Showing 1–41 of 41 results for author: Mohan, C

Constrained Deep Reinforcement Learning for Cognitive Radar Resource Management

Authors: Ziyang Lu, M. Cenk Gursoy, Chilukuri K. Mohan, Pramod K. Varshney

Abstract: In this paper, multi-target tracking and scanning are considered in a radar system operating in the track-while-scan mode. Specifically, time allocation for radar scanning and tracking of multiple maneuvering targets under a time budget constraint is addressed, aiming to jointly optimize the performance of both tracking and scanning in a cognitive radar. We first present the details of the model f… ▽ More In this paper, multi-target tracking and scanning are considered in a radar system operating in the track-while-scan mode. Specifically, time allocation for radar scanning and tracking of multiple maneuvering targets under a time budget constraint is addressed, aiming to jointly optimize the performance of both tracking and scanning in a cognitive radar. We first present the details of the model for tracking and scanning and formulate the time management task as a constrained optimization problem. Subsequently, we design a \gls{cdrl} framework to find the time allocation strategy for the problem. In the proposed \gls{cdrl} framework, the parameters of the neural networks and the dual variable are learned simultaneously. The deep deterministic policy gradient (DDPG) algorithm is introduced to tackle continuous action space and its performance is compared with deep Q-learning, heuristic approaches, and an optimization-based approach. Numerical results show that the radar with the proposed \gls{cdrl} framework can autonomously allocate more time to the tracking task that requires greater attention while providing time for scanning and also constraining the total time budget below the predefined threshold. △ Less

Submitted 3 June, 2026; originally announced June 2026.

Robust by Design: A Continuous Monitoring and Data Integration Framework for Medical AI

Authors: Mohammad Daouk, Jan Ulrich Becker, Neeraja Kambham, Anthony Chang, Chandra Mohan, Hien Van Nguyen

Abstract: Adaptive medical AI models often face performance drops in dynamic clinical environments due to data drift. We propose an autonomous continuous monitoring and data integration framework that maintains robust performance over time. Focusing on glomerular pathology image classification (proliferative vs. non-proliferative lupus nephritis), our three-stage method uses multi-metric feature analysis an… ▽ More Adaptive medical AI models often face performance drops in dynamic clinical environments due to data drift. We propose an autonomous continuous monitoring and data integration framework that maintains robust performance over time. Focusing on glomerular pathology image classification (proliferative vs. non-proliferative lupus nephritis), our three-stage method uses multi-metric feature analysis and Monte Carlo dropout-based uncertainty gating to decide when to retrain on new data. Only images statistically similar to the training distribution (via Euclidean, cosine, Mahalanobis metrics) and with low predictive entropy are integrated. The model is then incrementally retrained with these images under strict performance safeguards (no metric degradation >5%). In experiments with a ResNet18 ensemble on a multi-center dataset, the framework prevents performance degradation: new images were added without significant change in AUC (~0.92) or accuracy (~89%). This approach addresses data shift and avoids catastrophic forgetting, enabling sustained learning in medical imaging AI. △ Less

Submitted 10 April, 2026; originally announced April 2026.

Comments: Accepted at IEEE ISBI 2026. Chandra Mohan and Hien Van Nguyen jointly supervised this work

Shortcut Learning in Glomerular AI: Adversarial Penalties Hurt, Entropy Helps

Authors: Mohammad Daouk, Jan Ulrich Becker, Neeraja Kambham, Anthony Chang, Hien Van Nguyen, Chandra Mohan

Abstract: Stain variability is a pervasive source of distribution shift and potential shortcut learning in renal pathology AI. We ask whether lupus nephritis glomerular lesion classifiers exploit stain as a shortcut, and how to mitigate such bias without stain or site labels. We curate a multi-center, multi-stain dataset of 9,674 glomerular patches (224$\times$224) from 365 WSIs across three centers and fou… ▽ More Stain variability is a pervasive source of distribution shift and potential shortcut learning in renal pathology AI. We ask whether lupus nephritis glomerular lesion classifiers exploit stain as a shortcut, and how to mitigate such bias without stain or site labels. We curate a multi-center, multi-stain dataset of 9,674 glomerular patches (224$\times$224) from 365 WSIs across three centers and four stains (PAS, H&E, Jones, Trichrome), labeled as proliferative vs. non-proliferative. We evaluate Bayesian CNN and ViT backbones with Monte Carlo dropout in three settings: (1) stain-only classification; (2) a dual-head model jointly predicting lesion and stain with supervised stain loss; and (3) a dual-head model with label-free stain regularization via entropy maximization on the stain head. In (1), stain identity is trivially learnable, confirming a strong candidate shortcut. In (2), varying the strength and sign of stain supervision strongly modulates stain performance but leaves lesion metrics essentially unchanged, indicating no measurable stain-driven shortcut learning on this multi-stain, multi-center dataset, while overly adversarial stain penalties inflate predictive uncertainty. In (3), entropy-based regularization holds stain predictions near chance without degrading lesion accuracy or calibration. Overall, a carefully curated multi-stain dataset can be inherently robust to stain shortcuts, and a Bayesian dual-head architecture with label-free entropy regularization offers a simple, deployment-friendly safeguard against potential stain-related drift in glomerular AI. △ Less

Submitted 10 April, 2026; v1 submitted 9 April, 2026; originally announced April 2026.

Comments: Accepted at IEEE ISBI 2026. Hien Nguyen and Chandra Mohan jointly supervised this work

Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework

Authors: Sanup S. Araballi, Simon Khan, Chilukuri K. Mohan

Abstract: Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains. Existing explainability methods either provide only local insights (SHAP, LIME) or employ over-simplified surrogates failing to capture continuous dynamics (decision trees). This work proposes a Hierarchical Takagi-Sugeno-Kang (TSK) Fuzzy… ▽ More Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains. Existing explainability methods either provide only local insights (SHAP, LIME) or employ over-simplified surrogates failing to capture continuous dynamics (decision trees). This work proposes a Hierarchical Takagi-Sugeno-Kang (TSK) Fuzzy Classifier System (FCS) distilling neural policies into human-readable IF-THEN rules through K-Means clustering for state partitioning and Ridge Regression for local action inference. Three quantifiable metrics are introduced: Fuzzy Rule Activation Density (FRAD) measuring explanation focus, Fuzzy Set Coverage (FSC) validating vocabulary completeness, and Action Space Granularity (ASG) assessing control mode diversity. Dynamic Time Warping (DTW) validates temporal behavioral fidelity. Empirical evaluation on \textit{Lunar Lander(Continuous)} shows the Triangular membership function variant achieves 81.48\% $\pm$ 0.43\% fidelity, outperforming Decision Trees by 21 percentage points. The framework exhibits statistically superior interpretability (FRAD = 0.814 vs. 0.723 for Gaussian, $p < 0.001$) with low MSE (0.0053) and DTW distance (1.05). Extracted rules such as ``IF lander drifting left at high altitude THEN apply upward thrust with rightward correction'' enable human verification, establishing a pathway toward trustworthy autonomous systems. △ Less

Submitted 24 February, 2026; originally announced March 2026.

Comments: Accepted to AAAI 2026 Spring Symposium Series

Automated Assessment of Kidney Ureteroscopy Exploration for Training

Authors: Fangjie Li, Nicholas Kavoussi, Charan Mohan, Matthieu Chabanas, Jie Ying Wu

Abstract: Purpose: Kidney ureteroscopic navigation is challenging with a steep learning curve. However, current clinical training has major deficiencies, as it requires one-on-one feedback from experts and occurs in the operating room (OR). Therefore, there is a need for a phantom training system with automated feedback to greatly \revision{expand} training opportunities. Methods: We propose a novel, pure… ▽ More Purpose: Kidney ureteroscopic navigation is challenging with a steep learning curve. However, current clinical training has major deficiencies, as it requires one-on-one feedback from experts and occurs in the operating room (OR). Therefore, there is a need for a phantom training system with automated feedback to greatly \revision{expand} training opportunities. Methods: We propose a novel, purely ureteroscope video-based scope localization framework that automatically identifies calyces missed by the trainee in a phantom kidney exploration. We use a slow, thorough, prior exploration video of the kidney to generate a reference reconstruction. Then, this reference reconstruction can be used to localize any exploration video of the same phantom. Results: In 15 exploration videos, a total of 69 out of 74 calyces were correctly classified. We achieve < 4mm camera pose localization error. Given the reference reconstruction, the system takes 10 minutes to generate the results for a typical exploration (1-2 minute long). Conclusion: We demonstrate a novel camera localization framework that can provide accurate and automatic feedback for kidney phantom explorations. We show its ability as a valid tool that enables out-of-OR training without requiring supervision from an expert. △ Less

Submitted 17 February, 2026; originally announced February 2026.

