Search

Anomaly detection in energy consumption is a crucial step towards developing efficient energy saving systems, diminishing overall energy expenditure and reducing carbon emissions. Therefore, implementing powerful techniques to identify anomalous consumption in buildings and providing this information to end-users and managers is of significant importance. Accordingly, two novel schemes are proposed in this paper; the first one is an unsupervised abnormality detection based on one-class support vector machine, namely UAD-OCSVM, in which abnormalities are extracted without the need of annotated data; the second is a supervised abnormality detection based on micromoments (SAD-M2), which is implemented in the following steps: (i) normal and abnormal power consumptions are defined and assigned; (ii) a rule-based algorithm is introduced to extract the micromoments representing the intent-rich moments, in which the end-users make decisions to consume energy; and (iii) an improved K-nearest neighbors model is introduced to automatically classify consumption footprints as normal or abnormal. Empirical evaluation conducted in this framework under three different data sets demonstrates that SAD-M2 achieves both a highest abnormality detection performance and real-time processing capability with considerably lower computational cost in comparison with other machine learning methods. For instance, up to 99.71% accuracy and 99.77% F1 score have been achieved using a real-world data set collected at the Qatar University energy lab. 2021 Wiley Periodicals LLC This paper was made possible by National Priorities Research Program (NPRP) grant no. 10-0130-170288 from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the authors. Open Access funding provided by the Qatar National Library. Scopus

Intrusion detection systems (IDSs) play a significant role in the field of network security, dealing with the ever-increasing number of network threats. Machine learning-based IDSs have attracted a lot of interest owing to their powerful data-driven learning capabilities. However, it is challenging to train the supervised learning algorithms when there are no attack data at hand. Semi-supervised anomaly detection algorithms, which train the model with only normal data, are more suitable. In this study, we propose a novel semi-supervised anomaly detection-based IDS that leverages the capabilities of representation learning and two anomaly detectors. In detail, the autoencoder (AE) is applied to extract representative features of normal data in the first step, and then two semi-supervised detectors, the one-class support vector machine (OCSVM) and Gaussian mixture model (GMM), are trained on the derived features. The two detectors collaborate to detect anomalous samples. The OCSVM predicts the abnormal samples initially, and after that, the GMM is applied to recheck the misclassified samples further. The experiments demonstrate that the AE improves the detection rate, and two detectors are more promising than a single one.

This study aims to validate self-portraits using one-class support vector machine (OCSVM). To validate accurately, we build a model by combining texture feature extraction methods, Haralick and local binary pattern (LBP). We also reduce irrelevant features using forward selection (FS). OCSVM was selected because it can solve the problem caused by the inadequate variation of the negative class population. In OCSVM, we only need to feed the algorithm using the true class data, and the data with pattern that does not match will be classified as false. However, combining the two feature extractions produces many features, leading to the curse of dimensionality. The FS method is used to overcome this problem by selecting the best features. From the experiments carried out, the Haralick+LBP+FS+OCSVM model outperformed other models with an accuracy of 95.25% on validation data and 91.75% on test data.

Liquid rocket engines (LREs) are the main propulsive devices of launch vehicles. Due to the complex structures and extreme working environments, LREs are also the components prone to failure. It is of great engineering significance to develop fault detection technologies which can detect fault symptoms in time and provide criteria for further fault diagnosis and control measures to avoid serious consequences during both the ground tests and flight missions. This paper presents a novel fault detection method based on convolutional auto-encoder (CAE) and one-class support vector machine (OCSVM) for the steady-state process of LREs. We train the CAEs by normal ground hot-fire test data of a certain type of large LRE for automatic feature extraction. Then the obtained features are used to train the OCSVMs to accomplish the fault detection task. The results demonstrate that the proposed method outperforms traditional redline system (RS), adaptive threshold algorithm (ATA), and back-propagation neural network (BPNN). We also study the effect of sample sizes and domain knowledge on the performance of the proposed method. The results suggest that appropriate measures that enrich the effective information content in the training data, such as increasing sample size and introducing domain knowledge, can further improve the performance of the proposed fault detection method.

