Temporal and spatial outlier detection in wireless sensor networks

Outlier detection techniques play an important role in enhancing the reliability of data communication in wireless sensor networks (WSNs). Considering the importance of outlier detection in WSNs, many outlier detection techniques have been proposed. Unfortunately, most of these techniques still have some potential limitations, that is, (a) high rate of false positives, (b) high time complexity, and (c) failure to detect outliers online. Moreover, these approaches mainly focus on either temporal outliers or spatial outliers. Therefore, this paper aims to introduce novel algorithms that successfully detect both temporal outliers and spatial outliers. Our contributions are twofold: (i) modifying the Hampel Identifier (HI) algorithm to achieve high accuracy identification rate in temporal outlier detection, (ii) combining the Gaussian process (GP) model and graph‐based outlier detection technique to improve the performance of the algorithm in spatial outlier detection. The results demonstrate that our techniques outperform the state‐of‐the‐art methods in terms of accuracy and work well with various data types.     

Gravitational outlier detection for wireless sensor networks

Accuracy of sensed data and reliable delivery are the key concerns in addition to several other network‐related issues in wireless sensor networks (WSNs). Early detection of outliers reduces subsequent unwanted transmissions, thus preserving network resources. Recent techniques on outlier detection in WSNs are computationally expensive and based on message exchange. Message exchange‐based techniques incur communication overhead and are less preferred in WSNs. On the other hand, machine learning‐based outlier detection techniques are computationally expensive for resource constraint sensor nodes. The novelty of this paper is that it proposes a simple, non message exchange based, in‐network, real‐time outlier detection algorithm based on Newton's law of gravity. The mechanism is evaluated for its accuracy in detecting outliers, computational cost, and its influence on the network traffic and delay. The outlier detection mechanism resulted in almost 100% detection accuracy. Because the mechanism involves no message exchanges, there is a significant reduction in network traffic, energy consumption and end‐to‐end delay. An extension of the proposed algorithm for transient data sets is proposed, and analytic evaluation justifies that the mechanism is reactive to time series data. Copyright © 2016 John Wiley & Sons, Ltd.     

Trajectory-based multi-dimensional outlier detection in wireless sensor networks using Hidden Markov Models

Wireless sensor networks (WSNs) have been increasingly available for monitoring the traffic, weather, pollution, etc. Outlier detection in WSNs is an essential step for many important applications, such as abnormal event detection, fraud analysis, etc. While existing efforts focus on identifying individual outliers from sensory data, the unsupervised high semantic outlier detection in WSNs is more challenging and has received far less attentions. In addition, the correlation between multi-dimensional sensory data has not yet been considered when detecting outliers in WSNs. In this paper, based on multi-dimensional Hidden Markov Models, we propose a trajectory-based outlier detection algorithm by model training and model-based likelihood estimation. Our data preprocessing, clustering, model training and model updating schemes are developed to reduce the computational complexity and enhance the detecting performance. We also explore the possibility and feasibility of adapting the proposed algorithm to real-time outlier detections. Experimental results show that our methods achieve good performance on detecting various kinds of abnormal trajectories composed of multi-dimensional data.     

Composite Fault Diagnosis in Wireless Sensor Networks Using Neural Networks

Wireless sensor networks (WSNs) are spatially distributed devices to support various applications. The undesirable behavior of the sensor node affects the computational efficiency and quality of service. Fault detection, identification, and isolation in WSNs will increase assurance of quality, reliability, and safety. In this paper, a novel neural network based fault diagnosis algorithm is proposed for WSNs to handle the composite fault environment. Composite fault includes hard, soft, intermittent, and transient faults. The proposed fault diagnosis protocol is based on gradient descent and evolutionary approach. It detects, diagnose, and isolate the faulty nodes in the network. The proposed protocol works in four phases such as clustering phase, communication phase, fault detection and classification phase, and isolation phase. Simulation results show that the proposed protocol performs better than the existing protocols in terms of detection accuracy, false alarm rate, false positive rate, and detection latency.

     

A scalable correlation‐based approach for outlier detection in wireless body sensor networks

Outlier detection is one of the prominent research domain in the field of data mining and big data analytics. Nowadays, most of the data in healthcare centers are remotely monitored and are generated from different wireless sensors. The core objective of outlier detection in this domain is the recognition of the true physiologically anomalous data and the anomalies because of faulty sensors. In real healthcare monitoring scenario, various sensors are related to each other. So, while detecting outliers in wireless body sensor networks (WBSNs), correlation among different sensor nodes is of major concern. Most of the existing outlier detection techniques consider the sensors to be linearly correlated, which may not always be the case in real life applications. The traditional techniques for outlier detection are also not scalable to big data. To address the above issues, in this paper, we propose an approach for outlier detection that is scalable to big data and also handles the nonlinearly correlated attributes efficiently. The proposed approach is implemented on Hadoop map reduce framework for the rapid processing of big data. The evaluation results are validated using the simulated dataset of WBSNs taken from the Physionet library. The results are compared with various existing outlier detection approaches and demonstrated that the proposed approach is more effective in spotting the physiological outliers and sensor anomalies accurately.     

