检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shen, Chen He, Zhixue Guo, Hao Hu, Shuyue Tanimoto, Jun Shi, Lei Holme, Petter Faculty of Engineering Sciences Kyushu University Fukuoka816-8580 Japan School of Statistics and Mathematics Yunnan University of Finance and Economics Kunming650221 China Department of Computer Science and Technology Tsinghua University Beijing100084 China Shanghai Artificial Intelligence Laboratory Shanghai China Interdisciplinary Graduate School of Engineering Sciences Kyushu University Fukuoka816-8580 Japan Department of Computer Science Aalto University Espoo02150 Finland Center for Computational Social Science Kobe University Kobe650-0017 Japan

A stylized experiment, the public goods game, has taught us the peculiar reproducible fact that humans tend to contribute more to shared resources than expected from economically rational assumptions. There have been two competing explanations for this phenomenon: either contributing to the public good is an innate human trait (the prosocial preference hypothesis) or a transitory effect while learning the game (the confused learner hypothesis). We use large-scale experimental data from a novel experimental design to distinguish between these two hypotheses. By monitoring the effects of zealots (persistently cooperating bots) and varying the participants’ awareness of them, we find a considerably more complex scenario than previously reported. People indeed have a prosocial bias, but not to the degree that they always forego taking action to increase their profit. While our findings end the simplistic theorizing of prosociality in the public goods game, an observed positive, cooperative response to zealots has actionable policy implications. © 2024, CC BY-NC-SA.

关键词： Public policy

来源：评论

学校读者我要写书评

暂无评论

Information Fusion in Smart Agriculture: Machine Learning Applications and Future Research Directions

arXiv

引用

arXiv 2024年

作者： Katharria, Aashu Rajwar, Kanchan Pant, Millie Velásquez, Juan D. Snášel, Václav Deep, Kusum Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Roorkee India Statistical Quality Control and Operations Research Unit Indian Statistical Institute Hyderabad India Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Roorkee Roorkee India Department of Industrial Engineering University of Chile Santiago Chile Instituto Sistemas Complejos de Ingeniería Santiago Chile Department of Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic Department of Mathematics Indian Institute of Technology Roorkee Roorkee India

Machine learning (ML) is a rapidly evolving technology with expanding applications across various fields. This paper presents a comprehensive survey of recent ML applications in agriculture for sustainability and efficiency. Existing reviews mainly focus on narrow subdomains or lack a fusion-driven perspectives. This study provides a combined analysis of ML applications in agriculture, structured around five key objectives: (i) Analyzing ML techniques across pre-harvesting, harvesting, and post-harvesting phases. (ii) Demonstrating how ML can be used with agricultural data and data fusion. (iii) Conducting a bibliometric and statistical analysis to reveal research trends and activity. (iv) Investigating real-world case studies of leading artificial intelligence (AI)-driven agricultural companies that use different types of multisensors and multisource data. (v) Compiling publicly available datasets to support ML model training. Going beyond existing previous reviews, this review focuses on how machine learning (ML) techniques, combined with multi-source data fusion (integrating remote sensing, IoT, and climate analytics), enhance precision agriculture by improving predictive accuracy and decision-making. Case studies and statistical insights illustrate the evolving landscape of AI driven smart farming, while future research directions also discusses challenges associated with data fusion for heterogeneous datasets. This review bridges the gap between AI research and agricultural applications, offering a roadmap for researchers, industry professionals, and policymakers to harness information fusion and ML for advancing precision agriculture. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables

arXiv

引用

arXiv 2022年

作者： Yu, Erxin Du, Lan Jin, Yuan Wei, Zhepei Chang, Yi School of Artificial Intelligence Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University China International Center of Future Science Jilin University China Faculty of Information Technology Monash University Australia

