-
ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations
Authors:
Joao Fonseca,
Julia Stoyanovich
Abstract:
Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predictions, but require direct access to the underlying model, an assumption frequently violated in real-world deployments. Further, even when model access is possible, their exact computation may be prohibitively expensive.…
▽ More
Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predictions, but require direct access to the underlying model, an assumption frequently violated in real-world deployments. Further, even when model access is possible, their exact computation may be prohibitively expensive. We investigate whether meaningful Shapley value estimations can be obtained in a zero-shot setting, using only the input data distribution and no evaluations of the target model. To this end, we introduce ExplainerPFN, a tabular foundation model built on TabPFN that is pretrained on synthetic datasets generated from random structural causal models and supervised using exact or near-exact Shapley values. Once trained, ExplainerPFN predicts feature attributions for unseen tabular datasets without model access, gradients, or example explanations.
Our contributions are fourfold: (1) we show that few-shot learning-based explanations can achieve high fidelity to SHAP values with as few as two reference observations; (2) we propose ExplainerPFN, the first zero-shot method for estimating Shapley values without access to the underlying model or reference explanations; (3) we provide an open-source implementation of ExplainerPFN, including the full training pipeline and synthetic data generator; and (4) through extensive experiments on real and synthetic datasets, we show that ExplainerPFN achieves performance competitive with few-shot surrogate explainers that rely on 2-10 SHAP examples.
△ Less
Submitted 30 January, 2026;
originally announced January 2026.
-
SHAP-based Explanations are Sensitive to Feature Representation
Authors:
Hyunseung Hwang,
Andrew Bell,
Joao Fonseca,
Venetia Pliatsika,
Julia Stoyanovich,
Steven Euijong Whang
Abstract:
Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representation. In tabular data, feature values themselves are often considered interpretable. This paper examines the impact of data engineering choices on local feature-based explanations. We demonstrate that simple, common data en…
▽ More
Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representation. In tabular data, feature values themselves are often considered interpretable. This paper examines the impact of data engineering choices on local feature-based explanations. We demonstrate that simple, common data engineering techniques, such as representing age with a histogram or encoding race in a specific way, can manipulate feature importance as determined by popular methods like SHAP. Notably, the sensitivity of explanations to feature representation can be exploited by adversaries to obscure issues like discrimination. While the intuition behind these results is straightforward, their systematic exploration has been lacking. Previous work has focused on adversarial attacks on feature-based explainers by biasing data or manipulating models. To the best of our knowledge, this is the first study demonstrating that explainers can be misled by standard, seemingly innocuous data engineering techniques.
△ Less
Submitted 13 May, 2025;
originally announced May 2025.
-
Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs
Authors:
Joao Fonseca,
Andrew Bell,
Julia Stoyanovich
Abstract:
Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause significant harm, highlighting the critical need to safeguard widely-deployed models. Safeguarding approaches, which include fine-tuning models or having LLMs "self-…
▽ More
Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause significant harm, highlighting the critical need to safeguard widely-deployed models. Safeguarding approaches, which include fine-tuning models or having LLMs "self-reflect", may lengthen the inference time of a model, incur a computational penalty, reduce the semantic fluency of an output, and restrict ``normal'' model behavior. Importantly, these Safety-Performance Trade-offs (SPTs) remain an understudied area. In this work, we introduce a novel safeguard, called SafeNudge, that combines Controlled Text Generation with "nudging", or using text interventions to change the behavior of a model. SafeNudge triggers during text-generation while a jailbreak attack is being executed, and can reduce successful jailbreak attempts by 30% by guiding the LLM towards a safe responses. It adds minimal latency to inference and has a negligible impact on the semantic fluency of outputs. Further, we allow for tunable SPTs. SafeNudge is open-source and available through https://pypi.org/, and is compatible with models loaded with the Hugging Face "transformers" library.
△ Less
Submitted 2 January, 2025;
originally announced January 2025.
-
Output Scouting: Auditing Large Language Models for Catastrophic Responses
Authors:
Andrew Bell,
Joao Fonseca
Abstract:
Recent high profile incidents in which the use of Large Language Models (LLMs) resulted in significant harm to individuals have brought about a growing interest in AI safety. One reason LLM safety issues occur is that models often have at least some non-zero probability of producing harmful outputs. In this work, we explore the following scenario: imagine an AI safety auditor is searching for cata…
▽ More
Recent high profile incidents in which the use of Large Language Models (LLMs) resulted in significant harm to individuals have brought about a growing interest in AI safety. One reason LLM safety issues occur is that models often have at least some non-zero probability of producing harmful outputs. In this work, we explore the following scenario: imagine an AI safety auditor is searching for catastrophic responses from an LLM (e.g. a "yes" responses to "can I fire an employee for being pregnant?"), and is able to query the model a limited number times (e.g. 1000 times). What is a strategy for querying the model that would efficiently find those failure responses? To this end, we propose output scouting: an approach that aims to generate semantically fluent outputs to a given prompt matching any target probability distribution. We then run experiments using two LLMs and find numerous examples of catastrophic responses. We conclude with a discussion that includes advice for practitioners who are looking to implement LLM auditing for catastrophic responses. We also release an open-source toolkit (https://github.com/joaopfonseca/outputscouting) that implements our auditing framework using the Hugging Face transformers library.
