检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Mingjing Ju, Peizhong Liu, Jia Yang, Haibo Dept. of Computing and Information Sciences Ph.D. Rochester Institute of Technology United States Dept. of Computer Science University of Kentucky United States Dept. of Electrical and Computer Engineering The Ohio State University United States

ISBN: (纸本)157735897X

Multi-objective optimization (MOO) lies at the core of many machine learning (ML) applications that involve multiple, potentially conflicting objectives. despite the long history of MOO, recent years have witnessed a surge in interest within the ML community in the development of gradient manipulation algorithms for MOO, thanks to the availability of gradient information in many ML problems. However, existing gradient manipulation methods for MOO often suffer from long training times, primarily due to the need for computing dynamic weights by solving an additional optimization problem to determine a common descent direction that can decrease all objectives simultaneously. To address this challenge, we propose a new and efficient algorithm called Periodic Stochastic Multi-Gradient descent (PSMGd) to accelerate MOO. PSMGd is motivated by the key observation that dynamic weights across objectives exhibit small changes under minor updates over short intervals during the optimization process. Consequently, our PSMGd algorithm is designed to periodically compute these dynamic weights and utilizes them repeatedly, thereby effectively reducing the computational overload. Theoretically, we prove that PSMGd can achieve state-of-the-art convergence rates for strongly-convex, general convex, and non-convex functions. Additionally, we introduce a new computational complexity measure, termed backpropagation complexity, and demonstrate that PSMGd could achieve an objective-independent backpropagation complexity. Through extensive experiments, we verify that PSMGd can provide comparable or superior performance to state-of-the-art MOO algorithms while significantly reducing training time. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Shoe Shopping System based on Convolutional Neural Network Image Recognition

A Shoe Shopping System based on Convolutional Neural Network...

引用

IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE)

作者： Chin-Chih Chang Chi-Hung Wei Chen-Sheng Chen Jian-An Chen Shih-Hsien Yeh Sean Hsiao Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Department of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan Bachelor Program in Applied Foreign Language and Smart Commerce Chung Hua University Hsinchu Taiwan

In this article, we present an innovative approach to enhance the online shoe shopping experience. The convolutional neural network (CNN) image recognition technology was used to enhance shoe classification and recommendations. By training the CNN model on an extensive dataset, unique shoe features and styles were learned. Integrated into a user-friendly online platform, the system offers real-time image recognition, allowing users to snap a photo of a desired shoe for instant identification, including brand, price, and availability details. Moreover, the CNN-based recommendation engine provides personalized suggestions based on style, color, and customer preferences, enriching the shopping experience. Evaluation results confirmed the system's feasibility, and user feedback highlighted its effectiveness in simplifying the shopping process and enhancing satisfaction. This innovative system presents a significant leap in merging AI and e-commerce and shows the potential of image recognition to transform online marketplaces, benefiting consumers, offering valuable insights for retailers, and ultimately reshaping the future of online shoe shopping.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cuisine Image Recognition and Recommender System using Convolutional Neural Network

Cuisine Image Recognition and Recommender System using Convo...

引用

IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE)

作者： Chin-Chih Chang Chi-Hung Wei Kuan-Yun Wu Hao-Xiang Kao Sean Hsiao Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Department of Computer Science and Information Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Bachelor Program of Applied Foreign Language and Smart Commerce Chung Hua University Hsinchu Taiwan

The fusion of technology and culinary exploration has allowed for the emergence of advanced online customer service systems. We developed a novel approach to enhance the dining experience. We used a Cuisine Image Recognition and Recommender System (CIRRS) powered by Convolutional Neural Network (CNN) to identify and suggest diverse cuisines based on visual inputs. CIRRS swiftly identified diverse cuisines from user-captured images, offering information on origin, ingredients, and variations by crawling websites. The system enhanced dining experiences by suggesting personalized menus based on individual preferences and past selections. Extensively tested across various culinary genres, CIRRS consistently demonstrated accuracy and adaptability. User feedback validated its potential to simplify dining choices and elevate satisfaction. This innovative system enriched dining experiences as a valuable tool for culinary enthusiasts, chefs, and restaurateurs, bridging the gap between technology and gastronomy, It also offers a unique way to explore Taiwanese cuisines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-driven multi-omics integration for multi-scale predictive modeling of causal genotype-environment-phenotype relationships

arXiv

引用

arXiv 2024年

作者： Wu, You Xie, Lei Ph.D. Program in Computer Science The Graduate Center The City University of New York New YorkNY United States Ph.D. Program in Biology and Biochemistry The Graduate Center The City University of New York New YorkNY United States Department of Computer Science Hunter College The City University of New York New YorkNY United States Helen & Robert Appel Alzheimer’s Disease Research Institute Feil Family Brain & Mind Research Institute Weill Cornell Medicine Cornell University New YorkNY United States

despite the wealth of single-cell multi-omics data, it remains challenging to predict the consequences of novel genetic and chemical perturbations in the human body. It requires knowledge of molecular interactions at all biological levels, encompassing disease models and humans. Current machine learning methods primarily establish statistical correlations between genotypes and phenotypes but struggle to identify physiologically significant causal factors, limiting their predictive power. Key challenges in predictive modeling include scarcity of labeled data, generalization across different domains, and disentangling causation from correlation. In light of recent advances in multi-omics data integration, we propose a new artificial intelligence (AI)-powered biology-inspired multiscale modeling framework to tackle these issues. This framework will integrate multi-omics data across biological levels, organism hierarchies, and species to predict causal genotype-environment-phenotype relationships under various conditions. AI models inspired by biology may identify novel molecular targets, biomarkers, pharmaceutical agents, and personalized medicines for presently unmet medical needs. © 2024, CC BY.

