Outlier Detection in Wireless Sensor Networks Basedon OPTICS Method for Events and Errors Identification (original) (raw)

Outliers detection and classification in wireless sensor

2013

In the past few years, many wireless sensor networks had been deployed in the real world to collect large amounts of raw sensed data. However, the key challenge is to extract high-level knowledge from such raw data. In the applications of sensor networks, outlier/anomaly detection has been paid more and more attention. Outlier detection can be used to filter noisy data, find faulty nodes, and discover interesting events. In this paper we propose a novel in-network knowledge discovery approach that provides outlier detection and data clustering simultaneously. Our approach is capable to distinguish between an error due to faulty sensor and an error due to an event (probably an environmental event) which characterize the spatial and temporal correlations between events observed by sensor nodes in a confined network neighborhood. Experiments on both synthetic and real datasets show that the proposed algorithm outperforms other techniques in both effectiveness and efficiency.

Outliers detection and classification in wireless sensor networks

Egyptian Informatics Journal, 2013

In the past few years, many wireless sensor networks had been deployed in the real world to collect large amounts of raw sensed data. However, the key challenge is to extract high-level knowledge from such raw data. In the applications of sensor networks, outlier/anomaly detection has been paid more and more attention. Outlier detection can be used to filter noisy data, find faulty nodes, and discover interesting events. In this paper we propose a novel in-network knowledge discovery approach that provides outlier detection and data clustering simultaneously. Our approach is capable to distinguish between an error due to faulty sensor and an error due to an event (probably an environmental event) which characterize the spatial and temporal correlations between events observed by sensor nodes in a confined network neighborhood. Experiments on both synthetic and real datasets show that the proposed algorithm outperforms other techniques in both effectiveness and efficiency.

AN ANALYSIS OF OUTLIER DETECTION TECHNIQUES FOR WIRELESS SENSOR NETWORK APPLICATIONS

Outlier detection is the process of finding data objects whose behaviour are highly varying from expectation. It is considered to be one of the fundamental tasks of data mining. In Wireless sensor networks, outliers can be defined as those measurements that significantly deviate from the normal pattern of sensed data. Due to various reasons that includes fault in sensors, communication error etc., wireless sensors tend to generate outliers. The presence of outliers in a dataset leads to a biased outcome and erroneous conclusions, when the data is further analyzed. Identifying outliers before data analysis helps improvise the quality of data. In this paper, we analyze the performance of two different techniques and confirm the suitability of outlier detection technique for multivariate data.

A Comparison of Outlier Detection Algorithm for Wireless Sensor Network.

International Journal of Engineering Sciences & Research Technology, 2014

Wireless sensor networks had been deployed in the real world to collect large amounts of raw sensed data. However, the key challenge is to extract high level knowledge from such raw data. Sensor networks applications, outlier/anomaly detection has been paid more and more attention. The propose of a classification approach that provides outlier detection and data classification simultaneously. Experiments on Intel Berkley lab sensor dataset show that the proposed approach outperforms other techniques in both effectiveness & efficiency.

A Systematic Literature Review on Outlier Detection in Wireless Sensor Networks

Symmetry, 2020

A wireless sensor network (WSN) is defined as a set of spatially distributed and interconnected sensor nodes. WSNs allow one to monitor and recognize environmental phenomena such as soil moisture, air pollution, and health data. Because of the very limited resources available in sensors, the collected data from WSNs are often characterized as unreliable or uncertain. However, applications using WSNs demand precise readings, and uncertainty in data reading can cause serious damage (e.g., health monitoring data). Therefore, an efficient local/distributed data processing algorithm is needed to ensure: (1) the extraction of precise and reliable values from noisy readings; (2) the detection of anomalies from data reported by sensors; and (3) the identification of outlier sensors in a WSN. Several works have been conducted to achieve these objectives using several techniques such as machine learning algorithms, mathematical modeling, and clustering. The purpose of this paper is to conduct...

