Automatic classification with an autoencoder of seismic signals on a distributed acoustic sensing cable

Collaborative knowledge amalgamation: Preserving discriminability and transferability in unsupervised learning

Robust unsupervised feature learning is a critical yet tough task for synthetic aperture radar (SAR) automatic target recognition (ATR) with limited labeled data. The developing contrastive self-supervised learning (CSL) method, which learns informative representations by solving an instance discrimination task, provides a novel method for learning discriminative features from unlabeled SAR images. However, the instance-level contrastive loss can magnify the differences between samples belonging to the same class in the latent feature space. Therefore, CSL can dispel these targets from the same class and affect the downstream classification tasks. In order to address this problem, this paper proposes a novel framework called locality preserving property constrained contrastive learning (LPPCL), which not only learns informative representations of data but also preserves the local similarity property in the latent feature space. In LPPCL, the traditional InfoNCE loss of the CSL models is reformulated in a cross-entropy form where the local similarity of the original data is embedded as pseudo labels. Furthermore, the traditional two-branch CSL architecture is extended to a multi-branch structure, improving the robustness of models trained with limited batch sizes and samples. Finally, the self-attentive pooling module is used to replace the global average pooling layer that is commonly used in most of the standard encoders, which provides an adaptive method for retaining information that benefits downstream tasks during the pooling procedure and significantly improves the performance of the model. Validation and ablation experiments using MSTAR datasets found that the proposed framework outperformed the classic CSL method and achieved state-of-the-art (SOTA) results.

Anchor link prediction exacerbates the risk of privacy leakage via the de-anonymization of social network data. Embedding-based methods for anchor link prediction are limited by the excessive similarity of the associated nodes in a latent feature space and the variation between latent feature spaces caused by the semantics of different networks. In this article, we propose a novel method which reduces the impact of semantic discrepancies between different networks in the latent feature space. The proposed method consists of two phases. First, graph embedding focuses on the network structural roles of nodes and increases the distinction between the associated nodes in the embedding space. Second, a federated adversarial learning framework which performs graph embedding on each social network and an adversarial learning model on the server according to the observable anchor links is used to associate independent graph embedding approaches on different social networks. The combination of distinction enhancement and the association of graph embedding approaches alleviates variance between the latent feature spaces caused by the semantics of different social networks. Extensive experiments on real social networks demonstrate that the proposed method significantly outperforms the state-of-the-art methods in terms of both precision and robustness.

Anomaly detection in videos is challenging due to the scarcity and variance in positive samples. Current anomaly detection methods can be categorized into reconstruction models and future frame prediction-based models. However, reconstruction models might be exceptionally adapted to abnormal events due to the learning capacity and generalization ability of deep neural networks, whereas prediction-based methods can be sensitive to noise. In this study, we propose an anomaly detection model based on the latent feature space, which combines advantages from both sides. We argue that the constraints in the latent feature space can promote reconstruction; moreover, the optical flow is also considered to introduce temporal information. We use SPyNet for accurate and efficient optical flow estimation. We extensively validate our method on the UCSD Ped1, UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets. The results demonstrated the feasibility of the proposed method and the benefit of utilizing information in the latent feature space.

This study aimed to assess the impact and vulnerability of climate change by classifying 26 clusters of meteorologically homogeneous regions. To determine the optimal clustering method, both K-means and Gaussian Mixture Model (GMM) clustering were analyzed using the effective storage capacity to watershed area ratio. The optimal number of clusters was derived based on several evaluation metrics, including the Silhouette Score, Calinski-Harabasz Index, Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). Ultimately, GMM clustering was identified as the optimal method, with the best clustering results obtained at k = 4 for an effective storage capacity of 100,000 to 400,000 tons and k = 5 for an effective storage capacity of 400,000 to 10,000,000 tons. Additionally, standard reservoirs applicable to agricultural production infrastructure design standards were identified based on homogeneous weather region clusters, the optimal clustering method, and centroid results. The findings of this study can serve as fundamental data for the development and revision of design standards, contributing to more climate-resilient agricultural infrastructure.