An efficient approach for outlier detection in big sensor data of health care

In recent years, wireless sensor networks are pervasive and are generating tons of data every second. Performing outlier detection to detect faulty sensors from such a large amount of data becomes a challenging task. Most of the existing techniques for outlier detection in wireless sensor networks concentrate only on contents of the data source without considering correlation among different data attributes. Moreover, these methods are not scalable to big data. To address these 2 limitations, this paper proposes an outlier detection approach based on correlation and dynamic SMO (sequential minimal optimization) regression that is scalable to big data. Initially, correlation is used to find out strongly correlated attributes and then the point anomalous nodes are detected using dynamic SMO regression. For fast processing of big data, Hadoop MapReduce framework is used. The experimental analysis demonstrates that the proposed approach efficiently detects the point and contextual anomalies and reduces the number of false alarms. For experiments, real data of sensors used in body sensor networks are taken from Physionet database.     

Complex Event Detection in Extremely Resource-Constrained Wireless Sensor Networks

Complex Events are sequences of sensor measurements indicating interesting or unusual activity in the monitored process. Such events are ubiquitous in a wide range of Wireless Sensor Network (WSN) applications, yet there does not exist a common mechanism that addresses both the considerable constraints of WSNs and the specific properties of Complex Events. We argue that Complex Events cannot be described using standard threshold-based or composite logic approaches and attempting to represent them as such can lead to unpredictable execution cost while detection accuracy suffers from erroneous recording of observations which are common in WSNs. To address this, we develop a family of Complex Event Detection (CED) algorithms based on online symbolic conversion of sensor readings. With fixed execution cost and modest resource requirements, the CED algorithms cater for exact, approximate, non-parametric, multiple and probabilistic detection that is neither application nor data dependent. Overall, full implementation and simulations provide experimental evidence of the advantages of the proposed approach. We find that the proposed algorithms minimise configuration, promote unattended operation and complement the goal of prolonged lifetime—factors that satisfy the long-term research vision predicting Internet-scale WSNs comprising billions of devices.     

Connectivity Analysis for Wireless Sensor Networks with Antenna Array Integrated Central Node

In a wireless sensor network (WSN), after gathering information, tiny sensor nodes need to transmit data to a sink. It is important to guarantee that each node can communicate with a sink. Due to the multi-hop communication of WSNs, an essential condition for reliable transmission is completely connectivity of a network. Adaptive or smart antenna (SA) techniques in WSNs have been a topic of active research in recent years. These techniques have been shown to be effective with respect to decreasing energy consuming via specified regions which are formed by the SA beams. In this paper, we propose a probabilistic technique to determine the network connectivity probability of the SA integrated WSN. We employ the geometric shape model to evaluate the network connectivity probability of the WSN using the SA beam specifications. The sensor node density to satisfy the desired network connectivity is determined in terms of the beam-width of the antenna array and node transmission range. The analytical results agree with the simulation results by less than 4.7 % error in the average.     

Wireless sensor networks for intrusion detection: packet traffic modeling

Performance evaluation of wireless sensor network (WSN) protocols requires realistic data traffic models since most of the WSNs are application specific. In this letter, a sensor network packet traffic model is derived and analyzed for intrusion detection applications. Presented analytical work is also validated using simulations.     

WSNS中基于Fusion-Bayes的离群点检测

随着无线传感器网络技术的发展,数据采集量越来越大,维数也不断提高。然而现有的离群点检测算法多是面向单维或低维度数据,对此文中提出了基于Fusion-Bayes的离群点检测算法。该检测方法首先利用数据转换技术将不同数据属性转换成统一格式,使得各属性可以进行融合运算;然后再利用贝叶斯方法对融合后的属性进行离群点检测。通过实验得出,多维数据属性融合后的检测结果相比于单维属性或低维属性的检测更加准确、效果更好。     

MANNA: a management architecture for wireless sensor networks

Wireless sensor networks (WSNs) are becoming an increasingly important technology that will be used in a variety of applications such as environmental monitoring, infrastructure management, public safety, medical, home and office security, transportation, and military. WSNs will also play a key role in pervasive computing where computing devices and people are connected to the Internet. Until now, WSNs and their applications have been developed without considering a management solution. This is a critical problem since networks comprising tens of thousands of nodes are expected to be used in some of the applications above. This article proposes the MANNA management architecture for WSNs. In particular, it presents the functional, information, and physical management architectures that take into account specific characteristics of this type of network. Some of them are restrict physical resources such as energy and computing power, frequent reconfiguration and adaptation, and faults caused by nodes unavailable. The MANNA architecture considers three management dimensions: functional areas, management levels, and WSN functionalities. These dimensions are specified to the management of a WSN and are the basis for a list of management functions. The article also proposes WSN models to guide the management activities and the use of correlation in the WSN management. This is a first step into a largely unexplored research area.     

