One-class classification: taxonomy of study and review of techniques

A one-class classification approach for authentication of specialty coffees by inductively coupled plasma mass spectroscopy (ICP-MS)

Due to the lucrative nature of specialty coffees, there have been instances of adulteration where low-cost materials are mixed in to increase the overall volume, resulting in illegal profit. A widely used and recommended approach to detect possible adulteration is the application of one-class classifiers (OCC), which only require information about the target class to build the models. Thus, this work aimed to identify adulterations in specialty coffees with low-quality coffee using multielement analysis determined by ICP-MS and to evaluate the performance of one-class classifiers (dd-SIMCA, OCRF, and OCPLS). Therefore, authentic specialty coffee samples were adulterated with low-quality coffee in 25 % to 75 % (w/w) proportions. Samples were subjected to acid decomposition for analysis by ICP-MS. OCPLS method presented the best performance to detect adulterations with low-quality coffee in specialty coffees, showing higher specificity (SPE = 100 %) and reliability rate (RLR = 94.3 %).

A Novel Classification Method: Neighborhood-Based Positive Unlabeled Learning Using Decision Tree (NPULUD)

In a standard binary supervised classification task, the existence of both negative and positive samples in the training dataset are required to construct a classification model. However, this condition is not met in certain applications where only one class of samples is obtainable. To overcome this problem, a different classification method, which learns from positive and unlabeled (PU) data, must be incorporated. In this study, a novel method is presented: neighborhood-based positive unlabeled learning using decision tree (NPULUD). First, NPULUD uses the nearest neighborhood approach for the PU strategy and then employs a decision tree algorithm for the classification task by utilizing the entropy measure. Entropy played a pivotal role in assessing the level of uncertainty in the training dataset, as a decision tree was developed with the purpose of classification. Through experiments, we validated our method over 24 real-world datasets. The proposed method attained an average accuracy of 87.24%, while the traditional supervised learning approach obtained an average accuracy of 83.99% on the datasets. Additionally, it is also demonstrated that our method obtained a statistically notable enhancement (7.74%), with respect to state-of-the-art peers, on average.

Multiview Deep Anomaly Detection: A Systematic Exploration

Anomaly detection (AD), which models a given normal class and distinguishes it from the rest of abnormal classes, has been a long-standing topic with ubiquitous applications. As modern scenarios often deal with massive high-dimensional complex data spawned by multiple sources, it is natural to consider AD from the perspective of multiview deep learning. However, it has not been formally discussed by the literature and remains underexplored. Motivated by this blank, this article makes fourfold contributions: First, to the best of our knowledge, this is the first work that formally identifies and formulates the multiview deep AD problem. Second, we take recent advances in relevant areas into account and systematically devise various baseline solutions, which lays the foundation for multiview deep AD research. Third, to remedy the problem that limited benchmark datasets are available for multiview deep AD, we extensively collect the existing public data and process them into more than 30 multiview benchmark datasets via multiple means, so as to provide a better evaluation platform for multiview deep AD. Finally, by comprehensively evaluating the devised solutions on different types of multiview deep AD benchmark datasets, we conduct a thorough analysis on the effectiveness of the designed baselines and hopefully provide other researchers with beneficial guidance and insight into the new multiview deep AD topic.

Implementation of an electronic nose for real -time identification of odour emission peaks at a wastewater treatment plant

This paper proposes a novel approach for the real-time monitoring of odour emissions from a WasteWater Treatment Plant (WWTP) using an Instrumental Odour Monitoring System (IOMS). The plant is characterized by unpredictable odour peaks at its arrival tank (AT), generating nuisance and complaints in the population living nearby the plant. Odour peaks are most likely due to the conferment of non-identified and malodorous wastewaters coming from various industrial activities. Due to the high variability of sources collecting their wastewaters to the WWTP, a new methodology to train the IOMS, based on the use of a one-class classifier (OCC), has been exploited. The OCC enables to detect deviations from a "Normal Operating Region" (NOR), defined as to include odour concentrations levels unlikely to cause nuisance in the citizenship. Such deviations from the NOR thus should be representative of the odour peaks. The results obtained prove that the IOMS is able to detect real-time alterations of odour emissions from the AT with an accuracy on independent validation data of about 90% (CI95% 55-100%). This ability of detecting anomalous conditions at the AT of the WWTP allowed the targeted withdrawal of liquid and gas samples in correspondence of the odour peaks, then subjected to further analyses that in turn enabled to investigate their origin and take proper counteractions to mitigate the WWTP odour impact.

VLAD: Task-agnostic VAE-based lifelong anomaly detection

Lifelong learning represents an emerging machine learning paradigm that aims at designing new methods providing accurate analyses in complex and dynamic real-world environments. Although a significant amount of research has been conducted in image classification and reinforcement learning, very limited work has been done to solve lifelong anomaly detection problems. In this context, a successful method has to detect anomalies while adapting to changing environments and preserving knowledge to avoid catastrophic forgetting. While state-of-the-art online anomaly detection methods are able to detect anomalies and adapt to a changing environment, they are not designed to preserve past knowledge. On the other hand, while lifelong learning methods are focused on adapting to changing environments and preserving knowledge, they are not tailored for detecting anomalies, and often require task labels or task boundaries which are not available in task-agnostic lifelong anomaly detection scenarios. This paper proposes VLAD, a novel VAE-based Lifelong Anomaly Detection method addressing all these challenges simultaneously in complex task-agnostic scenarios. VLAD leverages the combination of lifelong change point detection and an effective model update strategy supported by experience replay with a hierarchical memory maintained by means of consolidation and summarization. An extensive quantitative evaluation showcases the merit of the proposed method in a variety of applied settings. VLAD outperforms state-of-the-art methods for anomaly detection, presenting increased robustness and performance in complex lifelong settings.

