Search Results (751)

Current deep learning models for time series often face challenges with generalizability in scenarios characterized by limited samples or inadequately labeled data. By tapping into the robust generative capabilities of diffusion models, which have shown success in computer vision and natural language processing, we see potential for improving the adaptability of deep learning models. However, the specific application of diffusion models in generating samples for time series classification tasks remains underexplored. To bridge this gap, we introduce the MDGPS model, which incorporates multi-task diffusion learning and gradient-free patch search (MDGPS). Our methodology aims to bolster the generalizability of time series classification models confronted with restricted labeled samples. The multi-task diffusion learning module integrates frequency-domain classification with random masked patches diffusion learning, leveraging frequency-domain feature representations and patch observation distributions to improve the discriminative properties of generated samples. Furthermore, a gradient-free patch search module, utilizing the particle swarm optimization algorithm, refines time series for specific samples through a pre-trained multi-task diffusion model. This process aims to reduce classification errors caused by random patch masking. The experimental results on four time series datasets show that the proposed MDGPS model consistently surpasses other methods, achieving the highest classification accuracy and F1-score across all datasets: 95.81%, 87.64%, 82.31%, and 100% in accuracy; and 95.21%, 82.32%, 78.57%, and 100% in F1-Score for Epilepsy, FD-B, Gesture, and EMG, respectively. In addition, evaluations in a reinforcement learning scenario confirm MDGPS’s superior performance. Ablation and visualization experiments further validate the effectiveness of its individual components. Full article

The number of cybersecurity vulnerabilities keeps growing every year. Each vulnerability must be reported to the MITRE Corporation and assessed by a Counting Number Authority, which generates a metrics vector that determines its severity score. This process can take up to several weeks, with higher-severity vulnerabilities taking more time. Several authors have successfully used Deep Learning to automate the score generation process and used explainable AI to build trust with the users. However, the explanations that were shown were surface label input saliency on binary classification. This is a limitation, as several metrics are multi-class and there is much more we can achieve with XAI than just visualizing saliency. In this work, we look for actionable actions CNAs can take using XAI. We achieve state-of-the-art results using an interpretable XGBoost model, generate explanations for multi-class labels using SHAP, and use the raw Shapley values to calculate cumulative word importance and generate IF rules that allow a more transparent look at how the model classified vulnerabilities. Finally, we made the code and dataset open-source for reproducibility. Full article

Background: Breast cancer is one of the most lethal cancers among women. Early detection and proper treatment reduce mortality rates. Histopathological images provide detailed information for diagnosing and staging breast cancer disease. Methods: The BreakHis dataset, which includes histopathological images, is used in this study. Medical images are prone to problems such as different textural backgrounds and overlapping cell structures, unbalanced class distribution, and insufficiently labeled data. In addition to these, the limitations of deep learning models in overfitting and insufficient feature extraction make it extremely difficult to obtain a high-performance model in this dataset. In this study, 20 state-of-the-art models are trained to diagnose eight types of breast cancer using the fine-tuning method. In addition, a comprehensive experimental study was conducted to determine the most successful new model, with 20 different custom models reported. As a result, we propose a novel model called MultiHisNet. Results: The most effective new model, which included a pointwise convolution layer, residual link, channel, and spatial attention module, achieved 94.69% accuracy in multi-class breast cancer classification. An ensemble model was created with the best-performing transfer learning and custom models obtained in the study, and model weights were determined with an Equilibrium Optimizer. The proposed ensemble model achieved 96.71% accuracy in eight-class breast cancer detection. Conclusions: The results show that the proposed model will support pathologists in successfully diagnosing breast cancer. Full article

