Avik Ghose
Avik Ghose has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Shalini Mukhopadhyay
TCS Research, Kolkata, India
5 shared publications - Swarnava Dey
TCS Research, Tata Consultancy Services Limited, Kolkata, India
5 shared publications - Aniruddha Sinha
Tata Consultancy Services Ltd
4 shared publications - Chirabrata Bhaumik
TCS Research
3 shared publications - Varsha Sharma
TCS Research, Kolkata, India
3 shared publications - Vivek Chandel
TCS Research, Gurugram, IN
3 shared publications
Latest Publications
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 130-135
Estimation and Localization of Chronic Pain level from EEG Signals
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 130-135
Open AccessEstimation and Localization of Chronic Pain level from EEG Signals
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 887-888
Demo: Smartwatch-Driven Gaming for Stroke Rehabilitation
Patients surviving a brain stroke often experience an impaired neuro-motor coordination and cognitive capability. Rehabilitation assisted by therapists can help them regain much of this coordination. In recent past, gamified activities have proved to be effective in this regard with enhanced patient engagement. But, they may require special hardware and certain usage restrictions regarding patient's positioning etc. for operating effectively. We have set out to develop a suite of games using a smartwatch to sense arm's motion to eliminate such challenges, supporting customized scoring for different post-stroke mobility stages and focusing on state-of-the-art 3D graphics offering a high realism aimed at better patient engagement and adherence. In this demonstration, we present two of these games. First is a 'Forest Stroll' game where the patient controls heading of an in-game character moving on a forest path, with scoring based on how closely the path is followed, with a few additional arm gestures which can be activated by the therapist optionally. Second is a 'Drumming' game, where the patient controls a virtual drumstick and tries to play a customizable pre-saved pattern involving multiple ranges of motion, scored on how closely the pattern is played, testing both motor and cognitive capabilities.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 887-888
Open AccessDemo: Smartwatch-Driven Gaming for Stroke Rehabilitation
Patients surviving a brain stroke often experience an impaired neuro-motor coordination and cognitive capability. Rehabilitation assisted by therapists can help them regain much of this coordination. In recent past, gamified activities have proved to be effective in this regard with enhanced patient engagement. But, they may require special hardware and certain usage restrictions regarding patient's positioning etc. for operating effectively. We have set out to develop a suite of games using a smartwatch to sense arm's motion to eliminate such challenges, supporting customized scoring for different post-stroke mobility stages and focusing on state-of-the-art 3D graphics offering a high realism aimed at better patient engagement and adherence. In this demonstration, we present two of these games. First is a 'Forest Stroll' game where the patient controls heading of an in-game character moving on a forest path, with scoring based on how closely the path is followed, with a few additional arm gestures which can be activated by the therapist optionally. Second is a 'Drumming' game, where the patient controls a virtual drumstick and tries to play a customizable pre-saved pattern involving multiple ranges of motion, scored on how closely the pattern is played, testing both motor and cognitive capabilities.
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 27-28
Enhancing Parkinson's Disease Management through Automatic Personalized Assistive Systems
As the global population ages, chronic diseases such as Parkinson's disease (PD) are on the rise, placing significant strain on healthcare systems. This paper presents a conceptual framework for automatic personalized assistive systems---integrating wearable sensors, mobile apps, and machine learning---to enhance PD management. These systems aim to deliver real-time interventions and tailored treatment plans to address the complex symptoms of PD. Successfully addressing challenges such as user acceptance and technical reliability could improve patients' quality of life and alleviate healthcare burdens.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 27-28
Open AccessEnhancing Parkinson's Disease Management through Automatic Personalized Assistive Systems
As the global population ages, chronic diseases such as Parkinson's disease (PD) are on the rise, placing significant strain on healthcare systems. This paper presents a conceptual framework for automatic personalized assistive systems---integrating wearable sensors, mobile apps, and machine learning---to enhance PD management. These systems aim to deliver real-time interventions and tailored treatment plans to address the complex symptoms of PD. Successfully addressing challenges such as user acceptance and technical reliability could improve patients' quality of life and alleviate healthcare burdens.
