to the relevant subgraph without requiring full recalculation. By exploiting GPU architectural optimizations, our algorithm achieves on average 13x and upto 102x speedup on large-scale datasets compared to state-of-the-art approaches. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Comments: To be published in the ACM International Conference on Supercomputing (ICS 2026)

VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection

Authors: PengYu Chen, Shang Wan, Xiaohou Shi, Yuan Chang, Yan Sun, Sajal K. Das

Abstract: Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability across different target datasets, hindering anomaly detection performance in various scenarios with scarce training data. To address this limitation, fou… ▽ More Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability across different target datasets, hindering anomaly detection performance in various scenarios with scarce training data. To address this limitation, foundation models have emerged as a promising direction. However, existing approaches either repurpose large language models (LLMs) or construct largescale time series datasets to develop general anomaly detection foundation models, and still face challenges caused by severe cross-modal gaps or in-domain heterogeneity. In this paper, we investigate the applicability of large-scale vision models to TSAD. Specifically, we adapt a visual Masked Autoencoder (MAE) pretrained on ImageNet to the TSAD task. However, directly transferring MAE to TSAD introduces two key challenges: overgeneralization and limited local perception. To address these challenges, we propose VAN-AD, a novel MAE-based framework for TSAD. To alleviate the over-generalization issue, we design an Adaptive Distribution Mapping Module (ADMM), which maps the reconstruction results before and after MAE into a unified statistical space to amplify discrepancies caused by abnormal patterns. To overcome the limitation of local perception, we further develop a Normalizing Flow Module (NFM), which combines MAE with normalizing flow to estimate the probability density of the current window under the global distribution. Extensive experiments on nine real-world datasets demonstrate that VAN-AD consistently outperforms existing state-of-the-art methods across multiple evaluation metrics.We make our code and datasets available at https://github.com/PenyChen/VAN-AD. △ Less

Submitted 15 July, 2026; v1 submitted 27 March, 2026; originally announced March 2026.

Comments: 15 pages, 7 figures

ReACT-TTC: Capacity-Aware Top Trading Cycles for Post-Choice Reassignment in Shared CPS

Authors: Anurag Satpathy, Arindam Khanda, Chittaranjan Swain, Sajal K. Das

Abstract: Cyber-physical systems (CPS) increasingly manage shared physical resources in the presence of human decision-making, where system-assigned actions must be executed by users or agents in the physical world. A fundamental challenge in such settings is user non-compliance: individuals may deviate from assigned resources due to personal preferences or local information, degrading system efficiency and… ▽ More Cyber-physical systems (CPS) increasingly manage shared physical resources in the presence of human decision-making, where system-assigned actions must be executed by users or agents in the physical world. A fundamental challenge in such settings is user non-compliance: individuals may deviate from assigned resources due to personal preferences or local information, degrading system efficiency and requiring light-weight reassignment schemes. This paper proposes a post-deviation reassignment framework for shared-resource CPS that operates on top of any initial allocation algorithm and is invoked only when users diverge from prescribed assignments. We advance the Top-Trading-Cycle (TTC) mechanism to enable voluntary, preference-driven exchanges after deviation events, and extend it to handle many-to-one resource capacities and unassigned resource conditions that are not supported by the classical TTC. We formalize these structural cases, introduce capacity-aware cycle-detection rules, and prove termination along with the preservation of Pareto efficiency, individual rationality, and strategy-proofness. A Prospect-Theoretic (PT) preference model is further incorporated to capture realistic user satisfaction behavior. We demonstrate the applicability of this framework on an electric-vehicle (EV) charging case study using real-world data, where it increases user satisfaction and effective assignment quality under non-compliant behavior. △ Less

Submitted 31 January, 2026; originally announced February 2026.

Comments: Accepted in the 17th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), Saint Mao, France, May 11-14, 2026

Congestion Mitigation in Vehicular Traffic Networks with Multiple Operational Modalities

Authors: Doris E. M. Brown, Sajal K. Das

Abstract: Modern commercial ground vehicles are increasingly equipped with multiple operational modalities (e.g., human driving, advanced driver assistance, remote tele-operation, full autonomy). These often rely on heterogeneous sensing infrastructures and distinct routing algorithms, which can yield misaligned perceptions of the traffic environment and route preferences. While such technologies accelerate… ▽ More Modern commercial ground vehicles are increasingly equipped with multiple operational modalities (e.g., human driving, advanced driver assistance, remote tele-operation, full autonomy). These often rely on heterogeneous sensing infrastructures and distinct routing algorithms, which can yield misaligned perceptions of the traffic environment and route preferences. While such technologies accelerate the transition toward increasingly intelligent transportation networks, their current deployment fails to avoid challenges associated with selfish routing behavior, in which drivers or automated agents prioritize individually optimal routes instead of network-wide congestion mitigation. Existing traffic flow management strategies can address leader-follower dynamics in traffic routing problems but are not designed to account for vehicles capable of dynamically switching between multiple operational modes. This paper models the interaction between a vehicle control arbitration system and a multi-modal vehicle as a repeated single-leader, multiple follower Stackelberg game with asymmetric information. To address the intractability of computing an exact solution in this setting, we propose a Trust-Aware Control Trading Strategy (TACTS) utilizing a regret matching-based algorithm to adaptively update the arbitration system's mixed strategy over sequential, dynamic routing decisions. Theoretical results provide bounds on the realized total network travel time under TACTS algorithm relative to the system-optimal total network travel time. Experimental results of simulations between the system and a vehicle in several real-world traffic networks under various different congestion levels demonstrate that TACTS consistently reduces network-wide congestion and generally outperforms alternative routing and control-allocation strategies, particularly under high congestion and heavy induced vehicle flows. △ Less

Submitted 8 January, 2026; originally announced January 2026.

Comments: 10 pages, 4 figures; This is a working draft and can potentially have errors. Any feedback will be greatly appreciated, and will be acknowledged in the subsequent versions

ESCHER: Efficient and Scalable Hypergraph Evolution Representation with Application to Triad Counting

Authors: S. M. Shovan, Arindam Khanda, Sanjukta Bhowmick, Sajal K. Das

Abstract: Higher-order interactions beyond pairwise relationships in large complex networks are often modeled as hypergraphs. Analyzing hypergraph properties such as triad counts is essential, as hypergraphs can reveal intricate group interaction patterns that conventional graphs fail to capture. In real-world scenarios, these networks are often large and dynamic, introducing significant computational chall… ▽ More Higher-order interactions beyond pairwise relationships in large complex networks are often modeled as hypergraphs. Analyzing hypergraph properties such as triad counts is essential, as hypergraphs can reveal intricate group interaction patterns that conventional graphs fail to capture. In real-world scenarios, these networks are often large and dynamic, introducing significant computational challenges. Due to the absence of specialized software packages and data structures, the analysis of large dynamic hypergraphs remains largely unexplored. Motivated by this gap, we propose ESCHER, a GPU-centric parallel data structure for Efficient and Scalable Hypergraph Evolution Representation, designed to manage large scale hypergraph dynamics efficiently. We also design a hypergraph triad-count update framework that minimizes redundant computation while fully leveraging the capabilities of ESCHER for dynamic operations. We validate the efficacy of our approach across multiple categories of hypergraph triad counting, including hyperedge-based, incident-vertex-based, and temporal triads. Empirical results on both large real-world and synthetic datasets demonstrate that our proposed method outperforms existing state-of-the-art methods, achieving speedups of up to 104.5x, 473.7x, and 112.5x for hyperedge-based, incident-vertex-based, and temporal triad types, respectively. △ Less

Submitted 7 April, 2026; v1 submitted 24 December, 2025; originally announced December 2025.

Comments: To be published in the 2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)

RED-F: Reconstruction-Elimination based Dual-stream Contrastive Forecasting for Multivariate Time Series Anomaly Prediction

Authors: PengYu Chen, Xiaohou Shi, Yuan Chang, Yan Sun, Sajal K. Das

Abstract: Anomaly prediction (AP) in multivariate time series (MTS) is crucial to ensure system dependability. Existing methods either focus solely on whether an anomaly is imminent without providing precise predictions for the future anomaly, or performing predictions directly on historical data, which is easily drowned out by the normal patterns. To address the challenges in AP task, we propose RED-F, a n… ▽ More Anomaly prediction (AP) in multivariate time series (MTS) is crucial to ensure system dependability. Existing methods either focus solely on whether an anomaly is imminent without providing precise predictions for the future anomaly, or performing predictions directly on historical data, which is easily drowned out by the normal patterns. To address the challenges in AP task, we propose RED-F, a novel framework comprised of the Reconstruction-Elimination Model (REM) and the Dual-stream Contrastive Forecasting Model (DFM). We utilize REM to construct a baseline of normal patterns from historical data, providing a foundation for subsequent predictions of anomalies. Then DFM simultaneously predicts both the constructed normal pattern and the current window, employing a contrastive forecast that transforms the difficult AP task into a simpler, more robust task of relative trajectory comparison by computing the divergence between these two predictions. To enable the forecasting model to generate a prediction not easily obscured by normal patterns, we propose a Multi-Series Prediction (MSP) training objective to enhance its sensitivity to the current window. Extensive experiments on multiple real-world datasets demonstrate the superior capability of RED-F in anomaly prediction tasks. Our code is available at http://github.com/PenyChen/RED-F. △ Less

Submitted 12 January, 2026; v1 submitted 25 November, 2025; originally announced November 2025.

