Sujit Dey

Sujit Dey

Auto-generated profile, based on publicly available information

Sujit Dey

Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 May 2024 in JMIR Cardio
Verified
Journal Article
Open access
JLJared Leitner
Jared Leitner
PCPo-Han Chiang
Po-Han Chiang
PAParag Agnihotri
Parag Agnihotri
SDSujit Dey
Sujit Dey
Background: Home blood pressure (BP) monitoring with lifestyle coaching is effective in managing hypertension and reducing cardiovascular risk. However, traditional manual lifestyle coaching models significantly limit availability due to high operating costs and personnel requirements. Furthermore, the lack of patient lifestyle monitoring and clinician time constraints can prevent personalized coaching on lifestyle modifications. Objective: This study assesses the effectiveness of a fully digital, autonomous, and artificial intelligence (AI)–based lifestyle coaching program on achieving BP control among adults with hypertension. Methods: Participants were enrolled in a single-arm nonrandomized trial in which they received a BP monitor and wearable activity tracker. Data were collected from these devices and a questionnaire mobile app, which were used to train personalized machine learning models that enabled precision lifestyle coaching delivered to participants via SMS text messaging and a mobile app. The primary outcomes included (1) the changes in systolic and diastolic BP from baseline to 12 and 24 weeks and (2) the percentage change of participants in the controlled, stage-1, and stage-2 hypertension categories from baseline to 12 and 24 weeks. Secondary outcomes included (1) the participant engagement rate as measured by data collection consistency and (2) the number of manual clinician outreaches. Results: In total, 141 participants were monitored over 24 weeks. At 12 weeks, systolic and diastolic BP decreased by 5.6 mm Hg (95% CI −7.1 to −4.2; P<.001) and 3.8 mm Hg (95% CI −4.7 to −2.8; P<.001), respectively. Particularly, for participants starting with stage-2 hypertension, systolic and diastolic BP decreased by 9.6 mm Hg (95% CI −12.2 to −6.9; P<.001) and 5.7 mm Hg (95% CI −7.6 to −3.9; P<.001), respectively. At 24 weeks, systolic and diastolic BP decreased by 8.1 mm Hg (95% CI −10.1 to −6.1; P<.001) and 5.1 mm Hg (95% CI −6.2 to −3.9; P<.001), respectively. For participants starting with stage-2 hypertension, systolic and diastolic BP decreased by 14.2 mm Hg (95% CI −17.7 to −10.7; P<.001) and 8.1 mm Hg (95% CI −10.4 to −5.7; P<.001), respectively, at 24 weeks. The percentage of participants with controlled BP increased by 17.2% (22/128; P<.001) and 26.5% (27/102; P<.001) from baseline to 12 and 24 weeks, respectively. The percentage of participants with stage-2 hypertension decreased by 25% (32/128; P<.001) and 26.5% (27/102; P<.001) from baseline to 12 and 24 weeks, respectively. The average weekly participant engagement rate was 92% (SD 3.9%), and only 5.9% (6/102) of the participants required manual outreach over 24 weeks. Conclusions: The study demonstrates the potential of fully digital, autonomous, and AI-based lifestyle coaching to achieve meaningful BP improvements and high engagement for patients with hypertension while substantially reducing clinician workloads. Trial Registration: ClinicalTrials.gov NCT06337734; https://clinicaltrials.gov/study/NCT06337734

18 March 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
STSamuel Thornton
Samuel Thornton
SDSujit Dey
Sujit Dey
The emergence of edge computing in Intelligent Transportation Systems (ITS) has shown promise in enabling real-time sensor fusion applications. In this paper, we explore how to utilize edge computing to aid in collaborative vehicular perception, an emerging topic within ITS which involves vehicles sharing sensor data with one another to extend each vehicle's perception beyond what its individual sensors can see. However, achieving real time collaborative perception is a challenge even with the utilization of edge computing; due to the large amount of multi-modal sensor data produced by modern intelligent vehicles, the amount of data transmitted over wireless channels and the complexity of computational tasks will need to be managed dynamically based on the wireless network conditions and available computing resources. As such we propose REFO, a Real-time Edge Fusion Optimization method that combines task partitioning with data reduction and model compression to maximize sensor fusion accuracy while adhering to Quality of Service (QoS) requirements. We define a performance metric termed effective mean average precision (EmAP), which incorporates both QoS and fusion accuracy, and show that our proposed neural network based REFO action decision framework can outperform the best comparison models by approximately 10% in terms of EmAP over 18 test combinations of network and computing conditions.

