Feature Representation Learning Research Articles

Network architecture search methods for constructing efficient fault diagnosis models in rotating machinery

Abstract The development of high-performance fault diagnosis models for specific tasks requires substantial expertise. Neural Architecture Search (NAS) offers a promising solution, but most NAS methodologies are hampered by lengthy search durations and low efficiency, and few researchers have applied these methods within the fault diagnosis domain. This paper introduces a novel differentiable architecture search (DARTS) method tailored for constructing efficient fault diagnosis models for rotating machinery, designed to rapidly and effectively search for network models suitable for specific datasets. Specifically, this study constructs a completely new and advanced search space, incorporating various efficient, lightweight convolutional operations to reduce computational complexity. To enhance the stability of the differentiable network architecture search process and reduce fluctuations in model accuracy, this study proposes a novel Multi-scale Pyramid Squeeze Attention (MPSA) module. This module aids in the learning of richer multi-scale feature representations and adaptively recalibrates the weights of multi-dimensional channel attention. The proposed method was validated on two rotating machinery fault datasets, demonstrating superior performance compared to manually designed networks and general network search methods, with notably improved diagnostic effectiveness.

High-Order Multimodal Interaction Network for Efficient Prediction of Drug-Drug Interaction

The pharmaceutical industry places a lot of focus on preventing drug-drug interactions (DDIs). Medication interaction detection has been the primary emphasis of machine learning-based DDI prediction methods. Since studies have shown that DDIs can cause different future occurrences, it is more beneficial to predict DDI connected events while examining the mechanism behind combination medicine consumption or adverse reactions. The areas of medication development and illness diagnostics are seeing increased usage of a developing approach that predicts DDIs-associated occurrences. We examine potential interactions between the two medications as well as the kinds of interactions that can occur in this research. Additionally, we provide a strategy that relies on learning and use High-Order Multimodal Interaction Network (HOMIN) to forecast DDIs by learning feature representations. The purpose of this work is to provide HOMIN-DDI, a new method for drug-drug interaction predictions that we have developed utilizing a HOMIN architecture. First, we develop feature vectors from medication categories, targets, paths, and digestive enzymes, and we use the Jaccard similarity to evaluate how similar drugs appear. After that, we build a new HOMIN using the feature representation to predict DDIs. The results of the experiments show that the drug categories feature type, when used to the HOMIN -DDI approach, is effective. Furthermore, compared to employing only one feature, combining numerous features yields more useful and informative results. Compared to other algorithms, HOMIN-DDI performs better when it comes to predicting DDIs.

Enhancing machine learning recommendation systems with CNN architectures: Applications and innovations in computer vision and speech recognition

Abstract. This paper provides an in-depth analysis of enhancing machine learning recommendation systems using Convolutional Neural Network (CNN) architectures, with a focus on their applications in computer vision and speech recognition. Traditional recommendation systems often struggle with scalability and the complexity of high-dimensional data. By integrating CNNs, these systems can utilize advanced feature extraction and representation learning to more effectively process and analyze diverse data sources. Our study demonstrates significant improvements in recommendation accuracy and personalization through CNN-enhanced systems. We discuss the architecture, design principles, and advantages of CNNs, supported by case studies across various domains. Our findings illustrate the potential of CNNs to revolutionize recommendation systems by addressing existing limitations and offering innovative solutions for real-time, high-quality recommendations. This research emphasizes the importance of advanced machine learning techniques in creating robust and scalable recommendation systems, paving the way for future advancements and applications in multiple fields.

Edge Detection of Source Body from Magnetic Anomaly Based on ResNet

Utilizing magnetic anomaly data for effective edge detection of source bodies can provide crucial evidence for the delineation of geological units and the division of fault structures. However, the existing edge detection methods of source bodies from magnetic anomalies are influenced by factors such as the source bodies’ burial depth, magnetization direction, and mutual interference of magnetic anomalies, leading to errors in subsequent interpretation tasks. The advanced convolutional neural network possesses robust capabilities for feature representation and deep learning, prompting this paper to introduce an edge detection method for source bodies based on convolutional neural networks. The issue is initially framed as a semantic segmentation problem, and four network architectures aimed at edge detection of a source body from magnetic anomaly are designed and modified based on the U-Net and ResNet. Subsequently, a multitude of high-quality sample data sets are constructed using models with varying locations, scales, quantities, and physical properties to train the network. This paper then details model experiments that escalate from simple to complex, taking into account the combined effects of burial depth and inclined magnetization on edge detection. Compared to conventional edge detection methods, the method proposed in this paper is shown to accurately identify edges of source bodies at various depths with little impact from inclined magnetization and can automatically extract edge information without manual intervention. The method’s efficacy is corroborated through real data tests.