Comments: 13 pages

FedFusion: Federated Learning with Diversity- and Cluster-Aware Encoders for Robust Adaptation under Label Scarcity

Authors: Ferdinand Kahenga, Antoine Bagula, Patrick Sello, Sajal K. Das

Abstract: Federated learning in practice must contend with heterogeneous feature spaces, severe non-IID data, and scarce labels across clients. We present FedFusion, a federated transfer-learning framework that unifies domain adaptation and frugal labelling with diversity-/cluster-aware encoders (DivEn, DivEn-mix, DivEn-c). Labelled teacher clients guide learner clients via confidence-filtered pseudo-labels… ▽ More Federated learning in practice must contend with heterogeneous feature spaces, severe non-IID data, and scarce labels across clients. We present FedFusion, a federated transfer-learning framework that unifies domain adaptation and frugal labelling with diversity-/cluster-aware encoders (DivEn, DivEn-mix, DivEn-c). Labelled teacher clients guide learner clients via confidence-filtered pseudo-labels and domain-adaptive transfer, while clients maintain personalised encoders tailored to local data. To preserve global coherence under heterogeneity, FedFusion employs similarity-weighted classifier coupling (with optional cluster-wise averaging), mitigating dominance by data-rich sites and improving minority-client performance. The frugal-labelling pipeline combines self-/semi-supervised pretext training with selective fine-tuning, reducing annotation demands without sharing raw data. Across tabular and imaging benchmarks under IID, non-IID, and label-scarce regimes, FedFusion consistently outperforms state-of-the-art baselines in accuracy, robustness, and fairness while maintaining comparable communication and computation budgets. These results show that harmonising personalisation, domain adaptation, and label efficiency is an effective recipe for robust federated learning under real-world constraints. △ Less

Submitted 23 September, 2025; originally announced September 2025.

FedFiTS: Fitness-Selected, Slotted Client Scheduling for Trustworthy Federated Learning in Healthcare AI

Authors: Ferdinand Kahenga, Antoine Bagula, Sajal K. Das, Patrick Sello

Abstract: Federated Learning (FL) has emerged as a powerful paradigm for privacy-preserving model training, yet deployments in sensitive domains such as healthcare face persistent challenges from non-IID data, client unreliability, and adversarial manipulation. This paper introduces FedFiTS, a trust and fairness-aware selective FL framework that advances the FedFaSt line by combining fitness-based client el… ▽ More Federated Learning (FL) has emerged as a powerful paradigm for privacy-preserving model training, yet deployments in sensitive domains such as healthcare face persistent challenges from non-IID data, client unreliability, and adversarial manipulation. This paper introduces FedFiTS, a trust and fairness-aware selective FL framework that advances the FedFaSt line by combining fitness-based client election with slotted aggregation. FedFiTS implements a three-phase participation strategy-free-for-all training, natural selection, and slotted team participation-augmented with dynamic client scoring, adaptive thresholding, and cohort-based scheduling to balance convergence efficiency with robustness. A theoretical convergence analysis establishes bounds for both convex and non-convex objectives under standard assumptions, while a communication-complexity analysis shows reductions relative to FedAvg and other baselines. Experiments on diverse datasets-medical imaging (X-ray pneumonia), vision benchmarks (MNIST, FMNIST), and tabular agricultural data (Crop Recommendation)-demonstrate that FedFiTS consistently outperforms FedAvg, FedRand, and FedPow in accuracy, time-to-target, and resilience to poisoning attacks. By integrating trust-aware aggregation with fairness-oriented client selection, FedFiTS advances scalable and secure FL, making it well suited for real-world healthcare and cross-domain deployments. △ Less

Submitted 23 September, 2025; originally announced September 2025.

Energy-Efficient Split Learning for Resource-Constrained Environments: A Smart Farming Solution

Authors: Keiwan Soltani, Vishesh Kumar Tanwar, Ashish Gupta, Sajal K. Das

Abstract: Smart farming systems encounter significant challenges, including limited resources, the need for data privacy, and poor connectivity in rural areas. To address these issues, we present eEnergy-Split, an energy-efficient framework that utilizes split learning (SL) to enable collaborative model training without direct data sharing or heavy computation on edge devices. By distributing the model betw… ▽ More Smart farming systems encounter significant challenges, including limited resources, the need for data privacy, and poor connectivity in rural areas. To address these issues, we present eEnergy-Split, an energy-efficient framework that utilizes split learning (SL) to enable collaborative model training without direct data sharing or heavy computation on edge devices. By distributing the model between edge devices and a central server, eEnergy-Split reduces on-device energy usage by up to 86 percent compared to federated learning (FL) while safeguarding data privacy. Moreover, SL improves classification accuracy by up to 6.2 percent over FL on ResNet-18 and by more modest amounts on GoogleNet and MobileNetV2. We propose an optimal edge deployment algorithm and a UAV trajectory planning strategy that solves the Traveling Salesman Problem (TSP) exactly to minimize flight cost and extend and maximize communication rounds. Comprehensive evaluations on agricultural pest datasets reveal that eEnergy-Split lowers UAV energy consumption compared to baseline methods and boosts overall accuracy by up to 17 percent. Notably, the energy efficiency of SL is shown to be model-dependent-yielding substantial savings in lightweight models like MobileNet, while communication and memory overheads may reduce efficiency gains in deeper networks. These results highlight the potential of combining SL with energy-aware design to deliver a scalable, privacy-preserving solution for resource-constrained smart farming environments. △ Less

Submitted 2 September, 2025; originally announced September 2025.

Comments: Accepted at the 22nd IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS), 2025

Learned Adaptive Indexing

Authors: Suvam Kumar Das, Suprio Ray

Abstract: Indexes can significantly improve search performance in relational databases. However, if the query workload changes frequently or new data updates occur continuously, it may not be worthwhile to build a conventional index upfront for query processing. Adaptive indexing is a technique in which an index gets built on the fly as a byproduct of query processing. In recent years, research in database… ▽ More Indexes can significantly improve search performance in relational databases. However, if the query workload changes frequently or new data updates occur continuously, it may not be worthwhile to build a conventional index upfront for query processing. Adaptive indexing is a technique in which an index gets built on the fly as a byproduct of query processing. In recent years, research in database indexing has taken a new direction where machine learning models are employed for the purpose of indexing. These indexes, known as learned indexes, can be more efficient compared to traditional indexes such as B+-tree in terms of memory footprints and query performance. However, a learned index has to be constructed upfront and requires training the model in advance, which becomes a challenge in dynamic situations when workload changes frequently. To the best of our knowledge, no learned indexes exist yet for adaptive indexing. We propose a novel learned approach for adaptive indexing. It is built on the fly as queries are submitted and utilizes learned models for indexing data. To enhance query performance, we employ a query workload prediction technique that makes future workload projection based on past workload data. We have evaluated our learned adaptive indexing approach against existing adaptive indexes for various query workloads. Our results show that our approach performs better than others in most cases, offering 1.2x - 5.6x improvement in query performance. △ Less

Submitted 5 August, 2025; originally announced August 2025.

A Parallel Algorithm for Finding Robust Spanners in Large Social Networks

Authors: Arindam Khanda, Satyaki Roy, Prithwiraj Roy, Sajal K. Das

Abstract: Social networks, characterized by community structures, often rely on nodes called structural hole spanners to facilitate inter-community information dissemination. However, the dynamic nature of these networks, where spanner nodes may be removed, necessitates resilient methods to maintain inter-community communication. To this end, we introduce robust spanners (RS) as nodes uniquely equipped to b… ▽ More Social networks, characterized by community structures, often rely on nodes called structural hole spanners to facilitate inter-community information dissemination. However, the dynamic nature of these networks, where spanner nodes may be removed, necessitates resilient methods to maintain inter-community communication. To this end, we introduce robust spanners (RS) as nodes uniquely equipped to bridge communities despite disruptions, such as node or edge removals. We propose a novel scoring technique to identify RS nodes and present a parallel algorithm with a CUDA implementation for efficient RS detection in large networks. Empirical analysis of real-world social networks reveals that high-scoring nodes exhibit a spanning capacity comparable to those identified by benchmark spanner detection algorithms while offering superior robustness. Our implementation on Nvidia GPUs achieves an average speedup of 244X over traditional spanner detection techniques, demonstrating its efficacy to identify RS in large social networks. △ Less

Submitted 2 August, 2025; originally announced August 2025.

CARGO: A Co-Optimization Framework for EV Charging and Routing in Goods Delivery Logistics

Authors: Arindam Khanda, Anurag Satpathy, Amit Jha, Sajal K. Das

Abstract: With growing interest in sustainable logistics, electric vehicle (EV)-based deliveries offer a promising alternative for urban distribution. However, EVs face challenges due to their limited battery capacity, requiring careful planning for recharging. This depends on factors such as the charging point (CP) availability, cost, proximity, and vehicles' state of charge (SoC). We propose CARGO, a fram… ▽ More With growing interest in sustainable logistics, electric vehicle (EV)-based deliveries offer a promising alternative for urban distribution. However, EVs face challenges due to their limited battery capacity, requiring careful planning for recharging. This depends on factors such as the charging point (CP) availability, cost, proximity, and vehicles' state of charge (SoC). We propose CARGO, a framework addressing the EV-based delivery route planning problem (EDRP), which jointly optimizes route planning and charging for deliveries within time windows. After proving the problem's NP-hardness, we propose a mixed integer linear programming (MILP)-based exact solution and a computationally efficient heuristic method. Using real-world datasets, we evaluate our methods by comparing the heuristic to the MILP solution, and benchmarking it against baseline strategies, Earliest Deadline First (EDF) and Nearest Delivery First (NDF). The results show up to 39% and 22% reductions in the charging cost over EDF and NDF, respectively, while completing comparable deliveries. △ Less

Submitted 2 August, 2025; originally announced August 2025.