ConStruct: Structural Distillation of Foundation Models for Prototype-Based Weakly Supervised Histopathology Segmentation

Authors: Khang Le, Ha Thach, Anh M. Vu, Trang T. K. Vo, Han H. Huynh, David Yang, Minh H. N. Le, Thanh-Huy Nguyen, Akash Awasthi, Chandra Mohan, Zhu Han, Hien Van Nguyen

Abstract: Weakly supervised semantic segmentation (WSSS) in histopathology relies heavily on classification backbones, yet these models often localize only the most discriminative regions and struggle to capture the full spatial extent of tissue structures. Vision-language models such as CONCH offer rich semantic alignment and morphology-aware representations, while modern segmentation backbones like SegFor… ▽ More Weakly supervised semantic segmentation (WSSS) in histopathology relies heavily on classification backbones, yet these models often localize only the most discriminative regions and struggle to capture the full spatial extent of tissue structures. Vision-language models such as CONCH offer rich semantic alignment and morphology-aware representations, while modern segmentation backbones like SegFormer preserve fine-grained spatial cues. However, combining these complementary strengths remains challenging, especially under weak supervision and without dense annotations. We propose a prototype learning framework for WSSS in histopathological images that integrates morphology-aware representations from CONCH, multi-scale structural cues from SegFormer, and text-guided semantic alignment to produce prototypes that are simultaneously semantically discriminative and spatially coherent. To effectively leverage these heterogeneous sources, we introduce text-guided prototype initialization that incorporates pathology descriptions to generate more complete and semantically accurate pseudo-masks. A structural distillation mechanism transfers spatial knowledge from SegFormer to preserve fine-grained morphological patterns and local tissue boundaries during prototype learning. Our approach produces high-quality pseudo masks without pixel-level annotations, improves localization completeness, and enhances semantic consistency across tissue types. Experiments on BCSS-WSSS datasets demonstrate that our prototype learning framework outperforms existing WSSS methods while remaining computationally efficient through frozen foundation model backbones and lightweight trainable adapters. △ Less

Submitted 11 December, 2025; originally announced December 2025.

DualProtoSeg: Simple and Efficient Design with Text- and Image-Guided Prototype Learning for Weakly Supervised Histopathology Image Segmentation

Authors: Anh M. Vu, Khang P. Le, Trang T. K. Vo, Ha Thach, Huy Hung Nguyen, David Yang, Han H. Huynh, Quynh Nguyen, Tuan M. Pham, Tuan-Anh Le, Minh H. N. Le, Thanh-Huy Nguyen, Akash Awasthi, Chandra Mohan, Zhu Han, Hien Van Nguyen

Abstract: Weakly supervised semantic segmentation (WSSS) in histopathology seeks to reduce annotation cost by learning from image-level labels, yet it remains limited by inter-class homogeneity, intra-class heterogeneity, and the region-shrinkage effect of CAM-based supervision. We propose a simple and effective prototype-driven framework that leverages vision-language alignment to improve region discovery… ▽ More Weakly supervised semantic segmentation (WSSS) in histopathology seeks to reduce annotation cost by learning from image-level labels, yet it remains limited by inter-class homogeneity, intra-class heterogeneity, and the region-shrinkage effect of CAM-based supervision. We propose a simple and effective prototype-driven framework that leverages vision-language alignment to improve region discovery under weak supervision. Our method integrates CoOp-style learnable prompt tuning to generate text-based prototypes and combines them with learnable image prototypes, forming a dual-modal prototype bank that captures both semantic and appearance cues. To address oversmoothing in ViT representations, we incorporate a multi-scale pyramid module that enhances spatial precision and improves localization quality. Experiments on the BCSS-WSSS benchmark show that our approach surpasses existing state-of-the-art methods, and detailed analyses demonstrate the benefits of text description diversity, context length, and the complementary behavior of text and image prototypes. These results highlight the effectiveness of jointly leveraging textual semantics and visual prototype learning for WSSS in digital pathology. △ Less

Submitted 11 December, 2025; originally announced December 2025.

LPD: Learnable Prototypes with Diversity Regularization for Weakly Supervised Histopathology Segmentation

Authors: Khang Le, Anh Mai Vu, Thi Kim Trang Vo, Ha Thach, Ngoc Bui Lam Quang, Thanh-Huy Nguyen, Minh H. N. Le, Zhu Han, Chandra Mohan, Hien Van Nguyen

Abstract: Weakly supervised semantic segmentation (WSSS) in histopathology reduces pixel-level labeling by learning from image-level labels, but it is hindered by inter-class homogeneity, intra-class heterogeneity, and CAM-induced region shrinkage (global pooling-based class activation maps whose activations highlight only the most distinctive areas and miss nearby class regions). Recent works address these… ▽ More Weakly supervised semantic segmentation (WSSS) in histopathology reduces pixel-level labeling by learning from image-level labels, but it is hindered by inter-class homogeneity, intra-class heterogeneity, and CAM-induced region shrinkage (global pooling-based class activation maps whose activations highlight only the most distinctive areas and miss nearby class regions). Recent works address these challenges by constructing a clustering prototype bank and then refining masks in a separate stage; however, such two-stage pipelines are costly, sensitive to hyperparameters, and decouple prototype discovery from segmentation learning, limiting their effectiveness and efficiency. We propose a cluster-free, one-stage learnable-prototype framework with diversity regularization to enhance morphological intra-class heterogeneity coverage. Our approach achieves state-of-the-art (SOTA) performance on BCSS-WSSS, outperforming prior methods in mIoU and mDice. Qualitative segmentation maps show sharper boundaries and fewer mislabels, and activation heatmaps further reveal that, compared with clustering-based prototypes, our learnable prototypes cover more diverse and complementary regions within each class, providing consistent qualitative evidence for their effectiveness. △ Less

Submitted 5 December, 2025; originally announced December 2025.

Comments: Note: Khang Le and Anh Mai Vu contributed equally

Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification

Authors: Anh Mai Vu, Tuan L. Vo, Ngoc Lam Quang Bui, Nam Nguyen Le Binh, Akash Awasthi, Huy Quoc Vo, Thanh-Huy Nguyen, Zhu Han, Chandra Mohan, Hien Van Nguyen

Abstract: Interpretability is essential in Whole Slide Image (WSI) analysis for computational pathology, where understanding model predictions helps build trust in AI-assisted diagnostics. While Integrated Gradients (IG) and related attribution methods have shown promise, applying them directly to WSIs introduces challenges due to their high-resolution nature. These methods capture model decision patterns b… ▽ More Interpretability is essential in Whole Slide Image (WSI) analysis for computational pathology, where understanding model predictions helps build trust in AI-assisted diagnostics. While Integrated Gradients (IG) and related attribution methods have shown promise, applying them directly to WSIs introduces challenges due to their high-resolution nature. These methods capture model decision patterns but may overlook class-discriminative signals that are crucial for distinguishing between tumor subtypes. In this work, we introduce Contrastive Integrated Gradients (CIG), a novel attribution method that enhances interpretability by computing contrastive gradients in logit space. First, CIG highlights class-discriminative regions by comparing feature importance relative to a reference class, offering sharper differentiation between tumor and non-tumor areas. Second, CIG satisfies the axioms of integrated attribution, ensuring consistency and theoretical soundness. Third, we propose two attribution quality metrics, MIL-AIC and MIL-SIC, which measure how predictive information and model confidence evolve with access to salient regions, particularly under weak supervision. We validate CIG across three datasets spanning distinct cancer types: CAMELYON16 (breast cancer metastasis in lymph nodes), TCGA-RCC (renal cell carcinoma), and TCGA-Lung (lung cancer). Experimental results demonstrate that CIG yields more informative attributions both quantitatively, using MIL-AIC and MIL-SIC, and qualitatively, through visualizations that align closely with ground truth tumor regions, underscoring its potential for interpretable and trustworthy WSI-based diagnostics △ Less

Submitted 13 November, 2025; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: Accepted to WACV 2026

FedDAF: Federated Domain Adaptation Using Model Functional Distance

Authors: Mrinmay Sen, Sidhant Nair, C Krishna Mohan

Abstract: Federated Domain Adaptation (FDA) improves model performance at a target client by collaborating with source clients while preserving data privacy. FDA faces two key challenges: domain shift between source and target data, and limited labeled data at the target, a common constraint when a new site joins a federation before it has accumulated its own labeled data, as in clinical deployments. Most e… ▽ More Federated Domain Adaptation (FDA) improves model performance at a target client by collaborating with source clients while preserving data privacy. FDA faces two key challenges: domain shift between source and target data, and limited labeled data at the target, a common constraint when a new site joins a federation before it has accumulated its own labeled data, as in clinical deployments. Most existing methods address domain shift alone, assuming ample target data; those that also tackle data scarcity still fail to prioritize source information according to the target's specific objective. We propose FedDAF, which addresses both challenges through similarity-based aggregation of the global source and target models, using their model functional distance, computed from the angle between their mean gradient fields on target data and normalized via a Gompertz function. The global source model itself is formed using a distance-based weighted average, giving greater weight to source models closer to the target model. Experiments on real-world datasets show FedDAF outperforms existing federated learning (FL), personalized FL, and FDA methods in test accuracy. △ Less

Submitted 9 July, 2026; v1 submitted 15 September, 2025; originally announced September 2025.

