检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Chen, Wanqiu Sun, Yuting Yang, Yihao Yu, Jiaxu Fuzhou University Multimedia Mobile and Web Development Fuzhou China Data Science and Big Data Technology Fuzhou University Fuzhou China Fuzhou University Software Engineering Fuzhou China

ISBN: (纸本)9798331528911

Facial expression recognition is integral to enhancing human-machine interactions, applicable across security, advertising, and social media. Traditionally, these systems relied on handcrafted features or basic algorithms, but advancements in computational power and neural network architecture like Convolutional Neural Networks (CNNs) have shifted this trend. This study presents a hybrid model combining multiple CNNs-MobileNetV1, MobileNetV2, and ResNet50-with an attention mechanism to improve the robustness and accuracy of facial expression recognition. Utilizing the strengths of these networks, the model utilizes an ensemble approach where feature extractions are integrated and optimized using a random forest to determine the most effective weightings for final predictions. This method not only harnesses the power of deep learning to enhance feature detection across diverse conditions but also implements transfer learning (i.e. ImageNet weights) to address challenges posed by small or non-varied datasets, significantly advancing the abilities of facial expression recognition systems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enabling secure modern web browsers against cache-based timing attacks

引用

International Journal of Security and Networks 2024年第1期19卷 43-54页

作者： Ganesan, Sangeetha Department of Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Tamil Nadu Tiruvallur India

Web applications have grown to be the foundation of any kind of system, ranging from cloud services to the internet of things (IoT) systems. As a huge amount of sensitive data is processed in web applications, user privacy shows as the most important concern in web security. In the virtualisation system, cache side channel (CSC) attack techniques have become popular to retrieve the secret information of other users. This paper presents a run-time detection and prevention mechanism, called browser watcher (BW), for time-driven CSC attacks. The computation overhead of the proposed BW java script engine is monitored and tabulated for the different domains. The average cache miss rate is measured from 23% to 89%. Once the BW system identifies the attacker, then it prevents stealing the secret information of the victim. This makes it very hard for the attacker to find the memory access pattern of the victim. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

Legalities in Metaverse - Ethereum Fraud Detection 9

Legalities in Metaverse - Ethereum Fraud Detection

引用

9th International Conference on science, technology, Engineering and Mathematics, ICONSTEM 2024

作者： Hudnurkar, Manoj Singh, Kartik Ambekar, Suhas Sahu, Geeta Yecho, Harshil Pune India Department of Information Technology And Data Science Mumbai India

ISBN: (纸本)9798350365092

The spread of the Metaverse has created new moral and legal challenges, especially when it comes to protecting against fraud. This study explores the legal complexities surrounding Ethereum-specific metaverse transactions and provides guidance on how to identify and address fraudulent activity. The focus of this investigation is the field of fraud detection in the Ethereum environment. Current methods of detecting fraud, such as Blockchain analysis and machine learning-based algorithms, are carefully examined. Next, a new approach to fraud detection is put out, which is predicated on a collection of seven machine learning algorithms: K-Nearest Neighbours (KNN), Decision Tree, Support Vector Machine (SVM), Random Forest, KNN, XGBoost (XGB), and Artificial Neural Network (ANN). The results of this study are carefully outlined, demonstrating the accuracy, recall, F1 score, and precision that each of the previously listed algorithms demonstrated. Moreover, this article lays out possible directions for further research, including the incorporation of group approaches and the investigation of creating characteristics to strengthen fraud detection abilities. This academic paper provides a significant and novel insight into the identification of fraudulent activity in Ethereum transactions, highlighting the potential benefits of using machine learning algorithms for this kind of discernment. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Research on Mining Association Rules for Classroom Concentration Based on Apriori Algorithm 7

Research on Mining Association Rules for Classroom Concentra...

引用

7th IEEE Information technology and Mechatronics Engineering Conference, ITOEC 2023

作者： Bai, Jingqiu Kong, Huafeng Hu, Wenhan Wuhan Business University Department of Information Engineering Hubei China Major in Data Science and Big Data Technology China The Main Research Direction Is the Computer Application China

ISBN: (纸本)9798350334197

This paper studies the correlation between students' concentration in class and learning interest, emotional state and other influencing factors. By collecting students' classroom status data, a data set suitable for data mining is constructed. Based on the idea of Apriori algorithm, the Anaconda Navigator programming tool is used to mine the association rules of students' classroom concentration. Through data mining based on Apriori algorithm, and the association rules between students' emotional state, learning interest and other factors and in-class test scores are output. The results of strong association rules show that the better students' emotional state, learning interest and other states are, the better their classroom concentration performance is. Mining the potential influencing factors of students' classroom concentration provides valuable reference theory for students to improve classroom concentration and teachers to improve classroom teaching effect, which is helpful for teachers and students to build a more efficient classroom together in the future. © 2023 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Predicting Delays for Truck Delivery Logistics: An Application of AI and ML 9

Predicting Delays for Truck Delivery Logistics: An Applicati...

