Search

The rapid growth of large-scale spatial gene expression data demands efficient and reliable computational tools to extract major trends of gene expression in their native spatial context. Here, we used stability-driven unsupervised learning (i.e., staNMF) to identify principal patterns (PPs) of 3D gene expression profiles and understand spatial gene distribution and anatomical localization at the whole mouse brain level. Our subsequent spatial correlation analysis systematically compared the PPs to known anatomical regions and ontology from the Allen Mouse Brain Atlas using spatial neighborhoods. We demonstrate that our stable and spatially coherent PPs, whose linear combinations accurately approximate the spatial gene data, are highly correlated with combinations of expert-annotated brain regions. These PPs yield a brain ontology based purely on spatial gene expression. Our PP identification approach outperforms principal component analysis and typical clustering algorithms on the same task. Moreover, we show that the stable PPs reveal marked regional imbalance of brainwide genetic architecture, leading to region-specific marker genes and gene coexpression networks. Our findings highlight the advantages of stability-driven machine learning for plausible biological discovery from dense spatial gene expression data, streamlining tasks that are infeasible by conventional manual approaches.

This project aims to mitigate the critical decline in bee populations, essential for crop pollination and food security. With a shortage of taxonomic specialists to identify the vast array of bee species, the project's goal is to enhance the monitoring of population changes through an automated classification system. Utilizing a dataset of bee wing images, the project aims to develop a computational pipeline to identify species based on their unique wing vein patterns. This approach not only supports bee conservation efforts but also expands our understanding of complex geometric variations in nature, offering wider applications in biological research. This poster was presented at the UCSB Data Science Capstone showcase in 2024.

Maintenance records of complex industrial equipment contain a large amount of unstructured data (e.g. technician notes) pertaining to repair actions and associated equipment sub-components, degradation conditions, failure mechanisms, etc. These unstructured data can yield valuable insights to improve the equipment design and maintenance plans, resulting in higher productivity and lower operating costs. Since manual review of information is time-consuming, companies make limited use of the maintenance records. To address this opportunity, we propose a taxonomy-guided method for automatically analysing the unstructured data and inferring critical information, specifically the hierarchy of the equipment's sub-assemblies and constituent parts that malfunctioned or failed during a breakdown event. Our method leverages syntactic (related to word frequency) as well as semantic (related to word co-occurrence and their meaning) knowledge. A novel contribution of our work is that we provide a confidence score for the information inferred by our method. Only the maintenance records which receive a low confidence score will require manual review to confirm the automated method's results, thus ensuring minimal use of human resources. We demonstrate the performance of our method using a real-world data set from equipment used in oil rigs. [ABSTRACT FROM AUTHOR]

Context contributes to multiple aspects of human episodic memory including segmentation and retrieval. The present studies tested if, in adult male and female mice, context influences the encoding of odors encountered in a single unsupervised sampling session of the type used for the routine acquisition of episodic memories. The three paradigms used differed in complexity (single vs. multiple odor cues) and period from sampling to testing. Results show that males consistently encode odors in a context-dependent manner: the mice discriminated novel from previously sampled cues when tested in the chamber of initial cue sampling but not in a distinct yet familiar chamber. This was independent of the interval between cue encounters or the latency from initial sampling to testing. In contrast, female mice acquired both single cues and the elements of multi-cue episodes, but recall of that information was dependent upon the surrounding context only when the cues were presented serially. These results extend the list of episodic memory features expressed by rodents and also introduce a striking and unexpected sex difference in context effects.

The advancement of the computer and information industry has led to the emergence of new demands for multivariate time series anomaly detection (MTSAD) models, namely, the necessity for unsupervised anomaly detection that is both efficient and accurate. However, long-term time series data typically encompass a multitude of intricate temporal pattern variations and noise. Consequently, accurately capturing anomalous patterns within such data and establishing precise and rapid anomaly detection models pose challenging problems. In this paper, we propose a decomposition GAN-based transformer for anomaly detection (DGTAD) in multivariate time series data. Specifically, DGTAD integrates a time series decomposition structure into the original transformer model, further decomposing the extracted global features into deep trend information and seasonal information. On this basis, we improve the attention mechanism, which uses decomposed time-dependent features to change the traditional focus of the transformer, enabling the model to reconstruct anomalies of different types in a targeted manner. This makes it difficult for anomalous data to adapt to these changes, thereby amplifying the anomalous features. Finally, by combining the GAN structure and using multiple generators from different perspectives, we alleviate the mode collapse issue, thereby enhancing the model's generalizability. DGTAD has been validated on nine benchmark datasets, demonstrating significant performance improvements and thus proving its effectiveness in unsupervised anomaly detection. [ABSTRACT FROM AUTHOR]

