Call For Paper Volume: V, Issue: 08 | AUGUST 2026 | International Journal of Advanced Trends in Engineering and Management (IJATEM)
Volume V | Issue 7 | 2026 | Paper ID: IJATEM-V05I07P3

Smart Home Intrusion Detection using a Kepler Optimized Dual Attention Sparse Transformer Network

Thomas Thangam

Smart Home Intrusion Detection Systems (IDS) protect residence by monitoring physical break and network vulnerabilities through integrated sensors and real time alerts. Therefore, in this paper, a Dual Attention Sparse Transformer Network (DASTN) with Kepler Optimization Algorithm (KOA) is proposed for smart home intrusion detection. Data preprocessing in a smart home IDS converts raw, noisy IoT sensor and network traffic logs into a clean format that Deep Learning (DL) models can accurately analyse. A DASTN detects smart home cyber threats by combining spatial temporal feature extraction with reduced computational overhead. The KOA is a physics-based metaheuristic technique used to fine-tune complex model architectures, optimize weights, and select critical hyperparameters. The performance analysis is carried out using python software and assesses the model's performance using key metrics such as precision, recall, F1-score, confusion matrix, and ROC-AUC. The proposed DASTN-KOA uses two classes and the proposed DASTN-KOA achieves high accuracy of 96.67% and better convergence speed. The proposed method outperforms conventional techniques, contributing a robust and reliable tool for smart home intrusion detection system.

DASTN, KOA, Smart home IDS, precision, recall, F1-score, confusion matrix, and ROC-AUC.

  • [1] Kang-Di Lu; Yao-Wei Yang; Guo-Qiang Zeng; Chen Peng; Guang-Gang Geng; Jian Weng, Year: 2025, “BPSO-AHDL-IDS: Binary Particle Swarm Optimization-Based Automated Hybrid Deep Learning Model for Intrusion Detection of Internet of Things”, IEEE Transactions on Automation Science and Engineering, Vol: 22.

  • [2] Fisayo Sangoleye; Jay Johnson; Eirini Eleni Tsiropoulou, Year: 2024, “Intrusion Detection in Industrial Control Systems Based on Deep Reinforcement Learning”, IEEE Access, Vol: 12.

  • [3] Mohamad Khayat; Ezedin Barka; Mohamed Adel Serhani; Farag Sallabi; Khaled Shuaib; Heba M. Khater, Year: 2025, “Reinforcement Learning With Deep Features: A Dynamic Approach for Intrusion Detection in IoT Networks”, IEEE Access, Vol: 13.

  • [4] Goce Stevanoski; Aleksandar Risteski; Nevena Serafimova; Marko Porjazovski; Mitko Bogdanoski, Year: 2026, “A Two-Stage Pareto-Driven Framework for Adaptive Resource Optimization in Lightweight Intrusion Detection Systems”, IEEE Access, Vol: 14.

  • [5] Sandeepkumar Racherla; Prathyusha Sripathi; Nuruzzaman Faruqui; Md Alamgir Kabir; Md Whaiduzzaman; Syed Aziz Shah, Year: 2024, “Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning”, IEEE Access, Vol: 12.

  • [6] Yue Li; Jiale Zhang; Yiting Yan; Yutian Lei; Chang Yin, Year: 2024, “Enhancing Network Intrusion Detection Through the Application of the Dung Beetle Optimized Fusion Model”, IEEE Access, Vol. 12.

  • [7] Manohar Srinivasan; Narayanan Chidambaram Senthilkumar, Year: 2025, “Intrusion Detection and Prevention System (IDPS) Model for IIoT Environments Using Hybridized Framework”, IEEE Access, Vol: 13.

  • [8] Kang-Di Lu; Jia-Cheng Huang; Guo-Qiang Zeng; Min-Rong Chen; Guang-Gang Geng; Jian Weng, Year: 2025, “Multi-Objective Discrete Extremal Optimization of Variable-Length Blocks-Based CNN by Joint NAS and HPO for Intrusion Detection in IIoT”, IEEE Transactions on Dependable and Secure Computing, Vol: 22, No: 4.

  • [9] Jing Li; Mohd Shahizan Othman; Xugang Ying; Dina S. M. Hassan; Hewan Chen; Lizawati Mi Yusuf, Year: 2026, “Adaptive NetFlow IIoT Intrusion Detection With Deep Transfer Learning, Genetic Optimization, and Ensemble Methods for Network Management”, IEEE Transactions on Network and Service Management, Vol: 23.

  • [10] Om Kumar Chandra Umakantham; Sudhakaran Gajendran; Suguna Marappan, Year: 2024, “Enhancing Intrusion Detection Through Federated Learning With Enhanced Ghost_ BiNet and Homomorphic Encryption”, IEEE Access, Vol: 12.