Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional ...Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance.展开更多
Background:Stomach cancer(SC)is one of the most lethal malignancies worldwide due to late-stage diagnosis and limited treatment.The transcriptomic,epigenomic,and proteomic,etc.,omics datasets generated by high-through...Background:Stomach cancer(SC)is one of the most lethal malignancies worldwide due to late-stage diagnosis and limited treatment.The transcriptomic,epigenomic,and proteomic,etc.,omics datasets generated by high-throughput sequencing technology have become prominent in biomedical research,and they reveal molecular aspects of cancer diagnosis and therapy.Despite the development of advanced sequencing technology,the presence of high-dimensionality in multi-omics data makes it challenging to interpret the data.Methods:In this study,we introduce RankXLAN,an explainable ensemble-based multi-omics framework that integrates feature selection(FS),ensemble learning,bioinformatics,and in-silico validation for robust biomarker detection,potential therapeutic drug-repurposing candidates’identification,and classification of SC.To enhance the interpretability of the model,we incorporated explainable artificial intelligence(SHapley Additive exPlanations analysis),as well as accuracy,precision,F1-score,recall,cross-validation,specificity,likelihood ratio(LR)+,LR−,and Youden index results.Results:The experimental results showed that the top four FS algorithms achieved improved results when applied to the ensemble learning classification model.The proposed ensemble model produced an area under the curve(AUC)score of 0.994 for gene expression,0.97 for methylation,and 0.96 for miRNA expression data.Through the integration of bioinformatics and ML approach of the transcriptomic and epigenomic multi-omics dataset,we identified potential marker genes,namely,UBE2D2,HPCAL4,IGHA1,DPT,and FN3K.In-silico molecular docking revealed a strong binding affinity between ANKRD13C and the FDA-approved drug Everolimus(binding affinity−10.1 kcal/mol),identifying ANKRD13C as a potential therapeutic drug-repurposing target for SC.Conclusion:The proposed framework RankXLAN outperforms other existing frameworks for serum biomarker identification,therapeutic target identification,and SC classification with multi-omics datasets.展开更多
This paper presents a unified Unmanned Aerial Vehicle-based(UAV-based)traffic monitoring framework that integrates vehicle detection,tracking,counting,motion prediction,and classification in a modular and co-optimized...This paper presents a unified Unmanned Aerial Vehicle-based(UAV-based)traffic monitoring framework that integrates vehicle detection,tracking,counting,motion prediction,and classification in a modular and co-optimized pipeline.Unlike prior works that address these tasks in isolation,our approach combines You Only Look Once(YOLO)v10 detection,ByteTrack tracking,optical-flow density estimation,Long Short-Term Memory-based(LSTM-based)trajectory forecasting,and hybrid Speeded-Up Robust Feature(SURF)+Gray-Level Co-occurrence Matrix(GLCM)feature engineering with VGG16 classification.Upon the validation across datasets(UAVDT and UAVID)our framework achieved a detection accuracy of 94.2%,and 92.3%detection accuracy when conducting a real-time UAV field validation.Our comprehensive evaluations,including multi-metric analyses,ablation studies,and cross-dataset validations,confirm the framework’s accuracy,efficiency,and generalizability.These results highlight the novelty of integrating complementary methods into a single framework,offering a practical solution for accurate and efficient UAV-based traffic monitoring.展开更多
A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such...A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such as casual and athletic styles,and consider attributes like color and texture when selecting outfits.To achieve personalized outfit recommendations in line with user style preferences,this paper proposes a personal style guided outfit recommendation with multi-modal fashion compatibility modeling,termed as PSGNet.Firstly,a style classifier is designed to categorize fashion images of various clothing types and attributes into distinct style categories.Secondly,a personal style prediction module extracts user style preferences by analyzing historical data.Then,to address the limitations of single-modal representations and enhance fashion compatibility,both fashion images and text data are leveraged to extract multi-modal features.Finally,PSGNet integrates these components through Bayesian personalized ranking(BPR)to unify the personal style and fashion compatibility,where the former is used as personal style features and guides the output of the personalized outfit recommendation tailored to the target user.Extensive experiments on large-scale datasets demonstrate that the proposed model is efficient on the personalized outfit recommendation.展开更多
Driven by both the“new engineering”initiative and the energy revolution,the traditional engineering education model can hardly meet the demand of the energy and electric power industry for diversified and interdisci...Driven by both the“new engineering”initiative and the energy revolution,the traditional engineering education model can hardly meet the demand of the energy and electric power industry for diversified and interdisciplinary outstanding engineers.Based on the“industry-university-research-application”four-in-one collaborative education concept,this paper constructs a new training system centered on classified cultivation and classified evaluation.The system aims to solve core problems such as homogeneous training,disconnection between industry and academia,single evaluation method,and insufficient faculty.Through measures including modular courses,the dual-tutor system,and diversified practical platforms,it realizes differentiated and precise talent training,so as to deliver outstanding engineers with the ability to“define problems,break through technologies,and create value”for the energy and electric power industry.展开更多
