EEG Emotion Recognition in Brain Computer Interface Through Neural Networks and Adaptive Machine Learning Yuvaraj D, Jagathpranesh R, T. Velmurugan, Gokul Anand S, Meenalochini M, Mithrun R S Iccids 2026 9th International Conference on Computational Intelligence in Data Science, 2026 Human Computer Interaction (HCI), affective computing, and mental health have experienced a sharp rise in use in EEG signal-based emotion classfication. Accurate and generalized emotion finding from Electroencephalography signal is a critical step for realizing the practical usage of functional Brain-Computer Interfaces (BCI). This work tracks a neat flowchart designed for dimensional emotion classification (Valence and Arousal) using public DEAP dataset. The primary innovation here is the use of a Multi-Task Time-Series Transformer (TST) model, which uses a Self-Attention method to dynamically filter subject specific noise and extract general neural patterns. The developed Time-Series Transformer framework predicts both Valence and Arousal simultaneously, by leveraging the intrinsic relation between two emotion factor. We used the Subject-Independent (LOSOCV) protocol combined with a non-leaking feature scaling strategy to ensure test data integrity. Experimental results confirm that the TST model’s effectiveness about 78.05% mean accuracy which was achieved for Valence classification, demonstrating state-of-the-art generalization capability across subjects. And the Arousal dimension came to 50.94% in the generalized test, experimentally confirming that Arousal-related features are highly subject-specific and thus demand individu-alized calibration. The proposed methodology establishes a new, verifiable benchmark for generalized EEG emotion recognition and automatically highlighting the potential and current limitations of BCI-based affective computing.
Smart Diagnosis of Cauliflower Diseases Using Deep Learning and Feature Optimization Meenalochini M., Amudha P. Journal of Innovative Image Processing, 2025 Cauliflower (Brassica oleracea var. botrytis) is one of the most popular crops that are subject to a variety of diseases affecting the leaf apparatus, which impact quality and production. Despite the progress in deep learning, appropriate disease detection under real-field conditions remains a serious problem. This paper introduces an expert system GNN-PDP, which is a novel Graph Neural Network based model for the automated classification of cauliflower leaf diseases using images taken with a smartphone. A Region Growing Segmentation (RGS) is used to extract perceptual regions in this structure and statistical features are utilized as graph node features. The Salp Swarm Algorithm (SSA) finds optimal features that result in better generalization. A total of 750 images were gathered in four categories of diseases. The assessment was made based on accuracy, precision, sensitivity, specificity, and F1-score, in relation to Linear Discriminant Analysis (LDA), Random Forest (RF), Deep Neural Networks (DNN), and CNN classifiers. GNN-PDP achieved a superior classification accuracy of 89.0%, outperforming all other experiments. The model has great potential for smart agriculture in disease management.
Capsule Network for Pioneering Disease Detection in Cauliflower Cultivation with Mobile Application Development Meenalochini M, Amudha P Journal of Machine and Computing, 2025 Cauliflower cultivation is challenged by various diseases that can severely impact crop health and yield. Traditional disease detection methods are often labour-intensive and prone to errors, highlighting the need for automated and efficient prediction systems. In this study, we propose the use of Capsule Neural Networks (CapsNet) for disease prediction in cauliflower cultivation named as CauliCaps. CapsNet introduces dynamic routing units to capture spatial relationships and hierarchical structures within images more effectively than traditional Convolutional Neural Networks (CNNs). We assemble a comprehensive dataset of labelled cauliflower leaf images, preprocess them for optimal input, and train the CapsNet model using an appropriate loss function and optimization algorithm. Metrics including accuracy, precision, recall, and F1-score are used to compare the model's performance to state-of-the-art techniques. Additionally, we discuss the development of a mobile application based on the trained CapsNet model for real-time disease diagnosis in cauliflower cultivation. This research aims to advance disease prediction in cauliflower cultivation, enabling proactive management strategies and ultimately contributing to improved crop health and sustainability.
