Empowering integrity and confidentiality in smart healthcare systems through effective edge cryptographic strategies R. Gowthamani, S. Oswalt Manoj, K. Sasi Kala Rani Automatika, 2025 Cybersecurity threats pose a significant risk to IoT-based smart healthcare technologies by compromising patient safety, disrupting services, and exposing sensitive health data to unauthorized access and misuse. This research aims to strengthen data integrity and confidentiality in smart healthcare systems by developing edge-level cryptographic strategies tailored for IoT-enabled edge environments, addressing the security and privacy challenges of resource-constrained devices. The proposed methodology Cryptographic Security Framework with SignaVault Authentication (CSFVA) integrates lightweight cryptographic techniques with edge computing to secure healthcare data efficiently and in real time. The novelty of this research lies in the unified implementation of a layered cryptographic pipeline, comprising Elliptic Curve Cryptography (ECC) for encryption, a Secure Hash Crypto Technique (SHCT) for data integrity, and a Signa-Vault (SV) authentication mechanism for user and device verification. This tri-layered approach ensures data confidentiality, integrity, and authenticity while sup porting the low-latency requirements of edge computing environments. Performance evaluation shows the model's efficiency, achieving a processing time of 5.81 seconds, memory use of 45.78 MB, power consumption of 4.2 W, and throughput of 99.67%. These results indicate that the proposed solution effectively balances security and resource efficiency, making it suitable for resource-limited IoT healthcare and scalable smart healthcare systems.
AI-Driven Optimization in Sustainable Smart Greenhouses: Leveraging LARA for Latency-Aware Resource Allocation in Stream Processing Analytics Akey Sungheetha, R C Karpagalakshmi, K Sasi Kala Rani, R Rajesh Sharma, Sheila Mahapatra 2nd International Conference on IT Innovations and Knowledge Discovery Itikd 2024, 2025 This paper presents a novel Latency-Aware Resource Allocation (LARA) framework for sustainable smart greenhouses that achieves significant performance improvements across multiple metrics. By integrating advanced stream processing analytics with machine learning algorithms, our solution optimizes resource allocation while prioritizing latency-sensitive operations. Experimental results across test deployments in Denmark, Italy, and India demonstrate a 45% improvement in energy efficiency, 62% reduction i n response time, a nd 38% increase in resource utilization compared to traditional methods. The LARA framework achieves 99.4% system reliability while maintaining a 94% crop yield improvement through precise environmental control. Performance analysis reveals that our approach reduces operational costs by 32% while increasing overall system throughput by 57%. This comprehensive solution addresses the critical challenges of latency management and resource optimization in smart greenhouse environments, providing a scalable and sustainable approach to modern agricultural technology integration.
AI-Enhanced Triboelectric Surface Analysis for Smart Urban Accessibility Pattern Detection Akey Sungheetha, Rajesh Sharma R, Sheila Mahapatra, Niharika Agrawal, Subhav Singh, K Sasi Kala Rani Procedia Computer Science, 2025 By combining triboelectric sensors with artificial intelligence, this study offers a novel method for detecting patterns in urban accessibility. We present TriboPATH (Triboelectric Pattern Analysis for Transit Heatmaps), a novel framework that integrates deep learning and triboelectric signal processing for real-time accessibility pattern recognition, building on previous work in self-powered angle sensors and urban analytics. Through the use of smart surfaces equipped with triboelectric sensors, the system records movement patterns and uses a specially designed neural network architecture to convert them into accessibility measures. Our solution outperforms current approaches by achieving 94.7% accuracy in pattern recognition over a range of view distances and angles. The system provides a long-term solution for smart city accessibility monitoring, exhibiting strong performance across 13 global metropolitan datasets.
Stock Movement Prediction with Artificial Intelligence-Based Cognitive Analysis K Sasi Kala Rani, M Anirudhan Prisha, Rajesh Sharma R, Sujan Prakash P, Sonali N, Akey Sungheetha 2025 2nd International Conference on New Frontiers in Communication Automation Management and Security Iccams 2025, 2025 One of the most important research areas in financial markets is stock trend prediction. Stock trend prediction: predicting the future price ups and downs of a stock. The traditional models that were used mainly depended on previous price data, but recent studies have shown that combining external factors with these models significantly improves the prediction. This research intends on showing how sentiment analysis can be used to predict stock trends. In these case, news articles, social media posts, or financial statements are the NLP tools analysis these and come up with a few steps. In casual language, the understanding of sentiments from all these sources of unorganized texts is the basis for affective and psychological impacts on investor behavior. The amazing concept explains in detail to combine sentiment signals with already going-on price of data for the purpose of predicting stock trends. Thus, it is still possible for companies to come up with even better stocks prediction strategies that are consistent and adaptable, because both quantitative and qualitative inputs are used.
