Engineering, Electrical and Electronic Engineering, Computer Engineering, Biomedical Engineering
14
Scopus Publications
38
Scholar Citations
4
Scholar h-index
1
Scholar i10-index
Scopus Publications
Energy-Efficient EEG-Based Autism Spectrum Disorder Detection Using a Hyperbolic Attention Neural Network Anshad A. S, Padmanaban K, L. Guganathan, Anupama J Developmental Neurobiology, 2026 Long‐term physiological monitoring using wearable wireless systems represents a paradigm change in next‐generation e‐health applications. Specifically, electroencephalography (EEG) represents a noninvasive and trustworthy way of recording brain activity and is a likely candidate for the early diagnosis of autism spectrum disorder (ASD). Yet, conventional methods involving the streaming of raw EEG signals to outside servers for classification consume significant energy and drastically shorten the operational life of wearable sensors. In response to these gaps, this research introduced an energy‐aware, sensor‐based scheme for ASD detection during early childhood from EEG signals. The system exploits on‐node signal denoising via chaotic signal models, feature extraction by dual tree discrete wavelet transform (DT‐DWT), and lightweight feature selection by parrot optimization (PO). The core detection is executed via a new Hyperbolic Cross‐Head Attention‐Based Neural Network (HyperCrossNet) that proposes deep reversible learning in conjunction with spatial and channel‐oriented attention mechanisms. The network weights are then optimized by the Pied Kingfisher Optimization Algorithm (PKO) for improved accuracy. Experimental outcomes indicate 99.92% classification, 99.91% recall, and a 99.90% F 1‐score not mentioning that it has lowered considerably the amount of energy used to transmit the raw data. This effective design enables real‐time wearable detection useful and applicable to long‐term monitoring.
AI-Based Intrusion Detection and Response Mechanisms A. S. Anshad, P. K. Poonguzhali, Sanjay Srivastava, R. Vidhya, Sandeep C. S., G. Saravanan, V. Bhoopathy AI Driven Cybersecurity for Autonomous Systems, 2026 Many online hazards exist beyond malware and DDOS attacks. Using a network intrusion detection system can avoid such attacks. IDS can de-generate alerts after intrusions. This intrusion detection system checks all network data. Thus, conventional intrusion systems cannot filter all data. Intruder detection systems demand a lot of maintenance. This is costly and varies by course. Digitising sensitive data is another trend. Intrusion detection systems help. Intrusion detection systems alert administrators to questionable activities. This is done with AI algorithms. AI provides advanced real-time intrusion detection, analysis, and reaction. The history and design of AI-powered IDS, the different AI methodologies employed in this sector, and their ability to discover new and unexpected threats are examined in this chapter. It compares conventional systems with AI-enabled ones and examines AI-driven adaptive reaction mechanisms to mitigate risks. The chapter concludes with current issues, ethical concerns, and future research.
Intelligent Anomaly Detection for Secure Data Transmission in Cloud Computing Systems over 6G Networks A. S. Anshad, Piyush Charan, Preethi N., Irshad Khan, Amruthalakshmi M. R., Sudhanshu Maurya, Savitha Hiremath, D. Anil Engineering Technology and Applied Science Research, 2025 The emergence of sixth-generation (6G) networks facilitates robust capabilities such as ultra-low latency and massive device connectivity, which simultaneously raise critical challenges in securing cloud-based data transmission. This study proposes a novel anomaly detection framework that integrates Autoencoders (AEs), Convolutional Neural Networks (CNNs), and Federated Learning (FL) to deliver real-time, privacy-preserving intrusion detection for 6G-enabled cloud computing environments. The framework is evaluated using four benchmark datasets, including NSL-KDD, UNSW-NB15, CIC-IDS2017, and CIC-DDoS2019. Across all datasets, the model achieved an average accuracy of 99.85%, precision of 99.76%, recall of 99.82%, and F1-score of 99.79%, while maintaining a False Alarm Rate (FAR) as low as 0.0011. The model also demonstrated high efficiency, operating with inference latency below 350 ms, making it highly suitable for the stringent requirements of 6G infrastructure. Enhanced with explainability tools, the system ensures transparent decision-making, offering an interpretable solution towards next-generation cybersecurity threats.