In 5G new radio(NR), polar codes are adopted for e MBB downlink control channels where the blind detection is employed in user equipment(UE) to identify the correct downlink control information(DCI). However, differen...In 5G new radio(NR), polar codes are adopted for e MBB downlink control channels where the blind detection is employed in user equipment(UE) to identify the correct downlink control information(DCI). However, different from that in the 4G LTE system, the cyclic redundancy check(CRC) in polar decoding plays both error correction and error detection roles. Consequently, the false alarm rates(FAR) may not meet the system requirements(FAR<1.52 × 10^(−5)). In this paper, to mitigate the FAR in polar code blind detection, we attach a binary classifier after the polar decoder to further remove the false alarm results and meanwhile retain the correct DCI. This classifier works by tracking the squared Euclidean distance ratio(SEDR) between the received signal and hypothesis. We derive an analytical method to fast compute proper classification threshold that is implementation-friendly in practical use. Combining the well-designed classifier, we show that some very short CRC sequences can even be used to meet the FAR requirements. This consequently reduces the CRC overhead and contributes to the system error performance improvements.展开更多
The current journal is mainly focused in zoological systematics. According to Systematics Agenda 2000(1994), systematics is the science built on the following tasks: Taxonomy—the science of discovering, describing, a...The current journal is mainly focused in zoological systematics. According to Systematics Agenda 2000(1994), systematics is the science built on the following tasks: Taxonomy—the science of discovering, describing, and classifying species or groups of species(together termed taxa);Phylogenetic analysis—the discovery of the evolutionary relationships among a group of species;and Classification—the grouping of species, ultimately on the basis of evolutionary relationships.展开更多
Background:In the field of genetic diagnostics,DNA sequencing is an important tool because the depth and complexity of this field have major implications in light of the genetic architectures of diseases and the ident...Background:In the field of genetic diagnostics,DNA sequencing is an important tool because the depth and complexity of this field have major implications in light of the genetic architectures of diseases and the identification of risk factors associated with genetic disorders.Methods:Our study introduces a novel two-tiered analytical framework to raise the precision and reliability of genetic data interpretation.It is initiated by extracting and analyzing salient features from DNA sequences through a CNN-based feature analysis,taking advantage of the power inherent in Convolutional neural networks(CNNs)to attain complex patterns and minute mutations in genetic data.This study embraces an elite collection of machine learning classifiers interweaved through a stern voting mechanism,which synergistically joins the predictions made from multiple classifiers to generate comprehensive and well-balanced interpretations of the genetic data.Results:This state-of-the-art method was further tested by carrying out an empirical analysis on a variants'dataset of DNA sequences taken from patients affected by breast cancer,juxtaposed with a control group composed of healthy people.Thus,the integration of CNNs with a voting-based ensemble of classifiers returned outstanding outcomes,with performance metrics accuracy,precision,recall,and F1-scorereaching the outstanding rate of 0.88,outperforming previous models.Conclusions:This dual accomplishment underlines the transformative potential that integrating deep learning techniques with ensemble machine learning might provide in real added value for further genetic diagnostics and prognostics.These results from this study set a new benchmark in the accuracy of disease diagnosis through DNA sequencing and promise future studies on improved personalized medicine and healthcare approaches with precise genetic information.展开更多
Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot interaction.However,recognizing actions f...Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot interaction.However,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera angles.This research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)videos.The first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale images.The YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further processing.The joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are included.These features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity classification.Real-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing methods.In particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.展开更多
Metal-organic frameworks(MOFs)have garnered widespread attention due to their designability and diversity[1].Customization has always been a pursuit of chemists and materials scientists[2].Topology provides a means of...Metal-organic frameworks(MOFs)have garnered widespread attention due to their designability and diversity[1].Customization has always been a pursuit of chemists and materials scientists[2].Topology provides a means of abstracting the complex structures of MOFs by identifying and classifying the fundamental building units and connection patterns,simplifying the understanding of MOF structures[3].展开更多
Background:Diabetic retinopathy remains one of the leading causes of vision impairment globally and poses diagnostic challenges due to the complexity of clinical imaging data and variability in disease progression.In ...Background:Diabetic retinopathy remains one of the leading causes of vision impairment globally and poses diagnostic challenges due to the complexity of clinical imaging data and variability in disease progression.In this study,we propose an innovative methodology that integrates artificial intelligence and quantum computing to enhance the early detection and clinical management of diabetic retinopathy.Methods:We developed a hybrid model combining machine learning algorithms with simulated quantum circuits to classify retinal images and associated clinical data.Anonymized datasets were used,and deep inductive transfer techniques were applied to improve diagnostic precision and generalizability.Results:The proposed model achieved a classification accuracy of 94.6%,significantly reducing diagnostic time and improving the prioritization of high-risk cases compared to conventional methods.The hybrid approach demonstrated superior performance in processing speed and accuracy for complex clinical scenarios.Conclusion:This study highlights the potential of combining AI and quantum computing to revolutionize the diagnosis of diabetic retinopathy.The proposed model provides a scalable and efficient solution for clinical environments,enabling faster and more accurate decision-making in ophthalmic care.展开更多
