检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hou, Yunlong Tan, Vincent Y.F. Zhong, Zixin Department of Mathematics National University of Singapore Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore Singapore Data Science and Analytics Thrust Hong Kong University of Science and Technology Guangzhou China

We propose a novel piecewise stationary linear bandit (PSLB) model, where the environment randomly samples a context from an unknown probability distribution at each changepoint, and the quality of an arm is measured by its return averaged over all contexts. The contexts and their distribution, as well as the changepoints are unknown to the agent. We design Piecewise-Stationary Ε-Best Arm Identification+ (PSΕBAI+), an algorithm that is guaranteed to identify an Ε-optimal arm with probability ≥ 1 − δ and with a minimal number of samples. PSΕBAI+ consists of two subroutines, PSΕBAI and NAÏVE Ε-BAI (NΕBAI), which are executed in parallel. PSΕBAI actively detects changepoints and aligns contexts to facilitate the arm identification process. When PSΕBAI and NΕBAI are utilized judiciously in parallel, PSΕBAI+ is shown to have a finite expected sample complexity. By proving a lower bound, we show the expected sample complexity of PSΕBAI+ is optimal up to a logarithmic factor. We compare PSΕBAI+ to baseline algorithms using numerical experiments which demonstrate its efficiency. Both our analytical and numerical results corroborate that the efficacy of PSΕBAI+ is due to the delicate change detection and context alignment procedures embedded in PSΕBAI. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ambiguous Edge Detection Method for Computed Tomography Scans of Coronavirus Disease 2019 Cases

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2024年第1期54卷 352-364页

作者： Singh, Pritpal Huang, Yo-Ping Central University of Rajasthan Quantum Optimization Research Lab Department of Data Science and Analytics Ajmer305817 India Department of Electrical Engineering National Penghu University of Science and Technology Magong88046 Taiwan The Department of Electrical Engineering National Taipei University of Technology Taipei10608 Taiwan The Department of Computer Science and Information Engineering National Taipei University New Taipei City23741 Taiwan The Department of Information and Communication Engineering Chaoyang University of Technology Taichung41349 Taiwan

Recently, the coronavirus disease of 2019 (COVID-19), as named by the World Health Organization (WHO), has spread to over 200 countries. The WHO has declared this disease as a worldwide public health emergency. One of the most difficult tasks in combating this epidemic is to identify and segregate the afflicted people. The reverse transcription-polymerase chain reaction test (RT-PCR) is the most common pathology test used to diagnose this infection. Studies show that the RT-PCR test has a low-positive rate and sometimes becomes ineffective in diagnosing infection. In some cases, computed tomography (CT) scans reveal acute pneumonia and pulmonary anomalies. Therefore, CT scans are used together with RT-PCR tests to confirm infected people. Existing artificial intelligence and machine learning techniques require a large number of CT scans for training, which is a time-consuming process. Visual inspection shows that most CT scans of COVID-19 cases have broken, blurred, and ambiguous edges for infectious areas. Another major issue with these images is the heterogeneous intensity of the pixels, high noise, and low resolution. As a result of all these issues, the problem of effective edges/boundaries of various areas of CT scans of COVID-19 cases cannot be resolved by the current edge detection approach. Indeed, improper selection of edges can lead to an incorrect diagnosis of diseases through CT scans of COVID-19 cases. Therefore, there is an urgent need for a diagnostic method in addition to the RT-PCR test that can extract useful information from the minimum number of chest CT scans of suspected COVID-19 cases. This study introduces a new ambiguous edge detection method (AEDM) for identifying the edges/boundaries of different regions in CT scans of COVID-19 cases. The proposed AEDM is developed on the basis of ambiguous set (AS) theory, which is highly efficient in processing ambiguous pixel information. For simulation purposes, various CT scans of COVID-19 cases are c

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Detection of Plant Disease Using Machine Learning and Deep Learning Algorithms 8

Detection of Plant Disease Using Machine Learning and Deep L...