△ Less
Submitted 28 March, 2025; v1 submitted 4 October, 2024;
originally announced October 2024.
-
The infrastructure powering IBM's Gen AI model development
Authors:
Talia Gershon,
Seetharami Seelam,
Brian Belgodere,
Milton Bonilla,
Lan Hoang,
Danny Barnett,
I-Hsin Chung,
Apoorve Mohan,
Ming-Hung Chen,
Lixiang Luo,
Robert Walkup,
Constantinos Evangelinos,
Shweta Salaria,
Marc Dombrowa,
Yoonho Park,
Apo Kayi,
Liran Schour,
Alim Alim,
Ali Sydney,
Pavlos Maniotis,
Laurent Schares,
Bernard Metzler,
Bengi Karacali-Akyamac,
Sophia Wen,
Tatsuhiro Chiba
, et al. (122 additional authors not shown)
Abstract:
AI Infrastructure plays a key role in the speed and cost-competitiveness of developing and deploying advanced AI models. The current demand for powerful AI infrastructure for model training is driven by the emergence of generative AI and foundational models, where on occasion thousands of GPUs must cooperate on a single training job for the model to be trained in a reasonable time. Delivering effi…
▽ More
AI Infrastructure plays a key role in the speed and cost-competitiveness of developing and deploying advanced AI models. The current demand for powerful AI infrastructure for model training is driven by the emergence of generative AI and foundational models, where on occasion thousands of GPUs must cooperate on a single training job for the model to be trained in a reasonable time. Delivering efficient and high-performing AI training requires an end-to-end solution that combines hardware, software and holistic telemetry to cater for multiple types of AI workloads. In this report, we describe IBM's hybrid cloud infrastructure that powers our generative AI model development. This infrastructure includes (1) Vela: an AI-optimized supercomputing capability directly integrated into the IBM Cloud, delivering scalable, dynamic, multi-tenant and geographically distributed infrastructure for large-scale model training and other AI workflow steps and (2) Blue Vela: a large-scale, purpose-built, on-premises hosting environment that is optimized to support our largest and most ambitious AI model training tasks. Vela provides IBM with the dual benefit of high performance for internal use along with the flexibility to adapt to an evolving commercial landscape. Blue Vela provides us with the benefits of rapid development of our largest and most ambitious models, as well as future-proofing against the evolving model landscape in the industry. Taken together, they provide IBM with the ability to rapidly innovate in the development of both AI models and commercial offerings.
△ Less
Submitted 13 January, 2025; v1 submitted 7 July, 2024;
originally announced July 2024.
-
Development of Machine Learning Classifiers for Blood-based Diagnosis and Prognosis of Suspected Acute Infections and Sepsis
Authors:
Ljubomir Buturovic,
Michael Mayhew,
Roland Luethy,
Kirindi Choi,
Uros Midic,
Nandita Damaraju,
Yehudit Hasin-Brumshtein,
Amitesh Pratap,
Rhys M. Adams,
Joao Fonseca,
Ambika Srinath,
Paul Fleming,
Claudia Pereira,
Oliver Liesenfeld,
Purvesh Khatri,
Timothy Sweeney
Abstract:
We applied machine learning to the unmet medical need of rapid and accurate diagnosis and prognosis of acute infections and sepsis in emergency departments. Our solution consists of a Myrna (TM) Instrument and embedded TriVerity (TM) classifiers. The instrument measures abundances of 29 messenger RNAs in patient's blood, subsequently used as features for machine learning. The classifiers convert t…
▽ More
We applied machine learning to the unmet medical need of rapid and accurate diagnosis and prognosis of acute infections and sepsis in emergency departments. Our solution consists of a Myrna (TM) Instrument and embedded TriVerity (TM) classifiers. The instrument measures abundances of 29 messenger RNAs in patient's blood, subsequently used as features for machine learning. The classifiers convert the input features to an intuitive test report comprising the separate likelihoods of (1) a bacterial infection (2) a viral infection, and (3) severity (need for Intensive Care Unit-level care). In internal validation, the system achieved AUROC = 0.83 on the three-class disease diagnosis (bacterial, viral, or non-infected) and AUROC = 0.77 on binary prognosis of disease severity. The Myrna, TriVerity system was granted breakthrough device designation by the United States Food and Drug Administration (FDA). This engineering manuscript teaches the standard and novel machine learning methods used to translate an academic research concept to a clinical product aimed at improving patient care, and discusses lessons learned.
△ Less
Submitted 2 July, 2024;
originally announced July 2024.