- Open Access
- 5 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 430-436
TinyStressNAS: Automated Feature Selection and Model Generation for On-device Stress Detection
Over the past decades, Electrodermal Activity (EDA)-based stress detection systems have observed increasing interest due to the significant impact of stress on daily life and the need for continuous, unobtrusive monitoring. The wearable form-factor and the unobtrusive nature of the EDA sensor make it highly suitable for this purpose. Many researchers have focused on developing EDA-based stress detection techniques, but few consider the resource footprint of such systems. Maintaining a good trade-off by manual optimization is a challenging task. Automation techniques can be very helpful in such scenarios. In this work, we introduce a novel method for the selection of an optimal feature subset, utilizing a deep Reinforcement Learning (RL) network on top of a Neural Architecture Search (NAS) framework to design tiny, customized models for on-device stress detection. The feature subset selection uses a multi-metric reward objective function to balance feature accuracy contributions against computational complexity, identifying the optimal feature subset. Initial analysis indicates that this optimal subset enhances accuracy while keeping the model size under 100 kB and minimally increasing computation.
- 5 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 430-436
Open AccessTinyStressNAS: Automated Feature Selection and Model Generation for On-device Stress Detection
Over the past decades, Electrodermal Activity (EDA)-based stress detection systems have observed increasing interest due to the significant impact of stress on daily life and the need for continuous, unobtrusive monitoring. The wearable form-factor and the unobtrusive nature of the EDA sensor make it highly suitable for this purpose. Many researchers have focused on developing EDA-based stress detection techniques, but few consider the resource footprint of such systems. Maintaining a good trade-off by manual optimization is a challenging task. Automation techniques can be very helpful in such scenarios. In this work, we introduce a novel method for the selection of an optimal feature subset, utilizing a deep Reinforcement Learning (RL) network on top of a Neural Architecture Search (NAS) framework to design tiny, customized models for on-device stress detection. The feature subset selection uses a multi-metric reward objective function to balance feature accuracy contributions against computational complexity, identifying the optimal feature subset. Initial analysis indicates that this optimal subset enhances accuracy while keeping the model size under 100 kB and minimally increasing computation.
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 598-599
Demo: Stress Detection on Tiny Edge Device with GSR Sensor
Stress management is paramount to maintaining optimal health and well-being; stress builds up in spikes, causing problems like hypertension and anxiety, necessitating personalized interventions delivered in real-time through wearable technology. This work underscores the pivotal role of unobtrusive stress detection and presents the development of auto-generated compact models tailored for on-device inference through Neural Architecture Search (NAS). These models aim to facilitate efficient stress monitoring directly on low-power devices, representing a promising avenue for advancing personalized healthcare with continuous monitoring and effective digital interventions.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 598-599
Open AccessDemo: Stress Detection on Tiny Edge Device with GSR Sensor
Stress management is paramount to maintaining optimal health and well-being; stress builds up in spikes, causing problems like hypertension and anxiety, necessitating personalized interventions delivered in real-time through wearable technology. This work underscores the pivotal role of unobtrusive stress detection and presents the development of auto-generated compact models tailored for on-device inference through Neural Architecture Search (NAS). These models aim to facilitate efficient stress monitoring directly on low-power devices, representing a promising avenue for advancing personalized healthcare with continuous monitoring and effective digital interventions.
- Open Access
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 494-495
Demo Abstract: Atrial Fibrillation Burden Computation from Single-Lead ECG on Device | Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems
Atrial Fibrillation (AF) is a common cardiac arrhythmia with significant health implications. To evaluate the severity of AF and monitor the effectiveness of treatments, continuous measurement of AF Burden (AFB) is crucial. This demo showcases a cost-effective, portable, and user-friendly solution for AFB monitoring. Our system integrates the Arduino Nano 33 BLE sense board with the AD8232 sensor to reliably capture single-lead ECG data. Additionally, a custom algorithm computes real-time AFB, providing insights into the frequency and duration of AF episodes. This system has the potential to enhance AF management and patient care, making cardiac health monitoring more accessible.