Upper-limb prostheses are either too expensive for many consumers or have a greatly simplified choice of actions. This research aims to enable an improvement to the quality of life for recipients of these devices by providing an understanding of how we use our hands in modern everyday life. To achieve this a taxonomy of grasps used in activities of daily living has been created. A portable motion capture system was developed to collect data. Thirteen participants' hand movements were recorded (totalling 62 hours and 10 minutes of data). From these data, 38 and 22 grasps were observed from the left and right hands, respectively. The portable system effectively captured natural hand motions, which formed an updated taxonomy of grasps. [ABSTRACT FROM AUTHOR]

Reconstruction of missing seismic traces is one of the key steps in seismic data processing. Deep neural network-based interpolation methods for seismic trace reconstruction have attracted much attention in recent years. However, the currently widely used supervised-based deep neural network interpolation models require the support of labeled data, which is difficult to obtain in real seismic exploration. In this study, we propose a novel unsupervised deep learning interpolation framework SSTI (Self-supervised Seismic Trace Interpolation), designed to address the limitations of existing supervised-based models by avoiding the need of labeled data. SSTI employs a unique combination of two semi-supervised models: temporal ensembling model and mean teacher model. The temporal ensembling model and mean teacher model jointly predict the missing traces by integrating the outputs and weights of each training epoch through Exponential Moving Average method, respectively. Furthermore, a joint loss function that combines consistency loss and self-supervised loss is designed to guide the training process of SSTI. We evaluated the interpolation performance of SSTI on synthetic and field seismic data. Comparative analyses demonstrate that our proposed method outperforms the traditional theory-guided methods in terms of mean square error, peak signal to noise ratio, structural similarity, and quality of the reconstructed traces. Notably, although it does not achieve the interpolation performance of supervised deep learning methods, SSTI has shown great potential since there is only a marginal performance difference between SSTI and supervised-based methods. Our findings suggest that SSTI presents a promising advancement in the field of unsupervised deep learning methods for seismic trace interpolation. The proposed architecture holds great potential for recovering the missing and corrupted traces at a low cost in field seismic exploration. [ABSTRACT FROM AUTHOR]

Design of an automated and continuous framework is of paramount importance to structural health monitoring (SHM). This study proposes an innovative multi-task unsupervised learning method for early assessment of damage in large-scale bridge structures under long-term monitoring. This method entails three main tasks of data cleaning, data partitioning, and anomaly detection. The first task includes discarding missing data and providing outlier-free samples by developing an approach based on the well-known DBSCAN algorithm. Accordingly, this approach enforces the DBSCAN to generate two clusters, one of which contains outlier-free samples and the other one comprises outlier data. In the second task, the outlier-free samples are fed into spectral clustering to partition them into local clusters. Subsequently, a cluster with the maximum cumulative local density is selected as the optimal partition whose features are extracted as the representative data. Finally, local empirical measures under the theory of empirical learning are used to compute anomaly indices for SHM. Long-term modal frequencies of two full-scale bridges are incorporated to verify the proposed method alongside comparative analyses. Results prove that this method can effectively detect damage by providing discriminative anomaly scores and mitigating the negative influences of severe environmental variability. [ABSTRACT FROM AUTHOR]

