Garvit Chugh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Garvit Chugh has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Suchetana Chakraborty
Computer Science and Engineering, Indian Institute of Technology Jodhpur
6 shared publications - Sandip Chakraborty
IIT Kharagpur, Kharagpur, West Bengal, India
5 shared publications - Nirmalya Roy
Information Systems, University of Maryland Baltimore County, Baltimore, MD, USA
4 shared publications - Indrajeet Ghosh
Department of Information Systems , USA and Center for Real-time Distributed Sensing and Autonomy (CARDS), University of Maryland Baltimore County, USA
3 shared publications Indrajeet Ghosh
2 shared publications- Ravi Bhandari
Department of Electrical and Computer Science Engineering, Institute of Infrastructure Technology Research and Management, Ahmedabad, India
2 shared publications
Latest Publications
- Open Access
- 5 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
Real-time Recognition of Contextual Composite Activities from Asynchronous Multi-IMU Sensor Streams
Human Activity Recognition (HAR) is foundational to intelligent systems delivering personalized healthcare and wellbeing services. Wearable devices equipped with inertial measurement units (IMUs), such as smartwatches and earables, have enabled non-intrusive recognition of motion-driven activities. However, real-time recognition of contextual composite activities – temporally overlapping actions initiated by distinct body parts – remains challenging due to asynchronous multi-IMU data streams, where data collected from multiple IMU-enabled wearable devices may exhibit heterogeneous sampling rates, independent device clocks, and communication delays, resulting in temporally misaligned sensor readings, variability in sensor quality, and limited contextual cues from low-resolution streaming data. To address these challenges, we propose Multisource Self-Supervised Learning (MSSL), a lightweight framework that exploits unlabeled multisource-IMU data to enhance composite activity recognition in real time. MSSL incorporates (1) a dynamic source selection mechanism leveraging probability density estimation to adaptively identify primary and auxiliary sensor sources, and (2) a multimodal contrastive learning strategy to improve feature representations across heterogeneous sensor modalities. Evaluations on an in-house dataset and four benchmark HAR datasets demonstrate that MSSL achieves (i) 95.26% accuracy on our in-house composite activity dataset, (ii) 85.93% on PAMAP2-ADL, (iii) 80.08% on Opportunity, (iv) 91.18% on RealDisp, and (v) 69.41% on PAMAP2-Locomotions. Notably, MSSL maintains robust performance even with only 10% labeled data (78.05% accuracy) while achieving low inference latency of 0.6328 milliseconds. These results underscore MSSL’s potential for reliable, context-aware composite activity recognition in real-time applications, paving the way for more responsive and personalized services.
- 5 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
Open AccessReal-time Recognition of Contextual Composite Activities from Asynchronous Multi-IMU Sensor Streams
Human Activity Recognition (HAR) is foundational to intelligent systems delivering personalized healthcare and wellbeing services. Wearable devices equipped with inertial measurement units (IMUs), such as smartwatches and earables, have enabled non-intrusive recognition of motion-driven activities. However, real-time recognition of contextual composite activities – temporally overlapping actions initiated by distinct body parts – remains challenging due to asynchronous multi-IMU data streams, where data collected from multiple IMU-enabled wearable devices may exhibit heterogeneous sampling rates, independent device clocks, and communication delays, resulting in temporally misaligned sensor readings, variability in sensor quality, and limited contextual cues from low-resolution streaming data. To address these challenges, we propose Multisource Self-Supervised Learning (MSSL), a lightweight framework that exploits unlabeled multisource-IMU data to enhance composite activity recognition in real time. MSSL incorporates (1) a dynamic source selection mechanism leveraging probability density estimation to adaptively identify primary and auxiliary sensor sources, and (2) a multimodal contrastive learning strategy to improve feature representations across heterogeneous sensor modalities. Evaluations on an in-house dataset and four benchmark HAR datasets demonstrate that MSSL achieves (i) 95.26% accuracy on our in-house composite activity dataset, (ii) 85.93% on PAMAP2-ADL, (iii) 80.08% on Opportunity, (iv) 91.18% on RealDisp, and (v) 69.41% on PAMAP2-Locomotions. Notably, MSSL maintains robust performance even with only 10% labeled data (78.05% accuracy) while achieving low inference latency of 0.6328 milliseconds. These results underscore MSSL’s potential for reliable, context-aware composite activity recognition in real-time applications, paving the way for more responsive and personalized services.