Waste Object Detection Using Mini Submarine in Water Bodies Using Adaptive Multi-Modal Fusion Transformer K Sasi Kala Rani, Arpitha, Akshay K M, Rajesh Sharma R, Sachin Shrishail Bhumar, Guru Ramdas, TP'Abhishek Adhav, Akey Sungheetha 2025 International Conference on Data Science and Business Systems Icdsbs 2025, 2025 In the modern era, water pollution poses a serious threat to marine ecosystems, leading to damage to aquatic life and in turn, a disastrous impact on long-term environmental threat. The system proposes advanced computer vision techniques to detect and classify the waste trash in the underwater environment. Methods like You Only Look Once (YOLO) and AUVs(Autonomous Underwater Vehicles) have practical limitations that reduce their effectiveness in underwater settings. To overcome the challenges and constraints, a novel algorithm Adaptive Multi-Modal Fusion Transformer (AMFT) is proposed for waste detection in an enhanced way. The proposed work compares the contemporary object detection framework, YOLO model, and AMFT. The system uses datasets with images of underwater with trash including plastic wastes, aluminum wastes and other debris for training and testing. The advantage of the proposed work is cost effectiveness and scalability. Waste hotspots can be identified and cleanup operations can be performed with high priority. The experimental results infer that AMFT based detection system performs extraordinarily well by achieving accurate waste recognition in different underwater conditions, like varying light levels and turbidity. The combination of advanced computer Vision techniques and real-time detection capabilities, the system offers a sustainable and scalable solution for identifying underwater waste, for cleaner water bodies and a more sustainable future. The experimental results showed that the accuracy of the clear water system exceeded 94%, while in dirty water conditions, accuracy decreased slightly but remained above 82 %
Early Diabetics Prediction Using Multi Model Approaches in Machine Learning Renugadevi G, Sasi Kala Rani K, Oswalt Manoj S, Saranya N, Goudhaman M Proceedings of 9th International Conference on Science Technology Engineering and Mathematics the Role of Emerging Technologies in Digital Transformation Iconstem 2024, 2024 Diabetics is the maximum common non-transmissible disease and the deadliest disease worldwide, affecting five hundred and thirty-seven mountain individuals. Diabetics container be carried on by a variety of sources, with an unhealthy diet, high BP, abnormal cholesterol, a personal antiquity of the disease, and inactivity. Early diabetes prediction using IoT can be done by monitoring various health parameters and identifying patterns that may indicate the development of diabetes. In Proposed work, Mendeley Data Repository is a real-time data have been taken for early diabetes prediction. The Proposed hybrid Backward elimination method with Maximum Relevance, Minimum Redundancy (BE-MRMR) algorithm When integrating backward elimination and the MRMR algorithm, you can use the strengths of both strategies to identify a small but informative set of features for early diabetic prediction, potentially enhancing model interpretability and generalisation. Finally, after eliminating features, left with a subdivision of structures that subsidize most to the replica's performance. This feature given to various machine learning classifiers RF, ANN, SVM to predict early diabetics. These models produce performance matrices is calculated in terms of accuracy, specificity, precision and sensitivity.