In the context of the studies of income and wealth distribution, this paper explores evidence to what extent recent monetary policy had distribution effects. This research utilizes the Federal Reserve Board's Survey of Consumer Finances to identify at least two sub populations and follow their dynamics as monetary policy moved from conventional interest rate setting to unconventional Quantitative Easting policy. This is achieved through use of Weighted Expectation Maximization Cluster Modeling, and the Malhalanobis Distance between cluster means. This approach is used to study volatility and bifurcation in distributions of capital gains and incomes to U.S. households through the Financial Crisis and Sars-CoV-2 pandemic. [ABSTRACT FROM AUTHOR]

Fluctuations in oil prices adversely affect decision making situations in which performance forecasting must be combined with realistic price forecasts. In periods of significant price drops, companies may consider extended duration of well shut-ins (i.e. temporarily stopping oil production) for economic reasons. For example, prices during the early days of the Covid-19 pandemic forced operators to consider shutting in all or some of their active wells. In the case of partial shut-in, selection of candidate wells may evolve as a challenging decision problem considering the uncertainties involved. In this study, a mature oil field with a long (50+ years) production history with 170+ wells is considered. Reservoirs with similar conditions face many challenges related to economic sustainability such as frequent maintenance requirements and low production rates. We aimed to solve this decision-making problem through unsupervised machine learning. Average reservoir characteristics at well locations, well production performance statistics and well locations are used as potential features that could characterize similarities and differences among wells. While reservoir characteristics are measured at well locations for the purpose of describing the subsurface reservoir, well performance consists of volumetric rates and pressures, which are frequently measured during oil production. After a multivariate data analysis that explored correlations among parameters, clustering algorithms were used to identify groups of wells that are similar with respect to aforementioned features. Using the field's reservoir simulation model, scenarios of shutting in different groups of wells were simulated. Forecasted reservoir performance for three years was used for economic evaluation that assumed an oil price drop to $30/bbl for 6, 12 or 18 months. Results of economic analysis were analyzed to identify which group(s) of wells should have been shut-in by also considering the sensitivity to different price levels. It was observed that wells can be characterized in the 3-cluster case as low, medium and high performance wells. Analyzing the forecasting scenarios showed that shutting in all or high- and medium-performance wells altogether results in better economic outcomes. The results were most sensitive to the number of active wells and the oil price during the high-price period. This study demonstrated the effectiveness of unsupervised machine learning in well classification for operational decision making purposes. Operating companies may use this approach for improved decision making to select wells for extended shut-in during low oil-price periods. This approach would lead to cost savings especially in mature fields with low-profit margins. [ABSTRACT FROM AUTHOR]

The point cloud keypoint detection algorithm like USIP that uses downsampling first and then fine-tuning the sampling points cannot effectively detect the defect part of the single view defect point cloud, resulting in the inability to output the keypoints of the defect part. Therefore, this paper proposes the twin structure key point detection algorithm named TSKPD based on the idea of contrastive learning, which uses two single-view defect point clouds to synthesize relatively more complete key points for learning, so as to promote the network model to learn the features of the complete point cloud. The robustness of key point detection of point cloud is effectively improved, and the detection of single view defect point cloud is realized. The test results on ModelNet40 and ShapeNet datasets show that the coverage rate of TSKPD on the missing part of the single view defect point cloud is 12.62 higher than the existing optimal algorithm. [ABSTRACT FROM AUTHOR]

We present a new clustering validation technique named: “Hypothesis Learning”. We build our method on three concepts: (1) clustering cohesion, (2) clustering dispersion and, (3) hypothesis quality. The first two notions focus on individual cluster quality. We measure them using a classifier estimating the tightness and separation as a likelihood. The third notion evaluates the complexity of learning the clustering partition. Similar to cohesion and dispersion, we get a likelihood value. Next, we aggregate these three measures to find a single index reporting clustering quality. Previous methods from the literature have already used supervised and unsupervised algorithms and stability concepts to validate clustering solutions. Our motivation is not only to improve these methods but to use learning algorithms in a novel manner to learn key clustering concepts such as cohesion and dispersion. Furthermore, we include a technical discussion on how to regularize a classifier to handle overfit, thus explaining the symbiosis between supervised and unsupervised algorithms. In our experimental setup, we tested “Hypothesis Learning” with a fast classifier, K Nearest Neighbour (KNN). However, in the discussion of the method, we explore other classifiers like CART and Random Forest. The experimental results compare our approach with a similar method and many other well-known clustering indexes. [ABSTRACT FROM AUTHOR]

