Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or...Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or indirect slurs.To address this gap,we propose a hybrid framework combining Term Frequency-Inverse Document Frequency(TF-IDF),word-to-vector(Word2Vec),and Bidirectional Encoder Representations from Transformers(BERT)based models for multi-class cyberbullying detection.Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships,fused with BERT’s contextual embeddings to capture syntactic and semantic complexities.We evaluate the framework on a publicly available dataset of 47,000 annotated social media posts across five cyberbullying categories:age,ethnicity,gender,religion,and indirect aggression.Among BERT variants tested,BERT Base Un-Cased achieved the highest performance with 93%accuracy(standard deviation across±1%5-fold cross-validation)and an average AUC of 0.96,outperforming standalone TF-IDF(78%)and Word2Vec(82%)models.Notably,it achieved near-perfect AUC scores(0.99)for age and ethnicity-based bullying.A comparative analysis with state-of-the-art benchmarks,including Generative Pre-trained Transformer 2(GPT-2)and Text-to-Text Transfer Transformer(T5)models highlights BERT’s superiority in handling ambiguous language.This work advances cyberbullying detection by demonstrating how hybrid feature extraction and transformer models improve multi-class classification,offering a scalable solution for moderating nuanced harmful content.展开更多
Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often stru...Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often struggle with low-contrast MRI images,class imbalance,and suboptimal feature extraction.This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans.Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization(CLAHE)and Enhanced Super-Resolution Generative Adversarial Networks(ESRGAN).A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient(MCC)-based evaluation method into the design.The trained and validated model gives a 98.88%accuracy rate and 0.9614 MCC score.We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52%(±1.51),a loss of 0.1671,and an MCC score of 0.9429 across folds.The proposed framework outperforms the state-of-the-art models with a 98%weighted F1-score while decreasing misdiagnosis results for every AD stage.The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis.These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis,contributing to improved computer-aided diagnosis(CAD)systems in clinical practice.展开更多
Artificial intelligence(AI),particularly deep learning algorithms utilizing convolutional neural networks,plays an increasingly pivotal role in enhancing medical image examination.It demonstrates the potential for imp...Artificial intelligence(AI),particularly deep learning algorithms utilizing convolutional neural networks,plays an increasingly pivotal role in enhancing medical image examination.It demonstrates the potential for improving diagnostic accuracy within dental care.Orthopantomograms(OPGs)are essential in dentistry;however,their manual interpretation is often inconsistent and tedious.To the best of our knowledge,this is the first comprehensive application of YOLOv5m for the simultaneous detection and classification of six distinct dental pathologies using panoramic OPG images.The model was trained and refined on a custom dataset that began with 232 panoramic radiographs and was later expanded to 604 samples.These included annotated subclasses representing Caries,Infection,Impacted Teeth,Fractured Teeth,Broken Crowns,and Healthy conditions.The training was performed using GPU resources alongside tuned hyperparameters of batch size,learning rate schedule,and early stopping tailored for generalization to prevent overfitting.Evaluation on a held-out test set showed strong performance in the detection and localization of various dental pathologies and robust overall accuracy.At an IoU of 0.5,the system obtained a mean precision of 94.22%and recall of 90.42%,with mAP being 93.71%.This research confirms the use of YOLOv5m as a robust,highly efficient AI technology for the analysis of dental pathologies using OPGs,providing a clinically useful solution to enhance workflow efficiency and aid in sustaining consistency in complex multi-dimensional case evaluations.展开更多
Accurate classification of encrypted traffic plays an important role in network management.However,current methods confronts several problems:inability to characterize traffic that exhibits great dispersion,inability ...Accurate classification of encrypted traffic plays an important role in network management.However,current methods confronts several problems:inability to characterize traffic that exhibits great dispersion,inability to classify traffic with multi-level features,and degradation due to limited training traffic size.To address these problems,this paper proposes a traffic granularity-based cryptographic traffic classification method,called Granular Classifier(GC).In this paper,a novel Cardinality-based Constrained Fuzzy C-Means(CCFCM)clustering algorithm is proposed to address the problem caused by limited training traffic,considering the ratio of cardinality that must be linked between flows to achieve good traffic partitioning.Then,an original representation format of traffic is presented based on granular computing,named Traffic Granules(TG),to accurately describe traffic structure by catching the dispersion of different traffic features.Each granule is a compact set of similar data with a refined boundary by excluding outliers.Based on TG,GC is constructed to perform traffic classification based on multi-level features.The performance of the GC is evaluated based on real-world encrypted network traffic data.Experimental results show that the GC achieves outstanding performance for encrypted traffic classification with limited size of training traffic and keeps accurate classification in dynamic network conditions.展开更多