ReinDSplit: Reinforced Dynamic Split Learning for Pest Recognition in Precision Agriculture

Authors: Vishesh Kumar Tanwar, Soumik Sarkar, Asheesh K. Singh, Sajal K. Das

Abstract: To empower precision agriculture through distributed machine learning (DML), split learning (SL) has emerged as a promising paradigm, partitioning deep neural networks (DNNs) between edge devices and servers to reduce computational burdens and preserve data privacy. However, conventional SL frameworks' one-split-fits-all strategy is a critical limitation in agricultural ecosystems where edge insec… ▽ More To empower precision agriculture through distributed machine learning (DML), split learning (SL) has emerged as a promising paradigm, partitioning deep neural networks (DNNs) between edge devices and servers to reduce computational burdens and preserve data privacy. However, conventional SL frameworks' one-split-fits-all strategy is a critical limitation in agricultural ecosystems where edge insect monitoring devices exhibit vast heterogeneity in computational power, energy constraints, and connectivity. This leads to straggler bottlenecks, inefficient resource utilization, and compromised model performance. Bridging this gap, we introduce ReinDSplit, a novel reinforcement learning (RL)-driven framework that dynamically tailors DNN split points for each device, optimizing efficiency without sacrificing accuracy. Specifically, a Q-learning agent acts as an adaptive orchestrator, balancing workloads and latency thresholds across devices to mitigate computational starvation or overload. By framing split layer selection as a finite-state Markov decision process, ReinDSplit convergence ensures that highly constrained devices contribute meaningfully to model training over time. Evaluated on three insect classification datasets using ResNet18, GoogleNet, and MobileNetV2, ReinDSplit achieves 94.31% accuracy with MobileNetV2. Beyond agriculture, ReinDSplit pioneers a paradigm shift in SL by harmonizing RL for resource efficiency, privacy, and scalability in heterogeneous environments. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Improving Bangla Linguistics: Advanced LSTM, Bi-LSTM, and Seq2Seq Models for Translating Sylheti to Modern Bangla

Authors: Sourav Kumar Das, Md. Julkar Naeen, MD. Jahidul Islam, Md. Anisul Haque Sajeeb, Narayan Ranjan Chakraborty, Mayen Uddin Mojumdar

Abstract: Bangla or Bengali is the national language of Bangladesh, people from different regions don't talk in proper Bangla. Every division of Bangladesh has its own local language like Sylheti, Chittagong etc. In recent years some papers were published on Bangla language like sentiment analysis, fake news detection and classifications, but a few of them were on Bangla languages. This research is for the… ▽ More Bangla or Bengali is the national language of Bangladesh, people from different regions don't talk in proper Bangla. Every division of Bangladesh has its own local language like Sylheti, Chittagong etc. In recent years some papers were published on Bangla language like sentiment analysis, fake news detection and classifications, but a few of them were on Bangla languages. This research is for the local language and this particular paper is on Sylheti language. It presented a comprehensive system using Natural Language Processing or NLP techniques for translating Pure or Modern Bangla to locally spoken Sylheti Bangla language. Total 1200 data used for training 3 models LSTM, Bi-LSTM and Seq2Seq and LSTM scored the best in performance with 89.3% accuracy. The findings of this research may contribute to the growth of Bangla NLP researchers for future more advanced innovations. △ Less

Submitted 24 May, 2025; originally announced May 2025.

Comments: 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)

Journal ref: 2024 15th Int. Conf. on Computing Communication and Networking Technologies (ICCCNT), Kamand, India, pp. 1-7, 2024

DATAMUt: Deterministic Algorithms for Time-Delay Attack Detection in Multi-Hop UAV Networks

Authors: Keiwan Soltani, Federico Corò, Punyasha Chatterjee, Sajal K. Das

Abstract: Unmanned Aerial Vehicles (UAVs), also known as drones, have gained popularity in various fields such as agriculture, emergency response, and search and rescue operations. UAV networks are susceptible to several security threats, such as wormhole, jamming, spoofing, and false data injection. Time Delay Attack (TDA) is a unique attack in which malicious UAVs intentionally delay packet forwarding, po… ▽ More Unmanned Aerial Vehicles (UAVs), also known as drones, have gained popularity in various fields such as agriculture, emergency response, and search and rescue operations. UAV networks are susceptible to several security threats, such as wormhole, jamming, spoofing, and false data injection. Time Delay Attack (TDA) is a unique attack in which malicious UAVs intentionally delay packet forwarding, posing significant threats, especially in time-sensitive applications. It is challenging to distinguish malicious delay from benign network delay due to the dynamic nature of UAV networks, intermittent wireless connectivity, or the Store-Carry-Forward (SCF) mechanism during multi-hop communication. Some existing works propose machine learning-based centralized approaches to detect TDA, which are computationally intensive and have large message overheads. This paper proposes a novel approach DATAMUt, where the temporal dynamics of the network are represented by a weighted time-window graph (TWiG), and then two deterministic polynomial-time algorithms are presented to detect TDA when UAVs have global and local network knowledge. Simulation studies show that the proposed algorithms have reduced message overhead by a factor of five and twelve in global and local knowledge, respectively, compared to existing approaches. Additionally, our approaches achieve approximately 860 and 1050 times less execution time in global and local knowledge, respectively, outperforming the existing methods. △ Less

Submitted 12 May, 2025; originally announced May 2025.

Iterative Recommendations based on Monte Carlo Sampling and Trust Estimation in Multi-Stage Vehicular Traffic Routing Games

Authors: Doris E. M. Brown, Venkata Sriram Siddhardh Nadendla, Sajal K. Das

Abstract: The shortest-time route recommendations offered by modern navigation systems fuel selfish routing in urban vehicular traffic networks and are therefore one of the main reasons for the growth of congestion. In contrast, intelligent transportation systems (ITS) prefer to steer driver-vehicle systems (DVS) toward system-optimal route recommendations, which are primarily designed to mitigate network c… ▽ More The shortest-time route recommendations offered by modern navigation systems fuel selfish routing in urban vehicular traffic networks and are therefore one of the main reasons for the growth of congestion. In contrast, intelligent transportation systems (ITS) prefer to steer driver-vehicle systems (DVS) toward system-optimal route recommendations, which are primarily designed to mitigate network congestion. However, due to the misalignment in motives, drivers exhibit a lack of trust in the ITS. This paper models the interaction between a DVS and an ITS as a novel, multi-stage routing game where the DVS exhibits dynamics in its trust towards the recommendations of ITS based on counterfactual and observed game outcomes. Specifically, DVS and ITS are respectively modeled as a travel-time minimizer and network congestion minimizer, each having nonidentical prior beliefs about the network state. A novel approximate algorithm to compute the Bayesian Nash equilibrium, called ROSTER(Recommendation Outcome Sampling with Trust Estimation and Re-evaluation), is proposed based on Monte Carlo sampling with trust belief updating to determine the best response route recommendations of the ITS at each stage of the game. Simulation results demonstrate that the trust prediction error in the proposed algorithm converges to zero with a growing number of multi-stage DVS-ITS interactions and is effectively able to both mitigate congestion and reduce driver travel times when compared to alternative route recommendation strategies. △ Less

Submitted 14 April, 2025; originally announced April 2025.

When Federated Learning Meets Quantum Computing: Survey and Research Opportunities

Authors: Aakar Mathur, Ashish Gupta, Sajal K. Das

Abstract: Quantum Federated Learning (QFL) is an emerging field that harnesses advances in Quantum Computing (QC) to improve the scalability and efficiency of decentralized Federated Learning (FL) models. This paper provides a systematic and comprehensive survey of the emerging problems and solutions when FL meets QC, from research protocol to a novel taxonomy, particularly focusing on both quantum and fede… ▽ More Quantum Federated Learning (QFL) is an emerging field that harnesses advances in Quantum Computing (QC) to improve the scalability and efficiency of decentralized Federated Learning (FL) models. This paper provides a systematic and comprehensive survey of the emerging problems and solutions when FL meets QC, from research protocol to a novel taxonomy, particularly focusing on both quantum and federated limitations, such as their architectures, Noisy Intermediate Scale Quantum (NISQ) devices, and privacy preservation, so on. With the introduction of two novel metrics, qubit utilization efficiency and quantum model training strategy, we present a thorough analysis of the current status of the QFL research. This work explores key developments and integration strategies, along with the impact of QC on FL, keeping a sharp focus on hybrid quantum-classical approaches. The paper offers an in-depth understanding of how the strengths of QC, such as gradient hiding, state entanglement, quantum key distribution, quantum security, and quantum-enhanced differential privacy, have been integrated into FL to ensure the privacy of participants in an enhanced, fast, and secure framework. Finally, this study proposes potential future directions to address the identified research gaps and challenges, aiming to inspire faster and more secure QFL models for practical use. △ Less

Submitted 13 November, 2025; v1 submitted 9 April, 2025; originally announced April 2025.

