检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Chen, Xinru Dong, Chengbo Ji, Jiaqi Cao, Juan Li, Xirong MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

The key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data, whilst specific to prevent false alarms on authentic images. Current research emphasizes the sensitivity, with the specificity overlooked. In this paper we address both aspects by multi-view feature learning and multi-scale supervision. By exploiting noise distribution and boundary artifact surrounding tampered regions, the former aims to learn semantic-agnostic and thus more generalizable features. The latter allows us to learn from authentic images which are nontrivial to be taken into account by current semantic segmentation network based methods. Our thoughts are realized by a new network which we term MVSS-Net. Extensive experiments on five benchmark sets justify the viability of MVSS-Net for both pixel-level and image-level manipulation detection. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Disentangled Representation Learning with Transmitted Information Bottleneck

arXiv

引用

arXiv 2023年

作者： Dang, Zhuohang Luo, Minnan Jia, Chengyou Dai, Guang Wang, Jihong Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi’an710049 China The SGIT AI Laboratory Xi’an710048 China The State Grid Shaanxi Electric Power Company Ltd. State Grid Corporation of China Xi’an710048 China The School of Information Science and Technology University of Science and Technology of China Hefei230026 China Abu Dhabi United Arab Emirates Baidu Inc Beijing100085 China

Encoding only the task-related information from the raw data, i.e., disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the information in representations with information theory, two major challenges remain: 1) the representation compression inevitably leads to performance drop;2) the disentanglement constraints on representations are in complicated optimization. To these issues, we introduce Bayesian networks with transmitted information to formulate the interaction among input and representations during disentanglement. Building upon this framework, we propose DisTIB (Transmitted Information Bottleneck for Disentangled representation learning), a novel objective that navigates the balance between information compression and preservation. We employ variational inference to derive a tractable estimation for DisTIB. This estimation can be simply optimized via standard gradient descent with a reparameterization trick. Moreover, we theoretically prove that DisTIB can achieve optimal disentanglement, underscoring its superior efficacy. To solidify our claims, we conduct extensive experiments on various downstream tasks to demonstrate the appealing efficacy of DisTIB and validate our theoretical analyses. Copyright © 2023, The Authors. All rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Image Manipulation Detection by Multi-View Multi-Scale Supervision

Image Manipulation Detection by Multi-View Multi-Scale Super...

引用

International Conference on Computer Vision (ICCV)

作者： Xinru Chen Chengbo Dong Jiaqi Ji Juan Cao Xirong Li MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

ISBN: (纸本)9781665428132

关键词： Representation learning Image segmentation Computer vision Sensitivity Costs Image edge detection Semantics

来源：评论

学校读者我要写书评

暂无评论

Study of Low-Cost-Based Smart Home Control Using IoT Powered by Photovoltaic Cells 1

引用

16th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of Information Technology, Applications and Tools, FITAT 2020

作者： Ahmad, Shoaib Chang, Kuo-Chi Sung, Tien-Wen Chu, Kai-Chun Zhou, Yu-Wen Omer, Abdalaziz Altayeb Ibrahim Amesimenu, Governor David Kwabena Chang, Fu-Hsiang Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China School of Information Science and Engineering Fujian University of Technology Fuzhou China Department of Business Management Fujian University of Technology Fuzhou China College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Kota Kinabalu Sabah Malaysia Department of Tourism Shih-Hsin University Taipei Taiwan

ISBN: (数字)9789813364202

ISBN: (纸本)9789813364196

This research mainly uses the Wi-Fi module (ESP8266) microcontroller to implement the IoT-based smart home system. In this study of smart home system is able to power the circuit by the photovoltaic cell itself and then wirelessly switch to the required load. As technology is expanding every day, mobile, robotics, machines learning are advancing their technology then why our house is an exception. Today’s house moving slowly based on common/human input controlling to smart/IoT-enabled devices to be controlled remotely. Currently, use the existing smart home system technology that is limited to this device only. Because of this, IoT devices are now being applied in various fields, but unfortunately, low cost and simple IoT applications are still insufficient in smart home. However, this study is concerned with the Node MCU (ESP8266) microcontroller used to control the power switches remotely. The users can control witches using web application after authenticating based on low cost and simple IoT application systems;this study has important contributions to the development of smart homes with high price–performance ratio in future. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Unsupervised vehicle re-identification with progressive adaptation 29

