Deisy Chelliah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Deisy Chelliah has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
A.M. Rajeswari
Department of CSE, Thiagarajar College of Engineering, Madurai, Tamil Nadu, India
4 shared publicationsA. M. Rajeswari
CSE Department, Thiagarajar College of Engineering, Madurai, India
3 shared publications- B. Subbulakshmi
Thiagarajar College of Engineering
3 shared publications - S. Ilankumaran
K.L.N. College of Engineering
3 shared publications S. Padmavathy
Thiyagarajar College of Engineering, Dept. of Computer Science Engineering, Tamilnadu, India
3 shared publicationsS. Parasuraman
Monash University Malaysia, School of Engineering, Selangor, 46150, Malaysia
3 shared publications
Latest Publications
- Open Access
- 28 September 2026
- Published by Elsevier in SSRN Electronic Journal
GAIL: A Multi-signal, Hysteresis-Regulated Adaptive Difficulty Algorithm for Gamified Skill-building in Neurodivergent Children
We describe GAIL-DDA, an interpretable controller for adjusting task difficulty in gamified skill-building activities. Rather than relying on accuracy alone, it folds a rolling accuracy measure, a completion-time adequacy term, and a webcam-derived observational expression signal into one weighted composite score, then decides whether that score is allowed to move the active difficulty level using a persistence-and-cooldown hysteresis rule. Because no human-subject data exists for the system yet, we validated it through a reproducible synthetic simulation built around four disclosed learner archetypes, five controller conditions, 40 matched random seeds, and 150 trials per condition-seed pair. Under the simulator and signal-generation assumptions documented in the accompanying reproducibility package, the full controller kept trials inside a predefined target-performance zone on 45.6% of trials, compared with 40.6% for an accuracy-only staircase baseline, and cut the mean absolute difficulty change per trial from 0.0889 to 0.0404. Both differences held up under matched-seed statistical testing. These figures differ somewhat from an earlier version of this manuscript: the original simulator code was not available to us, so it had to be rebuilt from the equations disclosed in the paper, and the numbers reported here come from that rebuild. What we report, then, is a simulation-level proof of concept and nothing more. We make no claims about human-subject usability, engagement, facial-expression accuracy, learning, or clinical or therapeutic outcomes in real children — human evaluation of the Feelio application remains future work.
- 28 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessGAIL: A Multi-signal, Hysteresis-Regulated Adaptive Difficulty Algorithm for Gamified Skill-building in Neurodivergent Children
We describe GAIL-DDA, an interpretable controller for adjusting task difficulty in gamified skill-building activities. Rather than relying on accuracy alone, it folds a rolling accuracy measure, a completion-time adequacy term, and a webcam-derived observational expression signal into one weighted composite score, then decides whether that score is allowed to move the active difficulty level using a persistence-and-cooldown hysteresis rule. Because no human-subject data exists for the system yet, we validated it through a reproducible synthetic simulation built around four disclosed learner archetypes, five controller conditions, 40 matched random seeds, and 150 trials per condition-seed pair. Under the simulator and signal-generation assumptions documented in the accompanying reproducibility package, the full controller kept trials inside a predefined target-performance zone on 45.6% of trials, compared with 40.6% for an accuracy-only staircase baseline, and cut the mean absolute difficulty change per trial from 0.0889 to 0.0404. Both differences held up under matched-seed statistical testing. These figures differ somewhat from an earlier version of this manuscript: the original simulator code was not available to us, so it had to be rebuilt from the equations disclosed in the paper, and the numbers reported here come from that rebuild. What we report, then, is a simulation-level proof of concept and nothing more. We make no claims about human-subject usability, engagement, facial-expression accuracy, learning, or clinical or therapeutic outcomes in real children — human evaluation of the Feelio application remains future work.