Aiming at the limitations of rapid fault diagnosis of blast furnace, a novel strategy based on cost-conscious least squares support vector machine （LS-SVM） is proposed to solve this problem. Firstly, modified discre...Aiming at the limitations of rapid fault diagnosis of blast furnace, a novel strategy based on cost-conscious least squares support vector machine （LS-SVM） is proposed to solve this problem. Firstly, modified discrete particle swarm optimization is applied to optimize the feature selection and the LS-SVM parameters. Secondly, cost-con- scious formula is presented for fitness function and it contains in detail training time, recognition accuracy and the feature selection. The CLS-SVM algorithm is presented to increase the performance of the LS-SVM classifier. The new method can select the best fault features in much shorter time and have fewer support vectbrs and better general- ization performance in the application of fault diagnosis of the blast furnace. Thirdly, a gradual change binary tree is established for blast furnace faults diagnosis. It is a multi-class classification method based on center-of-gravity formula distance of cluster. A gradual change classification percentage ia used to select sample randomly. The proposed new metbod raises the sped of diagnosis, optimizes the classifieation scraraey and has good generalization ability for fault diagnosis of the application of blast furnace.展开更多
Considering strip steel surface defect samples, a multi-class classification method was proposed based on enhanced least squares twin support vector machines （ELS-TWSVMs） and binary tree. Firstly, pruning region sam...Considering strip steel surface defect samples, a multi-class classification method was proposed based on enhanced least squares twin support vector machines （ELS-TWSVMs） and binary tree. Firstly, pruning region samples center method with adjustable pruning scale was used to prune data samples. This method could reduce classifierr s training time and testing time. Secondly, ELS-TWSVM was proposed to classify the data samples. By introducing error variable contribution parameter and weight parameter, ELS-TWSVM could restrain the impact of noise sam- ples and have better classification accuracy. Finally, multi-class classification algorithms of ELS-TWSVM were pro- posed by combining ELS-TWSVM and complete binary tree. Some experiments were made on two-dimensional data- sets and strip steel surface defect datasets. The experiments showed that the multi-class classification methods of ELS-TWSVM had higher classification speed and accuracy for the datasets with large-scale, unbalanced and noise samples.展开更多
The basic idea of multi-class classification is a disassembly method,which is to decompose a multi-class classification task into several binary classification tasks.In order to improve the accuracy of multi-class cla...The basic idea of multi-class classification is a disassembly method,which is to decompose a multi-class classification task into several binary classification tasks.In order to improve the accuracy of multi-class classification in the case of insufficient samples,this paper proposes a multi-class classification method combining K-means and multi-task relationship learning(MTRL).The method first uses the split method of One vs.Rest to disassemble the multi-class classification task into binary classification tasks.K-means is used to down sample the dataset of each task,which can prevent over-fitting of the model while reducing training costs.Finally,the sampled dataset is applied to the MTRL,and multiple binary classifiers are trained together.With the help of MTRL,this method can utilize the inter-task association to train the model,and achieve the purpose of improving the classification accuracy of each binary classifier.The effectiveness of the proposed approach is demonstrated by experimental results on the Iris dataset,Wine dataset,Multiple Features dataset,Wireless Indoor Localization dataset and Avila dataset.展开更多
Focusing on strip steel surface defects classification, a novel support vector machine with adjustable hyper-sphere （AHSVM） is formulated. Meanwhile, a new multi-class classification method is proposed. Originated f...Focusing on strip steel surface defects classification, a novel support vector machine with adjustable hyper-sphere （AHSVM） is formulated. Meanwhile, a new multi-class classification method is proposed. Originated from support vector data description, AHSVM adopts hyper-sphere to solve classification problem. AHSVM can obey two principles： the margin maximization and inner-class dispersion minimization. Moreover, the hyper-sphere of AHSVM is adjustable, which makes the final classification hyper-sphere optimal for training dataset. On the other hand, AHSVM is combined with binary tree to solve multi-class classification for steel surface defects. A scheme of samples pruning in mapped feature space is provided, which can reduce the number of training samples under the premise of classification accuracy, resulting in the improvements of classification speed. Finally, some testing experiments are done for eight types of strip steel surface defects. Experimental results show that multi-class AHSVM classifier exhibits satisfactory results in classification accuracy and efficiency.展开更多
