检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Artificial Intelligence Research Center AIST Tokyo Japan Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Innovation Technology Office Research Center PASCO Corporation Tokyo Japan Department of Computer Science Tokyo Institute of Technology Tokyo Japan

3D point clouds are discrete samples of continuous surfaces which can be used for various applications. However, the lack of true connectivity information, i.e., edge information, makes point cloud recognition challenging. Recent edge-aware methods incorporate edge modeling into network designs to better describe local structures. Although these methods show that incorporating edge information is beneficial, how edge information helps remains unclear, making it difficult for users to analyze its usefulness. To shed light on this issue, in this study, we propose a new algorithm called Diffusion Unit (DU) that handles edge information in a principled and interpretable manner while providing decent improvement. First, we theoretically show that DU learns to perform task-beneficial edge enhancement and suppression. Second, we experimentally observe and verify the edge enhancement and suppression behavior. Third, we empirically demonstrate that this behavior contributes to performance improvement. Extensive experiments and analyses performed on challenging benchmarks verify the effectiveness of DU. Specifically, our method achieves state-of-the-art performance in object part segmentation using ShapeNet part and scene segmentation using S3DIS. Our source code is available at https://***/martianxiu/DiffusionUnit. © 2022, CC BY.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Gender Prediction from Direct Pelvic Radiographs Using Efficientnet Deep Learning Model

SSRN

引用

SSRN 2024年

作者： Secgin, Yusuf Toy, Seyma Çakmak, Muhammet Oner, Zulal Ciftci, Rukiye Oner, Serkan Karabük University Faculty of Medicine Department of Anatomy Karabük Turkey Sinop University Faculty of Engineering and Architecture Department of Computer Engineering Sinop Turkey İzmir Bakırçay University Faculty of Medicine Department of Anatomy İzmir Turkey Gaziantep Islamic University of Science and Technology Department of Anatomy Gaziantep Turkey İzmir Bakırçay University Faculty of Medicine Department of Radiology İzmir Turkey

Objectives: EfficientNet is an up-to-date deep learning (DL) architecture and an important computer-based algorithm for forensic and basic medical sciences. The aim of this study is to perform highly accurate and precise gender estimation with images obtained from direct pelvic radiographs (X-Ray) using the EfficientNet deep learning *** and Methods: The study was performed using pelvis X-Ray images of 423 individuals aged 18-65 years. For the reliability of the DL architecture, data augmentation was applied to the images and the data set was increased to 1400. EfficientNet V2 B0 architecture was applied to the increased data set. The performance of the architecture was also compared using NASNet Mobile and ResNet152 rooted ***: As a result of the study, a gender prediction rate of 99.29% was obtained with the EfficientNet architecture, 97.86% with the NASNet Mobile architecture and 95.71% with the ResNet152 ***: As a result of the study, EfficientNet V2 B0, NASNet Mobile and ResNet152 DL architectures showed high accuracy and reliability in terms of gender estimation. In this respect, we believe that this study will guide forensic and basic medical sciences. © 2024, The Authors. All rights reserved.

关键词： X ray radiography

来源：评论

学校读者我要写书评

暂无评论

The New Concept of Guaranteeing Confidence in the E-Voting System

The New Concept of Guaranteeing Confidence in the E-Voting S...

引用

2020 IEEE International Conference on Problems of Infocommunications Science and technology, PIC S and T 2020

作者： Khlaponin, Yurii Vyshniakov, Volodymyr Prygara, Mykhailo Poltorak, Vadym Kyiv National University of Construction and Architecture Cybersecurity and Computer Engineering Department Kyiv Ukraine National University Machine Industry Technology Department Uzhhorod Uzhhorod Ukraine National Technical University of Ukraine 'Igor Sikorsky Kyiv Polytechnic Institute' Department of Technical Systems Automation and Control Kyiv Ukraine