-
ShaRP: Explaining Rankings and Preferences with Shapley Values
Authors:
Venetia Pliatsika,
Joao Fonseca,
Kateryna Akhynko,
Ivan Shevchenko,
Julia Stoyanovich
Abstract:
Algorithmic decisions in critical domains such as hiring, college admissions, and lending are often based on rankings. Given the impact of these decisions on individuals, organizations, and population groups, it is essential to understand them - to help individuals improve their ranking position, design better ranking procedures, and ensure legal compliance. In this paper, we argue that explainabi…
▽ More
Algorithmic decisions in critical domains such as hiring, college admissions, and lending are often based on rankings. Given the impact of these decisions on individuals, organizations, and population groups, it is essential to understand them - to help individuals improve their ranking position, design better ranking procedures, and ensure legal compliance. In this paper, we argue that explainability methods for classification and regression, such as SHAP, are insufficient for ranking tasks, and present ShaRP - Shapley Values for Rankings and Preferences - a framework that explains the contributions of features to various aspects of a ranked outcome.
ShaRP computes feature contributions for various ranking-specific profit functions, such as rank and top-k, and also includes a novel Shapley value-based method for explaining pairwise preference outcomes. We provide a flexible implementation of ShaRP, capable of efficiently and comprehensively explaining ranked and pairwise outcomes over tabular data, in score-based ranking and learning-to-rank tasks. Finally, we develop a comprehensive evaluation methodology for ranking explainability methods, showing through qualitative, quantitative, and usability studies that our rank-aware QoIs offer complementary insights, scale effectively, and help users interpret ranked outcomes in practice.
△ Less
Submitted 28 July, 2025; v1 submitted 29 January, 2024;
originally announced January 2024.
-
Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity
Authors:
Andrew Bell,
Joao Fonseca,
Carlo Abrate,
Francesco Bonchi,
Julia Stoyanovich
Abstract:
Algorithmic recourse -- providing recommendations to those affected negatively by the outcome of an algorithmic system on how they can take action and change that outcome -- has gained attention as a means of giving persons agency in their interactions with artificial intelligence (AI) systems. Recent work has shown that even if an AI decision-making classifier is ``fair'' (according to some reaso…
▽ More
Algorithmic recourse -- providing recommendations to those affected negatively by the outcome of an algorithmic system on how they can take action and change that outcome -- has gained attention as a means of giving persons agency in their interactions with artificial intelligence (AI) systems. Recent work has shown that even if an AI decision-making classifier is ``fair'' (according to some reasonable criteria), recourse itself may be unfair due to differences in the initial circumstances of individuals, compounding disparities for marginalized populations and requiring them to exert more effort than others. There is a need to define more methods and metrics for evaluating fairness in recourse that span a range of normative views of the world, and specifically those that take into account time. Time is a critical element in recourse because the longer it takes an individual to act, the more the setting may change due to model or data drift.
This paper seeks to close this research gap by proposing two notions of fairness in recourse that are in normative alignment with substantive equality of opportunity, and that consider time. The first considers the (often repeated) effort individuals exert per successful recourse event, and the second considers time per successful recourse event. Building upon an agent-based framework for simulating recourse, this paper demonstrates how much effort is needed to overcome disparities in initial circumstances. We then proposes an intervention to improve the fairness of recourse by rewarding effort, and compare it to existing strategies.
△ Less
Submitted 29 January, 2024;
originally announced January 2024.
-
Polygon Detection from a Set of Lines
Authors:
Alfredo Ferreira Jr.,
Manuel J. Fonseca,
Joaquim A. Jorge
Abstract:
Detecting polygons defined by a set of line segments in a plane is an important step in analyzing vector drawings. This paper presents an approach combining several algorithms to detect basic polygons from arbitrary line segments. The resulting algorithm runs in polynomial time and space, with complexities of $O\bigl((N + M)^4\bigr)$ and $O\bigl((N + M)^2\bigr)$, where $N$ is the number of line se…
▽ More
Detecting polygons defined by a set of line segments in a plane is an important step in analyzing vector drawings. This paper presents an approach combining several algorithms to detect basic polygons from arbitrary line segments. The resulting algorithm runs in polynomial time and space, with complexities of $O\bigl((N + M)^4\bigr)$ and $O\bigl((N + M)^2\bigr)$, where $N$ is the number of line segments and $M$ is the number of intersections between line segments. Our choice of algorithms was made to strike a good compromise between efficiency and ease of implementation. The result is a simple and efficient solution to detect polygons from lines.
△ Less
Submitted 26 December, 2023;
originally announced December 2023.