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 494-495
Open AccessDemo Abstract: Atrial Fibrillation Burden Computation from Single-Lead ECG on Device | Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems
Atrial Fibrillation (AF) is a common cardiac arrhythmia with significant health implications. To evaluate the severity of AF and monitor the effectiveness of treatments, continuous measurement of AF Burden (AFB) is crucial. This demo showcases a cost-effective, portable, and user-friendly solution for AFB monitoring. Our system integrates the Arduino Nano 33 BLE sense board with the AD8232 sensor to reliably capture single-lead ECG data. Additionally, a custom algorithm computes real-time AFB, providing insights into the frequency and duration of AF episodes. This system has the potential to enhance AF management and patient care, making cardiac health monitoring more accessible.
- Open Access
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 7-12
TinyPuff: Automated design of Tiny Smoking Puff Classifiers for Body Worn Devices
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 7-12
Open AccessTinyPuff: Automated design of Tiny Smoking Puff Classifiers for Body Worn Devices
- Open Access
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 586-587
Demo: On-device Puff Detection System for Smoking Cessation
Customized, on-device applications that provide timely interventions about smoking episodes are very helpful for smoking cessation. For this, real-time detection of smoking puffs are necessary through unobtrusive wearable devices. This work demonstrates auto-generated tiny puff detection models for on-device inference on low-power wearable devices.
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 586-587
Open AccessDemo: On-device Puff Detection System for Smoking Cessation
Customized, on-device applications that provide timely interventions about smoking episodes are very helpful for smoking cessation. For this, real-time detection of smoking puffs are necessary through unobtrusive wearable devices. This work demonstrates auto-generated tiny puff detection models for on-device inference on low-power wearable devices.
- Open Access
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 19-24
Imputation of Human Mobility Data for Comprehensive Risk Models
Sensor-equipped wearable devices are becoming increasingly popular in the healthcare industry, with some equipped with GPS and Proximity sensors as well. Raw (GPS) trajectories obtained through human-centric systems like body worn senors, and enriched with semantic annotations generate huge actionable insights for downstream domain specific applications like epidemic risk modeling. However, trajectory data suffer from missing data problem owing to various technical as well as behavioral factors. Our paper shows that, for a semantic trajectory dataset and using coarse grain semantic location for both prediction and imputation purposes, a simple ensemble classifier-based model can outperform the existing deep models where trajectory imputation is almost real-time delay.
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 19-24
Open AccessImputation of Human Mobility Data for Comprehensive Risk Models
Sensor-equipped wearable devices are becoming increasingly popular in the healthcare industry, with some equipped with GPS and Proximity sensors as well. Raw (GPS) trajectories obtained through human-centric systems like body worn senors, and enriched with semantic annotations generate huge actionable insights for downstream domain specific applications like epidemic risk modeling. However, trajectory data suffer from missing data problem owing to various technical as well as behavioral factors. Our paper shows that, for a semantic trajectory dataset and using coarse grain semantic location for both prediction and imputation purposes, a simple ensemble classifier-based model can outperform the existing deep models where trajectory imputation is almost real-time delay.
- Open Access
ProxiTrak: Intelligent Enablement of Social Distancing & Contact Tracing for a Safer Workplace in the New Normal
This paper describes an innovative solution that enables the enterprises to bring their associates (or employees) back to physical workspaces for critical operations in a safe manner in the wake of current COVID-19 pandemic.
Open AccessProxiTrak: Intelligent Enablement of Social Distancing & Contact Tracing for a Safer Workplace in the New Normal
This paper describes an innovative solution that enables the enterprises to bring their associates (or employees) back to physical workspaces for critical operations in a safe manner in the wake of current COVID-19 pandemic.