Comments: Under review at Machine Learning (Springer). Code available at https://github.com/sid0nair/FedDAF

ACM Class: I.2.6; I.5.1; C.2.4

Adaptive Resource Management in Cognitive Radar via Deep Deterministic Policy Gradient

Authors: Ziyang Lu, M. Cenk Gursoy, Chilukuri K. Mohan, Pramod K. Varshney

Abstract: In this paper, scanning for target detection, and multi-target tracking in a cognitive radar system are considered, and adaptive radar resource management is investigated. In particular, time management for radar scanning and tracking of multiple maneuvering targets subject to budget constraints is studied with the goal to jointly maximize the tracking and scanning performances of a cognitive rada… ▽ More In this paper, scanning for target detection, and multi-target tracking in a cognitive radar system are considered, and adaptive radar resource management is investigated. In particular, time management for radar scanning and tracking of multiple maneuvering targets subject to budget constraints is studied with the goal to jointly maximize the tracking and scanning performances of a cognitive radar. We tackle the constrained optimization problem of allocating the dwell time to track individual targets by employing a deep deterministic policy gradient (DDPG) based reinforcement learning approach. We propose a constrained deep reinforcement learning (CDRL) algorithm that updates the DDPG neural networks and dual variables simultaneously. Numerical results show that the radar can autonomously allocate time appropriately so as to maximize the reward function without exceeding the time constraint. △ Less

Submitted 5 July, 2025; originally announced July 2025.

Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning

Authors: Ziyang Lu, M. Cenk Gursoy, Chilukuri K. Mohan, Pramod K. Varshney

Abstract: Deep reinforcement learning has been extensively studied in decision-making processes and has demonstrated superior performance over conventional approaches in various fields, including radar resource management (RRM). However, a notable limitation of neural networks is their ``black box" nature and recent research work has increasingly focused on explainable AI (XAI) techniques to describe the ra… ▽ More Deep reinforcement learning has been extensively studied in decision-making processes and has demonstrated superior performance over conventional approaches in various fields, including radar resource management (RRM). However, a notable limitation of neural networks is their ``black box" nature and recent research work has increasingly focused on explainable AI (XAI) techniques to describe the rationale behind neural network decisions. One promising XAI method is local interpretable model-agnostic explanations (LIME). However, the sampling process in LIME ignores the correlations between features. In this paper, we propose a modified LIME approach that integrates deep learning (DL) into the sampling process, which we refer to as DL-LIME. We employ DL-LIME within deep reinforcement learning for radar resource management. Numerical results show that DL-LIME outperforms conventional LIME in terms of both fidelity and task performance, demonstrating superior performance with both metrics. DL-LIME also provides insights on which factors are more important in decision making for radar resource management. △ Less

Submitted 25 June, 2025; originally announced June 2025.

Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management

Authors: Ziyang Lu, Subodh Kalia, M. Cenk Gursoy, Chilukuri K. Mohan, Pramod K. Varshney

Abstract: The time allocation problem in multi-function cognitive radar systems focuses on the trade-off between scanning for newly emerging targets and tracking the previously detected targets. We formulate this as a multi-objective optimization problem and employ deep reinforcement learning to find Pareto-optimal solutions and compare deep deterministic policy gradient (DDPG) and soft actor-critic (SAC) a… ▽ More The time allocation problem in multi-function cognitive radar systems focuses on the trade-off between scanning for newly emerging targets and tracking the previously detected targets. We formulate this as a multi-objective optimization problem and employ deep reinforcement learning to find Pareto-optimal solutions and compare deep deterministic policy gradient (DDPG) and soft actor-critic (SAC) algorithms. Our results demonstrate the effectiveness of both algorithms in adapting to various scenarios, with SAC showing improved stability and sample efficiency compared to DDPG. We further employ the NSGA-II algorithm to estimate an upper bound on the Pareto front of the considered problem. This work contributes to the development of more efficient and adaptive cognitive radar systems capable of balancing multiple competing objectives in dynamic environments. △ Less

Submitted 25 June, 2025; originally announced June 2025.

Learning-Based Resource Management in Integrated Sensing and Communication Systems

Authors: Ziyang Lu, M. Cenk Gursoy, Chilukuri K. Mohan, Pramod K. Varshney

Abstract: In this paper, we tackle the task of adaptive time allocation in integrated sensing and communication systems equipped with radar and communication units. The dual-functional radar-communication system's task involves allocating dwell times for tracking multiple targets and utilizing the remaining time for data transmission towards estimated target locations. We introduce a novel constrained deep… ▽ More In this paper, we tackle the task of adaptive time allocation in integrated sensing and communication systems equipped with radar and communication units. The dual-functional radar-communication system's task involves allocating dwell times for tracking multiple targets and utilizing the remaining time for data transmission towards estimated target locations. We introduce a novel constrained deep reinforcement learning (CDRL) approach, designed to optimize resource allocation between tracking and communication under time budget constraints, thereby enhancing target communication quality. Our numerical results demonstrate the efficiency of our proposed CDRL framework, confirming its ability to maximize communication quality in highly dynamic environments while adhering to time constraints. △ Less

Submitted 25 June, 2025; originally announced June 2025.

pFedSOP : Accelerating Training Of Personalized Federated Learning Using Second-Order Optimization

Authors: Mrinmay Sen, Chalavadi Krishna Mohan

Abstract: Personalized Federated Learning (PFL) enables clients to collaboratively train personalized models tailored to their individual objectives, addressing the challenge of model generalization in traditional Federated Learning (FL) due to high data heterogeneity. However, existing PFL methods often require increased communication rounds to achieve the desired performance, primarily due to slow trainin… ▽ More Personalized Federated Learning (PFL) enables clients to collaboratively train personalized models tailored to their individual objectives, addressing the challenge of model generalization in traditional Federated Learning (FL) due to high data heterogeneity. However, existing PFL methods often require increased communication rounds to achieve the desired performance, primarily due to slow training caused by the use of first-order optimization, which has linear convergence. Additionally, many of these methods increase local computation because of the additional data fed into the model during the search for personalized local models. One promising solution to this slow training is second-order optimization, known for its quadratic convergence. However, employing it in PFL is challenging due to the Hessian matrix and its inverse. In this paper, we propose pFedSOP, which efficiently utilizes second-order optimization in PFL to accelerate the training of personalized models and enhance performance with fewer communication rounds. Our approach first computes a personalized local gradient update using the Gompertz function-based normalized angle between local and global gradient updates, incorporating client-specific global information. We then use a regularized Fisher Information Matrix (FIM), computed from this personalized gradient update, as an approximation of the Hessian to update the personalized models. This FIM-based second-order optimization speeds up training with fewer communication rounds by tackling the challenges with exact Hessian and avoids additional data being fed into the model during the search for personalized local models. Extensive experiments on heterogeneously partitioned image classification datasets with partial client participation demonstrate that pFedSOP outperforms state-of-the-art FL and PFL algorithms. △ Less

Submitted 8 June, 2025; originally announced June 2025.

MSC Class: 68Q25; 68T05; 90C06; 90C25; 90C30 ACM Class: I.2.6; G.1.6; C.2.4

Overcoming Challenges of Partial Client Participation in Federated Learning : A Comprehensive Review

Authors: Mrinmay Sen, Shruti Aparna, Rohit Agarwal, Chalavadi Krishna Mohan

Abstract: Federated Learning (FL) is a learning mechanism that falls under the distributed training umbrella, which collaboratively trains a shared global model without disclosing the raw data from different clients. This paper presents an extensive survey on the impact of partial client participation in federated learning. While much of the existing research focuses on addressing issues such as generalizat… ▽ More Federated Learning (FL) is a learning mechanism that falls under the distributed training umbrella, which collaboratively trains a shared global model without disclosing the raw data from different clients. This paper presents an extensive survey on the impact of partial client participation in federated learning. While much of the existing research focuses on addressing issues such as generalization, robustness, and fairness caused by data heterogeneity under the assumption of full client participation, limited attention has been given to the practical and theoretical challenges arising from partial client participation, which is common in real-world scenarios. This survey provides an in-depth review of existing FL methods designed to cope with partial client participation. We offer a comprehensive analysis supported by theoretical insights and empirical findings, along with a structured categorization of these methods, highlighting their respective advantages and disadvantages. △ Less

Submitted 6 June, 2025; v1 submitted 3 June, 2025; originally announced June 2025.