Machinery condition monitoring is beneficial to equipment maintenance and has been receiving much attention from academia and industry.Machine learning,especially deep learning,has become popular for machinery conditi...Machinery condition monitoring is beneficial to equipment maintenance and has been receiving much attention from academia and industry.Machine learning,especially deep learning,has become popular for machinery condition monitoring because that can fully use available data and computational power.Since significant accidents might be caused if wrong fault alarms are given for machine condition monitoring,interpretable machine learning models,integrate signal processing knowledge to enhance trustworthiness of models,are gradually becoming a research hotspot.A previous spectrum-based and interpretable optimized weights method has been proposed to indicate faulty and fundamental frequencies when the analyzed data only contains a healthy type and a fault type.Considering that multiclass fault types are naturally met in practice,this work aims to explore the interpretable optimized weights method for multiclass fault type scenarios.Therefore,a new multiclass optimized weights spectrum(OWS)is proposed and further studied theoretically and numerically.It is found that the multiclass OWS is capable of capturing the characteristic components associated with different conditions and clearly indicating specific fault characteristic frequencies(FCFs)corresponding to each fault condition.This work can provide new insights into spectrum-based fault classification models,and the new multiclass OWS also shows great potential for practical applications.展开更多
The categorization of brain tumors is a significant issue for healthcare applications.Perfect and timely identification of brain tumors is important for employing an effective treatment of this disease.Brain tumors po...The categorization of brain tumors is a significant issue for healthcare applications.Perfect and timely identification of brain tumors is important for employing an effective treatment of this disease.Brain tumors possess high changes in terms of size,shape,and amount,and hence the classification process acts as a more difficult research problem.This paper suggests a deep learning model using the magnetic resonance imaging technique that overcomes the limitations associated with the existing classification methods.The effectiveness of the suggested method depends on the coyote optimization algorithm,also known as the LOBO algorithm,which optimizes the weights of the deep-convolutional neural network classifier.The accuracy,sensitivity,and specificity indices,which are obtained to be 92.40%,94.15%,and 91.92%,respectively,are used to validate the effectiveness of the suggested method.The result suggests that the suggested strategy is superior for effectively classifying brain tumors.展开更多
This study presents an efficient feature selection method based on the Gower distance to enhance the accuracy and efficiency of standard classifiers on high-dimensional medical datasets.High-dimensional data poses sig...This study presents an efficient feature selection method based on the Gower distance to enhance the accuracy and efficiency of standard classifiers on high-dimensional medical datasets.High-dimensional data poses significant challenges for traditional classifiers due to feature redundancy or being irrelevant.The proposed method addresses these challenges by partitioning the dataset into blocks,calculating the Gower distance within each block,and selecting features based on their average similarity.Technically,the Gower distance normalizes the absolute difference between numerical features,ensuring that each feature contributes equally to the distance calculation.This normalization prevents features with larger scales from overshadowing those with smaller scales.This process facilitates the identification of features that exhibit high harmony and are the most relevant for classification.The proposed feature selection strategy significantly reduces dimensionality,retains the most relevant features,and improves model performance.Experimental results show that the accuracy for the classifiers including k-nearest neighbors(KNN),naive Bayes(NB),decision tree(DT),random forest(RF),support vector machine(SVM),and logistic regression(LR)was increased by 4.38%-7.02%.Besides,the reduction in the feature set size contributes to a considerable decrease in computational complexity and thus faster diagnosis speed.The execution time was averagely reduced by 77.82%for all samples and 76.45%for one sample.These results demonstrate that the proposed feature selection method shows enhanced performance on both prediction accuracy and diagnostic speed,making it a promising tool for real-time clinical decision-making and improving patient care outcomes.展开更多