On the evaluation of outlier detection and one-class classification: a comparative study of algorithms, model selection, and ensembles

It has been shown that unsupervised outlier detection methods can be adapted to the one-class classification problem (Janssens and Postma, in: Proceedings of the 18th annual Belgian-Dutch on machine learning, pp 56-64, 2009; Janssens et al. in: Proceedings of the 2009 ICMLA international conference on machine learning and applications, IEEE Computer Society, pp 147-153, 2009. 10.1109/ICMLA.2009.16). In this paper, we focus on the comparison of one-class classification algorithms with such adapted unsupervised outlier detection methods, improving on previous comparison studies in several important aspects. We study a number of one-class classification and unsupervised outlier detection methods in a rigorous experimental setup, comparing them on a large number of datasets with different characteristics, using different performance measures. In contrast to previous comparison studies, where the models (algorithms, parameters) are selected by using examples from both classes (outlier and inlier), here we also study and compare different approaches for model selection in the absence of examples from the outlier class, which is more realistic for practical applications since labeled outliers are rarely available. Our results showed that, overall, SVDD and GMM are top-performers, regardless of whether the ground truth is used for parameter selection or not. However, in specific application scenarios, other methods exhibited better performance. Combining one-class classifiers into ensembles showed better performance than individual methods in terms of accuracy, as long as the ensemble members are properly selected.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10618-023-00931-x.

One-Class Classification Using ℓp-Norm Multiple Kernel Fisher Null Approach

We address the one-class classification (OCC) problem and advocate a one-class MKL (multiple kernel learning) approach for this purpose. To this aim, based on the Fisher null-space OCC principle, we present a multiple kernel learning algorithm where an ℓ_p-norm regularisation (p ≥ 1) is considered for kernel weight learning. We cast the proposed one-class MKL problem as a min-max saddle point Lagrangian optimisation task and propose an efficient approach to optimise it. An extension of the proposed approach is also considered where several related one-class MKL tasks are learned concurrently by constraining them to share common weights for kernels. An extensive evaluation of the proposed MKL approach on a range of data sets from different application domains confirms its merits against the baseline and several other algorithms.

A Quantum-Classical Hybrid Solution for Deep Anomaly Detection

Machine learning (ML) has achieved remarkable success in a wide range of applications. In recent ML research, deep anomaly detection (AD) has been a hot topic with the aim of discriminating among anomalous data with deep neural networks (DNNs). Notably, image AD is one of the most representative tasks in current deep AD research. ML's interaction with quantum computing is giving rise to a heated topic named quantum machine learning (QML), which enjoys great prospects according to recent academic research. This paper attempts to address the image AD problem in a deep manner with a novel QML solution. Specifically, we design a quantum-classical hybrid DNN (QHDNN) that aims to learn directly from normal raw images to train a normality model and then exclude images that do not conform to this model as anomalies during its inference. To enable the QHDNN to perform satisfactorily in deep image AD, we explore multiple quantum layer architectures and design a VQC-based QHDNN solution. Extensive experiments were conducted on commonly used benchmarks to test the proposed QML solution, whose results demonstrate the feasibility of addressing deep image AD with QML. Importantly, the experimental results show that our quantum-classical hybrid solution can even yield superior performance to that of its classical counterpart when they share the same number of learnable parameters.

EEG Authentication System Based on One- and Multi-Class Machine Learning Classifiers

In the current Information Age, it is usual to access our personal and professional information, such as bank account data or private documents, in a telematic manner. To ensure the privacy of this information, user authentication systems should be accurately developed. In this work, we focus on biometric authentication, as it depends on the user's inherent characteristics and, therefore, offers personalized authentication systems. Specifically, we propose an electrocardiogram (EEG)-based user authentication system by employing One-Class and Multi-Class Machine Learning classifiers. In this sense, the main novelty of this article is the introduction of Isolation Forest and Local Outlier Factor classifiers as new tools for user authentication and the investigation of their suitability with EEG data. Additionally, we identify the EEG channels and brainwaves with greater contribution to the authentication and compare them with the traditional dimensionality reduction techniques, Principal Component Analysis, and χ2 statistical test. In our final proposal, we elaborate on a hybrid system resistant to random forgery attacks using an Isolation Forest and a Random Forest classifiers, obtaining a final accuracy of 82.3%, a precision of 91.1% and a recall of 75.3%.

One-Class Convolutional Neural Networks for Water-Level Anomaly Detection

Companies that own water systems to provide water storage and distribution services always strive to enhance and efficiently distribute water to different places for various purposes. However, these water systems are likely to face problems ranging from leakage to destruction of infrastructures, leading to economic and life losses. Thus, apprehending the nature of abnormalities that may interrupt or aggravate the service or cause the destruction is at the core of their business model. Normally, companies use sensor networks to monitor these systems and record operational data including any fluctuations in water levels considered abnormalities. Detecting abnormalities allows water companies to enhance the service's sustainability, quality, and affordability. This study investigates a 2D-CNN-based method for detecting water-level abnormalities as time-series anomaly pattern detection in the One-Class Classification (OCC) problem. Moreover, since abnormal data are usually scarce or unavailable, we explored a cheap method to generate synthetic temporal data and use them as a target class in addition to the normal data to train the CNN model for feature extraction and classification. These settings allow us to train a model to learn relevant pattern representations of the given classes in a binary classification fashion using cross-entropy loss. The ultimate goal of these investigations is to determine if any 2D-CNN-based model can be trained from scratch or if transfer learning of any pre-trained CNN model can be partially trained and used as the base network for one-class classification. The evaluation of the proposed One-Class CNN and previous approaches have shown that our approach has outperformed several state-of-the-art approaches by a significant margin. Additionally, in this paper, we mention two interesting findings: using synthetic data as the pseudo-class is a promising direction, and transfer learning should be dealt with considering that underfitting can happen because the transferred model is too complicated for training data.

