Predictive Boundary Tracking based on Motion Behavior Learning for Continuous Objects in Industrial Wireless Sensor Networks
Abstract : The diffusion of toxic gas, biochemical material, and radio-active contamination, known as continuous objects, endangers the safe production of petrochemical and nuclear industry. Industrial wireless sensor networks are a new paradigm, which shows great potential in monitoring evolving hazardous phenomena in unfriendly industrial field. To prolong the lifetime of IWSNs, existing research focuses on energy-efficient boundary nodes selection. However, sensor state cannot be scheduled proactively due to the difficulty of predicting the spatiotemporal evolution of diffusive hazard. In this article, we propose a predictive boundary tracking algorithm based on motion behavior learning (MBLPT) for continuous objects in IWSNs. Considering the multiple behavior patterns exhibited by continuous objects, MBLPB establishes data-driven models for motion state recognition, and then utilizes Bayesian model averaging for future boundary prediction. The prediction of MBLPT provides the knowledge for establishing a wake-up zone, in which sleeping nodes are activated in advance to participate in tracking the upcoming boundary. Simulation results demonstrate that MBLPB achieves superior energy efficiency under acceptable tracking accuracy.The diffusion of toxic gas, biochemical material, and radio-active contamination, known as continuous objects, endangers the safe production of petrochemical and nuclear industry. Industrial wireless sensor networks are a new paradigm, which shows great potential in monitoring evolving hazardous phenomena in unfriendly industrial field. To prolong the lifetime of IWSNs, existing research focuses on energy-efficient boundary nodes selection. However, sensor state cannot be scheduled proactively due to the difficulty of predicting the spatiotemporal evolution of diffusive hazard. In this article, we propose a predictive boundary tracking algorithm based on motion behavior learning (MBLPT) for continuous objects in IWSNs. Considering the multiple behavior patterns exhibited by continuous objects, MBLPB establishes data-driven models for motion state recognition, and then utilizes Bayesian model averaging for future boundary prediction. The prediction of MBLPT provides the knowledge for establishing a wake-up zone, in which sleeping nodes are activated in advance to participate in tracking the upcoming boundary. Simulation results demonstrate that MBLPB achieves superior energy efficiency under acceptable tracking accuracy.
? In this paper, we compare the continuous object localization and boundary detection schemes with respect to complexity, energy consumption, and estimation accuracy.
? Moreover, this paper presents the research directions for existing and future gas leakage source localization and boundary estimation schemes with WSNs.
? It is noted that this method outperforms several existing methods with the CRB accuracy.
? This survey provides a comprehensive overview of the existing and emerging work on gas leakage source detection and tracking of continuous objects with WSNs.Multiple gas source localization is less discussed in the existing literature.
? The itinerary scheduling of multiple mobile sensors can be reduced to a multiobjective optimization problem, which can be solved through adopting heuristic algorithms.
? We do not focus on static sensors’ data transmission strategy mainly because many researches have worked on data transmission routing problem.
? It requires that energy consumption and time consumption are similar for each mobile sensor. It can be formulated as a multiobjective optimization problem.
? To solve this multiobjective and multiconstrained optimization problem, heuristic algorithm like ACO can be applied to solve this kind of issues .
• An improved scheme is proposed in that reduces complexity of the algorithm by applying the decay factor.
• Afterward, an effective source localization algorithm called equilateral triangular distribution trilateration algorithm (ETDT) is proposed in where the beacon nodes are deployed in the equilateral triangles.
• To prolong the network lifetime, a distributed processing is proposed in where many intermediate estimates (IEs) are used in some of the active nodes.
• A distributed source localization method is proposed based on convex sets. Meanwhile, two parametric belief representation methods, which are suitable for various source types in different environments, are proposed for the distributed processing.
? Extensive evaluations are conducted to evaluate the accuracy of object boundary and the performance of mobile sensors deployment technique.
? We analyze the performance of mobile sensors. After network initialization, we select some stop stations on the predicted BL.
? In , a mobile WSN is applied to intrusion detection, and fog computing is applied to improve the network performance.
? Energy efficiency is the key issue in IoT, since IoT smart things are mostly battery-powered, and they are hardly to be recharged due to the harsh working environment.
? Mobile sensors collaborate to bypass sensing holes for generating a precise object boundary, while the energy efficiency is a main concern.
|