检索结果-内蒙古大学图书馆

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Weng, Caishan Shu, Zhiyang Xu, Zhengjia Zhang, Jinghui Luo, Junzhou Dong, Fang Wang, Peng Wang, Zhengang Southeast University School of Computer Science and Engineering Nanjing China Boston College Nanjing China Co. Ltd China Jiangsu HHigh-Tech Software Technology Co.Ltd China

ISBN: (纸本)9798350331684

Deep Neural Network (DNN) training on a large scale is extremely time-consuming and computationally intensive, which is accelerated by distributed training. In recent years, pipeline parallelism has been developed, which enables partitioning the model across several devices, e.g. GPU, and training efficiency is improved by dividing data batches into micro-batches, with each of them processed by a different stage of the model. Currently, parallel training assumes pipeline placement and partitioning are static, with parameters updating each iteration, without accounting for freezing. This results in computational resources not being fully utilized. In this paper, we propose FreezePipe, a novel method for optimizing deep learning training that combines the freezing mechanism with pipeline parallel training. In FreezePipe, a lightweight method for determining the freezing strategy based on gradient changes is employed. Considering that resources need to be released based on the frozen layer, a lightweight model partitioning algorithm was designed to determine the optimal strategy for pipeline partitioning. Experimental results show that FreezePipe can reduce the training time by 64.5% compared to Torchgpipe on CIFAR-10 dataset without compromising any model performance. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

EF-IMR: Embedded Flash with Interlaced Magnetic Recording Technology

EF-IMR: Embedded Flash with Interlaced Magnetic Recording Te...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Chenlin Ma Xiaochuan Zheng Kaoyi Sun Tianyu Wang Yi Wang College of Computer Science and Software Engineering Shenzhen University China State Key Laboratory of Radio Frequency Heterogeneous Integration

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Interlaced Magnetic Recording (IMR), a technology that improves storage density through track overlap, introduces significant latency due to Read-Modify-Write (RMW) operations. Writing to overlapped tracks affects underlying tracks, requiring additional I/O operations to read, back up, and rewrite them, resulting in significant head movement latency. We propose EF-IMR, a new architecture that ensures crash consistency in IMR while minimizing RMW latency and head movement. EF-IMR reduces head movement during RMW operations and decreases redundant RMW operations. Evaluations under real-world, intensive I/O workloads show that EF-IMR reduces RMW latency by 20.11 % and head movement latency by 89.37% compared to existing methods.

关键词： Tracking Europe Writing Magnetic heads computer crashes Delays Magnetic recording

来源：评论

学校读者我要写书评

暂无评论

HVAdam: A Full-Dimension Adaptive Optimizer 39

HVAdam: A Full-Dimension Adaptive Optimizer

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Yiheng Wu, Shaowu Xu, Yuanzhuo Wu, Jiajun Xu, Shang Drew, Steve Niu, Xiaoguang School of Computer Science Wuhan University China Department of Electrical and Software Engineering University of Calgary Canada Department of Computer Science University College London United Kingdom

ISBN: (纸本)157735897X

Adaptive optimizers such as Adam and RMSProp have gained attraction in complex neural networks, including generative adversarial networks (GANs) and Transformers, thanks to their stable performance and fast convergence compared to non-adaptive optimizers. A frequently overlooked limitation of adaptive optimizers is that adjusting the learning rate of each dimension individually would ignore the knowledge of the whole loss landscape, resulting in slow updates of parameters, invalidating the learning rate adjustment strategy and eventually leading to widespread insufficient convergence of parameters. In this paper, we propose HVAdam, a novel optimizer that associates all dimensions of the parameters to find a new parameter update direction, leading to a refined parameter update strategy for an increased convergence rate. We validated HVAdam in extensive experiments, showing its faster convergence, higher accuracy, and more stable performance on image classification, image generation, and natural language processing tasks. Particularly, HVAdam achieves a significant improvement on GANs compared with other state-of-the-art methods, especially in Wasserstein-GAN (WGAN) and its improved version with gradient penalty (WGAN-GP). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Fintech Marketing: A Comparative Study of Logistic Regression and XGBoost

arXiv

引用

arXiv 2024年

作者： Attota, Dinesh Chowdary Yarmohammadtoosky, Sahar Department of Data Science & Analytics College of Computer Science and Software Engineering Kennesaw State University MariettaGA United States