One class classification for the detection of β2 adrenergic receptor agonists using single-ligand dynamic interaction data

G protein-coupled receptors are involved in many biological processes, relaying the extracellular signal inside the cell. Signaling is regulated by the interactions between receptors and their ligands, it can be stimulated by agonists, or inhibited by antagonists or inverse agonists. The development of a new drug targeting a member of this family requires to take into account the pharmacological profile of the designed ligands in order to elicit the desired response. The structure-based virtual screening of chemical libraries may prioritize a specific class of ligands by combining docking results and ligand binding information provided by crystallographic structures. The performance of the method depends on the relevance of the structural data, in particular the conformation of the targeted site, the binding mode of the reference ligand, and the approach used to compare the interactions formed by the docked ligand with those formed by the reference ligand in the crystallographic structure. Here, we propose a new method based on the conformational dynamics of a single protein–ligand reference complex to improve the biased selection of ligands with specific pharmacological properties in a structure-based virtual screening exercise. Interactions patterns between a reference agonist and the receptor, here exemplified on the β2 adrenergic receptor, were extracted from molecular dynamics simulations of the agonist/receptor complex and encoded in graphs used to train a one-class machine learning classifier. Different conditions were tested: low to high affinity agonists, varying simulation duration, considering or ignoring hydrophobic contacts, and tuning of the classifier parametrization. The best models applied to post-process raw data from retrospective virtual screening obtained by docking of test libraries effectively filtered out irrelevant poses, discarding inactive and non-agonist ligands while identifying agonists. Taken together, our results suggest that consistency of the binding mode during the simulation is a key to the success of the method.

Enhancing the Performance of Software Authorship Attribution Using an Ensemble of Deep Autoencoders

Software authorship attribution, defined as the problem of software authentication and resolution of source code ownership, is of major relevance in the software engineering field. Authorship analysis of source code is more difficult than the classic task on literature, but it would be of great use in various software development activities such as software maintenance, software quality analysis or project management. This paper addresses the problem of code authorship attribution and introduces, as a proof of concept, a new supervised classification model AutoSoft for identifying the developer of a certain piece of code. The proposed model is composed of an ensemble of autoencoders that are trained to encode and recognize the programming style of software developers. An extension of the AutoSoft classifier, able to recognize an unknown developer (a developer that was not seen during the training), is also discussed and evaluated. Experiments conducted on software programs collected from the Google Code Jam data set highlight the performance of the proposed model in various test settings. A comparison to existing similar solutions for code authorship attribution indicates that AutoSoft outperforms most of them. Moreover, AutoSoft provides the advantage of adaptability, illustrated through a series of extensions such as the definition of class membership probabilities and the re-framing of the AutoSoft system to address one-class classification.

ArtSeg-Artifact segmentation and removal in brightfield cell microscopy images without manual pixel-level annotations

Brightfield cell microscopy is a foundational tool in life sciences. The acquired images are prone to contain visual artifacts that hinder downstream analysis, and automatically removing them is therefore of great practical interest. Deep convolutional neural networks are state-of-the-art for image segmentation, but require pixel-level annotations, which are time-consuming to produce. Here, we propose ScoreCAM-U-Net, a pipeline to segment artifactual regions in brightfield images with limited user input. The model is trained using only image-level labels, so the process is faster by orders of magnitude compared to pixel-level annotation, but without substantially sacrificing the segmentation performance. We confirm that artifacts indeed exist with different shapes and sizes in three different brightfield microscopy image datasets, and distort downstream analyses such as nuclei segmentation, morphometry and fluorescence intensity quantification. We then demonstrate that our automated artifact removal ameliorates this problem. Such rapid cleaning of acquired images using the power of deep learning models is likely to become a standard step for all large scale microscopy experiments.

One-Class Classification by Ensembles of Random Planes (OCCERPs)

One-class classification (OCC) deals with the classification problem in which the training data have data points belonging only to the target class. In this paper, we present a one-class classification algorithm, One-Class Classification by Ensembles of Random Plane (OCCERP), that uses random planes to address OCC problems. OCCERP creates many random planes. There is a pivot point in each random plane. A data point is projected in a random plane and a distance from a pivot point is used to compute the outlier score of the data point. Outlier scores of a point computed using many random planes are combined to get the final outlier score of the point. An extensive comparison of the OCCERP algorithm with state-of-the-art OCC algorithms on several datasets was conducted to show the effectiveness of the proposed approach. The effect of the ensemble size on the performance of the OCCERP algorithm is also studied.

Novelty Detection for Metabolic Dynamics Established On Breast Cancer Tissue Using 2D NMR TOCSY Spectra

•

Automatic novelty detection of metabolites of 2D-TOCSY NMR spectra.

•

Metabolic profiling of the dynamics changes in Breast cancer tissue sample.

•

Accurate and fast automatic multicomponent peak assignment of 2D NMR spectrum.

•

One- and multi- novelty detection of metabolites.

Most metabolic profiling approaches focus only on identifying pre-known metabolites on NMR TOCSY spectrum using configured parameters. However, there is a lack of tasks dealing with automating the detection of new metabolites that might appear during the dynamic evolution of biological cells. Novelty detection is a category of machine learning that is used to identify data that emerge during the test phase and were not considered during the training phase. We propose a novelty detection system for detecting novel metabolites in the 2D NMR TOCSY spectrum of a breast cancer-tissue sample. We build one- and multi-class recognition systems using different classifiers such as, Kernel Null Foley-Sammon Transform, Kernel Density Estimation, and Support Vector Data Description. The training models were constructed based on different sizes of training data and are used in the novelty detection procedure. Multiple evaluation measures were applied to test the performance of the novelty detection methods. Depending on the training data size, all classifiers were able to achieve 0% false positive rates and total misclassification error in addition to 100% true positive rates. The median total time for the novelty detection process varies between 1.5 and 20 seconds, depending on the classifier and the amount of training data. The results of our novel metabolic profiling method demonstrate its suitability, robustness and speed in automated metabolic research.

