Unsupervised Model Research Articles

Brazilian banks risk-taking and systemic risk

This study analyzes the marginal contribution of Brazilian banks to the systemic risk. The objective is to identify whether banks that share common characteristics similarly contribute to systemic financial shocks. First, the risk assumed by a sample of listed banks is measured from the accounting, market, and regulatory perspectives. Sample banks were segregated using an unsupervised clustering model. The results were compared with the methodology currently used by the Central Bank of Brazil to segment the banking institutions. Finally, we evaluate the banking groups’ marginal contribution to systemic financial risk using ΔCoVaR. These results suggest that institutions that share similar characteristics in relation to their risk profiles behave similarly during times of greater market stress. Notably, size, geographic diversification, and liquidity were common attributes among banks contributing significantly to systemic risk during financial crises. This study advances the field of banking finance by introducing an analytical framework that goes beyond the traditional focus on bank balance sheet size, aligning with international standards for evaluating the systemic importance of financial institutions.

Identification of eupneic breathing using machine learning.

The diaphragm muscle (DIAm) is the primary inspiratory muscle in mammals. In awake animals, considerable heterogeneity in the electromyographic (EMG) activity of the DIAm reflects varied ventilatory and nonventilatory behaviors. Experiments in awake animals are an essential component to understanding the neuromotor control of breathing, which has especially begun to be appreciated within the last decade. However, insofar as the intent is to study the control of breathing, it is paramount to identify DIAm EMG activity that in fact reflects breathing. Current strategies for doing so in a reproducible, reliable, and efficient fashion are lacking. In the present article, we evaluated DIAm EMG from awake animals using hierarchical clustering across four-dimensional feature space to classify eupneic breathing. Our model, which can be implemented with automated threshold of the clustering dendrogram, successfully identified eupneic breathing with high F1 score (0.92), specificity (0.70), and accuracy (0.88), suggesting that it is a robust and reliable tool for investigating the neural control of breathing.NEW & NOTEWORTHY The heterogeneity of diaphragm muscle (DIAm) activity in awake animals reflects real motor behavior diversity but makes assessments of eupneic breathing challenging. The present article uses an unsupervised machine learning model to identify eupneic breathing amidst a deluge of different DIAm electromyography (EMG) burst patterns in awake rats. This technique offers a scalable and reliable tool that improves efficiency of DIAm EMG analysis and minimizes potential sources of bias.

Remote sensing framework for geological mapping via stacked autoencoders and clustering

Supervised machine learning methods for geological mapping via remote sensing face limitations due to the scarcity of accurately labelled training data that can be addressed by unsupervised learning, such as dimensionality reduction and clustering. Dimensionality reduction methods have the potential to play a crucial role in improving the accuracy of geological maps. Although conventional dimensionality reduction methods may struggle with nonlinear data, unsupervised deep learning models such as autoencoders can model non-linear relationships. Stacked autoencoders feature multiple interconnected layers to capture hierarchical data representations useful for remote sensing data. We present an unsupervised machine learning-based framework for processing remote sensing data using stacked autoencoders for dimensionality reduction and k-means clustering for mapping geological units. We use Landsat 8, ASTER, and Sentinel-2 datasets to evaluate the framework for geological mapping of the Mutawintji region in Western New South Wales, Australia. We also compare stacked autoencoders with principal component analysis (PCA) and canonical autoencoders. Our results reveal that the framework produces accurate and interpretable geological maps, efficiently discriminating rock units. The results reveal that the combination of stacked autoencoders with Sentinel-2 data yields the best performance accuracy when compared to other combinations. We find that stacked autoencoders enable better extraction of complex and hierarchical representation of the input data when compared to canonical autoencoders and PCA. We also find that the generated maps align with prior geological knowledge of the study area while providing novel insights into geological structures.