Existing weakly supervised semantic segmentation(WSSS)methods based on image-level labels always rely on class activation maps(CAMs),which measure the relationships between features and classifiers.However,CAMs only f...Existing weakly supervised semantic segmentation(WSSS)methods based on image-level labels always rely on class activation maps(CAMs),which measure the relationships between features and classifiers.However,CAMs only focus on the most discriminative regions of images,resulting in their poor coverage performance.We attribute this to the deficiency in the recognition ability of a single classifier and the negative impacts caused by magnitudes during the CAMs normalisation process.To address the aforementioned issues,we propose to construct selective multiple classifiers(SMC).During the training process,we extract multiple prototypes for each class and store them in the corresponding memory bank.These prototypes are divided into foreground and background prototypes,with the former used to identify foreground objects and the latter aimed at preventing the false activation of background pixels.As for the inference stage,multiple prototypes are adaptively selected from the memory bank for each image as SMC.Subsequently,CAMs are generated by measuring the angle between SMC and features.We enhance the recognition ability of classifiers by adaptively constructing multiple classifiers for each image,while only relying on angle measurement to generate CAMs can alleviate the suppression phenomenon caused by magnitudes.Furthermore,SMC can be integrated into other WSSS approaches to help generate better CAMs.Extensive experiments conducted on standard WSSS benchmarks such as PASCAL VOC 2012 and MS COCO 2014 demonstrate the superiority of our proposed method.展开更多
Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computation...Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computational complexity,limited generalizability under varying conditions,and compromised real-time performance.To counter these,this paper introduces an Active Learning-aided Heuristic Deep Spatio-Textural Ensemble Learning(ALH-DSEL)framework.The model initially identifies keyframes from the surveillance videos with a Multi-Constraint Active Learning(MCAL)approach,with features extracted from DenseNet121.The frames are then segmented employing an optimized Fuzzy C-Means clustering algorithm with Firefly to identify areas of interest.A deep ensemble feature extractor,comprising DenseNet121,EfficientNet-B7,MobileNet,and GLCM,extracts varied spatial and textural features.Fused characteristics are enhanced through PCA and Min-Max normalization and discriminated by a maximum voting ensemble of RF,AdaBoost,and XGBoost.The experimental results show that ALH-DSEL provides higher accuracy,precision,recall,and F1-score,validating its superiority for real-time HAR in surveillance scenarios.展开更多
The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic techno...The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic technology,plays a pivotal role in ensuring mine safety by enabling real-time identifi cation and accurate classification of vibration signals such as microseismic signals,blasting signals,and noise.These classifications are critical for improving the efficacy of ground pressure monitoring systems,conducting stability analyses of deep rock masses,and implementing timely and precise roadway support measures.Such eff orts are essential for mitigating ground pressure disasters and ensuring safe mining operations.This study proposes an artificial intelligence-based automatic classification network model for mine vibration signals.Based on conventional convolutional neural networks,the proposed model further incorporates long short-term memory(LSTM)networks and attention mechanisms.The LSTM component eff ectively captures temporal correlations in time-series mining vibration data,while the attention mechanism enhances the models’ability to focus on critical features within the data.To validate the eff ectiveness of our proposed model,a dataset comprising 480,526 waveform records collected in 2022 by the microseismic monitoring system at Guangxi Shanhu Tungsten Mine was used for training,validation,and testing purposes.Results demonstrate that the proposed artifi cial intelligence-based classifi cation method achieves a higher recognition accuracy of 92.21%,significantly outperforming traditional manual classification methods.The proposed model represents a signifi cant advancement in ground pressure monitoring and disaster mitigation.展开更多
BACKGROUND The early diagnosis rate of pancreatic ductal adenocarcinoma(PDAC)is low and the prognosis is poor.It is important to develop an interpretable noninvasive early diagnostic model in clinical practice.AIM To ...BACKGROUND The early diagnosis rate of pancreatic ductal adenocarcinoma(PDAC)is low and the prognosis is poor.It is important to develop an interpretable noninvasive early diagnostic model in clinical practice.AIM To develop an interpretable noninvasive early diagnostic model for PDAC using plasma extracellular vesicle long RNA(EvlRNA).METHODS The diagnostic model was constructed based on plasma EvlRNA data.During the process of establishing the model,EvlRNA-index was introduced,and four algorithms were adopted to calculate EvlRNA-index.After the model was successfully constructed,performance evaluation was conducted.A series of bioinformatics methods were adopted to explore the potential mechanism of EvlRNA-index as the input feature of the model.And the relationship between key characteristics and PDAC were explored at the single-cell level.RESULTS A novel interpretable machine learning framework was developed based on plasma EvlRNA.In this framework,a two-layer classifier was established.A new concept was proposed:EvlRNA-index.Based on EvlRNA-index,a cancer diagnostic model was established,and a good diagnostic effect was achieved.The accuracy of PDACandCPvsHealth-Probabilistic PCA Index-SVM(PDAC and chronic pancreatitis vs health-probabilistic principal component analysis index-support vector machine)(1-18)was 91.51%,with Mathew’s correlation coefficient 0.7760 and area under the curve 0.9560.In the second layer of the model,the accuracy of PDACvsCP-Probabilistic PCA Index-RF(PDAC vs chronic pancreatitis-probabilistic principal component analysis index-random forest)(2-17)was 93.83%,with Mathew’s correlation coefficient 0.8422 and area under the curve 0.9698.Forty-nine PDAC-related genes were identified,among which 16 were known,inferring that the remaining ones were also PDAC-related genes.CONCLUSION An interpretable two-layer machine learning framework was proposed for early diagnosis and prediction of PDAC based on plasma EvlRNA,providing new insights into the clinical value of EvlRNA.展开更多
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.RS-2024-00406320)the Institute of Information&Communica-tions Technology Planning&Evaluation(IITP)-Innovative Human Resource Development for Local Intellectualization Program Grant funded by the Korea government(MSIT)(IITP-2026-RS-2023-00259678).