Comments: IEEE Communications Surveys and Tutorials

Integration of IoT- AI powered local weather forecasting: A Game-Changer for Agriculture

Authors: Suman Kumar Das, Pujyasmita Nayak

Abstract: The dynamic environment context necessitates harnessing digital technologies, including artificial intelligence and the Internet of Things, to supply high-resolution, real-time meteorological data to support agricultural decision-making and improve overall farm productivity and sustainability. This study investigates the potential application of various AI-powered, IoT-based, low-cost platforms fo… ▽ More The dynamic environment context necessitates harnessing digital technologies, including artificial intelligence and the Internet of Things, to supply high-resolution, real-time meteorological data to support agricultural decision-making and improve overall farm productivity and sustainability. This study investigates the potential application of various AI-powered, IoT-based, low-cost platforms for local weather forecasting to enable smart farming. Despite the increasing demand for this topic, a few promising studies have explored this area. This paper developed a conceptual research framework based on a systematic review of relevant literature and employed a case study method to validate the framework. The framework comprised five key components: the Data Acquisition Layer, Data Storage Layer, Data Processing Layer, Application Layer, and Decision-Making Layer. This paper contributes to the literature by exploring the integration of AI-ML and IoT techniques for weather prediction tasks to support agriculture, and the incorporation of IoT technologies that provide real-time, high-resolution meteorological data, representing a step forward. Furthermore, this paper discusses key research gaps, such as the significant obstacles impeding the adoption of AI in agriculture and local weather forecasting, including the lack of straightforward solutions and the lack of digital skills among farmers, particularly those in rural areas. Further empirical research is needed to enhance the existing frameworks and address these challenges. △ Less

Submitted 22 December, 2024; originally announced January 2025.

Comments: 14 pages, 1 figure, One table

Non-Convex Optimization in Federated Learning via Variance Reduction and Adaptive Learning

Authors: Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino, Sajal K. Das

Abstract: This paper proposes a novel federated algorithm that leverages momentum-based variance reduction with adaptive learning to address non-convex settings across heterogeneous data. We intend to minimize communication and computation overhead, thereby fostering a sustainable federated learning system. We aim to overcome challenges related to gradient variance, which hinders the model's efficiency, and… ▽ More This paper proposes a novel federated algorithm that leverages momentum-based variance reduction with adaptive learning to address non-convex settings across heterogeneous data. We intend to minimize communication and computation overhead, thereby fostering a sustainable federated learning system. We aim to overcome challenges related to gradient variance, which hinders the model's efficiency, and the slow convergence resulting from learning rate adjustments with heterogeneous data. The experimental results on the image classification tasks with heterogeneous data reveal the effectiveness of our suggested algorithms in non-convex settings with an improved communication complexity of $\mathcal{O}(ε^{-1})$ to converge to an $ε$-stationary point - compared to the existing communication complexity $\mathcal{O}(ε^{-2})$ of most prior works. The proposed federated version maintains the trade-off between the convergence rate, number of communication rounds, and test accuracy while mitigating the client drift in heterogeneous settings. The experimental results demonstrate the efficiency of our algorithms in image classification tasks (MNIST, CIFAR-10) with heterogeneous data. △ Less

Submitted 16 December, 2024; originally announced December 2024.

Comments: FLUID Workshop@AAAI 2025

SMEVCA: Stable Matching-based EV Charging Assignment in Subscription-Based Models

Authors: Arindam Khanda, Anurag Satpathy, Anusha Vangala, Sajal K. Das

Abstract: The rapid shift from internal combustion engine vehicles to battery-powered electric vehicles (EVs) presents considerable challenges, such as limited charging points (CPs), unpredictable wait times, and difficulty selecting appropriate CPs. To address these challenges, we propose a novel end-to-end framework called Stable Matching EV Charging Assignment (SMEVCA) that efficiently assigns charge-see… ▽ More The rapid shift from internal combustion engine vehicles to battery-powered electric vehicles (EVs) presents considerable challenges, such as limited charging points (CPs), unpredictable wait times, and difficulty selecting appropriate CPs. To address these challenges, we propose a novel end-to-end framework called Stable Matching EV Charging Assignment (SMEVCA) that efficiently assigns charge-seeking EVs to CPs with assistance from roadside units (RSUs). The proposed framework operates within a subscription-based model, ensuring that the subscribed EVs complete their charging within a predefined time limit enforced by a service level agreement (SLA). The framework SMEVCA employs a stable, fast, and efficient EV-CP assignment formulated as a one-to-many matching game with preferences. The matching process identifies the preferred coalition (a subset of EVs assigned to the CPs) using two strategies: (1) Preferred Coalition Greedy (PCG) that offers an efficient, locally optimal heuristic solution and (2) Preferred Coalition Dynamic (PCD) that is more computation-intensive but delivers a globally optimal coalition. Extensive simulations reveal that PCG and PCD achieve a gain of 14.6% and 20.8% over random elimination for in-network charge transferred with only 3% and 0.1% EVs unserved within the RSUs vicinity. △ Less

Submitted 13 December, 2024; originally announced December 2024.

Comments: This paper has been accepted for presentation at the 26th International Conference on Distributed Computing and Networking (ICDCN), 2025

Collision-free Exploration by Mobile Agents Using Pebbles

Authors: Sajal K. Das, Amit Kumar Dhar, Barun Gorain, Madhuri Mahawar

Abstract: In this paper, we study collision-free graph exploration in an anonymous pot labeled network. Two identical mobile agents, starting from different nodes in $G$ have to explore the nodes of $G$ in such a way that for every node $v$ in $G$, at least one mobile agent visits $v$ and no two agents are in the same node in any round and stop. The agents know the size of the graph but do not know its topo… ▽ More In this paper, we study collision-free graph exploration in an anonymous pot labeled network. Two identical mobile agents, starting from different nodes in $G$ have to explore the nodes of $G$ in such a way that for every node $v$ in $G$, at least one mobile agent visits $v$ and no two agents are in the same node in any round and stop. The agents know the size of the graph but do not know its topology. If an agent arrives in the one-hop neighborhood of the other agent, both agents can detect the presence of the other agent but have no idea at which neighboring node the other agent resides. The agents may wake up in different rounds An agent, after waking up, has no knowledge about the wake-up time of the other agent. We study the problem of collision-free exploration where some pebbles are placed by an Oracle at the nodes of the graph to assist the agents in achieving collision-free exploration. The Oracle knows the graph, the starting positions of the agents, and their wake-up schedule, and it places some pebbles that may be of different colors, at most one at each node. The number of different colors of the pebbles placed by the Oracle is called the {\it color index} of the corresponding pebble placement algorithm. The central question we study is as follows: "What is the minimum number $z$ such that there exists a collision-free exploration of a given graph with pebble placement of color index $z$?" For general graphs, we show that it is impossible to design an algorithm that achieves collision-free exploration with color index 1. We propose an exploration algorithm with color index 3. We also proposed a polynomial exploration algorithm for bipartite graphs with color index 2. △ Less

Submitted 22 October, 2024; originally announced October 2024.

CTG-KrEW: Generating Synthetic Structured Contextually Correlated Content by Conditional Tabular GAN with K-Means Clustering and Efficient Word Embedding

Authors: Riya Samanta, Bidyut Saha, Soumya K. Ghosh, Sajal K. Das

Abstract: Conditional Tabular Generative Adversarial Networks (CTGAN) and their various derivatives are attractive for their ability to efficiently and flexibly create synthetic tabular data, showcasing strong performance and adaptability. However, there are certain critical limitations to such models. The first is their inability to preserve the semantic integrity of contextually correlated words or phrase… ▽ More Conditional Tabular Generative Adversarial Networks (CTGAN) and their various derivatives are attractive for their ability to efficiently and flexibly create synthetic tabular data, showcasing strong performance and adaptability. However, there are certain critical limitations to such models. The first is their inability to preserve the semantic integrity of contextually correlated words or phrases. For instance, skillset in freelancer profiles is one such attribute where individual skills are semantically interconnected and indicative of specific domain interests or qualifications. The second challenge of traditional approaches is that, when applied to generate contextually correlated tabular content, besides generating semantically shallow content, they consume huge memory resources and CPU time during the training stage. To address these problems, we introduce a novel framework, CTGKrEW (Conditional Tabular GAN with KMeans Clustering and Word Embedding), which is adept at generating realistic synthetic tabular data where attributes are collections of semantically and contextually coherent words. CTGKrEW is trained and evaluated using a dataset from Upwork, a realworld freelancing platform. Comprehensive experiments were conducted to analyze the variability, contextual similarity, frequency distribution, and associativity of the generated data, along with testing the framework's system feasibility. CTGKrEW also takes around 99\% less CPU time and 33\% less memory footprints than the conventional approach. Furthermore, we developed KrEW, a web application to facilitate the generation of realistic data containing skill-related information. This application, available at https://riyasamanta.github.io/krew.html, is freely accessible to both the general public and the research community. △ Less

Submitted 3 September, 2024; originally announced September 2024.

Exact Trajectory Similarity Search With N-tree: An Efficient Metric Index for kNN and Range Queries

Authors: Ralf Hartmut Güting, Suvam Kumar Das, Fabio Valdés, Suprio Ray

Abstract: Similarity search is the problem of finding in a collection of objects those that are similar to a given query object. It is a fundamental problem in modern applications and the objects considered may be as diverse as locations in space, text documents, images, twitter messages, or trajectories of moving objects. In this paper we are motivated by the latter application. Trajectories are recorded… ▽ More Similarity search is the problem of finding in a collection of objects those that are similar to a given query object. It is a fundamental problem in modern applications and the objects considered may be as diverse as locations in space, text documents, images, twitter messages, or trajectories of moving objects. In this paper we are motivated by the latter application. Trajectories are recorded movements of mobile objects such as vehicles, animals, public transportation, or parts of the human body. We propose a novel distance function called DistanceAvg to capture the similarity of such movements. To be practical, it is necessary to provide indexing for this distance measure. Fortunately we do not need to start from scratch. A generic and unifying approach is metric space, which organizes the set of objects solely by a distance (similarity) function with certain natural properties. Our function DistanceAvg is a metric. Although metric indexes have been studied for decades and many such structures are available, they do not offer the best performance with trajectories. In this paper we propose a new design, which outperforms the best existing indexes for kNN queries and is equally good for range queries. It is especially suitable for expensive distance functions as they occur in trajectory similarity search. In many applications, kNN queries are more practical than range queries as it may be difficult to determine an appropriate search radius. Our index provides exact result sets for the given distance function. △ Less

Submitted 14 August, 2024; originally announced August 2024.

