One-class Approach Research Articles

AMAnD: an automated metagenome anomaly detection methodology utilizing DeepSVDD neural networks.

The composition of metagenomic communities within the human body often reflects localized medical conditions such as upper respiratory diseases and gastrointestinal diseases. Fast and accurate computational tools to flag anomalous metagenomic samples from typical samples are desirable to understand different phenotypes, especially in contexts where repeated, long-duration temporal sampling is done. Here, we present Automated Metagenome Anomaly Detection (AMAnD), which utilizes two types of Deep Support Vector Data Description (DeepSVDD) models; one trained on taxonomic feature space output by the Pan-Genomics for Infectious Agents (PanGIA) taxonomy classifier and one trained on kmer frequency counts. AMAnD's semi-supervised one-class approach makes no assumptions about what an anomaly may look like, allowing the flagging of potentially novel anomaly types. Three diverse datasets are profiled. The first dataset is hosted on the National Center for Biotechnology Information's (NCBI) Sequence Read Archive (SRA) and contains nasopharyngeal swabs from healthy and COVID-19-positive patients. The second dataset is also hosted on SRA and contains gut microbiome samples from normal controls and from patients with slow transit constipation (STC). AMAnD can learn a typical healthy nasopharyngeal or gut microbiome profile and reliably flag the anomalous COVID+ or STC samples in both feature spaces. The final dataset is a synthetic metagenome created by the Critical Assessment of Metagenome Annotation Simulator (CAMISIM). A control dataset of 50 well-characterized organisms was submitted to CAMISIM to generate 100 synthetic control class samples. The experimental conditions included 12 different spiked-in contaminants that are taxonomically similar to organisms present in the laboratory blank sample ranging from one strain tree branch taxonomic distance away to one family tree branch taxonomic distance away. This experiment was repeated in triplicate at three different coverage levels to probe the dependence on sample coverage. AMAnD was again able to flag the contaminant inserts as anomalous. AMAnD's assumption-free flagging of metagenomic anomalies, the real-time model training update potential of the deep learning approach, and the strong performance even with lightweight models of low sample cardinality would make AMAnD well-suited to a wide array of applied metagenomics biosurveillance use-cases, from environmental to clinical utility.

OneFall-GAN: A one-class GAN framework applied to fall detection

One of the most common health risks for senior citizens is a falling event, and to reduces the risk of death, a fall needs to be quickly reported. Thus, automatic fall detection systems were proposed to mitigate the falling problem, most of them relying on image detection. However, identifying a fall from a sequence of images is challenging because the contextual information present in some activities of daily living (ADL) are similar to fall events, and the recognition model has to deal with very high-level information. Furthermore, the publicly available datasets are generally unbalanced, having only synthetic data of fall events. Thus, approaches that do not need explicit labels to train a model are desirable. As falls are rare events, a possible solution is to use a one-class approach, and Generative Adversarial Networks (GAN) have presented competitive results in this context. This paper proposes OneFall-GAN, a One-Class GAN that uses only ADL for training and can identify a fall as an anomaly on the learned representations. We trained our neural network using the data captured by an RGB camera and pre-processed by a pre-trained Mask R-CNN that can segment and binarize a person in a scene. Thus, our model has robust temporal information used in the training phase and once trained, the discriminator is specialized on classifying ADL events. Consequently, when a fall event is presented, it is capable of classifying them as an anomaly. Using this approach, we are turning a binary classification problem into a one-class approach. Our experimental results show that our OneFall-GAN framework is a competitive alternative for fall classification as an anomaly detection task using only visual data, particularly because it achieved the best performance when compared to current state-of-the-art approaches, reaching an accuracy of 99.02%, 0.97 precision, 1.0 recall on PRECIS HAR and 98.75% accuracy, 0.87 precision, 0.99 recall on UP Fall.

Probabilistic Pocket Druggability Prediction via One-Class Learning.

