Aimed at the issue of high feature dimensionality, excessive data redundancy, and low recognition accuracy of using single classifiers on ground-glass lung nodule recognition, a recognition method based on CatBoost fe...
详细信息
Cross-projectsoftware defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source *** existing CPDP approaches rely on ...
详细信息
Cross-projectsoftware defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source *** existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for *** paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source *** proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long short-Term Memory(LsTM)networks to learn predictive *** process involves graph construction,feature learning through graph embedding and LsTM,and defect *** evaluation using nine open-source Java projects from the PROMIsE dataset demonstrates that GB-CPDP outperformsstate-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The resultsshowcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.
The issues of automated generation of mnemonic diagrams for automated workstations used by the operators of electrical installations are considered. The algorithm is implemented based on the substation configuration d...
详细信息
sleep posture surveillance is crucial for patient comfort,yet current systems face difficulties in providing compre-hensive studies due to the obstruction caused by *** posture assessment remains challenging because o...
详细信息
sleep posture surveillance is crucial for patient comfort,yet current systems face difficulties in providing compre-hensive studies due to the obstruction caused by *** posture assessment remains challenging because of the complex nature of the human body and variations in sleep ***,thisstudy introduces an innovative method utilizing RGB and thermal cameras for comprehensive posture classification,thereby enhancing the analysis of body position and *** method begins by capturing a dataset of sleep postures in the form of videos using RGB and thermal cameras,which depict six commonly adopted postures:supine,left log,right log,prone head,prone left,and prone *** study involves 10 participants under two conditions:with and without ***,the database is normalized into a video *** subsequent step entails training a fine-tuned,pretrained Visual Geometry Group(VGG16)and ResNet50 *** the third phase,the extracted features are utilized for *** fourth step of the proposed approach employs a serial fusion technique based on the normal distribution to merge the vectors derived from both the RGB and thermal ***,the fused vectors are passed to machine learning classifiers for final *** dataset,which includes human sleep postures used in thisstudy’s experiments,achieved a 96.7%accuracy rate using the Quadratic support Vector Machine(QsVM)without the ***,the Linear sVM,when utilized with a blanket,attained an accuracy of 96%.When normal distribution serial fusion was applied to the blanket features,it resulted in a remarkable average accuracy of 99%.
Image matting is to estimate the opacity of foreground objects from an image. A few deep learningbased methods have been proposed for image matting and perform well in capturing spatially close information. However, ...
详细信息
Image matting is to estimate the opacity of foreground objects from an image. A few deep learningbased methods have been proposed for image matting and perform well in capturing spatially close information. However, these methods fail to capture global contextual information, which has been proved essential in improving matting performance. This is because a matting image may be up to several megapixels, which is too big for a learning-based network to capture global contextual information due to the limit size of a receptive field. Although uniformly downsampling the matting image can alleviate this problem, it may result in the degradation of matting performance. To solve this problem, we introduce a natural image matting with the attended global context method to extract global contextual information from the whole image, and to condense them into a suitable size for learning-based network. specifically, we first leverage a deformable sampling layer to obtain condensed foreground and background attended images respectively. Then, we utilize a contextual attention layer to extract information related to unknown regions from condensed foreground and background images generated by a deformable sampling layer. Besides, our network predicts a background as well as the alpha matte to obtain more purified foreground, which contributes to better qualitative performance in composition. Comprehensive experimentsshow that our method achieves competitive performance on both Composition-1k and the *** benchmark quantitatively and qualitatively.
High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency...
详细信息
High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility *** order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client *** enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIs)configuration optimization framework for *** problem is decoupled into two convex *** to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIs configuration *** on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their *** simulation resultsshow that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.
Contrastive learning is a significant research direction in the field of deep ***,existing data augmentation methods often lead to issuessuch assemantic drift in generated views while the complexity of model pre-tra...
详细信息
Contrastive learning is a significant research direction in the field of deep ***,existing data augmentation methods often lead to issuessuch assemantic drift in generated views while the complexity of model pre-training limits further improvement in the performance of existing *** address these challenges,we propose the Efficient Clustering Network based on Matrix Factorization(ECN-MF).specifically,we design a batched low-rank singular Value Decomposition(sVD)algorithm for data augmentation to eliminate redundant information and uncover major patterns of variation and key information in the ***,we design a Mutual Information-Enhanced Clustering Module(MI-ECM)to accelerate the training process by leveraging a simple architecture to bring samples from the same cluster closer while pushing samples from other clusters *** experiments on six datasets demonstrate that ECN-MF exhibits more effective performance compared to state-of-the-art algorithms.
Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity co...
详细信息
Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and *** study presents an innovative approach to energy consumption forecasting using a bidirectional Long short-Term Memory(LsTM)*** a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear *** bidirectional LsTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LsTMs consider only a single temporal *** design,combined with dropout regularization,leads to a 20.6%reduction in RMsE and an 18.8%improvement in MAE over conventional unidirectional LsTMs,demonstrating a substantial enhancement in prediction accuracy and *** to existing models—including sVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMsE of 0.2213 during testing,significantly outperforming these *** results highlight the model’ssuperior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive *** integrating advanced machine learning techniqueswith IoT and cloud infrastructure,thisresearch contributes to the development of intelligent,sustainable urban environments.
The perceived visual quality of fruits and vegetables plays a central role in the choices made by retail customers. Machine learning (ML) approachesbased on image analysis have been recently proposed to overcome the ...
详细信息
Phishing attacks present a persistent and evolving threat in the cybersecurity land-scape,necessitating the development of more sophisticated detection *** machine learning approaches to phishing detection have relied...
详细信息
Phishing attacks present a persistent and evolving threat in the cybersecurity land-scape,necessitating the development of more sophisticated detection *** machine learning approaches to phishing detection have relied heavily on feature engineering and have often fallen short in adapting to the dynamically changing patterns of phishingUniformResource Locator(URLs).Addressing these challenge,we introduce a framework that integrates the sequential data processing strengths of a Recurrent Neural Network(RNN)with the hyperparameter optimization prowess of theWhale Optimization Algorithm(WOA).Ourmodel capitalizes on an extensive Kaggle dataset,featuring over 11,000 URLs,each delineated by 30 *** WOA’s hyperparameter optimization enhances the RNN’s performance,evidenced by a meticulous validation *** results,encapsulated in precision,recall,and F1-score metrics,surpass baseline models,achieving an overall accuracy of 92%.Thisstudy not only demonstrates the RNN’s proficiency in learning complex patterns but also underscores the WOA’s effectiveness in refining machine learning models for the critical task of phishing detection.
暂无评论