In the era of Big Data, Information can be generated, extracted, and utilized in diverse ways. In business, information about business capabilities can be a crucial aspect in understanding the strengths and competenci...
详细信息
Federated Learning (FL) and the Internet of Things (IoT) have revolutionized data processing and analysis, overcoming the traditional limitations of cloud computing. However, traditional machine learning strategies le...
详细信息
In this paper, we investigate the effectiveness of various machine learning methods for the multimodal classification of personality traits using the HEXACO model and open data from social media users. Particular atte...
详细信息
ISBN:
(数字)9798331511241
ISBN:
(纸本)9798331511258
In this paper, we investigate the effectiveness of various machine learning methods for the multimodal classification of personality traits using the HEXACO model and open data from social media users. Particular attention is paid to the analysis of data obtained from user profiles, including statistical, visual, and audio characteristics. For each personality trait from the HEXACO model, a machine learning model is trained that determines the manifestation degree of this trait (low, medium, high). The influence of different types of information, both individually and in combination, on the weighted F1-score is considered. The study provides a comparative analysis of traditional machine learning methods that use all features and approaches with the selection of the most significant features. A strategy for combining data from different modalities using early merger is evaluated. The experimental results demonstrate that early merger models using selected features from different modalities provide the best result of the weighted F1-score, which varies depending on the personality trait from 0.76 to 0.85.
Federated learning is a distributed machine learning paradigm. It entails training a global model across diverse organizations while ensuring privacy constraints are upheld. Despite its promising potential, challenges...
详细信息
ISBN:
(数字)9798350352894
ISBN:
(纸本)9798350352900
Federated learning is a distributed machine learning paradigm. It entails training a global model across diverse organizations while ensuring privacy constraints are upheld. Despite its promising potential, challenges arise when adversaries attempt to infer private information from exchanged parameters or compromise the global model. Although the development of multiple protocols to mitigate security threats, safeguarding the privacy of individual participants while countering Byzantine adversaries remains a challenge. Furthermore, the frequent transmission of gradients between the master server and participants results in significant communication overhead, thereby limiting the training efficiency of federated learning. In this study, We propose an efficient privacy-preserving federated learning scheme with Byzantine robustness (EFL-PB). For privacy protection and Byzantine robustness, we propose a novel aggregation strategy based on the multi-message shuffle protocol in differential privacy. For enhancing communication efficiency, we develop an adaptive gradient compression scheme. Theoretical analysis demonstrates that our multi-message shuffle protocol can satisfy differential privacy. Experimental results on the MNIST, FashionMNIST, and CIFAR-10 datasets validate the robustness and efficiency of the EFL-PB scheme. As well, the EFL-PB scheme exhibits strong performance on non-iid datasets.
Precisely identifying the fault-related operating state of the gear-box bearing represents a vital problem within industrial production. A bearing fault diagnosis method based on effectively improved NGO algorithm opt...
详细信息
ISBN:
(数字)9798350352894
ISBN:
(纸本)9798350352900
Precisely identifying the fault-related operating state of the gear-box bearing represents a vital problem within industrial production. A bearing fault diagnosis method based on effectively improved NGO algorithm optimized VMD and CNN-BILSTM-Cross Attention is proposed for bearing fault diagnosis. The method improves the NGO algorithm by introducing the SMP chaotic mapping to initialize the eagle swarm distribution, introducing the sine function and the inverse learning strategy to enhance the algorithm’s computational precision and search ability. The CNN-BILSTM model is integrated with the Cross Attention module, which aims to merge the bearing signal features in multiple ways and boost the model’s accuracy and robustness. The improved SCNGO algorithm is utilized to iteratively optimize crucial parameters, namely the intrinsic mode coefficient, and the quadratic penalty term [K, α]within the VMD denoising technology. The CNN is responsible for seizing the spatial features of the bearing vibration signal at diverse frequencies, while the BILSTM is in charge of capturing the temporal features of the same signal. Moreover, the Cross Attention mechanism is introduced to blend the spatial features extracted by the CNN and the temporal features obtained by the BILSTM. In comparison to other models, the proposed model demonstrates stronger generalization and robustness.
Cardiotocography measures the fetal heart rate in the fetus during pregnancy to ensure physical health because cardiotocography gives data about fetal heart rate and uterine shrinkages which is very beneficial to dete...