ISBN: (纸本)9781728191775

There is no doubt about the urgency of ensuring trust in e-voting systems since elections without trust cannot be acceptable in a democratic society. To solve this problem, it was proposed to use blockchain technology, however, in voting systems this leads to significant delays in the execution of transactions, and the software solution is accessible only to a narrow circle of specialists, which clearly does not help to show confidence on the part of voters. This paper proposes a different approach, which is based on the widely available verification of all means and processes that may cause distrust in the accuracy of the vote count or in ensuring their confidentiality. We offer a solution to the problem of transparency of all hardware and software that cause distrust. Voting systems that use this approach are implemented in three leading Ukrainian universities for student elections to self-government bodies. The conceptual model of the e-voting system for state elections on the example of Ukraine is presented. Links to Internet resources are provided where you can not only get acquainted with the principles of building the system, but also conduct an experimental vote in Ukrainian, English or Russian. You can also copy and test e-voting server software on your computers. © 2020 IEEE.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Tropes in films: An initial analysis

arXiv

引用

arXiv 2020年

作者： García-Ortega, Rubén Héctor García-Sánchez, Pablo Merelo-Guervós, Juan Julián Department of Computer Architecture and Technology University of Granada Department of Languages and Computer Systems University of Granada Department of Computer Architecture and Technology University of Granada

TVTropes is a wiki that describes tropes and which ones are used in which artistic work. We are mostly interested in films, so after releasing the TropeScraper Python module that extracts data from this site, in this report we use scraped information to describe statistically how tropes and films are related to each other and how these relations evolve in time. In order to do so, we generated a dataset through the tool TropeScraper in April 2020. We have compared it to the latest snapshot of DB Tropes, a dataset covering the same site and published in July 2016, providing descriptive analysis, studying the fundamental differences and addressing the evolution of the wiki in terms of the number of tropes, the number of films and connections. The results show that the number of tropes and films doubled their value and quadrupled their relations, and films are, at large, better described in terms of tropes. However, while the types of films with the most tropes has not changed significantly in years, the list of most popular tropes has. This outcome can help on shedding some light on how popular tropes evolve, which ones become more popular or fade away, and in general how a set of tropes represents a film and might be a key to its success. The dataset generated, the information extracted, and the summaries provided are useful resources for any research involving films and tropes. They can provide proper context and explanations about the behaviour of models built on top of the dataset, including the generation of new content or its use in machine learning. © 2020, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Programming-Based Optimal Charging Scheduling for Electric Vehicles

Dynamic Programming-Based Optimal Charging Scheduling for El...

引用

IEEE International Conference on Intelligent Transportation Engineering (ICITE)

作者： Kuan Li Ying Zhang Chenglie Du Tao You Lu Bai Jiaming Wu School of Software Northwestern Polytechnical University Xi’an China School of Computer Science Northwestern Polytechnical University Xi’an China Department of Architecture and Civil Engineering Chalmers University of Technology Gothenburg Sweden

The charging scheduling of electric vehicles not only affects the operation of the grid system, but also affects the charging cost of vehicle users. This paper studies the charging scheduling problem of electric vehicles from the user’s perspective by considering the grid’s as well as the user’s needs. On the basis of real-time electricity prices, an electric vehicle charging scheduling system aiming at the lowest charging cost is designed and an optimal charging scheduling method based on dynamic programming is established. In order to reduce the unnecessary computational expenses, this paper optimizes the dynamic programming algorithm, and defines the state transition limit of the dynamic programming search space according to the actual constraints, which reduces the computational complexity. The simulation results show that, on the premise of satisfying the power constraints and user charging demands, the electric vehicles charging scheduling system can effectively reduce the charging cost and time. In addition, the charging process has little impact on the power system from the perspective of grid fluctuation.

关键词： Fuzzy logic Vehicle-to-grid Costs Fluctuations Processor scheduling Simulation Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

Grain Size Distribution Analysis of Landslide Dams Caused by Dynamic Accumulation of Weathered Rock Landslides Using Discrete Element Modelling 29th

Grain Size Distribution Analysis of Landslide Dams Caused by...

引用

29th International Conference on Computational and Experimental Engineering and Sciences, ICCES 2023

作者： Peng, Ming Zhao, Qingxi Shen, Danyi Zhu, Yan Zhao, Qingxin Zhou, Jiawen Cai, Shuo Key Laboratory of Geotechnical & Underground Engineering of Ministry of Education Tongji University Shanghai China Department of Geotechnical Engineering College of Civil Engineering Tongji University Shanghai China Institute of Geotechnical Engineering College of Civil Engineering and Architecture Zhejiang University Hangzhou China Shanghai Research Center of Ocean & Shipbuilding Engineering China Shipbuilding NDRI Engineering Co. Ltd. Shanghai China State Key Laboratory Hydraulic & Mountain River Engineering Sichuan University Chengdu China School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China

