检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Karnik, Santhosh Veselovska, Anna Iwen, Mark Krahmer, Felix Department of Mathematics Northeastern University Boston United States Department of Computational Mathematics Science and Engineering Michigan State University East Lansing United States TUM School of Computation Information and Technology Munich Data Science Institute Technical University of Munich Garching Germany Munich Center for Machine Learning Munich Germany Department of Mathematics Michigan State University East Lansing United States

We provide a rigorous analysis of implicit regularization in an overparametrized tensor factorization problem beyond the lazy training regime. For matrix factorization problems, this phenomenon has been studied in a number of works. A particular challenge has been to design universal initialization strategies which provably lead to implicit regularization in gradient-descent methods. At the same time, it has been argued by [7] that more general classes of neural networks can be captured by considering tensor factorizations. However, in the tensor case, implicit regularization has only been rigorously established for gradient flow or in the lazy training regime. In this paper, we prove the first tensor result of its kind for gradient descent rather than gradient flow. We focus on the tubal tensor product and the associated notion of low tubal rank, encouraged by the relevance of this model for image data. We establish that gradient descent in an overparametrized tensor factorization model with a small random initialization exhibits an implicit bias towards solutions of low tubal rank. Our theoretical findings are illustrated in an extensive set of numerical simulations show-casing the dynamics predicted by our theory as well as the crucial role of using a small random initialization. © 2024, CC BY-SA.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Vehicle Prediction for BUS Identification Output from our Route Testing Real Time Algorithm

Vehicle Prediction for BUS Identification Output from our Ro...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： M. Misba R. Ramya Joel Dickson L. Sharmila J. Kavitha K. Udayakumar Department of Artificial Intelligence and Machine Learning Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu India Department of Artificial Intelligence and Data Science St. Joseph's College of Engineering Chennai Bethlehem Institute of Engineering Karungal Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

Traffic generation in Indian cities is of a mixed nature, comprising over a dozen types of vehicles that can be broadly categorized into slow-moving and fast-moving vehicles. This study highlights the challenges associated with the inefficient operation of the existing bus system. GPS and mobile networks form integral components of the current system, enabling data storage and management using PostgreSQL. The system provides robust and reliable data to fulfill requests from other software applications. Operating on cloud platforms, it is compatible with all major web browsers. The proposed algorithm continuously tracks the real-time location of buses and their corresponding WMS (Web Map Service) location, alerting users through marker notifications. This paper also explores measures to evaluate the efficiency and effectiveness of bus services. Recognizing that an inadequate public transport system impedes economic growth and development, this study emphasizes the need to enhance the overall quality and accessibility of public transportation. The findings aim to improve the operational efficiency of bus services, contributing to a more effective and sustainable transport system.

关键词： Urban areas Software algorithms Memory Prediction algorithms Real-time systems Software Maintenance Software reliability Public transportation Testing

来源：评论

学校读者我要写书评

暂无评论

Effects of a graphic organizer-based two-tier test approach on students’ learning achievement and behaviors in spherical video-based virtual learning contexts

引用

Computers and Education 2023年 198卷

作者： Hwang, Gwo-Jen Chen, Hui-Chueh Hsu, Chung-Yuan Hwang, Gwo-Haur Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology Taiwan Department of Child Care National Pingtung University of Science and Technology Taiwan Bachelor Program in Industrial Technology National Yunlin University of Science and Technology Taiwan Graduate Institute of Educational Information and Measurement National Taichung University of Education Taiwan Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Taiwan

Situating learners in a context relevant to scientific phenomena enables them to acquire knowledge through experience, reflection, conceptualization, and practice, which is an important learning mode in science education. However, learners generally do not have opportunities to experience many scientific phenomena in the real world. Therefore, virtual learning environments (VLE) are becoming a frequently adopted technology to provide authentic learning contexts. In particular, spherical video-based learning environments (SVLE), which are a low-tech form of VLE, have attracted the attention of school teachers and educational technology researchers. Additionally, effective assessment methods, such as the two-tier-test, have been adopted to examine learners' performance during the virtual learning process. On the other hand, researchers have pointed out that lack of effective learning strategies may decrease the learning effects in a virtual learning context. Hence, this study integrated a graphic organizer into a two-tier test-based learning mode, in which the first-tier questions were declarative items with a short answer (e.g., the questions of where, what, and when), whereas the second-tier questions were more in-depth, deeper causal-type questions (e.g., the questions of why and how), in the contexts of SVLE. To verify the effectiveness of this learning approach, a graphic organizer-based two-tier test SVLE was developed;moreover, a quasi-experimental design was conducted in the "Mysteries of the Earth" unit of the sixth graders' natural science course. A total of 41 sixth graders from two classes, with an average age of 12, were recruited in this experiment. One class was assigned to be the experimental group adopting the graphic organizer-based two-tier test SVLE (GT-SVLE), while the other was the control group adopting the conventional two-tier test-based SVLE (CT-SVLE). All of the students learned with the SVLE using tablet computers. Based on the results, the

