One-class Classification Model Research Articles

Analysis Of One-Class and Binary Classification For COVID-19 Image Data

With the recent Coronavirus Disease 2019 (COVID-19) outbreak, there has been a growing interest in the utilization of machine learning models to aid in medical diagnostics. However, during the initial phases of the pandemic, the available datasets were severely imbalanced due to a scarcity of positive cases. These datasets predominantly comprised normal cases, with only a limited number of disease instances. This inherent data imbalance restricted the effectiveness of binary classification, prompting an exploration of one-class classification. This study aims to compare the performance of one-class and binary classification models during the early stages of COVID-19 development. The objective is to provide healthcare professionals with the most effective machine learning-assisted solutions for handling future outbreaks of a similar nature. The experiment incorporates three distinct models: One-Class Support Vector Machine (OCSVM) for one-class classification, alongside Categorical Boosting (CatBoost) and Extreme Gradient Boosting (XGBoost) for binary classification. These models undergo a rigorous tuning process employing grid search, using training data composed of features extracted from compressed chest X-ray images. In summary, the research findings unequivocally demonstrate the superior performance of one-class classification over binary classification in all early stages, achieving an impressive F1 score of 0.46, compared to binary classification's modest score of 0.063. Consequently, it is strongly recommended to employ a one-class classification model to enhance real-life diagnostic processes. However, it is anticipated that as more positive cases are incorporated into the dataset, achieving a more balanced distribution, binary classification may exhibit greater potential. Thus, medical practitioners should reconsider the applicability of binary classification in later stages when the dataset attains improved balance.

Interpretable synthetic signals for explainable one-class time-series classification

This research paper introduces an innovative approach for explainable one-class time-series classification (XOCTSC). The proposed method involves generating pseudounseen synthetic signals by altering the amplitude and cycle of the original signals. Subsequently, a classification process is performed to distinguish between the original and synthetic signals, and the resulting model is applied to testing data. Instances classified as synthetic classes are treated as unseen classes, and the dissimilarity with the training data can be elucidated through an explanation of the synthetic class creation process. This approach aims to enhance the interpretability of one-class time-series classification models by providing insights into the reasoning behind their decisions. The proposed method is demonstrated with a ballistocardiogram (BCG) signal for the breathing dataset and an electroencephalogram (EEG) signal for the epilepsy dataset. The proposed method recognizes BCG amplitude reduction during breath holding. Moreover, EEG cycle changes during epileptic seizures are observed across multiple channels. These observations align with actual epilepsy symptoms and breathing behaviors.

Hierarchical One-Class Model With Subnetwork for Representation Learning and Outlier Detection.

The multilayer one-class classification (OCC) frameworks have gained great traction in research on anomaly and outlier detection. However, most multilayer OCC algorithms suffer from loosely connected feature coding, affecting the ability of generated latent space to properly generate a highly discriminative representation between object classes. To alleviate this deficiency, two novel OCC frameworks, namely: 1) OCC structure using the subnetwork neural network (OC-SNN) and 2) maximum correntropy-based OC-SNN (MCOC-SNN), are proposed in this article. The novelties of this article are as follows: 1) the subnetwork is used to build the discriminative latent space; 2) the proposed models are one-step learning networks, instead of stacking feature learning blocks and final classification layer to recognize the input pattern; 3) unlike existing works which utilize mean square error (MSE) to learn low-dimensional features, the MCOC-SNN uses maximum correntropy criterion (MCC) for discriminative feature encoding; and 4) a brand-new OCC dataset, called CO-Mask, is built for this research. Experimental results on the visual classification domain with a varying number of training samples from 6131 to 513 061 demonstrate that the proposed OC-SNN and MCOC-SNN achieve superior performance compared to the existing multilayer OCC models. For reproducibility, the source codes are available at https://github.com/W1AE/OCC.

Geographical origin identification of camellia oil based on fatty acid profiles combined with one-class classification

Geographical Indication (GI) agricultural products possess specific geographical origins and high qualities, which require an effective geographical origin traceability method for the important protective trademarks. In this study, authentication models for Changshan camellia oil were developed by fatty acid profiles and one-class classification methods including data-driven soft independent modeling of class analogy (DD-SIMCA) and one-class partial least squares (OCPLS), and compared with traditional two-class classification models. The results indicated that the prediction errors of three two-class classification models were 63.8%, 12.1%, and 65.2% for the samples out of targeted geographical origins, respectively. By contrast, the one-class classification models could completely differentiate Changshan from non-Changshan camellia oils, even from the adjacent counties. Moreover, compared with traditional indicators of mineral elements, the model built by fatty acid profiles possessed higher sensitivity and specificity. It also offered a reference strategy for the geographical origin identification of other high-value oils or foods.