Pixel-based classification is a complex but well-known process widely used for satellite imagery classification. This paper presents a supervised multi-classifier pipeline that combined multiple Earth Observation (EO) data and different classification approaches to improve specific land cover type identification. The multi-classifier pipeline was tested and applied within the SCO-Live project that aims to use olive tree phenological evolution as a bio-indicator to monitor climate change. To detect and monitor olive trees, we classify satellite images to precisely locate the various olive groves. For that first step we designed a multi-classifier pipeline by the concatenation of a first classifier which uses a temporal Random-Forest model, providing an overall classification, and a second classifier which uses the result from the first classification. IOTA2 process was used in the first classifier, and we compared Multi-layer Perceptron (MLP) and One-class Support Vector Machine (OCSVM) for the second. The multi-classifier pipelines managed to reduce the false positive (FP) rate by approximately 40% using the combination RF/MLP while the RF/OCSVM combination lowered the FP rate by around 13%. Both approaches slightly raised the true positive rate reaching 83.5% and 87.1% for RF/MLP and RF/OCSVM, respectively. The overall results indicated that the combination of two classifiers pipeline improves the performance on detecting the olive groves compared to pipeline using only one classifier.

Hyperspectral anomaly detection is a popular research direction for hyperspectral images; however, it is problematic because it separates the background and anomaly without prior target information. Currently, deep neural networks are used as an extractor to mine intrinsic features in hyperspectral images, which can be fed into separate anomaly detection methods to improve their performances. However, this hybrid approach is suboptimal because the subsequent detector is unable to drive the data representation in hidden layers, which makes it a challenge to maximize the capabilities of deep neural networks when extracting the underlying features customized for anomaly detection. To address this issue, a novel unsupervised, self-attention-based, one-class neural network (SAOCNN) is proposed in this paper. SAOCNN consists of two components: a novel feature extraction network and a one-class SVM (OC-SVM) anomaly detection method, which are interconnected and jointly trained by the OC-SVM-like loss function. The adoption of co-training updates the feature extraction network together with the anomaly detector, thus improving the whole network’s detection performance. Considering that the prominent feature of an anomaly lies in its difference from the background, we designed a deep neural extraction network to learn more comprehensive hyperspectral image features, including spectral, global correlation, and local spatial features. To accomplish this goal, we adopted an adversarial autoencoder to produce the residual image with highlighted anomaly targets and a suppressed background, which is input into an improved non-local module to adaptively select the useful global information in the whole deep feature space. In addition, we incorporated a two-layer convolutional network to obtain local features. SAOCNN maps the original hyperspectral data to a learned feature space with better anomaly separation from the background, making it possible for the hyperplane to separate them. Our experiments on six public hyperspectral datasets demonstrate the state-of-the-art performance and superiority of our proposed SAOCNN when extracting deep potential features, which are more conducive to anomaly detection.

Wireless Sensors Networks have been the focus of significant attention from research and development due to their applications of collecting data from various fields such as smart cities, power grids, transportation systems, medical sectors, military, and rural areas. Accurate and reliable measurements for insightful data analysis and decision-making are the ultimate goals of sensor networks for critical domains. However, the raw data collected by WSNs usually are not reliable and inaccurate due to the imperfect nature of WSNs. Identifying misbehaviours or anomalies in the network is important for providing reliable and secure functioning of the network. However, due to resource constraints, a lightweight detection scheme is a major design challenge in sensor networks. This paper aims at designing and developing a lightweight anomaly detection scheme to improve efficiency in terms of reducing the computational complexity and communication and improving memory utilization overhead while maintaining high accuracy. To achieve this aim, one-class learning and dimension reduction concepts were used in the design. The One-Class Support Vector Machine (OCSVM) with hyper-ellipsoid variance was used for anomaly detection due to its advantage in classifying unlabelled and multivariate data. Various One-Class Support Vector Machine formulations have been investigated and Centred-Ellipsoid has been adopted in this study due to its effectiveness. Centred-Ellipsoid is the most effective kernel among studies formulations. To decrease the computational complexity and improve memory utilization, the dimensions of the data were reduced using the Candid Covariance-Free Incremental Principal Component Analysis (CCIPCA) algorithm. Extensive experiments were conducted to evaluate the proposed lightweight anomaly detection scheme. Results in terms of detection accuracy, memory utilization, computational complexity, and communication overhead show that the proposed scheme is effective and efficient compared few existing schemes evaluated. The proposed anomaly detection scheme achieved the accuracy higher than 98%, with O(nd) memory utilization and no communication overhead.

