Energy efficient hierarchical clustering based dynamic data fusion algorithm for wireless sensor networks in smart agriculture Dhamodharan Srinivasan, Ajmeera Kiran, S. Parameswari, Jeevanantham Vellaichamy Scientific Reports, 2025 A potential strategy to increase agricultural yields and maximize resource use has emerged: smart agriculture. In order to monitor numerous environmental characteristics, wireless sensor networks (WSNs) are essential. Individual sensor data may be noisy, redundant, and not correctly reflect the status of the farm as a whole. The energy constraints of WSN nodes and the need for accurate event detection, however, make it difficult to develop reliable and efficient systems. This research proposes a fresh approach to these issues by using hierarchical clustering-based dynamic data fusion techniques for WSNs in smart agriculture. In order to increase energy efficiency and event detection precision in smart agriculture, this study suggests employing dynamic data fusion for WSNs that is based on hierarchical clustering. The hierarchical clustering technique is used initially in the suggested method to group sensor nodes into clusters. A dynamic data fusion method is used to collect and fuse data inside each cluster, generating indicative information about the cluster's status. This guarantees effective network resource utilization while minimizing data redundancy. In order to classify and anticipate events, the Extreme Learning Machine (ELM) technology is also used, allowing for the real-time identification of key events. The experimental outcomes show considerable increases in energy effectiveness and event detection precision, which makes this strategy an important contribution to the field of smart agriculture. The proposed model is implemented in Python software and has an accuracy of about 99.54% which is 1.81% higher than other existing methods like CH selection, K- prediction and data aggregation.
Machine learning driven early prediction of cardiac arrest Parameswari S, Jeevitha S, Sree Rathna Lakshmi NVS, Swetha BV Technology and Health Care, 2025 Background Cardiac Arrest (CA) is a major cause of mortality globally, often occurring suddenly without prior warning, making early detection and timely intervention crucial to saving lives. Traditional methods of predicting CA have proven inadequate due to the lack of clear warning signs. With the integration of Machine Learning (ML) techniques, the potential for more accurate early detection and intervention can improve survival rates. Objective This study proposes a machine learning-based approach for the early prediction of Cardiac Vascular Disease (CVD), which is a primary contributor to CA. The model incorporates various patient data, including lab results, vital signs, and Electrocardiogram (ECG) signal readings, to enhance prediction accuracy. Methods The study employs a range of advanced machine learning techniques, including Gradient-Boosting Algorithm (GBA), Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Networks (ANN). To process the data, Wavelet Transform (WT) is used to decompose the ECG signals, isolating important features while minimizing noise. Feature selection is performed through an innovative Modified Recursive Feature Elimination (MRFE) technique. Results The machine learning models were validated using the MATLAB simulator, with evaluation metrics including accuracy, precision, recall, and F-score. Among the models, ANN demonstrated the highest performance, achieving 96.3% accuracy, 96.1% precision, 95% recall, and 94.65% F-score. Conclusion This work demonstrates the effectiveness of machine learning in the early prediction of CA, enabling timely medical intervention and potentially saving lives. The results suggest that the proposed model could become a valuable tool for healthcare professionals in managing and preventing cardiac arrest.
Artificial intelligence: Augmented integrated development environments for boosting programmer productivity P. Ashok, Ravi Gorli, S. Parameswari, Lakshmi Sridevi, N. Janaki, S. Gopinath, Harishchander Anandaram, K. S. Shreenidhi, Samaya Pillai Iyengar Artificial Intelligence for Cloud Native Software Engineering, 2025 AI is transforming software development with technologies that improve speed, quality, and productivity. AI-powered technologies and their use in software development are covered in this abstract. NLP algorithms help extract and categorize requirements from unstructured documents during requirements collecting and analysis. Machine learning algorithms forecast hazards and resource needs using past project data, improving planning and estimating. In addition, machine learning models trained on massive code repositories may produce code snippets and functions from natural language descriptions. AI algorithms produce test cases, prioritize test scenarios, and anticipate defect-prone code for testing and quality assurance. Automatic bug detection technologies use deep learning to spot bugs before they hit production. This research article brings in more insights about the various tools and softwares that are utilized in various stages of software development life cycle for efficient product development.