Comments: 54 pages, 26 figures

ACM Class: H.2.2; H.3.3

Tackling Selfish Clients in Federated Learning

Authors: Andrea Augello, Ashish Gupta, Giuseppe Lo Re, Sajal K. Das

Abstract: Federated Learning (FL) is a distributed machine learning paradigm facilitating participants to collaboratively train a model without revealing their local data. However, when FL is deployed into the wild, some intelligent clients can deliberately deviate from the standard training process to make the global model inclined toward their local model, thereby prioritizing their local data distributio… ▽ More Federated Learning (FL) is a distributed machine learning paradigm facilitating participants to collaboratively train a model without revealing their local data. However, when FL is deployed into the wild, some intelligent clients can deliberately deviate from the standard training process to make the global model inclined toward their local model, thereby prioritizing their local data distribution. We refer to this novel category of misbehaving clients as selfish. In this paper, we propose a Robust aggregation strategy for FL server to mitigate the effect of Selfishness (in short RFL-Self). RFL-Self incorporates an innovative method to recover (or estimate) the true updates of selfish clients from the received ones, leveraging robust statistics (median of norms) of the updates at every round. By including the recovered updates in aggregation, our strategy offers strong robustness against selfishness. Our experimental results, obtained on MNIST and CIFAR-10 datasets, demonstrate that just 2% of clients behaving selfishly can decrease the accuracy by up to 36%, and RFL-Self can mitigate that effect without degrading the global model performance. △ Less

Submitted 22 July, 2024; originally announced July 2024.

Comments: 10 pages, 16 figures. European Conference on Artificial Intelligence (ECAI) 2024

Journal ref: Frontiers in Artificial Intelligence and Applications. 392(2024), 1888-1895

Addressing Data Heterogeneity in Federated Learning of Cox Proportional Hazards Models

Authors: Navid Seidi, Satyaki Roy, Sajal K. Das, Ardhendu Tripathy

Abstract: The diversity in disease profiles and therapeutic approaches between hospitals and health professionals underscores the need for patient-centric personalized strategies in healthcare. Alongside this, similarities in disease progression across patients can be utilized to improve prediction models in survival analysis. The need for patient privacy and the utility of prediction models can be simultan… ▽ More The diversity in disease profiles and therapeutic approaches between hospitals and health professionals underscores the need for patient-centric personalized strategies in healthcare. Alongside this, similarities in disease progression across patients can be utilized to improve prediction models in survival analysis. The need for patient privacy and the utility of prediction models can be simultaneously addressed in the framework of Federated Learning (FL). This paper outlines an approach in the domain of federated survival analysis, specifically the Cox Proportional Hazards (CoxPH) model, with a specific focus on mitigating data heterogeneity and elevating model performance. We present an FL approach that employs feature-based clustering to enhance model accuracy across synthetic datasets and real-world applications, including the Surveillance, Epidemiology, and End Results (SEER) database. Furthermore, we consider an event-based reporting strategy that provides a dynamic approach to model adaptation by responding to local data changes. Our experiments show the efficacy of our approach and discuss future directions for a practical application of FL in healthcare. △ Less

Submitted 20 July, 2024; originally announced July 2024.

TASR: A Novel Trust-Aware Stackelberg Routing Algorithm to Mitigate Traffic Congestion

Authors: Doris E. M. Brown, Venkata Sriram Siddhardh Nadendla, Sajal K. Das

Abstract: Stackelberg routing platforms (SRP) reduce congestion in one-shot traffic networks by proposing optimal route recommendations to selfish travelers. Traditionally, Stackelberg routing is cast as a partial control problem where a fraction of traveler flow complies with route recommendations, while the remaining respond as selfish travelers. In this paper, a novel Stackelberg routing framework is for… ▽ More Stackelberg routing platforms (SRP) reduce congestion in one-shot traffic networks by proposing optimal route recommendations to selfish travelers. Traditionally, Stackelberg routing is cast as a partial control problem where a fraction of traveler flow complies with route recommendations, while the remaining respond as selfish travelers. In this paper, a novel Stackelberg routing framework is formulated where the agents exhibit \emph{probabilistic compliance} by accepting SRP's route recommendations with a \emph{trust} probability. A greedy \emph{\textbf{T}rust-\textbf{A}ware \textbf{S}tackelberg \textbf{R}outing} algorithm (in short, TASR) is proposed for SRP to compute unique path recommendations to each traveler flow with a unique demand. Simulation experiments are designed with random travel demands with diverse trust values on real road networks such as Sioux Falls, Chicago Sketch, and Sydney networks for both single-commodity and multi-commodity flows. The performance of TASR is compared with state-of-the-art Stackelberg routing methods in terms of traffic congestion and trust dynamics over repeated interaction between the SRP and the travelers. Results show that TASR improves network congestion without causing a significant reduction in trust towards the SRP, when compared to most well-known Stackelberg routing strategies. △ Less

Submitted 28 March, 2024; originally announced March 2024.

Using Geographic Location-based Public Health Features in Survival Analysis

Authors: Navid Seidi, Ardhendu Tripathy, Sajal K. Das

Abstract: Time elapsed till an event of interest is often modeled using the survival analysis methodology, which estimates a survival score based on the input features. There is a resurgence of interest in developing more accurate prediction models for time-to-event prediction in personalized healthcare using modern tools such as neural networks. Higher quality features and more frequent observations improv… ▽ More Time elapsed till an event of interest is often modeled using the survival analysis methodology, which estimates a survival score based on the input features. There is a resurgence of interest in developing more accurate prediction models for time-to-event prediction in personalized healthcare using modern tools such as neural networks. Higher quality features and more frequent observations improve the predictions for a patient, however, the impact of including a patient's geographic location-based public health statistics on individual predictions has not been studied. This paper proposes a complementary improvement to survival analysis models by incorporating public health statistics in the input features. We show that including geographic location-based public health information results in a statistically significant improvement in the concordance index evaluated on the Surveillance, Epidemiology, and End Results (SEER) dataset containing nationwide cancer incidence data. The improvement holds for both the standard Cox proportional hazards model and the state-of-the-art Deep Survival Machines model. Our results indicate the utility of geographic location-based public health features in survival analysis. △ Less

Submitted 15 April, 2023; originally announced April 2023.

Journal ref: 2023 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), 2023, 80-91

Dispatching Point Selection for a Drone-Based Delivery System Operating in a Mixed Euclidean-Manhattan Grid

Authors: Francesco Betti Sorbelli, Federico Corò, Sajal K. Das, Cristina M. Pinotti, Anil Shende

Abstract: In this paper, we present a drone-based delivery system that assumes to deal with two different mixed-areas, i.e., rural and urban. In these mixed-areas, called EM-grids, the distances are measured with two different metrics, and the shortest path between two destinations concatenates the Euclidean and Manhattan metrics. Due to payload constraints, the drone serves a single customer at a time retu… ▽ More In this paper, we present a drone-based delivery system that assumes to deal with two different mixed-areas, i.e., rural and urban. In these mixed-areas, called EM-grids, the distances are measured with two different metrics, and the shortest path between two destinations concatenates the Euclidean and Manhattan metrics. Due to payload constraints, the drone serves a single customer at a time returning back to the dispatching point (DP) after each delivery to load a new parcel for the next customer. In this paper, we present the 1-Median Euclidean-Manhattan grid Problem (MEMP) for EM-grids, whose goal is to determine the drone's DP position that minimizes the sum of the distances between all the locations to be served and the point itself. We study the MEMP on two different scenarios, i.e., one in which all the customers in the area need to be served (full-grid) and another one where only a subset of these must be served (partial-grid). For the full-grid scenario we devise optimal, approximation, and heuristic algorithms, while for the partial-grid scenario we devise optimal and heuristic algorithms. Eventually, we comprehensively evaluate our algorithms on generated synthetic and quasi-real data. △ Less

Submitted 27 February, 2023; originally announced February 2023.

Biomedical image analysis competitions: The state of current participation practice

Authors: Matthias Eisenmann, Annika Reinke, Vivienn Weru, Minu Dietlinde Tizabi, Fabian Isensee, Tim J. Adler, Patrick Godau, Veronika Cheplygina, Michal Kozubek, Sharib Ali, Anubha Gupta, Jan Kybic, Alison Noble, Carlos Ortiz de Solórzano, Samiksha Pachade, Caroline Petitjean, Daniel Sage, Donglai Wei, Elizabeth Wilden, Deepak Alapatt, Vincent Andrearczyk, Ujjwal Baid, Spyridon Bakas, Niranjan Balu, Sophia Bano , et al. (331 additional authors not shown)

Abstract: The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis,… ▽ More The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps. △ Less

Submitted 12 September, 2023; v1 submitted 16 December, 2022; originally announced December 2022.