ISBN: (纸本)9783031425141

The differences in the structure and composition materials of landslide dams often lead to great dissimilarity in dam stability, which often depend on the dynamic accumulation process of landslide dam. In order to investigate the response of dynamic characteristics of landslide to the composition material distribution of landslide dams, the migration and accumulation process of rock slopes with two weathering degrees was simulated by bonded particles and micro-cracks based on discrete element modelling. A new reconstructed distribution identification method was proposed in this paper to quantify the grain size distribution of dam. The results showed that the composition materials of dam, formed by weakly weathered slope, was poorly sorted, with medium particles located in surface layer, coarse particles located in middle and fine particles located in bottom of the valley. The material composition of dam, formed by strongly weathered slope, was well sorted, which spatial distribution showed well reverse segregation structure. It was found that the differences in particle size distribution between two kinds of landslide dams were mainly manifested in fine particles and coarse particles. The kinetic disintegration in weakly weathered slope was weakened, due to the accumulation of force coupling below hard rock at substrate, which occurred because of the fragmentation of particles aside it. As a result, there are more coarse particles and fewer fine particles in grain size distribution of its accumulation dam. This paper contributes to a better understanding of the structure and materials distribution of landslide dams, and assists the prediction of the stability of landslide dams. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Particle size

来源：评论

学校读者我要写书评

暂无评论

The FaceChannel: A Fast and Furious Deep Neural Network for Facial Expression Recognition

引用

SN computer Science 2020年第6期1卷 321页

作者： Barros, Pablo Churamani, Nikhil Sciutti, Alessandra Cognitive Architecture for Collaborative Technologies Unit Istituto Italiano di Tecnologia Genoa Italy Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom

Current state-of-the-art models for automatic facial expression recognition (FER) are based on very deep neural networks that are effective but rather expensive to train. Given the dynamic conditions of FER, this characteristic hinders such models of been used as a general affect recognition. In this paper, we address this problem by formalizing the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks. We introduce an inhibitory layer that helps to shape the learning of facial features in the last layer of the network and, thus, improving performance while reducing the number of trainable parameters. To evaluate our model, we perform a series of experiments on different benchmark datasets and demonstrate how the FaceChannel achieves a comparable, if not better, performance to the current state-of-the-art in FER. Our experiments include cross-dataset analysis, to estimate how our model behaves on different affective recognition conditions. We conclude our paper with an analysis of how FaceChannel learns and adapts the learned facial features towards the different datasets. © 2020, The Author(s).

关键词： Affective computing Convolutional neural network Facial expression recognition

来源：评论

学校读者我要写书评

暂无评论

Agent-Based Modeling for Identifying Water Conflicts in Farmer Water User Organizations: A Socio-Hydrological Approach 24

Agent-Based Modeling for Identifying Water Conflicts in Farm...

引用

27th ACM Conference on computer-Supported Cooperative Work and Social Computing, CSCW Companion 2024

作者： Lillo Saavedra, Mario Velásquez, Pablo Salgado, Marcela García-Pedrero, Ángel Gonzalo-Martín, Consuelo Boumahdi, Meryeme Somos-Valenzuela, Marcelo Rivera, Diego Cisterna, Valentina Facultad Ingeniería Agrícola Universidad de Concepción Chillan Chile Facultad Ciencias Ambientales Universidad de Concepción Concepción Chile Department of Computer Architecture and Technology Universidad Politécnica de Madrid Madrid Spain Faculty of Agriculture and Environmental Sciences Universidad Politécnica de Madrid Madrid Spain Faculty of Agriculture and Environmental University of La Frontera Temuco Chile Engineering Faculty Universidad del Desarrollo Santiago Chile Facultad de Arquitectura Urbanismo y Geografía Universidad de Concepción Concepción Chile

ISBN: (纸本)9798400711145

Water conflicts in agricultural watersheds pose significant challenges for effective resource management. This study presents a novel approach to identifying potential water conflicts within water user organizations by integrating socio-hydrological data into an agent-based modeling tool, SHABM (Socio-Hydrological Agent-Based Model). The model simulates interactions between the Water Board, Canal Administrator, Farmers, and Crops, considering water distribution rates, crop water demands, farmer personalities, and irrigation infrastructure, among others. The study area is located in the Longaví River basin, Chile, and simulations were conducted from 2017 to 2022, considering various scenarios of canal lining and oversight levels. Results demonstrate the tool's ability to identify potential conflict areas and provide insights into the evolution of farmer decision-making. Integrating geospatial data, hydrological models, and social information proves crucial for achieving comprehensive water management and addressing complex water-related challenges in agricultural contexts. The SHABM tool has the potential to support decision-making processes and promote sustainable water governance in regions facing water scarcity and competing demands. © 2024 ACM.