23 September 2024 in IEEE Access
Verified
Journal Article
Open access
JCJianrong Chen
Jianrong Chen
SDSujit Dey
Sujit Dey
LWLei Wang
Lei Wang
NBNing Bi
Ning Bi
PLPeng Liu
Peng Liu
As Advanced Driver Assistance Systems (ADAS) become increasingly intelligent, facial expression recognition (FER) has become a significant requirement for the purpose of monitoring a driver’s emotional state as well as fatigue level. An automobile system with FER is very useful in improving transportation safety by recognizing the driver’s state to provide timely alerts and potentially reduce the likelihood of accidents. While deep neural networks (DNN) based systems have achieved high accuracy in FER in recent years based on data collected under good laboratory environments, recognizing real-world facial expressions remains challenging due to variations in lighting and head pose especially prevalent in the driving scenario. In this paper, we propose an attention-based multi-modal and multi-view fusion FER model that can accurately recognize facial expressions regardless of lighting conditions or head poses, using image data of various modalities including RGB, Near-infrared (NIR), and Depth Maps from different viewpoints. The model is developed on a novel facial expression dataset we collected that includes multiple modalities captured from multiple viewpoints, with varying lighting conditions and head poses. Our multi-modal and multi-view fusion approach shows superior performance compared with models that use data from a single modality/view. The model achieves an accuracy of over 95% when recognizing drivers’ facial expressions in real-world scenarios, even in poor lighting conditions and different head poses.

11 September 2024 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
BKBasar Kutukcu
Basar Kutukcu
SBSabur Hassan Baidya
Sabur Hassan Baidya
SDSujit Dey
Sujit Dey
Deep learning is a proven method in many applications. However, it requires high computation resources and usually has a constant architecture. Mobile systems are good candidates to benefit from deep learning applications since they are closely integrated in people’s life. However, mobile systems experience varying conditions for the same reason. Constant deep learning architectures against varying resources cannot satisfy the requirements of the applications, so dynamic deep learning architectures are needed. In this work, we propose SLEXNet, a slimmable early exit neural network architecture. SLEXNet combines dynamic depth and width architectures to adapt to varying time and power conditions. Moreover, we propose a runtime scheduling algorithm that can estimate inference time and power consumption of SLEXNet variations on runtime. We train SLEXNet on real aerial drone images and implement the runtime on NVIDIA Jetson Orin. We show that our approach achieves significantly better responses to time and power requirements in varying conditions than baseline dynamic depth and width techniques in a wide range of experiments.

24 January 2025 in IEEE Open Journal of Vehicular Technology
Verified
Journal Article
Open access
STSamuel Thornton
Samuel Thornton
NSNithin Santhanam
Nithin Santhanam
RCRajeev Chhajer
Rajeev Chhajer
SDSujit Dey
Sujit Dey
Vehicular sensing has reached new heights due to advances in external perception systems enabled by the increasing number and type of sensors in vehicles, as well as the availability of on-board computing. These changes have led to improvements in driver safety and have also created a highly heterogeneous environment of vehicles on the road today in terms of sensing and computing. Using collaborative perception, the information obtained by vehicles with sensing capabilities can be expanded and improved, and older vehicles that lack external sensors and computing capabilities can be informed of potential hazards, opening the opportunity to improve traffic efficiency and safety on the roads. However, achieving real-time collaborative perception is a difficult task due to the dynamic availability of vehicular sensing and computing and the highly variable nature of vehicular communications. To address these challenges, we propose a Heterogeneous Adaptive Collaborative Perception (HAdCoP) framework which utilizes a Context-aware Latency Prediction Network (CaLPeN) to intelligently select which vehicles should transmit their sensor data, the specific individual and collaborative perception tasks, and the amount of computational offloading that should be utilized given information about the current state of the environment. Additionally, we propose an Adaptive Perception Frequency (APF) model to determine the optimal end-to-end latency requirement according to the current state of the environment. The proposed CaLPeN model outperforms six implemented comparison models in terms of effective mean average precision (EmAP), beating the next best model's performance by 5.5% on average when tested on the OPV2V perception dataset using two different combinations of wireless communication conditions and vehicular sensor/computing distributions.

21 June 2023
Verified
Conference Paper
Open access
BGBhanu Garg
Bhanu Garg
APAlexander Postlmayr
Alexander Postlmayr
PCPamela Cosman
Pamela Cosman
SDSujit Dey
Sujit Dey
At-home exercising strongly predicts physical therapy patient outcomes, underscoring the need for analyzing patient behaviors at-home via remote patient monitoring. Contemporary methods for remote patient monitoring rely on specialized sensors, i.e., Inertial Measurement Units, RGB-Depth cameras, motion capture systems, or stereo vision which are costly and not scalable to all physical therapy patients. Here, we observe a lack of literature using only a monocular RGB camera. In this paper, we demonstrate a skeletal feedback model for at-home exercises using only video acquired from a smartphone camera. We propose models for (i) Patient Performance Evaluation - which classifies the correctness of exercises, and (ii) Guidance - which identifies why the exercise went wrong so the patient can correct themselves. We use these models on our dataset of four common physical therapy exercises labeled by a physical therapist. Our results demonstrate the feasibility of using skeletal data from state-of-the-art 3D human pose estimation models for physical rehabilitation exercise evaluation and guidance. Thus, we enable remote patient monitoring and guidance from a single camera - making it highly cost-effective and scalable.