Amudha J

Dr. Amudha J


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
14 November 2023 in IEEE Access
Verified
Journal Article
Open access
JCJyotsna C.
Jyotsna C.
AJAmudha J
Amudha J
ARAmritanshu Ram
Amritanshu Ram
DFDamiano Fruet
Damiano Fruet
GNGiandomenico Nollo
Giandomenico Nollo
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.

13 October 2021 in Sensors
Verified
Journal Article
Open access
PDF file
CKChandrika KR
Chandrika KR
AJAmudha J
Amudha J
In the current education environment, learning takes place outside the physical classroom, and tutors need to determine whether learners are absorbing the content delivered to them. Online assessment has become a viable option for tutors to establish the achievement of course learning outcomes by learners. It provides real-time progress and immediate results; however, it has challenges in quantifying learner aspects like wavering behavior, confidence level, knowledge acquired, quickness in completing the task, task engagement, inattentional blindness to critical information, etc. An intelligent eye gaze-based assessment system called IEyeGASE is developed to measure insights into these behavioral aspects of learners. The system can be integrated into the existing online assessment system and help tutors re-calibrate learning goals and provide necessary corrective actions.

28 February 2024 in Algorithms
Verified
Journal Article
Open access
PDF file
VLVarsha S Lalapura
Varsha S Lalapura
VBVeerender Reddy Bhimavarapu
Veerender Reddy Bhimavarapu
AJAmudha J
Amudha J
HSHariram Selvamurugan Satheesh
Hariram Selvamurugan Satheesh
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.

7 July 2022 in IEEE Access
Verified
Journal Article
Open access
SKSajitha Krishnan
Sajitha Krishnan
AJAmudha J
Amudha J
STSushma Tejwani
Sushma Tejwani
Glaucoma is a type of visual impairment that is caused due to damage in the optic nerve. The vision loss increases from the peripheral vision towards the central vision, leading to blindness if untreated. The proposed approach is a Computer-Aided Detection (CADe) system using deep learning to screen visual field loss in glaucoma patients while performing different day-to-day activities such as searching objects, viewing photographs, etc. Incorporating an eye-tracking device helps to identify eye movements of glaucoma patients while performing different activities. Different day-to-day activities are depicted in the form of visual exploration tasks. CADe system fuses performance parameters and eye gaze parameters during visual exploration tasks onto images, to guide health care professionals of primary eye care centers in glaucoma screening. The pertinent eye gaze and performance parameters are visualized in the form of three fusion maps: Gaze Fusion Map (GFM), Gaze Fusion Reaction Time (GFRT) map, Gaze Convex Hull Map (GCHM), which are the outcomes of different visual exploration tasks. In addition, the explainability techniques applied in CADe generated Gaze Exploration - index (GE-i) that discriminates glaucoma and normal.

14 June 2018 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Verified
Journal Article
Closed access
PDF file
AJAmudha J
Amudha J
HNHitha Nandakumar
Hitha Nandakumar
The general characteristics observed in Autism is decrease in communication skill, interaction and shows behavioral changes. The reasons for these can be studied by understanding their visual sensory processing. The research work presented here uses image stimuli to study the behavior in children by understanding when and where they look. A Fuzzy based Eye Gaze Point estimation (FEGP) has been proposed which observes the gaze coordinates of the child, analyze the eye gaze parameters to assess the difference in visual perception of an autistic child in comparison to a normal child. The approach helps to identify the visual behavior difference in autistic children with a performance level indicator, visualization and inferences that can be used to tune their learning programs with an attempt to meet their counterparts.

1 August 2023 in Sensors
Verified
Journal Article
Open access
PDF file
JCJyotsna C.
Jyotsna C.
AJAmudha J
Amudha J
ARAmritanshu Ram
Amritanshu Ram
GNGiandomenico Nollo
Giandomenico Nollo
The growing number of people with cognitive impairment will significantly increase healthcare demand. Screening tools are crucial for detecting cognitive impairment due to a shortage of mental health experts aiming to improve the quality of life for those living with this condition. Eye tracking is a powerful tool that can provide deeper insights into human behavior and inner cognitive processes. The proposed Eye-Tracking-Based Trail-Making Test, ETMT, is a screening tool for monitoring a person’s cognitive function. The proposed system utilizes a fuzzy-inference system as an integral part of its framework to calculate comprehensive scores assessing visual search speed and focused attention. By employing an adaptive neuro-fuzzy-inference system, the tool provides an overall cognitive-impairment score, allowing psychologists to assess and quantify the extent of cognitive decline or impairment in their patients. The ETMT model offers a comprehensive understanding of cognitive abilities and identifies potential deficits in various domains. The results indicate that the ETMT model is a potential tool for evaluating cognitive impairment and can capture significant changes in eye movement behavior associated with cognitive impairment. It provides a convenient and affordable diagnosis, prioritizing healthcare resources for severe conditions while enhancing feedback to practitioners.