检索结果-内蒙古大学图书馆

Generalized Formal Model-Verifier: A Formal Approach for Verifying Static Models

SN Computer Science 2024年第5期5卷 508页

作者： Somogyi, Norbert Mezei, Gergely Department of Automation and Applied Informatics Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Műegyetem rkp. 3 Budapest 1111 Hungary

The field of software modeling has gained significant popularity in the last decades. By capturing the static aspects of the software requirements, model-driven engineering eases the development and maintenance of software. However, additional constraints, such as invariants on model elements, that the solution must conform to may be too complex to include in the structure of the model itself. External solutions are often used to describe static constraints on models, the most prevalent approach being the Object Constraint Language (OCL) and its formal variants. This paper proposes the Generalized Formal Model-Verifier (GFMV), which is a general approach for verifying static constraints on software models. GFMV employs different formal verification methods based on Kripke Structures. Kripke Structures are used to capture the static structure of the model, then the constraints are formalized using a first-order branching-time logic, the Computational Tree Logic (CTL). Finally, the NuSMV model checker is reused to verify whether the constraints formalized in CTL hold on the formal Kripke Structure. When compared to existing solutions, GFMV offers increased generality and formal proof that the constraints hold on the model. The expressive power and runtime-scalability of the approach are evaluated on a real-world example model and OCL invariants cited from literature. © The Author(s) 2024.

关键词： CTL Formal verification Kripke structure NuSMV OCL UML

来源：评论

学校读者我要写书评

暂无评论

Modeling Electric Vehicle Charging Station in Bandung Area via Discrete Event Simulation

Modeling Electric Vehicle Charging Station in Bandung Area v...

引用

2024 International Conference on Green Energy, Computing and Sustainable technology, GECOST 2024

作者： Wahyudi, Selvi Aziz Rahman, Fathin Saifur Hariyanto, Nanang School of Electrical Engineering & Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9798350357905

The increasing adoption of electrical vehicles (EVs) presents an issue to transportation dynamics. One of the keys to be addressed is the limitation of driving characteristics of EVs due to the availability of electrical vehicle charging stations (EVCSs) in the system. In this study, we present a comprehensive study that utilizes discrete event simulation (DES) to analyze the complex dynamics of EV driving mobilities and charging events in an urban environment, of the Bandung region. The approach is demonstrated by designating several existing destinations and EVCS for EVs to drive across the network. To construct an accurate model, we develop scenarios where drivers potentially charge their EVs at home with different probabilities (Phc). However, the findings indicate that the public EVCS is only being utilized with Phc 0 - 75%. Specifically, only three stations,3, 6, and 9, are frequently visited with the charging duration peaks at around 107 minutes from 11 a.m. to 1 p.m. Finally, the study concludes by discussing offers valuable insights and improving the overall user experience within Bandung's EV charging infrastructure. © 2024 IEEE.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

Low Latency Video Streaming System for VR Teleoperation over 5G Networks 3

Low Latency Video Streaming System for VR Teleoperation over...

引用

3rd IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2024

作者： Blázovics, László Kovács, Viktor Gótzy, Márton Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Automation and Applied Informatics BudapestH-1111 Hungary

ISBN: (纸本)9798350378009

With the introduction of 5G networks, high-speed low-latency network connections became available for mobile and embedded devices without the limited range of WiFi networks. Although the source and the destination can now be hundreds of kilometres away, the communication between them can be flawless. Our goal is to have a low cost, low power, lightweight device that is able to stream video for UAV (unmanned aerial vehicles), mobile robot teleoperation over 5G networks to AR/VR (augmented/virtual reality) applications, to large distances without the need for line of sight. In this paper we compare the latency of existing low cost video streamer solutions (UAV camera streaming, single board computer) and present a custom hardware-software solution optimized for low latency, while conducting measurements over different network types (wired, campus 5G, public 5G). We have shown that the custom device was able to achieve with significantly lower latency (50-80 ms direct over direct connection, about 100-150 ms over public 5G). © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Overfitting Defeat with Dropout for Image Classification in Convolutional Neural Networks 10

Overfitting Defeat with Dropout for Image Classification in ...

