检索结果-内蒙古大学图书馆

2025 International Russian Smart Industry Conference, SmartIndustryCon 2025

作者： Tsyglyaev, Vladislav Rusak, Alena Belozubov, Alexander ITMO University Faculty of Software Engineering and Computer Systems Saint-Petersburg Russia

ISBN: (纸本)9798331511241

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. © 2025 IEEE.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Flexibility and Privacy: A Multi-Head Federated Continual Learning Framework for Dynamic Edge Environments 11

Flexibility and Privacy: A Multi-Head Federated Continual Le...

引用

11th International Symposium on Computing and Networking, CANDAR 2023

作者： Chen, Chunlu Wang, Kevin I-Kai Li, Peng Sakurai, Kouichi Kyushu University Graduate School of Information Science and Electrical Engineering Fukuoka Japan The University of Auckland Dept. of Electrical Computer and Software Engineering Auckland New Zealand The University of Aizu School of Computer Science and Engineering Aizuwakamatsu Japan Kyushu University Faculty of Information Science and Electrical Engineering Fukuoka Japan

ISBN: (纸本)9798350306705

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 lead to increased costs and catastrophic forgetting due to model retraining with new datasets. Continual learning has been proposed to counter this, enabling models to adapt to new data while preserving previous knowledge, which is beneficial for dynamic edge environments. Despite these advantages, the retention of previous knowledge during the continual learning process may lead to the information leakage. To address the inherent challenges of multitask scenarios, we present a Federated Continual Learning (FCL) framework that integrates the privacy-preserving benefits of Federated Learning (FL) into a continual learning system, ensuring both continual learning and privacy preservation in edge computing data processing and analysis. Specifically, our architecture introduces dedicated fully-connected layers for each task. This architecture ensures that distinctive features pertinent to each task are not only captured but also preserved throughout the model's lifespan. Within our framework, data is processed via task-specific layers. Subsequently, the final label is determined by associating it with the paramount prediction value, thus capitalizing on the model's comprehensive knowledge reservoir to bolster prediction accuracy. We subjected our FCL framework to rigorous validation using two benchmark datasets: MNIST and CFAR-10. Experimental outcomes unequivocally substantiate the efficacy of our proposed methodology. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Intelligent-Based Extraction of Business Capabilities from Company Descriptions 7

Intelligent-Based Extraction of Business Capabilities from C...

引用

7th International Conference on Information Technology, Information Systems and Electrical engineering, ICITISEE 2023

作者： Fahmi, Faisal Hamid, Siti Hafizah Ab Yuadi, Imam Airlangga University Faculty of Political and Social Science Department of Library and Information Science Indonesia Universiti Malaya Faculty of Computer Science & Information Technology Department of Software Engineering Malaysia

ISBN: (纸本)9798350382266

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 competencies of organizations. This Information can empower stakeholders to make informed decisions regarding partnerships, acquisitions, and market positioning. Additionally, by comparing capabilities across companies and industries, organizations can identify their competitive advantages, industry trends, potential disruptions, and effective resource allocations, leading to improved strategies and better market opportunities. Traditional methods for extracting business capabilities primarily rely on keyword matching or rule-based techniques, which often fail to capture the complex relationships between words in a sentence. This paper presents a comprehensive study on extracting business capabilities using dependency parsing techniques in natural language processing (NLP) to overcome limitations of the traditional methods and improve the accuracy of business capability extraction. Dependency parsing utilizes pre-trained language models to analyze the grammatical structure of sentences, identifying the dependencies between words and capturing their relationships. The feasibility and effectiveness of the proposed approach is demonstrated through experiments conducted on more than 40K real-world company descriptions crawled from Wikipedia. © 2023 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Methods for Multimodal Classification of Personality Traits Using Social Media Data

Machine Learning Methods for Multimodal Classification of Pe...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Vladislav Tsyglyaev Alena Rusak Alexander Belozubov Faculty of Software Engineering and Computer Systems ITMO University Saint-Petersburg Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

关键词： Support vector machines Industries Visualization Social networking (online) Corporate acquisitions Machine learning Feature extraction Vectors Data models Open data

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving Federated Learning with Byzantine Robustness

Efficient Privacy-Preserving Federated Learning with Byzanti...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Chunhua Jin Lulu Li Jiahao Wang Youwang Sun Ying Jin Guanhua Chen Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai’an China

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.