-
Setting the Right Expectations: Algorithmic Recourse Over Time
Authors:
Joao Fonseca,
Andrew Bell,
Carlo Abrate,
Francesco Bonchi,
Julia Stoyanovich
Abstract:
Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take action against an undesirable outcome made by an algorithmic system, is receiving growing attention. The bulk of the literature on algorithmic recourse to-date focuses primarily on how to provide recourse to a single in…
▽ More
Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take action against an undesirable outcome made by an algorithmic system, is receiving growing attention. The bulk of the literature on algorithmic recourse to-date focuses primarily on how to provide recourse to a single individual, overlooking a critical element: the effects of a continuously changing context. Disregarding these effects on recourse is a significant oversight, since, in almost all cases, recourse consists of an individual making a first, unfavorable attempt, and then being given an opportunity to make one or several attempts at a later date - when the context might have changed. This can create false expectations, as initial recourse recommendations may become less reliable over time due to model drift and competition for access to the favorable outcome between individuals.
In this work we propose an agent-based simulation framework for studying the effects of a continuously changing environment on algorithmic recourse. In particular, we identify two main effects that can alter the reliability of recourse for individuals represented by the agents: (1) competition with other agents acting upon recourse, and (2) competition with new agents entering the environment. Our findings highlight that only a small set of specific parameterizations result in algorithmic recourse that is reliable for agents over time. Consequently, we argue that substantial additional work is needed to understand recourse reliability over time, and to develop recourse methods that reward agents' effort.
△ Less
Submitted 13 September, 2023;
originally announced September 2023.
-
The Myth of Meritocracy and the Matilda Effect in STEM: Paper Acceptance and Paper Citation
Authors:
Joana Fonseca
Abstract:
Biases against women in the workplace have been documented in various studies. There is also a growing body of literature on biases within academia. But particularly in STEM, due to the heavily male-dominated field, studies suggest that if one's gender is identifiable, women are more likely to get their papers rejected and not cited as often as men. We propose two simple modifications to tackle ge…
▽ More
Biases against women in the workplace have been documented in various studies. There is also a growing body of literature on biases within academia. But particularly in STEM, due to the heavily male-dominated field, studies suggest that if one's gender is identifiable, women are more likely to get their papers rejected and not cited as often as men. We propose two simple modifications to tackle gender bias in STEM that can be applied to (but not only) IEEE conferences and journals. Regarding paper acceptance, we propose a double-blind review, and regarding paper citation, we propose one single letter to identify the authors' first names, followed by their family names. We also propose other modifications regarding gender bias in STEM and academia and encourage further reforms supported by current research on this topic with gender-segregated data.
△ Less
Submitted 19 June, 2023;
originally announced June 2023.
-
Data and Knowledge for Overtaking Scenarios in Autonomous Driving
Authors:
Mariana Pinto,
Inês Dutra,
Joaquim Fonseca
Abstract:
Autonomous driving has become one of the most popular research topics within Artificial Intelligence. An autonomous vehicle is understood as a system that combines perception, decision-making, planning, and control. All of those tasks require that the vehicle collects surrounding data in order to make a good decision and action. In particular, the overtaking maneuver is one of the most critical ac…
▽ More
Autonomous driving has become one of the most popular research topics within Artificial Intelligence. An autonomous vehicle is understood as a system that combines perception, decision-making, planning, and control. All of those tasks require that the vehicle collects surrounding data in order to make a good decision and action. In particular, the overtaking maneuver is one of the most critical actions of driving. The process involves lane changes, acceleration and deceleration actions, and estimation of the speed and distance of the vehicle in front or in the lane in which it is moving. Despite the amount of work available in the literature, just a few handle overtaking maneuvers and, because overtaking can be risky, no real-world dataset is available. This work contributes in this area by presenting a new synthetic dataset whose focus is the overtaking maneuver. We start by performing a thorough review of the state of the art in autonomous driving and then explore the main datasets found in the literature (public and private, synthetic and real), highlighting their limitations, and suggesting a new set of features whose focus is the overtaking maneuver.
△ Less
Submitted 30 May, 2023;
originally announced May 2023.
-
CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
Authors:
Chinedu Innocent Nwoye,
Tong Yu,
Saurav Sharma,
Aditya Murali,
Deepak Alapatt,
Armine Vardazaryan,
Kun Yuan,
Jonas Hajek,
Wolfgang Reiter,
Amine Yamlahi,
Finn-Henri Smidt,
Xiaoyang Zou,
Guoyan Zheng,
Bruno Oliveira,
Helena R. Torres,
Satoshi Kondo,
Satoshi Kasai,
Felix Holm,
Ege Özsoy,
Shuangchun Gui,
Han Li,
Sista Raviteja,
Rachana Sathish,
Pranav Poudel,
Binod Bhattarai
, et al. (24 additional authors not shown)
Abstract:
Formalizing surgical activities as triplets of the used instruments, actions performed, and target anatomies is becoming a gold standard approach for surgical activity modeling. The benefit is that this formalization helps to obtain a more detailed understanding of tool-tissue interaction which can be used to develop better Artificial Intelligence assistance for image-guided surgery. Earlier effor…
▽ More
Formalizing surgical activities as triplets of the used instruments, actions performed, and target anatomies is becoming a gold standard approach for surgical activity modeling. The benefit is that this formalization helps to obtain a more detailed understanding of tool-tissue interaction which can be used to develop better Artificial Intelligence assistance for image-guided surgery. Earlier efforts and the CholecTriplet challenge introduced in 2021 have put together techniques aimed at recognizing these triplets from surgical footage. Estimating also the spatial locations of the triplets would offer a more precise intraoperative context-aware decision support for computer-assisted intervention. This paper presents the CholecTriplet2022 challenge, which extends surgical action triplet modeling from recognition to detection. It includes weakly-supervised bounding box localization of every visible surgical instrument (or tool), as the key actors, and the modeling of each tool-activity in the form of <instrument, verb, target> triplet. The paper describes a baseline method and 10 new deep learning algorithms presented at the challenge to solve the task. It also provides thorough methodological comparisons of the methods, an in-depth analysis of the obtained results across multiple metrics, visual and procedural challenges; their significance, and useful insights for future research directions and applications in surgery.