Enhanced landslide susceptibility mapping in data-scarce regions via unsupervised few-shot learning

Given the critical need to assess landslide hazards, producing landslide susceptibility map (LSM) in regions with scarce historical landslide inventories poses significant challenges. This study introduces a novel landslide susceptibility assessment framework that combines unsupervised learning strategies with few-shot learning methods to increase the accuracy of LSM in these areas. The framework has been practically validated in a representative geological disaster-prone area along the West-East Gas Pipeline in Shaanxi Province, China. We employed three advanced few-shot learning models: a support vector machine, meta-learning, and transfer learning. These models implement feature representation learning for weakly correlated influencing factors through an unsupervised approach, thereby constructing an effective landslide susceptibility assessment model. We compared traditional learning methods and used the receiver operating characteristic (ROC) curve and SHAP values to quantify the effectiveness of the models. The results indicate that the meta-learning algorithm outperforms both the SVM and transfer learning in areas with limited landslide data. The integration of unsupervised strategies significantly improves performance, achieving area under the curve (AUC) values of 0.9385 and 0.9861, respectively. Compared with using meta-learning alone, incorporating unsupervised learning strategies increased the AUC by 4.76%, enhancing both the predictive power of the model and the interpretability of the features. Meta-learning under unsupervised conditions effectively mitigates the evaluation difficulties caused by insufficient landslide records, providing a viable path and empirical evidence for performance improvement in similar data- scarce regions worldwide.

A graph convolutional neural network model based on fused multi-subgraph as input and fused feature information as output

The graph convolution neural network (GCN)-based node classification model tackles the challenge of classifying nodes in graph data through learned feature representations. However, most existing graph neural networks primarily focus on the same type of edges, which might not accurately reflect the intricate real-world graph structure. This paper introduces a novel graph neural network model, MF-GCN, which integrates subgraphs with various edge types as input and combines feature information from each graph convolutional neural network layer to produce the final output. This model learns node feature representations by separately feeding subgraphs with different edge types into the graph convolutional layer. It then computes the weight vectors for fusing various edge type subgraphs based on the learned node features. Additionally, to efficiently extract feature information, the outputs of each graph convolution layer, without an activation function, are weighted and summed to obtain the final node features. This approach resolves the challenges of determining fusion weights and effectively extracting feature information during subgraph fusion. Experimental results show that the proposed model significantly improves performance on all three datasets, highlighting its effectiveness in node representation learning tasks.

LTFM: Long-tail few-shot module with loose coupling strategy for mineral spectral identification

In recent years, deep learning methods have exhibited superior performance in mineral identification when especially compared with conventional machine learning methods such as Support Vector Machine (SVM) and Partial Least Squares (PLS). Nevertheless, almost all of these deep learning methods pay more attention to improving and designing network structures, while neglecting the phenomenon of long-tail distribution in spectral data due to the inconsistency of ore distribution and the scarcity of several natural minerals. To alleviate the interference of majority categories on minority categories, we propose Long-Tail Few-shot Module (LTFM) which is inspired by rethinking the fashionable decoupling strategy that conducts primary representation learning and further classifier retrained on mineral spectral data. In particular, LTFM serves as a multi-expert mode, where these experts are respectively specialized in improving feature representation learning, mitigating the long-tail effect, and alleviating the interference of few shots. Additionally, the loose coupling learning strategy is introduced to facilitate primary representation learning and the subsequent additional experts to inherit this knowledge. Experiments on two publicly available spectral datasets show that the proposed LTFM significantly outperforms existing methods. In the end, extensive ablation studies are conducted to investigate the effectiveness, correctness, and robustness of our proposal.