The choice of target pocket is a key step in a drug discovery campaign. This step can be supported by in silico druggability prediction. In the literature, druggability prediction is often approached as a two-class classification task that distinguishes between druggable and non-druggable (or less druggable) pockets (or voxels). Apart from obvious cases, however, the non-druggable class is conceptually ambiguous. This is because any pocket (or target) is only non-druggable until a drug is found for it. It is therefore more appropriate to adopt a one-class approach, which uses only unambiguous information, namely, druggable pockets. Here, we propose using the import vector domain description (IVDD) algorithm to support this task. IVDD is a one-class probabilistic kernel machine that we previously introduced. To feed the algorithm, we use customized DrugPred descriptors computed via NanoShaper. Our results demonstrate the feasibility and effectiveness of the approach. In particular, we can remove or mitigate biases chiefly due to the labeling.

Learning to Classify DWDM Optical Channels from Tiny and Imbalanced Data.

Applying machine learning algorithms for assessing the transmission quality in optical networks is associated with substantial challenges. Datasets that could provide training instances tend to be small and heavily imbalanced. This requires applying imbalanced compensation techniques when using binary classification algorithms, but it also makes one-class classification, learning only from instances of the majority class, a noteworthy alternative. This work examines the utility of both these approaches using a real dataset from a Dense Wavelength Division Multiplexing network operator, gathered through the network control plane. The dataset is indeed of a very small size and contains very few examples of “bad” paths that do not deliver the required level of transmission quality. Two binary classification algorithms, random forest and extreme gradient boosting, are used in combination with two imbalance handling methods, instance weighting and synthetic minority class instance generation. Their predictive performance is compared with that of four one-class classification algorithms: One-class SVM, one-class naive Bayes classifier, isolation forest, and maximum entropy modeling. The one-class approach turns out to be clearly superior, particularly with respect to the level of classification precision, making it possible to obtain more practically useful models.

Target specific mining of COVID-19 scholarly articles using one-class approach.

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 behavior 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.

Detection of housing and utility problems in districts through social media texts

Abstract Social media stores a significant amount of information which can be used for extraction of specific knowledge. A variety of topics that arise there concerns a lot of everyday life aspects, including urban-related problems. In this work, we demonstrate the way of using the texts from social media on the topic of housing and utility problems, such as litter on the streets, graffiti on a public building or noisy neighbours. Our aim is to develop an approach based on machine learning to automatically filter such citizen messages and classify them into several categories. To achieve this, we solve the classification problem with an almost unlimited number of negative categories using the One-Class approach and combine data from several resources to construct proper text embedding by combining results from the guided topic model and deep neural pretrained BERT method. Comparison with statistics taken from the official site indicates that the distributions of posts on each problem category are similar for districts of Saint-Petersburg

Comparison of Different Multivariate Classification Methods for the Detection of Adulterations in Grape Nectars by Using Low-Field Nuclear Magnetic Resonance

Grape is the most consumed nectar in Brazil and a relatively expensive beverage. Therefore, it is susceptible to fraud by substitution with other less expensive fruit juices. Adulterations of grape nectars by the addition of apple juice, cashew juice, and mixtures of both were evaluated by using low-field nuclear magnetic resonance (LF-NMR) and supervised multivariate classification methods. Two different approaches were investigated using one-class (only unadulterated samples (UN) were modeled) and multiclass (three classes were modeled: UN, adulterated with cashew (CAS), and adulterated with apple (APP)) strategies. For the one-class approach, soft independent modeling of class analogy (SIMCA), one-class partial least squares (OCPLS), and data-driven SIMCA (DD-SIMCA) models were built. For the multiclass approach, partial least squares discriminant analysis (PLS-DA) and multiclass SIMCA models were built. The results obtained demonstrated good performances by all the one-class methods with efficiency rates higher than 93%. For the multiclass approach, the classification of samples containing only one type of adulterant presented efficiencies higher than 90% and 97% using SIMCA and PLS-DA, respectively. The classification of samples containing blends of two adulterants was satisfactory for the CAS class, but not for the APP class when applying PLS-DA. Nevertheless, multiclass SIMCA did not provide satisfactory predictions for either of these two classes.