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions. In this paper, we develop a topic-informed discrete latent variable model for semantic textual similarity, which learns a shared latent space for sentence-pair representation via vector quantization. Compared with previous models limited to local semantic contexts, our model can explore richer semantic information via topic modeling. We further boost the performance of semantic similarity by injecting the quantized representation into a transformer-based language model with a well-designed semantic-driven attention mechanism. We demonstrate, through extensive experiments across various English language datasets, that our model is able to surpass several strong neural baselines in semantic textual similarity tasks. © 2022, CC0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic geometric latent diffusion model for graph generation 24

Hyperbolic geometric latent diffusion model for graph genera...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xingcheng Fu Yisen Gao Yuecen Wei Qingyun Sun Hao Peng Jianxin Li Xianxian Li Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China and Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Electricity Theft Detection using Neural Turing Machines and Machine Learning

Optimizing Electricity Theft Detection using Neural Turing M...

引用

Software, Systems and Information technology (SSITCON), International Conference on

作者： Erdal Büyükbiçakci Selcuk Bulat C Senthilkumar A Rajesh Malatthi Sivasundaram Rama Raju Svsv Palla Department of Computer Technologies University of Applied Sciences Information Technologies Vocational Highschool Sakarya Turkey Department of Nanoscience and Nanoengineering Institute of Natural Sciences Sakarya University Turkey 2 Turkish Standards Institution Istanbul Turkey Department of Artificial Intelligence and Data Science Erode Sengunthar Engineering College Erode India Department of CSE Erode Sengunthar Engineering College Erode India Department of Computer Science and Design KSR College of Engineering Tiruchengode India Department of CSE Vignan’s Institute of Information Technology Duvvada India

ISBN: (数字)9798350352931

ISBN: (纸本)9798350352948

Electricity theft detection (ETD) is crucial for smart grids to maintain their cost-effectiveness. Current approaches for identifying theft struggle with large datasets of electricity use owing to problems with missing values, data variance, and nonlinear patterns in the data; furthermore, an integrated infrastructure to coordinate the study of electricity load data is not currently in *** suggested method trains models after feature extraction and stage preprocessing. data normalization, missing value imputation, and data cleansing are all components of data preprocessing. Utility data sets often suffer from inconsistent and missing data as a result of manual and unsynchronized meter reading and registering processes; however, this can be mitigated through the feature extraction process. All the way through training, the proposed approach stuck with the NTM paradigm. The average accuracy of this state-of-the-art approach is $\mathbf{94.22\%}$, which is higher than RNN and ELM.

关键词： Training Accuracy Turing machines Electricity Biological system modeling Feature extraction Imputation Smart grids Meter reading Synchronization

来源：评论

学校读者我要写书评

暂无评论

A Rapid Detection Method of Sewing Stitch Defects Based on Machine Vision

SSRN

引用

SSRN 2023年

作者： Zheng, Xiaohu Chen, Yufan Xu, Xiuliang Liu, Bing Institute of Artificial Intelligence Donghua University Shanghai201620 China Shanghai Industrial Big Data and Intelligent Systems Engineering Technology Center Shanghai201620 China College of Information Science and Technology Donghua University Shanghai201620 China Hangzhou Zhongfu Technology&Innovation Research Institute Co. Ltd Shanghai201620 China Precise Machinery Scientific & Technology Co. Ltd Shanghai201599 China

In order to solve the problem of motion blur caused by sewing speed, an image DeblurGAN-BSV3 algorithm is proposed. Firstly, different attention fusion mechanisms are introduced to achieve accurate extraction of image features. Secondly, the depth-separable convolution of the trunk network is replaced by blueprint convolution to ensure the processing speed of the detection algorithm and the clarity of the output image. In order to solve the difficulty of rapid detection of pin defects, a student-teacher feature pyramid matching method was proposed. Firstly, the abnormal region interpretation technology was used to explicitly visualize the defect area of the identified abnormal instances, and then the abnormal detection score was performed on the detected images to make good judgment. The experimental results show that the combination of the above two methods has a good ability for rapid defect detection. Rapid detection of common pin defects is realized. © 2023, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Cloud-magnetic resonance imaging system: In the era of 6G and artificial intelligence

