Wireless Sensor Networks for Pointer Meter Recognition

Even though smart instruments are popular in modern industrial processes, pointer meters without computer interfaces are still widely employed in many application areas. Automatic reading recognition of pointer meters based on computer vision provides a promising solution to input the meter readings to the existing monitoring system or IoT. However, most of the current reading recognition approaches for pointer meters are based on inconvenient wired systems or expensive inspection robots. Compared with a wired system, wireless sensor networks (WSNs) are low-cost, easy to install and relocate. To leverage these advantages of WSNs and address the limitation of its radio bandwidth, this paper proposes a novel automated meter reading system for pointer meter using WSNs with on-sensor image processing, in which meter image capturing, image preprocessing, and reading recognition are completed on WSNs end node, and then only the recognition result is transmitted through WSNs. The feasibility of the proposed method is evaluated by a set of experiments on the prototype. Experimental results indicate that the presented approach can recognize the meter reading with an error of 0.3% and significantly reduce the payload transmission data in the WSNs.

Automatic recognition system of pointer meters based on lightweight CNN and WSNs with on-sensor image processing

Wireless sensor networks have received a lot of attention in recent years due to their wide spectrum of applications. Localization a technique used in ubiquitous sensor networks. Most localization techniques apply RSSI-based ranging techniques to compute the location of the object in a wireless sensor network. However, a wireless sensor network is a fading-signal environment that has noise, which causes RSSI to become unstable and leads to abrupt distance estimates. In this paper, we propose the Verification-Based Localization Method (VBLM) to alleviate the effect of unstable signals to provide high-accuracy location estimates in wireless sensor environments. VBLM filters noisy signals in the localization process. The sensor node uses a neighboring beacon to help verify the quality of received signal under acceptable communication cost. Noisy signals can thus be removed to decrease localization error. A set of experiments was conducted in an outdoor environment. The experimental results show that VBLM reduces the localization error in unstable signal sensor networks better than is possible with other localization methods.

Wireless sensor networks are often only used to transmit monitored data to a central processing unit. However, they also offer the possibility to establish local intelligence and allow localized problem solutions. Existing monitoring systems have the following main drawbacks: centralized architecture that requires expensive infrastructure to run it, centralized decision making that makes reactions on events too slow and has high communication cost. In this paper we explore application of localized auction algorithms in decision making process. We show advantages of localized decision making over centralized in terms of communication cost minimization. Instead of using usual decision-level methods (e.g. weighted decision, classical inference etc.) we propose using localized auctions to get and combine relevant sensor information to make the decision. Simulation results are shown in the paper.

Underground coal mines are susceptible to many kinds of hazards. Mine fire is one of the most vulnerable threats that leads to loss of human lives and other resources inside the mines. Hence, continuous monitoring of underground coal mines is very important for early detection of mine fire. Nowadays, wireless sensor networks are being widely used for monitoring underground coal mines. However, the collected data from sensor nodes are inaccurate in nature, and there is a need for analyzing such data for taking preventive measure. In this article, we propose an optimized fuzzy logic-based fire monitoring system for wireless underground sensor network, which strengthens reliability of making decision in preventing mine fire. However, storing of large fuzzy rule set in the memory constraint sensor nodes and their traversal for every sensor reading are very challenging. Therefore, we use the binary particle swarm optimization (BPSO) algorithm to optimize the proposed fuzzy system that eliminates redundant rules but preserves event detection accuracy of the monitoring system. The proposed system is simulated using BPSO algorithm and Fuzzy Logic Toolbox inbuilt in the MATLAB. The simulation results demonstrate that the proposed system outperforms the existing monitoring systems for underground coal mines.

formula omitted]CA-GAM-ID: Coupling of probabilistic principal components analysis with generalised additive model to predict the [formula omitted]barriers for intrusion detection

Wireless Sensor Networks (WSN) play a vital role in IoT, smart agriculture and environmental monitoring, but their performance is severely limited by high energy consumption, inefficient routing and unbalanced clustering. This work introduces a hybrid energy-efficient routing framework that integrates Fuzzy Logic-based Extended Reinforcement Learning (FL-ERL) for adaptive cluster formation, Tent random function-based Bald Eagle Optimization (TBEO) for optimal Cluster Head (CH) selection and a genetic Levy flight-based optimized routing mechanism (GL-ORM) for global inter-cluster routing. The proposed model effectively optimizes node residual energy, node to Base Station (BS) distance and processing delay for a large-scale WSN with 1000 nodes. Simulated results in MATLAB demonstrate significant improvements over state-of-the-art models such as Black Widow Optimization Algorithm (BWOA), Spider Monkey Optimization (SMO), Fish Swarm Optimization (FSO), Grey Wolf Optimization (GWO) and Ant Colony Optimization (ACO). Specifically, the proposed method reduces energy consumption to 6.68 J, achieving 68%–72% reduction compared with GWO (20.12 J) and FSO (17.15 J). The model achieves a 50% higher throughput of 0.95 than ACO and maintains a 95% packet delivery ratio, outperforming existing schemes by 10–30%. These results highlight robustness, scalability and energy efficiency of the proposed framework, which demonstrates its ability to prolong WSN lifetime. This approach provides significance and reliable data delivery.