Triggering dark showers with conditional dual auto-encoders

Abstract We present a family of conditional dual auto-encoders (CoDAEs) for generic and model-independent new physics searches at colliders. New physics signals, which arise from new types of particles and interactions, are considered in our study as anomalies causing deviations in data with respect to expected background events. In this work, we perform a normal-only anomaly detection, which employs only background samples, to search for manifestations of a dark version of strong force applying (variational) auto-encoders on raw detector images, which are large and highly sparse, without leveraging any physics-based pre-processing or strong assumption on the signals. The proposed CoDAE has a dual-encoder design, which is general and can learn an auxiliary yet compact latent space through spatial conditioning, showing a neat improvement over competitive physics-based baselines and related approaches, therefore also reducing the gap with fully supervised models. It is the first time an unsupervised model is shown to exhibit excellent discrimination against multiple dark shower models, illustrating the suitability of this method as an accurate, fast, model-independent algorithm to deploy, e.g. in the real-time event triggering systems of large hadron collider experiments such as ATLAS and CMS.

Discrimination of coal geographical origins through HS-GC-IMS assisted with machine learning algorithms in larceny case

The process of globalization and industrialization has resulted in a rise in the theft of coal and other related products, thereby becoming a focal point for forensic science. This situation has engendered an escalated demand for effective detection and monitoring technologies. The precise identification of coal trace evidence presents a challenge with current methods, owing to its minute quantity, fine texture, and intricate composition. In this study, we integrated machine learning with the identification of volatiles to accurately differentiate coal geographical origins through the application of headspace-gas chromatography-ion mobility spectrometry (HS-GC-IMS). The topographic distribution of volatiles in coals was visually depicted to elucidate the subtle distinctions through spectra and fingerprint analysis. Additionally, four supervised machine learning algorithms were developed to quantitatively predict the geographical origins of natural coals utilizing the HS-GC-IMS dataset, and these were subsequently compared with unsupervised models. Remarkable volatile compounds were identified through the quantitative analysis and optimal Random Forest model, which offered a rapid readout and achieved an average accuracy of 100 % in coal identification. Our findings indicate that the integration of HS-GC-IMS and machine learning is anticipated to enhance the efficiency and accuracy of coal geographical traceability, thereby providing a foundation for litigation and trials.

Software defined networking based network traffic classification using machine learning techniques

The classification of network traffic has become increasingly crucial due to the rapid growth in the number of internet users. Conventional approaches, such as identifying traffic based on port numbers and payload inspection are becoming ineffective due to the dynamic and encrypted nature of modern network traffic. A number of researchers have implemented Software Defined Networking (SDN) based traffic classification using Machine Learning (ML) and Deep Learning (DL) models. However, the studies had various limitations such as encrypted traffic detection, payload inspection, poor detection accuracy, and challenges with testing models both in offline and real-time traffic modes. ML models together with SDN are adopted nowadays to enhance classification performance. In this paper, both supervised (Logistic Regression, Decision Tree, Random Forest, AdaBoost, and Support Vector Machine) and unsupervised (K-means clustering) ML models were used to classify Domain Name System (DNS), Telnet, Ping, and Voice traffic flows simulated using the Distributed Internet Traffic Generator (D-ITG) tool. The use of this tool effectively manages and classifies traffic types based on their application. The study discussed the dataset used, model selection, implementation of the model, and implementation techniques (such as pre-processing, feature extraction, ML algorithm, and model evaluation metrics). The proposed model in SDN was implemented in Mininet for designing the network architecture and generating network traffic. Anaconda Python environment was utilized for traffic classification using various ML techniques. Among the models tested, the Decision Tree supervised learning achieved the highest accuracy of 99.81%, outperforming other supervised and unsupervised learning algorithms. These results indicate that the integration of ML with SDN provides an efficient classification method for identifying and accurately classifying both offline and real-time network traffic, enhanced quality of service (QoS), detection of encrypted packets, deep packet inspection and management.