关键词： data integration

来源：评论

学校读者我要写书评

暂无评论

Selective detection of explosive nitro-aromatic compounds using the 2d organic nanosheets (2dONs) synthesize via 2d click chemistry directed by ultrasonication

引用

Journal of Industrial and Engineering Chemistry 2024年 134卷 504-513页

作者： dabur, deepak Chiu, Yun Cheih Wu, Hui-Fen International Ph.D. Program for Science National Sun Yat-Sen University Kaohsiung80424 Taiwan Department of Chemistry National Sun Yat-Sen University Kaohsiung 70 Lien-Hai Road Kaohsiung80424 Taiwan Institute of Medical Science and Technology National Sun Yat-Sen University Kaohsiung80424 Taiwan School of Pharmacy College of Pharmacy Kaohsiung Medical University Kaohsiung80708 Taiwan Institute of Precision Medicine College of Medicine National Sun Yat-Sen University Kaohsiung80424 Taiwan School of Medicine College of Medicine National Sun Yat-Sen University Kaohsiung80424 Taiwan

Recent advancements in click chemistry have made it an effective method for quickly and easily assembling extremely stable nanomaterial assemblies onto surfaces. Therefore, a new class of fluorescent sensor utilizing two-dimensional organic nanosheets (2dONs) for the selective sensing of 2,4-dinitrophenylhydrazine (2,4-dNph) has been proposed by using the click chemistry directed by the probe ultrasonication method (CCdPS) which is driven by the π-π stacking interactions with the aid of dMF solvent. Prolonged human exposure to 2, 4-dNph has been associated with various detrimental health consequences, including skin conditions, liver issues, and disturbances to the central nervous and cardiovascular systems. Fluorescence titration tests with nanomolar scale limit of detection (LOd, 100 nM or 0.1 μM) and limit of quantification (LOQ, 0.4 μM) for 2,4-dNph showed fluorescence quenching reactions and excellent reversibility. Additionally, zeta potential and UV-absorption spectroscopy were used to validate the interaction and binding characteristics of 2d ONs with 2,4-dNph. In contrast to the widely reported ground-state charge transfer or FRET-based probes for nitroaromatics detection, the signal response for 2,4-dNph was achieved by a strong inner filter effect with the combination of FRET (IFE-FRET). © 2024 The Korean Society of Industrial and Engineering Chemistry

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

A Review on digital Simulation Strategies and Its Applications for Advanced Compression Garments 16

A Review on Digital Simulation Strategies and Its Applicatio...

引用

16th Textile Bioengineering and Informatics Symposium, TBIS 2023

作者： Youn, Seonyoung darden, Ryan Mathur, Kavita Fiber and Polymer Science Ph.D. Program North Carolina State University RaleighNC27606 United States Department of Textile Engineering Chemistry and Sciences M.S. Textile Engineering Program North Carolina State University RaleighNC27606 United States Department of Textile and Apparel Technology and Management North Carolina State University RaleighNC27606 United States

ISBN: (纸本)9781713879473

This paper presents a comprehensive review on the current state of digital simulation technology and its strategic application usages with a key focus on advanced compression garments. Although three-dimensional (3d) digital garment simulators have significantly impacted the apparel and textile industry, their use has been limited to visual prototyping, quality checking, or marketing. The physical properties of garment simulators have been overlooked in advanced functional manufacturing. This literature review investigates the possibility of strategically utilizing virtual physical properties to enhance garment functions, specifically in wearables and medical-grade compression fields. The first phase of this paper gives an overview of the current state of 3d garment simulation tools and their measurement features. This is followed by a gap analysis between simulated and physical property evaluations, focusing on minimizing the gaps. The literature is thoroughly examined to identify appropriate studies that uses digital tools for compressional garments and add value to wearables and healthcare applications. This paper provides valuable insights for apparel and textile engineers, enabling them to better understand the limitations and capabilities of garment simulators in improving advanced features for specific end users. © TBIS 2023. All rights reserved.

关键词： physical properties

来源：评论

学校读者我要写书评

暂无评论

An Application-Aware Clustering Strategy in Vehicular Ad Hoc Network

An Application-Aware Clustering Strategy in Vehicular Ad Hoc...

