Scopus Publications
- Blockchain-enabled Water Supply Chain Management: A Decentralized Approach to Sustainability and Efficiency
N. KOUSIKA, P. Ramani, V. Ramya, M. AKILANDEESWARI
Blockchain and the Water Supply Chain Opportunities Challenges and Innovations, 2025
This chapter explores how blockchain can transform water resource management, enabling an efficient decentralized solution to the global stream crisis. It highlights the role of blockchain in water distribution, sustainability and governance, along with the opportunities and challenges associated with its adoption. The integration of IoT and blockchain produces audit trails that make it easier to transparently gather and examine data that is decentralized and cannot be altered. The decentralized structure of blockchain makes it appropriate for locations without direct access to data centers. Water supply chain management is made more sustainable by ensuring equitable distribution, preventing waste and optimizing water logistics through the maintenance of an unchangeable record. IoT sensor and smart contract integration improves water distribution tracking in real time, automates regulatory compliance and guarantees fair water distribution. Additionally, the management of water rights is simplified, enabling equitable and legally verifiable transactions pertaining to the availability and use of water. - Secured Data Retrieval from Cloud using Attribute Based Encryption
R. Ravi, N. Kousika, S. Sureshkumar, N. Saranya, P. Nandhini, S. Anitha
Aip Conference Proceedings, 2025 - Brain Tumor MRI Classification Using ResNetLite with Squeeze and Excitation Blocks and a Groq-Powered Conversational Assistant
Kousika N, Nigitha S, Megavarshini S, Monika J, Joshitha M
2025 IEEE 1st International Conference on Innovations in Engineering and Next Generation Technologies for Sustainability Icinvents 2025, 2025
Brain tumor detection from Magnetic Resonance Imaging (MRI) plays a vital role in clinical decisionmaking. Conventional diagnosis can be time consuming and subjective, requiring expert radiologists. This study presents an end-to-end AI-driven framework that integrates deep learning-based tumor classification with an interactive medical chatbot. The classification model is a lightweight ResNetLite CNN augmented with Squeeze-and Excitation (SE) blocks to enhance channel-wise attention. It processes 128×128 grayscale MRIs and categorizes them into glioma, meningioma, pituitary, or notumor. A robust preprocessing and augmentation pipeline further strengthens generalization. The proposed model achieved a test accuracy above 96%, along with strong ROC-AUC scores across all classes. To enhance accessibility, a Groq-powered conversational assistant was incorporated using the LLaMA3.3-70B versatile model. Configured for concise (<50 words) responses with medical disclaimers, the assistant is directly linked to classification results. Users can upload MRI scans, receive predictions, and query outcomes through a Gradiobased interface that combines image upload, classification, and chat functionality. This work demonstrates the potential of integrating lightweight CNNs with attention mechanisms for reliable medical imaging, alongside large language model-driven assistants for patient engagement. Limitations include the modest dataset size and he absence of large-scale clinical validation. - Blockchain in Action Across the Supply Chain: Ethical Sourcing and Blockchain Verification
N. Kousika, T. Latha Maheswari, V. Ramya, K. Parvathy, R. Nirmala, K.M. Majidha Fathima
Sustainable Supply Chains and Carbon Footprint Reduction the Blockchain Advantage, 2025
This chapter methodically examines current blockchain-based supply chain management (SCM) solutions and categorizes according to storage mechanisms, cryptographic underpinnings and architectural models. Beyond mere compliance, an ethical supply chain demonstrates a business's dedication to ecologically sound manufacturing, ethical sourcing and fair distribution. Using blockchain as a collaborative platform, supply chain partners can safely share data, automate procedures and work together to produce value. Blockchain is susceptible to security risks even while it improves SCM through increased transparency, traceability and immutability. The chapter classifies the primary security threats and attack methods specific to blockchain-based SCM systems. It emphasizes that, in addition to being a technology advancement, integrating blockchain into supply chains requires organizational, cultural and strategic change. Maintaining integrity, traceability and trustworthiness becomes a continuous and adaptable process as emerging technologies such as edge computing, artificial intelligence, the Internet of Everything and quantum computing revolutionize data management. - Retraction Note: An improved privacy-preserving data mining technique using singular value decomposition with three-dimensional rotation data perturbation (The Journal of Supercomputing, (2021), 77, 9, (10003-10011), 10.1007/s11227-021-03643-5)
N. Kousika, K. Premalatha
Journal of Supercomputing, 2024 - Advanced Privacy-Preserving Framework Using Homomorphic Encryption and Adaptive Privacy Parameters for Scalable Big Data Analysis