Securing Federated Learning against Overwhelming Collusive Attackers

Authors: Priyesh Ranjan, Ashish Gupta, Federico Corò, Sajal K. Das

Abstract: In the era of a data-driven society with the ubiquity of Internet of Things (IoT) devices storing large amounts of data localized at different places, distributed learning has gained a lot of traction, however, assuming independent and identically distributed data (iid) across the devices. While relaxing this assumption that anyway does not hold in reality due to the heterogeneous nature of device… ▽ More In the era of a data-driven society with the ubiquity of Internet of Things (IoT) devices storing large amounts of data localized at different places, distributed learning has gained a lot of traction, however, assuming independent and identically distributed data (iid) across the devices. While relaxing this assumption that anyway does not hold in reality due to the heterogeneous nature of devices, federated learning (FL) has emerged as a privacy-preserving solution to train a collaborative model over non-iid data distributed across a massive number of devices. However, the appearance of malicious devices (attackers), who intend to corrupt the FL model, is inevitable due to unrestricted participation. In this work, we aim to identify such attackers and mitigate their impact on the model, essentially under a setting of bidirectional label flipping attacks with collusion. We propose two graph theoretic algorithms, based on Minimum Spanning Tree and k-Densest graph, by leveraging correlations between local models. Our FL model can nullify the influence of attackers even when they are up to 70% of all the clients whereas prior works could not afford more than 50% of clients as attackers. The effectiveness of our algorithms is ascertained through experiments on two benchmark datasets, namely MNIST and Fashion-MNIST, with overwhelming attackers. We establish the superiority of our algorithms over the existing ones using accuracy, attack success rate, and early detection round. △ Less

Submitted 28 September, 2022; originally announced September 2022.

Comments: 7 Figures, 2 Tables

Digital Twin in Safety-Critical Robotics Applications: Opportunities and Challenges

Authors: Sabur Baidya, Sumit K. Das, Mohammad Helal Uddin, Chase Kosek, Chris Summers

Abstract: Digital Twin technology is being envisioned to be an integral part of the industrial evolution in modern generation. With the rapid advancement in the Internet-of-Things (IoT) technology and increasing trend of automation, integration between the virtual and the physical world is now realizable to produce practical digital twins. However, the existing definitions of digital twin is incomplete and… ▽ More Digital Twin technology is being envisioned to be an integral part of the industrial evolution in modern generation. With the rapid advancement in the Internet-of-Things (IoT) technology and increasing trend of automation, integration between the virtual and the physical world is now realizable to produce practical digital twins. However, the existing definitions of digital twin is incomplete and sometimes ambiguous. Herein, we conduct historical review and analyze the modern generic view of digital twin to create its new extended definition. We also review and discuss the existing work in digital twin in safety-critical robotics applications. Especially, the usage of digital twin in industrial applications necessitates autonomous and remote operations due to environmental challenges. However, the uncertainties in the environment may need close monitoring and quick adaptation of the robots which need to be safety-proof and cost effective. We demonstrate a case study on developing a framework for safety-critical robotic arm applications and present the system performance to show its advantages, and discuss the challenges and scopes ahead. △ Less

Submitted 26 September, 2022; originally announced September 2022.

Edge-assisted Collaborative Digital Twin for Safety-Critical Robotics in Industrial IoT

Authors: Sumit K. Das, Mohammad Helal Uddin, Sabur Baidya

Abstract: Digital Twin technology is playing a pivotal role in the modern industrial evolution. Especially, with the technological progress in the Internet-of-Things (IoT) and the increasing trend in autonomy, multi-sensor equipped robotics can create practical digital twin, which is particularly useful in the industrial applications for operations, maintenance and safety. Herein, we demonstrate a real-worl… ▽ More Digital Twin technology is playing a pivotal role in the modern industrial evolution. Especially, with the technological progress in the Internet-of-Things (IoT) and the increasing trend in autonomy, multi-sensor equipped robotics can create practical digital twin, which is particularly useful in the industrial applications for operations, maintenance and safety. Herein, we demonstrate a real-world digital twin of a safety-critical robotics applications with a Franka-Emika-Panda robotic arm. We develop and showcase an edge-assisted collaborative digital twin for dynamic obstacle avoidance which can be useful in real-time adaptation of the robots while operating in the uncertain and dynamic environments in industrial IoT. △ Less

Submitted 26 September, 2022; originally announced September 2022.

Suppressing Noise from Built Environment Datasets to Reduce Communication Rounds for Convergence of Federated Learning

Authors: Rahul Mishra, Hari Prabhat Gupta, Tanima Dutta, Sajal K. Das

Abstract: Smart sensing provides an easier and convenient data-driven mechanism for monitoring and control in the built environment. Data generated in the built environment are privacy sensitive and limited. Federated learning is an emerging paradigm that provides privacy-preserving collaboration among multiple participants for model training without sharing private and limited data. The noisy labels in the… ▽ More Smart sensing provides an easier and convenient data-driven mechanism for monitoring and control in the built environment. Data generated in the built environment are privacy sensitive and limited. Federated learning is an emerging paradigm that provides privacy-preserving collaboration among multiple participants for model training without sharing private and limited data. The noisy labels in the datasets of the participants degrade the performance and increase the number of communication rounds for convergence of federated learning. Such large communication rounds require more time and energy to train the model. In this paper, we propose a federated learning approach to suppress the unequal distribution of the noisy labels in the dataset of each participant. The approach first estimates the noise ratio of the dataset for each participant and normalizes the noise ratio using the server dataset. The proposed approach can handle bias in the server dataset and minimizes its impact on the participants' dataset. Next, we calculate the optimal weighted contributions of the participants using the normalized noise ratio and influence of each participant. We further derive the expression to estimate the number of communication rounds required for the convergence of the proposed approach. Finally, experimental results demonstrate the effectiveness of the proposed approach over existing techniques in terms of the communication rounds and achieved performance in the built environment. △ Less

Submitted 3 September, 2022; originally announced September 2022.

Comments: 11 pages, 5 figures

FedAR+: A Federated Learning Approach to Appliance Recognition with Mislabeled Data in Residential Buildings

Authors: Ashish Gupta, Hari Prabhat Gupta, Sajal K. Das

Abstract: With the enhancement of people's living standards and rapid growth of communication technologies, residential environments are becoming smart and well-connected, increasing overall energy consumption substantially. As household appliances are the primary energy consumers, their recognition becomes crucial to avoid unattended usage, thereby conserving energy and making smart environments more susta… ▽ More With the enhancement of people's living standards and rapid growth of communication technologies, residential environments are becoming smart and well-connected, increasing overall energy consumption substantially. As household appliances are the primary energy consumers, their recognition becomes crucial to avoid unattended usage, thereby conserving energy and making smart environments more sustainable. An appliance recognition model is traditionally trained at a central server (service provider) by collecting electricity consumption data, recorded via smart plugs, from the clients (consumers), causing a privacy breach. Besides that, the data are susceptible to noisy labels that may appear when an appliance gets connected to a non-designated smart plug. While addressing these issues jointly, we propose a novel federated learning approach to appliance recognition, called FedAR+, enabling decentralized model training across clients in a privacy preserving way even with mislabeled training data. FedAR+ introduces an adaptive noise handling method, essentially a joint loss function incorporating weights and label distribution, to empower the appliance recognition model against noisy labels. By deploying smart plugs in an apartment complex, we collect a labeled dataset that, along with two existing datasets, are utilized to evaluate the performance of FedAR+. Experimental results show that our approach can effectively handle up to $30\%$ concentration of noisy labels while outperforming the prior solutions by a large margin on accuracy. △ Less

Submitted 3 September, 2022; originally announced September 2022.

Comments: 11 pages, 9 figures, 4 tables

Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated Learning

Authors: Ashish Gupta, Tie Luo, Mao V. Ngo, Sajal K. Das

Abstract: Federated learning offers a framework of training a machine learning model in a distributed fashion while preserving privacy of the participants. As the server cannot govern the clients' actions, nefarious clients may attack the global model by sending malicious local gradients. In the meantime, there could also be unreliable clients who are benign but each has a portion of low-quality training da… ▽ More Federated learning offers a framework of training a machine learning model in a distributed fashion while preserving privacy of the participants. As the server cannot govern the clients' actions, nefarious clients may attack the global model by sending malicious local gradients. In the meantime, there could also be unreliable clients who are benign but each has a portion of low-quality training data (e.g., blur or low-resolution images), thus may appearing similar as malicious clients. Therefore, a defense mechanism will need to perform a three-fold differentiation which is much more challenging than the conventional (two-fold) case. This paper introduces MUD-HoG, a novel defense algorithm that addresses this challenge in federated learning using long-short history of gradients, and treats the detected malicious and unreliable clients differently. Not only this, but we can also distinguish between targeted and untargeted attacks among malicious clients, unlike most prior works which only consider one type of the attacks. Specifically, we take into account sign-flipping, additive-noise, label-flipping, and multi-label-flipping attacks, under a non-IID setting. We evaluate MUD-HoG with six state-of-the-art methods on two datasets. The results show that MUD-HoG outperforms all of them in terms of accuracy as well as precision and recall, in the presence of a mixture of multiple (four) types of attackers as well as unreliable clients. Moreover, unlike most prior works which can only tolerate a low population of harmful users, MUD-HoG can work with and successfully detect a wide range of malicious and unreliable clients - up to 47.5% and 10%, respectively, of the total population. Our code is open-sourced at https://github.com/LabSAINT/MUD-HoG_Federated_Learning. △ Less

Submitted 14 August, 2022; originally announced August 2022.