文摘Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance.
基金the Deanship of Research and Graduate Studies at King Khalid University,KSA,for funding this work through the Large Research Project under grant number RGP2/164/46.
文摘Background:Stomach cancer(SC)is one of the most lethal malignancies worldwide due to late-stage diagnosis and limited treatment.The transcriptomic,epigenomic,and proteomic,etc.,omics datasets generated by high-throughput sequencing technology have become prominent in biomedical research,and they reveal molecular aspects of cancer diagnosis and therapy.Despite the development of advanced sequencing technology,the presence of high-dimensionality in multi-omics data makes it challenging to interpret the data.Methods:In this study,we introduce RankXLAN,an explainable ensemble-based multi-omics framework that integrates feature selection(FS),ensemble learning,bioinformatics,and in-silico validation for robust biomarker detection,potential therapeutic drug-repurposing candidates’identification,and classification of SC.To enhance the interpretability of the model,we incorporated explainable artificial intelligence(SHapley Additive exPlanations analysis),as well as accuracy,precision,F1-score,recall,cross-validation,specificity,likelihood ratio(LR)+,LR−,and Youden index results.Results:The experimental results showed that the top four FS algorithms achieved improved results when applied to the ensemble learning classification model.The proposed ensemble model produced an area under the curve(AUC)score of 0.994 for gene expression,0.97 for methylation,and 0.96 for miRNA expression data.Through the integration of bioinformatics and ML approach of the transcriptomic and epigenomic multi-omics dataset,we identified potential marker genes,namely,UBE2D2,HPCAL4,IGHA1,DPT,and FN3K.In-silico molecular docking revealed a strong binding affinity between ANKRD13C and the FDA-approved drug Everolimus(binding affinity−10.1 kcal/mol),identifying ANKRD13C as a potential therapeutic drug-repurposing target for SC.Conclusion:The proposed framework RankXLAN outperforms other existing frameworks for serum biomarker identification,therapeutic target identification,and SC classification with multi-omics datasets.
基金supported by the IITP(Institute of Information&Communications Technology Planning&Evaluation)-ICAN(ICT Challenge and Advanced Network of HRD)(IITP-2025-RS-2022-00156326,50)grant funded by theKorea government(Ministry of Science and ICT)supported and funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R410)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia。
文摘This paper presents a unified Unmanned Aerial Vehicle-based(UAV-based)traffic monitoring framework that integrates vehicle detection,tracking,counting,motion prediction,and classification in a modular and co-optimized pipeline.Unlike prior works that address these tasks in isolation,our approach combines You Only Look Once(YOLO)v10 detection,ByteTrack tracking,optical-flow density estimation,Long Short-Term Memory-based(LSTM-based)trajectory forecasting,and hybrid Speeded-Up Robust Feature(SURF)+Gray-Level Co-occurrence Matrix(GLCM)feature engineering with VGG16 classification.Upon the validation across datasets(UAVDT and UAVID)our framework achieved a detection accuracy of 94.2%,and 92.3%detection accuracy when conducting a real-time UAV field validation.Our comprehensive evaluations,including multi-metric analyses,ablation studies,and cross-dataset validations,confirm the framework’s accuracy,efficiency,and generalizability.These results highlight the novelty of integrating complementary methods into a single framework,offering a practical solution for accurate and efficient UAV-based traffic monitoring.
基金Shanghai Frontier Science Research Center for Modern Textiles,Donghua University,ChinaOpen Project of Henan Key Laboratory of Intelligent Manufacturing of Mechanical Equipment,Zhengzhou University of Light Industry,China(No.IM202303)National Key Research and Development Program of China(No.2019YFB1706300)。
文摘A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such as casual and athletic styles,and consider attributes like color and texture when selecting outfits.To achieve personalized outfit recommendations in line with user style preferences,this paper proposes a personal style guided outfit recommendation with multi-modal fashion compatibility modeling,termed as PSGNet.Firstly,a style classifier is designed to categorize fashion images of various clothing types and attributes into distinct style categories.Secondly,a personal style prediction module extracts user style preferences by analyzing historical data.Then,to address the limitations of single-modal representations and enhance fashion compatibility,both fashion images and text data are leveraged to extract multi-modal features.Finally,PSGNet integrates these components through Bayesian personalized ranking(BPR)to unify the personal style and fashion compatibility,where the former is used as personal style features and guides the output of the personalized outfit recommendation tailored to the target user.Extensive experiments on large-scale datasets demonstrate that the proposed model is efficient on the personalized outfit recommendation.