Defect classification is the key task of a steel surface defect detection system.The current defect classification algorithms have not taken the feature noise into consideration.In order to reduce the adverse impact o...Defect classification is the key task of a steel surface defect detection system.The current defect classification algorithms have not taken the feature noise into consideration.In order to reduce the adverse impact of feature noise,an anti-noise multi-class classification method was proposed for steel surface defects.On the one hand,a novel anti-noise support vector hyper-spheres(ASVHs)classifier was formulated.For N types of defects,the ASVHs classifier built N hyper-spheres.These hyper-spheres were insensitive to feature and label noise.On the other hand,in order to reduce the costs of online time and storage space,the defect samples were pruned by support vector data description with parameter iteration adjustment strategy.In the end,the ASVHs classifier was built with sparse defect samples set and auxiliary information.Experimental results show that the novel multi-class classification method has high efficiency and accuracy for corrupted defect samples in steel surface.展开更多
The accurate identification and classification of various power quality disturbances are keys to ensuring high-quality electrical energy. In this study, the statistical characteristics of the disturbance signal of wav...The accurate identification and classification of various power quality disturbances are keys to ensuring high-quality electrical energy. In this study, the statistical characteristics of the disturbance signal of wavelet transform coefficients and wavelet transform energy distribution constitute feature vectors. These vectors are then trained and tested using SVM multi-class algorithms. Experimental results demonstrate that the SVM multi-class algorithms, which use the Gaussian radial basis function, exponential radial basis function, and hyperbolic tangent function as basis functions, are suitable methods for power quality disturbance classification.展开更多
Unlike external attacks,insider threats arise from legitimate users who belong to the organization.These individuals may be a potential threat for hostile behavior depending on their motives.For insider detection,many...Unlike external attacks,insider threats arise from legitimate users who belong to the organization.These individuals may be a potential threat for hostile behavior depending on their motives.For insider detection,many intrusion detection systems learn and prevent known scenarios,but because malicious behavior has similar patterns to normal behavior,in reality,these systems can be evaded.Furthermore,because insider threats share a feature space similar to normal behavior,identifying them by detecting anomalies has limitations.This study proposes an improved anomaly detection methodology for insider threats that occur in cybersecurity in which a discrete wavelet transformation technique is applied to classify normal vs.malicious users.The discrete wavelet transformation technique easily discovers new patterns or decomposes synthesized data,making it possible to distinguish between shared characteristics.To verify the efficacy of the proposed methodology,experiments were conducted in which normal users and malicious users were classified based on insider threat scenarios provided in Carnegie Mellon University’s Computer Emergency Response Team(CERT)dataset.The experimental results indicate that the proposed methodology with discrete wavelet transformation reduced the false-positive rate by 82%to 98%compared to the case with no wavelet applied.Thus,the proposed methodology has high potential for application to similar feature spaces.展开更多
Human activity recognition is a significant area of research in artificial intelligence for surveillance,healthcare,sports,and human-computer interaction applications.The article benchmarks the performance of You Only...Human activity recognition is a significant area of research in artificial intelligence for surveillance,healthcare,sports,and human-computer interaction applications.The article benchmarks the performance of You Only Look Once version 11-based(YOLOv11-based)architecture for multi-class human activity recognition.The article benchmarks the performance of You Only Look Once version 11-based(YOLOv11-based)architecture for multi-class human activity recognition.The dataset consists of 14,186 images across 19 activity classes,from dynamic activities such as running and swimming to static activities such as sitting and sleeping.Preprocessing included resizing all images to 512512 pixels,annotating them in YOLO’s bounding box format,and applying data augmentation methods such as flipping,rotation,and cropping to enhance model generalization.The proposed model was trained for 100 epochs with adaptive learning rate methods and hyperparameter optimization for performance improvement,with a mAP@0.5 of 74.93%and a mAP@0.5-0.95 of 64.11%,outperforming previous versions of YOLO(v10,v9,and v8)and general-purpose architectures like ResNet50 and EfficientNet.It exhibited improved precision and recall for all activity classes with high precision values of 0.76 for running,0.79 for swimming,0.80 for sitting,and 0.81 for sleeping,and was tested for real-time deployment with an inference time of 8.9 ms per image,being computationally light.Proposed YOLOv11’s improvements are attributed to architectural advancements like a more complex feature extraction process,better attention modules,and an anchor-free detection mechanism.While YOLOv10 was extremely stable in static activity recognition,YOLOv9 performed well in dynamic environments but suffered from overfitting,and YOLOv8,while being a decent baseline,failed to differentiate between overlapping static activities.The experimental results determine proposed YOLOv11 to be the most appropriate model,providing an ideal balance between accuracy,computational efficiency,and robustness for real-world deployment.Nevertheless,there exist certain issues to be addressed,particularly in discriminating against visually similar activities and the use of publicly available datasets.Future research will entail the inclusion of 3D data and multimodal sensor inputs,such as depth and motion information,for enhancing recognition accuracy and generalizability to challenging real-world environments.展开更多