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Optimal kernel choice for score function-based causal discovery 24

Optimal kernel choice for score function-based causal discov...

引用

Proceedings of the 41st International Conference on Machine learning

作者： Wenjie Wang Biwei Huang Feng Liu Xinge You Tongliang Liu Kun Zhang Mingming Gong School of Mathematics and Statistics The University of Melbourne Australia and Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Halicioğlu Data Science Institute (HDSI) University of California San Diego School of Computing and Information Systems The University of Melbourne Australia Huazhong University of Science and Technology China School of Computer Science Faculty of Engineering The University of Sydney Australia Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates and Department of Philosophy Carnegie Mellon University

Score-based methods have demonstrated their effectiveness in discovering causal relationships by scoring different causal structures based on their goodness of fit to the data. Recently, Huang et al. (2018) proposed a generalized score function that can handle general data distributions and causal relationships by modeling the relations in reproducing kernel Hilbert space (RKHS). The selection of an appropriate kernel within this score function is crucial for accurately characterizing causal relationships and ensuring precise causal discovery. However, the current method involves manual heuristic selection of kernel parameters, making the process tedious and less likely to ensure optimality. In this paper, we propose a kernel selection method within the generalized score function that automatically selects the optimal kernel that best fits the data. Specifically, we model the generative process of the variables involved in each step of the causal graph search procedure as a mixture of independent noise variables. Based on this model, we derive an automatic kernel selection method by maximizing the marginal likelihood of the variables involved in each search step. We conduct experiments on both synthetic data and real-world benchmarks, and the results demonstrate that our proposed method outperforms heuristic kernel selection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Paradigm shift in psychiatric neuroscience:Multidimensional integrative theory

Medicine Plus

引用

Medicine Plus 2024年第2期1卷 1-5页

作者： Zhu-Qing Gong Bharat B.Biswal Xi-Nian Zuo State Key Laboratory of Cognitive Neuroscience and Learning Beijing Normal UniversityBeijing 100875China Department of Biomedical Engineering New Jersey Institute of TechnologyNewarkNJ 07102USA Developmental Population Neuroscience Research Center IDG/McGovern Institute for Brain ScienceBeijing Normal UniversityBeijing 100875China National Basic Science Data Center Beijing 100190China

Abnormal structure and function of the human brain cause various mental and neurological *** search for neurobiological mechanisms and biomarkers associated with psychiatric disorders has always been a focal point and a challenging issue in *** magnetic resonance imaging(fMRI)allows the noninvasive re-cording of high spatial-temporal resolution brain activity in patients,making it one of the primary research methods in integrative neuroscience.

关键词： dimension shift siona multi integrative neuroscience paradigm psychiatric theory

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-Based Kidney Disease Detection: Resampling Cubature Kalman Filter and Physics-Guided VGG Cross-Contextual Network