△ Less
Submitted 14 July, 2023; v1 submitted 13 February, 2023;
originally announced February 2023.
-
Research Trends and Applications of Data Augmentation Algorithms
Authors:
Joao Fonseca,
Fernando Bacao
Abstract:
In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not always available, motivating research on regularization methods. In addition, current and past research have shown that simpler classification algorithms can r…
▽ More
In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not always available, motivating research on regularization methods. In addition, current and past research have shown that simpler classification algorithms can reach state-of-the-art performance on computer vision tasks given a robust method to artificially augment the training dataset. Because of this, data augmentation techniques became a popular research topic in recent years. However, existing data augmentation methods are generally less transferable than other regularization methods. In this paper we identify the main areas of application of data augmentation algorithms, the types of algorithms used, significant research trends, their progression over time and research gaps in data augmentation literature. To do this, the related literature was collected through the Scopus database. Its analysis was done following network science, text mining and exploratory analysis approaches. We expect readers to understand the potential of data augmentation, as well as identify future research directions and open questions within data augmentation research.
△ Less
Submitted 2 August, 2022; v1 submitted 18 July, 2022;
originally announced July 2022.
-
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
Authors:
Chinedu Innocent Nwoye,
Deepak Alapatt,
Tong Yu,
Armine Vardazaryan,
Fangfang Xia,
Zixuan Zhao,
Tong Xia,
Fucang Jia,
Yuxuan Yang,
Hao Wang,
Derong Yu,
Guoyan Zheng,
Xiaotian Duan,
Neil Getty,
Ricardo Sanchez-Matilla,
Maria Robu,
Li Zhang,
Huabin Chen,
Jiacheng Wang,
Liansheng Wang,
Bokai Zhang,
Beerend Gerats,
Sista Raviteja,
Rachana Sathish,
Rong Tao
, et al. (37 additional authors not shown)
Abstract:
Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in…
▽ More
Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of <instrument, verb, target> combination delivers comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. The challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. A total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms by competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery.
△ Less
Submitted 29 December, 2022; v1 submitted 10 April, 2022;
originally announced April 2022.
-
Developing Assistive Technology to Support Reminiscence Therapy: A User-Centered Study to Identify Caregivers' Needs
Authors:
Soraia M. Alarcão,
André Santana,
Carolina Maruta,
Manuel J. Fonseca
Abstract:
Reminiscence therapy is an inexpensive non-pharmacological therapy commonly used due to its therapeutic value for PwD, as it can be used to promote independence, positive moods and behavior, and improve their quality of life. Caregivers are one of the main pillars in the adoption of digital technologies for reminiscence therapy, as they are responsible for its administration. Despite their compreh…
▽ More
Reminiscence therapy is an inexpensive non-pharmacological therapy commonly used due to its therapeutic value for PwD, as it can be used to promote independence, positive moods and behavior, and improve their quality of life. Caregivers are one of the main pillars in the adoption of digital technologies for reminiscence therapy, as they are responsible for its administration. Despite their comprehensive understanding of the needs and difficulties associated with the therapy, their perspective has not been fully taken into account in the development of existing technological solutions. To inform the design of technological solutions within dementia care, we followed a user-centered design approach through worldwide surveys, follow-up semi-structured interviews, and focus groups. Seven hundred and seven informal and 52 formal caregivers participated in our study. Our findings show that technological solutions must provide mechanisms to carry out the therapy in a simple way, reducing the amount of work for caregivers when preparing and conducting therapy sessions. They should also diversify and personalize the current session (and following ones) based on both the biographical information of the PwD and their emotional reactions. This is particularly important since the PwD often become agitated, aggressive or angry, and caregivers might not know how to properly deal with this situation (in particular, the informal ones). Additionally, formal caregivers need an easy way to manage information of the different PwD they take care of, and consult the history of sessions performed (in particular, to identify images that triggered negative emotional reactions, and consult any notes taken about them). As a result, we present a list of validated functional requirements gathered for the PwD and both formal and informal caregivers, as well as the corresponding expected primary and secondary outcomes.