Comments: 15 pages, 6 tables, comprehensive survey of federated learning with partial client participation

Accelerated Training of Federated Learning via Second-Order Methods

Authors: Mrinmay Sen, Sidhant R Nair, C Krishna Mohan

Abstract: This paper explores second-order optimization methods in Federated Learning (FL), addressing the critical challenges of slow convergence and the excessive communication rounds required to achieve optimal performance from the global model. While existing surveys in FL primarily focus on challenges related to statistical and device label heterogeneity, as well as privacy and security concerns in fir… ▽ More This paper explores second-order optimization methods in Federated Learning (FL), addressing the critical challenges of slow convergence and the excessive communication rounds required to achieve optimal performance from the global model. While existing surveys in FL primarily focus on challenges related to statistical and device label heterogeneity, as well as privacy and security concerns in first-order FL methods, less attention has been given to the issue of slow model training. This slow training often leads to the need for excessive communication rounds or increased communication costs, particularly when data across clients are highly heterogeneous. In this paper, we examine various FL methods that leverage second-order optimization to accelerate the training process. We provide a comprehensive categorization of state-of-the-art second-order FL methods and compare their performance based on convergence speed, computational cost, memory usage, transmission overhead, and generalization of the global model. Our findings show the potential of incorporating Hessian curvature through second-order optimization into FL and highlight key challenges, such as the efficient utilization of Hessian and its inverse in FL. This work lays the groundwork for future research aimed at developing scalable and efficient federated optimization methods for improving the training of the global model in FL. △ Less

Submitted 29 May, 2025; originally announced May 2025.

Comments: 17 pages, 1 figure, 4 tables, submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)

MSC Class: 68Q25; 68T05; 90C06; 90C25; 90C30 ACM Class: I.2.6; G.1.6; C.2.4; C.4

The Cambridge Report on Database Research

Authors: Anastasia Ailamaki, Samuel Madden, Daniel Abadi, Gustavo Alonso, Sihem Amer-Yahia, Magdalena Balazinska, Philip A. Bernstein, Peter Boncz, Michael Cafarella, Surajit Chaudhuri, Susan Davidson, David DeWitt, Yanlei Diao, Xin Luna Dong, Michael Franklin, Juliana Freire, Johannes Gehrke, Alon Halevy, Joseph M. Hellerstein, Mark D. Hill, Stratos Idreos, Yannis Ioannidis, Christoph Koch, Donald Kossmann, Tim Kraska , et al. (21 additional authors not shown)

Abstract: On October 19 and 20, 2023, the authors of this report convened in Cambridge, MA, to discuss the state of the database research field, its recent accomplishments and ongoing challenges, and future directions for research and community engagement. This gathering continues a long standing tradition in the database community, dating back to the late 1980s, in which researchers meet roughly every five… ▽ More On October 19 and 20, 2023, the authors of this report convened in Cambridge, MA, to discuss the state of the database research field, its recent accomplishments and ongoing challenges, and future directions for research and community engagement. This gathering continues a long standing tradition in the database community, dating back to the late 1980s, in which researchers meet roughly every five years to produce a forward looking report. This report summarizes the key takeaways from our discussions. We begin with a retrospective on the academic, open source, and commercial successes of the community over the past five years. We then turn to future opportunities, with a focus on core data systems, particularly in the context of cloud computing and emerging hardware, as well as on the growing impact of data science, data governance, and generative AI. This document is not intended as an exhaustive survey of all technical challenges or industry innovations in the field. Rather, it reflects the perspectives of senior community members on the most pressing challenges and promising opportunities ahead. △ Less

Submitted 15 April, 2025; originally announced April 2025.

Detection of LLM-Generated Java Code Using Discretized Nested Bigrams

Authors: Timothy Paek, Chilukuri Mohan

Abstract: Large Language Models (LLMs) are currently used extensively to generate code by professionals and students, motivating the development of tools to detect LLM-generated code for applications such as academic integrity and cybersecurity. We address this authorship attribution problem as a binary classification task along with feature identification and extraction. We propose new Discretized Nested B… ▽ More Large Language Models (LLMs) are currently used extensively to generate code by professionals and students, motivating the development of tools to detect LLM-generated code for applications such as academic integrity and cybersecurity. We address this authorship attribution problem as a binary classification task along with feature identification and extraction. We propose new Discretized Nested Bigram Frequency features on source code groups of various sizes. Compared to prior work, improvements are obtained by representing sparse information in dense membership bins. Experimental evaluation demonstrated that our approach significantly outperformed a commonly used GPT code-detection API and baseline features, with accuracy exceeding 96% compared to 72% and 79% respectively in detecting GPT-rewritten Java code fragments for 976 files with GPT 3.5 and GPT4 using 12 features. We also outperformed three prior works on code author identification in a 40-author dataset. Our approach scales well to larger data sets, and we achieved 99% accuracy and 0.999 AUC for 76,089 files and over 1,000 authors with GPT 4o using 227 features. △ Less

Submitted 7 February, 2025; originally announced February 2025.

Comments: This preprint precedes the final peer-reviewed version, which will be published in Springer's CSCI 2024 proceedings

MSC Class: 68T50; 62H30 ACM Class: I.2.7; K.6.5; D.2.8

Minimizing Energy Costs in Deep Learning Model Training: The Gaussian Sampling Approach

Authors: Challapalli Phanindra Revanth, Sumohana S. Channappayya, C Krishna Mohan

Abstract: Computing the loss gradient via backpropagation consumes considerable energy during deep learning (DL) model training. In this paper, we propose a novel approach to efficiently compute DL models' gradients to mitigate the substantial energy overhead associated with backpropagation. Exploiting the over-parameterized nature of DL models and the smoothness of their loss landscapes, we propose a metho… ▽ More Computing the loss gradient via backpropagation consumes considerable energy during deep learning (DL) model training. In this paper, we propose a novel approach to efficiently compute DL models' gradients to mitigate the substantial energy overhead associated with backpropagation. Exploiting the over-parameterized nature of DL models and the smoothness of their loss landscapes, we propose a method called {\em GradSamp} for sampling gradient updates from a Gaussian distribution. Specifically, we update model parameters at a given epoch (chosen periodically or randomly) by perturbing the parameters (element-wise) from the previous epoch with Gaussian ``noise''. The parameters of the Gaussian distribution are estimated using the error between the model parameter values from the two previous epochs. {\em GradSamp} not only streamlines gradient computation but also enables skipping entire epochs, thereby enhancing overall efficiency. We rigorously validate our hypothesis across a diverse set of standard and non-standard CNN and transformer-based models, spanning various computer vision tasks such as image classification, object detection, and image segmentation. Additionally, we explore its efficacy in out-of-distribution scenarios such as Domain Adaptation (DA), Domain Generalization (DG), and decentralized settings like Federated Learning (FL). Our experimental results affirm the effectiveness of {\em GradSamp} in achieving notable energy savings without compromising performance, underscoring its versatility and potential impact in practical DL applications. △ Less

Submitted 11 June, 2024; originally announced June 2024.

Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning

Authors: K Naveen Kumar, C Krishna Mohan, Aravind Machiry

Abstract: Federated Learning (FL) is a collaborative learning paradigm enabling participants to collectively train a shared machine learning model while preserving the privacy of their sensitive data. Nevertheless, the inherent decentralized and data-opaque characteristics of FL render its susceptibility to data poisoning attacks. These attacks introduce malformed or malicious inputs during local model trai… ▽ More Federated Learning (FL) is a collaborative learning paradigm enabling participants to collectively train a shared machine learning model while preserving the privacy of their sensitive data. Nevertheless, the inherent decentralized and data-opaque characteristics of FL render its susceptibility to data poisoning attacks. These attacks introduce malformed or malicious inputs during local model training, subsequently influencing the global model and resulting in erroneous predictions. Current FL defense strategies against data poisoning attacks either involve a trade-off between accuracy and robustness or necessitate the presence of a uniformly distributed root dataset at the server. To overcome these limitations, we present FedZZ, which harnesses a zone-based deviating update (ZBDU) mechanism to effectively counter data poisoning attacks in FL. Further, we introduce a precision-guided methodology that actively characterizes these client clusters (zones), which in turn aids in recognizing and discarding malicious updates at the server. Our evaluation of FedZZ across two widely recognized datasets: CIFAR10 and EMNIST, demonstrate its efficacy in mitigating data poisoning attacks, surpassing the performance of prevailing state-of-the-art methodologies in both single and multi-client attack scenarios and varying attack volumes. Notably, FedZZ also functions as a robust client selection strategy, even in highly non-IID and attack-free scenarios. Moreover, in the face of escalating poisoning rates, the model accuracy attained by FedZZ displays superior resilience compared to existing techniques. For instance, when confronted with a 50% presence of malicious clients, FedZZ sustains an accuracy of 67.43%, while the accuracy of the second-best solution, FL-Defender, diminishes to 43.36%. △ Less

Submitted 5 April, 2024; originally announced April 2024.

Comments: 14 pages, 11 figures, 5 tables, Accepted in ACM CODASPY 2024

Segmentation of diagnostic tissue compartments on whole slide images with renal thrombotic microangiopathies (TMAs)

Authors: Huy Q. Vo, Pietro A. Cicalese, Surya Seshan, Syed A. Rizvi, Aneesh Vathul, Gloria Bueno, Anibal Pedraza Dorado, Niels Grabe, Katharina Stolle, Francesco Pesce, Joris J. T. H. Roelofs, Jesper Kers, Vitoantonio Bevilacqua, Nicola Altini, Bernd Schröppel, Dario Roccatello, Antonella Barreca, Savino Sciascia, Chandra Mohan, Hien V. Nguyen, Jan U. Becker

Abstract: The thrombotic microangiopathies (TMAs) manifest in renal biopsy histology with a broad spectrum of acute and chronic findings. Precise diagnostic criteria for a renal biopsy diagnosis of TMA are missing. As a first step towards a machine learning- and computer vision-based analysis of wholes slide images from renal biopsies, we trained a segmentation model for the decisive diagnostic kidney tissu… ▽ More The thrombotic microangiopathies (TMAs) manifest in renal biopsy histology with a broad spectrum of acute and chronic findings. Precise diagnostic criteria for a renal biopsy diagnosis of TMA are missing. As a first step towards a machine learning- and computer vision-based analysis of wholes slide images from renal biopsies, we trained a segmentation model for the decisive diagnostic kidney tissue compartments artery, arteriole, glomerulus on a set of whole slide images from renal biopsies with TMAs and Mimickers (distinct diseases with a similar nephropathological appearance as TMA like severe benign nephrosclerosis, various vasculitides, Bevacizumab-plug glomerulopathy, arteriolar light chain deposition disease). Our segmentation model combines a U-Net-based tissue detection with a Shifted windows-transformer architecture to reach excellent segmentation results for even the most severely altered glomeruli, arterioles and arteries, even on unseen staining domains from a different nephropathology lab. With accurate automatic segmentation of the decisive renal biopsy compartments in human renal vasculopathies, we have laid the foundation for large-scale compartment-specific machine learning and computer vision analysis of renal biopsy repositories with TMAs. △ Less

Submitted 28 November, 2023; v1 submitted 25 November, 2023; originally announced November 2023.

Comments: 12 pages, 3 figures

MADG: Margin-based Adversarial Learning for Domain Generalization

Authors: Aveen Dayal, Vimal K. B., Linga Reddy Cenkeramaddi, C. Krishna Mohan, Abhinav Kumar, Vineeth N Balasubramanian

Abstract: Domain Generalization (DG) techniques have emerged as a popular approach to address the challenges of domain shift in Deep Learning (DL), with the goal of generalizing well to the target domain unseen during the training. In recent years, numerous methods have been proposed to address the DG setting, among which one popular approach is the adversarial learning-based methodology. The main idea behi… ▽ More Domain Generalization (DG) techniques have emerged as a popular approach to address the challenges of domain shift in Deep Learning (DL), with the goal of generalizing well to the target domain unseen during the training. In recent years, numerous methods have been proposed to address the DG setting, among which one popular approach is the adversarial learning-based methodology. The main idea behind adversarial DG methods is to learn domain-invariant features by minimizing a discrepancy metric. However, most adversarial DG methods use 0-1 loss based $\mathcal{H}Δ\mathcal{H}$ divergence metric. In contrast, the margin loss-based discrepancy metric has the following advantages: more informative, tighter, practical, and efficiently optimizable. To mitigate this gap, this work proposes a novel adversarial learning DG algorithm, MADG, motivated by a margin loss-based discrepancy metric. The proposed MADG model learns domain-invariant features across all source domains and uses adversarial training to generalize well to the unseen target domain. We also provide a theoretical analysis of the proposed MADG model based on the unseen target error bound. Specifically, we construct the link between the source and unseen domains in the real-valued hypothesis space and derive the generalization bound using margin loss and Rademacher complexity. We extensively experiment with the MADG model on popular real-world DG datasets, VLCS, PACS, OfficeHome, DomainNet, and TerraIncognita. We evaluate the proposed algorithm on DomainBed's benchmark and observe consistent performance across all the datasets. △ Less

Submitted 14 November, 2023; originally announced November 2023.

Dictionary Attack on IMU-based Gait Authentication

Authors: Rajesh Kumar, Can Isik, Chilukuri K. Mohan

Abstract: We present a novel adversarial model for authentication systems that use gait patterns recorded by the inertial measurement unit (IMU) built into smartphones. The attack idea is inspired by and named after the concept of a dictionary attack on knowledge (PIN or password) based authentication systems. In particular, this work investigates whether it is possible to build a dictionary of IMUGait patt… ▽ More We present a novel adversarial model for authentication systems that use gait patterns recorded by the inertial measurement unit (IMU) built into smartphones. The attack idea is inspired by and named after the concept of a dictionary attack on knowledge (PIN or password) based authentication systems. In particular, this work investigates whether it is possible to build a dictionary of IMUGait patterns and use it to launch an attack or find an imitator who can actively reproduce IMUGait patterns that match the target's IMUGait pattern. Nine physically and demographically diverse individuals walked at various levels of four predefined controllable and adaptable gait factors (speed, step length, step width, and thigh-lift), producing 178 unique IMUGait patterns. Each pattern attacked a wide variety of user authentication models. The deeper analysis of error rates (before and after the attack) challenges the belief that authentication systems based on IMUGait patterns are the most difficult to spoof; further research is needed on adversarial models and associated countermeasures. △ Less

Submitted 31 December, 2023; v1 submitted 21 September, 2023; originally announced September 2023.

Comments: 12 pages, 9 figures, accepted at AISec23 colocated with ACM CCS, November 30, 2023, Copenhagen, Denmark

ACM Class: K.6.5

Evidence of In-Memory Computing in a Ferrofluid

Authors: Marco Crepaldi, Charanraj Mohan, Erik Garofalo, Andrew Adamatzky, Konrad Szaciłowski, Alessandro Chiolerio

Abstract: Magnetic fluids are excellent candidates for important research fields including energy harvesting, biomedical applications, soft robotics and exploration. However, notwithstanding relevant advancements such as shape reconfigurability, that have been demonstrated, there is no evidence for their computation capability, including the emulation of synaptic functions. Here, we experimentally demonstra… ▽ More Magnetic fluids are excellent candidates for important research fields including energy harvesting, biomedical applications, soft robotics and exploration. However, notwithstanding relevant advancements such as shape reconfigurability, that have been demonstrated, there is no evidence for their computation capability, including the emulation of synaptic functions. Here, we experimentally demonstrate that a Fe3O4 water-based Ferrofluid (FF) can perform electrical analog computing and be programmed using quasi DC signals and read at Radio Frequency (RF) mode. We have observed features in all respects attributable to a memristive behavior, featuring both short and long-term information storage capacity and plasticity. The colloid was capable of classifying digits of a 8x8 pixel dataset using a custom in-memory signal processing scheme, and through Physical Reservoir Computing (PRC) by training a readout layer. △ Less

Submitted 15 November, 2022; originally announced November 2022.