Unsupervised low-light image enhancement by data augmentation and contrastive learning

ABSTRACT Today, with the increasing demand for visual perception and high-level computational vision tasks, the field of low-light enhancement is rapidly developing. However, models trained on existing datasets often fail or suffer significant performance degradation in real-world low-light scenarios. This performance degradation is frequently due to the limitations of current databases, which typically contain small quantities of paired images of a single type. This article proposes an unsupervised model with a unique data augmentation technique that transforms a regular image database into a paired image database. By adjusting image parameters during training to change exposure, a regular image database can be converted into a paired one. The model restores low-exposure images by extracting lighting features through comparative learning. Evaluations of the LOL and DIV2K datasets demonstrate the proposed model's effectiveness, achieving notable results in low-light image enhancement. This method removes dataset restrictions, broadening the model's range of applications.

An optimal Bayesian strategy for comparing Wiener–Hunt deconvolution models in the absence of ground truth

Abstract This paper considers the quantitative comparison of several alternative models to perform deconvolution in situations where there is no ground truth data available. With applications to very large data sets in mind, we focus on linear deconvolution models based on a Wiener filter. Although comparatively simple, such models are widely prevalent in large scale setting such as high-resolution image restoration because they provide an excellent trade-off between accuracy and computational effort. However, in order to deliver accurate solutions, the models need to be properly calibrated in order to capture the covariance structure of the unknown quantity of interest and of the measurement error. This calibration often requires onerous controlled experiments and extensive expert supervision, as well as regular recalibration procedures. This paper adopts an unsupervised Bayesian statistical approach to model assessment that allows comparing alternative models by using only the observed data, without the need for ground truth data or controlled experiments. Accordingly, the models are quantitatively compared based on their posterior probabilities given the data, which are derived from the marginal likelihoods or evidences of the models. The computation of these evidences is highly non-trivial and this paper consider three different strategies to address this difficulty—a Chib approach, Laplace approximations, and a truncated harmonic expectation—all of which efficiently implemented by using a Gibbs sampling algorithm specialised for this class of models. In addition to enabling unsupervised model selection, the output of the Gibbs sampler can also be used to automatically estimate unknown model parameters such as the variance of the measurement error and the power of the unknown quantity of interest. The proposed strategies are demonstrated on a range of image deconvolution problems, where they are used to compare different modelling choices for the instrument’s point spread function and covariance matrices for the unknown image and for the measurement error.

Advancing anomaly detection in cloud environments with cutting‐edge generative AI for expert systems

AbstractAs artificial intelligence (AI) continues to advance, Generative AI emerges as a transformative force, capable of generating novel content and revolutionizing anomaly detection methodologies. This paper presents CloudGEN, a pioneering approach to anomaly detection in cloud environments by leveraging the potential of Generative Adversarial Networks (GANs) and Convolutional Neural Network (CNN). Our research focuses on developing a state‐of‐the‐art Generative AI‐based anomaly detection system, integrating GANs, deep learning techniques, and adversarial training. We explore unsupervised generative modelling, multi‐modal architectures, and transfer learning to enhance expert systems' anomaly detection systems. We illustrate our approach by dissecting anomalies regarding job performance, network behaviour, and resource utilization in cloud computing environments. The experimental results underscore a notable surge in anomaly detection accuracy with significant development of approximately 11%.

Reproductive Tract Microbial Transitions from Late Gestation to Early Postpartum Using 16S rRNA Metagenetic Profiling in First-Pregnancy Heifers.

