检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Keigo Tada Hiroki Naganuma Graduate school of Information Science and Engineering Ritsumeikan University Kusatsu Japan Department of Computer Science and Operations Research Mila - Quebec Artificial Intelligence Institute Université de Montréal Montréal Canada

In scenarios such as people-flow analysis and autonomous driving using camera footage, the performance of deep neural networks can be impacted by environmental changes such as the degradation of the camera lenses over time and changes in weather conditions. Understanding the impact of environmental changes on model performance is critical to the safe use of the model but has not been systematically investigated. In this study, we cast environmental changes as distribution shifts in the data and tackle the out-of-distribution generalization problem. In particular, we investigate the impact of performance degradation and uncertainty estimation under more than 30 distribution shifts considered in real-world applications. Our experimental results show that there is a correlation between classification accuracy and uncertainty in out-of-distribution environments. Furthermore, it is suggested that uncertainty calibration is not necessarily effective in environments where severe corruption occurs. We believe these findings will contribute to the safe use of the model in the real world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Huang, Huawei Mao, Shiwen The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The School of Software Engineering Sun Yat-Sen University Zhuhai China The Department of Electrical and Computer Engineering Auburn University Auburn United States

As Metaverse emerges as the next-generation Internet paradigm, the ability to efficiently generate content is paramount. AI-Generated Content (AIGC) emerges as a key solution, yet the resource-intensive nature of large Generative AI (GAI) models presents challenges. To address this issue, we introduce an AIGC-as-a-Service (AaaS) architecture, which deploys AIGC models in wireless edge networks to ensure broad AIGC services accessibility for Metaverse users. Nonetheless, an important aspect of providing personalized user experiences requires carefully selecting AIGC Service Providers (ASPs) capable of effectively executing user tasks, which is complicated by environmental uncertainty and variability. Addressing this gap in current research, we introduce the AI-Generated Optimal Decision (AGOD) algorithm, a diffusion model-based approach for generating the optimal ASP selection decisions. Integrating AGOD with Deep Reinforcement Learning (DRL), we develop the Deep Diffusion Soft Actor-Critic (D2SAC) algorithm, enhancing the efficiency and effectiveness of ASP selection. Our comprehensive experiments demonstrate that D2SAC outperforms seven leading DRL algorithms. Furthermore, the proposed AGOD algorithm has the potential for extension to various optimization problems in wireless networks, positioning it as a promising approach for future research on AIGC-driven services. The implementation of our proposed method is available at: https://***/Lizonghang/AGOD. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Empowering Machines to Think Like Chemists: Unveiling Molecular Structure-Polarity Relationships with Hierarchical Symbolic Regression

arXiv

引用

arXiv 2024年

作者： Lou, Siyu Liu, Chengchun Chen, Yuntian Mo, Fanyang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo315200 China School of Materials Science and Engineering Peking University Beijing100871 China -Preferred Program Peking University Shenzhen Graduate School Shenzhen518500 China

Thin-layer chromatography (TLC) is a crucial technique in molecular polarity analysis. Despite its importance, the interpretability of predictive models for TLC, especially those driven by artificial intelligence, remains a challenge. Current approaches, utilizing either high-dimensional molecular fingerprints or domain-knowledge-driven feature engineering, often face a dilemma between expressiveness and interpretability. To bridge this gap, we introduce Unsupervised Hierarchical Symbolic Regression (UHiSR), combining hierarchical neural networks and symbolic regression. UHiSR automatically distills chemical-intuitive polarity indices, and discovers interpretable equations that link molecular structure to chromatographic behavior. Copyright © 2024, The Authors. All rights reserved.

关键词： Thin layer chromatography

来源：评论

学校读者我要写书评

暂无评论

Customer Segment Classification Prediction in the Australian Retail Based on Machine Learning Algorithms 23

Customer Segment Classification Prediction in the Australian...

引用

Proceedings of the 2023 4th International Conference on Machine Learning and computer Application

作者： Yiming Luo Rui Zhang Fei Wang Tao Wei Business Schoo The University of Sydney Austialia Computer and information sciences program Harrisburg University of Science and Technology United States Faculty of Science and Technology Beijing Normal University-Hong Kong Baptist University United International College China School of Chemical and Environmental Engineering Sichuan University of Science & Engineering China

ISBN: (纸本)9798400709449

Customer segmentation is an essential area of business analytics today. Accurate customer segmentation is access to improves the efficiency of marketing campaigns and customer satisfaction. This study employs multiple machine learning methods to classify Australian Retail company BIGW's customer segments and first to apply multiple model explanation methods to find insights related to customer segmentation identification. After rigorous comparison and hyperparameter fine-tuning, XGBoost is the most adept for this dataset. We derive three key insights through the model results and model interpretive methods. First, BIGW's primary clientele comprises young families in urban areas who prefer cost-effective products, establishing the foundation of their consumer base. Second, the model result indicates a notable gap in BIGW's understanding of its high-end customers, suggesting an area for immediate attention. Third, a specific customer segment emerges from the data: individuals favoring online shopping, demonstrating high total expenditure but low interest in promotions, representing a high-value segment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing Haul Truck Safety: A Deep Neural Network-Based Driver Assistance System for Blind Spot Detection

Advancing Haul Truck Safety: A Deep Neural Network-Based Dri...