Enhanced Criminal Identification through MTCNN: Leveraging Advanced Facial Recognition Technology Gowthamani R, Sasi Kala Rani K, Gayathri D, Geetha R, Harish S, Rohini M Proceedings of 9th International Conference on Science Technology Engineering and Mathematics the Role of Emerging Technologies in Digital Transformation Iconstem 2024, 2024 Due to the rise in crime, it is harder for police to identify criminals in public. Constantly reviewing surveillance footage is a laborious process that requires careful attention to detail and is not cognitively stimulating, which increases the likelihood of mistakes. Even though many existing systems for the identification of criminals have been developed, their accuracy in recognizing them is very low. The project's goal is to use Multi-task Cascaded Convolutional Neural Networks to create an advanced criminal detection and alert system. The MTCNN model is trained using a variety of datasets that include the face features, attire, and other distinguishable traits of well-known criminals. Improving the network's capacity to identify patterns and characteristics that are essential for precise criminal identification is part of the training process. During real-time operation, the system continuously analyzes video streams from surveillance cameras, applying the trained MTCNN model to detect and identify potential criminals in public places. The utilization of MTCNN s enables the system to overcome challenges such as varying lighting conditions, partial obstructions, and changes in appearance, ensuring reliable performance in dynamic environments. Upon the detection of a potential match, the system triggers an alert mechanism, notifying law enforcement agencies in real-time. Relevant information is included in the notifications, such as the image, location, and details of the identified person. Our proposed system has the potential to enhance accuracy to 96.2 % for the identification of criminals in both public and private places.
Automated Glaucoma Screening in Retinal Fundus Imagery: Leveraging a Convolutional Neural Network Framework Tina Babu, M. Vengateshwaran, K. Sasi Kala Rani, Ramya Raghunath Joshi, Rekha R Nair, R Rajesh Sharma 2024 3rd International Conference for Advancement in Technology Iconat 2024, 2024 Glaucoma, a prevalent eye ailment, necessitates early detection and treatment to prevent irreversible vision loss. Conventional screening methods are often time-intensive and require specialized expertise, limiting accessibility, especially in remote areas lacking ophthalmologists. This study introduces a CNN model, harnessing deep learning to analyze retinal images and extract glaucomatous indicators. Evaluation of the CNN’s performance on a diverse dataset includes accuracy, sensitivity, specificity, and F-score assessment. Results underscore the CNN’s promise as an efficient and dependable tool for automated glaucoma screening. This advancement offers optimism for enhancing early diagnosis and intervention, critical for managing this sight-threatening condition.
Adaptive Stream Processing Framework for Energy-Efficient Smart Greenhouses Using Neuromorphic Computing Akey Sungheetha, R Rajesh Sharma, Sheila Mahapatra, K Sasi Kala Rani, A. Ezil Sam Leni, R Tamilarasi Proceedings of 5th International Conference on Iot Based Control Networks and Intelligent Systems Icicnis 2024, 2024 This paper presents an innovative framework combining neuromorphic computing and stream processing analytics for energy-efficient smart greenhouse management. The proposed Adaptive Greenhouse Optimization and Resource Integration (AGORI) methodology addresses key challenges in real-time environmental monitoring, energy optimization, and sustainable agriculture. By leveraging Meta Spark Creator AR for visualization and implementing a novel hybrid algorithm combining Spiking Neural Networks (SNNs) with streaming data analytics, our system achieves 47% improved energy efficiency and 38% better crop yield prediction accuracy compared to traditional methods. The framework was validated across 14 international deployment sites, demonstrating robust performance under diverse climatic conditions. Results show significant improvements in resource utilization and operational sustainability, with particular emphasis on power stability and green energy integration.
AI Powered Sentiment Analysis of Social Media Presence Tina Babu, Rajesh Sharma R, K. Sasi Kala Rani, Akey Sungheetha, B. Priyadarshini, A. Nivetha 2nd IEEE International Conference on Advances in Information Technology Icait 2024 Proceedings, 2024
AI-Powered Chat Agent: Revolutionizing Online Shopping Tina Babu, Sasi Kala Rani K Department, Shalini M, Shalini S, Yuvashree S, Rajesh Sharma R 2nd International Conference on Signal Processing Communication Power and Embedded Systems Scopes 2024, 2024
Applications of quantum AI for healthcare K. Sasi Kala Rani, J. M. Priyadharsheni, B. Karthikeyan, G. S. Pugalendhi Quantum Computing and Artificial Intelligence Training Machine and Deep Learning Algorithms on Quantum Computers, 2023
Knowledge visualization: AI integration with 360-degree dashboards Explainable Artificial Intelligence Xai Concepts Enabling Tools Technologies and Applications, 2023
Literature survey for improving quality of service for multimedia applications Life Science Journal, 2013
Improving QoS - Weighted throughput of multimedia packets through optimal fragmentation using different optimization techniques Life Science Journal, 2013
