One of the goals of verification and validation (V&V) activities for online adaptive control systems is providing assurance that they are able to detect novel system behaviors and provide adequate (safe) control actions. Novel (or abnormal) system behaviors cannot be enumerated or fully and explicitly described in requirements documentation. Therefore, they have to be observed and recognized du...

Abstract Fabric defect detection is anomaly detection, which widely studied in the textile industry. Like most tasks, there are some problems hindering results, such as class imbalance, defective sample scarcity, and feature selection. This paper proposes a method applying depthwise separable convolution autoencoder on dimensionality reduction one-class classifier support vector data descriptio...

One-class classification is an important problem with applications in several diÆerent areas such as outlier detection and machine monitoring. In this paper we propose a novel method for one-class classification, referred to as kernel k NNDDSRM. This is a modification of an earlier algorithm, the kNNDDSRM, which aims to make the method able to build more flexible descriptions with the use of th...

With the aim to improve the performance of iris segmentation method to process images with heterogeneous characteristics, the authors introduce a new method inspired by the support vector domain description (SVDD). A local geometric moment function is used to extract shape features of the iris borders. Then, these features are fed into the trained SVDD classifier for borders recognition followe...

We propose a novel approach to fault detection in rotating mechanical machines: fusion of multichannel measurements of machine vibration using Independent Component Analysis (ICA), followed by a description of the admissible domain (part of the feature space indicative of normal machine operation) with a Support Vector Domain Description (SVDD) method. The SVDD-method enables the determination ...

This paper shows the use of a data domain description method, inspired by the support vector machine by Vapnik, called the support vector domain description (SVDD). This data description can be used for novelty or outlier detection. A spherically shaped decision boundary around a set of objects is constructed by a set of support vectors describing the sphere boundary. It has the possibility of ...

This paper presents a fingerprinting method based on equivalence classes. An equivalence class is composed of a reference image and all its variations (or replicas). For each reference image, a decision function is built. The latter determines if a given image belongs to its corresponding equivalence class. This function is built in three steps: synthesis, projection, and analysis. In the first...

The problem of outlier detection consists in finding data that is not representative of the population from which it was ostensibly derived. Recently, to solve this problem, Liu et al. [1] proposed a two steps hypersphere-based approach, taking into account a confidence score pre-calculated for each input data. Defining these scores in a first step, independently from the second one, makes this...

In decomposition-based design optimization strategies such as analytical target cascading (ATC), it is sometimes necessary to use reduced representations of highly discretized functional data exchanged among subproblems to enable efficient design optimization. However, the variables used by such reduced representation methods are often abstract, making it difficult to constrain them directly be...

Abstract Algorithms are proposed to address the radar target detection problem of compressed sensing (CS) under conditions a low signal-to-noise ratio (SNR) and signal-to-clutter (SCR) echo signal. The algorithms include two-stage classification for targets based on compressive (CD) without signal reconstruction support vector data description (SVDD) one-class classifier. First, we present spar...