Schizophrenia is a chronic illness that imposes a significant burden on patients, their families, and the health care system. While it has a substantial genetic component, its heterogeneous nature—both genetic and clinical—limits the ability to identify causal genes and mechanisms. In this study, we analyzed the blood transcriptomes of 398 samples (212 patients with schizophrenia and 186 controls) obtained from five public datasets. We demonstrated this heterogeneity by clustering patients with schizophrenia into two molecular subtypes using an unsupervised machine-learning algorithm. We found that the genes most influential in clustering were enriched in pathways related to the ribosome and ubiquitin-proteasomes system, which are known to be associated with schizophrenia. Based on the expression levels of these genes, we developed a logistic regression model capable of predicting schizophrenia samples in unrelated datasets with a positive predictive value of 64% (p value = 0.039). In the future, integrating blood transcriptomics with clinical characteristics may enable the definition of distinct molecular subtypes, leading to a better understanding of schizophrenia pathophysiology and aiding in the development of personalized drugs and treatment options. [ABSTRACT FROM AUTHOR]

Urban green spaces play indispensable roles in various aspects, including the urban soil environment, thermal environment, and human environment. Accurately capturing characteristics such as the spatial distribution of urban green spaces is essential for effective planning, construction, and assessment of green space, and it represents a focal point in urban ecological research. Leveraging its remarkable self-learning capability, deep learning has emerged as a prominent research direction for extracting urban green space features. However, given the diverse range of deep learning methods and the unique features of urban green spaces, the next focus will be on how to exploit more effectively and apply the advantages of deep learning to advance the survey of urban green spaces. Therefore, this study comprehensively reviews a large body of relevant literature, categorizing deep learning methods applied to urban green space extraction into supervised, unsupervised, and semi-supervised learning approaches. It systematically summarizes the technical foundations, research progress, and applicable public datasets in this field, provides a reasoned outlook on future directions, and aims to provide geographers and urban planners with a comprehensive and scientifically grounded reference. [ABSTRACT FROM AUTHOR]

Image restoration is a critical task in computer vision that involves recovering an original image from corrupted or damaged versions of it. Traditional image restoration relies on interpolation and completion techniques, such as Navier–Stokes equations and the fast multipole boundary element method. However, these methods often fail to capture the advanced semantic information of an image, leading to inaccurate restoration results. In recent years, generative adversarial networks (GANs) have emerged as a practical approach in computer vision for image restoration tasks, as they can address image restoration issues related to damaged or missing image information. GANs are a deep‐learning network structure with a generator and discriminator. In image restoration, the generator is employed to restore damaged images, and the discriminator is used to assess the authenticity of the repair results. Competition between the generator and discriminator improves the quality of the repair results. This study proposes a novel generative image restoration method that utilizes contextual and perceptual semantic information mechanisms to strengthen GANs. Our approach demonstrates the effectiveness of GANs in restoring images through learning how to fuse the missing or damaged parts of an image with the undamaged parts surrounding them, resulting in visually appealing restoration results. [ABSTRACT FROM AUTHOR]

We describe a system for identifying dog emotions based on dogs' facial expressions and body posture. Towards that goal, we built a dataset with 2184 images of ten popular dog breeds, grouped into seven similarly sized primal mammalian emotion categories defined by neuroscientist and psychobiologist Jaak Panksepp as 'Exploring', 'Sadness', 'Playing', 'Rage', 'Fear', 'Affectionate' and 'Lust'. We modified the contrastive learning framework MoCo (Momentum Contrast for Unsupervised Visual Representation Learning) to train it on our original dataset and achieved an accuracy of 43.2% and a baseline of 14%. We also trained this model on a second publicly available dataset that resulted in an accuracy of 48.46% but had a baseline of 25%. We compared our unsupervised approach with a supervised model based on a ResNet50 architecture. This model, when tested on our dataset with the seven Panksepp labels, resulted in an accuracy of 74.32% [ABSTRACT FROM AUTHOR]

