An Energy-Efficient Edge-Cloud Computing Framework for Sustainable IoT Infrastructures in Smart Cities A.Nishanandhini, C.Narmada, S.Vijaya Lakshmi, U.Prakash, V.Baby Vennila, S.Ramasamy Proceedings of 6th International Conference on Iot Based Control Networks and Intelligent Systems Icicnis 2025, 2025 This study examines the potential benefits of integrating the edge-cloud computing with the Internet-connected equipment for enhancing environmental sustainability. To cut down the energy use and dependence on the centralized data centers, the suggested architecture are makes the advantage of edge computing. This strategy are backs up the previous studies that show the hybrid edge-cloud systems can reduce the energy consumption for specific workload categories by up to 50%. The suggested system includes a smart resource management strategies like shared resource pooling, machine learning-based energy optimization and two-phase absorption cooling which are based on the current concepts for sustainable edge computing. These techniques are increase scalability, dependability and energy efficiency while maintaining the system stability under changing the conditions. In comparison to conventional setups a simulations are conducted in smart city and IoT contexts show the framework could achieve the better energy usage tracking a lower carbon emissions and higher quality of service. In order to make a future edge-cloud systems both effective and environmentally conscious, the paper are concludes by highlighting the potential research objectives are such as creating a sustainable infrastructure for design and adaptive workload allocation algorithms.
Fire Alert System for Home using IoT Hariprasath M, Prakash U, Mohan Raja V, Santhana Bharathi R V Proceedings of 2024 International Conference on Science Technology Engineering and Management Icstem 2024, 2024 Fast warning of fire in residences is required to prevent loss of assets because of accidental fires inadvertent & purposeful. Being able to spot a fire is extremely important since it can be what separates life and its end. U sing a fire detection system helps to protect your family because fires can occur at anytime and anywhere. Some individuals contest the necessity of a system of fire alarms. Those simply believe they can smell the fires run away swiftly. A house today burns down on average in under 60 seconds. As a result, the house has likely already been destroyed by the fire by the moment you smell it and try to escape. By connecting these devices to the internet, we can alter or gather information from them. In this article, we'll use a variety of sensors to locate fires and alert lOT application users and first responders to their presence. It goes into great detail about the functions that each module does and how intricately they are implemented. Additionally discussed is the Internet of Things application for fire detection systems.
Advancing Intrusion Detection Precision Through Analysis of Diverse Classification Algorithms J Suriya Prakash, Snehitha Narasani, N Thangadurai, U. Prakash, S Kiran 2nd IEEE International Conference on Networks Multimedia and Information Technology Nmitcon 2024, 2024 This research commences a thorough examination of the possibilities for leveraging Machine Learning (ML) algorithms to support Intrusion Detection Systems (IDS). We make use of the Kyoto dataset, a standard for intrusion detection studies that includes a wide variety of network traffic patterns related to both benign and malevolent activity. We carefully review a range of machine learning (ML) methods, such as decision trees, random forests, logistic regression, K-Nearest Neighbors (KNN), and Support Vector Machines (SVM) with different kernel functions. The distinct advantages and disadvantages of each algorithm in identifying network anomalies are clarified by this thorough examination. In addition to examining the detection capabilities, we delve into the performance metrics of these algorithms, including accuracy, precision, recall, and F1-score, providing a comprehensive assessment of their effectiveness. We also investigate the computational efficiency of these models by analyzing their training times and the impact of different data splits on their performance. Specifically, we evaluate batch sizes using $80: 20,70: 30$, and 60:40 training-to-test ratios to understand their influence on the training dynamics and the overall efficacy of the IDS. Furthermore, we explore the resilience of these algorithms against various forms of intrusions, such as data alteration attempts, unauthorized access attempts, and denial-ofservice (DoS) attacks. By investigating these state-of-the-art developments and promoting a broader comprehension of IDS approaches, this research ultimately contributes to the strengthening of cybersecurity defenses over time. This guarantees the confidentiality, integrity, and availability of their vital data assets while enabling enterprises to adjust and stay resilient against the constantly shifting threat landscape within complex IT infrastructures. The source code of our paper is available at the following linkhttps://github.com/Snehitha-Narasani/IDS-using-ML-algorithms
Elevating Intrusion Detection Precision with Multi-Classification Algorithm Analysis J Suriya Prakash, Talluri Rashmika, N Thangadurai, U. Prakash, S Kiran 2nd IEEE International Conference on Networks Multimedia and Information Technology Nmitcon 2024, 2024 This paper examines the use of machine learning methods to detect network security threats. By analysing network traffic data and using a range of machine learning techniques. This paper focuses on improving IDS performance with ML techniques, utilizing the Kyoto20151207 dataset as a benchmark. It employs fifteen machine learning algorithms over a wide range of techniques to identify network breaches. This study aims to identify the most effective approach for intrusion detection tasks. Using comprehensive testing and assessment, several algorithm-performance couples are ranked according to correctness and accuracy. The study’s goal is to give insight on the efficacy of various strategies, allowing practitioners to choose the best approaches for intrusion detection tasks. Furthermore, the accuracies of these methods are compared to those reported in other works, providing insight into the overall performance context. Finally, the study seeks to help practitioners make educated judgments when selecting relevant categorization algorithms for similar scenarios in IDS deployment. The key findings of our research are we implemented 15 different machine learning algorithms and identified the best accuracy in CatBoostClassifier algorithm as $99.738 \\%$. This paper’s source code may be seen at the following website https://github.com/rashmika357/ideal-palm- tree
