Introducing Machine Learning to Wireless Sensor Networks

2020 ◽  
pp. 1-22
Author(s):  
Vidit Gulyani ◽  
Tushar Dhiman ◽  
Bharat Bhushan
Keyword(s):  
Machine Learning ◽  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
20Th Century ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Clustering Techniques ◽  
Reduce Power Consumption ◽  
Overall Performance ◽  
Hostile Environments

From its advent in mid-20th century, machine learning constantly improves the user experience of existing systems. It can be used in almost every field such as weather, sports, business, IoT, medical care, etc. Wireless sensor networks are often placed in hostile environments to observe change in surroundings. Since these communicate wirelessly, many problems such as localisation of nodes, security of data being routed create barriers for proper functioning of system. Extending the horizon of machine learning to WSN creates wonders and adds credibility to the system. This chapter aids to present various machine learning aspects applied on wireless sensor networks and the benefits and drawbacks of applying machine learning to WSN. It also describes various data aggregation and clustering techniques that aim to reduce power consumption and ensure confidentiality, authentication, integrity, and availability amongst sensor nodes. This could contribute to design and alter pre-existing ML algorithms to improve overall performance of wireless sensor networks.

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.

A Novel Bogus Data Detection and Filtering Scheme for Wireless Sensor Networks

2012 ◽  
Vol 531-532 ◽  
pp. 707-711
Author(s):  
Zhi Ming Zhang ◽  
Xiao Yong Xiong ◽  
Chang Gen Jiang
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Energy Savings ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Data Detection ◽  
Security Level ◽  
Forwarding Node ◽  
High Security Level ◽  
Hostile Environments

In many scenarios, wireless sensor networks are deployed in hostile environments. Adversaries could easily compromise sensor node, and bogus data could be injected into the network through the compromised sensor nodes, which decreases the accuracy of the sensing data and wastes scarce energy resources of the networks. In this paper, a novel bogus data detection and filtering scheme for wireless sensor networks was proposed based on one-way hash function. In the proposed scheme, if the sensing node was compromised, the based station could verify the endorsement report, and if the compromised forwarding node modified the report packet, the bogus data could be verified by the next forwarding node, and the modified report packet would be discarded. The analysis shows that the proposed scheme not only provides a high security level but also can detect most bogus data and achieve energy savings.

Secured Energy-Efficient Routing in Wireless Sensor Networks Using Machine Learning Algorithm

2020 ◽  
pp. 23-41
Author(s):  
Ahona Ghosh ◽  
Chiung Ching Ho ◽  
Robert Bestak
Keyword(s):  
Machine Learning ◽  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Energy Efficient ◽  
Learning Algorithm ◽  
Low Energy ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Energy Efficient Routing

Wireless sensor networks consist of unattended small sensor nodes having low energy and low range of communication. It has been observed that if there is any system to periodically start and stop the sensors sensing activities, then it saves some energy, and thus, the network lifetime gets extended. According to the current literature, security and energy efficiency are the two main concerns to improve the quality of service during transmission of data in wireless sensor networks. Machine learning has proved its efficiency in developing efficient processes to handle complex problems in various network aspects. Routing in wireless sensor network is the process of finding the route for transmitting data among different sensor nodes according to the requirement. Machine learning has been used in a broad way for designing energy efficient routing protocols, and this chapter reviews the existing works in the said domain, which can be the guide to someone who wants to explore the area further.

scholarly journals On the Use of Graphs for Node Connectivity in Wireless Sensor Networks for Hostile Environments

2019 ◽  
Vol 2019 ◽  
pp. 1-22
Author(s):  
Emmanuel García-González ◽  
Juan C. Chimal-Eguía ◽  
Mario E. Rivero-Angeles ◽  
Vicent Pla
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Data Gathering ◽  
Packet Delay ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Buffer Size ◽  
Distributed Data ◽  
Node Connectivity ◽  
Hostile Environments

Wireless sensor networks (WSNs) have been extensively studied in the literature. However, in hostile environments where node connectivity is severely compromised, the system performance can be greatly affected. In this work, we consider such a hostile environment where sensor nodes cannot directly communicate to some neighboring nodes. Building on this, we propose a distributed data gathering scheme where data packets are stored in different nodes throughout the network instead to considering a single sink node. As such, if nodes are destroyed or damaged, some information can still be retrieved. To evaluate the performance of the system, we consider the properties of different graphs that describe the connections among nodes. It is shown that the degree distribution of the graph has an important impact on the performance of the system. A teletraffic analysis is developed to study the average buffer size and average packet delay. To this end, we propose a reference node approach, which entails an approximation for the mathematical modeling of these networks that effectively simplifies the analysis and approximates the overall performance of the system.

scholarly journals Machine Learning Based Localization in Large-Scale Wireless Sensor Networks

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4179 ◽  
Author(s):  
Ghulam Bhatti
Keyword(s):  
Machine Learning ◽  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Regression Model ◽  
Sensor Nodes ◽  
Sensor Data ◽  
Wireless Sensor ◽  
Support Vector ◽  
Regression Problem ◽  
The Impact