This paper tries to solve anomaly detection, a very important issue in ensuring the safe and stable operation of power system. As the proportion of abnormal data in the operation of power system is very small, a one-class support vector machine (OCSVM) is adopted in this paper, which is suitable for classification of unbalanced data. However, the performance of OCSVM is sensitive to its parameters, and an unsuitable choice will decrease the classification accuracy and generalization ability of it. In this paper, particle swarm optimization (PSO) is used to optimize the parameters of OCSVM. The original PSO algorithm converges slowly and easily falls into local optimum. To overcome this issue, this paper proposes an improved PSO algorithm for parameters optimization, in which adaptive speed weighting and adaptive population splitting are introduced to improve the convergence speed of the algorithm and help the algorithm jump out of the local optimal position. Experiments on standard benchmarks and real power system experimental data sets demonstrate the effectiveness of the proposed algorithm.

Sustainability has been a concern for society over the past few decades, preserving natural resources being one of the main themes. Among the various natural resources, water was one of them. The treatment of residual waters for future reuse and release to the environment is a fundamental task performed by Wastewater Treatment Plants (WWTP). Hence, to guarantee the quality of the treated effluent in a WWTP, continuous control and monitoring of abnormal events in the substances present in this water resource are necessary. One of the most critical substances is the pH that represents the measurement of the hydrogen ion activity. Therefore, this work presents an approach with a conception, tune and evaluation of several candidate models, based on two Machine Learning algorithms, namely Isolation Forests (iF) and One-Class Support Vector Machines (OCSVM), to detect anomalies in the pH on the effluent of a multi-municipal WWTP. The OCSVM-based model presents better performance than iF-based with an approximate 0.884 of Area Under The Curve - Receiver Operating Characteristics (AUC-ROC)., This work is financed by National Funds through the Portuguese funding agency, FCT - Fundação para a Ciência e a Tecnologia within project DSAIPA/AI/0099/2019.

Inter-robot communication and high computational power are challenging issues for deploying indoor mobile robot applications with sensor data processing. Thus, this paper presents an efficient cloud-based multirobot framework with inter-robot communication and high computational power to deploy autonomous mobile robots for indoor applications. Deployment of usable indoor service robots requires uninterrupted movement and enhanced robot vision with a robust classification of objects and obstacles using vision sensor data in the indoor environment. However, state-of-the-art methods face degraded indoor object and obstacle recognition for multiobject vision frames and unknown objects in complex and dynamic environments. From these points of view, this paper proposes a new object segmentation model to separate objects from a multiobject robotic view-frame. In addition, we present a support vector data description (SVDD)-based one-class support vector machine for detecting unknown objects in an outlier detection fashion for the classification model. A cloud-based convolutional neural network (CNN) model with a SoftMax classifier is used for training and identification of objects in the environment, and an incremental learning method is introduced for adding unknown objects to the robot knowledge. A cloud–robot architecture is implemented using a Node-RED environment to validate the proposed model. A benchmarked object image dataset from an open resource repository and images captured from the lab environment were used to train the models. The proposed model showed good object detection and identification results. The performance of the model was compared with three state-of-the-art models and was found to outperform them. Moreover, the usability of the proposed system was enhanced by the unknown object detection, incremental learning, and cloud-based framework.