Fuzzy Logic-SVM Integration for Energy-Efficient Intrusion Detection in Wireless Sensor Networks Anshad A. S, Preeti Nitin Bhatt, Arun Raj S. R., M. Karthikkumar, G. Deepa, K. Sathish 2nd Asian Conference on Intelligent Technologies Acoit 2025, 2025 Wireless Sensor Networks (WSNs) are susceptible to many security risks, such as sinkhole, Sybil, and denial-of-service attacks, which compromise data integrity and network durability. Conventional intrusion detection systems frequently encounter compromises between precision and energy efficiency, hence constraining their efficiency in resource-limited settings. The proposed study introduces an innovative hybrid intrusion detection framework that integrates fuzzy logic's uncertainty management with Support Vector Machine (SVM) classification to achieve energy-efficient and high-accuracy detection. The fuzzy logic module pre-filters network input to selectively activate the SVM classifier, thereby reducing computational effort and energy expenditure. Experimental assessment of Kaggle-sourced WSN datasets reveals exceptional performance, achieving 96.8% accuracy, 95.6% precision, 97.2% recall, and a false positive rate of 2.8%, surpassing both SVM-only and fuzzy-only benchmarks. The suggested system provides an excellent equilibrium between detection effectiveness and energy efficiency, making it a viable alternative for safeguarding extensive wireless sensor network implementations.
A Blockchain-Enabled Secure and Energy-Efficient Routing Protocol for Wireless Sensor Networks in Environmental Monitoring Using RL-DDPGA Anshad A S, Geetha M N, S. Rajyalaxmi, Ganesha M, S. Kaliappan, D. Suganthi Proceedings of 2025 1st International Conference on Radio Frequency Communication and Networks Rfcon 2025, 2025 With the proliferation of IoT devices in this age of lightning-fast technical development, security has emerged as a key issue. WSN are made up of these tiny, power-efficient, and battery-operated devices. They find widespread use in fields like healthcare, building monitoring, food packaging, and accident prevention. This study suggests incorporating Blockchain technology into an Energy Efficient Routing Protocol for WSN to fix the security issues that come with these networks. Data preparation, normalisation, feature engineering, scaling blockchain transactions, and model training are all steps in the proposed model's systematic approach. To speed up training and improve model performance, RL-DDPGA, a framework based on reinforcement learning, is used. With a low FPR of 4.26% and a high TPR of 95.61%, the experimental assessment, carried out utilising an open racing automobile simulator, proves that the suggested method can successfully obtain control policies. These results validate the superior accuracy and efficiency of the proposed Blockchain-based energy-efficient routing architecture compared to current methods. This study offers a secure and performance-optimized routing solution for WSNs, which is a great step forward for IoT applications that prioritise energy efficiency and data security.
Enhancing Security in Wireless Sensor Networks with a Deep Learning and Game Theory-Based Hybrid Model for Malicious Node Detection Anshad A S, Elumalai J, Sajin R Nair, S. Sivaranjani, Janani K, A. Saritha Proceedings of 2025 1st International Conference on Radio Frequency Communication and Networks Rfcon 2025, 2025 WSN are a type of self-organising wireless network that use a large number of inexpensive, low-volume sensor nodes set up in a multi-hop fashion. Applications such as scientific observation, node analysis, and environmental monitoring make extensive use of these networks. But when used in unprotected areas, they are open to security breaches, especially when injected with false data by malicious actors, which makes detection systems less reliable. The crucial problem of identifying malevolent nodes in WSNs is tackled in this research. Sensor nodes, cluster heads, and gateways are the three main components of a WSN design. Sensor nodes gather data, while cluster heads process it. During the dataset cleaning step, outlier detection was employed to increase data quality. Then, the KMCIG approach was used for feature extraction. An intriguing strategy for improving decision-making in complicated network settings is the study's integration of RL-GameTheory. The suggested approach detects malicious nodes more accurately and robustly by utilising this combination. The experimental findings show that the suggested model outperforms the current systems by a stunning margin, reaching an accuracy of 99.62%. This study demonstrates the promise of RL and game theory for creating cutting-edge security solutions for networks and helps move the field closer to intelligent, secure WSN frameworks.
