Enhancing power equipment defect identification through multi-label classification methods

Multi-site structural damage identification using a multi-label classification scheme of machine learning

Convolutional neural network (CNN) has gained increasing attention in fault classification. However, the performance of CNN is sensitive to its learning rate. Some previous works have been done to tune the learning rate, including the "trial and error" and manual search, which heavily depend on the experts' experiences and should be conducted repeatedly on every dataset. Because of the variety of the fault data, it is time-consuming and labor intensive to use these traditional tuning methods for fault classification. To overcome this problem, in this article, we develop a novel learning rate scheduler based on the reinforcement learning (RL) for convolutional neural network (RL-CNN) in fault classification, which can schedule the learning rate efficiently and automatically. First, a new RL agent is designed to learn the policies about the learning rate adjustment during the training process. Second, a new structure of RL-CNN is developed to balance the exploration and exploitation of the agent. Third, the bagging ensemble version of RL-CNN (RL-CNN-Ens) is presented. Three bearing datasets are used to test the performance of RL-CNN-Ens. The results show that RL-CNN-Ens outperforms the traditional DLs and machine learning methods. Meanwhile, RL-CNN-Ens can find the state-of-the-art learning rate schedulers as human designed, showing its potential in fault classification.

Extreme multi-label text classification (XMTC), the problem of finding the most relevant label subset of each document from hundreds or even millions labels, has been a practical and important problem since the boom of big data. Significant progress has been made in recent years by the development of machine learning methods. However, although deep learning method has beaten traditional method in other related areas, it has no clear advantage in XMTC when we consider the performance of prediction. In order to improve the performance of deep learning method for Extreme multi-label text classification, we propose a novel feature extraction method to better explore the text space. Specifically, we build the model consisting of attention mechanism, convolutional neural network and recurrent neural network to extract multi-view features. Extensive experiments on four public available datasets show that our method achieves better performance than several strong baselines, including traditional methods and deep learning methods.

Mild cognitive impairment (MCI) is a clinical condition characterized by a decline in cognitive ability and progression of cognitive impairment. It is often considered a transitional stage between normal aging and Alzheimer's disease (AD). This study aimed to compare deep learning (DL) and traditional machine learning (ML) methods in predicting MCI using plasma proteomic biomarkers. A total of 239 adults were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort along with a pool of 146 plasma proteomic biomarkers. We evaluated seven traditional ML models (support vector machines (SVMs), logistic regression (LR), naïve Bayes (NB), random forest (RF), k-nearest neighbor (KNN), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost)) and six variations of a deep neural network (DNN) model-the DL model in the H2O package. Least Absolute Shrinkage and Selection Operator (LASSO) selected 35 proteomic biomarkers from the pool. Based on grid search, the DNN model with an activation function of "Rectifier With Dropout" with 2 layers and 32 of 35 selected proteomic biomarkers revealed the best model with the highest accuracy of 0.995 and an F1 Score of 0.996, while among seven traditional ML methods, XGBoost was the best with an accuracy of 0.986 and an F1 Score of 0.985. Several biomarkers were correlated with the APOE-ε4 genotype, polygenic hazard score (PHS), and three clinical cerebrospinal fluid biomarkers (Aβ42, tTau, and pTau). Bioinformatics analysis using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) revealed several molecular functions and pathways associated with the selected biomarkers, including cytokine-cytokine receptor interaction, cholesterol metabolism, and regulation of lipid localization. The results showed that the DL model may represent a promising tool in the prediction of MCI. These plasma proteomic biomarkers may help with early diagnosis, prognostic risk stratification, and early treatment interventions for individuals at risk for MCI.