Ultrasound-Based Kidney Disease Detection: Resampling Cubatu...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Padmanayana N.S.L. Kumar Kurumeti Veena S Ch. Raja Vijay Jagdish Upadhye Ramya Maranan Department of Artificial Intelligence and Data Science Engineering AJ Institute of Engineering and Technology Mangaluru Karnataka India Department of Artificial Intelligence and Machine Learning Aditya University Surampalem Andhra Pradesh India Department of Electronics and Communication Engineering SJC Institute of Technology Chikkaballapur Karnataka India Department of Electronics and Communication Engineering Mahatma Gandhi Institute of Technology Hyderabad Telangana India Department of Microbiology Dept of Microbiology Research and Development Cell (RDC) Parul Institute of Applied Sciences (PIAS) Parul University Post Limda Waghodia Gujarat India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Limitations of ultrasound-based identification of kidney disease include poor image resolution, operator reliance, and lack of detection of small tissue anomalies. Diagnostic accuracy may be affected by artefacts or noise, or changes in patient anatomy. It may also have difficulty detecting microscopic structural changes or renal disease in its incipiency. The limitations are overcome by the analysis of the Resampling Cubature Kalman Filter and Physics-Guided VGG Cross-Contextual Networks (RCKF-PG-VGG-CCNet) for kidney disease detection from ultrasound images based on the Kidney Ultrasound Image dataset. The initial use of the Resampling Cubature Kalman Filter and the first use of Physics-Guided VGG Cross-Contextual Networks is to enhance image quality. Through identifying regions through deviations, the Scale-Aware Meet Transformer (SAMT) performs segmentation. While the Synergistic Fibroblast Optimization (SFO) enhances classification performance through optimization of the search for diseased regions, the Physics-Guided VGG Cross-Contextual Networks (PG-VGG-CCNet) classify kidney disease and identify features. Experimental output from a Python-based experiment demonstrates that RCKF-PG-VGG-CCNet is more efficient than other methods with 99.9% efficiency and 99.8% sensitivity and may enhance the accuracy of kidney disease detection.

关键词： Ultrasonic imaging Accuracy Sensitivity Noise Fibroblasts Transformers Kalman filters Kidney Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

Advanced Process Control in Manufacturing Using IoT Devices and Artificial Neural Networks

Advanced Process Control in Manufacturing Using IoT Devices ...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： V. Sumathi Ramesh S Chethan Chandra S Basavaraddi Visumathi J Ishwarya M.V S. Srinivasan Department of Mathematics Sri Sairam Engineering College Chennai Tamil Nadu India Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning R&D Don Bosco Institute of Technology VTU Belagavi Karnataka India Department of Information Technology Veltech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Artificial intelligence and Data science Department Agni College of Technology Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Optimization of industrial activities is significantly helped by Advanced Process Control (APC), which increases efficiency, decreases costs, and improves product quality. Artificial Neural Networks (ANNs) and the Internet of Things (IoT) have greatly improved APC in manufacturing. It examines how APC systems may include ANNs and IoT devices in industrial processes. By connecting to a wide range of sensors placed strategically throughout a production facility, IoT devices may gather data in real time, allowing for managing and monitoring crucial parameters. To APC systems, ANNs are invaluable for predictive modeling and control due to their adaptability to changing process conditions and capacity to represent complicated nonlinear interactions. Manufacturers may gain better control over their operations, improving productivity and product quality, by using data from the IoT to train and update ANN models. Recent advances in APC using IoT devices and ANNs are reviewed in this study. Their applications in various industrial industries are discussed, and case examples are shown to demonstrate their usefulness. Further improvements in APC for manufacturing using IoT devices and ANNs may be guided by highlighting the field's problems and future research goals. Challenges with data security, integration challenges, and reliability impact the accuracy of predictive modeling, scalability, and performance of IoT systems.

关键词： Performance evaluation Adaptation models Process control Artificial neural networks Predictive models Real-time systems Manufacturing Sensors Internet of Things Monitoring

来源：评论

学校读者我要写书评

暂无评论

Parkinson’s Disease Detection using Hand Drawn Spirals and Waves

Parkinson’s Disease Detection using Hand Drawn Spirals and ...

引用

Recent Advances in Science and Engineering technology (ICRASET), International Conference on

作者： Shashidhara H S Saish K Kalbag Tanya Mathias Srinivasa K G Niranjanamurthy M Department of Informaition Science and Engineering M S Ramaiah Institute of Techology and Engineering Affiliated to Visvesvaraya Technological University Belgaum Bangalore India Department of Data Science and Artififial Intelligece International Institute of Information Technology Naya Raipur Chhattisgarh India Department of Artificial Intelligence and Machine Learning B M S Institute of Technology and Management Affiliated to Visvesvaraya Technological University Belgaum Bangalore India

