Bashima Islam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bashima Islam has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Mark Hasegawa-Johnson
University of Illinois
5 shared publications - Nancy L. McElwain
Beckman Institute for Advanced Science and Technology University of Illinois
5 shared publications - Mohammad Nur Hossain Khan
Worcester Polytechnic Institute, Worcester, Massachusetts, USA
4 shared publications - Subrata Biswas
Department of Electrical & Computer Engineering Worcester Polytechnic Institute 01609 Worcester MA
4 shared publications - Ashutosh Dhekne
Georgia Tech, Atlanta, Georgia, USA
2 shared publications - Camille Nebeker
Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego, La Jolla, CA, United States
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8236-8243
Hard Rules, Soft Preferences: Bridging Reasoning, Learning, and Optimization for Personalized Packing Checklist Generation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8236-8243
Open AccessHard Rules, Soft Preferences: Bridging Reasoning, Learning, and Optimization for Personalized Packing Checklist Generation
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-25
MindfulAgents: Personalizing Mindfulness Meditation via an Expert-Aligned Multi-Agent System
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-25
Open AccessMindfulAgents: Personalizing Mindfulness Meditation via an Expert-Aligned Multi-Agent System
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (1) , 162-172
ECG Statement Classification and Lead Reconstruction Using CNN-Based Models
ECG is an essential diagnostic tool that offers important insight into a person's cardiac and general health. The rise of intelligent wearable devices has opened a new avenue for clinicians and individuals to capture long term ECG data-albeit with fewer leads than the 12 leads that are typically used clinically, which can be vital for identifying and addressing health concerns. In this work, a multi-task convolutional neural network (CNN) classifier was used to study the influence of various combinations of ECG leads in interpretation of 71 cardiac statements spanning cardiac diagnostics, form, and rhythm. Results of this analysis suggest that the subset of limb leads I and II and chest leads V1, V3, and V6 can be used to identify several cardiac statements without loss of performance (average macro AUC of 0.903) when compared to a model trained using all 12- leads (average macro AUC of 0.905; p = 1). A hybrid CNNLSTM (long short-term memory) model was developed to reconstruct the missing chest leads. The highest performing lead reconstructor achieved an average R2 score of 0.835 when reconstructing three chest leads. This architecture was proposed as the foundation for a wearable system that could record a limited number of ECG leads while also providing a 12-lead ECG for clinical applications.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (1) , 162-172
ECG Statement Classification and Lead Reconstruction Using CNN-Based Models
ECG is an essential diagnostic tool that offers important insight into a person's cardiac and general health. The rise of intelligent wearable devices has opened a new avenue for clinicians and individuals to capture long term ECG data-albeit with fewer leads than the 12 leads that are typically used clinically, which can be vital for identifying and addressing health concerns. In this work, a multi-task convolutional neural network (CNN) classifier was used to study the influence of various combinations of ECG leads in interpretation of 71 cardiac statements spanning cardiac diagnostics, form, and rhythm. Results of this analysis suggest that the subset of limb leads I and II and chest leads V1, V3, and V6 can be used to identify several cardiac statements without loss of performance (average macro AUC of 0.903) when compared to a model trained using all 12- leads (average macro AUC of 0.905; p = 1). A hybrid CNNLSTM (long short-term memory) model was developed to reconstruct the missing chest leads. The highest performing lead reconstructor achieved an average R2 score of 0.835 when reconstructing three chest leads. This architecture was proposed as the foundation for a wearable system that could record a limited number of ECG leads while also providing a 12-lead ECG for clinical applications.