文摘Driven by both the“new engineering”initiative and the energy revolution,the traditional engineering education model can hardly meet the demand of the energy and electric power industry for diversified and interdisciplinary outstanding engineers.Based on the“industry-university-research-application”four-in-one collaborative education concept,this paper constructs a new training system centered on classified cultivation and classified evaluation.The system aims to solve core problems such as homogeneous training,disconnection between industry and academia,single evaluation method,and insufficient faculty.Through measures including modular courses,the dual-tutor system,and diversified practical platforms,it realizes differentiated and precise talent training,so as to deliver outstanding engineers with the ability to“define problems,break through technologies,and create value”for the energy and electric power industry.
基金supported in part by National Natural Science Foundation of China(No.62471054)in part by National Natural Science Foundation of China(No.92467301)+3 种基金in part by the National Natural Science Foundation of China(No.62201562)in part by the National Natural Science Foundation of China(No.62371063)in part by the National Natural Science Foundation of China(No.62321001)in part by Liaoning Provincial Natural Science Foundation of China(No.2024–BSBA–51).
文摘In 5G new radio(NR), polar codes are adopted for e MBB downlink control channels where the blind detection is employed in user equipment(UE) to identify the correct downlink control information(DCI). However, different from that in the 4G LTE system, the cyclic redundancy check(CRC) in polar decoding plays both error correction and error detection roles. Consequently, the false alarm rates(FAR) may not meet the system requirements(FAR<1.52 × 10^(−5)). In this paper, to mitigate the FAR in polar code blind detection, we attach a binary classifier after the polar decoder to further remove the false alarm results and meanwhile retain the correct DCI. This classifier works by tracking the squared Euclidean distance ratio(SEDR) between the received signal and hypothesis. We derive an analytical method to fast compute proper classification threshold that is implementation-friendly in practical use. Combining the well-designed classifier, we show that some very short CRC sequences can even be used to meet the FAR requirements. This consequently reduces the CRC overhead and contributes to the system error performance improvements.
文摘The current journal is mainly focused in zoological systematics. According to Systematics Agenda 2000(1994), systematics is the science built on the following tasks: Taxonomy—the science of discovering, describing, and classifying species or groups of species(together termed taxa);Phylogenetic analysis—the discovery of the evolutionary relationships among a group of species;and Classification—the grouping of species, ultimately on the basis of evolutionary relationships.
文摘Background:In the field of genetic diagnostics,DNA sequencing is an important tool because the depth and complexity of this field have major implications in light of the genetic architectures of diseases and the identification of risk factors associated with genetic disorders.Methods:Our study introduces a novel two-tiered analytical framework to raise the precision and reliability of genetic data interpretation.It is initiated by extracting and analyzing salient features from DNA sequences through a CNN-based feature analysis,taking advantage of the power inherent in Convolutional neural networks(CNNs)to attain complex patterns and minute mutations in genetic data.This study embraces an elite collection of machine learning classifiers interweaved through a stern voting mechanism,which synergistically joins the predictions made from multiple classifiers to generate comprehensive and well-balanced interpretations of the genetic data.Results:This state-of-the-art method was further tested by carrying out an empirical analysis on a variants'dataset of DNA sequences taken from patients affected by breast cancer,juxtaposed with a control group composed of healthy people.Thus,the integration of CNNs with a voting-based ensemble of classifiers returned outstanding outcomes,with performance metrics accuracy,precision,recall,and F1-scorereaching the outstanding rate of 0.88,outperforming previous models.Conclusions:This dual accomplishment underlines the transformative potential that integrating deep learning techniques with ensemble machine learning might provide in real added value for further genetic diagnostics and prognostics.These results from this study set a new benchmark in the accuracy of disease diagnosis through DNA sequencing and promise future studies on improved personalized medicine and healthcare approaches with precise genetic information.
基金funded by the Open Access Initiative of the University of Bremen and the DFG via SuUB Bremen.Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2024R348),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot interaction.However,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera angles.This research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)videos.The first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale images.The YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further processing.The joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are included.These features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity classification.Real-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing methods.In particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.
基金supported by the National Natural Science Foundation of China(22101039,22471027,22311530679)the Science Fund for Creative Research Groups of the National Natural Science Foundation of China(22021005)the Fundamental Research Funds for the Central Universities(DUT24LK004).
文摘Metal-organic frameworks(MOFs)have garnered widespread attention due to their designability and diversity[1].Customization has always been a pursuit of chemists and materials scientists[2].Topology provides a means of abstracting the complex structures of MOFs by identifying and classifying the fundamental building units and connection patterns,simplifying the understanding of MOF structures[3].