Unsupervised vehicle re-identification with progressive adap...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Peng, Jinjia Wang, Yang Wang, Huibing Zhang, Zhao Fu, Xianping Wang, Meng College of Information and Science Technology Dalian Maritime University Liaoning Dalian China Pengcheng Laboratory Shenzhen Guangdong China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China

ISBN: (纸本)9780999241165

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes;worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as "pseudo target samples". These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Cascading Fault Prevention of Power Grid Based on key Power Generation Nodes 1

引用

作者： Chang, Kuo-Chi Luo, Jie Deng, Hui-Qiong Li, Qin-Bin Zheng, Rong-Jin Li, Pei-Qiang School of Information Science and Engineering Fujian University of Technology Fuzhou350108 China Fujian Provincial University Engineering Research Genter of Smart Grid Simulation Analysis and Integrated Control Fuzhou350108 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (数字)9789813364202

ISBN: (纸本)9789813364196

In the case of power grid cascading trip, this study puts forward a strategy to prevent cascading trip by changing the output of generator set. Firstly, according to the specific performance of the power grid under the cascade tripping, combined with the action behavior of the line current-type backup protection, and an expression equation for measuring the safety level index between the power grid and the cascading trip failure is given. Secondly, the vulnerable branch is found out through the safety level index, the output of the key power generation nodes on the branch is taken as the optimization variable, and the optimization model is established to improve the safety level index under the chain trip of the power grid. Finally, a combination of sensitivity analysis and particle swarm optimization(PSO) was used to analyze an example on the IEEE-39 node system. The results demonstrate the feasibility and effectiveness of the model and method, and provide a reference for preventing chain trip accidents. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

A Survey of Common IOT Communication Protocols and IOT Smart-X Applications of 5G Cellular 1

引用

作者： Chu, Kai-Chun Turatsinze, Elias Chang, Kuo-Chi Zhou, Yu-Wen Chang, Fu-Hsiang Wang, Ming-Tsung Department of Business Management Fujian University of Technology Fuzhou China School of Information and Engineering Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Tourism Shih-Hsin University Taipei Taiwan Institute of Communications Engineering National Yunlin University of Science and Technology Yunlin Taiwan College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (数字)9789813364202

ISBN: (纸本)9789813364196

New technologies and the potential development of Internet-connected devices have made the IoT one of the main concerns in the areas of computing. In this review paper, Bluetooth, Zigbee, Z-Wave, Wi-Fi, 5G cellular, NFC, and LoRaWAN were described. Furthermore, IOT applications like smart city, smart energy and grids, smart transport, smart buildings, smart home, smart industrial manufacturing, smart Health, and smart farming were also described. However, every communication technology has its own merits and demerits when we consider scalability, cost, and network requirements. The survey provided sufficient knowledge to select the best communication protocol suitable for the application based on network reliability, roaming capabilities, recovery mechanisms, and costs. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

Study of Assessing the Stability of Rwanda’s Power System from Big data Based on Power Generation 1

引用

作者： Shyirambere, Gilbert Chang, Kuo-Chi Chu, Kai-Chun Wang, Hsiao-Chuan Omer, AbdalazizAltayeb Ibrahim Amesimenu, Governor David Kwabena Chang, Fu-Hsiang Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China School of Information Science and Engineering Fujian University of Technology Fuzhou China Department of Business Management Fujian University of Technology Fuzhou China Institute of Environmental Engineering National Taiwan University Taipei Taiwan College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia Department of Tourism Shih-Hsin University Taipei Taiwan