As several studies have shown, predicting credit risk is still a major concern for the financial services industry and is receiving a lot of scholarly interest. This area of study is crucial because it aids financial organizations in determining the probability that borrowers would default, which has a direct bearing on lending choices and risk management tactics. Despite the progress made in this domain, there is still a substantial knowledge gap concerning consumer actions that take place prior to the filing of credit card applications. The objective of this study is to predict customer responses to mail campaigns and assess the likelihood of default among those who engage. This research employs advanced machine learning techniques, specifically logistic regression and XGBoost, to analyze consumer behavior and predict responses to direct mail campaigns. By integrating different data preprocessing strategies, including imputation and binning, we enhance the robustness and accuracy of our predictive models. The results indicate that XGBoost consistently outperforms logistic regression across various metrics, particularly in scenarios using categorical binning and custom imputation. These findings suggest that XGBoost is particularly effective in handling complex data structures and provides a strong predictive capability in assessing credit risk. Copyright © 2024, The Authors. All rights reserved.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Expression Detection in Healthcare Monitoring Systems

引用

computers, Materials & Continua 2021年第5期67卷 2123-2139页

作者： Muhammad Kashif Ayyaz Hussain Asim Munir Abdul Basit Siddiqui AaqifAfzaal Abbasi Muhammad Aakif Arif Jamal Malik Fayez Eid Alazemi Oh-Young Song Department of Computer Science&Software Engineering International Islamic UniversityIslamabad44000Pakistan Department of Computer Science Quaid-i-Azam UniversityIslamabad44000Pakistan Department of Computer Science Capital University of Science&TechnologyIslamabad44000Pakistan Department of Software Engineering Foundation UniversityIslamabad44000Pakistan Department of Computer Science Abdul Wali Khan UniversityMardan23200Pakistan Department of Computer Science and Information Systems College of Business StudiesPAAET12062Kuwait Department of Software Sejong UniversitySeoul05006Korea

Expression detection plays a vital role to determine the patient’s condition in healthcare *** helps the monitoring teams to respond swiftly in case of *** to the lack of suitable methods,results are often compromised in an unconstrained environment because of pose,scale,occlusion and illumination variations in the image of the face of the patient.A novel patch-based multiple local binary patterns(LBP)feature extraction technique is proposed for analyzing human behavior using facial expression *** consists of three-patch[TPLBP]and four-patch LBPs[FPLBP]based feature engineering *** representation is encoded from local patch statistics using these *** and FPLBP capture information that is encoded to find likenesses between adjacent patches of pixels by using short bit strings contrary to pixel-based *** images are transformed into the frequency domain using a discrete cosine transform(DCT).Most discriminant features extracted from coded DCT images are combined to generate a feature *** vector machine(SVM),k-nearest neighbor(KNN),and Naïve Bayes(NB)are used for the classification of facial expressions using selected *** experimentation is performed to analyze human behavior by considering standard extended Cohn Kanade(CK+)and Oulu–CASIA *** demonstrate that the proposed methodology outperforms the other techniques used for comparison.