With the development of deep learning and Convolutional Neural Networks(CNNs),the accuracy of automatic food recognition based on visual data have significantly improved.Some research studies have shown that the deepe...With the development of deep learning and Convolutional Neural Networks(CNNs),the accuracy of automatic food recognition based on visual data have significantly improved.Some research studies have shown that the deeper the model is,the higher the accuracy is.However,very deep neural networks would be affected by the overfitting problem and also consume huge computing resources.In this paper,a new classification scheme is proposed for automatic food-ingredient recognition based on deep learning.We construct an up-to-date combinational convolutional neural network(CBNet)with a subnet merging technique.Firstly,two different neural networks are utilized for learning interested features.Then,a well-designed feature fusion component aggregates the features from subnetworks,further extracting richer and more precise features for image classification.In order to learn more complementary features,the corresponding fusion strategies are also proposed,including auxiliary classifiers and hyperparameters setting.Finally,CBNet based on the well-known VGGNet,ResNet and DenseNet is evaluated on a dataset including 41 major categories of food ingredients and 100 images for each category.Theoretical analysis and experimental results demonstrate that CBNet achieves promising accuracy for multi-class classification and improves the performance of convolutional neural networks.展开更多
Based on the framework of support vector machines （SVM） using one-against-one （OAO） strategy, a new multi-class kernel method based on directed aeyclie graph （DAG） and probabilistic distance is proposed to raise...Based on the framework of support vector machines （SVM） using one-against-one （OAO） strategy, a new multi-class kernel method based on directed aeyclie graph （DAG） and probabilistic distance is proposed to raise the multi-class classification accuracies. The topology structure of DAG is constructed by rearranging the nodes＇ sequence in the graph. DAG is equivalent to guided operating SVM on a list, and the classification performance depends on the nodes＇ sequence in the graph. Jeffries-Matusita distance （JMD） is introduced to estimate the separability of each class, and the implementation list is initialized with all classes organized according to certain sequence in the list. To testify the effectiveness of the proposed method, numerical analysis is conducted on UCI data and hyperspectral data. Meanwhile, comparative studies using standard OAO and DAG classification methods are also conducted and the results illustrate better performance and higher accuracy of the orooosed JMD-DAG method.展开更多
This paper presents a holistic multimodal approach for real-time anomaly detection and classification in largescale photovoltaic plants.The approach encompasses segmentation,geolocation,and classification of individua...This paper presents a holistic multimodal approach for real-time anomaly detection and classification in largescale photovoltaic plants.The approach encompasses segmentation,geolocation,and classification of individual photovoltaic modules.A fine-tuned Yolov7 model was trained for the individual module’s segmentation of both modalities;RGB and IR images.The localization of individual solar panels relies on photogrammetric measurements to facilitate maintenance operations.The localization process also links extracted images of the same panel using their geographical coordinates and preprocesses them for the multimodal model input.The study also focuses on optimizing pre-trained models using Bayesian search to improve and fine-tune them with our dataset.The dataset was collected from different systems and technologies within our research platform.It has been curated into 1841 images and classified into five anomaly classes.Grad-CAM,an explainable AI tool,is utilized to compare the use of multimodality to a single modality.Finally,for real-time optimization,the ONNX format was used to optimize the model further for deployment in real-time.The improved ConvNext-Tiny model performed well in both modalities,with 99%precision,recall,and F1-score for binary classification and 85%for multi-class classification.In terms of latency,the segmentation models have an inference time of 14 ms and 12 ms for RGB and IR images and 24 ms for detection and classification.The proposed holistic approach includes a built-in feedback loop to ensure the model’s robustness against domain shifts in the production environment.展开更多
In this paper,a new multiclass classification algorithm is proposed based on the idea of Locally Linear Embedding(LLE),to avoid the defect of traditional manifold learning algorithms,which can not deal with new sample...In this paper,a new multiclass classification algorithm is proposed based on the idea of Locally Linear Embedding(LLE),to avoid the defect of traditional manifold learning algorithms,which can not deal with new sample points.The algorithm defines an error as a criterion by computing a sample's reconstruction weight using LLE.Furthermore,the existence and characteristics of low dimensional manifold in range-profile time-frequency information are explored using manifold learning algorithm,aiming at the problem of target recognition about high range resolution MilliMeter-Wave(MMW) radar.The new algorithm is applied to radar target recognition.The experiment results show the algorithm is efficient.Compared with other classification algorithms,our method improves the recognition precision and the result is not sensitive to input parameters.展开更多
基金funded by Scientific Research Deanship at University of Hail-Saudi Arabia through Project Number RG-23092.