Investigating an SVM-driven, one-class approach to estimating ship systems condition

ABSTRACTMaintenance is a major point that can affect vessel operation sustainability and profitability. Recent literature has shown that condition monitoring of ship systems shows great potential, albeit at significant data requirement costs. In this respect, this paper presents a novel methodology for intelligent, system-level engine performance monitoring, utilising noon-report data with minimal data assumptions. The proposed methodology is based on the training of a one-class Support Vector Machine, which models a diesel generator’s normal behaviour. Unseen data are then input into the model, where its output reflects a gauge of their normality, compared to the training dataset. This aids the dynamic detection of ship machinery incipient faults, contributing to the minimisation of ship downtime. A case study presenting applications of this modelling approach on ship machinery raw data is included, complemented by a sensitivity analysis. This demonstrates the applicability of the developed methodology in identifying deviant, abnormal ship machinery conditions.

Object recognition under severe occlusions with a hidden Markov model approach

Shape classification has multiple applications. In real scenes, shapes may contain severe occlusions, hardening the identification of objects. In this paper, a method for object recognition under severe occlusion is proposed. Occlusion is dealt with separating shapes into parts through high curvature points, then tangent angle signature is found for each part and continuous wavelet transform is calculated for each signature. Next, the best matching object is calculated for each part using Pearson’s correlation coefficient as similarity measure between wavelets of the part and of the most probable objects in the database. For each probable class, a hidden Markov model is created in an ensemble through training with the one-class approach. For hypotheses validation, two area restrictions are set to enhance recognition performance. Experiments were conducted with 1500 test shape instances with different scenarios of object occlusion. Results showed the method not only was capable of identifying highly occluded shapes (60%–80% overlapping) but also present several advantages over previous methods.

Risk prediction for cardiovascular disease using ECG data in the China kadoorie biobank.

We set out to use machine learning techniques to analyse ECG data to improve risk evaluation of cardiovascular disease in a very large cohort study of the Chinese population. We performed this investigation by (i) detecting "abnormality" using 3 one-class classification methods, and (ii) predicting probabilities of "normality", arrhythmia, ischemia, and hypertrophy using a multiclass approach. For one-class classification, we considered 5 possible definitions for "normality" and used 10 automatically-extracted ECG features along with 4 blood pressure features. The one-class approach was able to identify abnormality with area-under-curve (AUC) 0.83, and with 75.6% accuracy. For four-class classification, we used 86 features in total, with 72 additional features extracted from the ECG. Accuracy for this four-class classifier reached 75.1%. The methods demonstrated proof-of-principle that cardiac abnormality can be detected using machine learning in a large cohort study.

Riemannian Geometry Applied to Detection of Respiratory States From EEG Signals: The Basis for a Brain-Ventilator Interface.

During mechanical ventilation, patient-ventilator disharmony is frequently observed and may result in increased breathing effort, compromising the patient's comfort and recovery. This circumstance requires clinical intervention and becomes challenging when verbal communication is difficult. In this study, we propose a brain-computer interface (BCI) to automatically and noninvasively detect patient-ventilator disharmony from electroencephalographic (EEG) signals: a brain-ventilator interface (BVI). Our framework exploits the cortical activation provoked by the inspiratory compensation when the subject and the ventilator are desynchronized. Use of a one-class approach and Riemannian geometry of EEG covariance matrices allows effective classification of respiratory states. The BVI is validated on nine healthy subjects that performed different respiratory tasks that mimic a patient-ventilator disharmony. Classification performances, in terms of areas under receiver operating characteristic curves, are significantly improved using EEG signals compared to detection based on air flow. Reduction in the number of electrodes that can achieve discrimination can be often desirable (e.g., for portable BCI systems). By using an iterative channel selection technique, the common highest order ranking, we find that a reduced set of electrodes (n = 6) can slightly improve for an intrasubject configuration, and it still provides fairly good performances for a general intersubject setting. Results support the discriminant capacity of our approach to identify anomalous respiratory states, by learning from a training set containing only normal respiratory epochs. The proposed framework opens the door to BVIs for monitoring patient's breathing comfort and adapting ventilator parameters to patient respiratory needs.

