检索结果-内蒙古大学图书馆

An event-driven approach for resources planning in distributed power generation systems

International Journal of Electrical Power and Energy Systems 2022年 137卷 107768-107768页

作者： Maschio, Dierli M.R. Duarte, Bruno Lazzaretti, André E. Lafay, Jean-Marc S. Adzkiya, Dieky da Costa, Jean Patric Teixeira, Marcelo Graduate Program in Electrical Engineering Federal University of Technology Paraná Brazil Graduate Program in Electrical Engineering and Industrial Informatics Federal University of Technology Paraná Brazil Department of Mathematics Institut Teknologi Sepuluh Nopember Indonesia

Renewable Energy Sources (RESs) stand as a straightforward alternative to complement the energy grid and have been recurrently integrated into the generation and distribution matrices. Physically, generation components have distributed nature and they are expected to work coordinately, complementing each other to supply centralised microgrids, which interface them with the main power grid and consumers. As RESs have intermittent nature, engineers are limited to plan resources consumption, fulfil unit commitments, stratify time, cost, environmental impact, and quality of energy. This paper exploits the event-driven behaviour of microgrids to provide ways for them to recognise their context and cooperate towards common goals. Our main result is a Petri net simulation model that estimates customisation policies to be applied back over the microgridvia event-based control. Results show that in some cases it is possible to save effort (and resources) of power generation by replacing reactiveness for a more balanced, context-aware, energy chain. A real photovoltaic plant is modelled by our approach with 86% accuracy. © 2021 Elsevier Ltd

关键词： Renewable energy resources

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Training of Monocular Depth Estimators via Self-Supervised Federated Learning

Privacy-Preserving Training of Monocular Depth Estimators vi...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Elton F. de S. Soares Carlos Alberto V. Campos Brazil Research Lab IBM Research Rio de Janeiro RJ Brazil Graduate Program in Informatics Federal University of the State of Rio de Janeiro Rio de Janeiro RJ Brazil

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Monocular depth estimation is gaining attention in computer vision for autonomous driving due to its cost-effectiveness and versatility. Recent works have used self-supervised learning to tackle this problem. However, they overlook crucial challenges for real-world deployment, such as data privacy, network consumption, computational cost, and unstable connectivity. Recent studies have shown the potential benefits of federated learning in addressing these challenges. Thus, we introduce FedSCDepth, a novel method that combines federated learning and deep self-supervision to efficiently learn monocular depth estimators with performance comparable to the state-of-the-art. Our evaluation using the KITTI dataset’s Eigen’s Split reveals that FedSCDepth achieves high efficacy, with a test loss below 0.13. It also demonstrates impressive efficiency, requiring only an average of 1.5k training steps and up to 0.415 GB of weight data transfer per autonomous vehicle in each round.

关键词： Training Data privacy Vehicular and wireless technologies Costs Federated learning Transportation Prototypes Self-supervised learning Autonomous vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS AND DETECTION OF SINGING TECHNIQUES IN REPERTOIRES OF J-POP SOLO SINGERS

arXiv

引用

arXiv 2022年

作者： Yamamoto, Yuya Nam, Juhan Terasawa, Hiroko Doctoral Program in Informatics University of Tsukuba Japan Graduate School of Culture Technology KAIST Korea Republic of

In this paper, we focus on singing techniques within the scope of music information retrieval research. We investigate how singers use singing techniques using real-world recordings of famous solo singers in Japanese popular music songs (J-POP). First, we built a new dataset of singing techniques. The dataset consists of 168 commercial J-POP songs, and each song is annotated using various singing techniques with timestamps and vocal pitch contours. We also present descriptive statistics of singing techniques on the dataset to clarify what and how often singing techniques appear. We further explored the difficulty of the automatic detection of singing techniques using previously proposed machine learning techniques. In the detection, we also investigate the effectiveness of auxiliary information (i.e., pitch and distribution of label duration), not only providing the baseline. The best result achieves 40.4% at macro-average F-measure on nine-way multi-class detection. We provide the annotation of the dataset and its detail on the appendix website 0 © 2022, CC BY.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Determinant Factors Affecting the Information System Success of Community-Based Application to Fight Covid-19 Pandemic

Determinant Factors Affecting the Information System Success...

