An Adaptive Lightweight Energy Efficient AI Assisted Nomaly Detection with Real Time Threat Mitigation for Resource Constrained Wireless Networks | Journal of Engineering Strategy and Innovation | JESI

Journal of Engineering Strategy and Innovation

Back to Archive
Research Article Portal Node

An Adaptive Lightweight Energy Efficient AI Assisted Nomaly Detection with Real Time Threat Mitigation for Resource Constrained Wireless Networks

Author(s) Registry Sivakami S, Ariharan K, Kishore Raj D K
Volume & IssueVol 1, Iss 01
Acceptance Date27 Jun 2026
Publication Date21 Jul 2026
Digital DOI Handle*

Abstract

Because of their restricted processing power, memory capacity, and battery limitations, resource-constrained wireless networks are more vulnerable to sophisticated cyberattacks. For wireless networks with limited resources, this study suggests a lightweight AI-assisted adaptive anomaly detection framework combined with an energy-efficient real-time threat mitigation mechanism. The suggested framework minimizes computing complexity by effectively analyzing both global traffic dependencies and sequential attack patterns using a lightweight hybrid Transformer-Gated Recurrent Unit (Transformer-GRU) model. In order to minimize false alarms, an adaptive anomaly threshold method dynamically modifies detection sensitivity in response to shifting network traffic patterns. In order to maintain network lifetime, an energyaware mitigation technique also optimizes communication routing and selectively isolates harmful nodes. The suggested framework delivers better detection accuracy, a lower false positive rate, minimal computing overhead, and increased energy economy, according to experimental evaluation.

Keywords

foreach(explode(',', $paper['keywords']) as $keyword) { $trimmed_keyword = trim($keyword); if(!empty($trimmed_keyword)) { echo '' . htmlspecialchars($trimmed_keyword) . ''; } } ?>

References (31)

  1. Gudala, Leeladhar, Mahammad Shaik, Srinivasan Venkataramanan, and Ashok Kumar Reddy Sadhu. Journal of Engineering Strategy and Innovation, 01(1), 41-48, 2026 8 "Leveraging artificial intelligence for enhanced threat detection, response, and anomaly identification in resource- constrained iot networks." Distributed Learning and Broad
  2. Applications in Scientific Research 5 (2019): 23-54.
  3. Parameswari, M., Nancy P, and R. Jeya Malar. "Next generation AI powered framework for autonomous energy optimization and real time anomaly detection in IoT driven wireless sensor networks." Scientific Reports 15, no. 1 (2025):
  4. Babalola, Olufunbi, Olaitan Miriam Olufisayo Raji, Jamiu Olamilekan Akande, Abdullahi Olalekan Abdulkareem, Vincent Anyah, Adeladan Samson, and Steve Folorunso. "AI- powered cybersecurity in edge computing: Lightweight neural models for anomaly detection." International Journal of Multidisciplinary Research and Growth Evaluation 5, no. 2 (2024): 1130-1138.
  5. Reis, Manuel JCS. "Lightweight Signal Processing and Edge AI for Real-Time Anomaly Detection in IoT Sensor
Download Full PDF
Total Downloads 0
Page Matrix pp. 40 - 47
Scholarly Citation Asset

An Adaptive Lightweight Energy Efficient AI Assisted Nomaly Detection with Real Time Threat Mitigation for Resource Constrained Wireless Networks

[1] S. S, A. K, K. R. D. K, "An Adaptive Lightweight Energy Efficient AI Assisted Nomaly Detection with Real Time Threat Mitigation for Resource Constrained Wireless Networks," *Journal of Engineering Strategy and Innovation (JESI)*, vol. 1, no. 1, pp. 40-47, 2026.