- 2 January 2026
- Published by Springer Nature
- p. 421-429
Explainable Deep Learning System for Retinal Disease Detection
- 2 January 2026
- Published by Springer Nature
- p. 421-429
Explainable Deep Learning System for Retinal Disease Detection
- RetractionOpen Access
- 21 October 2024
- Published by Springer Nature in Soft Computing
- Vol. 28 (S2) , 865
Retraction Note: Quality-based pattern C2 code score-level fusion in multimodal biometric authentication system using pattern net
- 21 October 2024
- Published by Springer Nature in Soft Computing
- Vol. 28 (S2) , 865
RetractionOpen AccessRetraction Note: Quality-based pattern C2 code score-level fusion in multimodal biometric authentication system using pattern net
- Open Access
- 1 October 2023
- Published by Ital Publication in Emerging Science Journal
- Vol. 7 (5) , 1636-1652
The Eye: A Light Weight Mobile Application for Visually Challenged People Using Improved YOLOv5l Algorithm
The eye is an essential sensory organ that allows us to perceive our surroundings at a glance. Losing this sense can result in numerous challenges in daily life. However, society is designed for the majority, which can create even more difficulties for visually impaired individuals. Therefore, empowering them and promoting self-reliance are crucial. To address this need, we propose a new Android application called “The Eye” that utilizes Machine Learning (ML)-based object detection techniques to recognize objects in real-time using a smartphone camera or a camera attached to a stick. The article proposed an improved YOLOv5l algorithm to improve object detection in visual applications. YOLOv5l has a larger model size and captures more complex features and details, leading to enhanced object detection accuracy compared to smaller variants like YOLOv5s and YOLOv5m. The primary enhancement in the improved YOLOv5l algorithm is integrating L1 and L2 regularization techniques. These techniques prevent overfitting and improve generalization by adding a regularization term to the loss function during training. Our approach combines image processing and text-to-speech conversion modules to produce reliable results. The Android text-to-speech module is then used to convert the object recognition results into an audio output. According to the experimental results, the improved YOLOv5l has higher detection accuracy than the original YOLOv5 and can detect small, multiple, and overlapped targets with higher accuracy. This study contributes to the advancement of technology to help visually impaired individuals become more self-sufficient and confident. Doi: 10.28991/ESJ-2023-07-05-011 Full Text: PDF
- 1 October 2023
- Published by Ital Publication in Emerging Science Journal
- Vol. 7 (5) , 1636-1652
Open AccessThe Eye: A Light Weight Mobile Application for Visually Challenged People Using Improved YOLOv5l Algorithm
The eye is an essential sensory organ that allows us to perceive our surroundings at a glance. Losing this sense can result in numerous challenges in daily life. However, society is designed for the majority, which can create even more difficulties for visually impaired individuals. Therefore, empowering them and promoting self-reliance are crucial. To address this need, we propose a new Android application called “The Eye” that utilizes Machine Learning (ML)-based object detection techniques to recognize objects in real-time using a smartphone camera or a camera attached to a stick. The article proposed an improved YOLOv5l algorithm to improve object detection in visual applications. YOLOv5l has a larger model size and captures more complex features and details, leading to enhanced object detection accuracy compared to smaller variants like YOLOv5s and YOLOv5m. The primary enhancement in the improved YOLOv5l algorithm is integrating L1 and L2 regularization techniques. These techniques prevent overfitting and improve generalization by adding a regularization term to the loss function during training. Our approach combines image processing and text-to-speech conversion modules to produce reliable results. The Android text-to-speech module is then used to convert the object recognition results into an audio output. According to the experimental results, the improved YOLOv5l has higher detection accuracy than the original YOLOv5 and can detect small, multiple, and overlapped targets with higher accuracy. This study contributes to the advancement of technology to help visually impaired individuals become more self-sufficient and confident. Doi: 10.28991/ESJ-2023-07-05-011 Full Text: PDF
- Top Cited Papers
- 6 March 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 122
A comparative study of deep learning and Internet of Things for precision agriculture
- 6 March 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 122
Top Cited PapersA comparative study of deep learning and Internet of Things for precision agriculture
- 9 September 2022
- Published by Springer Nature
- p. 317-327
A Decision Support System for Understanding the Importance of Two-Dosage Vaccination
- 9 September 2022
- Published by Springer Nature
- p. 317-327
A Decision Support System for Understanding the Importance of Two-Dosage Vaccination
- Open Access
- 11 November 2021
- Published by F1000 Research Ltd in F1000Research
- Vol. 10, 1143
An intelligent decision support system for crop yield prediction using hybrid machine learning algorithms
Background: In recent times, digitization is gaining importance in different domains of knowledge such as agriculture, medicine, recommendation platforms, the Internet of Things (IoT), and weather forecasting. In agriculture, crop yield estimation is essential for improving productivity and decision-making processes such as financial market forecasting, and addressing food security issues. The main objective of the article is to predict and improve the accuracy of crop yield forecasting using hybrid machine learning (ML) algorithms. Methods: This article proposes hybrid ML algorithms that use specialized ensembling methods such as stacked generalization, gradient boosting, random forest, and least absolute shrinkage and selection operator (LASSO) regression. Stacked generalization is a new model which learns how to best combine the predictions from two or more models trained on the dataset. To demonstrate the applications of the proposed algorithm, aerial-intel datasets from the github data science repository are used. Results: Based on the experimental results done on the agricultural data, the following observations have been made. The performance of the individual algorithm and hybrid ML algorithms are compared using cross-validation to identify the most promising performers for the agricultural dataset. The accuracy of random forest regressor, gradient boosted tree regression, and stacked generalization ensemble methods are 87.71%, 86.98%, and 88.89% respectively. Conclusions: The proposed stacked generalization ML algorithm statistically outperforms with an accuracy of 88.89% and hence demonstrates that the proposed approach is an effective algorithm for predicting crop yield. The system also gives fast and accurate responses to the farmers.
