Amudha Joseph
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Amudha Joseph has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- S. Akshay
Amrita Vishwa Vidyapeetham
5 shared publications - Chandrika Kamath Ramachandra
ABB Corporate Research, Bengaluru, India
3 shared publications - Jyotsna Chandrasekharan
Amrita School of Engineering, Amrita Vishwa Vidyapeetham
3 shared publications - Aarthi Ramachandran
Amrita School of Engineering, Amrita Vishwa Vidyapeetham
2 shared publications - Aiswariya Milan Kummaya
Amrita School of Computing, Amrita Vishwa Vidyapeetham
2 shared publications - Amritanshu Ram
Head, Yoga Department HealthCare Global Enterprises Ltd., Bangalore, India
2 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 128019-128045
Cross-Modal Knowledge Distillation Framework for Thermal-Guided RGB Object Detection With Depth Estimation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 128019-128045
Open AccessCross-Modal Knowledge Distillation Framework for Thermal-Guided RGB Object Detection With Depth Estimation
- 1 October 2025
- Published by Springer Nature
- p. 489-501
Automating Legal Inquiry: A Reinforcement Learning Approach to Query Generation
- 1 October 2025
- Published by Springer Nature
- p. 489-501
Automating Legal Inquiry: A Reinforcement Learning Approach to Query Generation
- Open Access
- 7 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-19
Learner stimulus intent: a framework for eye tracking data collection and feature extraction in computer programming education
Eye tracking technology offers valuable insights into the cognitive processes of learners in computer programming education. This research presents a novel framework called the Learner Stimulus Intent that offers useful insights into learners’ cognitive processes in computer programming education and has significant implications for assessment in computer science education. The comprehensive data collection, extraction of eye gaze and semantic features, and effective visualization techniques can be utilized to evaluate students’ understanding and engagement, offering a more nuanced and detailed picture of their learning progress than traditional assessment methods. Furthermore, the four distinct datasets generated by the framework each offers unique perspectives on learner behavior and their cognitive traits. These datasets are outcomes of the framework’s application, embodying its potential to revolutionize the way we understand and assess learning in computer science education. By utilizing this framework, educators and researchers can gain deeper insights into the cognitive processes of learners like cognitive workload, processing order of information, confusion in mind, attention etc, ultimately enhancing instructional strategies and improving learner outcomes.
- 7 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-19
Open AccessLearner stimulus intent: a framework for eye tracking data collection and feature extraction in computer programming education
Eye tracking technology offers valuable insights into the cognitive processes of learners in computer programming education. This research presents a novel framework called the Learner Stimulus Intent that offers useful insights into learners’ cognitive processes in computer programming education and has significant implications for assessment in computer science education. The comprehensive data collection, extraction of eye gaze and semantic features, and effective visualization techniques can be utilized to evaluate students’ understanding and engagement, offering a more nuanced and detailed picture of their learning progress than traditional assessment methods. Furthermore, the four distinct datasets generated by the framework each offers unique perspectives on learner behavior and their cognitive traits. These datasets are outcomes of the framework’s application, embodying its potential to revolutionize the way we understand and assess learning in computer science education. By utilizing this framework, educators and researchers can gain deeper insights into the cognitive processes of learners like cognitive workload, processing order of information, confusion in mind, attention etc, ultimately enhancing instructional strategies and improving learner outcomes.
- Open Access
- 27 February 2025
- Published by MDPI AG in Applied System Innovation
- Vol. 8 (2) , 28
Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity
Federated learning (FL) enables deep learning models to be trained locally on devices without the need for data sharing, ensuring data privacy. However, when clients have uneven or imbalanced data distributions, it leads to data heterogeneity. Data heterogeneity can appear in different ways, often due to variations in label, data distributions, feature variations, and structural inconsistencies in the images. This can significantly impact FL performance, as the global model often struggles to achieve optimal convergence. To enhance training efficiency and model performance, a common strategy in FL is to exclude clients with limited data. However, excluding such clients can raise fairness concerns, particularly for smaller populations. To understand the influence of data heterogeneity, a self-evaluating federated learning framework for heterogeneity, Fed-Hetero, was designed to assess the type of heterogeneity associated with the clients and provide recommendations to clients to enhance the global model’s accuracy. Fed-Hetero thus enables the clients with limited data to participate in FL processes by adopting appropriate strategies that enhance model accuracy. The results show that Fed-Hetero identifies the client with heterogeneity and provides personalized recommendations.