International Journal of Intelligent Systems and Applications in Engineering, 2024 - Enhanced Wireless Communication Optimization with Neural Networks, Proximal Policy Optimization and Edge Computing for Latency and Energy Efficiency
N. Kousika, J. Babitha Thangamalar, N. Pritha, Beulah Jackson, M. Aiswarya
International Journal of Electrical and Electronics Research, 2024
This research proposes a novel approach for efficient resource allocation in wireless communication systems. It combines dynamic neural networks, Proximal Policy Optimization (PPO), and Edge Computing Orchestrator (ECO) for latency-aware and energy-efficient resource allocation. The proposed system integrates multiple components, including a dynamic neural network, PPO, ECO, and a Mobile Edge Computing (MEC) server. The experimental methodology involves utilizing the NS-3 simulation platform to assess latency and energy efficiency in resource allocation within a wireless communication network, incorporating an ECO, MEC server, and dynamic task scheduling algorithms. It demonstrates a holistic and adaptable approach to resource allocation in dynamic environments, showcasing a notable reduction in latency for devices and tasks. Latency values range from 5 to 20 milliseconds, with corresponding resource utilization percentages varying between 80% and 95%. Additionally, energy-efficient resource allocation demonstrates a commendable reduction in energy consumption, with measured values ranging from 10 to 30 watts, coupled with efficient resource usage percentages ranging from 70% to 85%. These outcomes validate the efficacy of achieving both latency-aware and energy-efficient resource allocation for enhanced wireless communication systems. The proposed system has broad applications in healthcare, smart cities, IoT, real-time analytics, autonomous vehicles, and augmented reality, offering a valuable solution to optimize energy consumption, reduce latency, and enhance system efficiency in these industries. - Enhancing Multimodal Sentiment Analysis with Deep Learning Techniques to Foster Emotional Intelligence
N Kousika, N Nanda Kumar, Elango Baskaran, M S Abbenaya, G Arthika, M Ashwanth
Proceedings of the 2024 10th International Conference on Communication and Signal Processing Iccsp 2024, 2024
Sentiment analysis (SA) is a critical process in understanding the emotions associated with data on social networking sites. Building upon this foundational concept, this paper introduces a sophisticated web application aimed at enabling users to submit diverse forms of content, including text, images, videos, and audio, for hate content assessment. This platform employs BERT CNN and VGG16 CNN algorithms for performing a thorough analysis of provided information in various formats. Emphasizing the identification of emotions in text and the detection of hate speech, the methodology extends to incorporate facial emotion detection for images. Through meticulous preprocessing, feature extraction, and ensemble learning, the proposed solution provides a robust framework for accurately identifying and mitigating hate content across various modalities. Experimental tests employing varied datasets validated the usefulness of the strategy, contributing to the advancement of hate content detection systems and fostering a safer online environment. - Design and Implementation of a Comprehensive Intelligent E-Learning Systems Integrated Web App Solution For Dyslexic Students
R. Deepalakshmi, J Shanthalakshmi Revathy, S.P. Revathy, N. Kousika
2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
The prevalent learning disorder, dyslexia impair a person's capacity for reading, writing, and spelling. But with the aid of successful interventions like multisensory techniques, phonics training, and assistive technology, persons with dyslexia can improve their reading and writing skills and excel in school and in daily life. This research paper "Dyslexi Duo" is a comprehensive solution for dyslexic students in all age group and includes 3 major sections. A Super Pad for the age group >18 to help them read digital documents like pdf with ease. An Interactive & Educational game -Hydra Hunt for the age group of 4-10 to learn formation of words with letters using both visual & auditory techniques. This game incorporates 4 key elements: storyline, clear goals, multiple levels, and points. An attached mobile application "Alpha360" for the age group of 3-8, which is an interactive multimedia learning app using 3d viewing, TextToSpeech, SpeechToText technology & a multisensory approach. This entire application was tested & evaluated with dyslexic students of the corresponding age group. Overall, our application can be a one stop solution to help dyslexic students overcome theirchallenges at an earlier age and achieve academic success. - Investigation on Optical Sensors for Heart Rate Monitoring
V. Vijeya Kaveri, V. Meenakshi, N. Kousika, A. Pushpalatha
Modeling and Optimization of Optical Communication Networks, 2023