The Army Rapid Capabilities Office (RCO) sponsored a Blind Signal Classification Competition seeking algorithms to automatically identify the modulation schemes of RF signal from complex-valued IQ (in-phase quadrature) samples. Traditional spectrum sensing technology uses energy detection to detect the existence of RF signals but the RCO competition further aimed to detect the modulation scheme of signals without prior information. Machine Learning (ML) technologies have been widely used for blind signal classification problem. Traditional ML methods usually have two stages where the first stage is to manually extract the features of the IQ symbols by subject matter experts and the second stage is to feed the features to an ML algorithm (e.g., a support vector machine) to develop the classifier. The state-of-art technology is to apply deep learning technologies such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) directly to the complex-value IQ symbols to train a multi-class classifier. Our team, dubbed Deep Dreamers, participated in the RCO competition and placed 3rd out of 42 active teams across industry, academia, and government. In this work we share our experience and lessons learned from the competition. Deep learning methods such as CNN, Residual Neural Network (ResNet), and Long Short-Term Memory (LSTM) are the fundamental neural network layers we used to develop a multi-class classifier. None of our individual models were able to achieve a competitively high ranking in the competition. The key to our success was to use ensemble learning to average the outputs of multiple diverse classifiers. In order for ensemble methods to be more accurate than any of its base models; the base learners have to be as accurate as possible. We found that while ResNet was more accurate than the LSTM; the LSTM was less sensitive to deviations in the test set.

PurposeIntelligent diagnosis of equipment faults can effectively avoid the shutdown caused by equipment faults and improve the safety of the equipment. At present, the diagnosis of various kinds of bearing fault information, such as the occurrence, location and degree of fault, can be carried out by machine learning and deep learning and realized through the multiclassification method. However, the multiclassification method is not perfect in distinguishing similar fault categories and visual representation of fault information. To improve the above shortcomings, an end-to-end fault multilabel classification model is proposed for bearing fault diagnosis.Design/methodology/approachIn this model, the labels of each bearing are binarized by using the binary relevance method. Then, the integrated convolutional neural network and gated recurrent unit (CNN-GRU) is employed to classify faults. Different from the general CNN networks, the CNN-GRU network adds multiple GRU layers after the convolutional layers and the pool layers.FindingsThe Paderborn University bearing dataset is utilized to demonstrate the practicability of the model. The experimental results show that the average accuracy in test set is 99.7%, and the proposed network is better than multilayer perceptron and CNN in fault diagnosis of bearing, and the multilabel classification method is superior to the multiclassification method. Consequently, the model can intuitively classify faults with higher accuracy.Originality/valueThe fault labels of each bearing are labeled according to the failure or not, the fault location, the damage mode and the damage degree, and then the binary value is obtained. The multilabel problem is transformed into a binary classification problem of each fault label by the binary relevance method, and the predicted probability value of each fault label is directly output in the output layer, which visually distinguishes different fault conditions.

AIDS is a syndrome caused by the HIV. During the progression of AIDS, a patient's immune system is weakened, which increases the patient's susceptibility to infections and diseases. Although antiretroviral drugs can effectively suppress HIV, the virus mutates very quickly and can become resistant to treatment. In addition, the virus can also become resistant to other treatments not currently being used through mutations, which is known in the clinical research community as cross-resistance. Since a single HIV strain can be resistant to multiple drugs, this problem is naturally represented as a multilabel classification problem. Given this multilabel relationship, traditional single-label classification methods often fail to effectively identify the drug resistances that may develop after a particular virus mutation. In this work, we propose a novel multilabel Robust Sample Specific Distance (RSSD) method to identify multiclass HIV drug resistance. Our method is novel in that it can illustrate the relative strength of the drug resistance of a reverse transcriptase (RT) sequence against a given drug nucleoside analog and learn the distance metrics for all the drug resistances. To learn the proposed RSSDs, we formulate a learning objective that maximizes the ratio of the summations of a number of ℓ1-norm distances, which is difficult to solve in general. To solve this optimization problem, we derive an efficient, nongreedy iterative algorithm with rigorously proved convergence. Our new method has been verified on a public HIV type 1 drug resistance data set with over 600 RT sequences and five nucleoside analogs. We compared our method against several state-of-the-art multilabel classification methods, and the experimental results have demonstrated the effectiveness of our proposed method.