关键词： Training Privacy Differential privacy Protocols Federated learning Resists Robustness Security Servers Protection

来源：评论

学校读者我要写书评

暂无评论

Generating synthetic data on agricultural crops with DCGAN 11

Generating synthetic data on agricultural crops with DCGAN

引用

11th International Conference on Advanced Informatics: Concept, Theory and Application, ICAICTA 2024

作者： Pasaribu, Fieter Brain Dewi, Luh Joni Erawati Aryanto, Kadek Yota Ernanda Seputra, Ketut Agus Varnakovida, Pariwate Kertiasih, Ni Ketut Computer Science Universitas Pendidikan Ganesha Singaraja Indonesia Software Engineering Universitas Pendidikan Ganesha Singaraja Indonesia King Mongkut's University of Technology Faculty of Science Thonburi Thailand

ISBN: (纸本)9798331520311

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 various image processing tasks such as classification, object detection, and segmentation. However, even though CNN has great capabilities, one important thing to note is the amount of data. A considerable amount of data is needed for the CNN model to work optimally and avoid overfitting. To handle this problem, a synthetic data augmentation process is used using the Deep Convolutional Generative Adversarial Network (DCGAN) method. The generator network contained in the DCGAN model has a latent space dimension input whose value can vary. The size of the latent space dimension is very important in enabling data or image reconstruction during the training process. This study tested latent space dimension values on a corn plant dataset totaling 9159. The latent space values used in this experiment were 64, 100, and 128. In addition, this study also tested different batch sizes, namely 64 and 128. The model was evaluated using Fre'chet Inception Distance (FID) and Inception Score (IS). From the evaluation results, the best score on FID was 0.018001 and IS 1.239421. The greater the latent space value, the more realistic and clear the image results will be. Likewise, the smaller the batch size value, the more realistic and clear the image results. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Improved NGO Algorithm for Optimizing VMD-CNN-BILSTM-Cross Attention Bearing Fault Diagnosis Method

An Improved NGO Algorithm for Optimizing VMD-CNN-BILSTM-Cros...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Jiapeng Luo Xiaobing Chen Faculty of Computer and Software Engineering Huaiyin Insititute of Technology Huai’an China

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.

关键词： Fault diagnosis Vibrations Accuracy Chaotic mapping Computational modeling Switched mode power supplies Feature extraction Data models Robustness Optimization

来源：评论

学校读者我要写书评

暂无评论

Federated Machine Learning Based Fetal Health Prediction Empowered with Bio-Signal Cardiotocography

引用

computers, Materials & Continua 2024年第3期78卷 3303-3321页

作者： Muhammad Umar Nasir Omar Kassem Khalil Karamath Ateeq Bassam SaleemAllah Almogadwy Muhammad Adnan Khan Muhammad Hasnain Azam Khan Muhammad Adnan Department of Computer Sciences Bahria University Lahore CampusLahore54000Pakistan Faculty of Information Technology Liwa CollegeAbu Dhabi00000United Arab Emirates Department of Computing Skyline University CollegeSharjah1797United Arab Emirates Department of Computer Science Taibah UniversityMedina42353Saudi Arabia Riphah School of Computing and Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department of Engineering and Development Dubizzle LabsLahore54000Pakistan Department of Software Faculty of Artificial Intelligence and SoftwareGachon UniversitySeongnam-si13120Korea

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.

关键词： Cardiotocography ML FML fetal disease bio-signal

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection Using EfficientNet and XceptionNet 11

Deepfake Detection Using EfficientNet and XceptionNet

引用

11th IEEE International Conference on Intelligent Computing and Information Systems, ICICIS 2023

作者： Yasser, Basma Hani, Jumana El-Gayar, Salma Amgad, Omar Ahmed, Nourhan Ebied, Hala M. Amr, Habiba Salah, Mohamed Ain Shams University Software Engineering Faculty of Computer and Information Sciences Cairo Egypt Ain Shams University Faculty of Computer and Information Sciences Computer Science Department Cairo Egypt Ain Shams University Faculty of Computer and Information Sciences Scientific Computing Department Cairo Egypt

ISBN: (纸本)9798350322101

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 advanced CNN architectures such as EfficientNet-B4 and XceptionNet. The FF++ and Celeb-DF (v2) datasets are used to compare real and fake videos. The methodology involves preprocessing the Celeb- DF dataset by extracting frames and isolating faces, training the models, and evaluating their performance using log loss and Area Under the Curve (AUC) metrics. The study shows that both models are effective in accurately classifying real and fake videos and highlights the importance of continuously updating deepfake detection algorithms in response to evolving deepfake generation techniques. © 2023 IEEE.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Optimization Model for Garbage Image Classification Based on RepVGG

Optimization Model for Garbage Image Classification Based on...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Ken Lin Shaozhang Xiao Kaikai Shang Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huaian China

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.

关键词： Training Adaptation models Accuracy Convolution Computational modeling Stacking Feature extraction Kernel Image classification Periodic structures

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：