This chapter focuses on how the optical heart rate monitoring (OHRM) device operates, the components involved, and issues and challenges faced while monitoring the heart rate. Most wearable optical heart rate monitoring devices use photoplethysmography (PPG) to compute the heartbeat. PPG is shorthand for reflecting out onto the surface and trying to measure the quantity of sunlight scattered by blood circulation. PPG sensors emphasize that the beam joining the body disperses in a familiar sequence when blood circulation patterns change. The PPG sensor's core elements, such as the optoelectronic transmitter, computerized pulse controller, magnetometer, and machine learning, are critical in estimating the heartbeat. PPG assessment in a state of rest (falling asleep, seated, and standing always) is incredibly easy, but measuring PPG throughout the exercise program (workouts, jumping, riding bikes) is challenging. In reality, you will face five significant challenges when using OHRM to create wearable devices such as optical noise, skin tone, cross-over the problem, location of the sensor, and low perfusion. These challenges can be overcome by choosing good opt mechanics and signal extraction algorithms. PPG sensor is used to measure breathing rate, heart rate variability, blood pressure, and cardiac efficiency [3]. OHRM may be used for lifestyle, in-session, and personal health metrics in a real-time scenario. We have also focused on parameters like wearability, accuracy, battery life, and time usage of the device. - Secure and Efficient Modified Dynamic Partition Routing Algorithm for Mobile Ad Hoc Networks
V. Ramya, N. Kousika, P. Rajasekaran, Vijeyakaveri. V, J. JaganPradeep
2022 International Conference on Advanced Computing Technologies and Applications Icacta 2022, 2022 - Retraction:An improved privacy-preserving data mining technique using singular value decomposition with three-dimensional rotation data perturbation
N. Kousika, K. Premalatha
Journal of Supercomputing, 2021 - Retraction: Machine Learning based Fraud Analysis and Detection System
N Kousika, G Vishali, S Sunandhana, M Arvind Vijay
Journal of Physics Conference Series, 2021 - A system for fake news detection by using supervised learning model for social media contents
N. Kousika, Deepa. S, Deephika. C, Dhatchaiyine. B M, Amrutha. J
Proceedings 5th International Conference on Intelligent Computing and Control Systems Iciccs 2021, 2021 - Performance Comparison of Multiwavelet and Multicontourlet Frame Based Features for Improving Classification Accuracy in Remote Sensing Images
K. Venkateswaran, N. Kasthuri, N. Kousika
Journal of the Indian Society of Remote Sensing, 2017 - Scope of E-assessment of answers in mathematical domain
International Journal of Civil Engineering and Technology, 2017 - Counsel for sphere with penchants using wareabouts
R. Divya, N. Kousika
Proceedings of 2016 Online International Conference on Green Engineering and Technologies IC Get 2016, 2017 - Performance analysis of GA and PSO based feature selection techniques for improving classification accuracy in remote sensing images
K. Venkateswaran, T. Sowmya Shree, N. Kousika, N. Kasthuri
Indian Journal of Science and Technology, 2016 - Modified K-means algorithm for automatic stimation of number of clusters using advanced visual assessment of cluster tendency
D. Sharmilarani, N. Kousika, G. Komarasamy
2014 IEEE 8th International Conference on Intelligent Systems and Control Green Challenges and Smart Solutions Isco 2014 Proceedings, 2014
RECENT SCHOLAR PUBLICATIONS
- Blockchain in Action Across the Supply Chain: Ethical Sourcing and Blockchain Verification
N Kousika, T Latha Maheswari, V Ramya, K Parvathy, R Nirmala, ...
Sustainable Supply Chains and Carbon Footprint Reduction: The Blockchain … , 2025
2025 - Blockchain‐enabled Water Supply Chain Management: A Decentralized Approach to Sustainability and Efficiency
N KOUSIKA, P Ramani, V Ramya, M AKILANDEESWARI
Blockchain and the Water Supply Chain: Opportunities, Challenges and … , 2025
2025 - Brain Tumor MRI Classification Using Resnetlite with Squeeze and Excitation Blocks and a Groqpowered Conversational Assistant
N Kousika, S Nigitha, S Megavarshini, J Monika, M Joshitha
2025 IEEE First International Conference on Innovations in Engineering and … , 2025
2025 - Secured data retrieval from cloud using attribute based encryption
R Ravi, N Kousika, S Sureshkumar, N Saranya, P Nandhini, S Anitha
AIP Conference Proceedings 3204 (1), 050011 , 2025
2025 - Enhanced Wireless Communication Optimization with Neural Networks, Proximal Policy Optimization and Edge Computing for Latency and Energy Efficiency
N Kousika, JB Thangamalar, N Pritha, B Jackson, M Aiswarya
International Journal of Electrical and Electronics Research 12 (2), 721-726 , 2024
2024
Citations: 4 - Enhancing Multimodal Sentiment Analysis with Deep Learning Techniques to Foster Emotional Intelligence
N Kousika, NN Kumar, E Baskaran, MS Abbenaya, G Arthika, M Ashwanth
2024 10th International Conference on Communication and Signal Processing … , 2024
2024 - Advanced privacy-preserving framework using homomorphic encryption and adaptive privacy parameters for scalable Big Data analysis
R Shanthi, MD Babu, N Kousika, C Vijayaraj, SB Choubey, ...