引用

International Conference on Computing, Electronics & Communications Engineering (iCCECE)

作者： Chi-Hung Wei Chin-Chih Chang Chien-Hao Chu Sean Hsiao Ph.D. Program in Engineering Science Chung Hua University Hsinchu City Taiwan Department of Computer Science and Information Engineering Chung Hua University Hsinchu City Taiwan Bachelor Program in Applied Foreign Language and Smart Commerce Chung Hua University Hsinchu City Taiwan

VANET (Vehicular Ad Hoc Network) was developed to address the unique challenges of communication in a mobile vehicular environment. This technology can enhance driving safety and traffic control. Moreover, similar principles can be applied to unmanned aerial vehicles and robotics. When transmitting data in moving vehicles, it is challenging as access points and base stations keep changing, requiring handovers between different access points and base stations. Clustering is a popular approach used to address this challenge. Common clustering strategies are based on the proximity, communication range, the density, the application requirements of the moving vehicles, or hybrid of them. In this paper, we propose a clustering strategy based on the application sublayer in the vehicle communication protocol. If two computing devices on the move run the same application, they can be grouped together. The contribution of this research is to develop a clustering mechanism based on the application with very low overhead. We also validate the proposed method through simulations. The simulation results indicate that the proposed method is feasible.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fitness Movement Evaluation System Using deep Learning

A Fitness Movement Evaluation System Using Deep Learning

引用

International Conference on Knowledge and Systems Engineering (KSE)

作者： Chin-Chih Chang Chi-Hung Wei Hao-Wei Wu Sean Hsiao Department of Computer Science and Information Engineering Chung Hua University Hsinchu City Taiwan Ph.D. Program in Engineering Science Chung Hua University Hsinchu City Taiwan Bachelor Program in Applied Foreign Language and Smart Commerce Chung Hua University Hsinchu City Taiwan

This paper proposes a fitness movement evaluation system using deep learning. The system uses a deep convolutional neural network (CNN) to extract features from pictures of fitness movements. The features are then used to classify the movements into different categories. The system is evaluated on a dataset of pictures of fitness movements. The results show that the system can accurately classify the movements into different categories. The system is designed to provide feedback to users on their fitness movements. The proposed system is a valuable tool for fitness enthusiasts. The main contribution of this paper is to propose a way to give users a score for their fitness movement. It can help users improve their fitness and track their progress over time. The system is also a valuable tool for fitness professionals. It can help professionals develop new fitness programs and provide feedback to their clients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding server-assisted federated learning in the presence of incomplete client participation 24

Understanding server-assisted federated learning in the pres...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Haibo Yang Peiwen Qiu Prashant Khanduri Minghong Fang Jia Liu Department of Computing and Information Sciences Ph.D. Rochester Institute of Technology Rochester NY Department of Electrical and Computer Engineering The Ohio State University Columbus OH Department of Computer Science Wayne State University Detroit MI Department of Computer Science and Engineering University of Louisville Louisville KY

Existing works in federated learning (FL) often assume either full client or uniformly distributed client participation. However, in reality, some clients may never participate in FL training (aka incomplete client participation) due to various system heterogeneity factors. A popular solution is the server-assisted federated learning (SA-FL) framework, where the server uses an auxiliary dataset. despite empirical evidence of SA-FL's effectiveness in addressing incomplete client participation, theoretical understanding of SA-FL is lacking. Furthermore, the effects of incomplete client participation in conventional FL are poorly understood. This motivates us to rigorously investigate SA-FL. Toward this end, we first show that conventional FL is not PAC-learnable under incomplete client participation in the worst case. Then, we show that the PAC-learnability of FL with incomplete client participation can indeed be revived by SA-FL, which theoretically justifies the use of SA-FL for the first time. Lastly, to provide practical guidance for SA-FL training under incomplete client participation, we propose the SAFARI (server-assisted federated averaging) algorithm that enjoys the same linear convergence speedup guarantees as classic FL with ideal client participation assumptions, offering the first SA-FL algorithm with convergence guarantee. Extensive experiments on different datasets show SAFARI significantly improves the performance under incomplete client participation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meal Image Recognition and Healthy Meal Combination Recommendation System Integrated with Generative Artificial Intelligence

Meal Image Recognition and Healthy Meal Combination Recommen...

引用

IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)

作者： Chin-Chih Chang Chi-Hung Wei Sean Hsiao Chyuan-Huei Thomas Yang Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Bachelor's Program in Applied Foreign Language and Smart Commerce Chung Hua University Hsinchu Taiwan School of Information Engineering Shandong Vocational and Technical University of International Studies Shandong China

ISBN: (数字)9798350396133

ISBN: (纸本)9798350396140

People increasingly prioritize a balanced diet to enhance well-being, yet making informed dietary choices remains challenging amidst the abundance of options. To address this, we developed a meal image recognition and healthy meal combination recommender system, integrating generative artificial intelligence (AI). Convolutional neural networks were used for precise meal image recognition to identify diverse food items. The generative AI-augmented recommendation engine offers personalized meal suggestions aligned with nutritional goals and dietary preferences, utilizing a nutrition knowledge base to ensure overall well-being. The system's feasibility was validated, illustrating its excellence in meal recognition accuracy, recommendation diversity, and user engagement. By integrating generative AI, the system shows its potential to enhance dietary recommendations and public health.

关键词： Image recognition Accuracy Generative AI Knowledge based systems Convolutional neural networks Sustainable development Public healthcare Recommender systems Engines Biomedical engineering

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：