Recent Advances in Dynamic Path-Controllable Deep Unfolding Network to Predict the K-Barriers for Intrusion Detection Using a Wireless Sensor Network: A Systematic Review

Abstract

Wireless Sensor Networks (WSNs) play a crucial role in surveillance, border security, and intrusion detection systems. One of the fundamental problems in WSN-based intrusion detection is the prediction and maintenance of k-barriers, which ensure that an intruder cannot pass undetected through the network. The concept of barrier coverage is directly linked to network security and resilience, where the objective is to detect intrusion paths by minimizing undetected regions.  Recent advances in Artificial Intelligence (AI), particularly deep learning and deep unfolding networks, have significantly enhanced the ability to predict k-barriers and optimize intrusion detection mechanisms. Deep learning-based approaches such as Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks have demonstrated high accuracy in predicting k-barriers using network parameters like sensing range, node density, and transmission characteristics.  Dynamic path-controllable deep unfolding networks represent a novel paradigm that integrates model-based optimization with data-driven learning. These approaches enable adaptive path selection, improved intrusion detection accuracy, and efficient resource utilization in WSNs. Additionally, hybrid models combining CNN-LSTM architectures and fuzzy neural networks provide enhanced performance by capturing both spatial and temporal dependencies in network data.  This paper presents a systematic review of recent advancements (2020–2023) in AI-based k-barrier prediction and intrusion detection in WSNs. It analyses 30 studies, identifies emerging trends, compares techniques, and highlights key challenges such as computational complexity, scalability, and real-time deployment. The review concludes that deep unfolding and hybrid AI models are promising solutions for next-generation intrusion detection systems in wireless sensor networks.