Data Aggregation in Wireless Sensor Networks: Previous Research,Current Status and Future Directions

Wireless sensor networks (WSNs) consist of large number of small sized sensor nodes, whose main task is to sense the desired phenomena in a particular region of interest. These networks have large number of applications such as habitat monitoring, disaster management, security and military etc. Sensor nodes are very small in size and have limited processing capability as these nodes have very low battery power. WSNs are also prone to failure, due to low battery power constraint. Data aggregation is an energy efficient technique in WSNs. Due to high node density in sensor networks same data is sensed by many nodes, which results in redundancy. This redundancy can be eliminated by using data aggregation approach while routing packets from source nodes to base station. Researchers still face trouble to select an efficient and appropriate data aggregation technique from the existing literature of WSNs. This research work depicts a broad methodical literature analysis of data aggregation in the area of WSNs in specific. In this survey, standard methodical literature analysis technique is used based on a complete collection of 123 research papers out of large collection of 932 research papers published in 20 foremost workshops, symposiums, conferences and 17 prominent journals. The current status of data aggregation in WSNs is distributed into various categories. Methodical analysis of data aggregation in WSNs is presented which includes techniques, tools, methodology and challenges in data aggregation. The literature covered fifteen types of data aggregation techniques in WSNs. Detailed analysis of this research work will help researchers to find the important characteristics of data aggregation techniques and will also help to select the most suitable technique for data aggregation. Research issues and future research directions have also been suggested in this research literature.     

Fault management in wireless sensor networks

Wireless sensor networks (WSNs) have gradually emerged as one of the key growth areas for pervasive computing in the twenty-first century. Recent advances in WSN technologies have made possible the development of new wireless monitoring and environmental control applications. However, the nature of these applications and harsh environments also created significant challenges for sensor networks to maintain a high quality of service in potentially harsh environments. Therefore, efficient fault management and robust management architectures have become essential for WSNs. In this article, we address these challenges by surveying existing fault management approaches for WSNs. We divide the fault management process into three phases: fault detection, diagnosis, and recovery and classify existing approaches according to these phases. Finally, we outline future challenges for fault management in WSNs.     

An improved fault detection crow search algorithm for wireless sensor network

In wireless sensor networks (WSNs), the collected data during monitoring environment can have some faulty data, and these faults can lead to the failure of a system. These faults may occur due to many factors such as environmental interference, low battery, and sensors aging etc. We need an efficient fault detection technique for preventing the failures of a WSN or an IoT system. To address this major issue, we have proposed a new nature-inspired approach for fault detection for WSNs called improved fault detection crow search algorithm (IFDCSA). IFDCSA is an improved version of the original crow search algorithm (CSA). The proposed algorithm first injects the faults into the datasets, and then the faults are classified using improved CSA and machine learning classifiers. The proposed work has been evaluated on the three real-world datasets, ie, Intel lab data, multihop labeled data, and SensorScope data, and predicts the faults with an average accuracy of 99.94%. The results of the proposed algorithm have been compared with the three different machine learning classifiers (random forest, k-nearest neighbors, and decision trees) and Zidi model. The proposed algorithm outperforms the other classifiers/models, thus generating higher accuracy and lower features without degrading the performance of the system. Index Terms—big data, crow search algorithm, IoT, machine learning, nature-inspired algorithm, wireless sensor network.     

Privacy preservation in wireless sensor networks: A state-of-the-art survey

Much of the existing work on wireless sensor networks (WSNs) has focused on addressing the power and computational resource constraints of WSNs by the design of specific routing, MAC, and cross-layer protocols. Recently, there have been heightened privacy concerns over the data collected by and transmitted through WSNs. The wireless transmission required by a WSN, and the self-organizing nature of its architecture, makes privacy protection for WSNs an especially challenging problem. This paper provides a state-of-the-art survey of privacy-preserving techniques for WSNs. In particular, we review two main categories of privacy-preserving techniques for protecting two types of private information, data-oriented and context-oriented privacy, respectively. We also discuss a number of important open challenges for future research. Our hope is that this paper sheds some light on a fruitful direction of future research for privacy preservation in WSNs.     