The accurate identification of pills is essential for their safe administration in the medical field. Despite technological advancements, pill classification encounters hurdles such as ambiguous images, pattern similarities, mixed pills, and variations in pill shapes. A significant factor is the inability of 2D imaging to capture a pill’s 3D structure efficiently. Additionally, the scarcity of diverse datasets reflecting various pill shapes and colors hampers accurate prediction. Our experimental investigation shows that while color-based classification obtains a 95% accuracy rate, shape-based classification only reaches 66%, underscoring the inherent difficulty distinguishing between pills with similar patterns. In response to these challenges, we propose a novel system integrating Multi Combination Pattern Labeling (MCPL), a new method designed to accurately extract feature points and pill patterns. MCPL extracts feature points invariant to rotation and scale and effectively identifies unique edges, thereby emphasizing pills’ contour and structural features. This innovative approach enables the robust extraction of information regarding various shapes, sizes, and complex pill patterns, considering even the 3D structure of the pills. Experimental results show that the proposed method improves the existing recognition performance by about 1.2 times. By improving the accuracy and reliability of pill classification and recognition, MCPL can significantly enhance patient safety and medical efficiency. By overcoming the limitations inherent in existing classification methods, MCPL provides high-accuracy pill classification, even with constrained datasets. It substantially enhances the reliability of pill classification and recognition, contributing to improved patient safety and medical efficiency. Full article

Multi-Label Classification refers to the classification task where a data sample is associated with multiple labels simultaneously, which is widely used in text classification, image classification, and other fields. Different from the traditional single-label classification, each instance in Multi-Label Classification corresponds to multiple labels, and there is a correlation between these labels, which contains a wealth of information. Therefore, the ability to effectively mine and utilize the complex correlations between labels has become a key factor in Multi-Label Classification methods. In recent years, research on label correlations has shown a significant growth trend internationally, reflecting its importance. Given that, this paper presents a survey on the label correlations in Multi-Label Classification to provide valuable references and insights for future researchers. The paper introduces multi-label datasets across various fields, elucidates and categorizes the concept of label correlations, emphasizes their utilization in Multi-Label Classification and associated subproblems, and provides a prospect for future work on label correlations. Full article

The impact of the Fourth Industrial Revolution has brought significant attention to Condition-based maintenance (CBM) for autonomous ships. This study aims to apply CBM to the fuel supply pump of a ship. Five major failures were identified through reliability analysis, and structural analysis was conducted to investigate the mechanisms by which one failure induces another, leading to the identification of three compound failure scenarios. Data were collected on a test bed under normal conditions, five single failure conditions, and three compound failure conditions. The acceleration data from the experiments were transformed into 2D arrays corresponding to a single pump rotation, and a method was proposed to compensate for the errors accumulated during the repeated array generation. The data were vectorized using a simplified CNN structure and applied to six multi-label learning methods, which were compared to identify the optimal approach. Among the six methods, the Label Powerset (LP) was found to be the most effective. Multi-label learning captures correlations between labels, similar to the failure-inducing mechanisms learned from structural analysis. Full article

This study investigates the technical challenges of applying Support Vector Machines (SVM) for multi-class classification in network intrusion detection using the UWF-ZeekDataFall22 dataset, which is labeled based on the MITRE ATT&CK framework. A key challenge lies in handling imbalanced classes and complex attack patterns, which are inherent in intrusion detection data. This work highlights the difficulties in implementing SVMs for multi-class classification, particularly with One-vs.-One (OvO) and One-vs.-All (OvA) methods, including scalability issues due to the large volume of network traffic logs and the tendency of SVMs to be sensitive to noisy data and class imbalances. SMOTE was used to address class imbalances, while preprocessing techniques were applied to improve feature selection and reduce noise in the data. The unique structure of network traffic data, with overlapping patterns between attack vectors, posed significant challenges in achieving accurate classification. Our model reached an accuracy of over 90% with OvO and over 80% with OvA, demonstrating that despite these challenges, multi-class SVMs can be effectively applied to complex intrusion detection tasks when combined with appropriate balancing and preprocessing techniques. Full article