Mises-Fisher similarity-based boosted additive angular margin loss for breast cancer classification

To enhance the accuracy of breast cancer diagnosis, current practices rely on biopsies and microscopic examinations. However, this approach is known for being time-consuming, tedious, and costly. While convolutional neural networks (CNNs) have shown promise for their efficiency and high accuracy, training them effectively becomes challenging in real-world learning scenarios such as class imbalance, small-scale datasets, and label noises. Angular margin-based softmax losses, which concentrate on the angle between features and classifiers embedded in cosine similarity at the classification layer, aim to regulate feature representation learning. Nevertheless, the cosine similarity’s lack of a heavy tail impedes its ability to compactly regulate intra-class feature distribution, limiting generalization performance. Moreover, these losses are constrained to target classes when margin penalties are applied, which may not always optimize effectiveness. Addressing these hurdles, we introduce an innovative approach termed MF-BAM (Mises-Fisher Similarity-based Boosted Additive Angular Margin Loss), which extends beyond traditional cosine similarity and is anchored in the von Mises-Fisher distribution. MF-BAM not only penalizes the angle between deep features and their corresponding target class weights but also considers angles between deep features and weights associated with non-target classes. Through extensive experimentation on the BreaKHis dataset, MF-BAM achieves outstanding accuracies of 99.92%, 99.96%, 100.00%, and 98.05% for magnification levels of ×40, ×100, ×200, and ×400, respectively. Furthermore, additional experiments conducted on the BACH dataset for breast cancer classification, as well as on the LFW and YTF datasets for face recognition, affirm the generalization capability of our proposed loss function.

Investigation of Bird Sound Transformer Modeling and Recognition

Birds play a pivotal role in ecosystem and biodiversity research, and accurate bird identification contributes to the monitoring of biodiversity, understanding of ecosystem functionality, and development of effective conservation strategies. Current methods for bird sound recognition often involve processing bird songs into various acoustic features or fusion features for identification, which can result in information loss and complicate the recognition process. At the same time, the recognition method based on raw bird audio has not received widespread attention. Therefore, this study proposes a bird sound recognition method that utilizes multiple one-dimensional convolutional neural networks to directly learn feature representations from raw audio data, simplifying the feature extraction process. We also apply positional embedding convolution and multiple Transformer modules to enhance feature processing and improve accuracy. Additionally, we introduce a trainable weight array to control the importance of each Transformer module for better generalization of the model. Experimental results demonstrate our model’s effectiveness, with an accuracy rate of 99.58% for the public dataset Birds_data, as well as 98.77% for the Birdsonund1 dataset, and 99.03% for the UrbanSound8K environment sound dataset.

Unravelling sleep patterns: Supervised contrastive learning with self-attention for sleep stage classification

Sleep data scoring is a crucial and primary step for diagnosing sleep disorders to know the sleep stages from the PSG signals. This study uses supervised contrastive learning with a self-attention mechanism to classify sleep stages. We propose a deep learning framework for automatic sleep stage classification, which involves two training phases: (1) the feature representation learning phase, in which the feature representation network (encoder) learns to extract features from the electroencephalogram (EEG) signals, and (2) the classification network training phase, where a pre-trained encoder (trained during phase I) along with the classifier head is fine-tuned for the classification task. The PSG data shows a non-uniform distribution of sleep stages, with wake (W) (around 30% of total samples) and N2 stages (around 58% and 37% of total samples in Physionet EDF-Sleep 2013 and 2018 datasets, respectively) being more prevalent, leading to an imbalanced dataset. The imbalanced data issue is addressed using a weighted softmax cross-entropy loss function that assigns higher weights to minority sleep stages. Additionally, an oversampling technique (the synthetic minority oversampling technique (SMOTE) (Chawla et al., 2002)[1] ) is applied to generate synthetic samples for minority classes. The proposed model is evaluated on the Physionet EDF-Sleep 2013 and 2018 datasets using Fpz-Cz and Pz-Oz EEG channels. It achieved an overall accuracy of 94.1%, a macro F1 score of 92.64, and a Cohen’s Kappa coefficient of 0.92. Ablation studies demonstrated the importance of triplet loss-based pre-training and oversampling for enhancing performance. The proposed model requires minimal pre-processing, eliminating the need for extensive signal processing expertise, and thus is well-suited for clinicians diagnosing sleep disorders.