Parkinson’s disease, a neurodegenerative disorder, affects millions of people worldwide. Early detection is critical for effective treatment and management. Early detection of Parkinson’s disease is challenging due to the lack of accessible and non-invasive screening methods. Current diagnostic techniques often require specialized equipment and invasive procedures, limiting their feasibility for widespread screening. There is a need for cost-effective and accessible approaches that can accurately detect early stages of Parkinson’s disease. The model requires a high degree of precision in distinguishing between these patterns, which is a significant challenge to overcome. In this research work, we proposed a novel approach for detecting early stages of Parkinson’s disease by analyzing hand-drawn spirals and waves in photographs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

learning Counterfactual Outcomes Under Rank Preservation

arXiv

引用

arXiv 2025年

作者： Wu, Peng Li, Haoxuan Zheng, Chunyuan Zeng, Yan Chen, Jiawei Liu, Yang Guo, Ruocheng Zhang, Kun School of Mathematics and Statistics Beijing Technology and Business University China Center for Data Science Peking University China School of Mathematical Sciences Peking University China College of Computer Science and Technology Zhejiang University China Computer Science and Engineering University of California Santa Cruz Bolivia ByteDance Research China Department of Philosophy Carnegie Mellon University United States Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Counterfactual inference aims to estimate the counterfactual outcome at the individual level given knowledge of an observed treatment and the factual outcome, with broad applications in fields such as epidemiology, econometrics, and management science. Previous methods rely on a known structural causal model (SCM) or assume the homogeneity of the exogenous variable and strict monotonicity between the outcome and exogenous variable. In this paper, we propose a principled approach for identifying and estimating the counterfactual outcome. We first introduce a simple and intuitive rank preservation assumption to identify the counterfactual outcome without relying on a known structural causal model. Building on this, we propose a novel ideal loss for theoretically unbiased learning of the counterfactual outcome and further develop a kernel-based estimator for its empirical estimation. Our theoretical analysis shows that the rank preservation assumption is not stronger than the homogeneity and strict monotonicity assumptions, and shows that the proposed ideal loss is convex, and the proposed estimator is unbiased. Extensive semi-synthetic and real-world experiments are conducted to demonstrate the effectiveness of the proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Innovative Healthcare Advancements: Harnessing Artificial and Human Intelligence for Bionic Solutions

Innovative Healthcare Advancements: Harnessing Artificial an...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Samruddhi Sapkal Sulaxan Jadhav P Mallikarjun Rejuwan Shamim Atowar Ul Islam Kalyan Bamane Artificial Intelligence and Machine Learning D Y Patil International University Akurdi Pune India D Y Patil International University Akurdi Pune India Department of Electrical and Electronic Engineering Malla Reddy Engineering College JNTUH Hyderabad School of data science Maharishi University of Information Technology Noida India Department of Computer Science and Electronics University of Science and Technology Meghalaya Ri-Bhoi Techno city Kiling Road Baridua Meghalaya Department of Information Technology D Y Patil College of Engineering Akurdi Pune

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

According to initial data, individuals who have been diagnosed with type 2 diabetes (T2DM) appear to be at a more chances of evolving breast cancer compared to those who have not received a T2DM diagnosis. The primary goal of the research was to estimate the efficacy of three dissimilar methods in forecasting the probability of breast cancer in T2DM patients with diverse attributes. To achieve this objective, a danger expectation model was created for breast cancer in individuals with T2DM using the primary *** ensure a comprehensive analysis, we also gathered information on potential factors that may predict the growth of breast cancer. As the population sample size was restricted, we utilized Synthetic Minority Oversampling technology to amplify the quantity of accessible data. Random assignment of data points to training or test sets was conducted at a ratio of roughly 39 to 1. Three distinct models, specifically Artificial Neural Network (ANN), Logistic Regression (LR), and Random Forest (RF), were assessed for effectiveness using a range of performance criteria, including as $F 1$ score, area under the receiver operation characteristic curves, recalled, and correctness. (AUC). AUC values for these models were as follows: LR had an AUC of 0.834, ANN had an AUC of 0.865, and RF had an AUC of 0.959, with RF having the greatest AUC. According to our study, the Random Forest model outperformed the LR and ANN models in correctly estimating the incidence of breast cancer in people with T2DM.

关键词： Radio frequency Training Technological innovation Biological system modeling Artificial neural networks Receivers Predictive models

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：