We introduce a method based on Gaussian mixture model (GMM) clustering and level-set to automatically detect intraretina fluid on diabetic retinopathy (DR) from spectral domain optical coherence tomography (SD-OCT) images in this paper. First, each B-scan is segmented using GMM clustering. The original clustering results are refined using location and thickness information. Then, the spatial information among every consecutive five B-scans is used to search potential fluid. Finally, the improved level-set method is used to obtain the accurate boundaries. The high sensitivity and accuracy demonstrated here show its potential for detection of fluid.

Chapter 2 - Computational intelligence in healthcare and biosignal processing

Attributed graph clustering is a basic yet essential method for graph data exploration. Recent efforts over graph contrastive learning have achieved impressive clustering performance. However, we observe that the commonly adopted InfoMax operation tends to capture redundant information, limiting the downstream clustering performance. To this end, we develop a novel method termed attributed graph clustering with dual redundancy reduction (AGC-DRR) to reduce the information redundancy in both input space and latent feature space. Specifically, for the input space redundancy reduction, we introduce an adversarial learning mechanism to adaptively learn a redundant edge-dropping matrix to ensure the diversity of the compared sample pairs. To reduce the redundancy in the latent space, we force the correlation matrix of the cross-augmentation sample embedding to approximate an identity matrix. Consequently, the learned network is forced to be robust against perturbation while discriminative against different samples. Extensive experiments have demonstrated that AGC-DRR outperforms the state-of-the-art clustering methods on most of our benchmarks. The corresponding code is available at https://github.com/gongleii/AGC-DRR.

Deep expectation-maximization network for unsupervised image segmentation and clustering

We present an approach to explain the decisions of black box models for image classification. While using the black box to label images, our explanation method exploits the latent feature space learned through an adversarial autoencoder. The proposed method first generates exemplar images in the latent feature space and learns a decision tree classifier. Then, it selects and decodes exemplars respecting local decision rules. Finally, it visualizes them in a manner that shows to the user how the exemplars can be modified to either stay within their class, or to become counter-factuals by “morphing” into another class. Since we focus on black box decision systems for image classification, the explanation obtained from the exemplars also provides a saliency map highlighting the areas of the image that contribute to its classification, and areas of the image that push it into another class. We present the results of an experimental evaluation on three datasets and two black box models. Besides providing the most useful and interpretable explanations, we show that the proposed method outperforms existing explainers in terms of fidelity, relevance, coherence, and stability.

Clinical and biological information in large datasets of gene expression across cancers could be tapped with unsupervised deep learning. However, difficulties associated with biological interpretability and methodological robustness have made this impractical. Here we describe an unsupervised deep-learning framework for the generation of low-dimensional latent spaces for gene-expression data from 50,211 transcriptomes across 18 human cancers. The framework, which we named DeepProfile, outperformed dimensionality-reduction methods with respect to biological interpretability and allowed us to unveil that genes that are universally important in defining latent spaces across cancer types control immune cell activation, whereas cancer-type-specific genes and pathways define molecular disease subtypes. By linking latent variables in DeepProfile to secondary characteristics of tumours, we discovered that mutation burden is closely associated with the expression of cell-cycle-related genes, and that the activity of biological pathways for DNA-mismatch repair and MHC class II antigen presentation are consistently associated with patient survival. We also found that tumour-associated macrophages are a source of survival-correlated MHC class II transcripts. Unsupervised learning can facilitate the discovery of biological insight from gene-expression data.

To meet the needs of practical applications, current deep learning-based methods focus on using a single model to handle JPEG images with different compression qualities, while few of them consider the auxiliary effects of the compression quality information. Recently, several methods estimate quality factors in a supervised learning manner to guide their network to remove JPEG artifacts. However, they may fail to estimate unseen compression types, affecting the subsequent restoration performance. To remedy this issue, we propose an unsupervised compression quality representation learning strategy for the blind JPEG artifacts removal. Specifically, we utilize contrastive learning to obtain discriminative compression quality representations in the latent feature space. Then, to fully exploit the learned representations, we design a compression-guided blind JPEG artifacts removal network, which integrates the discriminative compression quality representations in an information lossless way. In this way, our single network can flexibly handle various JPEG compression images. Experiments demonstrate that our method can adapt to different compression qualities to obtain discriminative representations and outperform state-of-art methods.KeywordsJPEG Artifacts RemovalUnsupervised representation learningContrastive learningImage restoration

