SDAC: A Multimodal Synthetic Dataset for Anomaly and Corner Case Detection in Autonomous Driving

Conditions monitoring of industrial robot gears has the potential to increase the productivity of highly automated production systems. The huge amount of health indicators needed to monitor multiple gears of multiple robots requires an automated system for anomaly and trend detection. In this publication, such a system is presented and suitable anomaly detection and trend detection methods for the system are selected based on synthetic and real world industrial application data. A statistical test, namely the Cox-Stuart test, appears to be the most suitable approach for trend detection and the local outlier factor algorithm or the long short-term neural network performs best for anomaly detection in the application of industrial robot gear condition monitoring in the presented experiments.

Anomaly detection is often approached as an out-of-distribution (OOD) detection task, where a feature distribution from normal samples is constructed, and deviations are flagged as anomalies. This approach is dependent on manual labeling, as subtle visual anomalies can be easily overlooked, resulting in the potential for bias in labeling and subsequent unsatisfactory detection results. Based on the issue, we propose Anomaly Detection with Succinct Feature Filtering (ADSFF) for unlabeled samples. Our method avoids sample labeling bias and provides a solution to the coexistence of anomalous and normal features in the feature space of unlabeled samples. ADSFF includes a data preprocessing module and a feature filtering module, where the data preprocessing module improves the visibility of subtle anomalies, while the feature filtering module screens the local features of the samples. In feature filtering, we found that feedforward neural networks do not lose feature information during the feature transformation process. Consequently, we utilized feedforward neural networks for feature filtering and achieved expected results. Furthermore, we investigate the impact of sample imbalance on the task of anomaly detection using unlabeled samples. This paper assesses the performance of ADSFF using the MVTec AD and BeanTech Anomaly Detection (BTAD) datasets. The results demonstrate that ADSFF achieves an average area under the curve (AUC) of 0.978 on the MVTec AD and an average AUC of 0.942 on the BTAD. ADSFF outperformed other methods on seven test datasets in MVTec AD, achieving the highest average accuracy on MVTec AD.

Since the nonstationary distribution of the detected objects is general in the real world, the accurate and efficient outlier detection for data analysis within wireless sensor network (WSN) is a challenge. Recently, with high classification precision and affordable complexity, one-class quarter-sphere support vector machine (QSSVM) has been introduced to deal with the online and adaptive outlier detection in WSN. Regarding the one-sided consideration of optimization or iterative updating algorithm for QSSVM model within current techniques, we have proposed comprehensive outlier detection methods in WSN based on the QSSVM algorithm. To reduce the complexity of optimization algorithm for QSSVM model in existing techniques, a fast optimization algorithm based on average Euclidean distance has been developed and employed to the comprehensive outlier detection method. Evaluated by real and synthetic WSN data sets, our methods have shown an excellent outlier detection performance, and they have been proved to meet the requirements of online adaptive outlier detection in the case of nonstationary detection tasks of WSN.

Anomaly detection has been widely studied and used in diverse applications. Building an effective anomaly detection system requires the researchers/developers to learn the complex structure from noisy data, identify the dynamic anomaly patterns and detect anomalies while lacking sufficient labels. Recent advancement in deep learning techniques has made it possible to largely improve anomaly detection performance compared to the classical approaches. This tutorial will help the audience gain a comprehensive understanding of deep learning-based anomaly detection techniques in various application domains. First, it introduces what is the anomaly detection problem, the approaches taken before the deep model era and the challenges it faced. Then it surveys the state-of-the-art deep learning models extensively and discusses the techniques used to overcome the limitations from traditional algorithms. Second to last, it studies deep model anomaly detection techniques in real world examples from LinkedIn production systems. The tutorial concludes with a discussion of future trends.

Automatic time-series anomaly detection has been utilized for several applications such as general infrastructure systems. While accuracy and quickness are important factors for anomaly detection, explainability is crucial for safety-critical systems such as space systems. In this context, traditional machine learning-based methods of time-series anomaly detection such as Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) are not able to explain why symptoms of anomaly are detected. However, flight controllers of International Space Station (ISS) need to assess trends of telemetries and understand situations before making coordination with other domestic and foreign flight controllers and taking any actions corresponding to anomaly detections. In this research, we conducted the following three steps to detect signs of anomaly with rationales behind the anomaly, i.e., 1) selecting objective and explanatory variables, 2) conducting anomaly detections with time-series machine learning, 3) providing additional information with assessing the anomaly detections. The method was verified with the data of two anomaly events of Low Temperature loop (LTL) pump inverter of Japanese Experimental Module of the ISS in 2012 and 2014. There were some different trends of telemetries in 2012 and 2014. A selected objective variable was successfully predicted based on explanatory variables in normal period and away from the actual measured value in off-nominal period with LSTM for both cases. The analysis results showed the effectiveness of our new methods as the machine learning-based time-series predictive failure detection with identifying possible causes. Our proposed method can contribute to health monitoring of space systems and anomaly detections with showing possible reasons behind anomaly events. It is expected to widely contribute to the safety of space systems.

