Thomas Mary Little Flower
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Thomas Mary Little Flower has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Thirasama Jaya
Department of Electronics and Communication Engineering, Saveetha Engineering College, Thandalam
2 shared publicationsG. Glan Devadhas
Directorate of Research and Innovation, CMR University
1 shared publicationGeorge Glan Devadhas
Directorate of Research & Innovation, CMR University
1 shared publicationK. G. Jaya Christiyan
Department of Mechanical Engineering, Vimal Jyothi Engineering College
1 shared publicationK. Jessy
Department of Mechanical Engineering, Amal Jyothi College of Engineering
1 shared publication- Mary Little Flower Thomas
Department of ECE, St. Xavier’s Catholic College of Engineering
1 shared publication
Latest Publications
- Open Access
- 31 January 2026
- Published by Premier Science in Premier Journal of Science
- Vol. 15 (1)
AI-Driven Robotics in Agriculture: A Review
Artificial intelligence (AI) combined with robotics is changing how agriculture has always been practiced to a more efficient, precise, and sustainable one. The review critically discusses the latest achievements in AI-driven agricultural robotics, including vision-based navigation systems, deep learning-based crop surveillance, and autonomous robots based on hybrid control architectures. It analyses fundamental enabling technologies, such as vision-based navigation systems which use deep learning to compute obstacle avoidance and hybrid control structures which compromise robot autonomy and centralized control. The synthesis finds a prevailing trend of the integration of the state-of-the-art sensors, Light Detection and Range (LiDAR), Global Positioning System (GPS) and hyperspectral imaging with AI-based decisions to automatize the precision applications in targeted irrigation, harvesting, and early disease identification. These technologies will ensure that there is optimization in the utilization of resources, increased yields, as well as reduced environmental impact. Nevertheless, the analysis also discloses a considerable amount of barriers to the broad adoption, namely, the high initial costs, technical issues in unstructured settings, and insufficient and robust regulatory frameworks. Moreover, the review does not focus only on technical matters but addresses crucial socio-economic and ethical consequences, i.e., changes in labor market, data privacy, and fair access. It is important that future studies focus on the creation of stronger, low cost, and flexed robots. Such directions as improving the collaboration with the swarm of multi-robots, enhancing AI models with simulation-to-reality (sim2real) systems, and setting up policy-aware safety and data governance standards can be identified. The review reiterates the use of intelligent robotics as an instrumental tool in the formation of a productive and sustainable future in global agriculture.
- 31 January 2026
- Published by Premier Science in Premier Journal of Science
- Vol. 15 (1)
Open AccessAI-Driven Robotics in Agriculture: A Review
Artificial intelligence (AI) combined with robotics is changing how agriculture has always been practiced to a more efficient, precise, and sustainable one. The review critically discusses the latest achievements in AI-driven agricultural robotics, including vision-based navigation systems, deep learning-based crop surveillance, and autonomous robots based on hybrid control architectures. It analyses fundamental enabling technologies, such as vision-based navigation systems which use deep learning to compute obstacle avoidance and hybrid control structures which compromise robot autonomy and centralized control. The synthesis finds a prevailing trend of the integration of the state-of-the-art sensors, Light Detection and Range (LiDAR), Global Positioning System (GPS) and hyperspectral imaging with AI-based decisions to automatize the precision applications in targeted irrigation, harvesting, and early disease identification. These technologies will ensure that there is optimization in the utilization of resources, increased yields, as well as reduced environmental impact. Nevertheless, the analysis also discloses a considerable amount of barriers to the broad adoption, namely, the high initial costs, technical issues in unstructured settings, and insufficient and robust regulatory frameworks. Moreover, the review does not focus only on technical matters but addresses crucial socio-economic and ethical consequences, i.e., changes in labor market, data privacy, and fair access. It is important that future studies focus on the creation of stronger, low cost, and flexed robots. Such directions as improving the collaboration with the swarm of multi-robots, enhancing AI models with simulation-to-reality (sim2real) systems, and setting up policy-aware safety and data governance standards can be identified. The review reiterates the use of intelligent robotics as an instrumental tool in the formation of a productive and sustainable future in global agriculture.