详细信息
Cardiotocography measures the fetal heart rate in the fetus during pregnancy to ensure physical health because cardiotocography gives data about fetal heart rate and uterine shrinkages which is very beneficial to detect whether the fetus is normal or suspect or *** cardiotocography measures infer wrongly and give wrong predictions because of human *** traditional way of reading the cardiotocography measures is the time taken and belongs to numerous human errors as *** condition is very important to measure at numerous stages and give proper medications to the fetus for its *** the current period Machine learning(ML)is a well-known classification strategy used in the biomedical field on various issues because ML is very fast and gives appropriate results that are better than traditional *** techniques play a pivotal role in detecting fetal disease in its early *** research article uses Federated machine learning(FML)and ML techniques to classify the condition of the *** study proposed a model for the detection of bio-signal cardiotocography that uses FML and ML techniques to train and test the ***,the proposed model of FML used numerous data preprocessing techniques to overcome data deficiency and achieves 99.06%and 0.94%of prediction accuracy and misprediction rate,respectively,and parallel the proposed model applying K-nearest neighbor(KNN)and achieves 82.93%and 17.07%of prediction accuracy and misprediction accuracy,***,by comparing both models FML outperformed the KNN technique and achieved the best and most appropriate prediction results as compared with previous studies the proposed study achieves the best and most accurate results.
Convolutional Neural Network (CNN) is one of the deep learning architectures that is very effective for handling images. CNN is able to automatically extract important features from images, making it very suitable for...
详细信息
The application of deep learning to the classification of garbage images has been demonstrated to significantly enhance the accuracy and efficiency of classification through the extraction of features and the recognit...
详细信息
ISBN:
(数字)9798350352894
ISBN:
(纸本)9798350352900
The application of deep learning to the classification of garbage images has been demonstrated to significantly enhance the accuracy and efficiency of classification through the extraction of features and the recognition of patterns. However, in environments with limited resources or computational power, traditional models are unable to effectively handle complex trash image classification tasks. Consequently, the deployment of lightweight models in garbage image classification h as g arnered increasing interest. In this paper, the structure of the RepVGG model is optimized by combining depthwise separable convolution. Adapting the convolutional layers of the original trunk structure to training branches and replacing the convolutional kernel of the trunk with a 5 × 5 convolutional kernel results in the trunk and branches being reparameterized to a single 5 × 5 convolutional layer after training. This design enhances the image feature extraction capability at multiple levels. The inference structure retains the simple stacking of the original convolutional and ReLU layers. In this paper, the improved model is named DSC5RepVGG. The experimental results demonstrate that DSC5RepVGG reduces the number of parameters by 60.97% in comparison to RepVGG, reduces the theoretical floating-point computation by 58.22%, and improves the Top-1 accuracy by 1.29% on Kaggle’s Garbage Classification dataset.
The increasing prevalence of manipulated media, particularly deepfake videos, poses significant challenges in distinguishing real from fake content. This paper addresses the issue of detecting deepfake videos using ad...
详细信息
Aims to address the problems of low accuracy of existing garbage classification and low classification ac curacy of models, large model size and difficulty of deployment on portable devices. A lightweight garbage imag...
详细信息
ISBN:
(数字)9798350352894
ISBN:
(纸本)9798350352900
Aims to address the problems of low accuracy of existing garbage classification and low classification ac curacy of models, large model size and difficulty of deployment on portable devices. A lightweight garbage image classification model is proposed by merging the improved lightweight model ShuffleNet V2 and MobileViT. Firstly, the structure of the ShuffleNet V2 model is adjusted and improved to enhance the cross-channel information interaction ability of the model, which improves the feature information interaction ability between the channels of the ShuffleNet V 2 model; secondly, the improved ShuffleNet V2 model is fused with the MobileViT model, the advantage of the MobileViT module in global feature information extraction is used to overcome the shortcomings of the ShuffleNet V2 network, which is difficult to extract global feature information. Comparative experiments are conducted on public datasets to evaluate the performance of the model. The experimental results show that the accuracy of the proposed SNViT model is significantly better than the D enseNet-121 model, and also has a better classification performance compared to EfficientNet V2, MobileNet V2 and other models, while the precision rate, recall rate and F1 value are also improved. The improved SNViT model improves the accuracy of the image classification task and achieves high classification performance, while the number of parameters is small and easy to train and deploy.
暂无评论