Dr. S. Srijah, Thiagarajar College of Engineering, India
Srijah S is a Research Scholar under the Thiagarajar Research Fellowship at Thiagarajar College of Engineering, Madurai, affiliated with Anna University. Her research focuses on Artificial Intelligence, Deep Learning, Computer Vision, Explainable AI, Machine Learning, and AI-driven solutions for smart agriculture, with particular emphasis on plant disease detection, plant-stress assessment, mango disease diagnosis, and fruit-quality grading. Her current doctoral research explores an Artificial Intelligence-Based Decision Support System for Smart Agriculture.
Online Profiles
Srijah S maintains an ORCID profile (0009-0004-3192-8917) and a Google Scholar profile, providing platforms for documenting her academic research and scholarly publications. Her research portfolio is associated with Artificial Intelligence and Smart Agriculture, particularly deep-learning-based approaches for agricultural disease and quality assessment.
Education
Srijah S is pursuing a Ph.D. at Thiagarajar College of Engineering, Madurai, affiliated with Anna University, with research on an Artificial Intelligence-Based Decision Support System for Smart Agriculture, beginning in January 2024. She completed her M.E. in Computer Science and Engineering at Pavendar Bharathidasan College of Engineering and Technology, Anna University, during 2018–2020, with a thesis on securing cloud data under key exposure. She completed her B.E. in Computer Science and Engineering from the same institution during 2010–2013, with research on rapid energy-loss prevention using the PLGP algorithm in wireless ad hoc sensor networks, and a Diploma in Computer Engineering from Sudharsan Polytechnic College during 2008–2010, with a project on implementing the Decision Tree algorithm in data mining.
Research Focus
Her research is centered on the application of Artificial Intelligence and Deep Learning to smart agriculture, combining Computer Vision, Machine Learning, and Explainable AI techniques to develop intelligent agricultural decision-support solutions. Her research areas include mango leaf disease detection, plant-stress detection, fruit-quality assessment and grading, precision agriculture, and automated image-based agricultural analysis.
Experience
Srijah S has academic, teaching, coordination, and research experience across engineering and technical education. She served as Lecturer and Training & Placement Coordinator at Pavendar Bharathidasan Polytechnic College, contributing to learning materials, student development, seminars, administration, and placement activities, and subsequently served in a Head of Department and Training & Placement coordination role involving departmental management, resource planning, curriculum implementation, and student career development. She later worked as an Assistant Professor at Pavendar Bharathidasan College of Engineering from March 2022 to June 2023, contributing to teaching, curriculum improvement, collaborative research, and the education of more than 3,000 students. Since February 2024, she has been working as a Research Scholar at Thiagarajar College of Engineering, conducting doctoral research in AI-based smart agriculture and developing deep-learning models for leaf disease, plant stress, and fruit grading.
Research Timeline & Research Publications
Her research development spans computer science, machine learning, cloud security, wireless sensor networks, and Artificial Intelligence applications in agriculture. Her current doctoral research, initiated in 2024, focuses on AI-based decision support for smart agriculture, with recent research contributions addressing mango leaf disease detection, mango fruit grading, plant-stress detection, and tomato leaf disease classification. The nomination form reports 12 publications comprising 4 journal articles, 7 conference papers, and 1 book chapter, with the five publication records provided in the application representing selected research contributions from 2025 and 2026.
Research Impact
Srijah S’s research contributes to the development of automated and intelligent agricultural assessment systems designed to support disease diagnosis, plant-stress identification, and fruit-quality grading. Her work applies deep learning and computer vision to practical agricultural challenges, with research published in journal and conference venues. The application reports 12 total publications, an h-index of 1, an i10-index of 0, and 3 citations.
Innovation & Intellectual Property
Her innovative research lies in the development and application of deep-learning and hybrid computer-vision frameworks for agricultural intelligence, including custom CNN-based mango leaf disease detection, hybrid feature-fusion approaches for mango grading, and automated plant-stress detection. These approaches are directed toward improving the efficiency and reliability of image-based agricultural assessment.
Research Projects & Funding
Her principal ongoing research project is her doctoral work, titled “Artificial Intelligence Based Decision Support System for Smart Agriculture,” undertaken at Thiagarajar College of Engineering, Madurai, under Anna University. Her research activities include developing deep-learning models for leaf disease detection, plant-stress analysis, and fruit grading. She is also supported through the Thiagarajar Research Fellowship, under which she has been working as a Research Scholar since February 2024.
Conference Contributions
Srijah S has contributed to conference-oriented research through publications addressing computer-vision and deep-learning applications in agriculture. Her submitted publication record includes a paper on tomato leaf disease classification using an improved ResNet50 architecture, published in the Proceedings of ACIT 2025 by Springer Nature. She has also participated in academic and professional activities including faculty seminars and served as a reviewer for the International Conference on Sustainable Computing and Optimized Practices for Excellence (SCOPE 2025).
Academic Excellence
Her academic development demonstrates sustained engagement with Computer Science, Artificial Intelligence, Machine Learning, and Computer Vision. In addition to her doctoral research and academic qualifications, she completed the NPTEL 12-week course “Neural Networks for Computer Vision and Natural Language Processing” with a Gold and Elite Certificate during January–April 2026. The application also records NPTEL Elite Certificates in “Introduction to Machine Learning” and “Python for Data Science,” together with her role as a conference reviewer.
Societal / Industry Contribution
Her research has practical relevance to agriculture through the application of Artificial Intelligence and Computer Vision for automated plant disease diagnosis, plant-stress detection, and fruit-quality grading. By developing computational approaches for precision agriculture, her work supports the broader objective of improving agricultural monitoring and decision-making through intelligent technologies. Her teaching and academic roles have also involved student development, curriculum improvement, career development, and engagement with more than 3,000 students.
Global Recognition
Srijah S’s research has gained scholarly visibility through publications in international journal and conference venues, including Pakistan Journal of Agricultural Sciences, Scientific Reports, and Springer Nature conference proceedings. Her academic recognition also includes the Thiagarajar Research Fellowship, NPTEL certifications in advanced Artificial Intelligence and Machine Learning-related subjects, and professional service as a conference reviewer.
Publications
1. Smart Artificial Intelligence-Based Mango Leaf Disease Detection Using a Custom CNN with K-Fold Cross-Validation — Srijah S., Sridevi S., Rajaram S., & Diesy C. Pakistan Journal of Agricultural Sciences, 63, 459–468, 2026. DOI: 10.21162/PAKJAS/26.385.
2. A Hybrid Feature Fusion Framework Integrating HSM-CNN and GLCM-SVM for Real-Time Mango Grading — Srijah S. & Sridevi S. Scientific Reports, 2026. DOI: 10.1038/s41598-026-61228-9.
3. MobileNetV2: A Computationally Efficient Model for Mango Leaf Disease Diagnosis — Sasitharan S., Subbiah S., Malaichamy N. D., & Chelliah D. Premier Journal of Science (PJS), 14, Article 100164, 2025. DOI: 10.70389/PJS.100164.
4. Hybrid Deep Learning Framework for Automated Mango Leaf Stress Detection in Precision Agriculture — Srijah S. & Sridevi S. Thiagarajar Journal of Engineering, Science, Design and Technology, 2(1), 2026.
5. Tomato Leaf Disease Classification Using an Improved ResNet50 Architecture — Srijah S., Sridevi S., Ezhil G. R., & Saranya T. Proceedings of ACIT 2025, Springer Nature, pp. 529–539, 2025.