Comments: European Symposium on Research in Computer Security (ESORICS) 2022

Accurate and Efficient Modeling of 802.15.4 Unslotted CSMA/CA through Event Chains Computation

Authors: Domenico De Guglielmo, Francesco Restuccia, Giuseppe Anastasi, Marco Conti, Sajal K. Das

Abstract: Many analytical models have been proposed for evaluating the performance of event-driven 802.15.4 Wireless Sensor Networks (WSNs), in Non-Beacon Enabled (NBE) mode. However, existing models do not provide accurate analysis of large-scale WSNs, due to tractability issues and/or simplifying assumptions. In this paper, we propose a new approach called Event Chains Computation (ECC) to model the unslo… ▽ More Many analytical models have been proposed for evaluating the performance of event-driven 802.15.4 Wireless Sensor Networks (WSNs), in Non-Beacon Enabled (NBE) mode. However, existing models do not provide accurate analysis of large-scale WSNs, due to tractability issues and/or simplifying assumptions. In this paper, we propose a new approach called Event Chains Computation (ECC) to model the unslotted CSMA/CA algorithm used for channel access in NBE mode. ECC relies on the idea that outcomes of the CSMA/CA algorithm can be represented as chains of events that subsequently occur in the network. Although ECC can generate all the possible outcomes, it only considers chains with a probability to occur greater than a pre-defined threshold to reduce complexity. Furthermore, ECC parallelizes the computation by managing different chains through different threads. Our results show that, by an appropriate threshold selection, the time to derive performance metrics can be drastically reduced, with negligible impact on accuracy. We also show that the computation time decreases almost linearly with the number of employed threads. We validate our model through simulations and testbed experiments, and use it to investigate the impact of different parameters on the WSN performance, in terms of delivery ratio, latency, and energy consumption. △ Less

Submitted 30 May, 2022; originally announced May 2022.

Journal ref: In IEEE Transactions on Mobile Computing, vol. 15, no. 12, pp. 2954-2968, 1 Dec. 2016

The Internet of People (IoP): A New Wave in Pervasive Mobile Computing

Authors: Marco Conti, Andrea Passarella, Sajal K. Das

Abstract: Cyber-Physical convergence, the fast expansion of the Internet at its edge, and tighter interactions between human users and their personal mobile devices push towards an Internet where the human user becomes more central than ever, and where their personal devices become their proxies in the cyber world, in addition to acting as a fundamental tool to sense the physical world. The current Internet… ▽ More Cyber-Physical convergence, the fast expansion of the Internet at its edge, and tighter interactions between human users and their personal mobile devices push towards an Internet where the human user becomes more central than ever, and where their personal devices become their proxies in the cyber world, in addition to acting as a fundamental tool to sense the physical world. The current Internet paradigm, which is infrastructure-centric, is not the right one to cope with such emerging scenario with a wider range of applications. This calls for a radically new Internet paradigm, that we name the Internet of People (IoP), where the humans and their personal devices are not seen merely as end users of applications, but become active elements of the Internet. Note that IoP is not a replacement of the current Internet infrastructure, but it exploits legacy Internet services as (reliable) primitives to achieve end-to-end connectivity on a global-scale. In this visionary paper, we first discuss the key features of the IoP paradigm along with the underlying research issues and challenges. Then we present emerging networking and computing paradigms that are anticipating IoP △ Less

Submitted 27 May, 2022; originally announced May 2022.

Comments: arXiv admin note: text overlap with arXiv:2205.13970

Journal ref: Pervasive and Mobile Computing, Volume 41, 2017, Pages 1-27, ISSN 1574-1192

Service Provisioning in Mobile Environments through Opportunistic Computing

Authors: Davide Mascitti, Marco Conti, Andrea Passarella, Laura Ricci, Sajal K. Das

Abstract: Opportunistic computing is a paradigm for completely self-organised pervasive networks. Instead of relying only on fixed infrastructures as the cloud, users' devices act as service providers for each other. They use pairwise contacts to collect information about services provided and amount of time to provide them by the encountered nodes. At each node, upon generation of a service request, this i… ▽ More Opportunistic computing is a paradigm for completely self-organised pervasive networks. Instead of relying only on fixed infrastructures as the cloud, users' devices act as service providers for each other. They use pairwise contacts to collect information about services provided and amount of time to provide them by the encountered nodes. At each node, upon generation of a service request, this information is used to choose the most efficient service, or composition of services, that satisfy that request, based on local knowledge. Opportunistic computing can be exploited in several scenarios, including mobile social networks, IoT and Internet 4.0. In this paper we propose an opportunistic computing algorithm based on an analytical model, which ranks the available (composition of) services, based on their expected completion time. Through the model, a service requesters picks the one that is expected to be the best. Experiments show that the algorithm is accurate in ranking services, thus providing an effective service-selection policy. Such a policy achieves significantly lower service provisioning times compared to other reference policies. Its performance is tested in a wide range of scenarios varying the nodes mobility, the size of input/output parameters, the level of resource congestion, the computational complexity of service executions. △ Less

Submitted 27 May, 2022; originally announced May 2022.

Journal ref: in IEEE Transactions on Mobile Computing, vol. 17, no. 12, pp. 2898-2911, 1 Dec. 2018

Single Image Internal Distribution Measurement Using Non-Local Variational Autoencoder

Authors: Yeahia Sarker, Abdullah-Al-Zubaer Imran, Md Hafiz Ahamed, Ripon K. Chakrabortty, Michael J. Ryan, Sajal K. Das

Abstract: Deep learning-based super-resolution methods have shown great promise, especially for single image super-resolution (SISR) tasks. Despite the performance gain, these methods are limited due to their reliance on copious data for model training. In addition, supervised SISR solutions rely on local neighbourhood information focusing only on the feature learning processes for the reconstruction of low… ▽ More Deep learning-based super-resolution methods have shown great promise, especially for single image super-resolution (SISR) tasks. Despite the performance gain, these methods are limited due to their reliance on copious data for model training. In addition, supervised SISR solutions rely on local neighbourhood information focusing only on the feature learning processes for the reconstruction of low-dimensional images. Moreover, they fail to capitalize on global context due to their constrained receptive field. To combat these challenges, this paper proposes a novel image-specific solution, namely non-local variational autoencoder (\texttt{NLVAE}), to reconstruct a high-resolution (HR) image from a single low-resolution (LR) image without the need for any prior training. To harvest maximum details for various receptive regions and high-quality synthetic images, \texttt{NLVAE} is introduced as a self-supervised strategy that reconstructs high-resolution images using disentangled information from the non-local neighbourhood. Experimental results from seven benchmark datasets demonstrate the effectiveness of the \texttt{NLVAE} model. Moreover, our proposed model outperforms a number of baseline and state-of-the-art methods as confirmed through extensive qualitative and quantitative evaluations. △ Less

Submitted 2 April, 2022; originally announced April 2022.

Comments: A Preprint Version

Maximizing Social Welfare in Selfish Multi-Modal Routing using Strategic Information Design for Quantal Response Travelers

Authors: Sainath Sanga, Venkata Sriram Siddhardh Nadendla, Sajal K. Das

Abstract: Traditional selfish routing literature quantifies inefficiency in transportation systems with single-attribute costs using price-of-anarchy (PoA), and provides various technical approaches (e.g. marginal cost pricing) to improve PoA of the overall network. Unfortunately, practical transportation systems have dynamic, multi-attribute costs and the state-of-the-art technical approaches proposed in t… ▽ More Traditional selfish routing literature quantifies inefficiency in transportation systems with single-attribute costs using price-of-anarchy (PoA), and provides various technical approaches (e.g. marginal cost pricing) to improve PoA of the overall network. Unfortunately, practical transportation systems have dynamic, multi-attribute costs and the state-of-the-art technical approaches proposed in the literature are infeasible for practical deployment. In this paper, we offer a paradigm shift to selfish routing via characterizing idiosyncratic, multi-attribute costs at boundedly-rational travelers, as well as improving network efficiency using strategic information design. Specifically, we model the interaction between the system and travelers as a Stackelberg game, where travelers adopt multi-attribute logit responses. We model the strategic information design as an optimization problem, and develop a novel approximate algorithm to steer Logit Response travelers towards social welfare using strategic Information design (in short, LoRI). We demonstrate the performance of LoRI on a Wheatstone network with multi-modal route choices at the travelers. In our simulation experiments, we find that LoRI outperforms SSSP in terms of system utility, especially when there is a motive mismatch between the two systems and improves social welfare. For instance, we find that LoRI persuades a traveler towards a socially optimal route for 66.66% of the time on average, when compared to SSSP, when the system has 0.3 weight on carbon emissions. However, we also present a tradeoff between system performance and runtime in our simulation results. △ Less

Submitted 29 November, 2021; originally announced November 2021.