Background Artificial intelligence (AI) has revolutionized diagnostic radiology by improving accuracy, efficiency, and clinical decision-making. While numerous systematic reviews and meta-analyses have evaluated the performance of AI-based techniques, particularly traditional machine learning (ML) and deep learning (DL) models, a comprehensive synthesis of this evidence is lacking. An umbrella review is necessary to integrate and compare findings across various imaging applications, offering the highest level of evidence to inform clinical practice and policy. Objective This umbrella review aims to compare the diagnostic performance of traditional machine learning and deep learning methods in radiology by synthesizing evidence from existing systematic reviews and meta-analyses. Methods A systematic literature search was conducted in PubMed, Scopus, Web of Science, and Cochrane Library for systematic reviews and meta-analyses published between 2018 and 2024. Only peer-reviewed reviews evaluating diagnostic applications of AI in radiology were included. Methodological quality was assessed using the AMSTAR 2 tool, and risk of bias was evaluated using ROBIS. Results Seven systematic reviews and meta-analyses were included. Across multiple imaging domains—such as breast cancer screening, spinal stenosis, and tumor grading—deep learning consistently outperformed traditional ML in diagnostic accuracy and sensitivity. Evidence quality was rated moderate to high, though variability in reporting and a lack of external validation were noted. Explainability features in DL models were underutilized and poorly evaluated. Conclusion This umbrella review confirms the superior diagnostic performance of deep learning methods over traditional ML in radiology. Future research should prioritize model transparency, real-world validation, and standardization in clinical implementation.

Multi-label drill cuttings classification reveals the current lithologies during drilling, which is crucial for guiding oil drilling operations. Many existing methods rely on annotated images for feature extraction, making their accuracy highly dependent on dataset size. However, due to equipment and manpower constraints, datasets in this field are generally small, posing a significant challenge for improving traditional methods for accurate multi-label classification. Notably, we observed that geological layers influence the distribution of drill cuttings, highlighting the importance of effectively leveraging geological priors for classification. In this paper, we propose a geological layer-aware cross-modal learning framework, which explicitly leverages local layer-wise information and global label co-occurrence patterns for multi-label drill cuttings classification. Unlike conventional end-to-end models, our framework first estimates the geological layer of a given image and derives a corresponding cuttings proportion vector. These priors are then employed to guide the alignment between visual and textual features, leading to more precise visual representations. Furthermore, we introduce a global co-occurrence matrix that captures label dependencies and enhances enhances the learning of visual representations through a graph convolutional network GCN , resulting in more accurate label predictions. Experiments on our dataset demonstrate that our approach significantly outperforms state-of-the-art methods, achieving a mean average precision mAP of 98.8 .

The field of Alzheimer's Disease classification and prediction recently gains more and more attention. Traditionally, the method treating such a problem was using the combination of traditional machine learning algorithm and deep learning algorithm. But there are constant efforts made by researchers to search for the potential of only using the deep learning method. This article compares the pros and cons of using deep learning method in the field of Alzheimer's Disease. Even though traditional machine learning method may perform slightly better right now, with the accumulation of data, it is totally possible to only use the deep learning method to make the Alzheimer's Disease classification and prediction.

This article is oriented to the research of the vehicle-mounted intelligent traditional Chinese medicine (TCM) syndrome differentiation system to provide a quick and accurate diagnosis suggestion for smart and mobile medical vehicles. Nowadays, TCM modernization has attached more and more attention due to its remarkable clinical effect. The typical TCM diagnosis process is to induces the syndrome types of a patient from the four-diagnosis symptoms based on syndrome differentiation theory, that is, given a set of symptoms to treat, an overall syndrome representation is learned by fusing all the symptoms effectively to mimic how a doctor induce the syndromes. Therefore, we believe that an overall description of symptoms of a patient is very important for the follow-up treatment and should be handled carefully and properly. However, due to the complexity and diversity of syndromes, most recommended prescription of a patient lacks the explicit ground-truth of syndrome. Therefore, in this article, a new TCM syndrome differentiation method based on multi-label classification method and deep learning method was proposed to learn the implicit symptoms induction process in the real diagnosis. A Deep Belief Network (DBN) was used to reconstruct the TCM diagnosis model based on the Rrestricted Boltzman Machine (RBM) mechanism. Towards symptoms-syndrome groups learning, a symptom vector representing the symptom collection of a patient is constructed as the input of DBN, which was used to train the symptom data and labeled samples to build an unsupervised model at first. And then the parameters of DBN was adjusted gradually based on back propagation method. Secondly, binary classification algorithm was used to convert the multi-label classification problem into several corresponding labels. Each binary classifier model corresponds to a binary classifier to complete the classification from symptoms to corresponding syndrome types. Finally, Experiments were conducted on a self-built TCM clinical records database, demonstrating obvious improvements on the classification accuracy and convergence rate. Further studies should focus on the promotion of effectiveness of the proposed model to be more in line with the actual needs of onboard medical diagnosis and treatment.