引用

10th International Conference on Wireless and Telematics, ICWT 2024

作者： Nugroho, Kukuh Hendrawan Iskandar Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350377057

Data is a crucial part of machine learning, used to create models whose patterns are defined with specific algorithms. The primary purpose of the machine learning process is to generate the best prediction models. However, in general, models that trained well in the training phase differ when used in the testing phase. This phenomenon is called overfitting, a common problem in machine learning, mainly when developing image classification models using Convolutional Neural Networks (CNNs). The main task of the output layer in CNNs is to classify the truth labels from the data input images. One machine learning performance is defined by how well the models can predict the truth labels. Overfitting is one of the problems that can influence the model's performance. Dropout is one of the regularization techniques intended to solve this problem. Our purpose in this research is to know the relationship between the use of dropout and CNN's performance in image classification from the point of view of overfitting problems. The experimental results stated that this technique can alleviate overfitting by 35% with a learning rate value 0.001. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

PERISAI: Design and Implementation of a Remote Deployment System for IoT Applications

PERISAI: Design and Implementation of a Remote Deployment Sy...

引用

2024 IEEE International Conference on Data and Software engineering, ICoDSE 2024

作者： Rahman, Muhammad Garebaldhie E.R. Candra, Muhammad Zuhri Catur School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9798331506407

As the use of Internet of Things (IoT) devices continues to expand, the management of these devices has become increasingly complex and time-consuming. One of the key processes in managing IoT devices is deployment, which involves installing and updating software on the devices. Traditionally, this process has been performed manually, device by device, often through a wired connection such as USB, which is highly inefficient and labor-intensive. With advancements in technology, Over the Air (OTA) methods have emerged, allowing for wireless deployment of software updates. However, these methods still face significant challenges, particularly in terms of scalability and managing a diverse range of devices with different capabilities and constraints. Issues such as device heterogeneity, difficulty in diagnosing devices remotely, hardware resource limitations, and security concerns remain prevalent. This research addresses these challenges by designing and implementing PERISAI, a remote deployment system specifically tailored for IoT applications. PERISAI is designed to be platform-agnostic, meaning it can operate on any platform as long as it can run Kubernetes, and is optimized for devices with limited resources. The system utilizes Kubernetes, a widely adopted container orchestration tool, with the lightweight K3s distribution to manage deployments efficiently on resource-constrained devices such as Raspberry Pi. PERISAI has been tested by deploying a blink LED program across two Raspberry Pi devices with a single click, achieving successful deployment in under 4.7 seconds. © 2024 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Techno-economic Analysis of Hybrid Renewable Energy System for Rural Area: Study Case Lembor Selatan District 6

Techno-economic Analysis of Hybrid Renewable Energy System f...

引用

6th International Conference on Power engineering and Renewable Energy, ICPERE 2024

作者： Mangkung, Bemardinus G. A. Hamdani, Deny Rachmilda, Tri Desmana Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798331504694

Indonesia aims achieving Net Zero Emission by 2060. To meet this goal, Indonesia has raised its emission reduction target to 31.89 % by 2030. Utilizing the potential of Renewable Energy Source (RES), such as solar and wind, is one of the key strategies to support emission reduction efforts. This study focuses on analyzing various configurations of Hybrid Renewable Energy System (HRES) and scenarios applicable to the electrification of rural area. In addition to addressing load demand, the study aims to assess the potential of RES in rural area. Homer Pro is utilized for this analysis to model and evaluate different configurations and scenarios effectively. © 2024 IEEE.