MobileCaps: A Lightweight Model for Screening and Severity Analysis of COVID-19 Chest X-Ray Images

Authors: S J Pawan, Rahul Sankar, Amithash M Prabhudev, P A Mahesh, K Prakashini, Sudha Kiran Das, Jeny Rajan

Abstract: The world is going through a challenging phase due to the disastrous effect caused by the COVID-19 pandemic on the healthcare system and the economy. The rate of spreading, post-COVID-19 symptoms, and the occurrence of new strands of COVID-19 have put the healthcare systems in disruption across the globe. Due to this, the task of accurately screening COVID-19 cases has become of utmost priority. S… ▽ More The world is going through a challenging phase due to the disastrous effect caused by the COVID-19 pandemic on the healthcare system and the economy. The rate of spreading, post-COVID-19 symptoms, and the occurrence of new strands of COVID-19 have put the healthcare systems in disruption across the globe. Due to this, the task of accurately screening COVID-19 cases has become of utmost priority. Since the virus infects the respiratory system, Chest X-Ray is an imaging modality that is adopted extensively for the initial screening. We have performed a comprehensive study that uses CXR images to identify COVID-19 cases and realized the necessity of having a more generalizable model. We utilize MobileNetV2 architecture as the feature extractor and integrate it into Capsule Networks to construct a fully automated and lightweight model termed as MobileCaps. MobileCaps is trained and evaluated on the publicly available dataset with the model ensembling and Bayesian optimization strategies to efficiently classify CXR images of patients with COVID-19 from non-COVID-19 pneumonia and healthy cases. The proposed model is further evaluated on two additional RT-PCR confirmed datasets to demonstrate the generalizability. We also introduce MobileCaps-S and leverage it for performing severity assessment of CXR images of COVID-19 based on the Radiographic Assessment of Lung Edema (RALE) scoring technique. Our classification model achieved an overall recall of 91.60, 94.60, 92.20, and a precision of 98.50, 88.21, 92.62 for COVID-19, non-COVID-19 pneumonia, and healthy cases, respectively. Further, the severity assessment model attained an R$^2$ coefficient of 70.51. Owing to the fact that the proposed models have fewer trainable parameters than the state-of-the-art models reported in the literature, we believe our models will go a long way in aiding healthcare systems in the battle against the pandemic. △ Less

Submitted 19 August, 2021; originally announced August 2021.

Comments: 14 pages, 6 figures

MSC Class: 68T07 ACM Class: I.2.10

On the Robot Assisted Movement in Wireless Mobile Sensor Networks

Authors: Sajal K. Das, Rafał Kapelko

Abstract: This paper deals with random sensors initially randomly deployed on the line according to general random process and on the plane according to two independent general random processes. The mobile robot with carrying capacity $k$ placed at the origin point is to move the sensors to achieve the general scheduling requirement such as coverage, connectivity and thus to satisfy the desired communicatio… ▽ More This paper deals with random sensors initially randomly deployed on the line according to general random process and on the plane according to two independent general random processes. The mobile robot with carrying capacity $k$ placed at the origin point is to move the sensors to achieve the general scheduling requirement such as coverage, connectivity and thus to satisfy the desired communication property in the network. We study tradeoffs between the energy consumption in robot's movement, the numbers of sensors $n$, the sensor range $r$, the interference distance $s$, and the robot capacity $k$ until completion of the coverage simultaneously with interference scheduling task. In this work, we obtain upper bounds for the energy consumption in robot's movement and obtain the sharp decrease in the total movement cost of the robot so as to provide the coverage simultaneously with interference requirement. △ Less

Submitted 7 July, 2021; originally announced July 2021.

Social Behavior and Mental Health: A Snapshot Survey under COVID-19 Pandemic

Authors: Sahraoui Dhelim, Liming Luke Chen, Huansheng Ning, Sajal K Das, Chris Nugent, Devin Burns, Gerard Leavey, Dirk Pesch, Eleanor Bantry-White

Abstract: Online social media provides a channel for monitoring people's social behaviors and their mental distress. Due to the restrictions imposed by COVID-19 people are increasingly using online social networks to express their feelings. Consequently, there is a significant amount of diverse user-generated social media content. However, COVID-19 pandemic has changed the way we live, study, socialize and… ▽ More Online social media provides a channel for monitoring people's social behaviors and their mental distress. Due to the restrictions imposed by COVID-19 people are increasingly using online social networks to express their feelings. Consequently, there is a significant amount of diverse user-generated social media content. However, COVID-19 pandemic has changed the way we live, study, socialize and recreate and this has affected our well-being and mental health problems. There are growing researches that leverage online social media analysis to detect and assess user's mental status. In this paper, we survey the literature of social media analysis for mental disorders detection, with a special focus on the studies conducted in the context of COVID-19 during 2020-2021. Firstly, we classify the surveyed studies in terms of feature extraction types, varying from language usage patterns to aesthetic preferences and online behaviors. Secondly, we explore detection methods used for mental disorders detection including machine learning and deep learning detection methods. Finally, we discuss the challenges of mental disorder detection using social media data, including the privacy and ethical concerns, as well as the technical challenges of scaling and deploying such systems at large scales, and discuss the learnt lessons over the last few years. △ Less

Submitted 17 May, 2021; originally announced May 2021.

Comments: Submitted to ACM Computing Surveys

A Unified System for Data Analytics and In Situ Query Processing

Authors: Alex Watson, Suvam Kumar Das, Suprio Ray

Abstract: In today's world data is being generated at a high rate due to which it has become inevitable to analyze and quickly get results from this data. Most of the relational databases primarily support SQL querying with a limited support for complex data analysis. Due to this reason, data scientists have no other option, but to use a different system for complex data analysis. Due to this, data science… ▽ More In today's world data is being generated at a high rate due to which it has become inevitable to analyze and quickly get results from this data. Most of the relational databases primarily support SQL querying with a limited support for complex data analysis. Due to this reason, data scientists have no other option, but to use a different system for complex data analysis. Due to this, data science frameworks are in huge demand. But to use such a framework, all the data needs to be loaded into it. This requires significant data movement across multiple systems, which can be expensive. We believe that it has become the need of the hour to come up with a single system which can perform both data analysis tasks and SQL querying. This will save the data scientists from the expensive data transfer operation across systems. In our work, we present DaskDB, a system built over the Python's Dask framework, which is a scalable data science system having support for both data analytics and in situ SQL query processing over heterogeneous data sources. DaskDB supports invoking any Python APIs as User-Defined Functions (UDF) over SQL queries. So, it can be easily integrated with most existing Python data science applications, without modifying the existing code. Since joining two relations is a very vital but expensive operation, so a novel distributed learned index is also introduced to improve the join performance. Our experimental evaluation demonstrates that DaskDB significantly outperforms existing systems. △ Less

Submitted 7 April, 2021; v1 submitted 18 February, 2021; originally announced February 2021.

Heuristic Algorithms for Co-scheduling of Edge Analytics and Routes for UAV Fleet Missions

Authors: Aakash Khochare, Yogesh Simmhan, Francesco Betti Sorbelli, Sajal K. Das

Abstract: Unmanned Aerial Vehicles (UAVs) or drones are increasingly used for urban applications like traffic monitoring and construction surveys. Autonomous navigation allows drones to visit waypoints and accomplish activities as part of their mission. A common activity is to hover and observe a location using on-board cameras. Advances in Deep Neural Networks (DNNs) allow such videos to be analyzed for au… ▽ More Unmanned Aerial Vehicles (UAVs) or drones are increasingly used for urban applications like traffic monitoring and construction surveys. Autonomous navigation allows drones to visit waypoints and accomplish activities as part of their mission. A common activity is to hover and observe a location using on-board cameras. Advances in Deep Neural Networks (DNNs) allow such videos to be analyzed for automated decision making. UAVs also host edge computing capability for on-board inferencing by such DNNs. To this end, for a fleet of drones, we propose a novel Mission Scheduling Problem (MSP) that co-schedules the flight routes to visit and record video at waypoints, and their subsequent on-board edge analytics. The proposed schedule maximizes the utility from the activities while meeting activity deadlines as well as energy and computing constraints. We first prove that MSP is NP-hard and then optimally solve it by formulating a mixed integer linear programming (MILP) problem. Next, we design two efficient heuristic algorithms, JSC and VRC, that provide fast sub-optimal solutions. Evaluation of these three schedulers using real drone traces demonstrate utility-runtime trade-offs under diverse workloads. △ Less

Submitted 6 February, 2021; originally announced February 2021.

Comments: infocom 2021 paper

Speeding up Routing Schedules on Aisle-Graphs with Single Access

Authors: Francesco Betti Sorbelli, Stefano Carpin, Federico Coro, Sajal K. Das, Alfredo Navarra, Cristina M. Pinotti

Abstract: In this paper, we study the Orienteering Aisle-graphs Single-access Problem (OASP), a variant of the orienteering problem for a robot moving in a so-called single-access aisle-graph, i.e., a graph consisting of a set of rows that can be accessed from one side only. Aisle-graphs model, among others, vineyards or warehouses. Each aisle-graph vertex is associated with a reward that a robot obtains wh… ▽ More In this paper, we study the Orienteering Aisle-graphs Single-access Problem (OASP), a variant of the orienteering problem for a robot moving in a so-called single-access aisle-graph, i.e., a graph consisting of a set of rows that can be accessed from one side only. Aisle-graphs model, among others, vineyards or warehouses. Each aisle-graph vertex is associated with a reward that a robot obtains when visits the vertex itself. As the robot's energy is limited, only a subset of vertices can be visited with a fully charged battery. The objective is to maximize the total reward collected by the robot with a battery charge. We first propose an optimal algorithm that solves OASP in O(m^2 n^2) time for aisle-graphs with a single access consisting of m rows, each with n vertices. With the goal of designing faster solutions, we propose four greedy sub-optimal algorithms that run in at most O(mn (m+n)) time. For two of them, we guarantee an approximation ratio of 1/2(1-1/e), where e is the base of the natural logarithm, on the total reward by exploiting the well-known submodularity property. Experimentally, we show that these algorithms collect more than 80% of the optimal reward. △ Less

Submitted 10 February, 2021; originally announced February 2021.

Comments: re-submitted revised version to IEEE Transactions on Robotics (T-RO) after a conditionally accepted response