Enhancing the Security by Analyzing the Behavior of Multiple Classification Algorithms with Dimensionality Reduction to Obtain Better Accuracy Sai Nandini, Sreenivasa Murthy, Praksha P K, Prakash U, Suriya Prakash J Proceedings 2024 2nd International Conference on Advanced Computing and Communication Technologies Icacctech 2024, 2024 Intrusion detection in network traffic is a crucial component of modern cyber security strategies, aimed at identifying and mitigating malicious activities that threaten the integrity and availability of computer networks. With the proliferation of internet-enabled devices and the increasing sophistication of cyber threats, the importance of effective intrusion detection systems (IDS) cannot be overstated. This abstract provides an overview of the literature survey on intrusion detection in network traffic, which explores various techniques, algorithms, and methodologies employed in detecting and responding to cyber threats. Overall, this literature survey provides valuable insights into the complexities of intrusion detection in network traffic, offering readers a comprehensive overview of this critical aspect of cybersecurity. By understanding the latest trends, techniques, and challenges in intrusion detection, organisations can better protect their networks and mitigate the risks posed by cyber threats. Github link: https://github.com/pandhini13/intrusion-detection-and-network-traffic-
On Stream Face Mask and helmet detection System Using Machine Learning Techniques Sharada Ka, M. Mohan, U. Prakash, S Trisheela Mysurucon 2022 2022 IEEE 2nd Mysore Sub Section International Conference, 2022 Within the context of the current day, safety and cleanliness are the most important factors to consider in order to guarantee a healthy and risk-free human existence. Research has constantly proven that basic hygiene is vital, and that wearing a mask in public areas is crucial, in light of the terrible epidemic caused by the Coronavirus. Consider mandating the use of helmets as another precautionary safety measure for users of two-wheeled vehicles. A real-time Yolov3 object detector is used to train the model to recognise face masks and helmets in video footages, live feeds, or photos in order to search for public hygiene and safety. This is done in order to ensure that people are not exposed to potentially hazardous conditions. A neural network is used for the prediction of bounding boxes and the possibilities associated with those boxes over the whole picture. The dataset was gathered via the use of the internet. The model has been taught with the use of internet photos for several classes, such as wearing a mask but not a helmet; not wearing a mask or helmet; wearing a mask but not a helmet; wearing a helmet but not a mask; and wearing both a mask and a helmet. The trained dataset is used mostly for the purposes of classifying items and locating them within the aforementioned categories. In the event that neither the helmet nor the mask is located, the SMTP library module that is supplied by Python specifies an SMTP that may deliver mail to any internet device using SMTP or ESMTP as a client session object. The suggested approach was evaluated using a dataset that included photographs of persons adhering to COVID-19 safety regulations as well as photographs of people adhering to road safety recommendations while wearing helmets. Accuracy and precision are both quite good in the outcomes that were achieved.
A Survey on Artificial Intelligence in Telecommunication for Churn Prediction Prakash U, Anila A, Swetha C, Vigneshwaran K, Kavinayaa N 6th International Conference on Electronics Communication and Aerospace Technology Iceca 2022 Proceedings, 2022 One of the most significant issues in the telecom industry is jumping of customer to another network called customer churn. It has a direct impact on the revenue of the business, particularly in the telecom sector. As a result, businesses are attempting to develop strategies for anticipating customer turnover. Therefore, it is crucial to identify the factors that influence customer churn. Our paper demonstrates how to identify customer attrition effectively in the telecom sector. Our article includes a churn ANN model, which helps telecom businesses manage the individuals who are willing to churn, as well as some practical data analysis, which can be used to draw conclusions from the data. This prediction model with a high accuracy score can be created using neural networks, machine learning algorithms, artificial intelligence and other technologies.
Signal Quality Evaluation and Processing for QRS Detection in ECG based Smart Healthcare Systems Devendra Singh, ShaikVaseem Akram, T Sivakumar, U. Prakash, J Loyola Jasmine, Chaithra K N IEEE International Conference on Knowledge Engineering and Communication Systems Ickes 2022, 2022 The next-generation wearable electrocardiogram (ECG) equipment requires signal processing with low battery usage in order to transmit signals when harmful rhythms are recognized and to capture signals when anomalous rhythms are discovered. The visual deflections that are frequently visible on an ECG make up the QRS complex. This research suggests a real-time QRS recognition and R point detection system that is extremely accurate and simple. The recommended ECG signal modification eliminates baseline wandering while also enhancing QRS intervals and controlling P and $T$ waves. In this work, the peaks and valleys of the converted signal were used to calculate the fiducial point for the QR. The R point could then be determined using four QRS waveform templates, and the initial categorization of cardiac rhythms could be completed simultaneously. On two benchmark datasets, the proposed method's effectiveness is shown. Positive prediction (+P) and detected sensitivity (Se) values for QRS are 99.82 and 99.81 percent, respectively, according to the standard. The outcome demonstrates that the method has a low processing complexity and that real-time software may be successfully executed on both an embedded system and a mobile device.
