Outlier Detection for Sensor Systems (ODSS): A MATLAB Macro for Evaluating Microphone Sensor Data Quality

A Participation Degree-Based Fault Detection Method for Wireless Sensor Networks

In wireless sensor networks (WSNs), there are many challenges for outlier detection, such as fault detection, fraud detection, intrusion detection, and so on. In this paper, the participation degree of instances in the hierarchical clustering process infers the relationship between instances. However, most of the existing algorithms ignore such information. Thus, we propose a novel fault detection technique based on the participation degree, called fault detection based on participation degree (FDP). Our algorithm has the following advantages. First, it does not need data training in labeled datasets; in fact, it uses the participation degree to measure the differences between fault points and normal points without setting distance or density parameters. Second, FDP can detect global outliers without local cluster influence. Experimental results demonstrate the performance of our approach by applying it to synthetic and real-world datasets and contrasting it with four well-known techniques: isolation forest (IF), local outlier factor (LOF), one-class support vector machine (OCS), and robust covariance (RC).

Outlier-Detection Methodology for Structural Identification Using Sparse Static Measurements

The aim of structural identification is to provide accurate knowledge of the behaviour of existing structures. In most situations, finite-element models are updated using behaviour measurements and field observations. Error-domain model falsification (EDMF) is a multi-model approach that compares finite-element model predictions with sensor measurements while taking into account epistemic and stochastic uncertainties—including the systematic bias that is inherent in the assumptions behind structural models. Compared with alternative model-updating strategies such as residual minimization and traditional Bayesian methodologies, EDMF is easy-to-use for practising engineers and does not require precise knowledge of values for uncertainty correlations. However, wrong parameter identification and flawed extrapolation may result when undetected outliers occur in the dataset. Moreover, when datasets consist of a limited number of static measurements rather than continuous monitoring data, the existing signal-processing and statistics-based algorithms provide little support for outlier detection. This paper introduces a new model-population methodology for outlier detection that is based on the expected performance of the as-designed sensor network. Thus, suspicious measurements are identified even when few measurements, collected with a range of sensors, are available. The structural identification of a full-scale bridge in Exeter (UK) is used to demonstrate the applicability of the proposed methodology and to compare its performance with existing algorithms. The results show that outliers, capable of compromising EDMF accuracy, are detected. Moreover, a metric that separates the impact of powerful sensors from the effects of measurement outliers have been included in the framework. Finally, the impact of outlier occurrence on parameter identification and model extrapolation (for example, reserve capacity assessment) is evaluated.