Towards Accurate Glioma Segmentation: A Modified HTTU-Net with Multi-Scale Feature Encoding Anshad A S, Harpreet Singh Saghra, Manu Kumari, D Deepa, Shreeshayana R, Akshaya Kubba 2025 5th Asian Conference on Innovation in Technology Asiancon 2025, 2025 Glioma segmentation is the process of identifying of tumorous tissues in brain images and automatically classifying each pixel into its subsequent tumor sub-classes. The segmentation of gliomas is extremely challenging and complex because of its varied morphology. So, this work presents a modified Hybrid Two-Track U-Net (HTTU-Net) model to improve the multi-class segmentation of gliomas. The two tracks in the original HTTU-Net are modified by incorporating dilated convolutions of varying dilation factors to widen the receptive field for multi-scale evaluations. Additionally, a Scaled Exponential Linear Unit (SELU) activation function is utilized in both tracks to optimize the training process. The proposed architecture is evaluated on the Multimodal Brain Tumor Segmentation Challenge (BraTS 2018) database and it has obtained the average values of the dice score as 0.941, 0.943 and 0.911 and the Hausdorff distance as 3.281, 2.880 and 1.339 for the whole tumor core and enhancing tumor regions of gliomas, respectively.
Integrating IoT and Wireless Sensor Networks for Precision Agriculture Using TD-CNN-LSTM A S Anshad, K Sravanthi, S Manivannan, Neeru Malik, S. Kaliappan, Anvesh Perada 2025 IEEE 2nd International Conference on Advances in Modern Age Technologies for Health and Engineering Science Amathe 2025 Proceedings, 2025 Precision agriculture has difficulties in the management of spatial and temporal data for crop monitoring and irrigation planning. This research introduces a novel TD-CNNLSTM model that incorporates IoT-enabled Wireless Sensor Networks to tackle these challenges. The model efficiently captures spatial and temporal patterns by integrating convolutional and LSTM layers. The results indicate an accuracy of 97.2%, precision of 0.96, and an $F 1$-score of 0.955, significantly surpassing baseline models such as Random Forest and LSTM-only. These measures confirm its exceptional efficacy in yield prediction and the optimisation of irrigation timing. This study presents a comprehensive, scalable system that enhances precision agriculture by increasing efficiency and sustainability compared to current methods.
An Intelligent Hybrid Quantum-Deep Reinforcement Framework for Energy-Efficient Routing in Wireless Sensor Networks Anshad A S, Shaik Fakruddin Babavali, Cephas I, S. V. Ramanan, Lakshmi Priya G, Soumya Mishra 2025 6th International Conference for Emerging Technology Incet 2025, 2025 Wireless Sensor Networks (WSNs) experience increased energy consumption and inefficient routing, resulting in reduced network performance. Conventional methods, like Q-learning and Deep Q-Networks (DQN), have difficulties with scalability and adaptive learning in changing environments. We present a Hybrid Quantum-Deep Reinforcement Learning (QDRL) framework that combines quantum state encoding, experience replay, and deep reinforcement learning for optimum routing. The QD-RL system effectively identifies energy-optimized pathways, decreasing energy usage by 35% and extending network lifespan by 40%. In comparison to QLR, DQN, and EA-AODV, our model attains exceptional results: 98.6% accuracy, 97.8% precision, and 99.1% ROC-AUC. QDRL improves routing flexibility by utilising quantum superposition and deep reinforcement learning, making it suitable for extensive WSNs. Future investigations may examine quantum hardware acceleration to enhance real-time performance further. This study sets a novel benchmark for energy-efficient, intelligent WSN routing, facilitating the advancement of next-generation AI-driven networks.