International Journal of Intelligent Systems and Applications in Engineering … , 2024
2024
Citations: 7 - Investigation on Optical Sensors for Heart Rate Monitoring
V Vijeya Kaveri, V Meenakshi, N Kousika, A Pushpalatha
Modeling and Optimization of Optical Communication Networks, 1-10 , 2023
2023 - Design and implementation of a comprehensive intelligent e-learning systems integrated web app solution for dyslexic students
R Deepalakshmi, JS Revathy, SP Revathy, N Kousika
2023 International Conference on Research Methodologies in Knowledge … , 2023
2023
Citations: 8 - Secure and Efficient Modified Dynamic Partition Routing Algorithm for Mobile Ad Hoc Networks
V Ramya, N Kousika, P Rajasekaran, J JaganPradeep
2022 International Conference on Advanced Computing Technologies and … , 2022
2022 - RETRACTED ARTICLE: An improved privacy-preserving data mining technique using singular value decomposition with three-dimensional rotation data perturbation
N Kousika, K Premalatha
The Journal of Supercomputing 77 (9), 10003-10011 , 2021
2021
Citations: 47 - A system for fake news detection by using supervised learning model for social media contents
N Kousika, D BM
2021 5th International Conference on Intelligent Computing and Control … , 2021
2021
Citations: 15 - Machine learning based fraud analysis and detection system
N Kousika, G Vishali, S Sunandhana, MA Vijay
Journal of Physics: Conference Series 1916 (1), 012115 , 2021
2021
Citations: 26 - An effective fragment-based iterative consensus clustering algorithm with Cluster Validity Measurement
NKD Srivaishnavi
International Journal of Pure and Applied Mathematics, 673-682 , 2018
2018 - SCOPE OF E-ASSESSMENT OF ANSWERS IN MATHEMATICAL DOMAIN
M Ramamurthy, N Kousika, S Mohana Gowri, K Mageswari
International Journal of Civil Engineering and Technology (IJCIET) 8 (10) , 2017
2017
Citations: 2 - Counsel for sphere with penchants using wareabouts
R Divya, N Kousika
2016 Online International Conference on Green Engineering and Technologies … , 2016
2016 - An Efficient Hybrid Data Perturbation Approach to Preserve Privacy
N Kousika, K Premalatha
Asian Journal of Research in Social Sciences and Humanities 6 (10), 453-461 , 2016
2016 - A Detailed Survey on Privacy Enhanced Data Processing and Management in Outsourced Environments
KN Premalatha K.
Proceedings of International Conference on Computer Communication and … , 2015
2015 - Modified K-means algorithm for automatic stimation of number of clusters using advanced visual assessment of cluster tendency
D Sharmilarani, N Kousika, G Komarasamy
2014 IEEE 8th International Conference on Intelligent Systems and Control … , 2014
2014
Citations: 3 - K-Means Algorithm for Centroid Detection and Estimation of Number of Clusters-A Review
DS Rani, N Kousika, G Komarasamy
Data Mining and Knowledge Engineering, 410-414 , 2013
2013
MOST CITED SCHOLAR PUBLICATIONS
- RETRACTED ARTICLE: An improved privacy-preserving data mining technique using singular value decomposition with three-dimensional rotation data perturbation
N Kousika, K Premalatha
The Journal of Supercomputing 77 (9), 10003-10011 , 2021
2021
Citations: 47 - Machine learning based fraud analysis and detection system
N Kousika, G Vishali, S Sunandhana, MA Vijay
Journal of Physics: Conference Series 1916 (1), 012115 , 2021
2021
Citations: 26 - A system for fake news detection by using supervised learning model for social media contents
N Kousika, D BM
2021 5th International Conference on Intelligent Computing and Control … , 2021
2021
Citations: 15 - Design and implementation of a comprehensive intelligent e-learning systems integrated web app solution for dyslexic students
R Deepalakshmi, JS Revathy, SP Revathy, N Kousika
2023 International Conference on Research Methodologies in Knowledge … , 2023
2023
Citations: 8 - Advanced privacy-preserving framework using homomorphic encryption and adaptive privacy parameters for scalable Big Data analysis
R Shanthi, MD Babu, N Kousika, C Vijayaraj, SB Choubey, ...