A unified framework for visual domain adaptation with covariance matching

Hydrogenerators are strategic assets for power utilities. Their reliability and availability can lead to significant benefits. For decades, monitoring and diagnosis of hydrogenerators have been at the core of maintenance strategies. The main cause of hydrogenerator breakdown comes from failure of its high voltage stator, which is a major component of hydrogenerators. In our previous study, it was shown that more than 85% of stator failure mechanisms indicate the presence of Partial Discharges (PD) activity. PD are minute sparks that occur within voids inside high voltage insulation or in the air around the insulating system. Each PD event does not cause immediate failure, but it will slowly erode the insulation system and will lead to breakdown in years to decades. PD signal can be detected from the lead of the hydrogenerator while it is running, thus allowing for on-line diagnosis. Hydro-Québec has been collecting more than 33.000 unlabeled PD measurement files over the last decades including two types of measurement instruments. One of the instruments used is the Partial Discharge Analyzer (PDA). PDs have several different sources and each source is characterized by a specific signature. It is therefore essential to be able to automatically recognize the nature of the DPs in order to anticipate possible degradation. Expert rules to characterize these PD signals exist but these rules cannot be used as an automatic classification tool. Indeed, for certain ambiguous cases (conflict between classes) or the presence of several signatures at the same time (multi-classes), the expert's judgement remains essential.
 A Variationel AutoEncoder (VAE) is used for dimension reduction and projection into a 2D latent space to analyze the training data and then classify it. The 2D latent space of the VAE allows the data space to be restructured and reorganized to anticipate the performance of the classifier. The problem is how to optimize this latent space and thus obtain the best distribution of the different sources of PDs to maximize the chances of good responses from the classifier? To our knowledge, there is currently no method in the literature that clearly answers this question. What is certain, however, is that the optimization of the VAE learning is directly related to the quality of the learning base, i.e. a large size and a perfectly balanced database (all the cases are present and sufficiently represented). The objective of this paper is to compare the quality of the latent space obtained from the experts' rules with a latent space obtained directly from the input signal in an « End-to-End » approach.
 The first method concerns an original unsupervised deep learning method for PD recognition. Instead of labelling the PD measurement files by the expert for a supervised learning process, we use the rules developed by the experts of Hydro-Québec to create a feature vector from recognizable PD signatures. Indeed, labelling a sufficient quantity of signatures for a supervised approach is very time-consuming and therefore cannot be implemented. This is a common problem in the industry where more and more operational data is available but cannot be labelled by experts, who are busy with other tasks. Expert knowledge is then injected into a characteristic and feature vector. In the second method, several Generative Adversarial Networks (GANs) associated with several types of PDs are thus used to generate artificial signals in order to increase the size of the learning base and especially to balance it. A new latent space is thus obtained from the learning of the VAE exclusively carried out on data generated by the GANs.
 Validation tests based on the 33,000 measurements with metrics for evaluating the performances of the various latent spaces are used.

The transportation-disadvantaged population is rapidly increasing through aging; moreover, the mobility of the elderly has increased due to life expectancy improvements and lifestyle changes. To respond to these changes, a customized mobility service specifically tailored to the travel patterns of the elderly was developed in this study. In particular, an autonomous shuttle service that can improve the operational efficiency and the accessibility of existing transportation methods was proposed by considering the travel characteristics of elderly people, who mainly travel short distances. To this end, a study was conducted in Seongnam City, Republic of Korea, where mobility support services for the elderly are insufficient. Using smart card data, the elderly were classified according to their travel patterns, with autonomous shuttle routes suggested for each travel purpose. We derived four clusters via the Gaussian mixture model clustering, with travel purposes classified according to the spatiotemporal travel patterns. Finally, the major routes for each travel purpose were selected, and feasible road paths for autonomous shuttle operation were suggested using the concept of ODD (operational design domain). This holistic methodology is expected to contribute to the development of autonomous mobility services for the elderly and for the establishment of welfare policies based on the smart card data.