A Hybrid Deep Learning and Visualization Framework for Pushing Behavior Detection in Pedestrian Dynamics

Crowded event entrances could threaten the comfort and safety of pedestrians, especially when some pedestrians push others or use gaps in crowds to gain faster access to an event. Studying and understanding pushing dynamics leads to designing and building more comfortable and safe entrances. Researchers—to understand pushing dynamics—observe and analyze recorded videos to manually identify when and where pushing behavior occurs. Despite the accuracy of the manual method, it can still be time-consuming, tedious, and hard to identify pushing behavior in some scenarios. In this article, we propose a hybrid deep learning and visualization framework that aims to assist researchers in automatically identifying pushing behavior in videos. The proposed framework comprises two main components: (i) Deep optical flow and wheel visualization; to generate motion information maps. (ii) A combination of an EfficientNet-B0-based classifier and a false reduction algorithm for detecting pushing behavior at the video patch level. In addition to the framework, we present a new patch-based approach to enlarge the data and alleviate the class imbalance problem in small-scale pushing behavior datasets. Experimental results (using real-world ground truth of pushing behavior videos) demonstrate that the proposed framework achieves an 86% accuracy rate. Moreover, the EfficientNet-B0-based classifier outperforms baseline CNN-based classifiers in terms of accuracy.

One-Class LSTM Network for Anomalous Network Traffic Detection

Artificial intelligence-assisted security is an important field of research in relation to information security. One of the most important tasks is to distinguish between normal and abnormal network traffic (such as malicious or sudden traffic). Traffic data are usually extremely unbalanced, and this seriously hinders the detection of outliers. Therefore, the identification of outliers in unbalanced datasets has become a key issue. To help solve this challenge, there is increasing interest in focusing on one-class classification methods that train models based on the samples of a single given class. In this paper, long short-term memory (LSTM) is introduced into one-class classification, and one-class LSTM (OC-LSTM) is proposed based on the traditional one-class support vector machine (OC-SVM). In contrast with other hybrid deep learning methods based on auto-encoders, the proposed method is an end-to-end training network that uses a loss function such as the OC-SVM optimization objective for model training. A comprehensive experiment on three large complex network traffic datasets showed that this method is superior to the traditional shallow method and the most advanced deep method. Furthermore, the proposed method can provide an effective reference for anomaly detection research in the field of network security, especially for the application of one-class classification.

Lightweight Internet of Things Botnet Detection Using One-Class Classification

Like smart phones, the recent years have seen an increased usage of internet of things (IoT) technology. IoT devices, being resource constrained due to smaller size, are vulnerable to various security threats. Recently, many distributed denial of service (DDoS) attacks generated with the help of IoT botnets affected the services of many websites. The destructive botnets need to be detected at the early stage of infection. Machine-learning models can be utilized for early detection of botnets. This paper proposes one-class classifier-based machine-learning solution for the detection of IoT botnets in a heterogeneous environment. The proposed one-class classifier, which is based on one-class KNN, can detect the IoT botnets at the early stage with high accuracy. The proposed machine-learning-based model is a lightweight solution that works by selecting the best features leveraging well-known filter and wrapper methods for feature selection. The proposed strategy is evaluated over different datasets collected from varying network scenarios. The experimental results reveal that the proposed technique shows improved performance, consistent across three different datasets used for evaluation.

FamilyGuard: A Security Architecture for Anomaly Detection in Home Networks

The residential environment is constantly evolving technologically. With this evolution, sensors have become intelligent interconnecting home appliances, personal computers, and mobile devices. Despite the benefits of this interaction, these devices are also prone to security threats and vulnerabilities. Ensuring the security of smart homes is challenging due to the heterogeneity of applications and protocols involved in this environment. This work proposes the FamilyGuard architecture to add a new layer of security and simplify management of the home environment by detecting network traffic anomalies. Experiments are carried out to validate the main components of the architecture. An anomaly detection module is also developed by using machine learning through one-class classifiers based on the network flow. The results show that the proposed solution can offer smart home users additional and personalized security features using low-cost devices.

Laser fabrication and evaluation of holographic intrinsic physical unclonable functions

Optical Physical Unclonable Functions (PUFs) are well established as the most powerful anticounterfeiting tool. Despite the merits of optical PUFs, widespread use is hindered by existing implementations that are complicated and expensive. On top, the overwhelming majority of optical PUFs refer to extrinsic implementations. Here we overcome these limitations to demonstrate for the first time strong intrinsic optical PUFs with exceptional security characteristics. In doing so, we use Computer-Generated Holograms (CGHs) as optical, intrinsic, and image-based PUFs. The required randomness is offered by the non-deterministic fabrication process achieved with industrial friendly, nanosecond pulsed fiber lasers. Adding to simplicity and low cost, the digital fingerprint is derived by a setup which is designed to be adjustable in a production line. In addition, we propose a novel signature encoding and authentication mechanism that exploits manifold learning techniques to efficiently differentiate data reconstruction-related variation from counterfeit attacks. The proposed method is applied experimentally on silver plates. The robustness of the fabricated intrinsic optical PUFs is evaluated over time. The results have shown exceptional values for robustness and a probability of cloning up to \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$10^{-14}$$\end{document}10-14, which exceeds the standard acceptance rate in security applications.

Uncovering Contributing Factors to Interruptions in the Power Grid: An Arctic Case

Electric failures are a problem for customers and grid operators. Identifying causes and localizing the source of failures in the grid is critical. Here, we focus on a specific power grid in the Arctic region of Northern Norway. First, we collected data pertaining to the grid topology, the topography of the area, the historical meteorological data, and the historical energy consumption/production data. Then, we exploited statistical and machine-learning techniques to predict the occurrence of failures. The classification models achieve good performance, meaning that there is a significant relationship between the collected variables and fault occurrence. Thus, we interpreted the variables that mostly explain the classification results to be the main driving factors of power interruption. Wind speed of gust and local industry activity are found to be the main controlling parameters in explaining the power failure occurrences. The result could provide important information to the distribution system operator for implementing strategies to prevent and mitigate incoming failures.