引用

Smart World Congress (SWC), IEEE

作者： Qaiser Anwar Muhammad Hanif Daisuke Shimotoku Hill H Kobayashi Kobayashi Lab Center for Spatial Information Science (CSIS) University of Tokyo Chiba Japan Faculty of Computer Science and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences and Technology (GIKI) Topi Pakistan Kobayashi Lab Center for Spatial Information Science (CSIS) Information Technology Center (ITC) University of Tokyo Chiba Japan Kobayashi Lab Center for Spatial Information Science (CSIS) Information Technology Center (ITC) Graduate School of Frontier Sciences (GSFS) University of Tokyo Chiba Japan

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

The utilization of haul trucks within the mining industry presents a myriad of safety challenges, primarily due to their considerable size. Haul trucks serve as indispensable assets in large-scale construction projects, owing to their unparalleled capacity for transporting heavy loads. Tailored specifically for such rigorous tasks, these trucks are restricted to traversing non-crowded roads to uphold safety standards. Nonetheless, their sheer size and design contribute to numerous blind spots, rendering them challenging to operate. In this study, we address the issue of blind spots in haul trucks by proposing a cutting-edge machine vision system. Our innovative approach integrates machine vision technology with advanced Deep Neural Network (DNN) algorithms to detect objects within the truck’s blind spots and promptly alert the driver in real time. Leveraging a comprehensive dataset of images, the DNN is trained to identify objects of varying sizes and shapes accurately. To facilitate seamless monitoring, our system incorporates a visual display unit installed in the truck’s cab, offering the driver a real-time panoramic view of the surroundings. Initial testing conducted in controlled laboratory settings yielded promising results, with the DNN algorithm demonstrating high accuracy in object detection. To validate our concept, we opted to employ a standard car as a surrogate for the haul truck. Equipped with four strategically positioned cameras providing a 360 -degree field of view, we scaled down the truck’s dimensions to match those of a car. Utilizing the D455 Intel RealSense camera, we precisely measure the distances of detected objects and issue alerts to the driver within a 4 -meter range via a built-in buzzer. Our system is further fortified with the inclusion of the Jetson Orin Nano developer kit. Real-world testing conducted in a moving vehicle showcased the effectiveness of our system, garnering favorable results. Our endeavor underscores a significant ste

关键词： YOLO Visualization Artificial neural networks Cameras Real-time systems Safety Automobiles Standards Vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

A linearization for stable and fast geographically weighted Poisson regression

arXiv

引用

arXiv 2023年

作者： Murakami, Daisuke Tsutsumida, Narumasa Yoshida, Takahiro Nakaya, Tomoki Lu, Binbin Harris, Paul Department of Data Statistical Science Institute of Statistical Mathematics Tachikawa Japan Department of Information and Computer Sciences Graduate School of Science and Engineering Saitama University Saitama Japan Department of Urban Engineering School of Engineering The University of Tokyo Tokyo Japan Department of Frontier Science for Advanced Environment The Graduate School of Environmental Studies Tohoku University Sendai Japan School of Remote Sensing and Information Engineering Wuhan University Wuhan China Net Zero and Resilient Farming Rothamsted Research North Wyke United Kingdom

Although geographically weighted Poisson regression (GWPR) is a popular regression for spatially indexed count data, its development is relatively limited compared to that found for linear geographically weighted regression (GWR), where many extensions (e.g., multiscale GWR, scalable GWR) have been proposed. The weak development of GWPR can be attributed to the computational cost and identification problem in the underpinning Poisson regression model. This study proposes linearized GWPR (L-GWPR) by introducing a log-linear approximation into the GWPR model to overcome these bottlenecks. Because the L-GWPR model is identical to the Gaussian GWR model, it is free from the identification problem, easily implemented, computationally efficient, and offers similar potential for extension. Specifically, L-GWPR does not require a double-loop algorithm, which makes GWPR slow for large samples. Furthermore, we extended L-GWPR by introducing ridge regularization to enhance its stability (regularized L-GWPR). The results of the Monte Carlo experiments confirmed that regularized L-GWPR estimates local coefficients accurately and computationally efficiently. Finally, we compared GWPR and regularized L-GWPR through a crime analysis in Tokyo. Copyright © 2023, The Authors. All rights reserved.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

TPMARL-MSS Thought-Perception Multi-Agent Reinforcement Learning Meeting Scheduling System

TPMARL-MSS Thought-Perception Multi-Agent Reinforcement Lear...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Jinsong Zhang Xiaoxuan Mao Lu Li Hanqian Wu Joint graduate school Southeast University Nanjing China College of Software Engineering Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration of Ministry of Education School of Cyber Science and Engineering Southeast University Nanjing China