关键词： Detection expressions gestures analytics pain patch-based local binary descriptor discrete cosine transform healthcare

来源：评论

学校读者我要写书评

暂无评论

Semantically Robust Unsupervised Image Translation for Paired Remote Sensing Images

arXiv

引用

arXiv 2025年

作者： Fang, Sheng Li, Kaiyu Li, Zhe Zhao, Jianli Zhang, Xingli College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China School of Software Engineering Xi’an Jiaotong University Xi’an710049 China

Image translation for change detection or classification in bi-temporal remote sensing images is unique. Although it can acquire paired images, it is still unsupervised. Moreover, strict semantic preservation in translation is always needed instead of multimodal outputs. In response to these problems, this paper proposes a new method, SRUIT (Semantically Robust Unsupervised Image-to-image Translation), which ensures semantically robust translation and produces deterministic output. Inspired by previous works, the method explores the underlying characteristics of bi-temporal Remote Sensing images and designs the corresponding networks. Firstly, we assume that bi-temporal Remote Sensing images share the same latent space, for they are always acquired from the same land location. So SRUIT makes the generators share their high-level layers, and this constraint will compel two domain mapping to fall into the same latent space. Secondly, considering land covers of bi-temporal images could evolve into each other, SRUIT exploits the cross-cycle-consistent adversarial networks to translate from one to the other and recover them. Experimental results show that constraints of sharing weights and cross-cycle consistency enable translated images with both good perceptual image quality and semantic preservation for significant differences. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

On Site Personnel Access Monitoring and Early Warning in Photovoltaic Field Based on AI Image Recognition

On Site Personnel Access Monitoring and Early Warning in Pho...

引用

IEEE PES Asia-Pacific Power and Energy engineering Conference (APPEEC)

作者： Wenjin Zheng Yajun Wang Xiaochen Xu Hao Chu Danyang Jin Shibiao Fang POWERCHINA HUADONG ENGINEERING CORPORATION LIMITED Hangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350386127

ISBN: (纸本)9798350386134

The study aims to enhance the management and monitoring of photovoltaic (PV) construction sites, which are often located in remote areas with challenging conditions. Traditional monitoring methods are inefficient, costly, and prone to errors, necessitating the integration of advanced image recognition technology to improve site management. The research introduces image recognition technology, a core aspect of artificial intelligence (AI) and computer vision (CV), to automate the detection and monitoring of equipment, personnel behavior, materials, and construction progress at PV sites. The process involves real-time data collection via high-definition cameras, automated anomaly detection, reporting, and historical data analysis using advanced deep learning models like YOLO. The study developed an efficient and adaptive image recognition model tailored to the complexities of PV construction sites. The model successfully improves the accuracy of detecting safety hazards, optimizes resource utilization, and enhances the overall safety and efficiency of the construction process. The findings highlight the potential of image recognition technology to significantly improve the management of PV construction sites. As the technology advances and becomes more cost-effective, its application is expected to drive higher levels of efficiency, reliability, and safety in the renewable energy sector, supporting the industry's sustainable growth.

关键词： Photovoltaic systems Adaptation models Renewable energy sources Image recognition Accuracy Data collection Cameras Data models Artificial intelligence Monitoring

来源：评论

学校读者我要写书评

暂无评论

AI in Education: Improving Quality for Both Centralized and Decentralized Frameworks 14

AI in Education: Improving Quality for Both Centralized and ...

引用

14th IEEE Global engineering Education Conference, EDUCON 2023

作者： Madathil, Nisha Thorakkattu Alrabaee, Saed Al-Kfairy, Mousa Damseh, Rafat Belkacem, Abdelkader N College of IT United Arab Emirates University Department of Information Systems and Security United Arab Emirates College of Technological Innovation Zayed University Dubai United Arab Emirates College of IT Department of Computer Science and Software Engineering United Arab Emirates University United Arab Emirates College of IT Department of Computer Engineering and Networks United Arab Emirates University United Arab Emirates

ISBN: (纸本)9798350399431

Education is essential for achieving many Sustainable Development Goals (SDGs). Therefore, the education system focuses on empowering more educated people and improving the quality of the education system. One of the latest technologies to enhance the quality of education is Artificial Intelligence (AI)-based Machine Learning (ML). As a result, ML has a significant influence on the education system. ML is currently widely applied in the education system for various tasks, such as creating models by monitoring student performance and activities that accurately predict student outcomes, their engagement in learning activities, decision-making, problem-solving capabilities, etc. In this research, we provide a survey of machine learning frameworks for both distributed (clusters of schools and universities) and centralized (university or school) educational institutions to predict the quality of students' learning outcomes and find solutions to improve the quality of their education system. Additionally, this work explores the application of ML in teaching and learning for further improvements in the learning environment for centralized and distributed education systems. © 2023 IEEE.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