In recent years, there has been a growing interest in leveraging deep learning and neural networks to address scientific problems, particularly in solving partial differential equations (PDEs). However, many neural network-based methods like PINNs rely on auto differentiation and sampling collocation points, leading to a lack of interpretability and lower accuracy than traditional numerical methods. As a result, we propose a fully unsupervised approach, requiring no training data, to estimate finite difference solutions for PDEs directly via small linear convolutional neural networks. Our proposed approach uses substantially fewer parameters than similar finite difference-based approaches while also demonstrating comparable accuracy to the true solution for several selected elliptic and parabolic problems compared to the finite difference method. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions Pneumonia, a major infectious cause of morbidity and mortality among children worldwide, is typically diagnosed using low‐dose pediatric chest X‐ray [CXR (chest radiography)]. In pediatric CXR images, bone occlusion leads to a risk of missed diagnosis. Deep learning–based bone‐suppression networks relying on training data have enabled considerable progress to be achieved in bone suppression in adult CXR images; however, these networks have poor generalizability to pediatric CXR images because of the lack of labeled pediatric CXR images (i.e., bone images vs. soft‐tissue images). Dual‐energy subtraction imaging approaches are capable of producing labeled adult CXR images; however, their application is limited because they require specialized equipment, and they are infrequently employed in pediatric settings. Traditional image processing–based models can be used to label pediatric CXR images, but they are semiautomatic and have suboptimal performance.We developed an efficient labeling approach for fine‐tuning pediatric CXR bone‐suppression networks capable of automatically suppressing bone structures in CXR images for pediatric patients without the need for specialized equipment and technologist training.Three steps were employed to label pediatric CXR images and fine‐tune pediatric bone‐suppression networks: distance transform–based bone‐edge detection, traditional image processing–based bone suppression, and fully automated pediatric bone suppression. In distance transform–based bone‐edge detection, bone edges were automatically detected by predicting bone‐edge distance‐transform images, which were then used as inputs in traditional image processing. In this processing, pediatric CXR images were labeled by obtaining bone images through a series of traditional image processing techniques. Finally, the pediatric bone‐suppression network was fine‐tuned using the labeled pediatric CXR images. This network was initially pretrained on a public adult dataset comprising 240 adult CXR images (A240) and then fine‐tuned and validated on 40 pediatric CXR images (P260_40labeled) from our customized dataset (named P260) through five‐fold cross‐validation; finally, the network was tested on 220 pediatric CXR images (P260_220unlabeled dataset).The distance transform–based bone‐edge detection network achieved a mean boundary distance of 1.029. Moreover, the traditional image processing–based bone‐suppression model obtained bone images exhibiting a relative Weber contrast of 93.0%. Finally, the fully automated pediatric bone‐suppression network achieved a relative mean absolute error of 3.38%, a peak signal‐to‐noise ratio of 35.5 dB, a structural similarity index measure of 98.1%, and a bone‐suppression ratio of 90.1% on P260_40labeled.The proposed fully automated pediatric bone‐suppression network, together with the proposed distance transform–based bone‐edge detection network, can automatically acquire bone and soft‐tissue images solely from CXR images for pediatric patients and has the potential to help diagnose pneumonia in children. [ABSTRACT FROM AUTHOR]

Unsupervised anomaly detection, often approached as a one‐class classification problem, is a critical task in computer vision. Knowledge distillation has emerged as a promising technique for enhancing anomaly detection accuracy, especially with the advent of reverse distillation networks that employ encoder–decoder architectures. This study introduces a novel reverse knowledge distillation framework known as RDMS, which incorporates a pretrained teacher encoding module, a multi‐level feature fusion connection module, and a student decoding module consisting of three independent decoders. RDMS is designed to distill distinct features from the teacher encoder, mitigating overfitting issues associated with similar or identical teacher–student structures. The model achieves an average of 99.3%$\%$ image‐level AUROC and 98.34%$\%$ pixel‐level AUROC on the MVTec‐AD dataset and demonstrates state‐of‐the‐art performance on the more challenging BTAD dataset. The RDMS model's high accuracy in anomaly detection and localization underscores the potential of multi‐student reverse distillation to advance unsupervised anomaly detection capabilities. The source code is available at https://github.com/zihengchen777/RDMS [ABSTRACT FROM AUTHOR]