Multivariate time series anomaly detection has great potentials in many practical applications. Extreme unbalanced training set and noise interference make it challenging to accurately capture the distribution of normal data and then detect anomalies. Existing AutoEncoder(AE)-based approaches are lack of effective regularization method specially designed for anomaly detection tasks thus easily overfitting while Generative Adversarial Network(GAN)-based approaches are mostly trained under the hypothesis of pollution-free training set, which means the training set is all composed of normal samples and that is hard to satisfy in practice. To tackle these problems, in this paper we propose a GAN based anomaly detection method for multivariate time series named FGANomaly (letter F is for Filter). The core idea is to filter possible anomalous samples with pseudo-labels before training the discriminator thus to capture the distribution of normal data as precise as possible. In addition, we design a novel training objective for the generator, which leads the generator to concentrate more on plausible normal data and ignore anomalies. We conducted comprehensive experiments on four public datasets, and the experimental results show the superiority of our method over baselines in both performance and robustness.

Since the Local Outlier Factor (LOF) was first proposed, there is a large family of approaches that is derived from it. For the reason that the existing local outliers detection approaches only focus on the extent of overall separation between an object and its neighbors, and do not pay attention to the degree of dispersion between them, the precision of these approaches will be seriously affected in the scattered data sets for outlier detection. In this paper, we redefine the local outliers by combining the degree of dispersion of the object and its neighbors, and propose a new local outlier detection approach (N2DLOF). Compared to conventional approaches, the outliers obtained by N2DLOF are more sensitive to the degree of anomaly of the scattered data sets. Experiments show that our approach has a significant improvement on outlier detection precision in the case of scattered datasets with similar time complexity. In short, we extend the ecosystem of the local outlier detection approaches from a new perspective.

Datasets for autonomous cars are essential for the development and benchmarking of perception systems. However, most existing datasets are captured with camera and LiDAR sensors in good weather conditions. In this paper, we present the RAdar Dataset In Adverse weaThEr (RADIATE), aiming to facilitate research on object detection, tracking and scene understanding using radar sensing for safe autonomous driving. RADIATE includes 3 hours of annotated radar images with more than 200K labelled road actors in total, on average about 4.6 instances per radar image. It covers 8 different categories of actors in a variety of weather conditions (e.g., sun, night, rain, fog and snow) and driving scenarios (e.g., parked, urban, motorway and suburban), representing different levels of challenge. To the best of our knowledge, this is the first public radar dataset which provides high-resolution radar images on public roads with a large amount of road actors labelled. The data collected in adverse weather, e.g., fog and snowfall, is unique. Some baseline results of radar based object detection and recognition are given to show that the use of radar data is promising for automotive applications in bad weather, where vision and LiDAR can fail. RADIATE also has stereo images, 32-channel LiDAR and GPS data, directed at other applications such as sensor fusion, localisation and mapping. The public dataset can be accessed at http://pro.hw.ac.uk/radiate/.

Anomaly detection is an important problem in computer vision; however, the scarcity of anomalous samples makes this task difficult. Thus, recent anomaly detection methods have used only “normal images” with no abnormal areas for training. In this work, a powerful anomaly detection method is proposed based on student-teacher feature pyramid matching (STPM), which consists of a student and teacher network. Generative models are another approach to anomaly detection. They reconstruct normal images from an input and compute the difference between the predicted normal and the input. Unfortunately, STPM does not have the ability to generate normal images. To improve the accuracy of STPM, this work uses a student network, as in generative models, to reconstruct normal features. This improves the accuracy; however, the anomaly maps for normal images are not clean because STPM does not use anomaly images for training, which decreases the accuracy of the image-level anomaly detection. To further improve accuracy, a discriminative network trained with pseudo-anomalies from anomaly maps is used in our method, which consists of two pairs of student-teacher networks and a discriminative network. The method displayed high accuracy on the MVTec anomaly detection dataset.

In manufacturing industries, it is of fundamental importance to detect anomalies in production in order to meet the required quality goals and to limit the number of defective products that are accidentally delivered to the customers. Nevertheless, monitoring systems currently employed in production are typically very simple and rely on a set of univariate control charts that fail to capture the multivariate and complex nature of real-world industrial systems. In such context, Machine Learning (ML)-based approaches for Anomaly Detection (AD) have proven to be extremely effective in increasing anomalies detectability and, in general, in enhancing monitoring procedures. However, industrial data are typically very complex and not suitable to be fed directly to classical ML-based AD tools making feature extraction procedures a necessary step that unfortunately may lead to information loss and low scalability. Deep Learning, has proven very effective at learning useful representations of complex data in an automatic way. In this paper, we propose an AD pipeline that makes use of convolutional autoencoders to extract useful features from two-dimensional, non-image, data. We test our approach on real world Optical Emission Spectroscopy data that are typical of semiconductor manufacturing and we achieve improved performance over classical monitoring methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Advanced monitoring is one of the most important task in the context of Industry 4.0. Some of the main issues in developing Machine Learning-based solutions in industrial environment are: (i) the lack of reliable tagged data; (ii) the complexity of data structures present in real-world scenarios. In this paper we investigate unsupervised anomaly detection for 2-dimensional data in manufacturing environment: we provide an approach that exploit Deep Learning-based architecture for handling the data at hand. We show the effectiveness of the proposed approach in a real world case study related to optical emission spectroscopy data in semiconductor manufacturing process providing satisfactory classification accuracy.