Exploring sample relationship for few-shot classification

Few-shot classification (FSC) is a challenging problem, which aims to identify novel classes with limited samples. Most existing methods employ vanilla transfer learning or episodic meta-training to learn a feature extractor, and then measure the similarity between the query image and the few support examples of novel classes. However, these approaches merely learn feature representations from individual images, overlooking the exploration of the interrelationships among images. This neglect can hinder the attainment of more discriminative feature representations, thus limiting the potential improvement of few-shot classification performance. To address this issue, we propose a Sample Relationship Exploration (SRE) module comprising the Sample-level Attention (SA), Explicit Guidance (EG) and Channel-wise Adaptive Fusion (CAF) components, to learn discriminative category-related features. Specifically, we first employ the SA component to explore the similarity relationships among samples and obtain aggregated features of similar samples. Furthermore, to enhance the robustness of these features, we introduce the EG component to explicitly guide the learning of sample relationships by providing an ideal affinity map among samples. Finally, the CAF component is adopted to perform weighted fusion of the original features and the aggregated features, yielding category-related embeddings. The proposed method is a plug-and-play module which can be embedded into both transfer learning and meta-learning based few-shot classification frameworks. Extensive experiments on benchmark datasets show that the proposed module can effectively improve the performance over baseline models, and also perform competitively against the state-of-the-art algorithms. The source code is available at https://github.com/Chenguoz/SRE.

Self-supervised learning-based re-parameterization instance segmentation for hazardous object in terahertz image

Recently, terahertz imaging technology has shown widespread potential applications in the public security screening field. Previous terahertz hazardous object detection techniques primarily relied on manual recognition and image processing methods. Some solutions incorporating deep learning technologies depend on large quantities of high-quality data, making it challenging to achieve low-cost and high-performance detection. To solve the issue of dependency on large amounts of high-quality data, we propose a diversified dynamic structure You Only Look Once (DDS-YOLO) model based on masked image modeling and structural reparameterization for the instance segmentation of hazardous objects in terahertz security inspection images. To address the scarcity and annotating difficulty problems of terahertz security inspection image samples, we combine automatic data strategies with masked image modeling for self-supervised learning. We propose a multilevel feature refinement fusion mechanism to enhance the quality of learned feature representations. The backbone parameter transfer and fine-tuning training strategies are employed to achieve hazardous object instance segmentation on the terahertz dataset. To address the low detection accuracy issue caused by the poor terahertz image quality, we develop a reparameterizable hierarchical structure for the backbone, improve a multi-scale feature-integrating neck, and design a dynamically decoupled head with lower computational requirements to enhance the performance of the instance segmentation model. Experimental results demonstrate that the proposed model accurately outputs detection boxes, categories, and segmentation masks for hazardous objects with minimal training samples. The comparative experimental results indicate that the proposed model outperforms existing state-of-the-art methods in terms of detection performance. The proposed DDS-YOLO model achieves 59.3 % in mask mean Average Precision (mAP) and 61.3 % in box mAP, and the model parameters and computational requirements also meet practical application scenarios.

Cross-Subject Seizure Detection via Unsupervised Domain-Adaptation.

Automatic seizure detection from Electroencephalography (EEG) is of great importance in aiding the diagnosis and treatment of epilepsy due to the advantages of convenience and economy. Existing seizure detection methods are usually patient-specific, the training and testing are carried out on the same patient, limiting their scalability to other patients. To address this issue, we propose a cross-subject seizure detection method via unsupervised domain adaptation. The proposed method aims to obtain seizure specific information through shallow and deep feature alignments. For shallow feature alignment, we use convolutional neural network (CNN) to extract seizure-related features. The distribution gap of the shallow features between different patients is minimized by multi-kernel maximum mean discrepancies (MK-MMD). For deep feature alignment, adversarial learning is utilized. The feature extractor tries to learn feature representations that try to confuse the domain classifier, making the extracted deep features more generalizable to new patients. The performance of our method is evaluated on the CHB-MIT and Siena databases in epoch-based experiments. Additionally, event-based experiments are also conducted on the CHB-MIT dataset. The results validate the feasibility of our method in diminishing the domain disparities among different patients.

