Effective Denial-of-Service Attack (DoS) Detection Using Progressive Cyclical Convolutional Neural Network (CNN) in Wireless Sensor Networks E. Sivanantham, Neerukonda Kanthi Priyadarsini, Manikumar Thankaraj, T. R. Vijaya Lakshmi International Journal of Communication Systems, 2025 Wireless sensor networks (WSNs) are vital for modern applications but remain highly vulnerable to denial‐of‐service (DoS) attacks because of their limited resources. To address this, this paper proposes a DOSAD‐WSN‐PCCNN, an effective and lightweight DoS detection framework based on progressive cyclical convolutional neural network (PCCNN). This approach integrates advanced preprocessing using variational Bayesian–founded extreme correntropy cubature Kalman filter (VBECKF), feature selection using variable velocity strategy particle swarm optimization algorithm (VSPSOA), and parameter optimization using Tyrannosaurus optimization algorithm (TOA). This hybrid strategy significantly enhances detection accuracy, efficiency, and robustness. Experimental results on the WSN‐DS dataset demonstrate up to 99.5% accuracy and outperform baseline methods by over 25% in key metrics. The proposed system shows strong potential for real‐time deployment in resource‐constrained WSN environments, significantly improving network resilience against evolving DoS threats.
Optimized Hybrid Approach for Assessing Pollution Severity in Polymer Insulators Using Random Forest and Fuzzy Logic Kannan Kandavelu, Sivakumar Sivagnanam, Senthilkumar Angappan, Manikumar Thangaraj, Sangeetha Balashanmugam, Meenakshi Sundaram Padamanabhan, Moniya Pathrakalimuthu Automation and Remote Control, 2025 An insulator is one of the crucial parts of the high-voltage overhead cables. Leakage currents may circulate on the insulator’s surface as a result of external factors and contaminants adhered to the surface. Large leakage currents (LC) have the potential to produce flashover, heat losses and surface damage to the insulator. In order to prevent early flashover, this research offers a method that measures the severity of the insulator surface using harmonic measurements of leakage currents. In this work, on 11 kV polymer insulators, the leakage currents were assessed at various equivalent soluble deposit density (ESDD) levels. Discrete Wavelet transform topology is incorporated to extract features from the LC signal. Random forest (RF) with fuzzy inference system (FIS) using a diverse range of LC signals collected over an extended period is incorporated. From results, it is evident that the suggested pollution severity classifier, is highly effective with an accuracy about 95%. Its implementation holds great promise for electrical utilities.
A Comprehensive Attendance System 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Strategic and Sustainable ERP Decision Framework: Integrating Multi-Criteria Analysis with Deep-A-CNN-LSTM Models in Corporate Strategy Suman Dahiya, Nawab Akram, K.Srinath Yadav, T. Manikumar, Thulasimani T, Neha Barodia 2024 International Conference on Integration of Emerging Technologies for the Digital World Icietdw 2024, 2025 Customizing enterprise resource planning (ERP) software to meet a company's unique operational requirements is a crucial consideration throughout implementation. It offers a framework in this post to help management make decisions about customization choices and the capabilities needed to implement them. This structure allows us to identify several openings for tailoring the ERP system and company processes. A preprocessing step, feature extraction, and training the model make up the three phases of the said approach. The preprocessing steps include extracting summary metrics and performing temporal principal component analysis (PCA). One method for extracting features is Kernel Principal Component Analysis, or Kernel PCA. During the training process, a Deep-A-CNN-LSTM was utilized. With an average accuracy of 92.46%, the suggested method outperforms LSTM and CNN.
Unravelling Digital Crime Scenes: Pedagogical Strategies in Digital Forensics PBL , Dr. K. Venkatesh, Dr. R. Rajasubramanian, , Dr. T. Manikumar, , Akbar Badhusha Mohideen, and Journal of Engineering Education Transformations, 2024 The DIGIT framework emphasizes spanning the gap between digital forensics theory and real-world challenges through PBL assessment and teaching methods. To develop the practical skills, this method uses interactive exercises like simulated cybercrime investigations and data recovery assignments. Summative evaluations, such as investigative reports and practical tests, guarantee thorough evaluation, while formative assessments, such as peer reviews and reflective journals, offer ongoing feedback. Students were organized into 18 groups, focusing on activity recognition in various domains such as data acquisition, evidence analyser, and reporting and presentation for PBL. With the help of this approach, students can confidently and competently handle challenging forensic situations. To establish a dynamic and engaging learning environment that reflects real-world problem-solving, evaluation and pedagogies are used in problem-based learning (PBL). With the goal of measuring both the process and results of student learning, assessments guarantee a thorough assessment of abilities and knowledge. In order to help students connect with the material on a deep level, pedagogies are created to encourage teamwork, creativity, and critical thinking. The course resulted in six live solutions, with two projects submitted for patents and six converted into research publications. Qualitative feedback indicated high levels of student satisfaction, with 88% reporting increased engagement and 89% feeling better prepared for realworld applications. Future research should investigate the scalability of this approach across various engineering disciplines and evaluate its long-term impact on students' career. Keywords- problem-based learning, DIGIT, hands-on learning, real-world application, interdisciplinary approach.
