James Weimer
YOU?
Author Swipe
View article: Exploring Effective Sensing Indicators of Loneliness For Elderly Community in US and Japan
Exploring Effective Sensing Indicators of Loneliness For Elderly Community in US and Japan Open
Loneliness has long affected the elderly community. This issue is significantly worsened by the social isolation resulting from the COVID-19 pandemic. To address this pressing issue, we employed a sensor-based methodology to predict loneli…
View article: Memory-Consistent Neural Networks for Imitation Learning
Memory-Consistent Neural Networks for Imitation Learning Open
Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Eve…
View article: Curating Naturally Adversarial Datasets for Learning-Enabled Medical Cyber-Physical Systems
Curating Naturally Adversarial Datasets for Learning-Enabled Medical Cyber-Physical Systems Open
Deep learning models have shown promising predictive accuracy for time-series healthcare applications. However, ensuring the robustness of these models is vital for building trustworthy AI systems. Existing research predominantly focuses o…
View article: Automatically Predicting Perceived Conversation Quality in a Pediatric Sample Enriched for Autism
Automatically Predicting Perceived Conversation Quality in a Pediatric Sample Enriched for Autism Open
Social interaction quality ratings derived from short natural conversations can differentiate children with and without autism at the group level. In this work, we explored conversations between children and an unfamiliar adult who rated t…
View article: Prolonged Use of an Automated Insulin Delivery System Improves Sleep in Long-Standing Type 1 Diabetes Complicated by Impaired Awareness of Hypoglycemia
Prolonged Use of an Automated Insulin Delivery System Improves Sleep in Long-Standing Type 1 Diabetes Complicated by Impaired Awareness of Hypoglycemia Open
Background: This study assessed changes in actigraphy-estimated sleep and glycemic outcomes after initiating automated insulin delivery (AID). Methods: Ten adults with long-standing type 1 diabetes and impaired awareness of hypoglycemia (I…
View article: Short: Integrated Sensing Platform for Detecting Social Isolation and Loneliness In the Elderly Community
Short: Integrated Sensing Platform for Detecting Social Isolation and Loneliness In the Elderly Community Open
Social isolation is an objective absence or paucity of contacts and interactions between a person and a social network. Loneliness is a subjective feeling of being alone, separated, or apart from others. These two highly correlated mental …
View article: DOVE: Shoulder-based Opioid Overdose Detection and Reversal Device
DOVE: Shoulder-based Opioid Overdose Detection and Reversal Device Open
Naloxone is a life-saving drug capable of reversing a fatal opioid overdose. Although this drug has existed for over 50 years, opioid overdose-related deaths have consistently risen and surpassed 120,000 globally in 2021. Opioids induce re…
View article: Preface
Preface Open
Welcome, on behalf of the IEEE International Conference On Assured Autonomy (ICAA) 2023 organizing committee, we are pleased to present to you the proceedings of our second conference focused on Assured Autonomy.ICAA brings together resear…
View article: Detection of Adversarial Physical Attacks in Time-Series Image Data
Detection of Adversarial Physical Attacks in Time-Series Image Data Open
Deep neural networks (DNN) have become a common sensing modality in autonomous systems as they allow for semantically perceiving the ambient environment given input images. Nevertheless, DNN models have proven to be vulnerable to adversari…
View article: Automated Insulin Delivery for Hypoglycemia Avoidance and Glucose Counterregulation in Long-Standing Type 1 Diabetes with Hypoglycemia Unawareness
Automated Insulin Delivery for Hypoglycemia Avoidance and Glucose Counterregulation in Long-Standing Type 1 Diabetes with Hypoglycemia Unawareness Open
Objective: Automated insulin delivery (AID) may benefit individuals with long-standing type 1 diabetes where frequent exposure to hypoglycemia impairs counterregulatory responses. This study assessed the effect of 18 months AID on hypoglyc…
View article: Derivation and Validation of an Algorithm to Detect Stroke Using Arm Accelerometry Data
Derivation and Validation of an Algorithm to Detect Stroke Using Arm Accelerometry Data Open
Background Early diagnosis is essential for effective stroke therapy. Strokes in hospitalized patients are associated with worse outcomes compared with strokes in the community. We derived and validated an algorithm to identify strokes by …
View article: Guaranteed Conformance of Neurosymbolic Models to Natural Constraints
Guaranteed Conformance of Neurosymbolic Models to Natural Constraints Open
Deep neural networks have emerged as the workhorse for a large section of robotics and control applications, especially as models for dynamical systems. Such data-driven models are in turn used for designing and verifying autonomous system…
View article: Let's Talk Through Physics! Covert Cyber-Physical Data Exfiltration on Air-Gapped Edge Devices
Let's Talk Through Physics! Covert Cyber-Physical Data Exfiltration on Air-Gapped Edge Devices Open