Image dehazing via self-supervised depth guidance

Self-supervised learning methods have demonstrated promising benefits to feature representation learning for image dehazing tasks, especially for avoiding the laborious work of collecting hazy-clean image pairs, while also enabling better generalization abilities of the model. Despite the long-standing interests in depth estimation for image dehazing tasks, few works have fully explored the interactions between depth and dehazing tasks in an unsupervised manner. In this paper, a self-supervised image dehazing framework under the guidance of self-supervised depth estimation has been proposed, to fully exploit the interactions between depth and hazes for image dehazing. Specifically, the hazy image and the corresponding depth estimation are generated and optimized from the clear image in a dual-network self-supervised manner. The correlations between depth and hazy images are exploited in depth-guided hybrid attention Transformer blocks, which adaptively leverage both the cross-attention and self-attention to effectively model hazy densities via cross-modality fusion and capture global context information for better feature representations. In addition, the depth estimations of hazy images are further explored for the detection tasks on hazy images. Extensive experiments demonstrate that the depth estimation not only enhances the model generalization ability across different dehazing datasets, leading to state-of-the-art self-supervised dehazing performance, but also benefits downstream detection tasks on hazy images. Our code is available at https://github.com/DongLiangSXU/Depth-Guidance-dehazing.git.

A multi-scale dense residual correlation network for remote sensing scene classification

Most existing scene classification methods based on remote sensing images tend to ignore important interactive information at different levels in the image. We propose an effective remote sensing scene classification method named multi-scale dense residual correlation network. The method is divided into three parts. First, the multi-stream feature extraction module is introduced which effectively utilizes features at different scales to extract different levels of information. Secondly, the dense residual connected feature fusion technology is proposed, which allows for a wide range of feature fusion. The Correlation Attention Module learn feature representations at multiple levels. This improves classification performance. The method outperforms existing algorithms in terms of effectiveness and accuracy, achieving state-of-the-art results on widely used remote sensing scene classification benchmarks.

Deep contrastive learning for predicting cancer prognosis using gene expression values.

Recent advancements in image classification have demonstrated that contrastive learning (CL) can aid in further learning tasks by acquiring good feature representation from a limited number of data samples. In this paper, we applied CL to tumor transcriptomes and clinical data to learn feature representations in a low-dimensional space. We then utilized these learned features to train a classifier to categorize tumors into a high- or low-risk group of recurrence. Using data from The Cancer Genome Atlas (TCGA), we demonstrated that CL can significantly improve classification accuracy. Specifically, our CL-based classifiers achieved an area under the receiver operating characteristic curve (AUC) greater than 0.8 for 14 types of cancer, and an AUC greater than 0.9 for 3 types of cancer. We also developed CL-based Cox (CLCox) models for predicting cancer prognosis. Our CLCox models trained with the TCGA data outperformed existing methods significantly in predicting the prognosis of 19 types of cancer under consideration. The performance of CLCox models and CL-based classifiers trained with TCGA lung and prostate cancer data were validated using the data from two independent cohorts. We also show that the CLCox model trained with the whole transcriptome significantly outperforms the Cox model trained with the 16 genes of Oncotype DX that is in clinical use for breast cancer patients. The trained models and the Python codes are publicly accessible and provide a valuable resource that will potentially find clinical applications for many types of cancer.

Deep radiomics-based prognostic prediction of oral cancer using optical coherence tomography

BackgroundThis study aims to evaluate the integration of optical coherence tomography (OCT) and peripheral blood immune indicators for predicting oral cancer prognosis by artificial intelligence.MethodsIn this study, we examined patients undergoing radical oral cancer resection and explored inherent relationships among clinical data, OCT images, and peripheral immune indicators for oral cancer prognosis. We firstly built a peripheral blood immune indicator-guided deep learning feature representation method for OCT images, and further integrated a multi-view prognostic radiomics model incorporating feature selection and logistic modeling. Thus, we can assess the prognostic impact of each indicator on oral cancer by quantifying OCT features.ResultsWe collected 289 oral mucosal samples from 68 patients, yielding 1,445 OCT images. Using our deep radiomics-based prognosis model, it achieved excellent discrimination for oral cancer prognosis with the area under the receiver operating characteristic curve (AUC) of 0.886, identifying systemic immune-inflammation index (SII) as the most informative feature for prognosis prediction. Additionally, the deep learning model also performed excellent results with 85.26% accuracy and 0.86 AUC in classifying the SII risk.ConclusionsOur study effectively merged OCT imaging with peripheral blood immune indicators to create a deep learning-based model for inflammatory risk prediction in oral cancer. Additionally, we constructed a comprehensive multi-view radiomics model that utilizes deep learning features for accurate prognosis prediction. The study highlighted the significance of the SII as a crucial indicator for evaluating patient outcomes, corroborating our clinical statistical analyses. This integration underscores the potential of combining imaging and blood indicators in clinical decision-making.Trial registrationThe clinical trial associated with this study was prospectively registered in the Chinese Clinical Trial Registry with the trial registration number (TRN) ChiCTR2200064861. The registration was completed on 2021.