- 27 October 2026
- Published by Elsevier in Pervasive and Mobile Computing
- Vol. 124
An evaluation of earable-based inertial sensing for understanding eating behaviour
- 27 October 2026
- Published by Elsevier in Pervasive and Mobile Computing
- Vol. 124
An evaluation of earable-based inertial sensing for understanding eating behaviour
- Open Access
- 29 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (4) , 1-42
SpineSense: An Interactive System for Cervical Spine Monitoring and Clinician-Oriented Summaries using COTS Earables EICS005
We present SpineSense , an interactive earable-based framework for continuous monitoring of cervical spine posture and discomfort-related behavior in daily life. Leveraging inertial data from commercial off-the-shelf (COTS) earables (e.g., Apple AirPods Pro 2), SpineSense models the cervical vertebral chain (C1–C7) using SLERP-interpolated quaternions to estimate craniovertebral (CV) angles and identify early pain-relief gestures (e.g., neck rubbing, circular head rolls) that are associated with early signs of musculoskeletal fatigue, as informed by clinical observation. A real-time feedback loop delivers posture-based alerts and weekly compliance summaries to support user awareness and long-term posture correction. Central to our design is a clinician-in-the-loop methodology: clinical experts (including orthopedic surgeons and physiotherapists) informed threshold selection (e.g., CV angle cutoffs), interpreted common discomfort behaviors, and iteratively guided the structure of weekly feedback reports. We evaluate the system on 20 participants and achieve low spine angle estimation error (MAE: 0.876° , RMSE: 1.02° , r = 0.95), and discomfort gesture classification accuracy of F 1 = 0.97. Usability studies across diverse activities show high acceptance (SUS = 84.75, NASA-TLX = 32.7, PSSUQ = 2.13), with formal ANOVA tests validating statistically significant improvements over baseline interfaces. Together, our findings establish the feasibility of engineering interactive cervical health systems using COTS earables that support real-time feedback, clinician-informed reporting, and pervasive deployment in naturalistic settings.
- 29 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (4) , 1-42
Open AccessSpineSense: An Interactive System for Cervical Spine Monitoring and Clinician-Oriented Summaries using COTS Earables EICS005
We present SpineSense , an interactive earable-based framework for continuous monitoring of cervical spine posture and discomfort-related behavior in daily life. Leveraging inertial data from commercial off-the-shelf (COTS) earables (e.g., Apple AirPods Pro 2), SpineSense models the cervical vertebral chain (C1–C7) using SLERP-interpolated quaternions to estimate craniovertebral (CV) angles and identify early pain-relief gestures (e.g., neck rubbing, circular head rolls) that are associated with early signs of musculoskeletal fatigue, as informed by clinical observation. A real-time feedback loop delivers posture-based alerts and weekly compliance summaries to support user awareness and long-term posture correction. Central to our design is a clinician-in-the-loop methodology: clinical experts (including orthopedic surgeons and physiotherapists) informed threshold selection (e.g., CV angle cutoffs), interpreted common discomfort behaviors, and iteratively guided the structure of weekly feedback reports. We evaluate the system on 20 participants and achieve low spine angle estimation error (MAE: 0.876° , RMSE: 1.02° , r = 0.95), and discomfort gesture classification accuracy of F 1 = 0.97. Usability studies across diverse activities show high acceptance (SUS = 84.75, NASA-TLX = 32.7, PSSUQ = 2.13), with formal ANOVA tests validating statistically significant improvements over baseline interfaces. Together, our findings establish the feasibility of engineering interactive cervical health systems using COTS earables that support real-time feedback, clinician-informed reporting, and pervasive deployment in naturalistic settings.
- Open Access
- 10 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 622-635
WristSense: Sensing Hidden Wrist Strain in Routine Activities via Inertial Tokenization and LLM-Based Feedback
Wrist micro-behaviors during daily activities such as typing, handwriting, cooking, or carrying objects are valuable indicators for early detection of wrist disorders like Carpal Tunnel Syndrome and tendonitis. However, continuous personalized monitoring remains challenging without intrusive setups or hand-crafted rules. We present WristSense, a real-time, wrist-worn sensing system that introduces: (i) a magnetometer-stabilized quaternion fusion pipeline for orientation-agnostic tracking, (ii) a lightweight 1D-CNN + HMM model to distinguish functional gestures from strain-related coping behaviors, and (iii) an inertial tokenization scheme that converts events into structured prompts for a pretrained LLM. This enables zero-shot ergonomic feedback without per-user calibration. Evaluations across 12 participants show accurate posture tracking (< 10° MAE), high gesture recognition (macro F1 = 0.91), and improved usability (SUS = 85.2), with significantly higher user compliance compared to rule-based methods. WristSense demonstrates the potential of combining inertial sensing with LLMs for scalable, personalized ergonomic monitoring and early intervention.