In the field of data mining and machine learning, outlier detection is considered a significant procedure for many applications, such as fraud detection in bank transactions and decision support systems. Data streams are a major player in the big data era. Currently, data streams are generated from various sources with huge amounts of data. This has led to difficulty when using older algorithms, which are designed for static data. The Local Outlier Factor (LOF) is one of these algorithms. The most challenging issue of the LOF is that it needs to preserve the whole dataset in computer memory. A new LOF that can deal with a data stream in limited memory is needed. This paper is a case study of several benchmark datasets for outlier detection that aim to increase the efficiency of the accuracy of local outlier detection in data streams.

The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the field of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new approaches and ideas. We introduce the MVTec Anomaly Detection (MVTec AD) dataset containing 5354 high-resolution color images of different object and texture categories. It contains normal, i.e., defect-free, images intended for training and images with anomalies intended for testing. The anomalies manifest themselves in the form of over 70 different types of defects such as scratches, dents, contaminations, and various structural changes. In addition, we provide pixel-precise ground truth regions for all anomalies. We also conduct a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods based on deep architectures such as convolutional autoencoders, generative adversarial networks, and feature descriptors using pre-trained convolutional neural networks, as well as classical computer vision methods. This initial benchmark indicates that there is considerable room for improvement. To the best of our knowledge, this is the first comprehensive, multi-object, multi-defect dataset for anomaly detection that provides pixel-accurate ground truth regions and focuses on real-world applications.

The curse of dimensionality in high-dimensional data makes it difficult to capture the abnormality of data points in full data space. To deal with this problem, we propose an outlier detection model based on Variational Autoencoder and Genetic Algorithm for subspace outlier analysis of high-dimensional data (VAGA). The proposed VAGA model constructs a variational autoencoder (VAE) to preliminarily detect outliers. Then the genetic algorithm (GA) is used to search the abnormal subspace of the outliers obtained by the VAE layer to provide a basis for subspace outlier analysis. The subsequent clustering of the abnormal subspaces help filter out the false positives which are fed back to the VAE layer to adjust network weights. The comparative experiments performed on three public benchmark datasets show that the outlier detection results of the proposed VAGA model are highly interpretable and have better accuracy performance than the state-of-the-art outlier detection methods.

Anomalies in time series, also called “discord,” are the abnormal subsequences. The occurrence of anomalies in time series may indicate that some faults or disease will occur soon. Therefore, development of novel computational approaches for anomaly detection (discord search) in time series is of great significance for state monitoring and early warning of real-time system. Previous studies show that many algorithms were successfully developed and were used for anomaly classification, e.g., health monitoring, traffic detection, and intrusion detection. However, the anomaly detection of time series was not well studied. In this paper, we proposed a long short-term memory- (LSTM-) based anomaly detection method (LSTMAD) for discord search from univariate time series data. LSTMAD learns the structural features from normal (nonanomalous) training data and then performs anomaly detection via a statistical strategy based on the prediction error for observed data. In our experimental evaluation using public ECG datasets and real-world datasets, LSTMAD detects anomalies more accurately than other existing approaches in comparison.

Ventricular arrhythmias (VA) are among the most prevalent and clinically significant cardiac arrhythmias. Conventional detection methodologies predominantly employ supervised learning approaches that depend on precisely annotated training datasets. However, the morphological similarity between VA waveforms and noise artifacts poses a significant challenge for traditional algorithms in discriminating these clinically distinct categories. In this paper, we propose a novel anomaly detection framework named PHVA (Pseudo-data and Hard-sample mining for VA detection) based on one-class anomaly detection, where only normal ECGs are used for training, while pseudo-anomalies are generated through self-supervised modules. These modules, including pseudo-anomaly generation and hard-sample mining, provide supervisory signals without requiring abnormal labels. Specifically, we introduce a physiology-aware synthetic ECG generation method that captures the beat morphology and waveform characteristics of VA while incorporating realistic noise simulations based on conventional noise models. These pseudo-annotated signals are then used to refine the decision boundary of a time-frequency hypersphere, constructed from normal ECG features in both temporal and spectral domains. Additionally, we employ triplet-loss-based hard-sample mining to improve the model's discriminative power for ventricular fibrillation detection. Extensive experiments on three public ECG datasets demonstrate that our proposed method PHVA achieves superior overall performance, outperforming state-of-the-art anomaly detection baselines by up to 8.7% in AUC (the Area Under a Receiver Operating Characteristic Curve). We share an online repository containing the code and data processing scripts https://github.com/Augustgaoshaochen/PHVA.