Effective Task Scheduling based on Candidate Optimization Algorithm (COA) in Heterogeneous NoC-Based MPSoC Sathis Kumar K, Janani T, Karpagavadivu K, Raihana A, Meenalochini M Proceedings 4th International Conference on Smart Technologies Communication and Robotics 2025 Stcr 2025, 2025 Efficiency of the network communication and performance of the Network of Chips (NoC) with respect to the Quality of Service is greatly affected by the contention of the shared resources. Here, in this paper the design of MPSoC (MultiProcessor System on Chip) is done which is based on Network of Chips involves two steps – scheduling the sub tasks with respect to the Processing elements (PE) and further mapping the PE to the switching nodes which is present in the NoC topology. The evolutionary computation technique is applied once the development of the task model is completed to complete the first step which in turn helps in achieving less transfer cost as well as the running and execution time. The algorithm used in the proposed approach is the Candidate Optimization Algorithm (COA). Based on the NoC topology minimal expected network transmission delay along with less resource and power consumption is used to achieve the second step. The results obtained out of the comparison shows the resources and power consumption which is preferred by the COA algorithm in designing the system.
Advancements in Allergy Detection and Management: Leveraging YOLOv8 and Large Language Models for Enhanced Diagnostic Accuracy M. Meenalochini, M. Karthika, S. Pranesan, J. Regiin Arul Rithik Proceedings IEEE 2024 1st International Conference on Advances in Computing Communication and Networking Icac2n 2024, 2024 This study introduces an integrated system designed to enhance allergy management by combining advanced AI technologies with practical healthcare applications. Utilizing Large Language Models (LLMs) and YOLOv8 object detection, our approach leverages LLMs for in-depth analysis of user-submitted food diaries, offering personalized dietary advice and allergen detection. Simultaneously, YOLOv8 technology is deployed to identify signs of allergic reactions from images swiftly, enabling rapid responses to potential allergens. The system's architecture includes a robust server-laptop setup with PostgreSQL, ensuring secure and efficient data handling. Key components such as CrewAI facilitate modular tasks like dietary analysis, allergy detection, and interactive health chats through specialized agents and dynamic task execution, enhancing user engagement and system responsiveness. This holistic approach not only improves allergy management but also integrates seamlessly into clinical and daily settings, providing a user-friendly interface for continuous health monitoring and management. The system’s adaptability makes it a promising tool for healthcare professionals and individuals aiming to manage allergies effectively.
Smart Recommendation System For Flourishing Gardens Using Deep Learning Techniques M. Meenalochini, S. Kishore, V. Sabarika, S. Nandhakumar Proceedings IEEE 2024 1st International Conference on Advances in Computing Communication and Networking Icac2n 2024, 2024 Our project introduces a specialized model focusing on companion planting, specifically for the onion-carrot pair. It integrates advanced deep learning algorithms, including graph neural networks (GNNs), collaborative filtering, and content-based filtering. The model offers personalized companion plant recommendations based on user input and incorporates pest control and disease prediction functionalities tailored to selected plants. Through thorough data analysis and consideration of user preferences, the model provides customized suggestions to optimize plant growth and health, taking into account environmental factors such as climate conditions. Utilizing GNNs, the model enhances pest control by analyzing images to identify pests, while collaborative filtering refines pest management strategies based on similar contexts. For disease prediction, content-based filtering evaluates historical data and plant traits to forecast disease risks, facilitating proactive measures for plant health protection. By harnessing advanced deep learning techniques and tailored recommendations, this project aims to empower agricultural practitioners with actionable insights for sustainable gardening practices, enhancing crop productivity, and promoting environmental stewardship in agriculture.
GNN-based Disease Detection and Classification in Cassava Leaf M Meenalochini, A Amalroshini, K L Megha Nandhini, C R Sogil Murugan Proceedings of 5th International Conference on Iot Based Control Networks and Intelligent Systems Icicnis 2024, 2024 Cassava, a staple crop for millions of people worldwide, is highly susceptible to various leaf diseases, which can significantly reduce crop yields. Detecting and classifying these diseases at an early stage is crucial for effective disease management and crop protection. In this paper, we propose a novel approach for cassava leaf disease classification by combining Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs). While CNNs excel at extracting local features from images, they often fail to capture complex spatial relationships between different regions of the leaf. To address this limitation, we integrate GNNs, which are well-suited for learning from irregular, structured data, such as the vein patterns and disease spread structures found in cassava leaves. By modeling the relationship between different regions of the cassava leaf as a graph G (V, E), where V represents nodes corresponding to superpixel regions of the leaf, and E represents edges capturing spatial relationships, the hybrid CNN-GNN model offers a more comprehensive and accurate classification system. The model is trained and evaluated on a dataset of cassava leaf images covering multiple disease categories, demonstrating superior performance over traditional CNN-based image classification techniques. This approach provides a scalable solution for improving the detection and management of cassava leaf diseases.
