scholarly journals Learning Wireless Sensor Networks for Source Localization

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 635 ◽  
Author(s):  
S. Javadi ◽  
Hossein Moosaei ◽  
Domenico Ciuonzo
Keyword(s):  
Wireless Sensor Networks ◽  
Support Vector Machine ◽  
Sensor Networks ◽  
Source Localization ◽  
State Of The Art ◽  
Low Cost ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Support Vector ◽  
Network Nodes

Source localization and target tracking are among the most challenging problems in wireless sensor networks (WSN). Most of the state-of-the-art solutions are complicated and do not meet the processing and memory limitations of the existing low-cost sensor nodes. In this paper, we propose computationally-cheap solutions based on the support vector machine (SVM) and twin SVM (TWSVM) learning algorithms in which network nodes firstly detect the desired signal. Then, the network is trained to specify the nodes in the vicinity of the source (or target); hence, the region of event is detected. Finally, the centroid of the event region is considered as an estimation of the source location. The efficiency of the proposed methods is shown by simulations.

scholarly journals Anomaly Detection in Medical Wireless Sensor Networks using SVM and Linear Regression Models

2014 ◽  
Vol 5 (1) ◽  
pp. 20-45 ◽  
Author(s):  
Osman Salem ◽  
Alexey Guerassimov ◽  
Ahmed Mehaoua ◽  
Anthony Marcus ◽  
Borko Furht
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Anomaly Detection ◽  
Patient Data ◽  
Sensor Nodes ◽  
Sensor Data ◽  
Wireless Sensor ◽  
Smart Devices ◽  
Support Vector ◽  
Processing Unit

This paper details the architecture and describes the preliminary experimentation with the proposed framework for anomaly detection in medical wireless body area networks for ubiquitous patient and healthcare monitoring. The architecture integrates novel data mining and machine learning algorithms with modern sensor fusion techniques. Knowing wireless sensor networks are prone to failures resulting from their limitations (i.e. limited energy resources and computational power), using this framework, the authors can distinguish between irregular variations in the physiological parameters of the monitored patient and faulty sensor data, to ensure reliable operations and real time global monitoring from smart devices. Sensor nodes are used to measure characteristics of the patient and the sensed data is stored on the local processing unit. Authorized users may access this patient data remotely as long as they maintain connectivity with their application enabled smart device. Anomalous or faulty measurement data resulting from damaged sensor nodes or caused by malicious external parties may lead to misdiagnosis or even death for patients. The authors' application uses a Support Vector Machine to classify abnormal instances in the incoming sensor data. If found, the authors apply a periodically rebuilt, regressive prediction model to the abnormal instance and determine if the patient is entering a critical state or if a sensor is reporting faulty readings. Using real patient data in our experiments, the results validate the robustness of our proposed framework. The authors further discuss the experimental analysis with the proposed approach which shows that it is quickly able to identify sensor anomalies and compared with several other algorithms, it maintains a higher true positive and lower false negative rate.

Efficient Energy Conservation and Faulty Node Detection on Machine Learning-Based Wireless Sensor Networks

2021 ◽  
Vol 13 (2) ◽  
pp. 1-20
Author(s):  
Amarasimha T. ◽  
V. Srinivasa Rao
Keyword(s):  
Machine Learning ◽  
Wireless Sensor Networks ◽  
Energy Consumption ◽  
Sensor Networks ◽  
Data Communication ◽  
Energy Utilization ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Support Vector ◽  
Faulty Node

Wireless sensor networks are used in machine learning for data communication and classification. Sensor nodes in network suffer from low battery power, so it is necessary to reduce energy consumption. One way of decreasing energy utilization is reducing the information transmitted by an advanced machine learning process called support vector machine. Further, nodes in WSN malfunction upon the occurrence of malicious activities. To overcome these issues, energy conserving and faulty node detection WSN is proposed. SVM optimizes data to be transmitted via one-hop transmission. It sends only the extreme points of data instead of transmitting whole information. This will reduce transmitting energy and accumulate excess energy for future purpose. Moreover, malfunction nodes are identified to overcome difficulties on data processing. Since each node transmits data to nearby nodes, the misbehaving nodes are detected based on transmission speed. The experimental results show that proposed algorithm provides better results in terms of reduced energy consumption and faulty node detection.

Basic Concepts of Wireless Sensor Networks

2011 ◽  
pp. 57-64
Author(s):  
Lina M. Pestana Leão de Brito ◽  
Laura M. Rodríguez Peralta
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Low Cost ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Distributed Sensor Networks ◽  
Distributed Sensor ◽  
Technological Advances ◽  
The Cost ◽  
Communication Equipment

As with many technologies, defense applications have been a driver for research in sensor networks, which started around 1980 due to two important programs of the Defense Advanced Research Projects Agency (DARPA): the distributed sensor networks (DSN) and the sensor information technology (SensIT) (Chong & Kumar, 2003). However, the development of sensor networks requires advances in several areas: sensing, communication, and computing. The explosive growth of the personal communications market has driven the cost of radio devices down and has increased the quality. At the same time, technological advances in wireless communications and electronic devices (such as low-cost, low-power, small, simple yet efficient wireless communication equipment) have enabled the manufacturing of sensor nodes and, consequently, the development of wireless sensor networks (WSNs).

scholarly journals Fast outlier detection for high-dimensional data of wireless sensor networks

2020 ◽  
Vol 16 (10) ◽  
pp. 155014772096383
Author(s):  
Yan Qiao ◽  
Xinhong Cui ◽  
Peng Jin ◽  
Wu Zhang
Keyword(s):  
Wireless Sensor Networks ◽  
Support Vector Machine ◽  
Sensor Networks ◽  
Outlier Detection ◽  
Large Scale ◽  
Deep Belief Network ◽  
Wireless Sensor ◽  
High Dimensional ◽  
Support Vector ◽  
Belief Network