Patterns in official food control data – Modelling dioxin and PCB profiling data for authentication of Baltic Sea salmon

Fish and fish products are often subjected to food fraud. Due to the significant environmental pollution of the Baltic Sea, fish caught in this area might be labelled as originating from elsewhere. Therefore, analytical proof showing whether fish samples like salmon come from the Baltic Sea or not is of particular interest. Here, official food control data of dioxin and PCB congener concentrations in salmon was used separately and combined as parameters for building one-class classification models using data driven soft independent modelling of class analogy (DD-SIMCA). The training set consisted of Baltic Sea salmon data collected from 2002 through 2019, and the model was tested on Baltic Sea salmon data samples from 2021 and salmon samples coming from China, Chile, Canada, Norway, USA, and Vietnam. The model's performance showed accuracy rates up to 100 %, indicating the model’s future potential to predict whether salmon samples originate from the Baltic Sea or not. This study exemplarily illustrates how the exploration of underlying patterns in official food control data can be used for authentication purposes.

AAE-DSVDD: A one-class classification model for VPN traffic identification

Virtual Private Network(VPN) can provide a concealed transmission channel for communication and protect the privacy of users. However, it also brings hidden dangers to cybersecurity with its wide application. Malicious behavior or harmful information can be transmitted secretly through VPN tunnels to avoid firewall censorship. Therefore, VPN traffic identification is an important part of ensure cybersecurity. Although many efforts have been made for VPN traffic identification, existing methods mainly focus on supervised learning models. In this paper, we propose an one-class classification model called AAE-DSVDD for VPN traffic identification. First, we introduce Adversarial AutoEncoder(AAE) for preliminary modeling of VPN traffic. AAE can match the aggregated posterior distribution of the hidden layer to an arbitrary prior distribution. It associates the samples with a normal distribution in the hidden space. Secondly, We implement representation learning for VPN traffic via Deep Support Vector Data Description(DSVDD). A standardized method is designed to match the output distribution of DSVDD with the aggregated posterior distribution of AAE. It alleviates the hypersphere collapse problem of DSVDD and improves identification performance. Finally, we verify the abilities of the AAE-DSVDD model on the public dataset ISCXVPN. Compared with other one-class models, AAE-DSVDD achieved the best identification ability for VPN traffic identification. It also improves the recognition ability when identifying strange classes that are not included in the training data.

One-Class Classification for Radar-Based Human Fall Event Detection

Existing deep learning and machine learning techniques for radar-based fall event detection require a large number of fall activity instances at the training stage to produce reliable results. However, to replicate real-life scenarios, falls should be treated as rare events. This work pioneers the application of one-class classification (OCC) technique for radar-based fall event detection. A comparative analysis of three different types of OCC techniques using abstract features extracted from six different pre-trained models is shown. An improved novel feature fused OCC model is proposed that achieves an area under the curve value of 0.912 for fall event detection. All evaluations are done on a publicly available dataset of human radar signatures.

Two-Stream Network One-Class Classification Model for Defect Inspections.

Defect inspection is important to ensure consistent quality and efficiency in industrial manufacturing. Recently, machine vision systems integrating artificial intelligence (AI)-based inspection algorithms have exhibited promising performance in various applications, but practically, they often suffer from data imbalance. This paper proposes a defect inspection method using a one-class classification (OCC) model to deal with imbalanced datasets. A two-stream network architecture consisting of global and local feature extractor networks is presented, which can alleviate the representation collapse problem of OCC. By combining an object-oriented invariant feature vector with a training-data-oriented local feature vector, the proposed two-stream network model prevents the decision boundary from collapsing to the training dataset and obtains an appropriate decision boundary. The performance of the proposed model is demonstrated in the practical application of automotive-airbag bracket-welding defect inspection. The effects of the classification layer and two-stream network architecture on the overall inspection accuracy were clarified by using image samples collected in a controlled laboratory environment and from a production site. The results are compared with those of a previous classification model, demonstrating that the proposed model can improve the accuracy, precision, and F1 score by up to 8.19%, 10.74%, and 4.02%, respectively.