引用

8th IEEE International Conference on Science, Technology, engineering and Mathematics, ICONSTEM 2023

作者： Gollapudi, Kalyani Varigonda, Preethi Jancy, S. Pushpalatha, S. Marya, Viji Amutha Helen, Suji Sathyabama Institute of Science and Technology Computer Science and Engineering Chennai India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India Saveetha School of Engineering Simats Department of Data Analytics Chennai602105 India

ISBN: (纸本)9798350347791

Agriculture performs an critical position in India's economic system. Early detection of plant illnesses is critical to save you crop damage and similarly spread of diseases. Most plants, along with apple, tomato, cherry, grape, show symptoms of leaf ailment. These visible patterns may be found to correctly predict the disorder and take early movement to save you it. This can be triumph over with system getting to know and deep getting to know algorithms. We therefore recommend a method that determines tomato plant disease from pix of leaves. This method is performed with aid vector device (SVM), random woodland gadget studying algorithm, and look at algorithms Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and ResNet that is one of the switch learning techniques. Snoring. After the facts set is processed by way of the algorithms, the accuracy of the algorithms is compared and the snapshots are categorized. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed Bilevel Optimization with Communication Compression 41

Distributed Bilevel Optimization with Communication Compress...

引用

41st International Conference on Machine Learning, ICML 2024

作者： He, Yutong Hu, Jie Huang, Xinmeng Lu, Songtao Wang, Bin Yuan, Kun Peking University China University of Pennsylvania United States IBM Research United States Zhejiang University China National Engineering Labratory for Big Data Analytics and Applications China AI for Science Institute Beijing China

Stochastic bilevel optimization tackles challenges involving nested optimization structures. Its fast-growing scale nowadays necessitates efficient distributed algorithms. In conventional distributed bilevel methods, each worker must transmit full-dimensional stochastic gradients to the server every iteration, leading to significant communication overhead and thus hindering efficiency and scalability. To resolve this issue, we introduce the first family of distributed bilevel algorithms with communication compression. The primary challenge in algorithmic development is mitigating bias in hypergradient estimation caused by the nested structure. We first propose C-SOBA, a simple yet effective approach with unbiased compression and provable linear speedup convergence. However, it relies on strong assumptions on bounded gradients. To address this limitation, we explore the use of moving average, error feedback, and multi-step compression in bilevel optimization, resulting in a series of advanced algorithms with relaxed assumptions and improved convergence properties. Numerical experiments show that our compressed bilevel algorithms can achieve 10× reduction in communication overhead without severe performance degradation. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Graphene-and Multi-Walled Carbon Nanotubes-Coated Tapered Plastic Optical Fiber for Detection of Lard Adulteration in Olive Oil

引用

Photonic Sensors 2022年第4期12卷 1-10页

作者： Ika PUSPITA Ninik IRAWATI Kartika Anoraga MADURANI Fredy KURNIAWAN Sekartedjo KOENTJORO Agus Muhamad HATTA Department of Engineering Physics Faculty of Industrial Technology and System EngineeringInstitut Teknologi Sepuluh NopemberSurabaya 60111Indonesia Department of Physics National Taiwan UniversityTaipei 10617China Department of Chemistry Faculty of Science and Data AnalyticsInstitut Teknologi Sepuluh NopemberSurabaya 60111Indonesia

A rapid and high-performance sensor for lard adulterant in edible oil was developed using the tapered plastic optical fiber(POF)coated with graphene and multi-walled carbon *** coating material was deposited onto a tapered POF with a taper waist diameter and a taper length of 0.45 mm and 1 cm,*** addition of the coating material was used to increase the sensitivity and selectivity coefficient of the tapered POF toward the lard *** sensing mechanism is based on a simultaneous interaction of lard substance and an evanescent wave of tapered POF with the coating *** results showed that graphene coating on the tapered POF increased the selectivity coefficient of the tapered POF towards lard substance from 33.54 to 324.19,and it gave a sensitivity of 0.427 dBm/%.In comparison,multi-walled carbon nanotubes coating increased the selectivity coefficient to 71.65 and increased its sensitivity to 1.189 dBm/%.Thus,the proposed configuration of the tapered POF with the coating material offered a simple configuration for a rapid,high sensitivity and selectivity detection of lard adulterant in edible oils.