文摘Background:Diabetic retinopathy remains one of the leading causes of vision impairment globally and poses diagnostic challenges due to the complexity of clinical imaging data and variability in disease progression.In this study,we propose an innovative methodology that integrates artificial intelligence and quantum computing to enhance the early detection and clinical management of diabetic retinopathy.Methods:We developed a hybrid model combining machine learning algorithms with simulated quantum circuits to classify retinal images and associated clinical data.Anonymized datasets were used,and deep inductive transfer techniques were applied to improve diagnostic precision and generalizability.Results:The proposed model achieved a classification accuracy of 94.6%,significantly reducing diagnostic time and improving the prioritization of high-risk cases compared to conventional methods.The hybrid approach demonstrated superior performance in processing speed and accuracy for complex clinical scenarios.Conclusion:This study highlights the potential of combining AI and quantum computing to revolutionize the diagnosis of diabetic retinopathy.The proposed model provides a scalable and efficient solution for clinical environments,enabling faster and more accurate decision-making in ophthalmic care.
基金supported by the National Natural Science Foundation of China under Grant Nos.523B2043 and 52475112.
文摘Machinery condition monitoring is beneficial to equipment maintenance and has been receiving much attention from academia and industry.Machine learning,especially deep learning,has become popular for machinery condition monitoring because that can fully use available data and computational power.Since significant accidents might be caused if wrong fault alarms are given for machine condition monitoring,interpretable machine learning models,integrate signal processing knowledge to enhance trustworthiness of models,are gradually becoming a research hotspot.A previous spectrum-based and interpretable optimized weights method has been proposed to indicate faulty and fundamental frequencies when the analyzed data only contains a healthy type and a fault type.Considering that multiclass fault types are naturally met in practice,this work aims to explore the interpretable optimized weights method for multiclass fault type scenarios.Therefore,a new multiclass optimized weights spectrum(OWS)is proposed and further studied theoretically and numerically.It is found that the multiclass OWS is capable of capturing the characteristic components associated with different conditions and clearly indicating specific fault characteristic frequencies(FCFs)corresponding to each fault condition.This work can provide new insights into spectrum-based fault classification models,and the new multiclass OWS also shows great potential for practical applications.
文摘The categorization of brain tumors is a significant issue for healthcare applications.Perfect and timely identification of brain tumors is important for employing an effective treatment of this disease.Brain tumors possess high changes in terms of size,shape,and amount,and hence the classification process acts as a more difficult research problem.This paper suggests a deep learning model using the magnetic resonance imaging technique that overcomes the limitations associated with the existing classification methods.The effectiveness of the suggested method depends on the coyote optimization algorithm,also known as the LOBO algorithm,which optimizes the weights of the deep-convolutional neural network classifier.The accuracy,sensitivity,and specificity indices,which are obtained to be 92.40%,94.15%,and 91.92%,respectively,are used to validate the effectiveness of the suggested method.The result suggests that the suggested strategy is superior for effectively classifying brain tumors.
文摘This study presents an efficient feature selection method based on the Gower distance to enhance the accuracy and efficiency of standard classifiers on high-dimensional medical datasets.High-dimensional data poses significant challenges for traditional classifiers due to feature redundancy or being irrelevant.The proposed method addresses these challenges by partitioning the dataset into blocks,calculating the Gower distance within each block,and selecting features based on their average similarity.Technically,the Gower distance normalizes the absolute difference between numerical features,ensuring that each feature contributes equally to the distance calculation.This normalization prevents features with larger scales from overshadowing those with smaller scales.This process facilitates the identification of features that exhibit high harmony and are the most relevant for classification.The proposed feature selection strategy significantly reduces dimensionality,retains the most relevant features,and improves model performance.Experimental results show that the accuracy for the classifiers including k-nearest neighbors(KNN),naive Bayes(NB),decision tree(DT),random forest(RF),support vector machine(SVM),and logistic regression(LR)was increased by 4.38%-7.02%.Besides,the reduction in the feature set size contributes to a considerable decrease in computational complexity and thus faster diagnosis speed.The execution time was averagely reduced by 77.82%for all samples and 76.45%for one sample.These results demonstrate that the proposed feature selection method shows enhanced performance on both prediction accuracy and diagnostic speed,making it a promising tool for real-time clinical decision-making and improving patient care outcomes.
基金supported by the National Natural Science Foundation of China(Grants 62176097,61433007)Fundamental Research Funds for the Central Universities(Grant 2019kfyXKJC024)the 111 Project on Computational Intelligence and Intelligent Control(Grant B18024).
文摘Existing weakly supervised semantic segmentation(WSSS)methods based on image-level labels always rely on class activation maps(CAMs),which measure the relationships between features and classifiers.However,CAMs only focus on the most discriminative regions of images,resulting in their poor coverage performance.We attribute this to the deficiency in the recognition ability of a single classifier and the negative impacts caused by magnitudes during the CAMs normalisation process.To address the aforementioned issues,we propose to construct selective multiple classifiers(SMC).During the training process,we extract multiple prototypes for each class and store them in the corresponding memory bank.These prototypes are divided into foreground and background prototypes,with the former used to identify foreground objects and the latter aimed at preventing the false activation of background pixels.As for the inference stage,multiple prototypes are adaptively selected from the memory bank for each image as SMC.Subsequently,CAMs are generated by measuring the angle between SMC and features.We enhance the recognition ability of classifiers by adaptively constructing multiple classifiers for each image,while only relying on angle measurement to generate CAMs can alleviate the suppression phenomenon caused by magnitudes.Furthermore,SMC can be integrated into other WSSS approaches to help generate better CAMs.Extensive experiments conducted on standard WSSS benchmarks such as PASCAL VOC 2012 and MS COCO 2014 demonstrate the superiority of our proposed method.