Due to their conceptual simplicity and flexibility, non-parametric mixture models are widely used to identify latent clusters in data. However, when it comes to Big Data, such as Landsat imagery, such model fitting is computationally prohibitive. To overcome this issue, we fit Bayesian non-parametric models to pre-smoothed data, thereby reducing the computational time from days to minutes, while disregarding little of the useful information. Tree based clustering is used to partition the clusters into smaller and smaller clusters in order to identify clusters of high, medium and low interest. The tree-based clustering method is applied to Landsat images from the Brisbane region, which were the actual sources of motivation for development of the method. The images are taken as a part of the red imported fire-ant eradication program that was launched in September 2001 and which is funded by all Australian states and territories, along with the federal government. To satisfy budgetary constraints, modelling is performed to estimate the risk of fire-ant incursion in each cluster so that the eradication program focuses on high risk clusters. The likelihood of containment is successfully derived by combining the fieldwork survey data with the results obtained from the proposed method.

Highlights • In the presence of numerous research articles, extracting best-suited articles is timeconsuming and manually impractical. The objective of this paper is to extract the activity and trends of coronavirus related research articles using machine learning approaches to help the research community for future exploration concerning COVID-19 prevention and treatment techniques. • The COVID-19 open research dataset (CORD-19) is used for experiments, whereas several target-tasks along with explanations are defined for classification, based on domain knowledge. • Clustering techniques are used to create the different clusters of available articles, and later the task assignment is performed using parallel one-class support vector machines (OCSVMs). These defined tasks describes the behaviour of clusters to accomplish targetclass guided mining. • Experiments with original and reduced features validate the performance of the approach. It is evident that the k-means clustering algorithm, followed by parallel OCSVMs, outperforms other methods for both original and reduced feature space., The novel coronavirus disease 2019 (COVID-19) began as an outbreak from epicentre Wuhan, People’s Republic of China in late December 2019, and till June 27, 2020 it caused 9,904,906 infections and 496,866 deaths worldwide. The world health organization (WHO) already declared this disease a pandemic. Researchers from various domains are putting their efforts to curb the spread of coronavirus via means of medical treatment and data analytics. In recent years, several research articles have been published in the field of coronavirus caused diseases like severe acute respiratory syndrome (SARS), middle east respiratory syndrome (MERS) and COVID-19. In the presence of numerous research articles, extracting best-suited articles is time-consuming and manually impractical. The objective of this paper is to extract the activity and trends of coronavirus related research articles using machine learning approaches to help the research community for future exploration concerning COVID-19 prevention and treatment techniques. The COVID-19 open research dataset (CORD-19) is used for experiments, whereas several target-tasks along with explanations are defined for classification, based on domain knowledge. Clustering techniques are used to create the different clusters of available articles, and later the task assignment is performed using parallel one-class support vector machines (OCSVMs). These defined tasks describes the behaviour of clusters to accomplish target-class guided mining. Experiments with original and reduced features validate the performance of the approach. It is evident that the k-means clustering algorithm, followed by parallel OCSVMs, outperforms other methods for both original and reduced feature space.