Manufacturing companies focus on improving productivity, reducing costs, and aligning performance metrics with strategic objectives. In industries like paper manufacturing, minimizing equipment downtime is essential for maintaining high throughput. Leveraging the extensive data generated by these facilities offers opportunities for gaining competitive advantages through data-driven insights, revealing trends, patterns, and predicting future performance indicators like unplanned downtime length, which is essential in optimizing maintenance and minimizing potential losses. This paper explores statistical and machine learning techniques for modeling downtime length probability distributions and correlation with machine vibration measurements. We proposed a novel framework, employing advanced data-driven techniques like artificial neural networks (ANNs) to estimate parameters of probability distributions governing downtime lengths. Our approach specifically focuses on modeling parameters of these distribution, rather than directly modeling probability density function (PDF) values, as is common in other approaches. Experimental results indicate a significant performance boost, with the proposed method achieving up to 30% superior performance in modeling the distribution of downtime lengths compared to alternative methods. Moreover, this method facilitates unsupervised training, making it suitable for big data repositories of unlabelled data. The framework allows for potential expansion by incorporating additional input variables. In this study, machine vibration velocity measurements are selected for further investigation. The study underscores the potential of advanced data-driven techniques to enables companies to make better-informed decisions regarding their current maintenance practices and to direct improvement programs in industrial settings. [ABSTRACT FROM AUTHOR]

The use of decision trees for obtaining and representing clustering solutions is advantageous, due to their interpretability property. We propose a method called Decision Trees for Axis Unimodal Clustering (DTAUC), which constructs unsupervised binary decision trees for clustering by exploiting the concept of unimodality. Unimodality is a key property indicating the grouping behavior of data around a single density mode. Our approach is based on the notion of an axis unimodal cluster: a cluster where all features are unimodal, i.e., the set of values of each feature is unimodal as decided by a unimodality test. The proposed method follows the typical top-down splitting paradigm for building axis-aligned decision trees and aims to partition the initial dataset into axis unimodal clusters by applying thresholding on multimodal features. To determine the decision rule at each node, we propose a criterion that combines unimodality and separation. The method automatically terminates when all clusters are axis unimodal. Unlike typical decision tree methods, DTAUC does not require user-defined hyperparameters, such as maximum tree depth or the minimum number of points per leaf, except for the significance level of the unimodality test. Comparative experimental results on various synthetic and real datasets indicate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Echocardiography is a widely used, non-invasive imaging technique for diagnosing and monitoring heart conditions. However, accurate segmentation of cardiac structures, particularly the left ventricle, remains a complex task due to the inherent variability and noise in echocardiographic images. Current supervised models have achieved state-of-the-art results but are highly dependent on large, annotated datasets, which are costly and time-consuming to obtain and depend on the quality of the annotated data. These limitations motivate the need for unsupervised methods that can generalize across different image conditions without relying on annotated data. In this study, we propose an unsupervised approach for segmenting 2D echocardiographic images. By combining customized objective functions with convolutional neural networks (CNNs), our method effectively segments cardiac structures, addressing the challenges posed by low-resolution and gray-scale images. Our approach leverages techniques traditionally used outside of medical imaging, optimizing feature extraction through CNNs in a data-driven manner and with a new and smaller network design. Another key contribution of this work is the introduction of a post-processing algorithm that refines the segmentation to isolate the left ventricle in both diastolic and systolic positions, enabling the calculation of the ejection fraction (EF). This calculation serves as a benchmark for evaluating the performance of our unsupervised method. Our results demonstrate the potential of unsupervised learning to improve echocardiogram analysis by overcoming the limitations of supervised approaches, particularly in settings where labeled data are scarce or unavailable. [ABSTRACT FROM AUTHOR]