ACLNet: An Attention and Clustering-based Cloud Segmentation Network

Authors: Dhruv Makwana, Subhrajit Nag, Onkar Susladkar, Gayatri Deshmukh, Sai Chandra Teja R, Sparsh Mittal, C Krishna Mohan

Abstract: We propose a novel deep learning model named ACLNet, for cloud segmentation from ground images. ACLNet uses both deep neural network and machine learning (ML) algorithm to extract complementary features. Specifically, it uses EfficientNet-B0 as the backbone, "`a trous spatial pyramid pooling" (ASPP) to learn at multiple receptive fields, and "global attention module" (GAM) to extract finegrained d… ▽ More We propose a novel deep learning model named ACLNet, for cloud segmentation from ground images. ACLNet uses both deep neural network and machine learning (ML) algorithm to extract complementary features. Specifically, it uses EfficientNet-B0 as the backbone, "`a trous spatial pyramid pooling" (ASPP) to learn at multiple receptive fields, and "global attention module" (GAM) to extract finegrained details from the image. ACLNet also uses k-means clustering to extract cloud boundaries more precisely. ACLNet is effective for both daytime and nighttime images. It provides lower error rate, higher recall and higher F1-score than state-of-art cloud segmentation models. The source-code of ACLNet is available here: https://github.com/ckmvigil/ACLNet. △ Less

Submitted 13 July, 2022; originally announced July 2022.

Comments: 11 pages, 3 figures, 5 tables, Published in remote sensing letters

Journal ref: volume 13, pages 865-875, year 2022

WaferSegClassNet -- A Light-weight Network for Classification and Segmentation of Semiconductor Wafer Defects

Authors: Subhrajit Nag, Dhruv Makwana, Sai Chandra Teja R, Sparsh Mittal, C Krishna Mohan

Abstract: As the integration density and design intricacy of semiconductor wafers increase, the magnitude and complexity of defects in them are also on the rise. Since the manual inspection of wafer defects is costly, an automated artificial intelligence (AI) based computer-vision approach is highly desired. The previous works on defect analysis have several limitations, such as low accuracy and the need fo… ▽ More As the integration density and design intricacy of semiconductor wafers increase, the magnitude and complexity of defects in them are also on the rise. Since the manual inspection of wafer defects is costly, an automated artificial intelligence (AI) based computer-vision approach is highly desired. The previous works on defect analysis have several limitations, such as low accuracy and the need for separate models for classification and segmentation. For analyzing mixed-type defects, some previous works require separately training one model for each defect type, which is non-scalable. In this paper, we present WaferSegClassNet (WSCN), a novel network based on encoder-decoder architecture. WSCN performs simultaneous classification and segmentation of both single and mixed-type wafer defects. WSCN uses a "shared encoder" for classification, and segmentation, which allows training WSCN end-to-end. We use N-pair contrastive loss to first pretrain the encoder and then use BCE-Dice loss for segmentation, and categorical cross-entropy loss for classification. Use of N-pair contrastive loss helps in better embedding representation in the latent dimension of wafer maps. WSCN has a model size of only 0.51MB and performs only 0.2M FLOPS. Thus, it is much lighter than other state-of-the-art models. Also, it requires only 150 epochs for convergence, compared to 4,000 epochs needed by a previous work. We evaluate our model on the MixedWM38 dataset, which has 38,015 images. WSCN achieves an average classification accuracy of 98.2% and a dice coefficient of 0.9999. We are the first to show segmentation results on the MixedWM38 dataset. The source code can be obtained from https://github.com/ckmvigil/WaferSegClassNet. △ Less

Submitted 3 July, 2022; originally announced July 2022.

Comments: 11 pages, 2 figures, 7 tables, Published in Computers in Industry

Journal ref: Volume 142, 2022, 103720, ISSN 0166-3615,

Monte Carlo DropBlock for Modelling Uncertainty in Object Detection

Authors: Kumari Deepshikha, Sai Harsha Yelleni, P. K. Srijith, C Krishna Mohan

Abstract: With the advancements made in deep learning, computer vision problems like object detection and segmentation have seen a great improvement in performance. However, in many real-world applications such as autonomous driving vehicles, the risk associated with incorrect predictions of objects is very high. Standard deep learning models for object detection such as YOLO models are often overconfident… ▽ More With the advancements made in deep learning, computer vision problems like object detection and segmentation have seen a great improvement in performance. However, in many real-world applications such as autonomous driving vehicles, the risk associated with incorrect predictions of objects is very high. Standard deep learning models for object detection such as YOLO models are often overconfident in their predictions and do not take into account the uncertainty in predictions on out-of-distribution data. In this work, we propose an efficient and effective approach to model uncertainty in object detection and segmentation tasks using Monte-Carlo DropBlock (MC-DropBlock) based inference. The proposed approach applies drop-block during training time and test time on the convolutional layer of the deep learning models such as YOLO. We show that this leads to a Bayesian convolutional neural network capable of capturing the epistemic uncertainty in the model. Additionally, we capture the aleatoric uncertainty using a Gaussian likelihood. We demonstrate the effectiveness of the proposed approach on modeling uncertainty in object detection and segmentation tasks using out-of-distribution experiments. Experimental results show that MC-DropBlock improves the generalization, calibration, and uncertainty modeling capabilities of YOLO models in object detection and segmentation. △ Less

Submitted 8 August, 2021; originally announced August 2021.

Experimental Body-input Three-stage DC offset Calibration Scheme for Memristive Crossbar

Authors: Charanraj Mohan, L. A. Camuñas-Mesa, Elisa Vianello, Carlo Reita, José M. de la Rosa, Teresa Serrano-Gotarredona, Bernabé Linares-Barranco

Abstract: Reading several ReRAMs simultaneously in a neuromorphic circuit increases power consumption and limits scalability. Applying small inference read pulses is a vain attempt when offset voltages of the read-out circuit are decisively more. This paper presents an experimental validation of a three-stage calibration scheme to calibrate the DC offset voltage across the rows of the memristive crossbar. T… ▽ More Reading several ReRAMs simultaneously in a neuromorphic circuit increases power consumption and limits scalability. Applying small inference read pulses is a vain attempt when offset voltages of the read-out circuit are decisively more. This paper presents an experimental validation of a three-stage calibration scheme to calibrate the DC offset voltage across the rows of the memristive crossbar. The proposed method is based on biasing the body terminal of one of the differential pair MOSFETs of the buffer through a series of cascaded resistor banks arranged in three stages: coarse, fine and finer stages. The circuit is designed in a 130 nm CMOS technology, where the OxRAM-based binary memristors are built on top of it. A dedicated PCB and other auxiliary boards have been designed for testing the chip. Experimental results validate the presented approach, which is only limited by mismatch and electrical noise. △ Less

Submitted 3 March, 2021; originally announced March 2021.

Comments: 5 pages, 9 figures, conference paper published in ISCAS20

ACM Class: B.7

Implementation of binary stochastic STDP learning using chalcogenide-based memristive devices

Authors: C. Mohan, L. A. Camuñas-Mesa, J. M. de la Rosa, T. Serrano-Gotarredona, B. Linares-Barranco

Abstract: The emergence of nano-scale memristive devices encouraged many different research areas to exploit their use in multiple applications. One of the proposed applications was to implement synaptic connections in bio-inspired neuromorphic systems. Large-scale neuromorphic hardware platforms are being developed with increasing number of neurons and synapses, having a critical bottleneck in the online l… ▽ More The emergence of nano-scale memristive devices encouraged many different research areas to exploit their use in multiple applications. One of the proposed applications was to implement synaptic connections in bio-inspired neuromorphic systems. Large-scale neuromorphic hardware platforms are being developed with increasing number of neurons and synapses, having a critical bottleneck in the online learning capabilities. Spike-timing-dependent plasticity (STDP) is a widely used learning mechanism inspired by biology which updates the synaptic weight as a function of the temporal correlation between pre- and post-synaptic spikes. In this work, we demonstrate experimentally that binary stochastic STDP learning can be obtained from a memristor when the appropriate pulses are applied at both sides of the device. △ Less

Submitted 1 March, 2021; originally announced March 2021.

Journal ref: 2021 IEEE International Symposium on Circuits and Systems (ISCAS), 2021, pp. 1-5

Black-box Adversarial Attacks in Autonomous Vehicle Technology

Authors: K Naveen Kumar, C Vishnu, Reshmi Mitra, C Krishna Mohan

Abstract: Despite the high quality performance of the deep neural network in real-world applications, they are susceptible to minor perturbations of adversarial attacks. This is mostly undetectable to human vision. The impact of such attacks has become extremely detrimental in autonomous vehicles with real-time "safety" concerns. The black-box adversarial attacks cause drastic misclassification in critical… ▽ More Despite the high quality performance of the deep neural network in real-world applications, they are susceptible to minor perturbations of adversarial attacks. This is mostly undetectable to human vision. The impact of such attacks has become extremely detrimental in autonomous vehicles with real-time "safety" concerns. The black-box adversarial attacks cause drastic misclassification in critical scene elements such as road signs and traffic lights leading the autonomous vehicle to crash into other vehicles or pedestrians. In this paper, we propose a novel query-based attack method called Modified Simple black-box attack (M-SimBA) to overcome the use of a white-box source in transfer based attack method. Also, the issue of late convergence in a Simple black-box attack (SimBA) is addressed by minimizing the loss of the most confused class which is the incorrect class predicted by the model with the highest probability, instead of trying to maximize the loss of the correct class. We evaluate the performance of the proposed approach to the German Traffic Sign Recognition Benchmark (GTSRB) dataset. We show that the proposed model outperforms the existing models like Transfer-based projected gradient descent (T-PGD), SimBA in terms of convergence time, flattening the distribution of confused class probability, and producing adversarial samples with least confidence on the true class. △ Less

Submitted 15 January, 2021; originally announced January 2021.