Import Vector Domain Description: A Kernel Logistic One-Class Learning Algorithm.

Recognizing the samples belonging to one class in a heterogeneous data set is a very interesting but tough machine learning task. Some samples of the data set can be actual outliers or members of other classes for which training examples are lacking. In contrast to other kernel approaches present in the literature, in this work, the problem is faced defining a one-class kernel machine that delivers the probability for a sample to belong to the support of the distribution and that can be efficiently trained by a hybrid sequential minimal optimization-expectation maximization algorithm. Due to the analogy to the import vector machine and to the one-class approach, we named the method import vector domain description (IVDD). IVDD was tested on a toy 2-D data set in order to characterize its behavior on a set of widely used benchmarking UCI data sets and, lastly, challenged against a real world outlier detection data set. All the results were compared against state-of-the-art closely related methods such as one-class-SVM and Support Vector Domain Description, proving that the algorithm is equally accurate with the additional advantage of delivering the probability estimate for each sample. Finally, a few variants aimed at providing memory savings and/or computational speed-up in the light of big data analysis are briefly sketched.

A one-class approach to cardiotocogram assessment.

Cardiotocogram (CTG) is the most widely used means for the assessment of fetal condition. CTG consists of two traces one depicting the Fetal Heart Rate (FHR), and the other the Uterine Contractions (UC) activity. Many automatic methods have been proposed for the interpretation of the CTG. Most of them rely either on a binary classification approach or on a multiclass approach to come up with a decision about the class that the tracing belongs to. This work investigates the use of a one-class approach to the assessment of CTGs building a model only for the healthy data. The preliminary results are promising indicating that normal traces could be used as part of an automatic system that can detect deviations from normality.

Sequence Motif-Based One-Class Classifiers Can Achieve Comparable Accuracy to Two-Class Learners for Plant microRNA Detection

microRNAs (miRNAs) are short nucleotide sequences expressed by a genome that are involved in post transcriptional modulation of gene expression. Since miRNAs need to be co-expressed with their target mRNA to observe an effect and since miRNAs and target interactions can be cooperative, it is currently not possible to develop a comprehensive experimental atlas of miRNAs and their targets. To overcome this limitation, machine learning has been applied to miRNA detection. In general binary learning (two-class) approaches are applied to miRNA discovery. These learners consider both positive (miRNA) and negative (non-miRNA) examples during the training process. One-class classifiers, on the other hand, use only the information for the target class (miRNA). The one-class approach in machine learning is gradually receiving more attention particularly for solving problems where the negative class is not well defined. This is especially true for miRNAs where the positive class can be experimentally confirmed relatively easy, but where it is not currently possible to call any part of a genome a non-miRNA. To do that, it should be co-expressed with all other possible transcripts of the genome, which currently is a futile endeavor. For machine learning, miRNAs need to be transformed into a feature vector and some currently used features like minimum free energy vary widely in the case of plant miRNAs. In this study it was our aim to analyze different methods applying one-class approaches and the effectiveness of motif-based features for prediction of plant miRNA genes. We show that the application of these one-class classifiers is promising and useful for this kind of problem which relies only on sequence- based features such as k-mers and motifs comparing to the results from two-class classification. In some cases the results of one-class are, to our surprise, more accurate than results from two-class classifiers.