QoE-oriented Soft Caching with Content Recommendation for Edge Computing Networks

QoE-oriented Soft Caching with Content Recommendation for Ed...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Wang, Chenyang Chen, Yan Sun, Chuan Jia, Bosen Wang, Xiaofei Taleb, Tarik Leung, Victor C. M. Shenzhen University College of Computer Science & Software Engineering Shenzhen China Shenzhen518132 China Ruhr University Bochum Faculty of Electrical Engineering and Information Technology Bochum Germany Nanyang Technological University College of Computing and Data Science Singapore China Unicom Digital Technology Co. Ltd Beijing China Tianjin University College of Intelligence and Computing Tianjin China University of British Columbia Vancouver Canada

ISBN: (纸本)9798350351255

Mobile Edge Caching (MEC) can potentially alleviate Internet transmission congestion by delivering content at the network edge. However, current MEC solutions suffer from low resource utilization efficiency and often fail to meet user Quality of Experience (QoE), primarily due to dynamic user requests and obsessive pursuit of direct caching hits. Given the prevalence of recommendation systems, users often lack precise requests when using recommendation-based applications like TikTok and Taobao, insted passively enjoying recommended content. In this paper, we introduce a recommendation-enabled MEC architecture to enhance resource utilization and QoE. We develop a recommendation-enabled soft caching model and formulate the optimization problem as maximizing joint system revenue. To address this, we propose an attention-assisted federated learning deep Q-network algorithm. We conduct the simulations by using the real-world MIND dataset. The results demonstrate that our proposed algorithm outperforms existing baselines, demonstrating its effectiveness in improving resource utilization and QoE. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Empowering Cybersecurity: CyberShield AI Advanced Integration of Machine Learning and Deep Learning for Dynamic Ransomware Detection 5th

Empowering Cybersecurity: CyberShield AI Advanced Integratio...

引用

5th International Conference on Deep Learning Theory and Applications, DeLTA 2024

作者： Ali, Sijjad Ali, Asad Uzair, Muhammad Amir, Hamza Bari, Rana Zaki Abdul Sharif, Hamid Jamil, Maryam Hunza, M. Akram, Nabel Allaberdiev, Sharofiddin College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen518060 China School of Media and Communication Shenzhen University Guangdong Shenzhen518060 China College of Physics and Optoelectronic Engineering Shenzhen University Guangdong Shenzhen518060 China School of Government Shenzhen University Guangdong Shenzhen518060 China

ISBN: (纸本)9783031667046

Cybersecurity is an ever-changing field, and the onset of powerful ransomware attacks makes it important to develop high-technology detection techniques. In this article, CyberShield AI is presented as an innovative integration of Artificial Neural Networks (ANN), Light Gradient Boosting Machine (LightGBM), and eXtreme Gradient Boosting (XGBoost). The methodology utilizes on the specific strengths of its individual components to provide unprecedented precision, speed, and functionality in the process of ransomware detection. By applying rigorous data processing, feature selection, and accurate evaluation, CyberShield AI is featured for flawless detection of favorable cases and ransomware-affected samples. We conclude by providing a detailed account of the integration that arises from the combination of advanced machine learning and deep learning technologies, setting high standards for real-time threat detection. The application of CyberShield AI addresses the compromises in cybersecurity methodologies by offering robust defenses against dynamic cyber-threats. Hence, the research not only describes the remarkable detection capabilities of the model but also sets a standard for future cybersecurity measures by providing more robust barriers against ransomware and other malicious factors. The rise of CyberShield AI plays a exemplary role and marks the establishment of artificial intelligence-powered cybersecurity tools. © The Author(s), under exclusive license to Springer Nature Switzerland AG 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：