- 11 November 2021
- Published by F1000 Research Ltd in F1000Research
- Vol. 10, 1143
Open AccessAn intelligent decision support system for crop yield prediction using hybrid machine learning algorithms
Background: In recent times, digitization is gaining importance in different domains of knowledge such as agriculture, medicine, recommendation platforms, the Internet of Things (IoT), and weather forecasting. In agriculture, crop yield estimation is essential for improving productivity and decision-making processes such as financial market forecasting, and addressing food security issues. The main objective of the article is to predict and improve the accuracy of crop yield forecasting using hybrid machine learning (ML) algorithms. Methods: This article proposes hybrid ML algorithms that use specialized ensembling methods such as stacked generalization, gradient boosting, random forest, and least absolute shrinkage and selection operator (LASSO) regression. Stacked generalization is a new model which learns how to best combine the predictions from two or more models trained on the dataset. To demonstrate the applications of the proposed algorithm, aerial-intel datasets from the github data science repository are used. Results: Based on the experimental results done on the agricultural data, the following observations have been made. The performance of the individual algorithm and hybrid ML algorithms are compared using cross-validation to identify the most promising performers for the agricultural dataset. The accuracy of random forest regressor, gradient boosted tree regression, and stacked generalization ensemble methods are 87.71%, 86.98%, and 88.89% respectively. Conclusions: The proposed stacked generalization ML algorithm statistically outperforms with an accuracy of 88.89% and hence demonstrates that the proposed approach is an effective algorithm for predicting crop yield. The system also gives fast and accurate responses to the farmers.
- 27 February 2020
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 28 (3) , 1129-1145
Mathematical and Visual Understanding of a Deep Learning Model Towards m-Agriculture for Disease Diagnosis
- 27 February 2020
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 28 (3) , 1129-1145
Mathematical and Visual Understanding of a Deep Learning Model Towards m-Agriculture for Disease Diagnosis
- 26 March 2019
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 36 (3) , 2691-2704
Fuzzy logic based associative classifier for slow learners prediction
Education is a collective intelligence system where a group of persons ranging from students to management thinks and work together to achieve institutions’ goals. The primary goal of every institution is to accomplish excellent end-semester examinat
- 26 March 2019
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 36 (3) , 2691-2704
Fuzzy logic based associative classifier for slow learners prediction
Education is a collective intelligence system where a group of persons ranging from students to management thinks and work together to achieve institutions’ goals. The primary goal of every institution is to accomplish excellent end-semester examinat
- 1 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1063-1068
Disease Detection and Classification in Agricultural Plants Using Convolutional Neural Networks — A Visual Understanding
Convolutional Neural Network is the base of all deep learning models. Therefore a Convolutional Neural Network model is created and developed to perform plant disease detection and classification using apple and tomato leaf images of healthy and diseased plants. The model consists of four convolutional layers each followed by pooling layers. Two fully connected dense layers and sigmoid function is used to detect the probability of presence of disease or not. Training of the model was done on apple and tomato leaf image dataset containing 3663 images achieving an accuracy of 87%. The overfitting problem is identified and removed setting the dropout value to 0.2. As the model allows parallel processing, it is also run on GPU Tesla to evaluate its speed of performance and accuracy. Hence the paper provides an insight of creativeness to the researchers to develop an integrated plant disease identification system that gives successful results in realtime.
- 1 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1063-1068
Disease Detection and Classification in Agricultural Plants Using Convolutional Neural Networks — A Visual Understanding
Convolutional Neural Network is the base of all deep learning models. Therefore a Convolutional Neural Network model is created and developed to perform plant disease detection and classification using apple and tomato leaf images of healthy and diseased plants. The model consists of four convolutional layers each followed by pooling layers. Two fully connected dense layers and sigmoid function is used to detect the probability of presence of disease or not. Training of the model was done on apple and tomato leaf image dataset containing 3663 images achieving an accuracy of 87%. The overfitting problem is identified and removed setting the dropout value to 0.2. As the model allows parallel processing, it is also run on GPU Tesla to evaluate its speed of performance and accuracy. Hence the paper provides an insight of creativeness to the researchers to develop an integrated plant disease identification system that gives successful results in realtime.