关键词： Lard adulteration tapered optical fiber sensor graphene carbon nanotubes food safety

来源：评论

学校读者我要写书评

暂无评论

The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited

arXiv

引用

arXiv 2024年

作者： Tori, Floriano Holst, Vincent Ginis, Vincent Data Analytics Laboratory Vrije Universiteit Brussel Brussel Belgium Data Analytics Laboratory & Applied Physics Vrije Universiteit Brussel School of Engineering and Applied Sciences Harvard University Brussel Belgium

Message passing is the dominant paradigm in Graph Neural Networks (GNNs). The efficiency of it, however, can be limited by the topology of the graph. This happens when information is lost during propagation due to being oversquashed when travelling through bottlenecks. To remedy this, recent efforts have focused on graph rewiring techniques, which disconnect the input graph originating from the data and the computational graph, on which message passing is performed. A prominent approach for this is to use discrete graph curvature measures, of which several variants have been proposed, to identify and rewire around bottlenecks, facilitating information propagation. While oversquashing has been demonstrated in synthetic datasets, in this work we reevaluate the performance gains that curvature-based rewiring brings to real-world datasets. We show that in these datasets, edges selected during the rewiring process are not in line with theoretical criteria identifying bottlenecks. This implies they do not necessarily oversquash information during message passing. Subsequently, we demonstrate that SOTA accuracies on these datasets are outliers originating from sweeps of hyperparameters—both the ones for training and dedicated ones related to the rewiring algorithm—instead of consistent performance gains. In conclusion, our analysis nuances the effectiveness of curvature-based rewiring in real-world datasets and brings a new perspective on the methods to evaluate GNN improvements. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Digital Process Passport: A Conceptual Model for Information Collection and Sharing In Sustainable Manufacturing 57

Digital Process Passport: A Conceptual Model for Information...

引用

18th IFAC Workshop on Time Delay Systems, TDS 2024

作者： Glišic, Marija Møller, Charles Veluri, Badrinath Ramanujan, Devarajan Grundfos A/S Poul Due Jensens Vej Bjerringbro8850 Denmark Department of Mechanical and Production Engineering Aarhus University 89G-F Katrinebjergvej Aarhus N8200 Denmark DIGIT Centre Big Data and Data Analytics Finlandsgade 22 Aarhus N8200 Denmark

The transition towards smart manufacturing, aided by the concepts of Industry 4.0 and Industry 5.0, is enabling manufacturers to gather extensive amounts of data from machinery, systems, and operations. Access to manufacturing data can improve information flow and data sharing, enabling the possibility of reducing costs, saving material, and improving process and quality of production, while leading to fewer wastes and emissions. Typically, manufacturing information is spread across multiple enterprise information technology systems, and structured based on traditional product development paradigms (e.g., product design, process planning, manufacturing execution, quality control, etc.). However, realizing sustainable manufacturing requires integrating this information into a unified frame allowing for quantifying and subsequently mitigating the environmental impacts of production systems. Furthermore, the growing focus on standards-based reporting of product environmental footprints, e.g., through the European Union's Digital Product Passport (DPP) regulation, necessitates that manufacturers and their value chains share verifiable information on environmental impacts. Given that the structure and use cases for DPPs are still evolving, there is a need for manufacturing value chains to investigate, what manufacturing information needs to be collected, how to conduct information collection in complex manufacturing systems, what the needed level of granularity, and how to ensure the needed level of accuracy and verifiability. To support these goals, our work proposes a conceptual model for information collection and sharing in sustainable manufacturing titled Digital Process Passport. The goal of a Digital Process Passport is to enable systematic estimation, monitoring, sharing, and mitigating manufacturing-related environmental impacts, by providing a common template for representing circularity- and sustainability-focused information of production systems. © 2024 The

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Membership Functions, Set-Theoretic Operations, Distance Measurement Methods Based on Ambiguous Set Theory: A Solution to a Decision-Making Problem in Selecting the Appropriate Colleges

引用

International Journal of Fuzzy Systems 2023年第4期25卷 1311-1326页

作者： Singh, Pritpal Huang, Yo-Ping Deep Learning Lab Department of Data Science and Analytics Central University of Rajasthan Rajasthan Ajmer305817 India Department of Electrical Engineering National Penghu University of Science and Technology Penghu88046 Taiwan Department of Electrical Engineering National Taipei University of Technology Taipei10608 Taiwan Department of Information and Communication Engineering Chaoyang University of Technology Taichung41349 Taiwan