引用

9th International Conference on science, technology, Engineering and Mathematics, ICONSTEM 2024

作者： Hudnurkar, Manoj Renji, Kuriakose M. Ambekar, Suhas Sahu, Geeta Joseph, Kavitha Mary Pune India Department of Information Technology And Data Science Mumbai India

ISBN: (纸本)9798350365092

Supply chain management has a lot of logistical challenges, which can significantly affect the efficacy and efficiency of logistics operations as a whole. Machine learning techniques are increasingly popular because they can evaluate vast data volumes and produce precise predictions. Logistics management must include the forecast of delays in the supply chain. It entails anticipating delays in logistics operations, which can assist logistics managers in effectively planning and allocating resources. This paper summarizes the logistics delay prediction in truck delivery systems and identifies some opportunities and problems. The article also suggests a framework for predicting logistics delays based on machine learning methods and assesses the framework's effectiveness using actual data. Thus, the research uses machine learning and AI approaches to anticipate logistics delays. The study gathered information on previous logistical operations and determined the major causes of delays. Then, models for predicting logistical delays were used using machine learning techniques, such as Artificial Neural Networks (ANN), decision trees, random forests, and support vector machines. Our findings demonstrate that these methods have an accuracy rate of up to 97.6% in predicting logistics delays. Also, we discovered that the Adaboost classifier model performed better than the other models in accuracy and precision. Our study offers insightful information on the application of machine learning methods for anticipating logistics delays, which can assist supply chain managers and logistics firms in better organizing and manage their operations to cut down on delays and increase overall effectiveness. © 2024 IEEE.

关键词： Trucks

来源：评论

学校读者我要写书评

暂无评论

Practical operation and theoretical basis of difference-in-difference regression in science of science:The comparative trial on the scientific performance of Nobel laureates versus their coauthors

引用

Journal of data and Information science 2023年第1期8卷 29-46页

作者： Yurui Huang Chaolin Tian Yifang Ma Department of Statistics and Data Science Southern University of Science and TechnologyShenzhen 518055GuangdongChina

Purpose:In recent decades,with the availability of large-scale scientific corpus datasets,difference-in-difference(DID)is increasingly used in the science of science and bibliometrics *** method outputs the unbiased estimation on condition that several hypotheses hold,especially the common trend *** this paper,we gave a systematic demonstration of DID in the science of science,and the potential ways to improve the accuracy of DID ***/methodology/approach:At first,we reviewed the statistical assumptions,the model specification,and the application procedures of DID ***,to improve the necessary assumptions before conducting DID regression and the accuracy of estimation,we introduced some matching techniques serving as the pre-selecting step for DID design by matching control individuals who are equivalent to those treated ones on observational variables before the ***,we performed a case study to estimate the effects of prizewinning on the scientific performance of Nobel laureates,by comparing the yearly citation impact after the prizewinning year between Nobel laureates and their prizewinning-work ***:We introduced the procedures to conduct a DID estimation and demonstrated the effectiveness to use matching method to improve the *** a case study,we found that there are no significant increases in citations for Nobel laureates compared to their prizewinning *** limitations:This study ignored the rigorous mathematical deduction parts of DID,while focused on the practical *** implications:This work gives experimental practice and potential guidelines to use DID method in science of science and bibliometrics ***/value:This study gains insights into the usage of econometric tools in science of science.

关键词： science of science Bibliometrics Difference-in-Difference CEM PSM Nobel Prize

来源：评论

学校读者我要写书评

暂无评论

Research on Road Damage Detection Based on an Improved YOLOv8 Model 4

Research on Road Damage Detection Based on an Improved YOLOv...