Comments: 7 pages, 10 figures, published in 49th Annual IEEE AIPR 2020: Trusted Computing, Privacy, and Securing Multimedia Washington, D.C. October 13-15, 2020

Defining Traffic States using Spatio-temporal Traffic Graphs

Authors: Debaditya Roy, K. Naveen Kumar, C. Krishna Mohan

Abstract: Intersections are one of the main sources of congestion and hence, it is important to understand traffic behavior at intersections. Particularly, in developing countries with high vehicle density, mixed traffic type, and lane-less driving behavior, it is difficult to distinguish between congested and normal traffic behavior. In this work, we propose a way to understand the traffic state of smaller… ▽ More Intersections are one of the main sources of congestion and hence, it is important to understand traffic behavior at intersections. Particularly, in developing countries with high vehicle density, mixed traffic type, and lane-less driving behavior, it is difficult to distinguish between congested and normal traffic behavior. In this work, we propose a way to understand the traffic state of smaller spatial regions at intersections using traffic graphs. The way these traffic graphs evolve over time reveals different traffic states - a) a congestion is forming (clumping), the congestion is dispersing (unclumping), or c) the traffic is flowing normally (neutral). We train a spatio-temporal deep network to identify these changes. Also, we introduce a large dataset called EyeonTraffic (EoT) containing 3 hours of aerial videos collected at 3 busy intersections in Ahmedabad, India. Our experiments on the EoT dataset show that the traffic graphs can help in correctly identifying congestion-prone behavior in different spatial regions of an intersection. △ Less

Submitted 27 July, 2020; originally announced August 2020.

Comments: Accepted in 23rd IEEE International Conference on Intelligent Transportation Systems September 20 to 23, 2020. 6 pages, 6 figures

StyPath: Style-Transfer Data Augmentation For Robust Histology Image Classification

Authors: Pietro Antonio Cicalese, Aryan Mobiny, Pengyu Yuan, Jan Becker, Chandra Mohan, Hien Van Nguyen

Abstract: The classification of Antibody Mediated Rejection (AMR) in kidney transplant remains challenging even for experienced nephropathologists; this is partly because histological tissue stain analysis is often characterized by low inter-observer agreement and poor reproducibility. One of the implicated causes for inter-observer disagreement is the variability of tissue stain quality between (and within… ▽ More The classification of Antibody Mediated Rejection (AMR) in kidney transplant remains challenging even for experienced nephropathologists; this is partly because histological tissue stain analysis is often characterized by low inter-observer agreement and poor reproducibility. One of the implicated causes for inter-observer disagreement is the variability of tissue stain quality between (and within) pathology labs, coupled with the gradual fading of archival sections. Variations in stain colors and intensities can make tissue evaluation difficult for pathologists, ultimately affecting their ability to describe relevant morphological features. Being able to accurately predict the AMR status based on kidney histology images is crucial for improving patient treatment and care. We propose a novel pipeline to build robust deep neural networks for AMR classification based on StyPath, a histological data augmentation technique that leverages a light weight style-transfer algorithm as a means to reduce sample-specific bias. Each image was generated in 1.84 +- 0.03 seconds using a single GTX TITAN V gpu and pytorch, making it faster than other popular histological data augmentation techniques. We evaluated our model using a Monte Carlo (MC) estimate of Bayesian performance and generate an epistemic measure of uncertainty to compare both the baseline and StyPath augmented models. We also generated Grad-CAM representations of the results which were assessed by an experienced nephropathologist; we used this qualitative analysis to elucidate on the assumptions being made by each model. Our results imply that our style-transfer augmentation technique improves histological classification performance (reducing error from 14.8% to 11.5%) and generalization ability. △ Less

Submitted 9 July, 2020; originally announced July 2020.

ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks

Authors: Rajat Saini, Nandan Kumar Jha, Bedanta Das, Sparsh Mittal, C. Krishna Mohan

Abstract: The capability of the self-attention mechanism to model the long-range dependencies has catapulted its deployment in vision models. Unlike convolution operators, self-attention offers infinite receptive field and enables compute-efficient modeling of global dependencies. However, the existing state-of-the-art attention mechanisms incur high compute and/or parameter overheads, and hence unfit for c… ▽ More The capability of the self-attention mechanism to model the long-range dependencies has catapulted its deployment in vision models. Unlike convolution operators, self-attention offers infinite receptive field and enables compute-efficient modeling of global dependencies. However, the existing state-of-the-art attention mechanisms incur high compute and/or parameter overheads, and hence unfit for compact convolutional neural networks (CNNs). In this work, we propose a simple yet effective "Ultra-Lightweight Subspace Attention Mechanism" (ULSAM), which infers different attention maps for each feature map subspace. We argue that leaning separate attention maps for each feature subspace enables multi-scale and multi-frequency feature representation, which is more desirable for fine-grained image classification. Our method of subspace attention is orthogonal and complementary to the existing state-of-the-arts attention mechanisms used in vision models. ULSAM is end-to-end trainable and can be deployed as a plug-and-play module in the pre-existing compact CNNs. Notably, our work is the first attempt that uses a subspace attention mechanism to increase the efficiency of compact CNNs. To show the efficacy of ULSAM, we perform experiments with MobileNet-V1 and MobileNet-V2 as backbone architectures on ImageNet-1K and three fine-grained image classification datasets. We achieve $\approx$13% and $\approx$25% reduction in both the FLOPs and parameter counts of MobileNet-V2 with a 0.27% and more than 1% improvement in top-1 accuracy on the ImageNet-1K and fine-grained image classification datasets (respectively). Code and trained models are available at https://github.com/Nandan91/ULSAM. △ Less

Submitted 26 June, 2020; originally announced June 2020.

Comments: Accepted as a conference paper in 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)

ACM Class: I.5.1; I.5.2; I.5.4

Journal ref: WACV (2020) 1627-1636

Credibility-based Fake News Detection

Authors: Niraj Sitaula, Chilukuri K. Mohan, Jennifer Grygiel, Xinyi Zhou, Reza Zafarani

Abstract: Fake news can significantly misinform people who often rely on online sources and social media for their information. Current research on fake news detection has mostly focused on analyzing fake news content and how it propagates on a network of users. In this paper, we emphasize the detection of fake news by assessing its credibility. By analyzing public fake news data, we show that information o… ▽ More Fake news can significantly misinform people who often rely on online sources and social media for their information. Current research on fake news detection has mostly focused on analyzing fake news content and how it propagates on a network of users. In this paper, we emphasize the detection of fake news by assessing its credibility. By analyzing public fake news data, we show that information on news sources (and authors) can be a strong indicator of credibility. Our findings suggest that an author's history of association with fake news, and the number of authors of a news article, can play a significant role in detecting fake news. Our approach can help improve traditional fake news detection methods, wherein content features are often used to detect fake news. △ Less

Submitted 2 November, 2019; originally announced November 2019.