AutoOC: Automated multi-objective design of deep autoencoders and one-class classifiers using grammatical evolution

One-Class Classification (OCC) corresponds to a subclass of unsupervised Machine Learning (ML) that is valuable when labeled data is non-existent. In this paper, we present AutoOC, a computationally efficient Grammatical Evolution (GE) approach that automatically searches for OCC models. AutoOC assumes a multi-objective optimization, aiming to increase the OCC predictive performance while reducing the ML training time. AutoOC also includes two execution speedup mechanisms, a periodic training sampling, and a multi-core fitness evaluation. In particular, we study two AutoOC variants: a pure Neuroevolution (NE) setup that optimizes two types of deep learning models, namely dense Autoencoder (AE) and Variational Autoencoder (VAE); and a general Automated Machine Learning (AutoML) ALL setup that considers five distinct OCC base learners, specifically Isolation Forest (IF), Local Outlier Factor (LOF), One-Class SVM (OC-SVM), AE and VAE. Several experiments were conducted, using eight public OpenML datasets and two validation scenarios (unsupervised and supervised). The results show that AutoOC requires a reasonable amount of execution time and tends to obtain lightweight OCC models. Moreover, AutoOC provides quality predictive results, outperforming a baseline IF for all analyzed datasets and surpassing the best supervised OpenML human modeling for two datasets.

A green method for the authentication of sugarcane spirit and prediction of density and alcohol content based on near infrared spectroscopy and chemometric tools

Cachaça is a Brazilian beverage obtained from the fermentation of sugarcane juice (sugarcane spirit) and is considered one of the most consumed alcoholic beverages in the world with a strong economic impact on the northeastern Brazil, more specifically in the Brejo. This microregion produces sugarcane spirits with high quality associated to edaphoclimatic conditions. In this sense, analysis for sample authentication and quality control that uses solvent-free, environmentally friendly, rapid and non-destructive methods is advantageous for cachaça producers and production chain. Thus, in this work commercial cachaça samples using near-infrared spectroscopy (NIRS) were classified based on geographical origin using one-class classification Data-Driven in Soft Independent Modelling of Class Analogy (DD-SIMCA) and One-Class Partial Least Squares (OCPLS) and predicted quality parameters of alcohol content and density based on different chemometric algorithms. A total of 150 sugarcane spirits samples were purchased from the Brazilian retail market being 100 from Brejo and 50 from other regions of Brazil. The one-class chemometric classification model was obtained with DD-SIMCA using the Savitzky-Golay derivative with first derivative, 9-point window and 1st degree polynomial as preprocessing algorithm and sensibility was 96.70 % and specificity 100 % in the spectral range 7,290–11,726 cm−1. Satisfactory results were obtained in the model constructs for density and the chemometric model, iSPA-PLS algorithm with baseline offset as preprocessing, obtained root mean square errors of prediction (RMSEP) of 0.0011 mg/L and Relative Error of Prediction (REP) of 0.12 %. The chemometric model for alcohol content prediction used the iSPA-PLS algorithm with Savitzky-Golay derivative with first derivative, 9-point window and 1st degree polynomial as algorithm as preprocessing obtaining RMSEP and REP of 0.69 and 1.81 % (v/v), respectively. Both models used the spectral range from 7,290–11,726 cm−1. The results reflected the potential of vibrational spectroscopy coupled with chemometrics to build reliable models for identifying the geographical origin of cachaça samples for predicting quality parameters in cachaça samples.

A Lightweight Intelligent Network Intrusion Detection System Using One-Class Autoencoder and Ensemble Learning for IoT.

Network intrusion detection technology is key to cybersecurity regarding the Internet of Things (IoT). The traditional intrusion detection system targeting Binary or Multi-Classification can detect known attacks, but it is difficult to resist unknown attacks (such as zero-day attacks). Unknown attacks require security experts to confirm and retrain the model, but new models do not keep up to date. This paper proposes a Lightweight Intelligent NIDS using a One-Class Bidirectional GRU Autoencoder and Ensemble Learning. It can not only accurately identify normal and abnormal data, but also identify unknown attacks as the type most similar to known attacks. First, a One-Class Classification model based on a Bidirectional GRU Autoencoder is introduced. This model is trained with normal data, and has high prediction accuracy in the case of abnormal data and unknown attack data. Second, a multi-classification recognition method based on ensemble learning is proposed. It uses Soft Voting to evaluate the results of various base classifiers, and identify unknown attacks (novelty data) as the type most similar to known attacks, so that exception classification becomes more accurate. Experiments are conducted on WSN-DS, UNSW-NB15, and KDD CUP99 datasets, and the recognition rates of the proposed models in the three datasets are raised to 97.91%, 98.92%, and 98.23% respectively. The results verify the feasibility, efficiency, and portability of the algorithm proposed in the paper.