Energy‐efficient data transmission technique for wireless sensor networks based on DSC and virtual MIMO

In a wireless sensor network (WSN), the data transmission technique based on the cooperative multiple‐input multiple‐output (CMIMO) scheme reduces the energy consumption of sensor nodes quite effectively by utilizing the space‐time block coding scheme. However, in networks with high node density, the scheme is ineffective due to the high degree of correlated data. Therefore, to enhance the energy efficiency in high node density WSNs, we implemented the distributed source coding (DSC) with the virtual multiple‐input multiple‐output (MIMO) data transmission technique in the WSNs. The DSC‐MIMO first compresses redundant source data using the DSC and then sends it to a virtual MIMO link. The results reveal that, in the DSC‐MIMO scheme, energy consumption is lower than that in the CMIMO technique; it is also lower in the DSC single‐input single‐output (SISO) scheme, compared to that in the SISO technique at various code rates, compression rates, and training overhead factors. The results also indicate that the energy consumption per bit is directly proportional to the velocity and training overhead factor in all the energy saving schemes.     

一种新的无线传感器网络中异常节点检测定位算法

无线传感器网络中异常节点检测是确保网络数据准确性和可靠性的关键步骤。基于图信号处理理论,该文提出了一种新的无线传感器网络异常节点检测定位算法。新算法首先对网络建立图信号模型,然后基于节点域-图频域联合分析的方法,实现异常节点的检测和定位。具体而言,第1步是利用高通图滤波器提取网络信号的高频分量。第2步首先将网络划分为多个子图,然后筛选出子图输出信号的特定频率分量。第3步对筛选出的子图信号进行阈值判断从而定位疑似异常的子图中心节点。最后通过比较各子图的节点集合和疑似异常节点集合,检测并定位出网络中的异常节点。实验仿真表明,与已有的无线传感器网络中异常检测方法相比,新算法不仅有着较高的异常检测概率,而且异常节点的定位率也较高。     

REBTAM: reliable energy balance traffic aware data reporting algorithm for object tracking in multi-sink wireless sensor networks

Recently, Multi-sink Wireless Sensor Networks (WSNs) have received more and more attention due to their significant advantages over the single sink WSNs such as improving network throughput, balancing energy consumption, and prolonging network lifetime. Object tracking is regarded as one of the key applications of WSNs due to its wide real-life applications such as wildlife animal monitoring and military area intrusion detection. However, many object tracking researches usually focus on how to track the location of objects accurately, while few researches focus on data reporting. In this work, we propose an efficient data reporting method for object tracking in multi-sink WSNs. Due to the limited energy resource of sensor nodes, it seems especially important to design an energy efficient data reporting algorithm for object tracking in WSNs. Moreover, the reliable data transmission is an essential aspect that should be considered when designing a WSN for object tracking application, where the loss of data packets will affect the accuracy of the tracking and location estimation of a mobile object. In addition, congestion in WSNs has negative impact on the performance, namely, decreased throughput, increased per-packet energy consumption and delay, thus congestion control is an important issue in WSNs. Consequentially, this paper aims to achieve both minimum energy consumption in reporting operation and balanced energy consumption among sensor nodes for WSN lifetime extension. Furthermore, data reliability is considered in our model where the sensed data can reach the sink node in a more reliable way. Finally, this paper presents a solution that sufficiently exerts the underloaded nodes to alleviate congestion and improve the overall throughput in WSNs. This work first formulates the problem as 0/1 Integer Linear Programming problem, and proposes a Reliable Energy Balance Traffic Aware greedy Algorithm in multi-sink WSNs (REBTAM) to solve the optimization problem. Through simulation, the performance of the proposed approach is evaluated and analyzed compared with the previous work which is related to our topic such as DTAR, NBPR, and MSDDGR protocols.     

Low-cost group rekeying for unattended wireless sensor networks

Wireless sensor networks (WSNs) are made up of large groups of nodes that perform distributed monitoring services. Since sensor measurements are often sensitive data acquired in hostile environments, securing WSN becomes mandatory. However, WSNs consists of low-end devices and frequently preclude the presence of a centralized security manager. Therefore, achieving security is even more challenging. State-of-the-art proposals rely on: (1) attended and centralized security systems; or (2) establishing initial keys without taking into account how to efficiently manage rekeying. In this paper we present a scalable group key management proposal for unattended WSNs that is designed to reduce the rekeying cost when the group membership changes.     

Pareto-optimal clustering scheme using data aggregation for wireless sensor networks

The presence of cluster heads (CHs) in a clustered wireless sensor network (WSN) leads to improved data aggregation and enhanced network lifetime. Thus, the selection of appropriate CHs in WSNs is a challenging task, which needs to be addressed. A multicriterion decision-making approach for the selection of CHs is presented using Pareto-optimal theory and technique for order preference by similarity to ideal solution (TOPSIS) methods. CHs are selected using three criteria including energy, cluster density and distance from the sink. The overall network lifetime in this method with 50% data aggregation after simulations is 81% higher than that of distributed hierarchical agglomerative clustering in similar environment and with same set of parameters. Optimum number of clusters is estimated using TOPSIS technique and found to be 9–11 for effective energy usage in WSNs.