The rapid proliferation of wireless sensor networks over the past few years has posed some serious technical challenges to researchers. The primary function of a multi-hop wireless sensor network (WSN) is to collect and forward sensor data towards the destination node. However, for many applications, the knowledge of the location of sensor nodes is crucial for meaningful interpretation of the sensor data. Localization refers to the process of estimating the location of sensor nodes in a WSN. Self-localization is required in large wireless sensor networks where these nodes cannot be manually positioned. Traditional methods iteratively localize these nodes by using triangulation. However, the inherent instability in wireless signals introduces an error, however minute it might be, in the estimated position of the target node. This results in the embedded error propagating and magnifying rapidly. Machine learning based localizing algorithms for large wireless sensor networks do not function in an iterative manner. In this paper, we investigate the suitability of some of these algorithms while exploring different trade-offs. Specifically, we first formulate a novel way of defining multiple feature vectors for mapping the localizing problem onto different machine learning models. As opposed to treating the localization as a classification problem, as done in the most of the reported work, we treat it as a regression problem. We have studied the impact of varying network parameters, such as network size, anchor population, transmitted signal power, and wireless channel quality, on the localizing accuracy of these models. We have also studied the impact of deploying the anchor nodes in a grid rather than placing these nodes randomly in the deployment area. Our results have revealed interesting insights while using the multivariate regression model and support vector machine (SVM) regression model with radial basis function (RBF) kernel.

Localization Security in Wireless Sensor Networks

2008 ◽  
pp. 617-627 ◽  
Author(s):  
Yawen Wei ◽  
Zhen Yu ◽  
Yong Guan
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Location Information ◽  
Malicious Attacks ◽  
Distance Measurements ◽  
Secure Localization ◽  
Comprehensive Survey ◽  
Hostile Environments

Localization of sensor nodes is very important for many applications proposed for wireless sensor networks (WSN), such as environment monitoring, geographical routing, and target tracking. Because sensor networks may be deployed in hostile environments, localization approaches can be compromised by many malicious attacks. The adversaries can broadcast corrupted location information; they can jam or modify the transmitting signals between sensors to mislead them to obtain incorrect distance measurements or nonexistent connectivity links. All these malicious attacks will cause sensors not able to or wrongly estimate their locations. In this chapter, we summarize the threat models and provide a comprehensive survey and taxonomy of existing secure localization and verification schemes for wireless sensor networks.

Performance Analysis of TBC-ACO Routing Protocol with Existing Routing Protocols of Wireless Sensor Networks

2017 ◽  
Vol 7 (8) ◽  
pp. 169
Author(s):  
A. Radhika ◽  
D. Haritha
Keyword(s):  
Energy Efficiency ◽  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Swarm Intelligence ◽  
Routing Protocol ◽  
Routing Protocols ◽  
Energy Efficient ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Congestion Aware

Wireless Sensor Networks, have witnessed significant amount of improvement in research across various areas like Routing, Security, Localization, Deployment and above all Energy Efficiency. Congestion is a problem of  importance in resource constrained Wireless Sensor Networks, especially for large networks, where the traffic loads exceed the available capacity of the resources . Sensor nodes are prone to failure and the misbehaviour of these faulty nodes creates further congestion. The resulting effect is a degradation in network performance, additional computation and increased energy consumption, which in turn decreases network lifetime. Hence, the data packet routing algorithm should consider congestion as one of the parameters, in addition to the role of the faulty nodes and not merely energy efficient protocols .Nowadays, the main central point of attraction is the concept of Swarm Intelligence based techniques integration in WSN.  Swarm Intelligence based Computational Swarm Intelligence Techniques have improvised WSN in terms of efficiency, Performance, robustness and scalability. The main objective of this research paper is to propose congestion aware , energy efficient, routing approach that utilizes Ant Colony Optimization, in which faulty nodes are isolated by means of the concept of trust further we compare the performance of various existing routing protocols like AODV, DSDV and DSR routing protocols, ACO Based Routing Protocol  with Trust Based Congestion aware ACO Based Routing in terms of End to End Delay, Packet Delivery Rate, Routing Overhead, Throughput and Energy Efficiency. Simulation based results and data analysis shows that overall TBC-ACO is 150% more efficient in terms of overall performance as compared to other existing routing protocols for Wireless Sensor Networks.

Deterministic Deployment for Wireless Image Sensor Nodes

2014 ◽  
Vol 8 (1) ◽  
pp. 668-674
Author(s):  
Junguo Zhang ◽  
Yutong Lei ◽  
Fantao Lin ◽  
Chen Chen
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Visual Information ◽  
Image Sensor ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Coverage Area ◽  
Effective Coverage ◽  
Area Of Interest ◽  
Key Issues

Wireless sensor networks composed of camera enabled source nodes can provide visual information of an area of interest, potentially enriching monitoring applications. The node deployment is one of the key issues in the application of wireless sensor networks. In this paper, we take the effective coverage and connectivity as the evaluation indices to analyze the effect of the perceivable angle and the ratio of communication radius and sensing radius for the deterministic circular deployment. Experimental results demonstrate that the effective coverage area of the triangle deployment is the largest when using the same number of nodes. When the nodes are deployed in the same monitoring area in the premise of ensuring connectivity, rhombus deployment is optimal when √2 < rc / rs < √3 . The research results of this paper provide an important reference for the deployment of the image sensor networks with the given parameters.