Effective One-Class Classifier Model for Memory Dump Malware Detection

Malware complexity is rapidly increasing, causing catastrophic impacts on computer systems. Memory dump malware is gaining increased attention due to its ability to expose plaintext passwords or key encryption files. This paper presents an enhanced classification model based on One class SVM (OCSVM) classifier that can identify any deviation from the normal memory dump file patterns and detect it as malware. The proposed model integrates OCSVM and Principal Component Analysis (PCA) for increased model sensitivity and efficiency. An up-to-date dataset known as “MALMEMANALYSIS-2022” was utilized during the evaluation phase of this study. The accuracy achieved by the traditional one-class classification (TOCC) model was 55%, compared to 99.4% in the one-class classification with the PCA (OCC-PCA) model. Such results have confirmed the improved performance achieved by the proposed model.

One-class Classification-Based Machine Learning Model for Estimating the Probability of Wildfire Risk

Wildfires have caused devastating consequences to property and human and animal lives, which has become a global problem. Consequently, advanced wildfire prediction models are required to treat complex features and climate conditions. As a result, Machine Learning and Deep Learning models are becoming popular. However, creating a balanced true and false labeled dataset in the wild-fire domain is often challenging. Hence, One-class classification models are a promising approach to overcome this concern. In this paper, several One-class classification models are investigated; linear models (Principal Component Analysis and One-Class Support Vector Machines), outlier ensemble models (Lightweight On-line Detector of Anomalies and Locally Selective Combination of Parallel Outlier Ensembles), proximity-based models (Histogram-based Outlier Score and Rotation-based Outlier Detection), probabilistic models (Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions and Copula-Based Outlier Detection), neural network-based models (Deep One-class Classification and Adversarially Learned Anomaly Detection) is used in two case studies for California and Western Australian states. In conclusion, it was found that Deep learning-based One-class classification models outperform other models in terms of performance and feature importance of showcasing the effectiveness of deep neural network models in the wildfire prediction domain.

One-Class Adversarial Fraud Detection Nets with Class Specific Representations

Most fraud detection algorithms identify the anomaly by learning from a small number of existing fraud samples, therefore they are often ineffective when deal with complex and unknown situations. This paper proposes a new one-class classification model called one-class adversarial fraud detection nets with class specific representations (CS-OCAN), which consists of modified autoencoders and Complementary generative adversarial networks (GAN). Firstly, the two-iteration framework is designed to make reasonable use of the reference data generated by Complementary GAN. Secondly, an additional loss function is added in the latent space of the autoencoder, which transforms the semi-supervised problem into a supervised problem that aims to maximize inter-class distances between two classes and minimize intra-class variances. We have conducted experiments on UMD Wikipedia dataset and Credit card fraud detection dataset. Experimental results show that our method CS-OCAN has significantly improved the detection accuracy and stability compared with the state-of-the-art one-class classification models.

A One-Class Classification Model for Burned-Area Detection Based on Mutual Ordering of Normalized Differences

A One-Class Classification Model for Burned-Area Detection Based on Mutual Ordering of Normalized Differences

ADS-Lead: Lifelong Anomaly Detection in Autonomous Driving Systems

Autonomous Vehicles (AVs) are closely connected in the Cooperative Intelligent Transportation System (C-ITS). They are equipped with various sensors and controlled by Autonomous Driving Systems (ADSs) to provide high-level autonomy. The vehicles exchange different types of real-time data with each other, which can help reduce traffic accidents and congestion, and improve the efficiency of transportation systems. However, when interacting with the environment, AVs suffer from a broad attack surface, and the sensory data are susceptible to anomalies caused by faults, sensor malfunctions, or attacks, which may jeopardize traffic safety and result in serious accidents. In this paper, we propose <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ADS-Lead</monospace> , an efficient collaborative anomaly detection methodology to protect the lane-following mechanism of ADSs. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ADS-Lead</monospace> is equipped with a novel transformer-based one-class classification model to identify time series anomalies (GPS spoofing threat) and adversarial image examples (traffic sign and lane recognition attacks). Besides, AVs inside the C-ITS form a cognitive network, enabling us to apply the federated learning technology to our anomaly detection method, where the vehicles in the C-ITS jointly update the detection model with higher model generalization and data privacy. Experiments on Baidu Apollo and two public data sets (GTSRB and Tumsimple) indicate that our method can not only detect sensor anomalies effectively and efficiently but also outperform state-of-the-art anomaly detection methods.