Studies in recent years indicate that reproductive tract microbial communities are crucial for shaping mammals' health and reproductive outcomes. Following parturition, uterine bacterial contamination often occurs due to the open cervix, which may lead to postpartum uterine inflammatory diseases, especially in primiparous individuals. However, investigations into spatio-temporal microbial transitions in the reproductive tract of primigravid females remain limited. Our objective was to describe and compare the microbial community compositions in the vagina at late gestation and in the vagina and uterus at early postpartum in first-pregnancy heifers. Three swab samples were collected from 33 first-pregnancy Holstein Friesian heifers: one vaginal sample at gestation day 258 ± 4, and vaginal and uterine samples at postpartum day 7 ± 2. Each sample underwent 16S rRNA V4 region metagenetic analysis via Illumina MiSeq, with bioinformatics following Mothur MiSeq SOP. The reproductive tract bacterial communities were assigned to 1255 genus-level OTUs across 30 phyla. Dominant phyla, accounting for approximately 90% of the communities, included Proteobacteria, Firmicutes, Actinobacteria, Bacteroidetes, and Fusobacteria. However, the results revealed distinct shifts in microbial composition between the prepartum vagina (Vag-pre), postpartum vagina (Vag-post), and postpartum uterus (Utr-post). The Vag-pre and Utr-post microbial profiles were the most distinct. The Utr-post group had lower relative abundances of Proteobacteria but higher abundances of Bacteroidetes, Fusobacteria, and Tenericutes compared to Vag-pre, while Vag-post displayed intermediate values for these phyla, suggesting a transitional profile. Additionally, the Utr-post group exhibited lower bacterial richness and diversity compared to both Vag-pre and Vag-post. The unsupervised probabilistic Dirichlet Multinomial Mixtures model identified two distinct community types: most Vag-pre samples clustered into one type and Utr-post samples into another, while Vag-post samples were distributed evenly between the two. LEfSe analysis revealed distinct microbial profiles at the genus level. Overall, specific microbial markers were associated with anatomical and temporal transitions, revealing a dynamic microbial landscape during the first pregnancy and parturition. These differences highlight the complexity of these ecosystems and open new avenues for research in reproductive biology and microbial ecology.

Phyformer: A degradation physics-informed self-data driven approach to machinery prognostics

Machinery degradation prognostics methods have been suffering the “dilemma” that both physics and data-driven methods have their own limitations. On one hand, constructing accurate close-form mathematical physics models are prohibitively difficult for a complex system. On the other hand, for pure data driven models such as deep learning models, due to the lack of physics guidance, their extrapolation capability decays over time and even yield unexplainable predictions that violate common cognition. Therefore, relaxing the pursuit for the perfect and accurate degradation model, and instead coupling general degradation model with deep learning model, fully leveraging the advantages from both physics-based prognostics and data-driven prognostics, is a promising way to solve the “dilemma”. Driven by this motivation, this paper proposes Phyformer, a general degradation physics-informed self-data-driven method for machinery prognostics. A backbone deep learning model based on auto-correlation and Transformer architecture is developed for time series data prediction. Multiple local physical models that are constructed with data in sliding time windows are embedded into the backbone model in the form of loss function. Only the historical data of the machine itself are used to extrapolate the future, which is significant especially for high-end equipment since their run-to-fail data are scarce. Then the predicted data are mapped to degradation stage by an unsupervised clustering model Gath-Geva adaptively without the requirement of knowing the number of degradation stages in advance. Due to the above nature, Phyformer is high flexibility, easy to be deployed in different applications, working condition-independent and simple. Two typical prognostics tasks are studied, which use direct and indirect condition monitoring data as input, respectively. Comparisons with other state-of-the-art machinery prognostics models show the advances of Phyformer.

MREIFlow: Unsupervised dense and time-continuous optical flow estimation from image and event data

Objectives:We focus on exploring an unsupervised learning-based model which can take advantage of a single image and events to estimate dense and time-continuous optical flow. Methods:We propose a multi-scale optical flow recurrent estimation network, called MREIFlow, which mainly consists of a triplet feature encoder, a feature fusion subnetwork, and a flow iterative decoder. The triplet feature encoder is capable of extracting multi-scale features from a single image and events. The feature fusion subnetwork is designed to integrate spatial–temporal information in features and generate pseudo-features. The flow iterative decoder can perform feature correlation and estimate full-resolution optical flow iteratively in a coarse-to-fine way. We train the network in an unsupervised learning way to avoid using labeled data. In order to provide plentiful and reliable supervisory signals, we design a hierarchical unsupervised learning scheme. In the scheme, the multi-level optimization objectives are designed to supervise network training in different aspects. We also introduce a teacher model to provide auxiliary supervision. Besides, we apply a loss selection strategy to mine promising supervisory signals. Results:Experiments on the MVSEC dataset show that the proposed method achieves remarkable performance under indoor and outdoor circumstances. Compared with previous methods, the proposed method can provide dense and time-continuous optical flow estimation. Conclusion:The proposed network can take advantage of a single image and events to produce dense and time-continuous optical flow estimation, and can be trained through unsupervised learning techniques. However, it requires high computation and memory to guarantee the precision of optical flow. To address this problem, we will explore an efficient and lightweight network architecture in the future.