文摘Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or indirect slurs.To address this gap,we propose a hybrid framework combining Term Frequency-Inverse Document Frequency(TF-IDF),word-to-vector(Word2Vec),and Bidirectional Encoder Representations from Transformers(BERT)based models for multi-class cyberbullying detection.Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships,fused with BERT’s contextual embeddings to capture syntactic and semantic complexities.We evaluate the framework on a publicly available dataset of 47,000 annotated social media posts across five cyberbullying categories:age,ethnicity,gender,religion,and indirect aggression.Among BERT variants tested,BERT Base Un-Cased achieved the highest performance with 93%accuracy(standard deviation across±1%5-fold cross-validation)and an average AUC of 0.96,outperforming standalone TF-IDF(78%)and Word2Vec(82%)models.Notably,it achieved near-perfect AUC scores(0.99)for age and ethnicity-based bullying.A comparative analysis with state-of-the-art benchmarks,including Generative Pre-trained Transformer 2(GPT-2)and Text-to-Text Transfer Transformer(T5)models highlights BERT’s superiority in handling ambiguous language.This work advances cyberbullying detection by demonstrating how hybrid feature extraction and transformer models improve multi-class classification,offering a scalable solution for moderating nuanced harmful content.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01295).
文摘Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often struggle with low-contrast MRI images,class imbalance,and suboptimal feature extraction.This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans.Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization(CLAHE)and Enhanced Super-Resolution Generative Adversarial Networks(ESRGAN).A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient(MCC)-based evaluation method into the design.The trained and validated model gives a 98.88%accuracy rate and 0.9614 MCC score.We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52%(±1.51),a loss of 0.1671,and an MCC score of 0.9429 across folds.The proposed framework outperforms the state-of-the-art models with a 98%weighted F1-score while decreasing misdiagnosis results for every AD stage.The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis.These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis,contributing to improved computer-aided diagnosis(CAD)systems in clinical practice.
基金funding from the Princess Nourah bint Abdulrahman University Researchers Supporting Project(PNURSP2025R195)the University of Bisha through its Fast-Track Research Support Program.
文摘Artificial intelligence(AI),particularly deep learning algorithms utilizing convolutional neural networks,plays an increasingly pivotal role in enhancing medical image examination.It demonstrates the potential for improving diagnostic accuracy within dental care.Orthopantomograms(OPGs)are essential in dentistry;however,their manual interpretation is often inconsistent and tedious.To the best of our knowledge,this is the first comprehensive application of YOLOv5m for the simultaneous detection and classification of six distinct dental pathologies using panoramic OPG images.The model was trained and refined on a custom dataset that began with 232 panoramic radiographs and was later expanded to 604 samples.These included annotated subclasses representing Caries,Infection,Impacted Teeth,Fractured Teeth,Broken Crowns,and Healthy conditions.The training was performed using GPU resources alongside tuned hyperparameters of batch size,learning rate schedule,and early stopping tailored for generalization to prevent overfitting.Evaluation on a held-out test set showed strong performance in the detection and localization of various dental pathologies and robust overall accuracy.At an IoU of 0.5,the system obtained a mean precision of 94.22%and recall of 90.42%,with mAP being 93.71%.This research confirms the use of YOLOv5m as a robust,highly efficient AI technology for the analysis of dental pathologies using OPGs,providing a clinically useful solution to enhance workflow efficiency and aid in sustaining consistency in complex multi-dimensional case evaluations.
基金supported in part by the Shandong Provincial Natural Science Foundation under Grant ZR2021QF008the National Natural Science Foundation of China under Grant 62072351+1 种基金in part by the open research project of ZheJiang Lab under grant 2021PD0AB01in part by the 111 Project under Grant B16037。
文摘Accurate classification of encrypted traffic plays an important role in network management.However,current methods confronts several problems:inability to characterize traffic that exhibits great dispersion,inability to classify traffic with multi-level features,and degradation due to limited training traffic size.To address these problems,this paper proposes a traffic granularity-based cryptographic traffic classification method,called Granular Classifier(GC).In this paper,a novel Cardinality-based Constrained Fuzzy C-Means(CCFCM)clustering algorithm is proposed to address the problem caused by limited training traffic,considering the ratio of cardinality that must be linked between flows to achieve good traffic partitioning.Then,an original representation format of traffic is presented based on granular computing,named Traffic Granules(TG),to accurately describe traffic structure by catching the dispersion of different traffic features.Each granule is a compact set of similar data with a refined boundary by excluding outliers.Based on TG,GC is constructed to perform traffic classification based on multi-level features.The performance of the GC is evaluated based on real-world encrypted network traffic data.Experimental results show that the GC achieves outstanding performance for encrypted traffic classification with limited size of training traffic and keeps accurate classification in dynamic network conditions.