The identification of key nodes in complex networks is an important topic in many network science areas. It is vital to a variety of real-world applications, including viral marketing, epidemic spreading and influence maximization. In recent years, machine learning algorithms have proven to outperform the conventional, centrality-based methods in accuracy and consistency, but this approach still requires further refinement. What information about the influencers can be extracted from the network? How can we precisely obtain the labels required for training? Can these models generalize well? In this paper, we answer these questions by presenting an enhanced machine learning-based framework for the influence spread problem. We focus on identifying key nodes for the Independent Cascade model, which is a popular reference method. Our main contribution is an improved process of obtaining the labels required for training by introducing "Smart Bins" and proving their advantage over known methods. Next, we show that our methodology allows ML models to not only predict the influence of a given node, but to also determine other characteristics of the spreading process—which is another novelty to the relevant literature. Finally, we extensively test our framework and its ability to generalize beyond complex networks of different types and sizes, gaining important insight into the properties of these methods. [ABSTRACT FROM AUTHOR]

Multi-view clustering aims to explore the feature information of objects from multiple perspectives to obtain accurate clustering results. However, existing research often fails to handle the information conflicts that arise during view fusion and does not fully utilize the complementary information between multiple views. To address these issues, this paper proposed a self-supervised multi-view clustering model guided by multi-angle semantic labels. The model first mapped the latent representations of each view to independent low-dimensional feature spaces, focusing on optimizing the consistency between views in one space to maintain the local structure of the feature space and the relative relationships between samples. At the same time, in another space, clustering information was directly extracted from the view level to capture richer and more diverse semantic features. Finally, pseudo-labels generated from multi-angle semantic features guided the clustering assignment at the object level, achieving collaborative optimization of the two representations. Extensive experimental results demonstrate that this approach can comprehensively explore both common and complementary information in multi-view data and exhibit good clustering performance. Moreover, compared to other methods, this approach has advantages in scenarios with a larger number of views. [ABSTRACT FROM AUTHOR]

The status of production equipment in industries is prone to change due to various factors. Thus, a proper anomaly detection procedure for equipment is indispensable. Supervised learning is commonly used in equipment state monitoring. However, these approaches need much manpower and time to obtain sufficient labeled data. In contrast to the technique, unsupervised learning-based Autoencoder, which learns from unlabeled datasets to discover patterns without human supervision, has recently demonstrated its promising performance in anomaly detection. Based on this advantage, this paper proposes the tool performance estimation (TPE) scheme to clearly detect abnormalities of any machinery equipment in industries. Through the collaborative interaction among four well-designed modules: AE (Autoencoder), PO (parameter optimization), RE (reconstruction error), and DI (deviation indicator), TPE defines three systematic and generic troubleshooting scenarios: (i) equipment, (ii) parameters, and (iii) others, by analyzing the severity of RE and DI. TPE is proven to immediately remind users to troubleshoot when abnormalities occur during production. In example 1, TPE has the best accuracy among benchmark methods. In example 2, TPE saves 33.9 % of productivity and a 34-day earlier warning to prevent production from shutting down. [ABSTRACT FROM AUTHOR]

The recent acceleration in genome sequencing targeting previously unexplored parts of the tree of life presents computational challenges. Samples collected from the wild often contain sequences from several organisms, including the target, its cobionts, and contaminants. Effective methods are therefore needed to separate sequences. Though advances in sequencing technology make this task easier, it remains difficult to taxonomically assign sequences from eukaryotic taxa that are not well represented in databases. Therefore, reference-based methods alone are insufficient. Here, I examine how we can take advantage of differences in sequence composition between organisms to identify symbionts, parasites, and contaminants in samples, with minimal reliance on reference data. To this end, I explore data from the Darwin Tree of Life project, including hundreds of high-quality HiFi read sets from insects. Visualizing two-dimensional representations of read tetranucleotide composition learned by a variational autoencoder can reveal distinct components of a sample. Annotating the embeddings with additional information, such as coding density, estimated coverage, or taxonomic labels allows rapid assessment of the contents of a dataset. The approach scales to millions of sequences, making it possible to explore unassembled read sets, even for large genomes. Combined with interactive visualization tools, it allows a large fraction of cobionts reported by reference-based screening to be identified. Crucially, it also facilitates retrieving genomes for which suitable reference data are absent. [ABSTRACT FROM AUTHOR]