WiSer: A Highly Available HTAP DBMS for IoT Applications

Authors: Ronald Barber, Christian Garcia-Arellano, Ronen Grosman, Guy Lohman, C. Mohan, Rene Muller, Hamid Pirahesh, Vijayshankar Raman, Richard Sidle, Adam Storm, Yuanyuan Tian, Pinar Tozun, Yingjun Wu

Abstract: In a classic transactional distributed database management system (DBMS), write transactions invariably synchronize with a coordinator before final commitment. While enforcing serializability, this model has long been criticized for not satisfying the applications' availability requirements. When entering the era of Internet of Things (IoT), this problem has become more severe, as an increasing nu… ▽ More In a classic transactional distributed database management system (DBMS), write transactions invariably synchronize with a coordinator before final commitment. While enforcing serializability, this model has long been criticized for not satisfying the applications' availability requirements. When entering the era of Internet of Things (IoT), this problem has become more severe, as an increasing number of applications call for the capability of hybrid transactional and analytical processing (HTAP), where aggregation constraints need to be enforced as part of transactions. Current systems work around this by creating escrows, allowing occasional overshoots of constraints, which are handled via compensating application logic. The WiSer DBMS targets consistency with availability, by splitting the database commit into two steps. First, a PROMISE step that corresponds to what humans are used to as commitment, and runs without talking to a coordinator. Second, a SERIALIZE step, that fixes transactions' positions in the serializable order, via a consensus procedure. We achieve this split via a novel data representation that embeds read-sets into transaction deltas, and serialization sequence numbers into table rows. WiSer does no sharding (all nodes can run transactions that modify the entire database), and yet enforces aggregation constraints. Both readwrite conflicts and aggregation constraint violations are resolved lazily in the serialized data. WiSer also covers node joins and departures as database tables, thus simplifying correctness and failure handling. We present the design of WiSer as well as experiments suggesting this approach has promise. △ Less

Submitted 5 August, 2019; originally announced August 2019.

Transport properties of beta-Ga2O3 Nanoparticles embedded in Nb thin films

Authors: L. S. Vaidhyanathan, M. P. Srinivasan, P. Chandra Mohan, D. K. Baisnab, R. Mythili, M. P. Janawadkar

Abstract: The origin of ferromagnetism in nanoparticles of nonmagnetic oxides is an interesting area of research. In the present work, transport properties of niobium thin films, with beta-Ga2O3 nanoparticles embedded within them, are presented. Nanoparticles of beta-Ga2O3 embedded in a Nb matrix were prepared at room temperature by radio frequency co-sputtering technique on Si (100) and glass substrates he… ▽ More The origin of ferromagnetism in nanoparticles of nonmagnetic oxides is an interesting area of research. In the present work, transport properties of niobium thin films, with beta-Ga2O3 nanoparticles embedded within them, are presented. Nanoparticles of beta-Ga2O3 embedded in a Nb matrix were prepared at room temperature by radio frequency co-sputtering technique on Si (100) and glass substrates held at room temperature. The thin films deposited on Si substrates were subjected to Ar annealing at a temperature range of 600-650 C for 1 hour. Films were characterized by X-ray diffraction (XRD), Micro-Raman and elemental identification was performed with an Energy Dispersive X-ray Spectroscopy (EDS). Transport measurements were performed down to liquid helium temperatures by four-probe contact technique, showed characteristics analogous to those observed in the context of a Kondo system. A comparison of the experimental data with the theoretical formalism of Kondo and Hamann is presented. It is suggested that this behavior arises from the existence of magnetic moments associated with the oxygen vacancy defects in the nanoparticles of the nonmagnetic oxide Ga2O3. △ Less

Submitted 8 October, 2014; originally announced October 2014.

Comments: 15 pages, 4 figures

A strategy to identify components using clustering approach for component reusability

Authors: N. Md Jubair Basha, Chandra Mohan

Abstract: Component Based Software Engineering (CBSE) has played a very important role for building larger software systems The current practices of software industry demands development of a software within time and budget which is highly productive. It is necessary to achieve how much effectively the software component is reusable. To achieve this, the component identification is mandatory. The traditiona… ▽ More Component Based Software Engineering (CBSE) has played a very important role for building larger software systems The current practices of software industry demands development of a software within time and budget which is highly productive. It is necessary to achieve how much effectively the software component is reusable. To achieve this, the component identification is mandatory. The traditional approaches are presented in the literature. However effective reuse is still a challenging issue. In this paper, a strategy has been proposed for the identification of a business component using clustering methodology. This approach will be useful in identifying the reusable components for different domains. The proposed approach has identified the reconfigured component using the CBO measure to reduce the coupling between the objects. By considering this proposed strategy, the productivity can be increased in the organization. △ Less

Submitted 14 June, 2014; originally announced June 2014.

Comments: arXiv admin note: substantial text overlap with arXiv:1207.4938, arXiv:1202.5609, arXiv:1406.3727

A methodology to identify the level of reuse using template factors

Authors: N. Md Jubair Basha, Chandra Mohan

Abstract: To build large scale software systems, Component Based Software Engineering (CBSE) has played a vital role. The current practices of software industry demands more development of a software within time and budget which is highly productive to them. It became so necessary to achieve how effectively the software component is reusable. In order to meet this, the component level reuse, in terms of bot… ▽ More To build large scale software systems, Component Based Software Engineering (CBSE) has played a vital role. The current practices of software industry demands more development of a software within time and budget which is highly productive to them. It became so necessary to achieve how effectively the software component is reusable. In order to meet this, the component level reuse, in terms of both class and method level can be possibly done. The traditional approaches are presented in the literature upto the level of extent of achievement of reuse. Any how still effective reuse is a challenging issue as a part. In this paper, a methodology has proposed for the identification of reuse level which has been considered by the using reuse metrics such as the Class Template Factor(CTF) and Method Template Factor(MTF). By considering these measures makes easy to identify the level of reuse so that helps in the growth the productivity in the organization. △ Less

Submitted 14 June, 2014; originally announced June 2014.

Comments: arXiv admin note: text overlap with arXiv:1203.1328, arXiv:1207.4938, arXiv:1202.5609

Content Based Image Retrieval Using Exact Legendre Moments and Support Vector Machine

Authors: Ch. Srinivasa Rao, S. Srinivas Kumar, B. Chandra Mohan

Abstract: Content Based Image Retrieval (CBIR) systems based on shape using invariant image moments, viz., Moment Invariants (MI) and Zernike Moments (ZM) are available in the literature. MI and ZM are good at representing the shape features of an image. However, non-orthogonality of MI and poor reconstruction of ZM restrict their application in CBIR. Therefore, an efficient and orthogonal moment based CBIR… ▽ More Content Based Image Retrieval (CBIR) systems based on shape using invariant image moments, viz., Moment Invariants (MI) and Zernike Moments (ZM) are available in the literature. MI and ZM are good at representing the shape features of an image. However, non-orthogonality of MI and poor reconstruction of ZM restrict their application in CBIR. Therefore, an efficient and orthogonal moment based CBIR system is needed. Legendre Moments (LM) are orthogonal, computationally faster, and can represent image shape features compactly. CBIR system using Exact Legendre Moments (ELM) for gray scale images is proposed in this work. Superiority of the proposed CBIR system is observed over other moment based methods, viz., MI and ZM in terms of retrieval efficiency and retrieval time. Further, the classification efficiency is improved by employing Support Vector Machine (SVM) classifier. Improved retrieval results are obtained over existing CBIR algorithm based on Stacked Euler Vector (SERVE) combined with Modified Moment Invariants (MMI). △ Less

Submitted 29 May, 2010; originally announced May 2010.

Comments: 11 Pages, IJMA

Journal ref: International journal of Multimedia & Its Applications 2.2 (2010) 69-79

Image Compression and Watermarking scheme using Scalar Quantization

Authors: Kilari Veera Swamy, B. Chandra Mohan, Y. V. Bhaskar Reddy, S. Srinivas Kumar

Abstract: This paper presents a new compression technique and image watermarking algorithm based on Contourlet Transform (CT). For image compression, an energy based quantization is used. Scalar quantization is explored for image watermarking. Double filter bank structure is used in CT. The Laplacian Pyramid (LP) is used to capture the point discontinuities, and then followed by a Directional Filter Bank (D… ▽ More This paper presents a new compression technique and image watermarking algorithm based on Contourlet Transform (CT). For image compression, an energy based quantization is used. Scalar quantization is explored for image watermarking. Double filter bank structure is used in CT. The Laplacian Pyramid (LP) is used to capture the point discontinuities, and then followed by a Directional Filter Bank (DFB) to link point discontinuities. The coefficients of down sampled low pass version of LP decomposed image are re-ordered in a pre-determined manner and prediction algorithm is used to reduce entropy (bits/pixel). In addition, the coefficients of CT are quantized based on the energy in the particular band. The superiority of proposed algorithm to JPEG is observed in terms of reduced blocking artifacts. The results are also compared with wavelet transform (WT). Superiority of CT to WT is observed when the image contains more contours. The watermark image is embedded in the low pass image of contourlet decomposition. The watermark can be extracted with minimum error. In terms of PSNR, the visual quality of the watermarked image is exceptional. The proposed algorithm is robust to many image attacks and suitable for copyright protection applications. △ Less

Submitted 29 March, 2010; originally announced March 2010.

Comments: 11 Pages, IJNGN Journal 2010

Journal ref: International Journal of Next-Generation Networks 2.1 (2010) 37-47