Reliable multi-modal medical image-to-image translation independent of pixel-wise aligned data.

The current mainstream multi-modal medical image-to-image translation methods face a contradiction. Supervised methods with outstanding performance rely on pixel-wise aligned training data to constrain the model optimization. However, obtaining pixel-wise aligned multi-modal medical image datasets is challenging. Unsupervised methods can be trained without paired data, but their reliability cannot be guaranteed. At present, there is no ideal multi-modal medical image-to-image translation method that can generate reliable translation results without the need for pixel-wise aligned data. This work aims to develop a novel medical image-to-image translation model that is independent of pixel-wise aligned data (MITIA), enabling reliable multi-modal medical image-to-image translation under the condition of misaligned trainingdata. The proposed MITIA model utilizes a prior extraction network composed of a multi-modal medical image registration module and a multi-modal misalignment error detection module to extract pixel-level prior information from training data with misalignment errors to the largest extent. The extracted prior information is then used to construct a regularization term to constrain the optimization of the unsupervised cycle-consistent Generative Adversarial Network model, restricting its solution space and thereby improving the performance and reliability of the generator. We trained the MITIA model using six datasets containing different misalignment errors and two well-aligned datasets. Subsequently, we conducted quantitative analysis using peak signal-to-noise ratio and structural similarity as metrics. Moreover, we compared the proposed method with six other state-of-the-art image-to-image translationmethods. The results of both quantitative analysis and qualitative visual inspection indicate that MITIA achieves superior performance compared to the competing state-of-the-art methods, both on misaligned data and aligned data. Furthermore, MITIA shows more stability in the presence of misalignment errors in the training data, regardless of their severity or type. The proposed method achieves outstanding performance in multi-modal medical image-to-image translation tasks without aligned training data. Due to the difficulty in obtaining pixel-wise aligned data for medical image translation tasks, MITIA is expected to generate significant application value in this scenario compared to existingmethods.

Predicting ultrasound wave stimulated bone growth in bioinspired scaffolds using machine learning

For conditions like osteoporosis, changes in bone pore geometry even when porosity is constant have been shown to correlate to increased fracture risk using techniques such as dual-energy x-ray absorptiometry (DXA) and computed tomography (CT). Additionally, studies have found that bone pore geometry can be characterized by ultrasound to determine fracture risk, since certain pore geometries can cause stress concentration which in turn will be a source for fracture. However, it is not yet fully understood if changes in pore geometry can be detected by ultrasound when the porosity is constant. Therefore, this study develops an unsupervised machine learning model classifying pore geometry between bioinspired and quadrilateral pore scaffolds with constant porosity using experimental ultrasound wave transmission data. Our results demonstrate that differences in pore geometry can be detected by ultrasound, even at constant porosity, and that these differences can be distinguished in an unsupervised manner with machine learning. For traumatic bone injuries and late-stage osteoporosis where fracture occurs, tissue scaffolds are used to aid the healing of fractures or bone loss. The scaffold design is optimized to match material properties closely with bone, and healing can be enhanced with ultrasound stimulation. In this study we predict the combined effects of ultrasound parameters, such as wave frequency and mode of displacement, and scaffold material properties on bone tissue growth. We therefore develop an unsupervised machine learning clustering model of bone tissue growth in the scaffolds using finite element analysis and bone growth algorithms evaluating effects of pore geometry, scaffold materials, ultrasound wave type and frequency, and mesenchymal stem cell distribution on bone tissue growth. The computational predictions of tissue growth agreed within 10% of comparable experimental studies. The data corresponding to pore geometry, mesenchymal stem cell distribution, and scaffold material demonstrate distinct clusters of total bone formation, while ultrasound frequency and mesenchymal stem cell distribution show distinct clusters in bone growth rate. These variables can be tuned to tailor the scaffold design and optimize the required amount and rate of bone growth to meet a patient's specific needs.