This article addresses the problem of outlier detection for wireless sensor networks. As increasing amounts of observational data are tending to be high-dimensional and large scale, it is becoming increasingly difficult for existing techniques to perform outlier detection accurately and efficiently. Although dimensionality reduction tools (such as deep belief network) have been utilized to compress the high-dimensional data to support outlier detection, these methods may not achieve the desired performance due to the special distribution of the compressed data. Furthermore, because most existed classification methods must solve a quadratic optimization problem in their training stage, they cannot perform well in large-scale datasets. In this article, we developed a new form of classification model called “deep belief network online quarter-sphere support vector machine,” which combines deep belief network with online quarter-sphere one-class support vector machine. Based on this model, we first propose a model training method that learns the radius of the quarter sphere by a sorting method. Then, an online testing method is proposed to perform online outlier detection without supervision. Finally, we compare the proposed method with the state of the arts using extensive experiments. The experimental results show that our method not only reduces the computational cost by three orders of magnitude but also improves the detection accuracy by 3%–5%.

A STATIC-LEACH WSNs for Hazardous Materials Monitoring

2012 ◽  
Vol 463-464 ◽  
pp. 261-265
Author(s):  
Fei Hui ◽  
Xiao Le Wang ◽  
Xin Shi
Keyword(s):  
Wireless Sensor Networks ◽  
Energy Consumption ◽  
Sensor Networks ◽  
Routing Protocol ◽  
Low Cost ◽  
Hazardous Materials ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Hazardous Materials Transportation ◽  
Adaptive Clustering

In this paper, hazardous materials transportation monitoring system is designed, implemented, and tested using Wireless Sensor Networks (WSNs). According to energy consumption and response time during clustering of Wireless Sensor Networks LEACH (Low Energy Adaptive Clustering Hierarchy) routing protocol, we proposed STATIC-LEACH routing protocol based on static clustering, it can effectively reduce energy consumption of the wireless sensor nodes and reduce network latency of cluster. With WSN and GSM/GPRS, low cost and easy deployment remote monitoring is possible without interfering with the operation of the transportation.

scholarly journals A Combined Localization Algorithm for Wireless Sensor Networks

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Xiaogang Qi ◽  
Xiaoke Liu ◽  
Lifang Liu
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
State Of The Art ◽  
Sensor Nodes ◽  
Vehicle Tracking ◽  
Wireless Sensor ◽  
Localization Algorithm ◽  
Environment And Health ◽  
Anchor Nodes ◽  
Positioning Algorithm

Wireless sensor networks (WSNs) are widely used in various fields to monitor and track various targets by gathering information, such as vehicle tracking and environment and health monitoring. The information gathered by the sensor nodes becomes meaningful only if it is known where it was collected from. Considering that multilateral algorithm and MDS algorithm can locate the position of each node, we proposed a localization algorithm combining the merits of these two approaches, which is called MA-MDS, to reduce the accumulation of errors in the process of multilateral positioning algorithm and improve the nodes’ positioning accuracy in WSNs. It works in more robust fashion for noise sparse networks, even with less number of anchor nodes. In the MDS positioning phase of this algorithm, the Prussian Analysis algorithm is used to obtain more accurate coordinate transformation. Through extensive simulations and the repeatable experiments under diverse representative networks, it can be confirmed that the proposed algorithm is more accurate and more efficient than the state-of-the-art algorithms.

Energy Efficient Mobile Wireless Sensor Networks

Aerospace ◽  
2006 ◽  
Author(s):  
Shashank Priya ◽  
Dan Popa ◽  
Frank Lewis
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Low Cost ◽  
Electric Energy ◽  
Cmos Technology ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Total Power ◽  
Gas Temperature ◽  
Traditional Use

Wireless sensor networks (WSN) have tremendous potential in many environmental and structural health monitoring applications including, gas, temperature, pressure and humidity monitoring, motion detection, and hazardous materials detection. Recent advances in CMOS-technology, IC manufacturing, and networking utilizing Bluetooth communications have brought down the total power requirements of wireless sensor nodes to as low as a few hundred microwatts. Such nodes can be used in future dense ad-hoc networks by transmitting data 1 to 10 meters away. For communication outside 10 meter ranges, data must be transmitted in a multi-hop fashion. There are significant implications to replacing large transmission distance WSN with multiple low-power, low-cost WSN. In addition, some of the relay nodes could be mounted on mobile robotic vehicles instead of being stationary, thus increasing the fault tolerance, coverage and bandwidth capacity of the network. The foremost challenge in the implementation of a dense sensor network is managing power consumption for a large number of nodes. The traditional use of batteries to power sensor nodes is simply not scalable to dense networks, and is currently the most significant barrier for many applications. Self-powering of sensor nodes can be achieved by developing a smart architecture which utilizes all the environmental resources available for generating electrical power. These resources can be structural vibrations, wind, magnetic fields, light, sound, temperature gradients and water currents. The generated electric energy is stored in the matching media selected by the microprocessor depending upon the power magnitude and output impedance. The stored electrical energy is supplied on demand to the sensors and communications devices. This paper shows the progress in our laboratory on powering stationary and mobile untethered sensors using a fusion of energy harvesting approaches. It illustrates the prototype hardware and software required for their implementation including MEMS pressure and strain sensors mounted on mobile robots or stationary, power harvesting modules, interface circuits, algorithms for interrogating the sensor, wireless data transfer and recording.

Sign in / Sign up

Export Citation Format

Share Document