- 27 February 2025
- Published by MDPI AG in Applied System Innovation
- Vol. 8 (2) , 28
Open AccessFed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity
Federated learning (FL) enables deep learning models to be trained locally on devices without the need for data sharing, ensuring data privacy. However, when clients have uneven or imbalanced data distributions, it leads to data heterogeneity. Data heterogeneity can appear in different ways, often due to variations in label, data distributions, feature variations, and structural inconsistencies in the images. This can significantly impact FL performance, as the global model often struggles to achieve optimal convergence. To enhance training efficiency and model performance, a common strategy in FL is to exclude clients with limited data. However, excluding such clients can raise fairness concerns, particularly for smaller populations. To understand the influence of data heterogeneity, a self-evaluating federated learning framework for heterogeneity, Fed-Hetero, was designed to assess the type of heterogeneity associated with the clients and provide recommendations to clients to enhance the global model’s accuracy. Fed-Hetero thus enables the clients with limited data to participate in FL processes by adopting appropriate strategies that enhance model accuracy. The results show that Fed-Hetero identifies the client with heterogeneity and provides personalized recommendations.
- Open Access
- 4 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Automated Insight Tool: Analyzing Eye Tracking Data of Expert and Novice Radiologists During Optic Disc Detection Task
In specialized medical research, eye-tracking analysis proves instrumental for monitoring and dissecting eye movements and gaze patterns. This methodology is employed to get insights into diverse human behavior, cognition, and health facets. This study analyzes radiologists gaze patterns as they locate optic discs in retinal fundus images. The underlying premise is that experts possess a more profound understanding of the designated area of interest (AOI) within retinal images than non-experts. We considered visual attention distribution, and the visual focus shift between experts and novice during the viewing task. Identifying expert radiologists will benefit in two main ways: first, it will facilitate the development of an effective training system that assists radiologists in recognizing their technical proficiency, and second, it will enable the automation of the diagnostic process. The proposed methodology utilizes insights from radiologists Region of Interest (IOR) to interpret experts and novice eye gaze behavior, classify radiologists expertise levels, and compare visual patterns among different expertise levels. This study introduces an automated tool to analyze experts behaviors within regions of interest, offering a comprehensive understanding of radiological diagnostic processes.
- 4 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessAutomated Insight Tool: Analyzing Eye Tracking Data of Expert and Novice Radiologists During Optic Disc Detection Task
In specialized medical research, eye-tracking analysis proves instrumental for monitoring and dissecting eye movements and gaze patterns. This methodology is employed to get insights into diverse human behavior, cognition, and health facets. This study analyzes radiologists gaze patterns as they locate optic discs in retinal fundus images. The underlying premise is that experts possess a more profound understanding of the designated area of interest (AOI) within retinal images than non-experts. We considered visual attention distribution, and the visual focus shift between experts and novice during the viewing task. Identifying expert radiologists will benefit in two main ways: first, it will facilitate the development of an effective training system that assists radiologists in recognizing their technical proficiency, and second, it will enable the automation of the diagnostic process. The proposed methodology utilizes insights from radiologists Region of Interest (IOR) to interpret experts and novice eye gaze behavior, classify radiologists expertise levels, and compare visual patterns among different expertise levels. This study introduces an automated tool to analyze experts behaviors within regions of interest, offering a comprehensive understanding of radiological diagnostic processes.
- Open Access
- 28 February 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (3) , 104
A Systematic Evaluation of Recurrent Neural Network Models for Edge Intelligence and Human Activity Recognition Applications
The Recurrent Neural Networks (RNNs) are an essential class of supervised learning algorithms. Complex tasks like speech recognition, machine translation, sentiment classification, weather prediction, etc., are now performed by well-trained RNNs. Local or cloud-based GPU machines are used to train them. However, inference is now shifting to miniature, mobile, IoT devices and even micro-controllers. Due to their colossal memory and computing requirements, mapping RNNs directly onto resource-constrained platforms is arcane and challenging. The efficacy of edge-intelligent RNNs (EI-RNNs) must satisfy both performance and memory-fitting requirements at the same time without compromising one for the other. This study’s aim was to provide an empirical evaluation and optimization of historic as well as recent RNN architectures for high-performance and low-memory footprint goals. We focused on Human Activity Recognition (HAR) tasks based on wearable sensor data for embedded healthcare applications. We evaluated and optimized six different recurrent units, namely Vanilla RNNs, Long Short-Term Memory (LSTM) units, Gated Recurrent Units (GRUs), Fast Gated Recurrent Neural Networks (FGRNNs), Fast Recurrent Neural Networks (FRNNs), and Unitary Gated Recurrent Neural Networks (UGRNNs) on eight publicly available time-series HAR datasets. We used the hold-out and cross-validation protocols for training the RNNs. We used low-rank parameterization, iterative hard thresholding, and spare retraining compression for RNNs. We found that efficient training (i.e., dataset handling and preprocessing procedures, hyperparameter tuning, and so on, and suitable compression methods (like low-rank parameterization and iterative pruning) are critical in optimizing RNNs for performance and memory efficiency. We implemented the inference of the optimized models on Raspberry Pi.