GaitLRDF: gait recognition via local relevant feature representation and discriminative feature learning

GaitLRDF: gait recognition via local relevant feature representation and discriminative feature learning

Electricity behaviors anomaly detection based on multi-feature fusion and contrastive learning

Abnormal electricity usage detection is the process of discovering and diagnosing abnormal electricity usage behavior by monitoring and analyzing the electricity usage in the power system. How to improve the accuracy of anomaly detection is a popular research topic. Most studies use neural networks for anomaly detection, but ignore the effect of missing electricity data on anomaly detection performance. Missing value completion is an important method to improve the quality of electricity data and to optimize the anomaly detection performance. Moreover, most studies have ignored the potential correlation relationship between spatial features by modeling the temporal features of electricity data. Therefore, this paper proposes an electricity anomaly detection model based on multi-feature fusion and contrastive learning. The model integrates the temporal and spatial features to jointly accomplish electricity anomaly detection. In terms of temporal feature representation learning, an improved bi-directional LSTM is designed to achieve the missing value completion of electricity data, and combined with CNN to capture the electricity consumption behavior patterns in the temporal data. In terms of spatial feature representation learning, GCN and Transformer are used to fully explore the complex correlation relationships among data. In addition, in order to improve the performance of anomaly detection, this paper also designs a gated fusion module and combines the idea of contrastive learning to strengthen the representation ability of electricity data. Finally, we demonstrate through experiments that the method proposed in this paper can effectively improve the performance of electricity behavior anomaly detection.

Dynamic category-sensitive hypergraph inferring and homo-heterogeneous neighbor feature learning for drug-related microbe prediction.

The microbes in human body play a crucial role in influencing the functions of drugs, as they can regulate the activities and toxicities of drugs. Most recent methods for predicting drug-microbe associations are based on graph learning. However, the relationships among multiple drugs and microbes are complex, diverse, and heterogeneous. Existing methods often fail to fully model the relationships. In addition, the attributes of drug-microbe pairs exhibit long-distance spatial correlations, which previous methods have not integrated effectively. We propose a new prediction method named DHDMP which is designed to encode the relationships among multiple drugs and microbes and integrate the attributes of various neighbor nodes along with the pairwise long-distance correlations. First, we construct a hypergraph with dynamic topology, where each hyperedge represents a specific relationship among multiple drug nodes and microbe nodes. Considering the heterogeneity of node attributes across different categories, we developed a node category-sensitive hypergraph convolution network to encode these diverse relationships. Second, we construct homogeneous graphs for drugs and microbes respectively, as well as drug-microbe heterogeneous graph, facilitating the integration of features from both homogeneous and heterogeneous neighbors of each target node. Third, we introduce a graph convolutional network with cross-graph feature propagation ability to transfer node features from homogeneous to heterogeneous graphs for enhanced neighbor feature representation learning. The propagation strategy aids in the deep fusion of features from both types of neighbors. Finally, we design spatial cross-attention to encode the attributes of drug-microbe pairs, revealing long-distance correlations among multiple pairwise attribute patches. The comprehensive comparison experiments showed our method outperformed state-of-the-art methods for drug-microbe association prediction. The ablation studies demonstrated the effectiveness of node category-sensitive hypergraph convolution network, graph convolutional network with cross-graph feature propagation, and spatial cross-attention. Case studies on three drugs further showed DHDMP's potential application in discovering the reliable candidate microbes for the interested drugs. Source codes and supplementary materials are available at https://github.com/pingxuan-hlju/DHDMP.