An effective compression based secure authentication protocol for WSN International Journal of Applied Engineering Research, 2015
RECENT SCHOLAR PUBLICATIONS
AI Based.Road Accident Prediction Device DA A S IN Patent 445261-001 , 2026 2026
Energy-Efficient EEG-Based Autism Spectrum Disorder Detection Using a Hyperbolic Attention Neural Network AS Anshad, K Padmanaban, J Anupama Developmental neurobiology 86 (2), e70011 , 2026 2026
AI-Based Intrusion Detection and Response Mechanisms AS Anshad, PK Poonguzhali, S Srivastava, R Vidhya, S CS, G Saravanan, ... AI-Driven Cybersecurity for Autonomous Systems, 85-116 , 2026 2026
Intelligent Anomaly Detection for Secure Data Transmission in Cloud Computing Systems over 6G Networks AS Anshad, P Charan, I Khan, A MR, S Maurya, S Hiremath, D Anil Engineering, Technology & Applied Science Research 15 (6), 30349-30355 , 2025 2025 Citations: 3
WEARABLE DISASTER EMERGENCY COMMUNICATION DEVICE DA A S IN Patent 440002-001 , 2025 2025
Fuzzy Logic-SVM Integration for Energy-Efficient Intrusion Detection in Wireless Sensor Networks PN Bhatt, AR SR, M Karthikkumar, G Deepa, K Sathish 2025 2nd Asian Conference on Intelligent Technologies (ACOIT), 1-7 , 2025 2025
An Intelligent Hybrid Quantum-Deep Reinforcement Framework for Energy-Efficient Routing in Wireless Sensor Networks DA A S 2025 6th International Conference for Emerging Technology (INCET) , 2025 2025 Citations: 4
Restoration of Soil Microbial Diversity through Long-Term Organic Cultivation Practices AS Anshad Europian Journal of Organic Farming & Agri Practices E ISSN-3051-0236 1 (06 … , 2025 2025
Towards Accurate Glioma Segmentation: A Modified HTTU-Net with Multi-Scale Feature Encoding AS Anshad, HS Saghra, M Kumari, D Deepa, R Shreeshayana, A Kubba 2025 5th Asian Conference on Innovation in Technology (ASIANCON), 1-7 , 2025 2025
Enhancing Security in Wireless Sensor Networks with a Deep Learning and Game Theory-Based Hybrid Model for Malicious Node Detection AS Anshad, J Elumalai, RN Sajin, K Janani 2025 1st International Conference on Radio Frequency Communication and … , 2025 2025
A Blockchain-Enabled Secure and Energy-Efficient Routing Protocol for Wireless Sensor Networks in Environmental Monitoring Using RL-DDPGA AS Anshad, MN Geetha, M Ganesha 2025 1st International Conference on Radio Frequency Communication and … , 2025 2025 Citations: 2
Artificial Intelligence and Machine Learning - Driven Approaches to Enhance Project Management in Engineering DA A S Machine Intelligence Research 19 (1(2025)), 390-403 , 2025 2025
A SYSTEM AND METHOD FOR ENERGY OPTIMIZATION IN WIRELESS SENSOR NETWORKS DA A S IN Patent 122193 - 49/2025 Dated 05/12/2,025 , 2025 2025
Self-Supervised Vision Transformers for Next-Generation Object Detection and Image Segmentation AS Anshad, BS Yogesh, Preethi, D Anil, M Kaur, A Kaur International Conference on Computer Vision and Robotics, 167-177 , 2025 2025
Integrating IoT and Wireless Sensor Networks for Precision Agriculture Using TD-CNN-LSTM AS Anshad, K Sravanthi, S Manivannan, N Malik, S Kaliappan, A Perada 2025 International Conference on Advances in Modern Age Technologies for … , 2025 2025 Citations: 1
Communication Protocols and AI Integration for Real-Time Monitoring and Predictive Healthcare Systems in Smart Cities DA A S RadEmics Publications https://rademics.com/books/43 1, 463 , 2025 2025
Proceedings of NCRIESR 2025 EDA A S National Conference on Recent Innovation in Engineering and Scientific … , 2025 2025
Artificial Intelligence-Powered Learning Analytics and Student Feedback Mechanisms for Dynamic Curriculum Enhancement and Continuous Quality Improvement in Outcome-Based Education DA A.S RadEmics ISBN: 9789349552531 1, 502 , 2025 2025
Smart Farming Technologies: Integrating AI and IoT for Sustainable Agriculture AS Anshad Agricultural Innovation and Sustain Ability Journal E-ISSN 3051-0325 1 (01 … , 2025 2025 Citations: 1
WIRELESS CHARGING STATION INTEGRATED WITH SENSOR DA A S IN Patent 440012-001 , 2025 2025
MOST CITED SCHOLAR PUBLICATIONS