文摘Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computational complexity,limited generalizability under varying conditions,and compromised real-time performance.To counter these,this paper introduces an Active Learning-aided Heuristic Deep Spatio-Textural Ensemble Learning(ALH-DSEL)framework.The model initially identifies keyframes from the surveillance videos with a Multi-Constraint Active Learning(MCAL)approach,with features extracted from DenseNet121.The frames are then segmented employing an optimized Fuzzy C-Means clustering algorithm with Firefly to identify areas of interest.A deep ensemble feature extractor,comprising DenseNet121,EfficientNet-B7,MobileNet,and GLCM,extracts varied spatial and textural features.Fused characteristics are enhanced through PCA and Min-Max normalization and discriminated by a maximum voting ensemble of RF,AdaBoost,and XGBoost.The experimental results show that ALH-DSEL provides higher accuracy,precision,recall,and F1-score,validating its superiority for real-time HAR in surveillance scenarios.
基金supported in part by the National Science Fund for Distinguished Young Scholars under Grant (42025403)the National Key Research and Development Plan of China (2021YFA0716800)the National Key Research and Development Plan of China (2022YFC2903804)。
文摘The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic technology,plays a pivotal role in ensuring mine safety by enabling real-time identifi cation and accurate classification of vibration signals such as microseismic signals,blasting signals,and noise.These classifications are critical for improving the efficacy of ground pressure monitoring systems,conducting stability analyses of deep rock masses,and implementing timely and precise roadway support measures.Such eff orts are essential for mitigating ground pressure disasters and ensuring safe mining operations.This study proposes an artificial intelligence-based automatic classification network model for mine vibration signals.Based on conventional convolutional neural networks,the proposed model further incorporates long short-term memory(LSTM)networks and attention mechanisms.The LSTM component eff ectively captures temporal correlations in time-series mining vibration data,while the attention mechanism enhances the models’ability to focus on critical features within the data.To validate the eff ectiveness of our proposed model,a dataset comprising 480,526 waveform records collected in 2022 by the microseismic monitoring system at Guangxi Shanhu Tungsten Mine was used for training,validation,and testing purposes.Results demonstrate that the proposed artifi cial intelligence-based classifi cation method achieves a higher recognition accuracy of 92.21%,significantly outperforming traditional manual classification methods.The proposed model represents a signifi cant advancement in ground pressure monitoring and disaster mitigation.
基金Supported by Talent Scientific Research Start-up Foundation of Wannan Medical College,No.WYRCQD2023045.
文摘BACKGROUND The early diagnosis rate of pancreatic ductal adenocarcinoma(PDAC)is low and the prognosis is poor.It is important to develop an interpretable noninvasive early diagnostic model in clinical practice.AIM To develop an interpretable noninvasive early diagnostic model for PDAC using plasma extracellular vesicle long RNA(EvlRNA).METHODS The diagnostic model was constructed based on plasma EvlRNA data.During the process of establishing the model,EvlRNA-index was introduced,and four algorithms were adopted to calculate EvlRNA-index.After the model was successfully constructed,performance evaluation was conducted.A series of bioinformatics methods were adopted to explore the potential mechanism of EvlRNA-index as the input feature of the model.And the relationship between key characteristics and PDAC were explored at the single-cell level.RESULTS A novel interpretable machine learning framework was developed based on plasma EvlRNA.In this framework,a two-layer classifier was established.A new concept was proposed:EvlRNA-index.Based on EvlRNA-index,a cancer diagnostic model was established,and a good diagnostic effect was achieved.The accuracy of PDACandCPvsHealth-Probabilistic PCA Index-SVM(PDAC and chronic pancreatitis vs health-probabilistic principal component analysis index-support vector machine)(1-18)was 91.51%,with Mathew’s correlation coefficient 0.7760 and area under the curve 0.9560.In the second layer of the model,the accuracy of PDACvsCP-Probabilistic PCA Index-RF(PDAC vs chronic pancreatitis-probabilistic principal component analysis index-random forest)(2-17)was 93.83%,with Mathew’s correlation coefficient 0.8422 and area under the curve 0.9698.Forty-nine PDAC-related genes were identified,among which 16 were known,inferring that the remaining ones were also PDAC-related genes.CONCLUSION An interpretable two-layer machine learning framework was proposed for early diagnosis and prediction of PDAC based on plasma EvlRNA,providing new insights into the clinical value of EvlRNA.