Energy Efficient Group Based Linear Wireless Sensor Networks for Application in Pipeline Monitoring

2020 ◽  
Vol 10 ◽  
Author(s):  
Chinedu Duru ◽  
Neco Ventura ◽  
Mqhele Dlodlo
Keyword(s):  
Wireless Sensor Networks ◽  
Energy Consumption ◽  
Sensor Networks ◽  
Remote Monitoring ◽  
Linear Array ◽  
Minimum Energy ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Sink Node ◽  
Pipeline Monitoring

Background: Wireless Sensor Networks (WSNs) have been researched to be one of the ground-breaking technologies for the remote monitoring of pipeline infrastructure of the Oil and Gas industry. Research have also shown that the preferred deployment approach of the sensor network on pipeline structures follows a linear array of nodes, placed a distance apart from each other across the infrastructure length. The linear array topology of the sensor nodes gives rise to the name Linear Wireless Sensor Networks (LWSNs) which over the years have seen themselves being applied to pipelines for effective remote monitoring and surveillance. This paper aims to investigate the energy consumption issue associated with LWSNs deployed in cluster-based fashion along a pipeline infrastructure. Methods: Through quantitative analysis, the study attempts to approach the investigation conceptually focusing on mathematical analysis of proposed models to bring about conjectures on energy consumption performance. Results: From the derived analysis, results have shown that energy consumption is diminished to a minimum if there is a sink for every placed sensor node in the LWSN. To be precise, the analysis conceptually demonstrate that groups containing small number of nodes with a corresponding sink node is the approach to follow when pursuing a cluster-based LWSN for pipeline monitoring applications. Conclusion: From the results, it is discovered that energy consumption of a deployed LWSN can be decreased by creating groups out of the total deployed nodes with a sink servicing each group. In essence, the smaller number of nodes each group contains with a corresponding sink, the less energy consumed in total for the entire LWSN. This therefore means that a sink for every individual node will attribute to minimum energy consumption for every non-sink node. From the study, it can be concurred that energy consumption of a LWSN is inversely proportional to the number of sinks deployed and hence the number of groups created.

Improved DV-Hop Localization Scheme for Randomly Deployed WSNs

2020 ◽  
Vol 10 (1) ◽  
pp. 94-109 ◽  
Author(s):  
Rekha Goyat ◽  
Mritunjay Kumar Rai ◽  
Gulshan Kumar ◽  
Hye-Jin Kim ◽  
Se-Jung Lim
Keyword(s):  
Wireless Sensor Networks ◽  
Energy Consumption ◽  
Sensor Networks ◽  
Research Area ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Localization Error ◽  
Anchor Nodes ◽  
Least Energy ◽  
Range Free

Background: Wireless Sensor Networks (WSNs) is considered one of the key research area in the recent. Various applications of WSNs need geographic location of the sensor nodes. Objective: Localization in WSNs plays an important role because without knowledge of sensor nodes location the information is useless. Finding the accurate location is very crucial in Wireless Sensor Networks. The efficiency of any localization approach is decided on the basis of accuracy and localization error. In range-free localization approaches, the location of unknown nodes are computed by collecting the information such as minimum hop count, hop size information from neighbors nodes. Methods: Although various studied have been done for computing the location of nodes but still, it is an enduring research area. To mitigate the problems of existing algorithms, a range-free Improved Weighted Novel DV-Hop localization algorithm is proposed. Main motive of the proposed study is to reduced localization error with least energy consumption. Firstly, the location information of anchor nodes is broadcasted upto M hop to decrease the energy consumption. Further, a weight factor and correction factor are introduced which refine the hop size of anchor nodes. Results: The refined hop size is further utilized for localization to reduces localization error significantly. The simulation results of the proposed algorithm are compared with other existing algorithms for evaluating the effectiveness and the performance. The simulated results are evaluated in terms localization error and computational cost by considering different parameters such as node density, percentage of anchor nodes, transmission range, effect of sensing field and effect of M on localization error. Further statistical analysis is performed on simulated results to prove the validation of proposed algorithm. A paired T-test is applied on localization error and localization time. The results of T-test depicts that the proposed algorithm significantly improves the localization accuracy with least energy consumption as compared to other existing algorithms like DV-Hop, IWCDV-Hop, and IDV-Hop. Conclusion: From the simulated results, it is concluded that the proposed algorithm offers 36% accurate localization than traditional DV-Hop and 21 % than IDV-Hop and 13% than IWCDV-Hop.

Sign in / Sign up

Export Citation Format

Share Document