- 1 December 2025
- Published by Elsevier in Journal of Electromyography and Kinesiology
- Vol. 86, 103097
Machine learning-based estimation of EMG baseline noise standard deviation without rest trials
- 1 December 2025
- Published by Elsevier in Journal of Electromyography and Kinesiology
- Vol. 86, 103097
Machine learning-based estimation of EMG baseline noise standard deviation without rest trials
- Open Access
- 11 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 423-426
Dataset: A Novel Aliasing vs Non Aliasing Audio Dataset for Always-On IoT Microphone Experimentation
- 11 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 423-426
Open AccessDataset: A Novel Aliasing vs Non Aliasing Audio Dataset for Always-On IoT Microphone Experimentation
- Open Access
- 11 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 262-265
EfficientMic: Adaptive Acoustic Sensing with a Single Microphone for Smart Infrastructure
- 11 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 262-265
Open AccessEfficientMic: Adaptive Acoustic Sensing with a Single Microphone for Smart Infrastructure
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 893-899
LLaSA: A Sensor-Aware LLM for Natural Language Reasoning of Human Activity from IMU Data
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 893-899
Open AccessLLaSA: A Sensor-Aware LLM for Natural Language Reasoning of Human Activity from IMU Data
- Open Access
OWL: Geometry-Aware Spatial Reasoning for Audio Large Language Models
Spatial reasoning is fundamental to auditory perception, yet current audio large language models (ALLMs) largely rely on unstructured binaural cues and single step inference. This limits both perceptual accuracy in direction and distance estimation and the capacity for interpretable reasoning. Recent work such as BAT demonstrates spatial QA with binaural audio, but its reliance on coarse categorical labels (left, right, up, down) and the absence of explicit geometric supervision constrain resolution and robustness. We introduce the $\textbf{Spatial-Acoustic Geometry Encoder (SAGE}$), a geometry-aware audio encoder that aligns binaural acoustic features with 3D spatial structure using panoramic depth images and room-impulse responses at training time, while requiring only audio at inference. Building on this representation, we present $\textbf{OWL}$, an ALLM that integrates $\textbf{SAGE}$ with a spatially grounded chain-of-thought to rationalize over direction-of-arrivals (DoA) and distance estimates. Through curriculum learning from perceptual QA to multi-step reasoning, $\textbf{OWL}$ supports o'clock-level azimuth and DoA estimation. To enable large-scale training and evaluation, we construct and release $\textbf{BiDepth}$, a dataset of over one million QA pairs combining binaural audio with panoramic depth images and room impulse responses across both in-room and out-of-room scenarios. Across two benchmark datasets, our new $\textbf{BiDepth}$ and the public SpatialSoundQA, $\textbf{OWL}$ reduces mean DoA error by $\textbf{11$^{\circ}$}$ through $\textbf{SAGE}$ and improves spatial reasoning QA accuracy by up to $\textbf{25}$\% over BAT.Open AccessOWL: Geometry-Aware Spatial Reasoning for Audio Large Language Models
Spatial reasoning is fundamental to auditory perception, yet current audio large language models (ALLMs) largely rely on unstructured binaural cues and single step inference. This limits both perceptual accuracy in direction and distance estimation and the capacity for interpretable reasoning. Recent work such as BAT demonstrates spatial QA with binaural audio, but its reliance on coarse categorical labels (left, right, up, down) and the absence of explicit geometric supervision constrain resolution and robustness. We introduce the $\textbf{Spatial-Acoustic Geometry Encoder (SAGE}$), a geometry-aware audio encoder that aligns binaural acoustic features with 3D spatial structure using panoramic depth images and room-impulse responses at training time, while requiring only audio at inference. Building on this representation, we present $\textbf{OWL}$, an ALLM that integrates $\textbf{SAGE}$ with a spatially grounded chain-of-thought to rationalize over direction-of-arrivals (DoA) and distance estimates. Through curriculum learning from perceptual QA to multi-step reasoning, $\textbf{OWL}$ supports o'clock-level azimuth and DoA estimation. To enable large-scale training and evaluation, we construct and release $\textbf{BiDepth}$, a dataset of over one million QA pairs combining binaural audio with panoramic depth images and room impulse responses across both in-room and out-of-room scenarios. Across two benchmark datasets, our new $\textbf{BiDepth}$ and the public SpatialSoundQA, $\textbf{OWL}$ reduces mean DoA error by $\textbf{11$^{\circ}$}$ through $\textbf{SAGE}$ and improves spatial reasoning QA accuracy by up to $\textbf{25}$\% over BAT. - Open Access
- 3 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (3) , 1-32
Mindfulness Meditation and Respiration: Accelerometer-based Respiration Rate and Mindfulness Progress Estimation to Enhance App Engagement and Mindfulness Skills
Mindfulness training is widely recognized for its benefits in reducing depression, anxiety, and loneliness. With the rise of smartphone-based mindfulness apps, digital meditation has become more accessible, but sustaining long-term user engagement remains a challenge. This paper explores whether respiration biosignal feedback and mindfulness skill estimation enhance system usability and skill development. We develop a smartphone's accelerometer-based respiration tracking algorithm, eliminating the need for additional wearables. Unlike existing methods, our approach accurately captures slow breathing patterns typical of mindfulness meditation. Additionally, we introduce the first quantitative framework to estimate mindfulness skills---concentration, sensory clarity, and equanimity---based on accelerometer-derived respiration data. We develop and test our algorithms on 261 mindfulness sessions in both controlled and real-world settings. A user study comparing an experimental group receiving biosignal feedback with a control group using a standard app shows that respiration feedback enhances system usability. Our respiration tracking model achieves a mean absolute error (MAE) of 1.6 breaths per minute, closely aligning with ground truth data, while our mindfulness skill estimation attains F1 scores of 80-84% in tracking skill progression. By integrating respiration tracking and mindfulness estimation into a commercial app, we demonstrate the potential of smartphone sensors to enhance digital mindfulness training.