关键词： Canal linings

来源：评论

学校读者我要写书评

暂无评论

RumorLens: Interactive Analysis and Validation of Suspected Rumors on Social Media

arXiv

引用

arXiv 2022年

作者： Wang, Ran Zhao, Yifei Wang, Shipan Du, Kehan Tang, Mojie Li, Yiyao Chen, Qianhe Tao, Hongxi Wang, Yong School of Journalism and Information Communication Huazhong University of Science and Technology China School of Artificial Intelligence and Automation Huazhong University of Science and Technology China School of Computer Science United Kingdom University of Bristol United Kingdom School of Architecture and Urban Planning Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China Computer Science Department University College London United Kingdom School of Computing and Information Systems Singapore Management University Singapore

With the development of social media, various rumors can be easily spread on the Internet and such rumors can have serious negative effects on society. Thus, it has become a critical task for social media platforms to deal with suspected rumors. However, due to the lack of effective tools, it is often difficult for platform administrators to analyze and validate rumors from a large volume of information on a social media platform efficiently. We have worked closely with social media platform administrators for four months to summarize their requirements of identifying and analyzing rumors, and further proposed an interactive visual analytics system, RumorLens, to help them deal with the rumor efficiently and gain an in-depth understanding of the patterns of rumor spreading. RumorLens integrates natural language processing (NLP) and other data processing techniques with visualization techniques to facilitate interactive analysis and validation of suspected rumors. We propose well-coordinated visualizations to provide users with three levels of details of suspected rumors: an overview displays both spatial distribution and temporal evolution of suspected rumors;a projection view leverages a metaphor-based glyph to represent each suspected rumor and further enable users to gain a quick understanding of their overall characteristics and similarity with each other;a propagation view visualizes the dynamic spreading details of a suspected rumor with a novel circular visualization design, and facilitates interactive analysis and validation of rumors in a compact manner. By using a real-world dataset collected from Sina Weibo, one case study with a domain expert is conducted to evaluate RumorLens. The results demonstrated the usefulness and effectiveness of our approach. Copyright © 2022, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Design of Subsea storage tanks for Arctic conditions - heat treatment of materials

引用

Materials Today: Proceedings 2023年

作者： Kishor Tirumanur Shanmugavelu, Arvind Muraliraja, R. Shanmugam, Ragavanantham Pal Singh Pawar, Mayur Vishwakarma, Rajoo Sarkar, Proshanta Department of Naval Architecture and Offshore Engineering Vels Institute of Science Technology & Advanced Studies Chennai 600117 Tamil Nadu India Department of Mechanical Engineering Vels Institute of Science Technology & Advanced Studies Chennai 600117 Tamil Nadu India Advanced Manufacturing Engineering Technology Navajo Technical University NM 87313 United States Department of Civil Engineering IES College of Technology Bhopal 462044 Madhya Pradesh India Department of Mechanical Engineering Suyash Institute of Information Technology Gorakhpur 273016 Uttar Pradesh India Department of Computer Science Kalinga University Naya Raipur 492101 Chhattisgarh India

The Arctic region contains a plethora of recoverable hydrocarbon wealth in the form of oil and gas in existing conventional wells and other undiscovered fields. The main challenges faced in the Arctic region are both environmental and operational. Some environmental challenges are low ambient temperature, winterization, severity and unpredictability of the weather. However, the issue of multi-phase flow in the current operation coupled with the decline of the reservoir pressure are the major concerns in this gas field. In the early stages of field life, the reservoir pressure is sufficient to allow the natural flow from reservoir formation to surface without additional supporting compression. Unfortunately, the pressure naturally declines throughout the entire life cycle of the field. To achieve a better production profile in the arctic region the idea is to implement a Subsea processing concept employing a Subsea Storage Tank (SST) in order to maximize production from additional infield wells, introducing a novel step in this field development phase that will change the entire oil and gas industry especially for subsea processing field architecture. The incorporation of SST in the subsea system will enhance the production rate as well as it avoids the transportation problems through pipe lines. By this work, the production rate is increased by 50% and decrease the oil spill accidents considerably. © 2023 Elsevier Ltd. All rights reserved.

关键词： Heat transfer

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：