△ Less
Submitted 7 January, 2022;
originally announced January 2022.
-
Narratives and Needs: Analyzing Experiences of Cyclone Amphan Using Twitter Discourse
Authors:
Ancil Crayton,
João Fonseca,
Kanav Mehra,
Michelle Ng,
Jared Ross,
Marcelo Sandoval-Castañeda,
Rachel von Gnechten
Abstract:
People often turn to social media to comment upon and share information about major global events. Accordingly, social media is receiving increasing attention as a rich data source for understanding people's social, political and economic experiences of extreme weather events. In this paper, we contribute two novel methodologies that leverage Twitter discourse to characterize narratives and identi…
▽ More
People often turn to social media to comment upon and share information about major global events. Accordingly, social media is receiving increasing attention as a rich data source for understanding people's social, political and economic experiences of extreme weather events. In this paper, we contribute two novel methodologies that leverage Twitter discourse to characterize narratives and identify unmet needs in response to Cyclone Amphan, which affected 18 million people in May 2020.
△ Less
Submitted 11 September, 2020;
originally announced September 2020.
-
Cooperative decentralized circumnavigation with application to algal bloom tracking
Authors:
Joana Fonseca,
Jieqiang Wei,
Karl H. Johansson,
Tor Arne Johansen
Abstract:
Harmful algal blooms occur frequently and deteriorate water quality. A reliable method is proposed in this paper to track algal blooms using a set of autonomous surface robots. A satellite image indicates the existence and initial location of the algal bloom for the deployment of the robot system. The algal bloom area is approximated by a circle with time varying location and size. This circle is…
▽ More
Harmful algal blooms occur frequently and deteriorate water quality. A reliable method is proposed in this paper to track algal blooms using a set of autonomous surface robots. A satellite image indicates the existence and initial location of the algal bloom for the deployment of the robot system. The algal bloom area is approximated by a circle with time varying location and size. This circle is estimated and circumnavigated by the robots which are able to locally sense its boundary. A multi-agent control algorithm is proposed for the continuous monitoring of the dynamic evolution of the algal bloom. Such algorithm comprises of a decentralized least squares estimation of the target and a controller for circumnavigation. We prove the convergence of the robots to the circle and in equally spaced positions around it. Simulation results with data provided by the SINMOD ocean model are used to illustrate the theoretical results.
△ Less
Submitted 14 March, 2019;
originally announced March 2019.
-
Personal Virtual Traffic Light Systems
Authors:
Vanessa Martins,
João Rufino,
Bruno Fernandes,
Luís Silva,
João Almeida,
Joaquim Ferreira,
José Fonseca
Abstract:
Traffic control management at intersections, a challenging and complex field of study, aims to attain a balance between safety and efficient traffic control. Nowadays, traffic control at intersections is typically done by traffic light systems which are not optimal and exhibit several drawbacks, e.g. poor efficiency and real-time adaptability. With the advent of Intelligent Transportation Systems…
▽ More
Traffic control management at intersections, a challenging and complex field of study, aims to attain a balance between safety and efficient traffic control. Nowadays, traffic control at intersections is typically done by traffic light systems which are not optimal and exhibit several drawbacks, e.g. poor efficiency and real-time adaptability. With the advent of Intelligent Transportation Systems (ITS), vehicles are being equipped with state-of-the-art technology, enabling cooperative decision-making which will certainly overwhelm the available traffic control systems. This solution strongly penalizes users without such capabilities, namely pedestrians, cyclists and other legacy vehicles. Therefore, in this work, a prototype based on an alternative technology to the standard vehicular communications, BLE, is presented. The proposed framework aims to integrate legacy and modern vehicular communication systems into a cohesive management system. In this framework, the movements of users at intersections are managed by a centralized controller which, through the use of networked retransmitters deployed at intersections, broadcasts alerts and virtual light signalization orders. Users receive the aforementioned information on their own smart devices, discarding the need for dedicated light signalization infrastructures. Field tests, carried-out with a real-world implementation, validate the correct operation of the proposed framework.
△ Less
Submitted 20 September, 2018;
originally announced September 2018.
-
Enhancing speed and scalability of the ParFlow simulation code
Authors:
Carsten Burstedde,
Jose A. Fonseca,
Stefan Kollet
Abstract:
Regional hydrology studies are often supported by high resolution simulations of subsurface flow that require expensive and extensive computations. Efficient usage of the latest high performance parallel computing systems becomes a necessity. The simulation software ParFlow has been demonstrated to meet this requirement and shown to have excellent solver scalability for up to 16,384 processes. In…
▽ More
Regional hydrology studies are often supported by high resolution simulations of subsurface flow that require expensive and extensive computations. Efficient usage of the latest high performance parallel computing systems becomes a necessity. The simulation software ParFlow has been demonstrated to meet this requirement and shown to have excellent solver scalability for up to 16,384 processes. In the present work we show that the code requires further enhancements in order to fully take advantage of current petascale machines. We identify ParFlow's way of parallelization of the computational mesh as a central bottleneck. We propose to reorganize this subsystem using fast mesh partition algorithms provided by the parallel adaptive mesh refinement library p4est. We realize this in a minimally invasive manner by modifying selected parts of the code to reinterpret the existing mesh data structures. We evaluate the scaling performance of the modified version of ParFlow, demonstrating good weak and strong scaling up to 458k cores of the Juqueen supercomputer, and test an example application at large scale.