The rapid development of remote sensing technology has provided new sources of data for marine rescue and has made it possible to find and track survivors. Due to the requirement of tracking multiple survivors at the same time, multi-object tracking (MOT) has become the key subtask of marine rescue. However, there exists a significant gap between fine-grained objects in realistic marine rescue remote sensing data and the fine-grained object tracking capability of existing MOT technologies, which mainly focuses on coarse-grained object scenarios and fails to track fine-grained instances. Such a gap limits the practical application of MOT in realistic marine rescue remote sensing data, especially when rescue forces are limited. Given the promising fine-grained classification performance of recent text-guided methods, we delve into leveraging labels and attributes to narrow the gap between MOT and fine-grained maritime rescue. We propose a text-guided multi-class multi-object tracking (TG-MCMOT) method. To handle the problem raised by fine-grained classes, we design a multi-modal encoder by aligning external textual information with visual inputs. We use decoding information at different levels, simultaneously predicting the category, location, and identity embedding features of objects. Meanwhile, to improve the performance of small object detection, we also develop a data augmentation pipeline to generate pseudo-near-infrared images based on RGB images. Extensive experiments demonstrate that our TG-MCMOT not only performs well on typical metrics in the maritime rescue task (SeaDronesSee dataset), but it also effectively tracks open-set categories on the BURST dataset. Specifically, on the SeaDronesSee dataset, the Higher Order Tracking Accuracy (HOTA) reached a score of 58.8, and on the BURST test dataset, the HOTA score for the unknown class improved by 16.07 points. Full article

Agricultural productivity is one of the critical factors towards ensuring food security across the globe. However, some of the main crops, such as potato, tomato, and mango, are usually infested by leaf diseases, which considerably lower yield and quality. The traditional practice of diagnosing disease through visual inspection is labor-intensive, time-consuming, and can lead to numerous errors. To address these challenges, this study evokes the AgirLeafNet model, a deep learning-based solution with a hybrid of NASNetMobile for feature extraction and Few-Shot Learning (FSL) for classification. The Excess Green Index (ExG) is a novel approach that is a specified vegetation index that can further the ability of the model to distinguish and detect vegetative properties even in scenarios with minimal labeled data, demonstrating the tremendous potential for this application. AgirLeafNet demonstrates outstanding accuracy, with 100% accuracy for potato detection, 92% for tomato, and 99.8% for mango leaves, producing incredibly accurate results compared to the models already in use, as described in the literature. By demonstrating the viability of a deep learning/IoT system architecture, this study goes beyond the current state of multi-crop disease detection. It provides practical, effective, and efficient deep-learning solutions for sustainable agricultural production systems. The innovation of the model emphasizes its multi-crop capability, precision in results, and the suggested use of ExG to generate additional robust disease detection methods for new findings. The AgirLeafNet model is setting an entirely new standard for future research endeavors. Full article

Multi-label text classification (MLTC) aims to assign appropriate labels to each document from a given set. Prior research has acknowledged the significance of label information, but its utilization remains insufficient. Existing approaches often focus on either label correlation or label textual semantics, without fully leveraging the information contained within labels. In this paper, we propose a multi-perspective contrastive model (MPCM) with an attention mechanism to integrate labels and documents, utilizing contrastive methods to enhance label information from both textual semantic and correlation perspectives. Additionally, we introduce techniques for contrastive global representation learning and positive label representation alignment to improve the model’s perception of accurate labels. The experimental results demonstrate that our algorithm achieves superior performance compared to existing methods when evaluated on the AAPD and RCV1-V2 datasets. Full article

In practical working environments, rolling bearings are one of the components that are prone to failure. Their vibration signal samples are faced with challenges, mainly including the imbalance between normal and fault samples as well as an insufficient number of labeled samples. This study proposes a sample-expansion method based on generative adversarial networks (GANs) and a fault diagnosis method based on a transformer to solve the above issues. First, selective kernel networks (SKNets) and a genetic algorithm (GA) were introduced to construct a conditional variational autoencoder–evolutionary generative adversarial network with a selective kernel (CVAE-SKEGAN) to achieve a balance between the proportion of normal and faulty samples. Then, a semi-supervised learning–variational convolutional Swin transformer (SSL-VCST) network was built for the fault classification, specifically introducing variational attention and semi-supervised mechanisms to reduce the overfitting risk of the model and solve the problem of a shortage of labeled samples. Three typical operating conditions were designed for the multi-case applicability verification. The results show that the method proposed in this study had good application effects when solving both sample imbalances and labeled-sample deficiencies and improved the accuracy of fault diagnosis in the above scenarios. Full article