International Journal of Intelligent Systems and Applications in Engineering … , 2024
2024
Citations: 7 - Enhanced Wireless Communication Optimization with Neural Networks, Proximal Policy Optimization and Edge Computing for Latency and Energy Efficiency
N Kousika, JB Thangamalar, N Pritha, B Jackson, M Aiswarya
International Journal of Electrical and Electronics Research 12 (2), 721-726 , 2024
2024
Citations: 4 - Modified K-means algorithm for automatic stimation of number of clusters using advanced visual assessment of cluster tendency
D Sharmilarani, N Kousika, G Komarasamy
2014 IEEE 8th International Conference on Intelligent Systems and Control … , 2014
2014
Citations: 3 - SCOPE OF E-ASSESSMENT OF ANSWERS IN MATHEMATICAL DOMAIN
M Ramamurthy, N Kousika, S Mohana Gowri, K Mageswari
International Journal of Civil Engineering and Technology (IJCIET) 8 (10) , 2017
2017
Citations: 2 - Blockchain in Action Across the Supply Chain: Ethical Sourcing and Blockchain Verification
N Kousika, T Latha Maheswari, V Ramya, K Parvathy, R Nirmala, ...
Sustainable Supply Chains and Carbon Footprint Reduction: The Blockchain … , 2025
2025 - Blockchain‐enabled Water Supply Chain Management: A Decentralized Approach to Sustainability and Efficiency
N KOUSIKA, P Ramani, V Ramya, M AKILANDEESWARI
Blockchain and the Water Supply Chain: Opportunities, Challenges and … , 2025
2025 - Brain Tumor MRI Classification Using Resnetlite with Squeeze and Excitation Blocks and a Groqpowered Conversational Assistant
N Kousika, S Nigitha, S Megavarshini, J Monika, M Joshitha
2025 IEEE First International Conference on Innovations in Engineering and … , 2025
2025 - Secured data retrieval from cloud using attribute based encryption
R Ravi, N Kousika, S Sureshkumar, N Saranya, P Nandhini, S Anitha
AIP Conference Proceedings 3204 (1), 050011 , 2025
2025 - Enhancing Multimodal Sentiment Analysis with Deep Learning Techniques to Foster Emotional Intelligence
N Kousika, NN Kumar, E Baskaran, MS Abbenaya, G Arthika, M Ashwanth
2024 10th International Conference on Communication and Signal Processing … , 2024
2024 - Investigation on Optical Sensors for Heart Rate Monitoring
V Vijeya Kaveri, V Meenakshi, N Kousika, A Pushpalatha
Modeling and Optimization of Optical Communication Networks, 1-10 , 2023
2023 - Secure and Efficient Modified Dynamic Partition Routing Algorithm for Mobile Ad Hoc Networks
V Ramya, N Kousika, P Rajasekaran, J JaganPradeep
2022 International Conference on Advanced Computing Technologies and … , 2022
2022 - An effective fragment-based iterative consensus clustering algorithm with Cluster Validity Measurement
NKD Srivaishnavi
International Journal of Pure and Applied Mathematics, 673-682 , 2018
2018 - Counsel for sphere with penchants using wareabouts
R Divya, N Kousika
2016 Online International Conference on Green Engineering and Technologies … , 2016
2016 - An Efficient Hybrid Data Perturbation Approach to Preserve Privacy
N Kousika, K Premalatha
Asian Journal of Research in Social Sciences and Humanities 6 (10), 453-461 , 2016
2016 - A Detailed Survey on Privacy Enhanced Data Processing and Management in Outsourced Environments
KN Premalatha K.
Proceedings of International Conference on Computer Communication and … , 2015
2015 - K-Means Algorithm for Centroid Detection and Estimation of Number of Clusters-A Review
DS Rani, N Kousika, G Komarasamy
Data Mining and Knowledge Engineering, 410-414 , 2013
2013