Bonevoyage: Navigating the depths of osteoporosis detection with a dual-core ensemble of cascaded ShuffleNet and neural networks Dhamodharan Srinivasan, Ajmeera Kiran, S. Parameswari, Jeevanantham Vellaichamy Journal of X Ray Science and Technology, 2025 Background Osteoporosis (OP) is a condition that significantly decreases bone density and strength, often remaining undetected until the occurrence of a fracture. Timely identification of OP is essential for preventing fractures, reducing morbidity, and enhancing the quality of life. Objective This study aims to improve the accuracy, speed, and reliability of early-stage osteoporosis detection by integrating the compact architecture of Cascaded ShuffleNet with the pattern recognition prowess of Artificial Neural Networks (ANNs). Methods BoneVoyage leverages the efficiency of ShuffleNet and the analytical capabilities of ANNs to extract and analyze complex features from bone density scans. The framework was trained and validated on a comprehensive dataset containing thousands of bone density images, ensuring robustness across diverse cases. Results This model achieving an accuracy of 97.2%, with high sensitivity and specificity. These results significantly surpass those of existing OP detection methods, highlighting the effectiveness of the BoneVoyage framework in identifying subtle changes in bone density indicative of early-stage osteoporosis. Conclusions BoneVoyage represents a significant advancement in the early detection of osteoporosis, offering a reliable tool for healthcare providers to identify at-risk individuals prematurely. The early detection facilitated by BoneVoyage allows for the implementation of preventive measures and targeted treatments.
Design and analysis of rectangular patch antenna for microwave frequency band applications S. Parameswari, A. Dharshini, S. Ashwathi, T. Sowmiya, C. Chitra Recent Trends in Intelligent Computing and Communication Volume 1, 2025 A rectangular patch antenna's abstract usually gives a brief synopsis of the antenna's features, design, and possible uses. It draws attention to important details including the antenna's size, resonance frequency, and performance indicators. The abstract may also discuss the design process and any special characteristics that make the rectangular patch antenna stand out. It might also briefly discuss the anticipated use cases, including wireless applications or communication systems, demonstrating the antenna's significance in contemporary technology. Because of its small size, simplicity in production, and performance adaptability, rectangular patch antennas are frequently used in microwave frequency spectrum applications. Usually, these antennas are made up of a rectangular metallic patch that is affixed to a dielectric substrate. The operating frequency and radiation properties are determined by their dimensions, specifically the patch's length and width. The antenna's performance can be customized to fit particular frequency bands and applications by modifying these dimensions. Low profile, directed radiation patterns, and compatibility with array integration for improved performance are some benefits of patch antennas. Due to their performance and high performance at microwave frequencies, they are used in a variety of applications such as wireless devices, radar systems, satellite communications and telecommunications.
IoT-based forest monitoring device S. Parameswari, C. Chitra, S. Vignesh, P. Viswa, V. Gokul Recent Trends in Intelligent Computing and Communication Volume 1, 2025 The “IoT-Based Forest Monitoring System” uses innovative and reliable monitoring techniques towards conserving and protecting the environment of the forest. This is an advanced system, constantly drawing out and analyzing data with regard to changes in the surroundings due to vibrations, tree-cutting operations by humans, trespassing, among other odd sounds. After these data have been analyzed, this device will sound the alarm on dangers like illegal logging or trespassing. Inside every tracking unit, all that is integrated holds sensors connected to a micro-controller with the aim of gathering data in an efficient manner. The system employs LoRaWAN antennas even in isolated and heavily forested terrains for distance coverage and highly energy-efficient consumption that readily alerts the forest wardens. This project provides a scalable and affordable solution to extensive forest surveillance because of the IoT technology. Besides building efforts toward conservation, the project offers incentives for preventive measures concerning the conservation of biodiversity and natural resources.
