Completed Ph.D from Anna University,Chennai in the year 2010
Completed M.E from Madurai Kamaraj University in the year 1997
Completed B.E from Madurai Kamaraj University in the year 1994
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Engineering, Computer Networks and Communications, Computational Theory and Mathematics, Computer Science Applications
34
Scopus Publications
Scopus Publications
IoT-Monitored and Controlled Isolated Bipolar DC-DC Converter for Electric Vehicle Battery Charging System Srinivasan P., N. Sankar Ram, M. Sadhasivam, D. Kabilan International Energy Journal, 2026 With the increasing popularity of electric vehicles (EVs), there's a rising demand for advanced power conversion systems that boost efficiency, reliability, and safety in charging batteries. This research presents the development of a specialized isolated bipolar DC-DC converter designed specifically to enhance the integration of energy storage in electric vehicle battery charging systems. The bipolar power outputs, essential for ensuring balanced charging and increasing the lifespan of the batteries, will be stable as well as efficient due to switching functions controlled by the converter using the dsPIC30F2010 microcontroller. To enhance monitoring features in the main control unit, the system includes an ESP32 microcontroller, based on IoT. With this arrangement, you can keep an eye on key battery metrics like voltage and temperature in real time, all thanks to wireless technology. This IoT-connected system not only boosts clarity in how charging works but also helps manage issues by sending out warnings for problems like overheating or too much voltage. This monitoring system enhances battery safety and extends its lifespan during operation. Isolated design gives this converter the advantages of increased electrical safety and interference reduction, making it perfect for fragile automotive environments. In simulation, the converter stepped up a 50 V input to 320 V DC, delivering a battery current of 85 A at 80.6% SOC, verified under resistive loading with a 10 kHz switching frequency. A FOPID controller provided precise voltage regulation and stable operation across varying duty cycles. In hardware implementation, the prototype achieved output regulation between 12 V–34 V at switching frequencies up to 25 kHz, with efficiency exceeding 90% and stable thermal performance under load variations. Real-time monitoring of battery voltage, current, and SOC% was realized through the Blynk IoT application, providing predictive fault alerts against overvoltage, overheating, and abnormal charging patterns. Hardware-based implementation in real conditions clearly demonstrates its practical application and efficiency. This converter combines strong power electronics with smart control and monitoring, improving EV charging systems by tackling both technical and practical issues related to high-performance and safe battery management systems.
Indigenous Leafy Green Identification Using Deep Learning and Image Processing Techniques R Srinitish, J Keshav, Jason Abraham, K. Subha, A. Senthilselvi, N. Sankarram 2025 8th International Conference on Circuit Power and Computing Technologies Iccpct 2025, 2025 This research presents a deep learning-based image classification system to identify and classify leaves to help users determine the type of leafy green (Keerai) they want to detect, recognize its indigenous (local) name, and learn about its nutritional and medicinal properties—all by simply scanning the leaf. The system automatically classifies the leaves into different subcategories while distinguishing them from non-leafy objects using a convolutional neural network (CNN). The dataset that was created includes several types of Keerai (leafy greens), other leaves, and non-leafy objects, structured into training, validation, and testing sets, initially focusing on five different types of Keerai datasets. The model’s accuracy was improved by implementing image augmentation techniques like rotation, zooming, and flipping, thus making it work without any problems in varying real-world conditions such as lighting and positioning. The CNN model is trained with different convolutional and max-pooling layers, dropout layers for regularization, and a final softmax classification layer for precise identification of leafy greens. The Adam optimizer is used with categorical cross-entropy loss to get a high classification performance. This solution is designed for public use, enabling individuals, including farmers and vendors, to identify these leafy greens conveniently with scanning systems. In addition to the applications in smart agriculture and market authentication, it also helps preserve and propagate knowledge of Tamil traditional medicine and its benefits.
Machine learning models for enhancing cyber security P.R. Therasa, M. Shanmuganathan, B.R. Tapas Bapu, N. Sankarram International Journal of Electronic Security and Digital Forensics, 2024 Because networks are having an ever-increasing impact on contemporary life, cybersecurity has become an increasingly essential area of research. Virus protection, firewalls, intrusion detection systems, and other related technologies are the primary focus of most cybersecurity strategies. These methods defend networks against assaults from both within and outside the organisation. The ever-increasing complexity of deep learning as well as machine learning-based technologies has been applied in the detection and prevention of possible threats. The objective of this research is to investigate and expand upon the applications of machine learning techniques within the context of the topic of cybersecurity. We offer accessible a multi-layered system that is built on machine learning with the intention of modelling cybersecurity. This will be our key area of focus as we work toward achieving our goal of guiding the application toward data-driven, intelligent decision-making for the aim of protecting systems from being attacked by cybercriminals.
Underwater Wireless Sensor Networks with Energy Efficient Routing Protocol Using Load Balancing Technique Tapas Bapu, Pradeep S, Nagaraju V, Partheeban Nagappan, Sankarram N, Srinivasan Sriramulu Ecs Transactions, 2022 Underwater Wireless Sensor Networks is effective and intelligent utilization of energy for routing protocol in longer network lifetime. Energy Consumption and load balancing are the vital roles for a network lifetime. The use of load balancing in WSN is granted as the best resource of sink mobility which protects energy sources to organize. The aim of this paper is to evaluate various deployed strategies involving sink mobility. Multiple mobile sinks are capable of performing computational operations like collecting information from electric joints instantly, storage and also communication capability. It evaluates the results and the effect of sink mobility by comparing with another routing protocol GEDAR.
A reliable data sharing protocol for increasing data availability in manet International Journal of Advanced Science and Technology, 2019
Recommendation based on prediction of commuter flow and occupancy in bus transport M. Sreekrishna*, , N. Sankarram, Dinesh Sha, Dakshin, Ashwini, , , , and International Journal of Recent Technology and Engineering, 2019 The current public transportation in India is found to have higher traffic congestion levels within the bus and is an inefficient transport system for the public. The traffic and the over congested public transports we see on the roads is an effect of this problem. Increasing the public transportation is not the only solution, to make it better we also need to make it smarter. Though there are many other proposals for smart transportation we have come up with a unique way of approaching it. The aim is to provide smartness to the existing transportation system so that it becomes efficient and user-friendly for the public. The public need not depend on the paper tickets anymore and instead can have an smart RF ID with themselves which is not a big issue since its just credit card sized. One big advantage with this system is that public who are waiting to board can know the number of passengers in the vehicle and can decide whether to board or not beforehand. By this way the higher authorities can also see if there is a scarcity in any particular route and can immediately send more vehicles in the particular route. Using this technique, the congestion of the vehicles can be reduced and it will be easier for the public to make use of the public transportation system.
Reroute the packets after finding zombie using DPM techniques International Journal of Recent Technology and Engineering, 2019
Co-operative cluster based multi-agent approach for efficient traffic forecasting and management in VANET International Journal of Innovative Technology and Exploring Engineering, 2019
Efficient data transmission in WSN using AODV protocol considering throughput International Journal of Engineering and Advanced Technology, 2019
Entity based source code summarization (EBSCS) Chitti babu K, Kavitha C., SankarRam N Icaccs 2016 3rd International Conference on Advanced Computing and Communication Systems Bringing to the Table Futuristic Technologies from Arround the Globe, 2016
A new framework for software architecture generation and fault rectification in software engineering International Journal of Applied Engineering Research, 2015
A framework for safe composable testing model for multiple applications testing environment Journal of Theoretical and Applied Information Technology, 2014
A five-factor software architecture analysis based on far for ATM banking system Journal of Theoretical and Applied Information Technology, 2014