RECENT SCHOLAR PUBLICATIONS
An Energy-Efficient Edge–Cloud Computing Framework for Sustainable IoT Infrastructures in Smart Cities A Nishanandhini, C Narmada, SV Lakshmi, U Prakash, VB Vennila, ... 2025 6th International Conference on IoT Based Control Networks and … , 2025 2025
Sustainable groundwater development using semi-supervised learning and community-led total forestry and pasture approach A Alphy, G Deivasikamani, U Prakash, FD Shadrach, MA Kumar, S Manoj Groundwater for Sustainable Development 25, 101093 , 2024 2024 Citations: 1
Fire Alert System for Home Using IoT M Hariprasath, U Prakash, V Mohan Raja, RV Santhana Bharathi 2024 International Conference on Science Technology Engineering and … , 2024 2024 Citations: 1
Signal Quality Evaluation and Processing for QRS Detection in ECG based Smart Healthcare Systems D Singh, SV Akram, T Sivakumar, U Prakash, JL Jasmine, C KN 2022 International Conference on Knowledge Engineering and Communication … , 2022 2022 Citations: 1
A Survey on Artificial Intelligence in Telecommunication for Churn Prediction U Prakash, A Anila, C Swetha, K Vigneshwaran, N Kavinayaa 2022 6th International Conference on Electronics, Communication and … , 2022 2022 Citations: 1
On Stream Face Mask and helmet detection System Using Machine Learning Techniques S Ka, M Mohan, U Prakash, S Trisheela 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), 1-6 , 2022 2022 Citations: 1
Mining Gene Expression Data Based Affinity Search Clustering Technique U Prakash International Journal of Modern trends in Engineering and Research 2 (4), 7 , 2015 2015
Denoising and Back Ground Clutter of Video Sequence using Adaptive Gaussian Mixture Model Based Segmentation for Human Action Recognition K Shanmugapriya, U Prakash International Journal of Electronics Communication and Computer Engineering … , 2014 2014
ROBUST VISUAL CRYPTOGRAPHY FOR BIOMETRIC PRIVACY USING PIXEL EXPANSION National Conference on Infromation,Networking and Communication Technologies , 2012 2012
MOST CITED SCHOLAR PUBLICATIONS
Sustainable groundwater development using semi-supervised learning and community-led total forestry and pasture approach A Alphy, G Deivasikamani, U Prakash, FD Shadrach, MA Kumar, S Manoj Groundwater for Sustainable Development 25, 101093 , 2024 2024 Citations: 1
Fire Alert System for Home Using IoT M Hariprasath, U Prakash, V Mohan Raja, RV Santhana Bharathi 2024 International Conference on Science Technology Engineering and … , 2024 2024 Citations: 1
Signal Quality Evaluation and Processing for QRS Detection in ECG based Smart Healthcare Systems D Singh, SV Akram, T Sivakumar, U Prakash, JL Jasmine, C KN 2022 International Conference on Knowledge Engineering and Communication … , 2022 2022 Citations: 1
A Survey on Artificial Intelligence in Telecommunication for Churn Prediction U Prakash, A Anila, C Swetha, K Vigneshwaran, N Kavinayaa 2022 6th International Conference on Electronics, Communication and … , 2022 2022 Citations: 1
On Stream Face Mask and helmet detection System Using Machine Learning Techniques S Ka, M Mohan, U Prakash, S Trisheela 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), 1-6 , 2022 2022 Citations: 1
An Energy-Efficient Edge–Cloud Computing Framework for Sustainable IoT Infrastructures in Smart Cities A Nishanandhini, C Narmada, SV Lakshmi, U Prakash, VB Vennila, ... 2025 6th International Conference on IoT Based Control Networks and … , 2025 2025
Mining Gene Expression Data Based Affinity Search Clustering Technique U Prakash International Journal of Modern trends in Engineering and Research 2 (4), 7 , 2015 2015
Denoising and Back Ground Clutter of Video Sequence using Adaptive Gaussian Mixture Model Based Segmentation for Human Action Recognition K Shanmugapriya, U Prakash International Journal of Electronics Communication and Computer Engineering … , 2014 2014
ROBUST VISUAL CRYPTOGRAPHY FOR BIOMETRIC PRIVACY USING PIXEL EXPANSION National Conference on Infromation,Networking and Communication Technologies , 2012 2012