引用

Magnetic Resonance Letters 2025年 57-68页

作者： Yirong Zhou Yanhuang Wu Yuhan Su Jing Li Jianyu Cai Yongfu You Jianjun Zhou Di Guo Xiaobo Qu Department of Electronic Science Intelligent Medical Imaging R&D Center Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance National Institute for Data Science in Health and Medicine Xiamen University Department of Electronic Science Key Laboratory of Digital Fujian on IoT Communication Xiamen University Shanghai Electric Group Co. Ltd China Telecom Group China Mobile Group Department of Radiology Zhongshan Hospital (Xiamen) Fudan University Xiamen Municipal Clinical Research Center for Medical Imaging Fujian Province Key Clinical Specialty Construction Project (Medical Imaging Department) Xiamen Key Laboratory of Clinical Transformation of Imaging Big Data and Artificial Intelligence School of Computer and Information Engineering Xiamen University of Technology

Magnetic resonance imaging(MRI) plays an important role in medical diagnosis,generating petabytes of image data annually in large *** voluminous data stream requires a significant amount of network bandwidth and extensive storage ***,local data processing demands substantial manpower and hardware *** isolation across different healthcare institutions hinders crossinstitutional collaboration in clinics and *** this work,we anticipate an innovative MRI system and its four generations that integrate emerging distributed cloud computing,6G bandwidth,edge computing,federated learning,and blockchain *** system is called Cloud-MRI,aiming at solving the problems of MRI data storage security,transmission speed,artificial intelligence(AI) algorithm maintenance,hardware upgrading,and collaborative *** workflow commences with the transformation of k-space raw data into the standardized Imaging Society for Magnetic Resonance in Medicine Raw data(ISMRMRD) ***,the data are uploaded to the cloud or edge nodes for fast image reconstruction,neural network training,and automatic ***,the outcomes are seamlessly transmitted to clinics or research institutes for diagnosis and other *** Cloud-MRI system will save the raw imaging data,reduce the risk of data loss,facilitate inter-institutional medical collaboration,and finally improve diagnostic accuracy and work efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flying Neural Network-Based Optimistic Financial Early Alert System in AI Model

Flying Neural Network-Based Optimistic Financial Early Alert...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Saikrishna Boggavarapu S. Shabbir Ali G. Manikandan R. Mohanraj Devesh Pratap Singh Revathi. R Department of Information Technology University of the Cumberlands Prospect Heights IIIioni United States Department of Electronics & Communication Engineering KL University Guntur India Department of Electronics and Communication Engineering Saveetha School Of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Chennai India Department of Artificial Intelligence and Data Science St.Martin's Engineering College Secunderabad Telangana India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttrakhand India Department of Computer Science Karpagam Academy of Higher Education Coimbatore

An innovative method for early warnings in the area of financial risk management is the Flying Neural Network-based Optimistic Financial Early Alert System (FNN-OFEAS). The FNN-OFEAS outperforms conventional models and rule-based systems because it makes use of the Flying Neural Network architecture and incorporates sentiment analysis. Using a fictitious dataset including past stock prices, financial ratios, economic indicators, and sentiment analysis data, this study details the development, use, and findings of the FNN-OFEAS. The results show that the system is effective at capturing complicated temporal correlations, recognising non-linear patterns, and factoring in market sentiment, all of which contribute to improved risk identification in a timely and accurate manner. Early risk identification, investment decision assistance, regulatory compliance, and financial stability evaluation are just few of the real-world uses for the FNN-OFEAS. Its application is beneficial for financial institutions, investors, regulators, and policymakers since it enhances decision-making, reduces risk, and sheds light on previously hidden information. More work has to be done to improve the model architecture, include other data sources, provide real-time implementations, evaluate the model's resilience, and make it easier to comprehend the results. Addressing financial risks and bolstering financial stability in volatile market settings is one area where the FNN-OFEAS shows promise.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Last-iterate Convergence Algorithms in Solving Games

arXiv

引用

arXiv 2023年

作者： Meng, Linjian Zhang, Youzhi Ge, Zhenxing Yang, Shangdong Ding, Tianyu Li, Wenbin Yang, Tianpei An, Bo Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS Hong Kong Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications China Microsoft Corporation United States School of Computer Science and Engineering Nanyang Technological University Singapore