Principal Component Analysis of the start-up transient and Hidden Markov Modeling for broken rotor bar fault diagnosis in asynchronous machines

This article presents a novel computational method for the diagnosis of broken rotor bars in three phase asynchronous machines. The proposed method is based on Principal Component Analysis (PCA) and is applied to the stator’s three phase start-up current. The fault detection is easier in the start-up transient because of the increased current in the rotor circuit, which amplifies the effects of the fault in the stator’s current independently of the motor’s load. In the proposed fault detection methodology, PCA is initially utilized to extract a characteristic component, which reflects the rotor asymmetry caused by the broken bars. This component can be subsequently processed using Hidden Markov Models (HMMs). Two schemes, a multiclass and a one-class approach are proposed. The efficiency of the novel proposed schemes is evaluated by multiple experimental test cases. The results obtained indicate that the suggested approaches based on the combination of PCA and HMMs, can be successfully utilized not only for identifying the presence of a broken bar but also for estimating the severity (number of broken bars) of the fault.

A Two-Class Approach to the Detection of Physiological Deterioration in Patient Vital Signs, With Clinical Label Refinement

Hospital patient outcomes can be improved by the early identification of physiological deterioration. Automatic methods of detecting patient deterioration in vital-sign data typically attempt to identify deviations from assumed normal physiological conditions, which is a one-class approach to classification. This paper investigates the use of a two-class approach, in which abnormal physiology is modelled explicitly. The success of such a method relies on the accuracy of data labels provided by clinical experts, which may be incomplete (due to large dataset size) or imprecise (due to clinical labels covering intervals, rather than each data point within those intervals). We propose a novel method of refining clinical labels such that the two-class classification approach may be adopted for identifying patient deterioration. We demonstrate the effectiveness of the proposed methods using a large dataset acquired in a 24-bed hospital step-down unit.

One-class approach: models for virtual screening of non-nucleoside HIV-1 reverse transcriptase inhibitors based on the concept of continuous molecular fields

One-class models for virtual screening of potent non-nucleoside HIV reverse transcriptase inhibitors were built for the first time in terms of the one-class approach using the support vector machine method. The training set included 786 structures of 2-substituted pyrimidinones and their inhibitory activity against the enzyme of wild-type and mutant (K103, IRLL98, Y188L) HIV-1 strains. The representation of molecular structures of organic ligands based on continuous molecular fields can be used to build classification models of higher quality compared to conventional approaches using Carhart fragment-based descriptors, molecular fingerprints, and spectrophores.

Real-time aircraft noise likeness detector

Abstract One of the most difficult tasks involved in the process of noise monitoring near airports is related to the automatic detection and classification of aircraft noise events. These tasks can be solved by applying pattern recognition techniques to the audio signal captured by a microphone. But now the problem is caused by the background noise, which is present in real environments. This paper proposes a real-time method for continuously tracking the similarity of the input sound and the aircraft’s sounds. Using these facilities, the monitoring unit will be able to mark aircraft events, or to make measurements only when aircraft sound is louder than background noise. A one-class approach has been applied to this detection-by-classification method. Using the default setup, 93% of the aircraft’s events which held an SNR of 6–8 dB were detected, for 30 different locations with diverse soundscapes.

An application of one-class support vector machine to nosocomial infection detection.

Nosocomial infections (NIs)---those acquired in health care settings---are among the major causes of increased mortality among hospitalized patients. They are a significant burden for patients and health authorities alike; it is thus important to monitor and detect them through an effective surveillance system. This paper describes a retrospective analysis of a prevalence survey of NIs done in the Geneva University Hospital. Our goal is to identify patients with one or more NIs on the basis of clinical and other data collected during the survey. In this two-class classification task, the main difficulty lies in the significant imbalance between positive or infected (11%) and negative (89%) cases. To cope with class imbalance, we investigate one-class SVMs which can be trained to distinguish two classes on the basis of examples from a single class (in this case, only "normal" or non infected patients). The infected ones are then identified as "abnormal" cases or outliers that deviate significantly from the normal profile. Experimental results are encouraging: whereas standard 2-class SVMs scored a baseline sensitivity of 50.6% on this problem, the one-class approach increased sensitivity to as much as 92.6%. These results are comparable to those obtained by the authors in a previous study on asymmetrical soft margin SVMs; they suggest that one-class SVMs can provide an effective and efficient way of overcoming data imbalance in classification problems.