Multi-Objective Unsupervised Feature Selection and Cluster Based on Symbiotic Organism Search

Unsupervised learning is a type of machine learning that learns from data without human supervision. Unsupervised feature selection (UFS) is crucial in data analytics, which plays a vital role in enhancing the quality of results and reducing computational complexity in huge feature spaces. The UFS problem has been addressed in several research efforts. Recent studies have witnessed a surge in innovative techniques like nature-inspired algorithms for clustering and UFS problems. However, very few studies consider the UFS problem as a multi-objective problem to find the optimal trade-off between the number of selected features and model accuracy. This paper proposes a multi-objective symbiotic organism search algorithm for unsupervised feature selection (SOSUFS) and a symbiotic organism search-based clustering (SOSC) algorithm to generate the optimal feature subset for more accurate clustering. The efficiency and robustness of the proposed algorithm are investigated on benchmark datasets. The SOSUFS method, combined with SOSC, demonstrated the highest f-measure, whereas the KHCluster method resulted in the lowest f-measure. SOSFS effectively reduced the number of features by more than half. The proposed symbiotic organisms search-based optimal unsupervised feature-selection (SOSUFS) method, along with search-based optimal clustering (SOSC), was identified as the top-performing clustering approach. Following this, the SOSUFS method demonstrated strong performance. In summary, this empirical study indicates that the proposed algorithm significantly surpasses state-of-the-art algorithms in both efficiency and effectiveness. Unsupervised learning in artificial intelligence involves machine-learning techniques that learn from data without human supervision. Unlike supervised learning, unsupervised machine-learning models work with unlabeled data to uncover patterns and insights independently, without explicit guidance or instruction.

Geologically constrained unsupervised dual-branch deep learning algorithm for geochemical anomalies identification

The identification of geochemical anomalies is crucial in mineral exploration. However, the limited sample size, high-dimensional features, and mixed geochemical information make identifying geochemical anomalies a significant challenge. Machine learning algorithms (MLAs), especially those with spatial and spectrum branches, have been proven to be a high efficiency tools for detecting geochemical anomalies related to mineralization. The spatial branch MLAs take two-dimensional images (pixel-patches) as input and mainly capture the spatial characteristics of geochemical patterns. The spectrum branch MLAs take one-dimensional sequence data (pixels) as input and mainly consider the elemental concentration and assemblies. Simultaneously considering the spatial patterns and geochemical concentrations of the geochemical survey data can mitigate geochemical concentration variations arising from objective factors and amplify subtle mineralization anomalies. This study proposes an unsupervised spatial-spectrum autoencoder (AE), namely dual-AE, which consists of a graph convolutional autoencoder (GCN-AE) and a long short-term memory network autoencoder (LSTM-AE) for geochemical anomalies identification. The spatial branch is constructed using the GCN-AE, which can effectively capture spatial geochemical patterns and extract spatial relationships between neighboring pixels. The spectrum branch consists of an LSTM-AE that can study geochemical elemental assemblies within a single pixel. A key ore-controlling factor was added into the dual-AE as a soft constraint to construct a geologically constrained dual-AE. A case study was conducted to recognize geochemical anomalies associated with iron polymetallic mineralization in Southwest Fujian Province, China. The obtained results demonstrated that (1) the unsupervised spatial-spectrum deep learning algorithm serves as a potent method for detecting geochemical anomalies related to mineralization, (2) the geologically constrained unsupervised spatial-spectrum dual-branch model can improve the accuracy and interpretability of geochemical anomaly identification, and (3) the identified anomalous areas can provide essential clues for further mineral exploration.