To establish last-iterate convergence for Counterfactual Regret Minimization (CFR) algorithms in learning a Nash equilibrium (NE) of extensive-form games (EFGs), recent studies reformulate learning an NE of the original EFG as learning the NEs of a sequence of (perturbed) regularized EFGs. Consequently, proving last-iterate convergence in solving the original EFG reduces to proving last-iterate convergence in solving (perturbed) regularized EFGs. However, the empirical convergence rates of the algorithms in these studies are suboptimal, since they do not utilize Regret Matching (RM)-based CFR algorithms to solve perturbed EFGs, which are known the exceptionally fast empirical convergence rates. Additionally, since solving multiple perturbed regularized EFGs is required, fine-tuning across all such games is infeasible, making parameter-free algorithms highly desirable. In this paper, we prove that CFR+, a classical parameter-free RM-based CFR algorithm, achieves last-iterate convergence in learning an NE of perturbed regularized EFGs. Leveraging CFR+ to solve perturbed regularized EFGs, we get Reward Transformation CFR+ (RTCFR+). Importantly, we extend prior work on the parameter-free property of CFR+, enhancing its stability, which is crucial for the empirical convergence of RTCFR+. Experiments show that RTCFR+ significantly outperforms existing algorithms with theoretical last-iterate convergence guarantees. Copyright © 2023, The Authors. All rights reserved.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Implementing Genetic Algorithms for Optimization in Neuro-Cognitive Rehabilitation Robotics

Implementing Genetic Algorithms for Optimization in Neuro-Co...

引用

Cognitive Robotics and Intelligent Systems (ICC - ROBINS), International Conference on

作者： L. B. Abhang Ravindra Changala Anudeb Ghosh Prabhakar S Manage Vuda Sreenivasa Rao B Kiran Bala Automation and Robotics Dept Pravara Rural Engineering College Loni Under. SPPU University Pune Department of Information Technology Guru Nanak Institutions Technical Campus Hyderabad India Department of Environmental Studies Siksha - Bhavana Visva-Bharati Santiniketan Department of Electronics and Communication KLE Technological University's MSSCET Belagavi Campus Belagavi Karnataka Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram A.P the Department Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering Trichy

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

The study explores the intersection of robotics and neuro-cognitive rehabilitation to offer personalized assistance for individuals with neurological disorders, emphasizing autism spectrum disorder (ASD). The proposed methodology integrates Genetic Algorithms (GAs) to optimize the performance of robotic interventions. The data collection phase involves compiling a comprehensive image dataset capturing facial expressions, gestures, and relevant visual cues associated with ASD. Leveraging robotic platforms designed for therapeutic interventions, feature extraction techniques identify intricate patterns within the data. Advanced algorithms, including GAs, classify the dataset into positive (ASD) and negative (non-ASD) categories. The framework introduces a Diagnosis Matrix for enhanced diagnostic precision, correlating observed robotic interactions with clinical assessments. An Ontology Knowledge base adapts responses based on evolving patient needs. The proposed method surpasses all others, achieving an accuracy of 95.08% and demonstrating superior precision, recall, and F1-score metrics. This indicates the efficacy of the proposed approach in achieving a well-balanced performance with high accuracy and robustness in correctly identifying positive instances. The results underscore the potential of the proposed method for classification tasks, showcasing its superiority in comparison to traditional SVM, CNN, and even a well-established deep learning architecture like VGG-16. The Receiver Operating Characteristic curve validates the model's discriminatory power.

关键词： Support vector machines Neurological diseases Visualization Knowledge based systems Receivers Ontologies Robustness

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：