An Outlier Detection and Rectification Method in Cluster Based Wireless Sensor Network

The evolution of Wireless Sensor networks (WSNs) is a demandable, efficient and emerging area of Computer Science Engineering which has been currently employed in various field of engineering particularly in communication system to make it effective and reliable. For successful application of WSN it is important to maintain the basic security level, both from external and internal attacks else entire network may collapse. In the field of WSNs, if the sensed patterns that significantly deviate from the normal pattern are considered as outlier. The possible source of outlier includes noise, errors, events and malicious attack on the network. WSNs are more likely to generate outlier due to their special characteristics like constrained available with the resources causing frequent physical failure and harsh deployment area. In this paper we have investigated and experimented different outlier attack in WSN and how these attacks are efficiently detected and rectified. The usual outlier detection techniques are not directly applicable to wireless sensor network due to the nature of sensed data, specific requirements and limitations of the WSNs. Our proposed method will train and test data set for detection as well as rectification of outlier due the malicious attack and identify the affected sensor nodes in a largely deployed cluster based wireless sensor network under a common outlier detection framework which is designed by some well specified supervised learning and classification based data mining technique.

An Efficient Approach for Outlier Detection in Wireless Sensor Network

Wireless Sensor Networks are those networks which include many sensors, sensors have many sensor nodes that are spread all over the world. A wireless sensor network (WSN) normally has many sensor nodes which are very modest, having minimum cost dispersed over the world having high-powered sink nodes which collect the readings of the sensor nodes. These nodes are comprised with high sensing power, processing and wireless communication abilities. A sensor network involves large number of sensors, collecting and communicating the sensor measurements of observing physical world scenarios. The main problem in WSN is outlier. Basically outlier is an element of a data set that falls in an abnormal range. For the capabilities of WSNs, it is clear that we need an accurate and robust technique which can be used for multivariate data too and can give the optimum results in output threshold, and that technique should help to increase the special characteristics of WSNs such as node mobility, network topology change and making distinction between errors and events. Among all the techniques KERNEL FUNCTIONS is the best technique because it can be used for multivariate data also. Except it FTDA and LSH are also produce optimum results.

Outlier Detection Techniques and Cleaning of Data for Wireless Sensor Networks: A Survey

2012

Pattern recognition is the scientific discipline where the goal is the classification of objects into a number of categories or classes. Pattern recognition is an integral part in most sensing networks built for outlier detection. The significant deviations from the pattern of sensed data are considered as outliers in wireless sensor networks. These outliers include noise, errors, and malicious attack on the network. This affects the performance of the wireless sensor networks. Mostly the nature of sensor data is multivariate but it may be univariate also. Because of this, the traditional techniques are not directly applicable to wireless sensor networks. This contribution overviews existing outlier detection techniques developed for wireless sensor networks. It also presents a outlier detection technique framework to be used as a guideline to select a technique for outlier detection suitable for application based on the characteristics, such as, data type, outlier type and outlier ...

An Outlier detection approach with data mining in wireless sensor network

Wireless sensor networks had been deployed in the real world to collect large amounts of raw sensed data. However, the key challenge is to extract high level knowledge from such raw data. Sensor networks applications; outlier/anomaly detection has been paid more and more attention. The propose of a classification approach that provides outlier detection and data classification simultaneously. Experiments on Intel Berkley lab sensor dataset show that the proposed approach outperforms other techniques in both effectiveness & efficiency.

In-network outlier detection in wireless sensor networks

Knowledge and Information Systems, 2013

To address the problem of unsupervised outlier detection in wireless sensor networks, we develop an approach that (1) is flexible with respect to the outlier definition, (2) computes the result in-network to reduce both bandwidth and energy usage, (3) only uses single hop communication thus permitting very simple node failure detection and message reliability assurance mechanisms (e.g., carrier-sense), and (4) seamlessly accommodates dynamic updates to data. We examine performance using simulation with real sensor data streams. Our results demonstrate that our approach is accurate and imposes a reasonable communication load and level of power consumption.