- 10 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 622-635
Open AccessWristSense: Sensing Hidden Wrist Strain in Routine Activities via Inertial Tokenization and LLM-Based Feedback
Wrist micro-behaviors during daily activities such as typing, handwriting, cooking, or carrying objects are valuable indicators for early detection of wrist disorders like Carpal Tunnel Syndrome and tendonitis. However, continuous personalized monitoring remains challenging without intrusive setups or hand-crafted rules. We present WristSense, a real-time, wrist-worn sensing system that introduces: (i) a magnetometer-stabilized quaternion fusion pipeline for orientation-agnostic tracking, (ii) a lightweight 1D-CNN + HMM model to distinguish functional gestures from strain-related coping behaviors, and (iii) an inertial tokenization scheme that converts events into structured prompts for a pretrained LLM. This enables zero-shot ergonomic feedback without per-user calibration. Evaluations across 12 participants show accurate posture tracking (< 10° MAE), high gesture recognition (macro F1 = 0.91), and improved usability (SUS = 85.2), with significantly higher user compliance compared to rule-based methods. WristSense demonstrates the potential of combining inertial sensing with LLMs for scalable, personalized ergonomic monitoring and early intervention.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
MorsEar: Toward Generalizable Low-Resource Covert Messaging via Earable based Inertial Sensing
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessMorsEar: Toward Generalizable Low-Resource Covert Messaging via Earable based Inertial Sensing
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 718-728
High-Order Moments Conditional Domain Adaptation Networks for Wearable Human Activity Recognition
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 718-728
Open AccessHigh-Order Moments Conditional Domain Adaptation Networks for Wearable Human Activity Recognition
- Open Access
- 18 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 142-151
β-Decode: Attention-based Decoding Temporal Artifacts via Unsupervised β-Variational Autoencoder
- 18 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 142-151
Open Accessβ-Decode: Attention-based Decoding Temporal Artifacts via Unsupervised β-Variational Autoencoder
- Open Access
Unsupervised Domain Adaptation for Action Recognition via Self-Ensembling and Conditional Embedding Alignment
Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions, but adoption remains limited due to the lack of expert annotations and domain discrepancies from user variations. Limited annotations hinder the model's ability to generalize to out-of-distribution samples. While data augmentation can improve generalizability, unsupervised augmentation techniques must be applied carefully to avoid introducing noise. Unsupervised domain adaptation (UDA) addresses domain discrepancies by aligning conditional distributions with labeled target samples, but vanilla pseudo-labeling can lead to error propagation. To address these challenges, we propose $μ$DAR, a novel joint optimization architecture comprised of three functions: (i) consistency regularizer between augmented samples to improve model classification generalizability, (ii) temporal ensemble for robust pseudo-label generation and (iii) conditional distribution alignment to improve domain generalizability. The temporal ensemble works by aggregating predictions from past epochs to smooth out noisy pseudo-label predictions, which are then used in the conditional distribution alignment module to minimize kernel-based class-wise conditional maximum mean discrepancy ($k$CMMD) between the source and target feature space to learn a domain invariant embedding. The consistency-regularized augmentations ensure that multiple augmentations of the same sample share the same labels; this results in (a) strong generalization with limited source domain samples and (b) consistent pseudo-label generation in target samples. The novel integration of these three modules in $μ$DAR results in a range of $\approx$ 4-12% average macro-F1 score improvement over six state-of-the-art UDA methods in four benchmark wHAR datasetsOpen AccessUnsupervised Domain Adaptation for Action Recognition via Self-Ensembling and Conditional Embedding Alignment
Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions, but adoption remains limited due to the lack of expert annotations and domain discrepancies from user variations. Limited annotations hinder the model's ability to generalize to out-of-distribution samples. While data augmentation can improve generalizability, unsupervised augmentation techniques must be applied carefully to avoid introducing noise. Unsupervised domain adaptation (UDA) addresses domain discrepancies by aligning conditional distributions with labeled target samples, but vanilla pseudo-labeling can lead to error propagation. To address these challenges, we propose $μ$DAR, a novel joint optimization architecture comprised of three functions: (i) consistency regularizer between augmented samples to improve model classification generalizability, (ii) temporal ensemble for robust pseudo-label generation and (iii) conditional distribution alignment to improve domain generalizability. The temporal ensemble works by aggregating predictions from past epochs to smooth out noisy pseudo-label predictions, which are then used in the conditional distribution alignment module to minimize kernel-based class-wise conditional maximum mean discrepancy ($k$CMMD) between the source and target feature space to learn a domain invariant embedding. The consistency-regularized augmentations ensure that multiple augmentations of the same sample share the same labels; this results in (a) strong generalization with limited source domain samples and (b) consistent pseudo-label generation in target samples. The novel integration of these three modules in $μ$DAR results in a range of $\approx$ 4-12% average macro-F1 score improvement over six state-of-the-art UDA methods in four benchmark wHAR datasets - Open Access