Active anomaly detection based on deep one-class classification

Active learning has been utilized as an efficient tool in building anomaly detection models by leveraging expert feedback. In an active learning framework, a model queries samples to be labeled by experts and re-trains the model with the labeled data samples. It unburdens in obtaining annotated datasets while improving anomaly detection performance. However, most of the existing studies focus on helping experts identify as many abnormal data samples as possible, which is a sub-optimal approach for one-class classification-based deep anomaly detection. In this paper, we tackle two essential problems of active learning for Deep SVDD: query strategy and semi-supervised learning method. First, rather than solely identifying anomalies, our query strategy selects uncertain samples according to an adaptive boundary. Second, we apply noise contrastive estimation in training a one-class classification model to incorporate both labeled normal and abnormal data effectively. We analyze that the proposed query strategy and semi-supervised loss individually improve an active learning process of anomaly detection and further improve when combined together on seven anomaly detection datasets.

Establishment and evaluation of multiple adulteration detection of camellia oil by mixture design

Multiple adulteration is a common trick to mask adulteration detection methods. In this study, the representative multiple adulterated camellia oils were prepared according to the mixture design. Then, these representative oils were employed to build two-class classification models and validate one-class classification model combined with fatty acid profiles. The cross-validation results indicated that the recursive SVM model possessed higher classification accuracy (97.9%) than PLS-DA. In OCPLS model, the optimal percentage of RO, SO, CO and SUO was 2.8%, 0%, 7.2%, 0% respectively in adulterated camellia oil, which is the most similar to the authentic camellia oils. Further validation showed that five adulterated oils with the optimal percentage could be correctly identified, indicating that the OCPLS model could identify multiple adulterated oils with these four cheaper oils. Moreover, this study serves as a reference for one class classification model evaluation and a solution for multiple adulteration detection of other foods.

Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images

Combining deep learning and UAV images to map wetland vegetation distribution has received increasing attention from researchers. However, it is difficult for one multi-classification convolutional neural network (CNN) model to meet the accuracy requirements for the overall classification of multi-object types. To resolve these issues, this paper combined three decision fusion methods (Majority Voting Fusion, Average Probability Fusion, and Optimal Selection Fusion) with four CNNs, including SegNet, PSPNet, DeepLabV3+, and RAUNet, to construct different fusion classification models (FCMs) for mapping wetland vegetations in Huixian Karst National Wetland Park, Guilin, south China. We further evaluated the effect of one-class and multi-class FCMs on wetland vegetation classification using ultra-high-resolution UAV images and compared the performance of one-class classification (OCC) and multi-class classification (MCC) models for karst wetland vegetation. The results highlight that (1) the use of additional multi-dimensional UAV datasets achieved better classification performance for karst wetland vegetation using CNN models. The OCC models produced better classification results than MCC models, and the accuracy (average of IoU) difference between the two model types was 3.24–10.97%. (2) The integration of DSM and texture features improved the performance of FCMs with an increase in accuracy (MIoU) from 0.67% to 8.23% when compared to RGB-based karst wetland vegetation classifications. (3) The PSPNet algorithm achieved the optimal pixel-based classification in the CNN-based FCMs, while the DeepLabV3+ algorithm produced the best attribute-based classification performance. (4) Three decision fusions all improved the identification ability for karst wetland vegetation compared to single CNN models, which achieved the highest IoUs of 81.93% and 98.42% for Eichhornia crassipes and Nelumbo nucifera, respectively. (5) One-class FCMs achieved higher classification accuracy for karst wetland vegetation than multi-class FCMs, and the highest improvement in the IoU for karst herbaceous plants reached 22.09%.

Authentication of saffron using 60 MHz 1H NMR spectroscopy

60 MHz proton NMR spectroscopy was used to analyse extracts from saffron spice and a range of potential adulterants and mixtures. Using a simple extraction procedure, good quality spectra were obtained which contain peaks from the characteristic metabolites picrocrocin and crocins, fatty acids and kaempferol. The spectra of samples from trusted suppliers were used to train one-class classification models by SIMCA, nearest neighbour and isolation forest methods. Applying these to spectra of saffron samples purchased from the online marketplace, it was found that 7 out of 33 samples were highly anomalous. From comparison with the spectra of known mixtures and confirmatory spectral analysis using 600 MHz NMR, it is probable that these contain considerable amounts of undisclosed foreign matter.