引用

2021 International Conference on Computer, Control, informatics and Its Applications - Learning Experience: Raising and Leveraging the Digital Technologies During the COVID-19 Pandemic, IC3INA

作者： Purwanto, Adnan Asih, Dybio Dompu Hot Nurjabar, Ilham Cahyani, Trisiwi Indra Hidayat, Deni Manik, Lindung Computer Science Graduate Program University of Nusa Mandiri Jakarta Indonesia Research Center for Informatics National Research and Innovation Agency Bandung Indonesia

ISBN: (纸本)9781450385244

National governments around the world have made every effort to fight Covid-19. One of which is by building mobile applications that can be used to trace and monitor the citizens' health during this pandemic. These applications are expensive. It requires a significant amount of time and effort to develop and maintain the information systems. Therefore, there is a continuous struggle to identify the key factors influencing the information systems' adoption, utilization, and success. This study was performed to address the problem by identifying parameters that affect the information system success of "10 Rumah Aman (10 Safe Houses)", a community-based application in fighting the Covid-19 pandemic, using the DeLone and McLean (D&M) model. As a result, system quality positively affected the use and user satisfaction. Furthermore, service quality positively influenced use but not user satisfaction. Meanwhile, information quality had no significant effect either on use or satisfaction. Both use and user satisfaction had a significant effect on net benefits. © 2021 ACM.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Towards Continual Federated Learning of Monocular Depth for Autonomous Vehicles

Towards Continual Federated Learning of Monocular Depth for ...

引用

IEEE Conference on Vehicular Technology (VTC)

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Recent investigations in computer vision for autonomous vehicles have focused on depth estimation from images, owing to its cost-efficiency and adaptability. Monocular depth estimation, using a single camera, is notable for its adaptability compared to binocular techniques that require two fixed cameras. Sophisticated methodologies employ self-supervised deep neural networks, while latest research proposes the use of federated learning to tackle crucial challenges for autonomous driving, such as data privacy, network usage, computation distribution, and connectivity robustness. Nevertheless, continual learning presents an additional challenge for both centralized and federated training, as updating models with novel datasets may induce the forgetting of previously acquired samples, thereby diminishing the model’s versatility. Meanwhile, recent research indicates that experience replay strategies can be used to alleviate forgetting in autonomous driving use cases. We introduce ERFedSCDepth, an innovative approach amalgamating experience replay, federated learning, and deep self-supervision to allow the training of monocular depth estimators with high effectiveness and efficiency. Assessment using KITTI and DDAD datasets shows the efficacy of our approach, achieving enhanced continual learning performance over state-of-the-art baseline at standard depth metrics.

关键词： Continuing education Training Data privacy Vehicular and wireless technologies Federated learning Computational modeling Transportation Cameras Autonomous vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

Deformable CNN and Imbalance-Aware Feature Learning for Singing Technique Classification

arXiv

引用

arXiv 2022年

作者： Yamamoto, Yuya Nam, Juhan Terasawa, Hiroko Doctoral Program in Informatics University of Tsukuba Japan Graduate School of Culture Technology KAIST Korea Republic of

Singing techniques are used for expressive vocal performances by employing temporal fluctuations of the timbre, the pitch, and other components of the voice. Their classification is a challenging task, because of mainly two factors: 1) the fluctuations in singing techniques have a wide variety and are affected by many factors and 2) existing datasets are imbalanced. To deal with these problems, we developed a novel audio feature learning method based on deformable convolution with decoupled training of the feature extractor and the classifier using a class-weighted loss function. The experimental results show the following: 1) the deformable convolution improves the classification results, particularly when it is applied to the last two convolutional layers, and 2) both re-training the classifier and weighting the cross-entropy loss function by a smoothed inverse frequency enhance the classification performance. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

FluxProg 2.0 - Extended Version of a Visual Tool for Teaching programming Logic Using Flowcharts with Real and Simulated Robots

FluxProg 2.0 - Extended Version of a Visual Tool for Teachin...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： Matheus Biscaya Gutierrez João Alberto Fabro André Cristiano Cordeiro Academic Department of Informatics (DAINF-CT) Federal University of Technology - Paraná (UTFPR) Curitiba PR Brazil Graduate Program on Applied Computing (PPGCA) DAINF-CT - UTFPR Curitiba PR Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

This paper presents a new teaching tool with the goal of facilitating the learning of basic programming concepts among high school students and university freshmen. The tool incorporates a user-friendly visual interface and robotics, expanding on the existing Fluxprog project. New features were implemented, such as variables, logical and mathematical operations, conditional structures, and loops, to motivate students to engage in challenges that promote logical thinking. This paper presents the design, implementation and evaluation of a programming teaching tool using a visual language based on flowcharts, with subsequent data collection through a questionnaire and analysis of preliminary results to evaluate the user's experience while interacting with the tool.