Perceptual Hashing for Content Based image Retrieval M. Meenalochini, K. Saranya, G.V. Rajkumar, Akash Mahto Proceedings of the 3rd International Conference on Communication and Electronics Systems Icces 2018, 2018 Content based image retrieval plays a most important role in large collection of images and image database. It will search the image based on user's request and it involves the image features like color, texture and shape. In this paper, CBIR using Perceptual hashing is implemented with feature extraction techniques like Color histogram, Gabor filters, and Canny's edge detection. The hash codes are generated for feature extracted images and similarity measure is computed for retrieved images. By using hashing codes, we can achieve linear search time complexity and can speed up the retrieving process.
Secure continuous aggregation and load balancing with false temporal pattern identification for wireless sensor networks T. Abirami, M. Meenalochini, S. Thilakraj Icetech 2015 2015 IEEE International Conference on Engineering and Technology, 2015 Continuous aggregation is required in sensor applications to obtain the temporal variation information of aggregates. It helps the users to understand how the environment changes over time and track real time measurements for trend analysis. In the continuous aggregation, the attacker could manipulate a series of aggregation results through compromised nodes to fabricate false temporal variation patterns of the aggregates. Existing secure aggregation schemes conduct one individual verification for each aggregation result. Due to the high frequency and the long period of a continuous aggregation in every epoch, the false temporal variation pattern would incur a great communication cost. In this paper, we detect and verify a false temporal variations pattern by checking only a small part of aggregation results to reduces a verification cost. A sampling based approach is used to check the aggregation results and we also proposed a security mechanisms to protect the sampling process.
RECENT SCHOLAR PUBLICATIONS
GNN Based Cauliflower Plant Disease Prediction Using Deep Learning Techniques PA Meenalochini. M International Journal of Intelligent System and Application in Engineering … , 2024 2024
Using Deep Learning Techniques M Meenalochini, P Amudha Proceedings of World Conference on Artificial Intelligence: Advances and … , 2023 2023
Cauliflower Plant Disease Prediction Using Deep Learning Techniques World Conference on Artificial Intelligence:Advances and Applications(WCAIAA … , 2023 2023
“Weapon detection using YOLO V3” International virtual conference on Advances in Digital Transformation … , 2022 2022
Soil Maintenance and Protection of Crops using IoT AICTE sponsored International Conference on Emerging Trends in Communication … , 2021 2021
Iot Based Soil Maintenance And Protection Of Crops From Excess Water Using Prediction Algorithm Design Engineering 50 (6) , 2021 2021
Finding Missed Product and Loss Prediction Using Market Basket Analysis(MBA) Turkish Online Journal of Qualitative Inquiry 12 (3) , 2021 2021
“Iot fog based fire Monitoring System” International e-Conference on Information, Communication and Networking … , 2021 2021
Enhanced Trust Based Secure Routing for MANET A Gokilavani Journal of Huazhong University of Science and Technology 50 (3) , 2021 2021
Diagnosis and Management of COVID-19 using Artificial Intelligence IN Patent App. 202141044540 A , 2021 2021
Analysis of Emotion Detection for Infant Cry MJ Meenalochini.M International conference on Intelligent Communication Technologies and … , 2019 2019
Cloud Backup Services using Geneic Algorithm NG Meenalochini.M International journal for scientific Research and Development 6 (7) , 2018 2018
Perception Hashing for Content based Image retrieval M Meenalochini. IEEE International conference on Communications and Electronic Systems(ICCES … , 2018 2018 Citations: 7
Indian Journal of Engineering R Kanmani, M Meenalochini, R Keerthana Indian Journal of Engineering 13 (32), 172-176 , 2016 2016
Accurate and faster converging technique for wireless sensor networks in the presence of collusion attacks R Kanmani, M Meenalochini, R Keerthana Indian Journal of Engineering 13 (32), 172-176 , 2016 2016