Wearable multimodal sensors for the detection of behavioral and psychological symptoms of dementia using personalized machine learning models

Introduction

Behavioral and psychological symptoms of dementia (BPSD) signal distress or unmet needs and present a risk to people with dementia and their caregivers. Variability in the expression of these symptoms is a barrier to the performance of digital biomarkers. The aim of this study was to use wearable multimodal sensors to develop personalized machine learning models capable of detecting individual patterns of BPSD.

Methods

Older adults with dementia and BPSD (n = 17) on a dementia care unit wore a wristband during waking hours for up to 8 weeks. The wristband captured motion (accelerometer) and physiological indicators (blood volume pulse, electrodermal activity, and skin temperature). Agitation or aggression events were tracked, and research staff reviewed videos to precisely annotate the sensor data. Personalized machine learning models were developed using 1‐minute intervals and classifying the presence of behavioral symptoms, and behavioral symptoms by type (motor agitation, verbal aggression, or physical aggression).

Results

Behavioral events were rare, representing 3.4% of the total data. Personalized models classified behavioral symptoms with a median area under the receiver operating curve (AUC) of 0.87 (range 0.64–0.95). The relative importance of the different sensor features to the predictive models varied both by individual and behavior type.

Discussion

Patterns of sensor data associated with BPSD are highly individualized, and future studies of the digital phenotyping of these behaviors would benefit from personalization.

A network-based positive and unlabeled learning approach for fake news detection

Fake news can rapidly spread through internet users and can deceive a large audience. Due to those characteristics, they can have a direct impact on political and economic events. Machine Learning approaches have been used to assist fake news identification. However, since the spectrum of real news is broad, hard to characterize, and expensive to label data due to the high update frequency, One-Class Learning (OCL) and Positive and Unlabeled Learning (PUL) emerge as an interesting approach for content-based fake news detection using a smaller set of labeled data than traditional machine learning techniques. In particular, network-based approaches are adequate for fake news detection since they allow incorporating information from different aspects of a publication to the problem modeling. In this paper, we propose a network-based approach based on Positive and Unlabeled Learning by Label Propagation (PU-LP), a one-class and transductive semi-supervised learning algorithm that performs classification by first identifying potential interest and non-interest documents into unlabeled data and then propagating labels to classify the remaining unlabeled documents. A label propagation approach is then employed to classify the remaining unlabeled documents. We assessed the performance of our proposal considering homogeneous (only documents) and heterogeneous (documents and terms) networks. Our comparative analysis considered four OCL algorithms extensively employed in One-Class text classification (k-Means, k-Nearest Neighbors Density-based, One-Class Support Vector Machine, and Dense Autoencoder), and another traditional PUL algorithm (Rocchio Support Vector Machine). The algorithms were evaluated in three news collections, considering balanced and extremely unbalanced scenarios. We used Bag-of-Words and Doc2Vec models to transform news into structured data. Results indicated that PU-LP approaches are more stable and achieve better results than other PUL and OCL approaches in most scenarios, performing similarly to semi-supervised binary algorithms. Also, the inclusion of terms in the news network activate better results, especially when news are distributed in the feature space considering veracity and subject. News representation using the Doc2Vec achieved better results than the Bag-of-Words model for both algorithms based on vector-space model and document similarity network.

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.

OCTID: a one-class learning-based Python package for tumor image detection

MOTIVATION

Tumor tile selection is a necessary prerequisite in patch-based cancer whole slide image analysis, which is labor-intensive and requires expertise. Whole slides are annotated as tumor or tumor free, but tiles within a tumor slide are not. As all tiles within a tumor free slide are tumor free, these can be used to capture tumor-free patterns using the one-class learning strategy.

RESULTS

We present a Python package, termed OCTID, which combines a pretrained convolutional neural network (CNN) model, Uniform Manifold Approximation and Projection (UMAP) and one-class support vector machine to achieve accurate tumor tile classification using a training set of tumor free tiles. Benchmarking experiments on four H&E image datasets achieved remarkable performance in terms of F1-score (0.90 ± 0.06), Matthews correlation coefficient (0.93 ± 0.05) and accuracy (0.94 ± 0.03).

AVAILABILITY AND IMPLEMENTATION

Detailed information can be found in the Supplementary File.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Positive-unlabeled learning in bioinformatics and computational biology: a brief review

Conventional supervised binary classification algorithms have been widely applied to address significant research questions using biological and biomedical data. This classification scheme requires two fully labeled classes of data (e.g. positive and negative samples) to train a classification model. However, in many bioinformatics applications, labeling data is laborious, and the negative samples might be potentially mislabeled due to the limited sensitivity of the experimental equipment. The positive unlabeled (PU) learning scheme was therefore proposed to enable the classifier to learn directly from limited positive samples and a large number of unlabeled samples (i.e. a mixture of positive or negative samples). To date, several PU learning algorithms have been developed to address various biological questions, such as sequence identification, functional site characterization and interaction prediction. In this paper, we revisit a collection of 29 state-of-the-art PU learning bioinformatic applications to address various biological questions. Various important aspects are extensively discussed, including PU learning methodology, biological application, classifier design and evaluation strategy. We also comment on the existing issues of PU learning and offer our perspectives for the future development of PU learning applications. We anticipate that our work serves as an instrumental guideline for a better understanding of the PU learning framework in bioinformatics and further developing next-generation PU learning frameworks for critical biological applications.