- Open Access
- 7 January 2026
- Published by Premier Science in Premier Journal of Science
- Vol. 15 (1)
EEG-Based Emotion Recognition: A Systematic Review of Traditional and Deep Learning Methods
OBJECTIVE This systematic review provides a synthesis of the existing data concerning the Electroencephalogram (EEG)-based emotion recognition and assesses the development of the old machine learning models to the current deep learning models. The purpose of the review is the comparison of their performance and the identification of trends in the approaches to the methodology and the evaluation of the strength and the reproducibility of the discipline. METHODS The review was done based on the Preferred Reporting Items of Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines. Five electronic databases (IEEE Xplore, Scopus, PubMed, ScienceDirect, and SpringerLink) that have been published not earlier than January 2012 were searched systematically. Due to the removal of duplicates and two rounds of screening against pre-defined inclusion criteria, 50 studies were incorporated to be final synthesized. FINDINGS It has been demonstrated that there is a definite trend towards end-to-end deep learning models, especially Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and architectures combining both. These models, particularly when using maps of topographic features and maps of functional connectivity, have shown a higher level of performance, and their classification accuracies of 90 percent or higher in benchmark data such as DEAP and SEED in subject-dependent contexts. But, there is a significant decline in the performance in cross-subject validation, which is an outstanding generalization issue. It also becomes evident during the synthesis that validation protocols, data preprocessing and reporting standards exhibit high heterogeneity, thus making it difficult to directly compare them and jeopardizing reproducibility. CONCLUSION Deep learning approaches are an important development in emotion recognition of EEG, but the area is plagued by lack of uniformity and focus on real-world applicability. The next step in work is to focus on the creation of standardized evaluation metrics, explicable AI methods, and effective, cross-subject models to enable the movement of laboratory studies to the reliable, deployable systems.
- 7 January 2026
- Published by Premier Science in Premier Journal of Science
- Vol. 15 (1)
Open AccessEEG-Based Emotion Recognition: A Systematic Review of Traditional and Deep Learning Methods
OBJECTIVE This systematic review provides a synthesis of the existing data concerning the Electroencephalogram (EEG)-based emotion recognition and assesses the development of the old machine learning models to the current deep learning models. The purpose of the review is the comparison of their performance and the identification of trends in the approaches to the methodology and the evaluation of the strength and the reproducibility of the discipline. METHODS The review was done based on the Preferred Reporting Items of Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines. Five electronic databases (IEEE Xplore, Scopus, PubMed, ScienceDirect, and SpringerLink) that have been published not earlier than January 2012 were searched systematically. Due to the removal of duplicates and two rounds of screening against pre-defined inclusion criteria, 50 studies were incorporated to be final synthesized. FINDINGS It has been demonstrated that there is a definite trend towards end-to-end deep learning models, especially Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and architectures combining both. These models, particularly when using maps of topographic features and maps of functional connectivity, have shown a higher level of performance, and their classification accuracies of 90 percent or higher in benchmark data such as DEAP and SEED in subject-dependent contexts. But, there is a significant decline in the performance in cross-subject validation, which is an outstanding generalization issue. It also becomes evident during the synthesis that validation protocols, data preprocessing and reporting standards exhibit high heterogeneity, thus making it difficult to directly compare them and jeopardizing reproducibility. CONCLUSION Deep learning approaches are an important development in emotion recognition of EEG, but the area is plagued by lack of uniformity and focus on real-world applicability. The next step in work is to focus on the creation of standardized evaluation metrics, explicable AI methods, and effective, cross-subject models to enable the movement of laboratory studies to the reliable, deployable systems.
- Open Access
- 3 July 2024
- Published by Taylor & Francis in Automatika
- Vol. 65 (4) , 1325-1338
Data augmentation using a 1D-CNN model with MFCC/MFMC features for speech emotion recognition
- 3 July 2024
- Published by Taylor & Francis in Automatika
- Vol. 65 (4) , 1325-1338
Open AccessData augmentation using a 1D-CNN model with MFCC/MFMC features for speech emotion recognition