In today's evolving society, the increasing complexity and frequency of meetings necessitate advanced scheduling systems. Traditional methods are constrained by rigid prede-fined strategies, lack intelligent negotiation mechanisms, and often compromise user privacy. Addressing these challenges, we introduce the Thought-Perception Multi-Agent Reinforcement Learning Meeting Scheduling System (TPMARL-MSS). Unlike conventional systems, TPMARL-MSS autonomously learns and refines its strategies through continuous feedback. It features automated negotiation and adaptive decision-making, offering a more nuanced scheduling approach. Importantly, our Thought-Perception module protect privacy, allowing the agent to deduce preferences from participant behavior without revealing personal data. Evaluations on the real-world dataset shows that TPMARL-MSS surpasses traditional methods in efficiency and schedule quality, highlighting its practical applicability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Interactive Sign Language Based Mobile Application for Deaf People

An Interactive Sign Language Based Mobile Application for De...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Vionna Setiawan Raynaldo Thendyliputra Sherly Angelina Santami Daniel Hansen Harco Leslie Hendric Spits Warnars Arief Ramdhan Antoine Doucet Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Telkom University Bandung Indonesia Laboratoire L3i Universite de La Rochelle France

Disability is a complex problem affecting many lives in Indonesia, especially people with hearing impairments. Disability is also a complex phenomenon, starting from the type of disability, degree of disability, and age of persons with disabilities to interactions and environmental impacts on disability. Moreover, there are many testimonies from around the world that people with disabilities are more likely to be weak and less likely to get an education. This paper aims to present a mobile application that offers sign language images and videos of any text in a learning environment that is shaped like a dictionary module to increase their vocabulary, learn a new sign language, and pronounce a word. This mobile application is specially designed for deaf people who have limitations in learning and educational training. This mobile application is equipped with several features such as user registration for the deaf and normal people who like to learn sign language, discussing through forums, using a sign language dictionary containing sign language text and pictures, using interactive learning videos, registering for an event activity, including giving input, and also make a donation.

关键词： Training Vocabulary Dictionaries Gesture recognition Auditory system Assistive technologies Market research

来源：评论

学校读者我要写书评

暂无评论

Multicast Routing Technique for Augmenting Routing Efficiency in Mobile WSN

Multicast Routing Technique for Augmenting Routing Efficienc...

引用

International Conference on Computing Methodologies and Communication (ICCMC)

作者： K. Anand M. Rajkumar Srikanth MS S. Radhika Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai Tamil Nadu India School of Information Technology and Engineering VIT University Vellore Tamil Nadu India Program Specialist TNS India Foundation Bangalore Karnataka India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India

Mobile Wireless Sensor Network (MWSN) is an active network completely self-governing from a fixed structure. Also, MWSN has small channel bandwidth, great node movement, and inadequate battery energy. In WSN, flooding raises the reliability regarding successful communication of a packet with greater overhead. The flooding consumes the network's resources quickly, especially in terms of the lifetime of the node and energy, etc. Unicast routing creates an extra overhead and increases energy consumption because unicast routing mainly focuses on only minimum distance. But, multicasting is used when the desired destination is at maximum distance and increases the network's reliability in terms of throughput. This paper's objectives are to develop an efficient and reliable protocol using multicasting and unicasting to overcome the issue of higher overhead due to flooding. Multicast Routing Technique for Augmenting (MRTA) routing efficiency in MWSN is introduced. This method aims to enhance the link stability of the route for raising the route lifetime and diminishing the routing load. This method discovers the stable path from several ways to decline the overhead and delay between the sender and receiver. Simulation results demonstrate that this approach improves the network lifetime increases the throughput, and minimizes the routing load in the MWSN.

关键词： Wireless sensor networks Unicast Receivers Multicast communication Routing Throughput Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Conflict-Based Search and Improvement Strategies for Solving a New Lexicographic Bi-Objective Multi-Agent Path Finding Problem

Conflict-Based Search and Improvement Strategies for Solving...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Li, Siyi Li, Xingyang Zhou, Mengchu Zhao, Ziyan Liu, Shixin Northeastern University College of Information Science and Engineering Shenyang110819 China Northeastern University Foshan Graduate School of Innovation Foshan528311 China Northeastern University Faculty of Robot Science and Engineering Shenyang110819 China New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States Macao Inst. of Systems Engineering and Collaborative Laboratory for Intelligent Science and Systems Macau University of Science and Technology 999078 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Multi-Agent Path Finding (MAPF) is an important problem with a variety of applications. Its aim is to find collision-free paths for agents having separate start and goal positions. This work proposes a new lexicographic bi-objective MAPF considering different task types, where agents are divided into two kinds to perform critical and acritical tasks. This is common in practical intelligent warehousing scenarios where a critical/acritical-task-performing agent (called c-agent and a-agent, respectively) may represent a full-load/no-load one or the one conducting urgent/non-urgent tasks. The primary objective is to minimize the sum-of-costs of c-agents, while the secondary objective is to minimize the sum-of-costs of a-agents. Two MAPF algorithms are modified to fit and solve the concerned problem for the first time. Moreover, four improvement strategies are embedded to the proposed algorithms and proved to be effective in solving MAPF problems with different task types. © 2022 IEEE.

关键词： Multi agent systems

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：