- 21 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 126-137
Exploring Earables to Monitor Temporal Lack of Focus during Online Meetings to Identify Onset of Neurological Disorders
This paper presents a framework called enGauge that leverages ear-based inertial sensing to continuously monitor listener focus levels in online meetings and provide feedback to the speaker about audience engagement. This allows for the identification of the onset of several neurodevelopmental disorders, including attention deficit hyperactivity disorder (ADHD), and can help to improve the effectiveness of online meetings by allowing speakers to adjust their speaking pace and style based on audience engagement. We explore a contrastive learning-based approach coupled with a judicial selection of anchor events from the meeting contents to model the system. enGauge can detect patterns or shifts in behavior and focus levels of passive listeners to accurately identify changes in focus. Results from a user study with 38 participants showed an overall F1-score of 0.89 for detecting passive listeners' focus levels. Our study suggests that ear-based inertial sensing has the potential to be a valuable tool for the early detection and monitoring of several neurodevelopmental disorders among individuals.
- 21 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 126-137
Open AccessExploring Earables to Monitor Temporal Lack of Focus during Online Meetings to Identify Onset of Neurological Disorders
This paper presents a framework called enGauge that leverages ear-based inertial sensing to continuously monitor listener focus levels in online meetings and provide feedback to the speaker about audience engagement. This allows for the identification of the onset of several neurodevelopmental disorders, including attention deficit hyperactivity disorder (ADHD), and can help to improve the effectiveness of online meetings by allowing speakers to adjust their speaking pace and style based on audience engagement. We explore a contrastive learning-based approach coupled with a judicial selection of anchor events from the meeting contents to model the system. enGauge can detect patterns or shifts in behavior and focus levels of passive listeners to accurately identify changes in focus. Results from a user study with 38 participants showed an overall F1-score of 0.89 for detecting passive listeners' focus levels. Our study suggests that ear-based inertial sensing has the potential to be a valuable tool for the early detection and monitoring of several neurodevelopmental disorders among individuals.
- Open Access
- 11 September 2022
- Published by Association for Computing Machinery (ACM)
- p. 236-241
enVolve: Are You Listening? Inertial Sensing to Monitor the Involvement of Silent Listeners during an Online Interaction
Understanding the level of participation for a remote attendee in an online meeting setup could significantly improve the quality of experience for virtual interaction. However, gauging audience involvement over an online meeting becomes particularly challenging when the attendees prefer to turn off the cameras. IMU data have shown promising results in the past to pervasively monitor users’ body language, including the determination of various bodily gestures, postures, and facial expressions. This paper demonstrates how earables could help address the stated problem. We provide a motivational study to assess earables for detecting body language corresponding to involved listeners. We further compare it with other sensing modalities like smartwatches and smartphones and accordingly develop a platform called enVolve. A lab-scale study with 17 participants demonstrates the efficacy of the proposed system with an average F1 score of more than .
- 11 September 2022
- Published by Association for Computing Machinery (ACM)
- p. 236-241
Open AccessenVolve: Are You Listening? Inertial Sensing to Monitor the Involvement of Silent Listeners during an Online Interaction
Understanding the level of participation for a remote attendee in an online meeting setup could significantly improve the quality of experience for virtual interaction. However, gauging audience involvement over an online meeting becomes particularly challenging when the attendees prefer to turn off the cameras. IMU data have shown promising results in the past to pervasively monitor users’ body language, including the determination of various bodily gestures, postures, and facial expressions. This paper demonstrates how earables could help address the stated problem. We provide a motivational study to assess earables for detecting body language corresponding to involved listeners. We further compare it with other sensing modalities like smartwatches and smartphones and accordingly develop a platform called enVolve. A lab-scale study with 17 participants demonstrates the efficacy of the proposed system with an average F1 score of more than .