关键词： Visualization Flowcharts Conferences Education Data collection User experience Logic Robots programming profession

来源：评论

学校读者我要写书评

暂无评论

Spatial dynamics of dengue fever spreading for the coexistence of two serotypes with an application to the city of Sao Paulo, Brazil

引用

COMPUTER METHODS AND programS IN BIOMEDICINE 2022年 219卷 106758-106758页

作者： Pereira, F. M. M. Schimit, P. H. T. Informatics and Knowledge Management Graduate Program Universidade Nove de Julho Rua Vergueiro 235/249 São Paulo 01525-000 SP Brazil

Background and objective: Dengue fever is a disease in which individuals' spatial distribution and Aedes aegypti mosquitoes breeding places are important factors for the disease dynamics. Typically urban, dengue is a problem for least developed countries due to the ineffectiveness in controlling the vector and disorderly urbanization processes. The result is a composition of urban sanitation problems and areas with high demographic densities and intense flows of people. This paper explores the spatial distribution of vector breeding places to evaluate introducing a new dengue serotype to a population at equilibrium for a pre-existing serotype. The paper's objective is to analyze the spatial dynamics of dengue using variations of the basic reproduction ***: A model based on probabilistic cellular automata is proposed to permitting the necessary flexibility to consider some spatial distributions of vector breeding places. Then, ordinary differential equations are used as a mean-field approach of the model, and the basic reproduction number ( R 0 ) is derived considering the next-generation matrix method. A spatial approach for R 0 is also proposed, and the model is tested in a neighbourhood from the city of Sao Paulo, Brazil, to examine the potential risks of vector breeding cells ***: The results indicated that the more spread out these places, the higher are the values of R 0 . When the model is applied to a neighbourhood in Sao Paulo, residential areas may boost the infections and must be under public vigilance to combat vector breeding ***: Considering the mean-field approximation of the cellular automata model by ordinary differential equations, the basic reproduction number derived returned an estimative of the disease dynamics in the population. However, the spatial basic reproduction number was more assertive in showing areas with a higher disease incidence. Moreover, the model could be easily adapted to be used in rea

关键词： Basic reproduction number Dengue Probabilistic cellular automata Spatial basic reproduction number Spatial dynamics

来源：评论

学校读者我要写书评

暂无评论

Testing Approach for IoT System (Case Study: Air Quality Monitoring System)

Testing Approach for IoT System (Case Study: Air Quality Mon...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Theresia Herlina Rochadiani Haryono Soeparno Ford Lumban Gaol Yulyani Arifin Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Informatics Department Pradita University Tangerang Indonesia

The Internet of Things (IoT) was evaluated as part of this study. The IoT system in this study is the air quality monitoring system. The system consists of three layers, three end devices with air quality monitoring sensors as the perception layer, the LoRaWAN network as the network layer, and the monitoring website as the presentation layer. Before being made available to the public, IoT hardware and software must undergo testing. For IoT systems, there are no established standards or quality criteria. This study's goal is to evaluate the methodology for an air quality monitoring system. Website speed is measured using Pingdom tools. The website received a performance grade of B. Pingdom offers advice for enhancing website performance. Sucuri is utilized as a security test tool to evaluate the website's security, and consequently, no malware was discovered. The latency and data dependability are monitored to assess the system's performance fully. The outcome demonstrates that all system components consistently and accurately receive data with a latency of less than 1 s.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constructing Coronary Artery Vessel Segmentation Based on Deep Learning Models and Image Processing 24

Constructing Coronary Artery Vessel Segmentation Based on De...

引用

8th International Conference on Medical and Health informatics, ICMHI 2024

作者： Peng, Kang-Syuan Chang, Hsiao-Huang Hsu, Ying-Kai Chien, Ting-Ying Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Cardiovascular Surgery Department Taipei Veterans General Hospital Taipei City TaiwanTaipei Medical University Taipei City Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan City Taiwan TaiwanInnovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan

ISBN: (纸本)9798400716874

Narrowing of the coronary arteries is an important indicator of the severity of coronary artery disease (CAD) in patients. Previous research using deep learning to identify narrowed vessels has primarily been based on object detection, but this approach has several problems, such as the inability to detect multivessel narrowing, calculate the actual rate of narrowing, and determine the exact location of occurrence. Therefore, we believe that the determination of narrowing should return to the original method, namely, calculating the maximum and minimum diameters around the vessel. However, to automate this task, a preprocessing step for separating each vessel is needed, especially for the complex structure of the left coronary artery. We designed a deep learning model capable of analyzing an entire coronary angiography (CAG) image for the separation and tracking of vessels. This not only serves as a preprocessing step for calculating narrowing but also allows for the analysis of different vessel flow directions, providing doctors with comprehensive assessment indicators. © 2024 Copyright ACM.

关键词： Image segmentation

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：