Most conventional diagnostic methods for fault diagnosis in rolling bearings are able to work only for the case of stationary operating conditions (constant speed and load), whereas, bearings often work at time-varying conditions. Some methods have been proposed for damage detection in bearings working under time-varying speed conditions. However, their application might increase the instrumentation cost because of providing a phase reference signal. Furthermore, some methods such as order tracking methods can only be applied for limited speed variations. In this study, a novel combined method for fault detection in rolling bearings based on cointegration is proposed for the development of fault features which are sensitive to the presence of defects while in the same time they are insensitive to changes in the operational conditions. The method makes use solely of the measured vibration signals and does not require any additional measurements while it can identify defects even for considerable speed variations. The signals acquired during run-up condition are decomposed into zero-mean modes called intrinsic mode functions using the performance improved ensemble empirical mode decomposition method. Then, the cointegration, which is finding stationary linear combination of some non-stationary time series, is applied to the intrinsic mode functions to extract stationary residuals. The feature vectors are created by applying the Teager–Kaiser energy operator to the obtained stationary residuals. Finally, the feature vectors of the healthy bearing signals are utilized to construct a separating hyperplane using the one-class support vector machine method. Eventually the proposed method was applied to vibration signals measured on an experimental bearing test rig. The results confirm that the method can be successfully applied to distinguish between healthy and faulty bearings even if the shaft speed changes dramatically.

This study is focused on the current challenges dealing with electromechanical system monitoring applied in industrial frameworks, that is, the presence of unknown events and the limitation to the nominal healthy condition as starting knowledge. Thus, an industrial machinery condition monitoring methodology based on novelty detection and classification is proposed in this study. The methodology is divided in three main stages. First, a dedicated feature calculation and reduction over each available physical magnitude. Second, an ensemble structure of novelty detection models based on one-class support vector machines to identify not previously considered events. Third, a diagnosis model supported by a feature fusion scheme in order to reach high fault classification capabilities. The effectiveness of the fault detection and identification methodology has been compared with classical single model approach, and verified by experimental results obtained from an electromechanical machine. © 2018 IEEE.

Actualmente las empresas que no gestionan un elevado número de cheques deben acudir periódicamente a una oficina para depositarlos. En este artículo se plantea el desarrollo de una aplicación móvil Android que permita a los clientes de "La Caixa" capturar cheques de manera ergonómica, proporcionándoles un ahorro en dinero y tiempo de gestión. El sistema se basa en técnicas de visión por computador para detectar automáticamente los cheques, capturarlos y, finalmente, validar sus contenidos. Currently the companies that do not manage a large number of checks must periodically go to an office to make their deposit. This article describes the development of a mobile application for Android, that will allow to "La Caixa" customers to capture checks, save money and time. The system is based on computer vision techniques that allow it to automatically detect checks, capture them and finally validate their contents. Actualment les empreses que no gestionen un elevat nombre de xecs han d'acudir periòdicament a una oficina per dipositar-los. En aquest article es planteja el desenvolupament d'una aplicació mòbil Android que permeti als clients de "La Caixa" capturar xecs de manera ergonòmica, proporcionant-los un estalvi en diners i temps de gestió. El sistema es basa en tècniques de visió per computador per detectar automàticament els xecs, capturar-los i finalment validar els seus continguts.

In the last few years, due to the technological improvement of advanced metering infrastructures, water and natural gas grids can be regarded as smart-grids, similarly to power ones. However, considering the number of studies related to the application of computational intelligence to distribution grids, the gap between power grids and water/gas grids is notably wide. For this purpose, in this paper, a framework for leakage identification is presented. The framework is composed of three sections aimed at the extraction and the selection of features and at the detection of leakages. A variation of the Sequential Feature Selection (SFS) algorithm is used to select the best performing features within a set, including, also, innovative temporal ones. The leakage identification is based on novelty detection and exploits the characterization of a normality model. Three statistical approaches, The Gaussian Mixture Model (GMM), Hidden Markov Model (HMM) and One-Class Support Vector Machine (OC-SVM), are adopted, under a comparative perspective. Both residential and office building environments are investigated by means of two datasets. One is the Almanac of Minutely Power dataset (AMPds), and it provides water and gas data consumption at 1, 10 and 30 min of time resolution; the other is the Department of International Development (DFID) dataset, and it provides water and gas data consumption at 30 min of time resolution. The achieved performance, computed by means of the Area Under the Curve (AUC), reaches 90 % in the office building case study, thus confirming the suitability of the proposed approach for applications in smart water and gas grids.