CARL: Unsupervised Code-Based Adversarial Attacks for Programming Language Models via Reinforcement Learning

Code based adversarial attacks play a crucial role in revealing vulnerabilities of software system. Recently, pre-trained programming language models (PLMs) have demonstrated remarkable success in various significant software engineering tasks, progressively transforming the paradigm of software development. Despite their impressive capabilities, these powerful models are vulnerable to adversarial attacks. Therefore, it is necessary to carefully investigate the robustness and vulnerabilities of the PLMs by means of adversarial attacks. Adversarial attacks entail imperceptible input modifications that cause target models to make incorrect predictions. Existing approaches for attacking PLMs often employ either identifier renaming or the greedy algorithm, which may yield sub-optimal performance or lead to high inference times. In response to these limitations, we propose CARL, an unsupervised black-box attack model that leverages reinforcement learning to generate imperceptible adversarial examples. Specifically, CARL comprises a programming language encoder and a perturbation prediction layer. In order to achieve more effective and efficient attack, we cast the task as a sequence decision-making process, optimizing through policy gradient with a suite of reward functions. We conduct extensive experiments to validate the effectiveness of CARL on code summarization, code translation, and code refinement tasks, covering various programming languages and PLMs. The experimental results demonstrate that CARL surpasses state-of-the-art code attack models, achieving the highest attack success rate across multiple tasks and PLMs while maintaining high attack efficiency, imperceptibility, consistency, and fluency.

Dual-drive RUL prediction of gear transmission systems based on dynamic model and unsupervised domain adaption under zero sample

Gear transmission systems are key components in rotating machinery, and its remaining useful life (RUL) prediction can provide adequate leading time for well-timed maintenance. Existing RUL prediction models usually rely on sufficient training data. However, the acquisition of full life cycle dataset of gear transmission system is difficult or impossible. To solve the problem on the difficult startup and poor generalization of prediction model under zero environment, a dual-drive prediction method based on dynamic model of gear transmission system and unsupervised domain adaptation is proposed in this paper. Firstly, a dynamic model of gear transmission system and growth mechanism of local defect is established to generate full-life cycle simulation data. Then, the multi-scale modulation features are extracted based on simulated and measured data. Furthermore, multi-scale temporal convolution operations are introduced into dual-channel unsupervised domain adaptation model. Besides, a compound principle of reverse truncation and forward expansion principle is investigated to determine the first prediction time. Finally, the validity of the proposed model is verified by two kinds of gearbox data. Ablation experiments are carried out to evaluate the contribution of each module in proposed model. In addition, the effectiveness and generalization ability of proposed model are verified when compared with other advanced transfer learning methods.

Unsupervised learning of charge-discharge cycles from various lithium-ion battery cells to visualize dataset characteristics and to interpret model performance

Machine learning (ML) is a rapidly growing tool even in the lithium-ion battery (LIB) research field. To utilize this tool, more and more datasets have been published. However, applicability of a ML model to different information sources or various LIB cell types has not been well studied. In this paper, an unsupervised learning model called variational autoencoder (VAE) is evaluated with three datasets of charge-discharge cycles with different conditions. The model was first trained with a publicly available dataset of commercial cylindrical cells, and then evaluated with our private datasets of commercial pouch and hand-made coin cells. These cells used different chemistry and were tested with different cycle testers under different purposes, which induces various characteristics to each dataset. We report that researchers can recognise these characteristics with VAE to plan a proper data preprocessing. We also discuss about interpretability of a ML model.

Unsupervised Hybrid Models Integrating Deep Autoencoders and Process Controllers’ Models for Enhanced Process Monitoring and Fault Detection

Unsupervised Hybrid Models Integrating Deep Autoencoders and Process Controllers’ Models for Enhanced Process Monitoring and Fault Detection