基金Item Sponsored by National Natural Science Foundation of China(60843007,61050006)
文摘Aiming at the limitations of rapid fault diagnosis of blast furnace, a novel strategy based on cost-conscious least squares support vector machine （LS-SVM） is proposed to solve this problem. Firstly, modified discrete particle swarm optimization is applied to optimize the feature selection and the LS-SVM parameters. Secondly, cost-con- scious formula is presented for fitness function and it contains in detail training time, recognition accuracy and the feature selection. The CLS-SVM algorithm is presented to increase the performance of the LS-SVM classifier. The new method can select the best fault features in much shorter time and have fewer support vectbrs and better general- ization performance in the application of fault diagnosis of the blast furnace. Thirdly, a gradual change binary tree is established for blast furnace faults diagnosis. It is a multi-class classification method based on center-of-gravity formula distance of cluster. A gradual change classification percentage ia used to select sample randomly. The proposed new metbod raises the sped of diagnosis, optimizes the classifieation scraraey and has good generalization ability for fault diagnosis of the application of blast furnace.
基金Item Sponsored by National Natural Science Foundation of China(61050006)
文摘Considering strip steel surface defect samples, a multi-class classification method was proposed based on enhanced least squares twin support vector machines （ELS-TWSVMs） and binary tree. Firstly, pruning region samples center method with adjustable pruning scale was used to prune data samples. This method could reduce classifierr s training time and testing time. Secondly, ELS-TWSVM was proposed to classify the data samples. By introducing error variable contribution parameter and weight parameter, ELS-TWSVM could restrain the impact of noise sam- ples and have better classification accuracy. Finally, multi-class classification algorithms of ELS-TWSVM were pro- posed by combining ELS-TWSVM and complete binary tree. Some experiments were made on two-dimensional data- sets and strip steel surface defect datasets. The experiments showed that the multi-class classification methods of ELS-TWSVM had higher classification speed and accuracy for the datasets with large-scale, unbalanced and noise samples.
基金supported by the National Natural Science Foundation of China(61703131 61703129+1 种基金 61701148 61703128)
文摘The basic idea of multi-class classification is a disassembly method,which is to decompose a multi-class classification task into several binary classification tasks.In order to improve the accuracy of multi-class classification in the case of insufficient samples,this paper proposes a multi-class classification method combining K-means and multi-task relationship learning(MTRL).The method first uses the split method of One vs.Rest to disassemble the multi-class classification task into binary classification tasks.K-means is used to down sample the dataset of each task,which can prevent over-fitting of the model while reducing training costs.Finally,the sampled dataset is applied to the MTRL,and multiple binary classifiers are trained together.With the help of MTRL,this method can utilize the inter-task association to train the model,and achieve the purpose of improving the classification accuracy of each binary classifier.The effectiveness of the proposed approach is demonstrated by experimental results on the Iris dataset,Wine dataset,Multiple Features dataset,Wireless Indoor Localization dataset and Avila dataset.
文摘Focusing on strip steel surface defects classification, a novel support vector machine with adjustable hyper-sphere （AHSVM） is formulated. Meanwhile, a new multi-class classification method is proposed. Originated from support vector data description, AHSVM adopts hyper-sphere to solve classification problem. AHSVM can obey two principles： the margin maximization and inner-class dispersion minimization. Moreover, the hyper-sphere of AHSVM is adjustable, which makes the final classification hyper-sphere optimal for training dataset. On the other hand, AHSVM is combined with binary tree to solve multi-class classification for steel surface defects. A scheme of samples pruning in mapped feature space is provided, which can reduce the number of training samples under the premise of classification accuracy, resulting in the improvements of classification speed. Finally, some testing experiments are done for eight types of strip steel surface defects. Experimental results show that multi-class AHSVM classifier exhibits satisfactory results in classification accuracy and efficiency.
基金This work was supported by the National Natural Science Foundation of China(No.51674140)Natural Science Foundation of Liaoning Province,China(No.20180550067)+2 种基金Department of Education of Liaoning Province,China(Nos.2017LNQN11 and 2020LNZD06)University of Science and Technology Liaoning Talent Project Grants(No.601011507-20)University of Science and Technology Liaoning Team Building Grants(No.601013360-17).