Background: Distantly supervised relation extraction (DSRE) aims to identify semantic relations in large-scale texts automatically labeled via knowledge base alignment. It has garnered significant attention due to its high efficiency, but existing methods are plagued by noise at both the word and sentence level and fail to address these issues adequately. The former level of noise arises from the large proportion of irrelevant words within sentences, while noise at the latter level is caused by inaccurate relation labels for various sentences. Method: We propose a novel multi-level noise reduction neural network (MLNRNN) to tackle both issues by mitigating the impact of multi-level noise. We first build an iterative keyword semantic aggregator (IKSA) to remove noisy words, and capture distinctive features of sentences by aggregating the information of keywords. Next, we implement multi-objective multi-instance learning (MOMIL) to reduce the impact of incorrect labels in sentences by identifying the cluster of correctly labeled instances. Meanwhile, we leverage mislabeled sentences with cross-level contrastive learning (CCL) to further enhance the classification capability of the extractor. Results: Comprehensive experimental results on two DSRE benchmark datasets demonstrated that the MLNRNN outperformed state-of-the-art methods for distantly supervised relation extraction in almost all cases. Conclusions: The proposed MLNRNN effectively addresses both word- and sentence-level noise, providing a significant improvement in relation extraction performance under distant supervision. Full article

This paper proposes a method for multi-label visual emotion recognition that fuses fore-background features to address the following issues that visual-based multi-label emotion recognition often overlooks: the impacts of the background that the person is placed in and the foreground, such as social interactions between different individuals on emotion recognition; the simplification of multi-label recognition tasks into multiple binary classification tasks; and it ignores the global correlations between different emotion labels. First, a fore-background-aware emotion recognition model (FB-ER) is proposed, which is a three-branch multi-feature hybrid fusion network. It efficiently extracts body features by designing a core region unit (CR-Unit) that represents background features as background keywords and extracts depth map information to model social interactions between different individuals as foreground features. These three features are fused at both the feature and decision levels. Second, a multi-label emotion recognition classifier (ML-ERC) is proposed, which captures the relationship between different emotion labels by designing a label co-occurrence probability matrix and cosine similarity matrix, and uses graph convolutional networks to learn correlations between different emotion labels to generate a classifier that considers emotion correlations. Finally, the visual features are combined with the object classifier to enable the multi-label recognition of 26 different emotions. The proposed method was evaluated on the Emotic dataset, and the results show an improvement of 0.732% in the mAP and 0.007 in the Jaccard’s coefficient compared with the state-of-the-art method. Full article

Medical named entity recognition (NER) focuses on extracting and classifying key entities from medical texts. Through automated medical information extraction, NER can effectively improve the efficiency of electronic medical record analysis, medical literature retrieval, and intelligent medical question–answering systems, enabling doctors and researchers to obtain the required medical information more quickly and thereby helping to improve the accuracy of diagnosis and treatment decisions. The current methods have certain limitations in dealing with contextual dependencies and entity memory and fail to fully consider the contextual relevance and interactivity between entities. To address these issues, this paper proposes a Chinese medical named entity recognition model that combines contextual dependency perception and a new memory unit. The model combines the BERT pre-trained model with a new memory unit (GLMU) and a recall network (RMN). The GLMU can efficiently capture long-distance dependencies, while the RMN enhances multi-level semantic information processing. The model also incorporates fully connected layers (FC) and conditional random fields (CRF) to further optimize the performance of entity classification and sequence labeling. The experimental results show that the model achieved F1 values of 91.53% and 64.92% on the Chinese medical datasets MCSCSet and CMeEE, respectively, surpassing other related models and demonstrating significant advantages in the field of medical entity recognition. Full article

The difficulty of classifying retinal fundus images with one or more illnesses present or missing is known as fundus multi-lesion classification. The challenges faced by current approaches include the inability to extract comparable morphological features from images of different lesions and the inability to resolve the issue of the same lesion, which presents significant feature variances due to grading disparities. This paper proposes a multi-disease recognition network model, Fundus-DANet, based on the dilated convolution. It has two sub-modules to address the aforementioned issues: the interclass learning module (ILM) and the dilated-convolution convolutional block attention module (DA-CBAM). The DA-CBAM uses a convolutional block attention module (CBAM) and dilated convolution to extract and merge multiscale information from images. The ILM uses the channel attention mechanism to map the features to lower dimensions, facilitating exploring latent relationships between various categories. The results demonstrate that this model outperforms previous models in classifying fundus multilocular lesions in the OIA-ODIR dataset with 93% accuracy. Full article