The value of human data annotation for machine learning based anomaly detection in environmental systems

Anomaly detection is the process of identifying unexpected data samples in datasets. Automated anomaly detection is either performed using supervised machine learning models, which require a labelled dataset for their calibration, or unsupervised models, which do not require labels. While academic research has produced a vast array of tools and machine learning models for automated anomaly detection, the research community focused on environmental systems still lacks a comparative analysis that is simultaneously comprehensive, objective, and systematic. This knowledge gap is addressed for the first time in this study, where 15 different supervised and unsupervised anomaly detection models are evaluated on 5 different environmental datasets from engineered and natural aquatic systems. To this end, anomaly detection performance, labelling efforts, as well as the impact of model and algorithm tuning are taken into account. As a result, our analysis reveals the relative strengths and weaknesses of the different approaches in an objective manner without bias for any particular paradigm in machine learning. Most importantly, our results show that expert-based data annotation is extremely valuable for anomaly detection based on machine learning.

Neural correlates of intra-saccadic motion perception

Retinal motion of the visual scene is not consciously perceived during ocular saccades in normal everyday conditions. It has been suggested that extra-retinal signals actively suppress intra-saccadic motion perception to preserve stable perception of the visual world. However, using stimuli optimized to preferentially activate the M-pathway, Castet and Masson (2000) demonstrated that motion can be perceived during a saccade. Based on this psychophysical paradigm, we used electroencephalography and eye-tracking recordings to investigate the neural correlates related to the conscious perception of intra-saccadic motion. We demonstrated the effective involvement during saccades of the cortical areas V1-V2 and MT-V5, which convey motion information along the M-pathway. We also showed that individual motion perception was related to retinal temporal frequency.

Learning Target Class Feature Subspace (LTC-FS) Using Eigenspace Analysis and N-ary Search-Based Autonomous Hyperparameter Tuning for OCSVM

Existing dimensionality reduction (DR) techniques such as principal component analysis (PCA) and its variants are not suitable for target class mining due to the negligence of unique statistical properties of class-of-interest (CoI) samples. Conventionally, these approaches utilize higher or lower eigenvalued principal components (PCs) for data transformation; but the higher eigenvalued PCs may split the target class, whereas lower eigenvalued PCs do not contribute significant information and wrong selection of PCs leads to performance degradation. Considering these facts, the present research offers a novel target class-guided feature extraction method. In this approach, initially, the eigendecomposition is performed on variance–covariance matrix of only the target class samples, where the higher- and lower-valued eigenvectors are rejected via statistical analysis, and the selected eigenvectors are utilized to extract the most promising feature subspace. The extracted feature-subset gives a more tighter description of the CoI with enhanced associativity among target class samples and ensures the strong separation from nontarget class samples. One-class support vector machine (OCSVM) is evaluated to validate the performance of learned features. To obtain optimized values of hyperparameters of OCSVM a novel [Formula: see text]-ary search-based autonomous method is also proposed. Exhaustive experiments with a wide variety of datasets are performed in feature-space (original and reduced) and eigenspace (obtained from original and reduced features) to validate the performance of the proposed approach in terms of accuracy, precision, specificity and sensitivity.

Outliers in clinical symptoms as preictal biomarkers

Previous findings have suggested that a preictal state might precede the epileptic seizure onset, which is the basis for seizure prediction attempts. Preictal states can be apprehended as outliers that differ from an interictal baseline and display clinical changes. We collected daily clinical scores from patients with epilepsy who underwent continuous video-EEG and assessed the ability of several outlier detection methods to identify preictal states. Results from 24 patients suggested that outlying clinical features were suggestive of preictal states and can be identified by statistical methods: AUC = 0.71, 95 % CI = [0.63 - 0.79]; PPV = 0.77, 95 % CI = [0.70 - 0.84]; FPR = 0.31, 95 % CI = [0.21 - 0.44]); and F1 score = 0.74, 95 % CI = [0.64 - 0.81]. Such algorithms could be straightforwardly implemented in a mobile device (e.g., tablet or smartphone), which would allow a longer data collection that could improve prediction performances. Additional clinical - and even multimodal - parameters could identify more subtle physiological modifications.

A literature review on one-class classification and its potential applications in big data

In severely imbalanced datasets, using traditional binary or multi-class classification typically leads to bias towards the class(es) with the much larger number of instances. Under such conditions, modeling and detecting instances of the minority class is very difficult. One-class classification (OCC) is an approach to detect abnormal data points compared to the instances of the known class and can serve to address issues related to severely imbalanced datasets, which are especially very common in big data. We present a detailed survey of OCC-related literature works published over the last decade, approximately. We group the different works into three categories: outlier detection, novelty detection, and deep learning and OCC. We closely examine and evaluate selected works on OCC such that a good cross section of approaches, methods, and application domains is represented in the survey. Commonly used techniques in OCC for outlier detection and for novelty detection, respectively, are discussed. We observed one area that has been largely omitted in OCC-related literature is its application context for big data and its inherently associated problems, such as severe class imbalance, class rarity, noisy data, feature selection, and data reduction. We feel the survey will be appreciated by researchers working in these areas of big data.

A Study of One-Class Classification Algorithms for Wearable Fall Sensors

In recent years, the popularity of wearable devices has fostered the investigation of automatic fall detection systems based on the analysis of the signals captured by transportable inertial sensors. Due to the complexity and variety of human movements, the detection algorithms that offer the best performance when discriminating falls from conventional Activities of Daily Living (ADLs) are those built on machine learning and deep learning mechanisms. In this regard, supervised machine learning binary classification methods have been massively employed by the related literature. However, the learning phase of these algorithms requires mobility patterns caused by falls, which are very difficult to obtain in realistic application scenarios. An interesting alternative is offered by One-Class Classifiers (OCCs), which can be exclusively trained and configured with movement traces of a single type (ADLs). In this paper, a systematic study of the performance of various typical OCCs (for diverse sets of input features and hyperparameters) is performed when applied to nine public repositories of falls and ADLs. The results show the potentials of these classifiers, which are capable of achieving performance metrics very similar to those of supervised algorithms (with values for the specificity and the sensitivity higher than 95%). However, the study warns of the need to have a wide variety of types of ADLs when training OCCs, since activities with a high degree of mobility can significantly increase the frequency of false alarms (ADLs identified as falls) if not considered in the data subsets used for training.