SmartCityPredict: An AI and Machine Learning Framework for Enhancing Urban Service Efficiency Through Real-Time Data Analytics Vasu Koduri, Dhamodharan Srinivasan, S.Parameswari, Ajmeera Kiran, Jaber H. Majeed, Salam Ahmed Mahdi, Basheer Husamaldeen Alhayaly Iccr 2025 3rd International Conference on Cyber Resilience, 2025 Urbanization is still accelerating worldwide, which is putting significant strain on cities' infrastructure, governance, and service delivery systems. This is putting cities under more and more pressure. SmartCityPredict's thorough architecture, created as a response to these problems, is driven by artificial intelligence (AI) and machine learning (ML). This system aims to reach the maximum feasible efficiency in delivering urban services using real-time data analytics techniques. The system uses many data sources for predictive modeling and dynamic decision-making across several urban sectors. These data sources include citizen feedback platforms, waste management units, energy grids, transportation systems, and sensor networks. SmartCityPredict guarantees low-latency analytics and scalable processing using a hybrid architecture combining edge-cloud computing paradigms with deep learning models, including LSTM, CNN, and Transformer networks. Compared to traditional models, the empirical analysis of smart city datasets that act as benchmarks shows notable improvements in the accuracy of projections, the speed with which services are delivered, and operational efficiency. SmartCityPredict provides a reasonable basis for the growth of smart cities that are intelligent, resilient, and focused on the needs of their citizens. Data-driven government and proactive urban management help to promote this basis. Focusing on integrating artificial intelligence innovation with pragmatic city planning and operations, this study contributes to the larger objective of sustainable urban transformation. The study, therefore, aims to identify means of combining these two facets.
Enhancing Audit Effectiveness Through Strategic Data Analytics Ashok Panchapakesan, Harishchander Anandaram, Lakshmi Sridevi, Kumar M. Sathish, P. Dhivya, S. Parameswari, K. S. Shreenidhi, Henil Kapadia Machine Learning and Modeling Techniques in Financial Data Science, 2025 The integration of advanced data analytics into internal audit processes represents a transformative approach to organizational risk management. This exploration examines data analytics methodologies within audit frameworks, addressing technological innovation, operational efficiency, and compliance. Data analytics enables internal audit departments to transition from retrospective, sample-based reviews to comprehensive, real-time risk assessment and predictive modelling. Analyzing applications across financial services, healthcare, technology, and manufacturing reveals consistent benefits. Implementation challenges include technological infrastructure requirements, skill set gaps, data quality concerns, and complex regulatory landscapes. Emerging trends like artificial intelligence, machine learning, and predictive analytics promise to revolutionize internal audit capabilities. Future opportunities focus on developing adaptable data analytics frameworks that can dynamically respond to evolving technological and regulatory environments.
Multi Slotted Microstrip Patch Antenna for Wireless Application S Parameswari, M Dinesh, G Vignesh, M Dhanush Kumar 2024 International Conference on Communication Computing and Internet of Things Ic3iot 2024 Proceedings, 2024 An innovative multislotted microstrip patch antenna design for wireless applications is shown in this abstract. The need for fast wireless communication systems is growing, and this calls for the creation of small, effective antennas. Multiple slots are incorporated into the microstrip patch structure of the suggested antenna design in order to optimise performance attributes like greater directivity, decreased return loss, and improved bandwidth. The choice of an appropriate substrate material with the required dielectric properties is the first step in the design process. In order to achieve the required resonance frequency and impedance matching, the patch’s geometry is optimised. The antenna’s performance parameters are then enhanced by carefully introducing slots into the patch construction. An essential component of wireless communication systems is antenna bandwidth expansion, which is made possible by the slots in the patch structure. Additionally, the slots improve the antenna’s ability to match impedance and lower return loss. Additionally, the multislotted design improves the antenna’s directivity, which boosts signal strength and coverage.
A Review on Wideband High-Gain Low-THz Antennas for Wireless Applications Dhamodharan Srinivasan, M Premkumar, S Deepa Nivethika, P Dhilipkumar, S Parameswari, M Kalpana Chowdary Proceedings of the 18th Indiacom 2024 11th International Conference on Computing for Sustainable Global Development Indiacom 2024, 2024