Artificial intelligence-powered learning analytics and student feedback mechanisms for dynamic curriculum enhancement and continuous quality improvement in outcome-based education PK Scholapurapu DOI 10, 9789349552531-06 , 2025 2025.0 Citations: 10
Fundamentals of Research Methodology and Intellectual Property Rights DA Anshad RK Publishers , 2025 2025.0 Citations: 5
Intelligent Healthcare System. RadEmics, 2025 DA Anshad Citations: 5
An Intelligent Hybrid Quantum-Deep Reinforcement Framework for Energy-Efficient Routing in Wireless Sensor Networks DA A S 2025 6th International Conference for Emerging Technology (INCET) , 2025 2025.0 Citations: 4
Enhanced connectivity for nodes to measure coverage range using anchor node–based PATH monitoring algorithm in WSN AS Anshad, R Radhakrishnan Transactions on Emerging Telecommunications Technologies 31 (12), e3836 , 2020 2020.0 Citations: 4
Intelligent Anomaly Detection for Secure Data Transmission in Cloud Computing Systems over 6G Networks AS Anshad, P Charan, I Khan, A MR, S Maurya, S Hiremath, D Anil Engineering, Technology & Applied Science Research 15 (6), 30349-30355 , 2025 2025.0 Citations: 3
A Blockchain-Enabled Secure and Energy-Efficient Routing Protocol for Wireless Sensor Networks in Environmental Monitoring Using RL-DDPGA AS Anshad, MN Geetha, M Ganesha 2025 1st International Conference on Radio Frequency Communication and … , 2025 2025.0 Citations: 2
Improved network lifetime to identify unexploited PATH using series cornerstone PATH algorithm in wireless sensor networks AS Anshad, R Radhakrishnan Peer-to-Peer Networking and Applications 13 (6), 2189-2200 , 2020 2020.0 Citations: 2
Integrating IoT and Wireless Sensor Networks for Precision Agriculture Using TD-CNN-LSTM AS Anshad, K Sravanthi, S Manivannan, N Malik, S Kaliappan, A Perada 2025 International Conference on Advances in Modern Age Technologies for … , 2025 2025.0 Citations: 1
Smart Farming Technologies: Integrating AI and IoT for Sustainable Agriculture AS Anshad Agricultural Innovation and Sustain Ability Journal E-ISSN 3051-0325 1 (01 … , 2025 2025.0 Citations: 1
An Energy Efficient Improved Clustering based Data Compression Protocol in Wireless Sensor Network AS Anshad, S Tiwari, GD Vignesh, P Charan, KR Chandra, R Manchanda 2024 7th International Conference on Contemporary Computing and Informatics … , 2024 2024.0 Citations: 1
AI Based.Road Accident Prediction Device DA A S IN Patent 445261-001 , 2026 2026.0
Energy-Efficient EEG-Based Autism Spectrum Disorder Detection Using a Hyperbolic Attention Neural Network AS Anshad, K Padmanaban, J Anupama Developmental neurobiology 86 (2), e70011 , 2026 2026.0
AI-Based Intrusion Detection and Response Mechanisms AS Anshad, PK Poonguzhali, S Srivastava, R Vidhya, S CS, G Saravanan, ... AI-Driven Cybersecurity for Autonomous Systems, 85-116 , 2026 2026.0
WEARABLE DISASTER EMERGENCY COMMUNICATION DEVICE DA A S IN Patent 440002-001 , 2025 2025.0
Fuzzy Logic-SVM Integration for Energy-Efficient Intrusion Detection in Wireless Sensor Networks PN Bhatt, AR SR, M Karthikkumar, G Deepa, K Sathish 2025 2nd Asian Conference on Intelligent Technologies (ACOIT), 1-7 , 2025 2025.0
Restoration of Soil Microbial Diversity through Long-Term Organic Cultivation Practices AS Anshad Europian Journal of Organic Farming & Agri Practices E ISSN-3051-0236 1 (06 … , 2025 2025.0
Towards Accurate Glioma Segmentation: A Modified HTTU-Net with Multi-Scale Feature Encoding AS Anshad, HS Saghra, M Kumari, D Deepa, R Shreeshayana, A Kubba 2025 5th Asian Conference on Innovation in Technology (ASIANCON), 1-7 , 2025 2025.0
Enhancing Security in Wireless Sensor Networks with a Deep Learning and Game Theory-Based Hybrid Model for Malicious Node Detection AS Anshad, J Elumalai, RN Sajin, K Janani 2025 1st International Conference on Radio Frequency Communication and … , 2025 2025.0
Artificial Intelligence and Machine Learning - Driven Approaches to Enhance Project Management in Engineering DA A S Machine Intelligence Research 19 (1(2025)), 390-403 , 2025 2025.0