关键词： Electrification

来源：评论

学校读者我要写书评

暂无评论

Design Optimization of Nutrient and Water Application in Chili Plant Based on Living Lab in Parepare City 11

Design Optimization of Nutrient and Water Application in Chi...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Heliana, Sitti Samodra, Bayu Solang, Marthen Amelius School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9798350389654

Chili is one of the leading national food commodities. Price variations and inflation in Parepare City are frequently caused by its reliance on supply from outside the region. The development of chili cultivation by utilizing IoT technology can increase crop productivity. This research proposes a design for optimizing the provision of nutrients and water to chili plants using the Living Lab approach, where there are four main activities: Plan, Build, Run, and Evaluate, which require integration from the technology and non-technology side. The involvement of stakeholders, such as the government, community, and farmer groups with researchers from the planning to evaluating stage, has resulted in the design of technological solutions that can answer the challenges of inflation. In this study, with a total of 36 respondents, most stakeholders, 84 %, were interested in the technological solution design. Furthermore, 50% of stakeholders stated that the technology could be applied to a land area of 10-20 m' of chili plants. This research verifies that the Living Lab approach to improving digital literacy can help develop a resilient and sustainable local economy. © 2024 IEEE.

关键词： Chili Design IoT Living Lab Parepare

来源：评论

学校读者我要写书评

暂无评论

Development and testing midpoint voltage balance algorithms of three-level inverters

Renewable Energy and Power Quality Journal

引用

Renewable Energy and Power Quality Journal 2023年 21卷 521-526页

作者： Stranyóczky, L. Balogh, A. Sütő, Z. Varjasi, I. Department of Automation and Applied Informatics Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Műegyetem rkp. 3. BudapestH-1111 Hungary

Nowadays, the use of inverters is increasing in more and more applications. Environmental awareness is becom-ing a trend, so more and more people install solar energy systems on their houses, which also require the use of inverters. Higher power levels have led to the emergence of three-level inverters which has opened up new challenges, such as the issue of midpoint voltage balancing. This paper discusses voltage balancing and voltage ripple reduction techniques for three-level inverters with Neutral-Point Clamped (NPC) topology. The balancing is based on injecting zero-sequence voltage component in carrier-based modulation. The viability of the modulation techniques are verified by computer simulation and then tested on hardware. © 2023, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

PSKV-System : A Framework for AI-Powered Healthy Ageing 11

PSKV-System : A Framework for AI-Powered Healthy Ageing

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Gantini, Tiur Langi, Armein Z.R. Mengko, Tati Latifah E.R. Koesoema, Allya Paramita School of Electrical and Informatics Engineering Institute of Technology Bandung Universitas Kristen Maranatha Pptikitb Bandung Indonesia School of Electrical and Informatics Engineering Institute of Technology Bandung Bandung Indonesia

ISBN: (纸本)9798350389654

This paper explores the application of the Product-Service-Knowledge- Value Systems (PSKV -S) framework in the design of Artificial Intelligence (AI) solutions for healthy aging. With the global population aging rapidly, there is a growing need for innovative approaches to support the health and well-being of older adults. AI offers a promising avenue for addressing this challenge, providing tools for enhanced diagnostics, personalized healthcare, cognitive support, and independent living. The PSKV-S framework, which considers the interconnectedness of products, services, knowledge, and value, provides a valuable lens for analyzing and designing AI systems for healthy aging. The paper examines the potential of AI biomarkers for aging, highlighting their role in understanding biological aging processes and facilitating drug discovery. It also discusses the services and knowledge generated through AI-powered solutions, emphasizing the importance of data collection and analysis for improving treatment protocols and advancing research. © 2024 IEEE.

关键词： Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Smart Waste Sorting System for Automatic Waste Classification in Campus Areas (Study Case: Bandung Institute of technology)

Implementation of a Smart Waste Sorting System for Automatic...

引用

2024 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2024

作者： Zahra, Salimatussholati Az Simatupang, Verawati Esteria Sirichit Bandung, Yoanes School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9798331521219

This study addresses the critical challenge of waste management at the Bandung Institute of technology, where manual waste sorting is time-consuming, labor-intensive, and prone to errors due to confusion about waste categories. To improve efficiency and accuracy, an automated waste sorting system was developed using machine learning and Internet of Things (IoT) technology. The system, based on the YOLOv5n object detection algorithm, achieved high precision and performance in identifying and sorting waste. Additionally, a data management subsystem was implemented to monitor and optimize waste bin placement through cloud databases and a web interface. The testing results confirmed the system’s effectiveness and ease of use, offering a scalable solution for better waste management on campus. ©2024 IEEE.

关键词： internet of things machine learning smart waste sorting system

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：