Advancing PV technology with ZnO/Ag+ nanocomposites V. Revathi, Savita Rani, M. Balamurugan, T. Manikumar, S. Sivakumar, et al. Digest Journal of Nanomaterials and Biostructures, 2024 This study focuses on the synthesis and characterization of hybrid zinc oxide/silver ion (ZnO/Ag+) nanocomposites tailored for PV cell applications. The nanocomposites are synthesized through a cost-effective method, leveraging the unique properties of both ZnO and Ag. Characterization techniques including X-ray diffraction (XRD), scanning electron microscopy (SEM) are employed to analyze the structural, morphological and optical properties of the nanocomposites. Moreover, the electrical properties and photoelectric performance of the PV solar cells are evaluated and compared with conventional PV devices. The results demonstrate the potential of ZnO/Ag+ nanocomposites in enhancing the overall performance of PV solar cells.
Real Time Yoga Posture Location and Assessment Utilizing Deep Learning T. Manikumar, Jeevan Kankanala, Kannali Kishore, Lali Sriram 5th International Conference on Sustainable Communication Networks and Application Icscna 2024 Proceedings, 2024 This research work proposes a new technique that helps people practice yoga correctly through real-time physical visualization and feedback. As yoga and its health benefits grow, so does the need for tools that help practitioners maintain correct posture, especially when they do not have access to an instructor. The system captures video of the user's movements on a webcam and uses special algorithms to compare it with previously stored descriptions in the database. This algorithm accurately measures the difference between the user's body and the body. When the user's motor is correct, the system will offer suggestions for improvement; otherwise, it will cause the user to correct their body. The technology is designed to leverage MediaPipe's functionality to work well in different lighting conditions and with different users, allowing it to work well on different computer models. Future plans include integration into mobile applications or wearable devices to improve user experience. Overall, this research contributes to the development of AI-based health and wellness tools by providing practical solutions to improve the accuracy and health benefits of yoga practice.
Enhancing Software Engineering Education through Project-Based Learning , Dr.T. Manikumar, Dr.R.Raja Subramanian, , Dr.K. Venkatesh, , Mr.Akabar Badhusa Mohideen, and Journal of Engineering Education Transformations, 2024 — Software engineering course designed for third year students. PBL, has become a highly promising pedagogical strategy. In order to improve the learning experiences and results of students taking software engineering courses, this paper offers a framework for incorporating PBL. The framework stresses active, student-centered learning through the investigation and solution of real-world software engineering challenges, drawing on well-established PBL and software engineering education ideas. The article also discusses obstacles to be overcome when introducing PBL in software engineering courses and offers solutions. Software engineering instructors can help students gain a deeper comprehension of theoretical ideas and practical skills through the use of PBL, equipping them for success in the dynamic and challenging area of software development. Keywords— Problem-Based Learning, Real-World Applications, Software Engineering, Student Engagement, Tangible Outcomes
Decentralized Traceability and Direct Marketing Supply Chains T. Manikumar, Korrapati Mahendra Sunny Goud, Maddu Prem Teja, Majjiga Ganesh, Mohammed Yasin 5th International Conference on Sustainable Communication Networks and Application Icscna 2024 Proceedings, 2024 The agricultural sector is currently facing significant challenges, one of the most critical being the absence of a streamlined and direct supply chain between farmers and buyers. This disconnect often leads to inefficiencies, price manipulation, and vulnerability for farmers, resulting in reduced income and compromised product quality. To address these pressing issues, we are developing an innovative webbased platform that provides visibility into farmers profiles, enabling buyers to access critical information such as product availability, and pricing directly and product reviews from the source. This portal will empower buyers to connect with farmers in real time, allowing for direct communication, price negotiations, and quick updates on agreement terms. To further enhance the system's transparency and security, Blockchain technology is integrated to record all transactions and store them in an immutable, decentralized ledger. By securing the integrity of transaction data, Blockchain ensures traceability, reduces the risk of fraud, and fosters trust between stakeholders. The proposed web portal aims to bridge the gap between farmers and buyers, fostering a more transparent, trustworthy, and efficient agricultural marketplace. The approach not only has the potential to improve the livelihoods of farmers by ensuring fair trade but also benefits buyers by providing direct access to quality produce. Furthermore, it promotes sustainability in agricultural practices by encouraging more transparent supply chains.