△ Less
Submitted 2 October, 2017; v1 submitted 22 February, 2017;
originally announced February 2017.
-
Can information be spread as a virus? Viral Marketing as epidemiological model
Authors:
Helena Sofia Rodrigues,
Manuel José Fonseca
Abstract:
In epidemiology, an epidemic is defined as the spread of an infectious disease to a large number of people in a given population within a short period of time. In the marketing context, a message is viral when it is broadly sent and received by the target market through person-to-person transmission. This specific marketing communication strategy is commonly referred as viral marketing. Due to thi…
▽ More
In epidemiology, an epidemic is defined as the spread of an infectious disease to a large number of people in a given population within a short period of time. In the marketing context, a message is viral when it is broadly sent and received by the target market through person-to-person transmission. This specific marketing communication strategy is commonly referred as viral marketing. Due to this similarity between an epidemic and the viral marketing process and because the understanding of the critical factors to this communications strategy effectiveness remain largely unknown, the mathematical models in epidemiology are presented in this marketing specific field. In this paper, an epidemiological model SIR (Susceptible- Infected-Recovered) to study the effects of a viral marketing strategy is presented. It is made a comparison between the disease parameters and the marketing application, and Matlab simulations are performed. Finally, some conclusions are carried out and their marketing implications are exposed: interactions across the parameters suggest some recommendations to marketers, as the profitability of the investment or the need to improve the targeting criteria of the communications campaigns.
△ Less
Submitted 8 November, 2016;
originally announced November 2016.
-
NEMO5: Achieving High-end Internode Communication for Performance Projection Beyond Moore's Law
Authors:
Robert Andrawis,
Jose David Bermeo,
James Charles,
Jianbin Fang,
Jim Fonseca,
Yu He,
Gerhard Klimeck,
Zhengping Jiang,
Tillmann Kubis,
Daniel Mejia,
Daniel Lemus,
Michael Povolotskyi,
Santiago Alonso Perez Rubiano,
Prasad Sarangapani,
Lang Zeng
Abstract:
Electronic performance predictions of modern nanotransistors require nonequilibrium Green's functions including incoherent scattering on phonons as well as inclusion of random alloy disorder and surface roughness effects. The solution of all these effects is numerically extremely expensive and has to be done on the world's largest supercomputers due to the large memory requirement and the high per…
▽ More
Electronic performance predictions of modern nanotransistors require nonequilibrium Green's functions including incoherent scattering on phonons as well as inclusion of random alloy disorder and surface roughness effects. The solution of all these effects is numerically extremely expensive and has to be done on the world's largest supercomputers due to the large memory requirement and the high performance demands on the communication network between the compute nodes. In this work, it is shown that NEMO5 covers all required physical effects and their combination. Furthermore, it is also shown that NEMO5's implementation of the algorithm scales very well up to about 178176CPUs with a sustained performance of about 857 TFLOPS. Therefore, NEMO5 is ready to simulate future nanotransistors.
△ Less
Submitted 15 October, 2015;
originally announced October 2015.
-
Arabesque: A System for Distributed Graph Mining - Extended version
Authors:
Carlos H. C. Teixeira,
Alexandre J. Fonseca,
Marco Serafini,
Georgos Siganos,
Mohammed J. Zaki,
Ashraf Aboulnaga
Abstract:
Distributed data processing platforms such as MapReduce and Pregel have substantially simplified the design and deployment of certain classes of distributed graph analytics algorithms. However, these platforms do not represent a good match for distributed graph mining problems, as for example finding frequent subgraphs in a graph. Given an input graph, these problems require exploring a very large…
▽ More
Distributed data processing platforms such as MapReduce and Pregel have substantially simplified the design and deployment of certain classes of distributed graph analytics algorithms. However, these platforms do not represent a good match for distributed graph mining problems, as for example finding frequent subgraphs in a graph. Given an input graph, these problems require exploring a very large number of subgraphs and finding patterns that match some "interestingness" criteria desired by the user. These algorithms are very important for areas such as social net- works, semantic web, and bioinformatics. In this paper, we present Arabesque, the first distributed data processing platform for implementing graph mining algorithms. Arabesque automates the process of exploring a very large number of subgraphs. It defines a high-level filter-process computational model that simplifies the development of scalable graph mining algorithms: Arabesque explores subgraphs and passes them to the application, which must simply compute outputs and decide whether the subgraph should be further extended. We use Arabesque's API to produce distributed solutions to three fundamental graph mining problems: frequent subgraph mining, counting motifs, and finding cliques. Our implementations require a handful of lines of code, scale to trillions of subgraphs, and represent in some cases the first available distributed solutions.