Traditional multi-label text classification methods, especially deep learning, have achieved remarkable results, but most of these methods use the word2vec technique to represent continuous text information, which fails to fully capture the semantic information of the text. To solve this problem, we built a hierarchical Transformer-CNN model and applied it in multi-label classification. Taking into account the characteristics of natural language, a hierarchical Transformer-CNN model is constructed to capture the semantic information of different levels of the text at the word and sentence levels using multi-headed self-attention mechanism, and a sentence convolutional neural network was used to extract key semantic features. For the hierarchical Transformer-CNN model we proposed, sufficient experiments have been conducted on the RCV1 and AAPD data sets to verify the model's effectiveness.

IntroductionAccurate classification of brain tumors from MRI scans is a critical task for improving patient outcomes. Machine learning (ML) and deep learning (DL) methods have shown promise in this domain, but their relative performance remains unclear.MethodsThis study evaluates several ML and DL techniques using the BraTS 2024 dataset. The models assessed include traditional algorithms such as Random Forest and advanced deep learning architectures including Simple CNN, VGG16, VGG19, ResNet50, Inception-ResNetV2, and EfficientNet. Preprocessing strategies were applied to optimize model performance.ResultsThe Random Forest classifier achieved the highest accuracy of 87%, outperforming all deep learning models, which achieved accuracy in the range of 47% to 70%. This indicates that traditional ML approaches can sometimes surpass state-of-the-art DL methods in tumor classification tasks.DiscussionThe findings highlight the importance of model selection and parameter tuning in automated brain tumor diagnosis. While deep learning models are generally considered standard for image analysis, Random Forest demonstrated superior performance in this context. This underscores the need for fine-grained consideration of dataset characteristics, computational resources, and diagnostic requirements.ConclusionThe study shows that carefully selected and optimized ML approaches can improve tumor classification and support more accurate and efficient diagnostic systems for brain tumor patients.

As security threats become more complex, the need for effective intrusion detection systems (IDSs) has grown. Traditional machine learning methods are limited by the need for extensive feature engineering and data preprocessing. To overcome this, we propose two enhanced hybrid deep learning models, an autoencoder–convolutional neural network (Autoencoder–CNN) and a transformer–deep neural network (Transformer–DNN). The Autoencoder reshapes network traffic data, addressing class imbalance, and the CNN performs precise classification. The transformer component extracts contextual features, which the DNN uses for accurate classification. Our approach utilizes an enhanced hybrid adaptive synthetic sampling–synthetic minority oversampling technique (ADASYN-SMOTE) for binary classification and enhanced SMOTE for multi-class classification, along with edited nearest neighbors (ENN) for further class imbalance handling. The models were designed to minimize false positives and negatives, improve real-time detection, and identify zero-day attacks. Evaluations based on the CICIDS2017 dataset showed 99.90% accuracy for Autoencoder–CNN and 99.92% for Transformer–DNN in binary classification, and 99.95% and 99.96% in multi-class classification, respectively. On the NF-BoT-IoT-v2 dataset, the Autoencoder–CNN achieved 99.98% in binary classification and 97.95% in multi-class classification, while the Transformer–DNN reached 99.98% and 97.90%, respectively. These results demonstrate the superior performance of the proposed models compared with traditional methods for handling diverse network attacks.

Emotion classification is a research field that aims to detect the emotions in a text using machine learning methods. In traditional machine learning (TML) methods, feature engineering processes cause the loss of some meaningful information, and classification performance is negatively affected. In addition, the success of modelling using deep learning (DL) approaches depends on the sample size. More samples are needed for Turkish due to the unique characteristics of the language. However, emotion classification data sets in Turkish are quite limited. In this study, the pretrained language model approach was used to create a stronger emotion classification model for Turkish. Well-known pretrained language models were fine-tuned for this purpose. The performances of these fine-tuned models for Turkish emotion classification were comprehensively compared with the performances of TML and DL methods in experimental studies. The proposed approach provides state-of-the-art performance for Turkish emotion classification.