In today’s world, one of the most severe attacks that wireless sensor networks (WSNs) face is a Black-Hole (BH) attack which is a type of Denial of Service (DoS) attack. This attack blocks data and injects infected programs into a set of sensors in a group to capture packets before reached to the target. Therefore, raw data in the BH region is thwarted and is unable to reach its destination. The network is susceptible to various types of attacks as it is accessible to all types of users and minimizing the energy depletion without compromising the network lifetime is an NP-hard problem. Even though numerous protocols came into effect to overcome the BH attack and to enhance the security of packet delivery in WSNs, Simulated Annealing Black-hole attack Detection (SABD) based Enhanced Gravitational Search Algorithm (EGSA) is yet another implemented strategy to reduce the BH attacks. EGSA-SABD detects and isolates the BH infectors in WSNs. Initially, sensor nodes are hierarchically clustered using similar residual energy to reduce energy consumption. Then, the BH attack possibility in a deployed node is evaluated to find the existence of BH nodes in the region. In the end, EGSA-SABD is employed to detect and quarantine BH attackers in WSNs. The performance of EGSA-SABD is evaluated with certain metrics such as BH attack detection probability rate (BHatt_Prate), energy consumption (Ec), Duration of BH attack detection (Attduration), Packet delivery ratio (Pdr). Based on the experimental observations, the EGSA-SABD outperforms the BHatt_Prate by 13% and also reduces the energy consumption by 21%.

Wireless sensor networks, by providing an unprecedented way of interacting with the physical environment, have become a hot topic for research over the last few years. As with any new technology, results from real experimentations using these networks are still scarce, as real deployments are either costly, or still unfeasible in the current state of technology. There is therefore an increasing need for simulation tools allowing the testing of different architectures, communication protocols or information processing algorithms in sensor networks. In this paper, we investigate a simulation framework for the testing of data processing in wireless sensor network applications. In a first stage, data is generated using partial differential equations, allowing the modeling of a large panel of physical phenomena. In a second stage, sensing unit operating system and network constraints are simulated using an instance of a versatile simulator to account for the platform characteristics. Insights provided by the proposed simulation frame are illustrated by a set of experiments on a heat source detection task.

Optimizing K-coverage of mobile WSNs

Wireless Sensor Networking is a sensor information gathering technology that has a wide range of applications in numerous fields. However due to the fact that sensor nodes have limited battery and are deployed in remote and harsh environments, energy efficient and real time transmission of the information are still open challenges. Since in a wireless sensor network data transmission is the most power consuming task, so far most useful techniques for the purpose of energy efficient and real time transmissions are based on data compression, the majority of them are based on wavelet transform. This paper give performance analysis of different wavelets for energy efficient and real time image data transmission in application like environment monitoring using wireless visual sensor networks. The performance evaluation shows that Haar wavelet is better in terms of energy efficiency and transmission time.

Location-awareness plays an important role in Wireless Sensor Networks (WSNs) by aiding in tasks such as packet routing, event mapping, and energy savings. The use of Global Positioning System (GPS) on sensor nodes is not always viable due to a number of issues, e.g., power constraints. Location estimation solves the problem of computing sensor node positions by using information from devices that can house a GPS module, e.g., a mobile sink. However, GPS error may affect the accuracy of position estimations. In this paper, we propose a range-based scheme that uses trilateration and also handles GPS error. The proposed approach takes advantage of sink beacons used in packet routing. These beacons are used as position packets in order to estimate the position of nodes while reducing network overhead. However, a mobile sink poses issues when used as a source of position packets. Therefore, we propose Position Distance, Circle Limit and a Hybrid version of the algorithms in order to decide on the best position packets from the sink to be used in trilateration. An extensive set of performance evaluation experiments is conducted and results show that the proposed algorithms can improve position estimation accuracy, while sustaining acceptable packet delivery ratio and reducing network overhead.

A scalable approach for serial data fusion in Wireless Sensor Networks

Abstract. Low cost cameras and embedded devices with high processing capabilities have increased the use of computer vision systems for precision agriculture applications. Image processing devices may serve as remote sensing nodes to measure the vegetative development for different crop areas. Therefore, these types of devices require to be included as additional elements into current wireless sensor networks (WSN) in order to acquire and transmit image data. IEEE 802.15.4 protocol has become the de facto standard for the implementation of WSN due the low-cost and low-power consumption technology. However, this protocol has been designed to communicate small amount of data, which produces a big challenge when large image files are integrated into the current network infrastructure and have to be fragmented and transmitted into small data packets. This paper evaluates the performance of static and dynamic scheduling policies for the communication of image data through a WSN, in a typical precision agriculture application such as a closed-loop irrigation system. The parameters considered on the performance evaluation include communication bandwidth, packet loss rate, and also the effects on the overall performance of the irrigation system are analyzed.

SummarySoftware‐defined wireless sensor network (SDWSN) has aroused great interest due to its new operating characteristics in recent years. For instance, centralized user association control, full network state information perception, and seamless switching. Furthermore, with the development of the Internet of things(IoT), all sensors and user equipment (UE) will be connected. The proposal of the Internet of everything concept has expanded the scope of SDWSN. It is a very challenging issue to ensure the quality of experience(QoE) while achieving load balancing when associating the UE and the base station (BS). Based on the new features of SDWSN, this paper studies a multi‐objective optimization model under multiple constraints in high‐density situations. The goal is to minimize the number of unsatisfied UEs and maximize system throughput by achieving load balancing. This problem was solved by employing an artificial neural network (ANN), which was optimized by the fruit fly optimization algorithm (FOA). This ANN–FOA scheme greatly reduced the execution time and significantly promoted the result of the multi‐objective optimization model. Through simulation, we verified the effectiveness of our proposed ANN–FOA scheme, and the influence of different sample quantity and different ANN architecture on the final result was explored.