- 28 February 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (3) , 104
Open AccessA Systematic Evaluation of Recurrent Neural Network Models for Edge Intelligence and Human Activity Recognition Applications
The Recurrent Neural Networks (RNNs) are an essential class of supervised learning algorithms. Complex tasks like speech recognition, machine translation, sentiment classification, weather prediction, etc., are now performed by well-trained RNNs. Local or cloud-based GPU machines are used to train them. However, inference is now shifting to miniature, mobile, IoT devices and even micro-controllers. Due to their colossal memory and computing requirements, mapping RNNs directly onto resource-constrained platforms is arcane and challenging. The efficacy of edge-intelligent RNNs (EI-RNNs) must satisfy both performance and memory-fitting requirements at the same time without compromising one for the other. This study’s aim was to provide an empirical evaluation and optimization of historic as well as recent RNN architectures for high-performance and low-memory footprint goals. We focused on Human Activity Recognition (HAR) tasks based on wearable sensor data for embedded healthcare applications. We evaluated and optimized six different recurrent units, namely Vanilla RNNs, Long Short-Term Memory (LSTM) units, Gated Recurrent Units (GRUs), Fast Gated Recurrent Neural Networks (FGRNNs), Fast Recurrent Neural Networks (FRNNs), and Unitary Gated Recurrent Neural Networks (UGRNNs) on eight publicly available time-series HAR datasets. We used the hold-out and cross-validation protocols for training the RNNs. We used low-rank parameterization, iterative hard thresholding, and spare retraining compression for RNNs. We found that efficient training (i.e., dataset handling and preprocessing procedures, hyperparameter tuning, and so on, and suitable compression methods (like low-rank parameterization and iterative pruning) are critical in optimizing RNNs for performance and memory efficiency. We implemented the inference of the optimized models on Raspberry Pi.
- 4 December 2023
- Published by Springer Nature
- p. 279-288
iGAME: Cognitive Game Analysis Through Eye Movements of the Player
- 4 December 2023
- Published by Springer Nature
- p. 279-288
iGAME: Cognitive Game Analysis Through Eye Movements of the Player
- 4 December 2023
- Published by Springer Nature
- p. 260-269
iBEHAVE: Behaviour Analysis Using Eye Gaze Metrices
- 4 December 2023
- Published by Springer Nature
- p. 260-269
iBEHAVE: Behaviour Analysis Using Eye Gaze Metrices
- Open Access
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 128383-128409
PredictEYE: Personalized Time Series Model for Mental State Prediction Using Eye Tracking
Mental health is vital for emotional, psychological, and social well-being. Mental illness can affect thoughts, feelings, and behaviors. Early intervention and specialized care can manage major mental illnesses. Predicting mental state accurately can facilitate behavioral changes and promote overall well-being. The paper proposes a novel personalized time series model called PredictEYE, which aims to predict a person’s mental state and identify the specific scene responsible for that mental state. The model achieves this by analyzing individuals’ eye-tracking time series data while watching calm and stressful videos. The model utilizes deep learning time-series univariate regression model based on Long Short-Term Memory for predicting the future sequence of each feature and a machine learning-based Random Forest algorithm for the mental state prediction. The model’s performance was compared across the state-of-the-art literature survey. The predictEYE model could achieve an accuracy of 86.4% accuracy in predicting mental state. Tailoring eye tracking models to individual differences is more effective in comprehending mental states than models that make comparisons across multiple participants, given eye tracking data’s unique and distinctive idiosyncratic nature. The eye tracking features play a crucial role in predicting the mental state, and the model is adaptable to work with webcam-based eye tracking and can relate to applications where continuous and non-invasive monitoring is required.
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 128383-128409
Open AccessPredictEYE: Personalized Time Series Model for Mental State Prediction Using Eye Tracking
Mental health is vital for emotional, psychological, and social well-being. Mental illness can affect thoughts, feelings, and behaviors. Early intervention and specialized care can manage major mental illnesses. Predicting mental state accurately can facilitate behavioral changes and promote overall well-being. The paper proposes a novel personalized time series model called PredictEYE, which aims to predict a person’s mental state and identify the specific scene responsible for that mental state. The model achieves this by analyzing individuals’ eye-tracking time series data while watching calm and stressful videos. The model utilizes deep learning time-series univariate regression model based on Long Short-Term Memory for predicting the future sequence of each feature and a machine learning-based Random Forest algorithm for the mental state prediction. The model’s performance was compared across the state-of-the-art literature survey. The predictEYE model could achieve an accuracy of 86.4% accuracy in predicting mental state. Tailoring eye tracking models to individual differences is more effective in comprehending mental states than models that make comparisons across multiple participants, given eye tracking data’s unique and distinctive idiosyncratic nature. The eye tracking features play a crucial role in predicting the mental state, and the model is adaptable to work with webcam-based eye tracking and can relate to applications where continuous and non-invasive monitoring is required.