△ Less
Submitted 14 October, 2015;
originally announced October 2015.
-
Viral marketing as epidemiological model
Authors:
Helena Sofia Rodrigues,
Manuel José Fonseca
Abstract:
In epidemiology, an epidemic is defined as the spread of an infectious disease to a large number of people in a given population within a short period of time. In the marketing context, a message is viral when it is broadly sent and received by the target market through person-to-person transmission. This specific marketing communication strategy is commonly referred as viral marketing. Due to thi…
▽ More
In epidemiology, an epidemic is defined as the spread of an infectious disease to a large number of people in a given population within a short period of time. In the marketing context, a message is viral when it is broadly sent and received by the target market through person-to-person transmission. This specific marketing communication strategy is commonly referred as viral marketing. Due to this similarity between an epidemic and the viral marketing process and because the understanding of the critical factors to this communications strategy effectiveness remain largely unknown, the mathematical models in epidemiology are presented in this marketing specific field. In this paper, an epidemiological model SIR (Susceptible- Infected-Recovered) to study the effects of a viral marketing strategy is presented. It is made a comparison between the disease parameters and the marketing application, and simulations using the Matlab software are performed. Finally, some conclusions are given and their marketing implications are exposed: interactions across the parameters are found that appear to suggest some recommendations to marketers, as the profitability of the investment or the need to improve the targeting criteria of the communications campaigns.
△ Less
Submitted 24 July, 2015;
originally announced July 2015.
-
Standing Together for Reproducibility in Large-Scale Computing: Report on reproducibility@XSEDE
Authors:
Doug James,
Nancy Wilkins-Diehr,
Victoria Stodden,
Dirk Colbry,
Carlos Rosales,
Mark Fahey,
Justin Shi,
Rafael F. Silva,
Kyo Lee,
Ralph Roskies,
Laurence Loewe,
Susan Lindsey,
Rob Kooper,
Lorena Barba,
David Bailey,
Jonathan Borwein,
Oscar Corcho,
Ewa Deelman,
Michael Dietze,
Benjamin Gilbert,
Jan Harkes,
Seth Keele,
Praveen Kumar,
Jong Lee,
Erika Linke
, et al. (30 additional authors not shown)
Abstract:
This is the final report on reproducibility@xsede, a one-day workshop held in conjunction with XSEDE14, the annual conference of the Extreme Science and Engineering Discovery Environment (XSEDE). The workshop's discussion-oriented agenda focused on reproducibility in large-scale computational research. Two important themes capture the spirit of the workshop submissions and discussions: (1) organiz…
▽ More
This is the final report on reproducibility@xsede, a one-day workshop held in conjunction with XSEDE14, the annual conference of the Extreme Science and Engineering Discovery Environment (XSEDE). The workshop's discussion-oriented agenda focused on reproducibility in large-scale computational research. Two important themes capture the spirit of the workshop submissions and discussions: (1) organizational stakeholders, especially supercomputer centers, are in a unique position to promote, enable, and support reproducible research; and (2) individual researchers should conduct each experiment as though someone will replicate that experiment. Participants documented numerous issues, questions, technologies, practices, and potentially promising initiatives emerging from the discussion, but also highlighted four areas of particular interest to XSEDE: (1) documentation and training that promotes reproducible research; (2) system-level tools that provide build- and run-time information at the level of the individual job; (3) the need to model best practices in research collaborations involving XSEDE staff; and (4) continued work on gateways and related technologies. In addition, an intriguing question emerged from the day's interactions: would there be value in establishing an annual award for excellence in reproducible research?
△ Less
Submitted 2 January, 2015; v1 submitted 17 December, 2014;
originally announced December 2014.
-
A security framework for SOA applications in mobile environment
Authors:
Johnneth Fonseca,
Zair Abdelouahab,
Denivaldo Lopes,
Sofiane Labidi
Abstract:
A Rapid evolution of mobile technologies has led to the development of more sophisticated mobile devices with better storage, processing and transmission power. These factors enable support to many types of application but also give rise to a necessity to find a model of service development. Actually, SOA (Service Oriented Architecture) is a good option to support application development. This pap…
▽ More
A Rapid evolution of mobile technologies has led to the development of more sophisticated mobile devices with better storage, processing and transmission power. These factors enable support to many types of application but also give rise to a necessity to find a model of service development. Actually, SOA (Service Oriented Architecture) is a good option to support application development. This paper presents a framework that allows the development of SOA based application in mobile environment. The objective of the framework is to give developers with tools for provision of services in this environment with the necessary security characteristics.
△ Less
Submitted 6 April, 2010;
originally announced April 2010.