文摘Defect classification is the key task of a steel surface defect detection system.The current defect classification algorithms have not taken the feature noise into consideration.In order to reduce the adverse impact of feature noise,an anti-noise multi-class classification method was proposed for steel surface defects.On the one hand,a novel anti-noise support vector hyper-spheres(ASVHs)classifier was formulated.For N types of defects,the ASVHs classifier built N hyper-spheres.These hyper-spheres were insensitive to feature and label noise.On the other hand,in order to reduce the costs of online time and storage space,the defect samples were pruned by support vector data description with parameter iteration adjustment strategy.In the end,the ASVHs classifier was built with sparse defect samples set and auxiliary information.Experimental results show that the novel multi-class classification method has high efficiency and accuracy for corrupted defect samples in steel surface.
文摘The accurate identification and classification of various power quality disturbances are keys to ensuring high-quality electrical energy. In this study, the statistical characteristics of the disturbance signal of wavelet transform coefficients and wavelet transform energy distribution constitute feature vectors. These vectors are then trained and tested using SVM multi-class algorithms. Experimental results demonstrate that the SVM multi-class algorithms, which use the Gaussian radial basis function, exponential radial basis function, and hyperbolic tangent function as basis functions, are suitable methods for power quality disturbance classification.
基金This work was supported by the Research Program through the National Research Foundation of Korea,NRF-2022R1F1A1073375。
文摘Unlike external attacks,insider threats arise from legitimate users who belong to the organization.These individuals may be a potential threat for hostile behavior depending on their motives.For insider detection,many intrusion detection systems learn and prevent known scenarios,but because malicious behavior has similar patterns to normal behavior,in reality,these systems can be evaded.Furthermore,because insider threats share a feature space similar to normal behavior,identifying them by detecting anomalies has limitations.This study proposes an improved anomaly detection methodology for insider threats that occur in cybersecurity in which a discrete wavelet transformation technique is applied to classify normal vs.malicious users.The discrete wavelet transformation technique easily discovers new patterns or decomposes synthesized data,making it possible to distinguish between shared characteristics.To verify the efficacy of the proposed methodology,experiments were conducted in which normal users and malicious users were classified based on insider threat scenarios provided in Carnegie Mellon University’s Computer Emergency Response Team(CERT)dataset.The experimental results indicate that the proposed methodology with discrete wavelet transformation reduced the false-positive rate by 82%to 98%compared to the case with no wavelet applied.Thus,the proposed methodology has high potential for application to similar feature spaces.
基金supported by King Saud University,Riyadh,Saudi Arabia,under Ongoing Research Funding Program(ORF-2025-951).
文摘Human activity recognition is a significant area of research in artificial intelligence for surveillance,healthcare,sports,and human-computer interaction applications.The article benchmarks the performance of You Only Look Once version 11-based(YOLOv11-based)architecture for multi-class human activity recognition.The article benchmarks the performance of You Only Look Once version 11-based(YOLOv11-based)architecture for multi-class human activity recognition.The dataset consists of 14,186 images across 19 activity classes,from dynamic activities such as running and swimming to static activities such as sitting and sleeping.Preprocessing included resizing all images to 512512 pixels,annotating them in YOLO’s bounding box format,and applying data augmentation methods such as flipping,rotation,and cropping to enhance model generalization.The proposed model was trained for 100 epochs with adaptive learning rate methods and hyperparameter optimization for performance improvement,with a mAP@0.5 of 74.93%and a mAP@0.5-0.95 of 64.11%,outperforming previous versions of YOLO(v10,v9,and v8)and general-purpose architectures like ResNet50 and EfficientNet.It exhibited improved precision and recall for all activity classes with high precision values of 0.76 for running,0.79 for swimming,0.80 for sitting,and 0.81 for sleeping,and was tested for real-time deployment with an inference time of 8.9 ms per image,being computationally light.Proposed YOLOv11’s improvements are attributed to architectural advancements like a more complex feature extraction process,better attention modules,and an anchor-free detection mechanism.While YOLOv10 was extremely stable in static activity recognition,YOLOv9 performed well in dynamic environments but suffered from overfitting,and YOLOv8,while being a decent baseline,failed to differentiate between overlapping static activities.The experimental results determine proposed YOLOv11 to be the most appropriate model,providing an ideal balance between accuracy,computational efficiency,and robustness for real-world deployment.Nevertheless,there exist certain issues to be addressed,particularly in discriminating against visually similar activities and the use of publicly available datasets.Future research will entail the inclusion of 3D data and multimodal sensor inputs,such as depth and motion information,for enhancing recognition accuracy and generalizability to challenging real-world environments.