- 3 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (3) , 1-32
Open AccessMindfulness Meditation and Respiration: Accelerometer-based Respiration Rate and Mindfulness Progress Estimation to Enhance App Engagement and Mindfulness Skills
Mindfulness training is widely recognized for its benefits in reducing depression, anxiety, and loneliness. With the rise of smartphone-based mindfulness apps, digital meditation has become more accessible, but sustaining long-term user engagement remains a challenge. This paper explores whether respiration biosignal feedback and mindfulness skill estimation enhance system usability and skill development. We develop a smartphone's accelerometer-based respiration tracking algorithm, eliminating the need for additional wearables. Unlike existing methods, our approach accurately captures slow breathing patterns typical of mindfulness meditation. Additionally, we introduce the first quantitative framework to estimate mindfulness skills---concentration, sensory clarity, and equanimity---based on accelerometer-derived respiration data. We develop and test our algorithms on 261 mindfulness sessions in both controlled and real-world settings. A user study comparing an experimental group receiving biosignal feedback with a control group using a standard app shows that respiration feedback enhances system usability. Our respiration tracking model achieves a mean absolute error (MAE) of 1.6 breaths per minute, closely aligning with ground truth data, while our mindfulness skill estimation attains F1 scores of 80-84% in tracking skill progression. By integrating respiration tracking and mindfulness estimation into a commercial app, we demonstrate the potential of smartphone sensors to enhance digital mindfulness training.
- Open Access
UnIT: Scalable Unstructured Inference-Time Pruning for MAC-efficient Neural Inference on MCUs
Existing pruning methods are typically applied during training or compile time and often rely on structured sparsity. While compatible with low-power microcontrollers (MCUs), structured pruning underutilizes the opportunity for fine-grained efficiency on devices without SIMD support or parallel compute. To address these limitations, we introduce UnIT (Unstructured Inference-Time pruning), a lightweight method that dynamically identifies and skips unnecessary multiply-accumulate (MAC) operations during inference, guided by input-specific activation patterns. Unlike structured pruning, UnIT embraces irregular sparsity and does not require retraining or hardware specialization. It transforms pruning decisions into lightweight comparisons, replacing multiplications with threshold checks and approximated divisions. UnIT further optimizes compute by reusing threshold computations across multiple connections and applying layer- and group-specific pruning sensitivity. We present three fast, hardware-friendly division approximations tailored to the capabilities of common embedded platforms. Demonstrated on the MSP430 microcontroller, UnIT achieves 11.02% to 82.03% MAC reduction, 27.30% to 84.19% faster inference, and 27.33% to 84.38% lower energy consumption compared to training-time pruned models, while maintaining accuracy with 0.48-7%. Under domain shift, UnIT matches or exceeds the accuracy of retrained models while requiring significantly fewer MACs. These results establish unstructured inference-time pruning as a viable and practical solution for efficient, retraining-free deployment of deep neural networks on MCUs.
Open AccessUnIT: Scalable Unstructured Inference-Time Pruning for MAC-efficient Neural Inference on MCUs
Existing pruning methods are typically applied during training or compile time and often rely on structured sparsity. While compatible with low-power microcontrollers (MCUs), structured pruning underutilizes the opportunity for fine-grained efficiency on devices without SIMD support or parallel compute. To address these limitations, we introduce UnIT (Unstructured Inference-Time pruning), a lightweight method that dynamically identifies and skips unnecessary multiply-accumulate (MAC) operations during inference, guided by input-specific activation patterns. Unlike structured pruning, UnIT embraces irregular sparsity and does not require retraining or hardware specialization. It transforms pruning decisions into lightweight comparisons, replacing multiplications with threshold checks and approximated divisions. UnIT further optimizes compute by reusing threshold computations across multiple connections and applying layer- and group-specific pruning sensitivity. We present three fast, hardware-friendly division approximations tailored to the capabilities of common embedded platforms. Demonstrated on the MSP430 microcontroller, UnIT achieves 11.02% to 82.03% MAC reduction, 27.30% to 84.19% faster inference, and 27.33% to 84.38% lower energy consumption compared to training-time pruned models, while maintaining accuracy with 0.48-7%. Under domain shift, UnIT matches or exceeds the accuracy of retrained models while requiring significantly fewer MACs. These results establish unstructured inference-time pruning as a viable and practical solution for efficient, retraining-free deployment of deep neural networks on MCUs.