Multi-Perspective Anomaly Detection

Anomaly detection is a critical problem in the manufacturing industry. In many applications, images of objects to be analyzed are captured from multiple perspectives which can be exploited to improve the robustness of anomaly detection. In this work, we build upon the deep support vector data description algorithm and address multi-perspective anomaly detection using three different fusion techniques, i.e., early fusion, late fusion, and late fusion with multiple decoders. We employ different augmentation techniques with a denoising process to deal with scarce one-class data, which further improves the performance (ROC AUC =80%). Furthermore, we introduce the dices dataset, which consists of over 2000 grayscale images of falling dices from multiple perspectives, with 5% of the images containing rare anomalies (e.g., drill holes, sawing, or scratches). We evaluate our approach on the new dices dataset using images from two different perspectives and also benchmark on the standard MNIST dataset. Extensive experiments demonstrate that our proposed multi-perspective approach exceeds the state-of-the-art single-perspective anomaly detection on both the MNIST and dices datasets. To the best of our knowledge, this is the first work that focuses on addressing multi-perspective anomaly detection in images by jointly using different perspectives together with one single objective function for anomaly detection.

Maximum Correntropy Criterion-Based Hierarchical One-Class Classification

Due to the effectiveness of anomaly/outlier detection, one-class algorithms have been extensively studied in the past. The representatives include the shallow-structure methods and deep networks, such as the one-class support vector machine (OC-SVM), one-class extreme learning machine (OC-ELM), deep support vector data description (Deep SVDD), and multilayer OC-ELM (ML-OCELM/MK-OCELM). However, existing algorithms are generally built on the minimum mean-square-error (mse) criterion, which is robust to the Gaussian noises but less effective in dealing with large outliers. To alleviate this deficiency, a robust maximum correntropy criterion (MCC)-based OC-ELM (MC-OCELM) is first proposed and then further extended to a hierarchical network to enhance its capability in characterizing complex and large data (named HC-OCELM). The gradient derivation combining with a fixed-point iterative updation scheme is adopted for the output weight optimization. Experiments on many benchmark data sets are conducted for effectiveness validation. Comparisons to many state-of-the-art approaches are provided for the superiority demonstration.

One-class classification of special agroforestry Brazilian coffee using NIR spectrometry and chemometric tools

The near-infrared spectrometry combined with the one-class classification method was applied as quality control of the agroforestry-grown specialty coffee. A total of 34 samples were analyzed in this study. Spectral data were obtained using a NIR portable and different pre-treatment strategies for baseline correction were evaluated. Unsupervised pattern recognition (PCA and HCA) techniques were performed. The construction of the classification model was carried out using the dd-SIMCA algorithm with 19 samples acquired directly from producers that are recognized for the best quality control of the specialty type coffee. In order to test the model, 15 samples of non-specialty type, obtained in local markets, were evaluated. The classification model with the highest correct classification rate (CCR) scored 100% and 87% in the validation and test groups, respectively. The results demonstrated that the application of this strategy was successful in verifying the authenticity of specialty type agroforestry-grown coffee samples.

Predictive analytics for step-up therapy: Supervised or semi-supervised learning?

BACKGROUND

Step-up therapy is a patient management approach that aims to balance the efficacy, costs and risks posed by different lines of medications. While the initiation of first line medications is a straightforward decision, stepping-up a patient to the next treatment line is often more challenging and difficult to predict. By identifying patients who are likely to move to the next line of therapy, prediction models could be used to help healthcare organizations with resource planning and chronic disease management.

OBJECTIVE

To compared supervised learning versus semi-supervised learning to predict which rheumatoid arthritis patients will move from the first line of therapy (i.e., conventional synthetic disease-modifying antirheumatic drugs) to the next line of therapy (i.e., disease-modifying antirheumatic drugs or targeted synthetic disease-modifying antirheumatic drugs) within one year.

MATERIALS AND METHODS

Five groups of features were extracted from an administrative claims database: demographics, medications, diagnoses, provider characteristics, and procedures. Then, a variety of supervised and semi-supervised learning methods were implemented to identify the most optimal method of each approach and assess the contribution of each feature group. Finally, error analysis was conducted to understand the behavior of misclassified patients.

RESULTS

XGBoost yielded the highest F-measure (42%) among the supervised approaches and one-class support vector machine achieved the highest F-measure (65%) among the semi-supervised approaches. The semi-supervised approach had significantly higher F-measure (65% vs. 42%; p < 0.01), precision (51% vs. 33%; p < 0.01), and recall (89% vs. 59%; p < 0.01) than the supervised approach. Excluding demographic, drug, diagnosis, provider, and procedure features reduced theF-measure from 65% to 61%, 57%, 54%, 51% and 49% respectively (p < 0.01). The error analysis showed that a substantial portion of false positive patients will change their line of therapy shortly after the prediction period.

CONCLUSION

This study showed that supervised learning approaches are not an optimal option for a difficult clinical decision regarding step-up therapy. More specifically, negative class labels in step-up therapy data are not a robust ground truth, because the costs and risks associated with higher line of therapy impact objective decision making of patients and providers. The proposed semi-supervised learning approach can be applied to other step-up therapy applications.