基金This paper is partially supported by National Natural Foundation of China(Grant No.61772561)the Key Research&Development Plan of Hunan Province(Grant No.2018NK2012)+2 种基金Postgraduate Research and Innovative Project of Central South University of Forestry and Technology(Grant No.20183012)Graduate Education and Teaching Reform Project of Central South University of Forestry and Technology(Grant No.2018JG005)Teaching Reform Project of Central South University of Forestry and Technology(Grant No.20180682).
文摘With the development of deep learning and Convolutional Neural Networks(CNNs),the accuracy of automatic food recognition based on visual data have significantly improved.Some research studies have shown that the deeper the model is,the higher the accuracy is.However,very deep neural networks would be affected by the overfitting problem and also consume huge computing resources.In this paper,a new classification scheme is proposed for automatic food-ingredient recognition based on deep learning.We construct an up-to-date combinational convolutional neural network(CBNet)with a subnet merging technique.Firstly,two different neural networks are utilized for learning interested features.Then,a well-designed feature fusion component aggregates the features from subnetworks,further extracting richer and more precise features for image classification.In order to learn more complementary features,the corresponding fusion strategies are also proposed,including auxiliary classifiers and hyperparameters setting.Finally,CBNet based on the well-known VGGNet,ResNet and DenseNet is evaluated on a dataset including 41 major categories of food ingredients and 100 images for each category.Theoretical analysis and experimental results demonstrate that CBNet achieves promising accuracy for multi-class classification and improves the performance of convolutional neural networks.
基金Sponsored by the National Natural Science Foundation of China(Grant No.61201310)the Fundamental Research Funds for the Central Universities(Grant No.HIT.NSRIF.201160)the China Postdoctoral Science Foundation(Grant No.20110491067)
文摘Based on the framework of support vector machines （SVM） using one-against-one （OAO） strategy, a new multi-class kernel method based on directed aeyclie graph （DAG） and probabilistic distance is proposed to raise the multi-class classification accuracies. The topology structure of DAG is constructed by rearranging the nodes＇ sequence in the graph. DAG is equivalent to guided operating SVM on a list, and the classification performance depends on the nodes＇ sequence in the graph. Jeffries-Matusita distance （JMD） is introduced to estimate the separability of each class, and the implementation list is initialized with all classes organized according to certain sequence in the list. To testify the effectiveness of the proposed method, numerical analysis is conducted on UCI data and hyperspectral data. Meanwhile, comparative studies using standard OAO and DAG classification methods are also conducted and the results illustrate better performance and higher accuracy of the orooosed JMD-DAG method.
基金Digitalized PV plant project financed by OCP group[Reference:Digital and smart photovoltaic power plant].
文摘This paper presents a holistic multimodal approach for real-time anomaly detection and classification in largescale photovoltaic plants.The approach encompasses segmentation,geolocation,and classification of individual photovoltaic modules.A fine-tuned Yolov7 model was trained for the individual module’s segmentation of both modalities;RGB and IR images.The localization of individual solar panels relies on photogrammetric measurements to facilitate maintenance operations.The localization process also links extracted images of the same panel using their geographical coordinates and preprocesses them for the multimodal model input.The study also focuses on optimizing pre-trained models using Bayesian search to improve and fine-tune them with our dataset.The dataset was collected from different systems and technologies within our research platform.It has been curated into 1841 images and classified into five anomaly classes.Grad-CAM,an explainable AI tool,is utilized to compare the use of multimodality to a single modality.Finally,for real-time optimization,the ONNX format was used to optimize the model further for deployment in real-time.The improved ConvNext-Tiny model performed well in both modalities,with 99%precision,recall,and F1-score for binary classification and 85%for multi-class classification.In terms of latency,the segmentation models have an inference time of 14 ms and 12 ms for RGB and IR images and 24 ms for detection and classification.The proposed holistic approach includes a built-in feedback loop to ensure the model’s robustness against domain shifts in the production environment.
基金Supported by the National Defense Pre-Research Foundation of China (Grant No.9140A05070107BQ0204)
文摘In this paper,a new multiclass classification algorithm is proposed based on the idea of Locally Linear Embedding(LLE),to avoid the defect of traditional manifold learning algorithms,which can not deal with new sample points.The algorithm defines an error as a criterion by computing a sample's reconstruction weight using LLE.Furthermore,the existence and characteristics of low dimensional manifold in range-profile time-frequency information are explored using manifold learning algorithm,aiming at the problem of target recognition about high range resolution MilliMeter-Wave(MMW) radar.The new algorithm is applied to radar target recognition.The experiment results show the algorithm is efficient.Compared with other classification algorithms,our method improves the recognition precision and the result is not sensitive to input parameters.