Secure data aggregation with false temporal pattern identification in wireless sensor networks M Meenalochini. International Journal of Engineering and Advanced Technology(IJEAT) 4 (2) , 2016 2016
Secure continuous aggregation and load balancing with false temporal pattern identification for wireless sensor networks T Abirami, M Meenalochini, S Thilakraj 2015 IEEE International Conference on Engineering and Technology (ICETECH), 1-3 , 2015 2015
SECURE CONTINUOUS AGGREGATION WITH LOAD BALANCING FOR WIRELESS SENSOR NETWORKS M Meenalochini, T Abirami, PG Scholar 2015
Secure Continuous Aggregation with Load Balancing for Wireless Sensor Networks DT Abirami, M Meenalochini International Journal of Advanced Research Trends in Engineering and … , 2015 2015 Citations: 2
Secure Data Aggregation with False Temporal Pattern Identification for Wireless Sensor Networks SAT Abirami, M Meenalochini, S Anandamurugan International Journal of Engineering and Advanced Technology, 195-197 , 2014 2014 Citations: 2
MOST CITED SCHOLAR PUBLICATIONS
Perception Hashing for Content based Image retrieval M Meenalochini. IEEE International conference on Communications and Electronic Systems(ICCES … , 2018 2018 Citations: 7
Cauliflower plant disease prediction using deep learning techniques M Meenalochini, P Amudha International Conference on Worldwide Computing and Its Applications, 163-175 , 1997 1997 Citations: 7
Secure Continuous Aggregation with Load Balancing for Wireless Sensor Networks DT Abirami, M Meenalochini International Journal of Advanced Research Trends in Engineering and … , 2015 2015 Citations: 2
Secure Data Aggregation with False Temporal Pattern Identification for Wireless Sensor Networks SAT Abirami, M Meenalochini, S Anandamurugan International Journal of Engineering and Advanced Technology, 195-197 , 2014 2014 Citations: 2
GNN Based Cauliflower Plant Disease Prediction Using Deep Learning Techniques PA Meenalochini. M International Journal of Intelligent System and Application in Engineering … , 2024 2024
Using Deep Learning Techniques M Meenalochini, P Amudha Proceedings of World Conference on Artificial Intelligence: Advances and … , 2023 2023
Cauliflower Plant Disease Prediction Using Deep Learning Techniques World Conference on Artificial Intelligence:Advances and Applications(WCAIAA … , 2023 2023
“Weapon detection using YOLO V3” International virtual conference on Advances in Digital Transformation … , 2022 2022
Soil Maintenance and Protection of Crops using IoT AICTE sponsored International Conference on Emerging Trends in Communication … , 2021 2021
Iot Based Soil Maintenance And Protection Of Crops From Excess Water Using Prediction Algorithm Design Engineering 50 (6) , 2021 2021
Finding Missed Product and Loss Prediction Using Market Basket Analysis(MBA) Turkish Online Journal of Qualitative Inquiry 12 (3) , 2021 2021
“Iot fog based fire Monitoring System” International e-Conference on Information, Communication and Networking … , 2021 2021
Enhanced Trust Based Secure Routing for MANET A Gokilavani Journal of Huazhong University of Science and Technology 50 (3) , 2021 2021
Diagnosis and Management of COVID-19 using Artificial Intelligence IN Patent App. 202141044540 A , 2021 2021
Analysis of Emotion Detection for Infant Cry MJ Meenalochini.M International conference on Intelligent Communication Technologies and … , 2019 2019
Cloud Backup Services using Geneic Algorithm NG Meenalochini.M International journal for scientific Research and Development 6 (7) , 2018 2018
Indian Journal of Engineering R Kanmani, M Meenalochini, R Keerthana Indian Journal of Engineering 13 (32), 172-176 , 2016 2016
Accurate and faster converging technique for wireless sensor networks in the presence of collusion attacks R Kanmani, M Meenalochini, R Keerthana Indian Journal of Engineering 13 (32), 172-176 , 2016 2016
Secure data aggregation with false temporal pattern identification in wireless sensor networks M Meenalochini. International Journal of Engineering and Advanced Technology(IJEAT) 4 (2) , 2016 2016
Secure continuous aggregation and load balancing with false temporal pattern identification for wireless sensor networks T Abirami, M Meenalochini, S Thilakraj 2015 IEEE International Conference on Engineering and Technology (ICETECH), 1-3 , 2015 2015