引用

4th International Conference on Computer science, Electronic Information Engineering and Intelligent Control technology, CEI 2024

作者： Xiao, Yuhan Wan, Chufeng Lin, Junqing Dong, Shu Gao, Weishun Mei, Liangcai Beijing Institute of Technology Zhuhai Department of Data Science Zhuhai China

ISBN: (纸本)9798350378542

This paper presents the YOLOv8 model for road damage detection, highlighting performance enhancements. YOLOv8 features a novel backbone network, an anchor-free detection head, and new loss functions, ensuring efficient operation across various hardware platforms. A self-attention mechanism is integrated to enhance classification accuracy and robustness. Experimental comparisons indicate that while the attention-augmented YOLOv8 improves precision and recall, the modified version achieves superior overall performance. Analyses using confusion matrices and precision-recall curves demonstrate the enhanced YOLOv8's greater accuracy and stability with complex backgrounds and diverse damage types. The results confirm its superiority in practical applications, showcasing strong performance in road damage detection. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Image inpainting via Smooth Tucker decomposition and Low-rank Hankel constraint

引用

International Journal of Computers and Applications 2023年第6期45卷 421-432页

作者： Cai, Jing Jiang, Jiawei Wang, Yibing Zheng, Jianwei Xu, Honghui Department of Forensic Science Zhejiang Police College Hangzhou China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Hangzhou China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

Image inpainting, aiming at exactly recovering missing pixels from partially observed entries, is typically an ill-posed problem. As a powerful constraint, low-rank priors have been widely applied in image inpainting to transform such problems into well-posed ones. However, the low-rank assumption of original visual data is only in an approximate mode, which in turn results in suboptimal recovery of fine-grained details, particularly when the missing rate is extremely high. Moreover, a single prior cannot faithfully capture the complex texture structure of an image. In this paper, we propose a joint usage of Smooth Tucker decomposition and Low-rank Hankel constraint (STLH) for image inpainting, which enables simultaneous capturing of the global low-rankness and local piecewise smoothness. Specifically, based on the Hankelization operation, the original image is mapped to a high-order structure for capturing more spatial and spectral information. By employing Tucker decomposition for optimizing the Hankel tensor and simultaneously applying Discrete Total Variation (DTV) to the Tucker factors, sharper edges are generated and better isotropic properties are enhanced. Moreover, to approximate the essential rank of the Tucker decomposition and avoid facing the uncertainty problem of the upper-rank limit, a reverse strategy is adopted to approximate the true rank of the Tucker decomposition. Finally, the overall image inpainting model is optimized by the well-known alternate least squares (ALS) algorithm. Extensive experiments show that the proposed method achieves state-of-the-art performance both quantitatively and qualitatively. Particularly, in the extreme case with 99% pixels missed, the results from STLH are averagely ahead of others at least 0.9dB in terms of PSNR values. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

CBIR: a novel identification approach for college students in need based on consumer behavior psychology theory

引用

Neural Computing and Applications 2025年第6期37卷 4663-4677页

作者： Liu, Xinze Liu, Shixi Hu, Xiaojing Zhang, Yudong Fang, Xianwen School of Computer and Information Engineering Chuzhou University Chuzhou239000 China School of Computer Science and Engineering Southeast University Nanjing210096 China School of Mathematics and Big Data Anhui University of Science and Technology Huainan232001 China

The accurate identification of students in need is crucial for governments and colleges to allocate resources more effectively and enhance social equity and educational fairness. Existing approaches to identifying students in need rely on manual operations that include manually extracting consumption behavior information, statistical consumption characteristics and principal component analysis. However, this issue may lead to low prediction accuracy and inefficiency in identifying students in need. We design a three-stage framework to accurately identify college students in need from the perspective of consumer behavior psychology. The consumption behavior information is first obtained from the student consumption records using the consumption behavior clustering approach. The consumption behavior matrix is then built by extracting consumption and spatiotemporal information in different periods. Finally, a novel consumption behavior identification ResNeSt (CBIR) model is proposed to identify college students in need accurately. The experimental results on real datasets show that the CBIR model has higher prediction accuracy than the baseline models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Social psychology

来源：评论

学校读者我要写书评

暂无评论

Preserving Privacy in Healthcare Analytics: Federated Learning for Breast Cancer Prediction in a Collaborative Learning Framework 15

Preserving Privacy in Healthcare Analytics: Federated Learni...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Anuvarshini, G.B. Varshaa, D. Sujithra, M. Devi, D. Sudha Department of Computing- Data Science Coimbatore Institute of Technology Coimbatore India

ISBN: (纸本)9798331300579

Federated learning has emerged as a promising technique in machine learning, enabling collaborative training across distributed datasets. Particularly in fields like healthcare, where data privacy is paramount, federated learning offers a means to improve privacy and security. This paper addresses the critical need for safeguarding sensitive medical data by proposing a privacy-preserving federated learning algorithm. Leveraging homomorphic encryption, the proposed algorithm ensures that the learning process protects both data and model integrity. By employing a secure multi-party computation protocol, the algorithm defends against potential adversaries seeking to compromise the deep learning model. Evaluation on real-world medical datasets demonstrates the effectiveness of the approach in preserving privacy and security amidst collaborative learning environments. © Grenze Scientific Society, 2024.

关键词： Adversarial machine learning

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：