To deal with uncertainty in a very precise way, the ambiguous set theory has been proposed. This theory supports the representation of ambiguities in terms of four membership degrees, namely "true," "false," "true-ambiguous," and "false-ambiguous." These membership degrees are linearly dependent on each other, because they are defined over the same event. However, these four membership degrees have the difficulty of unclear margins that prevent them to be separated from each other in the ambiguities representation of an event. To address this problem of unclear margins in the ambiguous set, the membership degrees are defined using four different functions, and called ambiguous membership functions (AMFs). These membership degrees are defined in such a way that their sum should be less than or equal to 2, and the individual membership degree should be in the range [0, 1]. To visually represent the uncertain margins for the membership degrees, the concept of an ambiguous region (AR) is introduced. In this study, various set-theoretic operations, their properties, and methods for measuring distances in support of the ambiguous sets are discussed. Finally, we discuss a real-time application of the ambiguous set theory with respect to solving the decision-making problem of choosing the appropriate colleges for students. © 2023, The Author(s) under exclusive licence to Taiwan Fuzzy Systems Association.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Wearable Ultrasound devices for continuous health monitoring: Current and future Prospects 8

Wearable Ultrasound devices for continuous health monitoring...

引用

8th IEEE International Energy Conference, ENERGYCON 2024

作者： Ottakath, Najmath Al-Maadeed, Somaya Bouridane, Ahmed Chowdhury, Muhammad E.H. Sadasivuni, Kishor Kumar Department of Computer Science and Engineering Qatar University Doha Qatar Center of Data Analytics and Cybersecurity University of Sharjah Sharjah United Arab Emirates Department of Electrical Engineering Qatar University Doha Qatar Center for Advanced Materials Qatar University Doha Qatar

ISBN: (纸本)9798350382150

Advancements in wearable electronics and portable sensors have enabled long-term and real-time health monitoring. Among these advancements, wearable ultrasound devices have garnered attention due to their portability, ease of use, and ability to penetrate deep tissues in the human body. The images generated by these devices can be harnessed for computer vision tasks, providing valuable insights into an individual’s health status even during physical activity. This paper explores the design of such wearable ultrasound imagers, surveys their current applications, and offers insights into future prospects, including visual image processing and real-time analysis. The study also addresses the challenges of using wearable ultrasound for long-term health monitoring, emphasizing the need for ongoing innovation and research. ©2024 IEEE.

关键词： Ultrasonics

来源：评论

学校读者我要写书评

暂无评论

An Empirical Benchmark for Resource Use in Fused Deposition Modelling 3D Printing of Isovolumetric Mechanical Components 29

An Empirical Benchmark for Resource Use in Fused Deposition ...

引用

29th CIRP Conference on Life Cycle engineering, LCE 2022

作者： Szemeti, Gergo Ramanujan, Devarajan Department of Mechanical and Production Engineering Aarhus University Aarhus8000 Denmark Center for Digitalisation Big Data and Data Analytics Affiliation Aarhus University Aarhus8000 Denmark

The lack of detailed process information such as part shape, process setups, and process efficiencies limit the accuracy of life cycle inventory models that are used for estimating environmental impacts of manufacturing processes. Such limitations are particularly true for processes such as additive manufacturing, where part shape significantly influences the resulting process characteristics. To address the above knowledge gap, this paper investigates the influence of part shape on process inventory of fused deposition modeling 3D printing. To this end, we experimentally measured the resource consumption for printing 68 different isovolumetric mechanical components with identical print settings. These results are presented in a structured form, titled "Resource Use for 3D Printing Isovolumetric Mechanical Components (r3DiM) Benchmark", that includes our experimental data, 3D model files, NC code used for printing the models, and layer-wise energy consumption of the heaters of the bed & extruder, material use, and other printing peripherals of each object. It is our hope that the r3DiM benchmark will serve as a reference of future researchers interested in creating shape-aware, predictive life cycle inventory models for fused deposition modeling 3D printing processes. The r3DiM benchmark can be accessed from the following url: https://***/r3DiMBenchmark. © 2022 Elsevier B.V.. All rights reserved.

关键词： Energy utilization

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：