Data cleaning issues in class imbalanced datasets: instance selection and missing values imputation for one-class classifiers

Purpose

Class imbalance learning, which exists in many domain problem datasets, is an important research topic in data mining and machine learning. One-class classification techniques, which aim to identify anomalies as the minority class from the normal data as the majority class, are one representative solution for class imbalanced datasets. Since one-class classifiers are trained using only normal data to create a decision boundary for later anomaly detection, the quality of the training set, i.e. the majority class, is one key factor that affects the performance of one-class classifiers.

Design/methodology/approach

In this paper, we focus on two data cleaning or preprocessing methods to address class imbalanced datasets. The first method examines whether performing instance selection to remove some noisy data from the majority class can improve the performance of one-class classifiers. The second method combines instance selection and missing value imputation, where the latter is used to handle incomplete datasets that contain missing values.

Findings

The experimental results are based on 44 class imbalanced datasets; three instance selection algorithms, including IB3, DROP3 and the GA, the CART decision tree for missing value imputation, and three one-class classifiers, which include OCSVM, IFOREST and LOF, show that if the instance selection algorithm is carefully chosen, performing this step could improve the quality of the training data, which makes one-class classifiers outperform the baselines without instance selection. Moreover, when class imbalanced datasets contain some missing values, combining missing value imputation and instance selection, regardless of which step is first performed, can maintain similar data quality as datasets without missing values.

Originality/value

The novelty of this paper is to investigate the effect of performing instance selection on the performance of one-class classifiers, which has never been done before. Moreover, this study is the first attempt to consider the scenario of missing values that exist in the training set for training one-class classifiers. In this case, performing missing value imputation and instance selection with different orders are compared.

Improved One-Class Modeling of High-Dimensional Metabolomics Data via Eigenvalue-Shrinkage

One-class modelling is a useful approach in metabolomics for the untargeted detection of abnormal metabolite profiles, when information from a set of reference observations is available to model "normal" or baseline metabolite profiles. Such outlying profiles are typically identified by comparing the distance between an observation and the reference class to a critical limit. Often, multivariate distance measures such as the Mahalanobis distance (MD) or principal component-based measures are used. These approaches, however, are either not applicable to untargeted metabolomics data, or their results are unreliable. In this paper, five distance measures for one-class modeling in untargeted metabolites are proposed. They are based on a combination of the MD and five so-called eigenvalue-shrinkage estimators of the covariance matrix of the reference class. A simple cross-validation procedure is proposed to set the critical limit for outlier detection. Simulation studies are used to identify which distance measure provides the best performance for one-class modeling, in terms of type I error and power to identify abnormal metabolite profiles. Empirical evidence demonstrates that this method has better type I error (false positive rate) and improved outlier detection power than the standard (principal component-based) one-class models. The method is illustrated by its application to liquid chromatography coupled to mass spectrometry (LC-MS) and nuclear magnetic response spectroscopy (NMR) untargeted metabolomics data from two studies on food safety assessment and diagnosis of rare diseases, respectively.

A double-dichotomy clustering of dual pathology dementia patients

INTRODUCTION

Subcortical ischemic vascular disease (SIVD) and Alzheimer's disease (AD) related dementia can coexist in older subjects, leading to mixed dementia (MX). Identification of dementia sub-groups is important for designing proper treatment plans and clinical trials.

METHOD

An Alzheimer's disease severity (ADS) score and a vascular disease severity (VDS) score are calculated from CSF and MRI biomarkers, respectively. These scores, being sensitive to different Alzheimer's and vascular disease processes are combined orthogonally in a double-dichotomy plot. This formed an objective basis for clustering the subjects into four groups, consisting of AD, SIVD, MX and leukoaraiosis (LA). The relationship of these four groups is examined with respect to cognitive assessments and clinical diagnosis.

RESULTS

Cluster analysis had at least 83% agreement with the clinical diagnosis for groups based either on Alzheimer's or on vascular sensitive biomarkers, and a combined agreement of 68.8% for clustering the four groups. The VDS score was correlated to executive function (r = -0.28, p < 0.01) and the ADS score to memory function (r = -0.35, p < 0.002) after adjusting for age, sex, and education. In the subset of patients for which the cluster scores and clinical diagnoses agreed, the correlations were stronger (VDS score-executive function: r = -0.37, p < 0.006 and ADS score-memory function: r = -0.58, p < 0.0001).

CONCLUSIONS

The double-dichotomy clustering based on imaging and fluid biomarkers offers an unbiased method for identifying mixed dementia patients and selecting better defined sub-groups. Differential correlations with neuropsychological tests support the hypothesis that the categories of dementia represent different etiologies.

From fault detection to one-class severity discrimination of 3D printers with one-class support vector machine

The lack of faulty condition data reduces the feasibility of supervised learning for fault detection or fault severity discrimination in new manufacturing technologies. To deal with this issue, one-class learning arises for building binary discriminative models using only healthy condition data. However, these models have not been extrapolated to severity discrimination. This paper proposes to extend OCSVM, which is typically used for fault detection, to 3D printer fault severity discrimination. First, a set of features is extracted from a set of normal signals. An optimized OCSVM model is obtained by tuning the kernel and model hyperparameters. The resulting models are evaluated for fault detection and fault severity discrimination using a proposed performance evaluation approach. Experimental comparisons for belt-based faults in 3D printers show that the distance to the hyperplane has the information to discriminate the severity level, and its use is feasible. The proposed hyperparameter optimization technique improves the OCSVM for fault detection and severity discrimination compared to some other methods.

Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods

The notion of uncertainty is of major importance in machine learning and constitutes a key element of machine learning methodology. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions. Yet, due to the steadily increasing relevance of machine learning for practical applications and related issues such as safety requirements, new problems and challenges have recently been identified by machine learning scholars, and these problems may call for new methodological developments. In particular, this includes the importance of distinguishing between (at least) two different types of uncertainty, often referred to as aleatoric and epistemic. In this paper, we provide an introduction to the topic of uncertainty in machine learning as well as an overview of attempts so far at handling uncertainty in general and formalizing this distinction in particular.