ISBN: (数字)9789813364202

ISBN: (纸本)9789813364196

Rwanda has insufficient of electricity in which the electricity access among its citizens is at 53% equals to 224 MW of power generation. However, even among 53% of electrification, there are still some blackouts and erratic outages in cities during the night when many devices are connected on the system. This blackout and sudden shutdown could make the power system stability of Rwanda to be questionable and it can be so-called unstable. Meanwhile, the Rwanda Government is very ambitious targeting to achieve universal access by 2023/24 in which 52% will be on-grid connected and 48% off-grid. In this study, the current and proposed Rwanda power generation sector, transmission sector, and distribution sector are discussed;general Rwanda energy sources like, hydro, solar, diesel thermal, methane gas, peat are also discussed based on big data. In the end, conclusion and some recommendations have been proposed to be done in order to make stable the power system. For instance, Kalman-filtered solar forecasting approach could be used to predict weather condition every hour so that blackout coming from bad atmosphere could be prevented. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Outages

来源：评论

学校读者我要写书评

暂无评论

Optimal Power Generation Output Considering Cascading Failure 1

引用

作者： Deng, Hui-Qiong Luo, Jie Li, Qin-Bin Zheng, Rong-Jin Li, Pei-Qiang Chang, Kuo-Chi School of Information Science and Engineering Fujian University of Technology Fuzhou350108 China Fujian Provincial University Engineering Research Genter of Smart Grid Simulation Analysis and Integrated Control Fuzhou350108 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (数字)9789813364202

ISBN: (纸本)9789813364196

Aiming at the cascading fault phenomenon of power system, this paper analyzes the disturbed branches involved in the initial fault and their relationship with the power generating nodes. Firstly, according to the performance of the initial fault branch in the cascading fault phenomenon and the action of relay protection, an expression form of evaluating the severity of the initial fault branch is given. Secondly, the relationship between the current of the residual system branch and the injection power of the nodes after the initial fault removal is analyzed. Then, on the basis of synthesizing the severity of the disturbed branch and its correlation with the power generating nodes, the key power generating nodes on the seriously disturbed branch are selected by clustering analysis. Finally, based on the key power generation nodes, the optimal power generation output model considering the power generation operation cost was established, the model was solved by particle swarm optimization (PSO), the model was simulated by IEEE39 bus system in MATLAB environment, and the correctness of the established model and method was verified. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Study of Smart Decorating Machine on Cake Patten 1

引用

作者： Jiang, Shi-Jie Chang, Kuo-Chi Wang, Hong-Jiang Chu, Kai-Chun Wang, Hsiao-Chuan Chang, Fu-Hsiang School of Information Science and Engineering Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Business Management Fujian University of Technology Fuzhou China Institute of Environmental Engineering National Taiwan University Taipei Taiwan Department of Tourism Shih-Hsin University Taipei Taiwan College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (数字)9789813364202

ISBN: (纸本)9789813364196

Adding some shapes to food in the production process can greatly increase the added value of food and make the same food. The market is more competitive. At present, cake decorating is mainly done manually, which requires high operating skills of personnel, and there are fewer optional decorating styles. Aiming at these shortcomings, a design concept of a smart cake spotting machine is proposed. This design uses a three-axis linkage device to cooperate with the cream delivery mechanism;the main control system used STM32F103ZET6 chip. It stores the G-code files of the flower pattern through the SD card and externally stores the SD card in the SD card data, external stepper motor drive circuit to control the operation of the mechanical structure. Finally, the stepper motor controls the displacement of the mechanism and conveys the cream. The movement of the mechanism makes it possible to finish the work of decorating the cake. In this article, the specific design and implementation of the cake automatic flowering machine are introduced in detail. This study has undergone experimental testing and the results show that the cake embossing machine designed by this study institute can automatically complete embossing according to the set embossing pattern. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Stepping motors

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：