Although organizations are continuously making concerted efforts to harden their systems against network attacks by air-gapping critical systems, attackers continuously adapt and uncover covert channels to exfiltrate data from air-gapped s…
View article: Narrowing the Gap: Towards Analyzable and Realistic Simulators for Safety Analysis of Neural Network Control Systems
Narrowing the Gap: Towards Analyzable and Realistic Simulators for Safety Analysis of Neural Network Control Systems Open
International audience
View article: How Do a Person's Bed Movements Relate to Fall Risk?: A Systematic Review (Preprint)
How Do a Person's Bed Movements Relate to Fall Risk?: A Systematic Review (Preprint) Open
BACKGROUND Patients with high fall risk tend to spend substantial time in bed due to reduced physical activity. Thus, accidental falls frequently occur during body position changes, including when a person rises from the bed to stand. Thi…
View article: Alarm Burden in Infants With Bronchopulmonary Dysplasia Monitored With Pulse Oximetry at Home
Alarm Burden in Infants With Bronchopulmonary Dysplasia Monitored With Pulse Oximetry at Home Open
This cohort study evaluates the association of settings on home oxygen saturation monitors with alarm incidence for infants with bronchopulmonary dysplasia (BPD).
View article: Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations
Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations Open
Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on t…
View article: 0585 Use of a Hybrid Closed Loop Insulin Delivery System Improves Sleep and Glycemic Control in Adults with Long-Standing Type 1 Diabetes and Hypoglycemia Unawareness
0585 Use of a Hybrid Closed Loop Insulin Delivery System Improves Sleep and Glycemic Control in Adults with Long-Standing Type 1 Diabetes and Hypoglycemia Unawareness Open
Introduction Insulin delivery and continuous glucose monitoring systems (CGMs) have been reported to disrupt sleep in individuals with type 1 diabetes (T1D), potentially thwarting the adoption and continued use of diabetes therapeutic tech…
View article: A Framework for Checkpointing and Recovery of Hierarchical Cyber-Physical Systems
A Framework for Checkpointing and Recovery of Hierarchical Cyber-Physical Systems Open
This paper tackles the problem of making complex resource-constrained cyber-physical systems (CPS) resilient to sensor anomalies. In particular, we present a framework for checkpointing and roll-forward recovery of state-estimates in nonli…
View article: Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates
Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates Open
Long horizon robot learning tasks with sparse rewards pose a significant challenge for current reinforcement learning algorithms. A key feature enabling humans to learn challenging control tasks is that they often receive expert interventi…
View article: ARCH-COMP21 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants
ARCH-COMP21 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants Open
This report presents the results of a friendly competition for formal verification of continuous and hybrid systems with artificial intelligence (AI) components. Specifically, machine learning (ML) components in cyber-physical systems (CPS…
View article: VitalCore: Analytics and Support Dashboard for Medical Device Integration
VitalCore: Analytics and Support Dashboard for Medical Device Integration Open
Medical professionals spend extensive time collecting, validating, reviewing, and analyzing medical device data. These devices use vendor-specific applications with lengthy troubleshooting times, causing extended downtimes where medical pr…
View article: Chef: a cheap and fast pipeline for iteratively cleaning label uncertainties
Chef: a cheap and fast pipeline for iteratively cleaning label uncertainties Open
High-quality labels are expensive to obtain for many machine learning tasks, such as medical image classification tasks. Therefore, probabilistic (weak) labels produced by weak supervision tools are used to seed a process in which influent…
View article: Improving Neural Network Robustness via Persistency of Excitation
Improving Neural Network Robustness via Persistency of Excitation Open
Improving adversarial robustness of neural networks remains a major challenge. Fundamentally, training a neural network via gradient descent is a parameter estimation problem. In adaptive control, maintaining persistency of excitation (PoE…
View article: Robust Learning via Persistency of Excitation
Robust Learning via Persistency of Excitation Open
Improving adversarial robustness of neural networks remains a major challenge. Fundamentally, training a network is a parameter estimation problem. In adaptive control theory, maintaining persistency of excitation (PoE) is integral to ensu…
View article: Confidence Calibration with Bounded Error Using Transformations
Confidence Calibration with Bounded Error Using Transformations Open
As machine learning techniques become widely adopted in new domains, especially in safety-critical systems such as autonomous vehicles, it is crucial to provide accurate output uncertainty estimation. As a result, many approaches have been…