检索结果-内蒙古大学图书馆

12th International electrical engineering Congress, iEECON 2024

作者： Sakarin, Pipat Sitjongsataporn, Suchada Mahanakorn University Of Technology The Electrical Engineering Graduate Program Faculty Of Engineering And Technology Bangkok Thailand Mahanakorn University Of Technology Department Of Electronic Engineering Bangkok Thailand

ISBN: (纸本)9798350383591

This paper presents the human fall detection by convolutional neural network (CNN) classification and MobileNet algorithm. In order to reduce the number of parameter, we propose a vision-based fall detection model, that is called 'Applied Depthwise separable-based CNN-MobileNet (ACM) algorithm'. This model is based on CNN, deptwise convolution and pointwise convolution of MobileNet algorithm. Experimental results show the accuracy of proposed ACM model about 97.68% and number of parameters of proposed ACM model is less than conventional CNN model. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Optimizing Indoor Vertical Farming with DDPG Reinforcement Learning: Enhancing Control of Nutrient Levels, Climate Conditions, and Plant Health 5

Optimizing Indoor Vertical Farming with DDPG Reinforcement L...

引用

5th IEEE International Conference on Technology, Informatics, Management, engineering and Environment, TIME-E 2024

作者： Albert Panggabean, Good Fried Romadhon, Rahmat Lubis, Ramot Joelianto, Endra Institut Teknologi Bandung Doctoral Program in Engineering Physics Bandung Indonesia Institut Teknologi Del Faculty of Informatics and Electrical Engineering Toba Indonesia Institut Teknologi Bandung Engineering Physics Study Program Bandung Indonesia Institut Teknologi Bandung Instrumentation Control and Automation Research Group Bandung Indonesia

ISBN: (纸本)9798350364743

In indoor vertical farming systems, managing dynamic and complex environments poses significant challenges. Traditional control strategies often fall short in adapting to rapid changes in critical parameters such as nutrient levels, climate conditions, and plant health indicators. To address these challenges, this paper presents a novel approach for optimizing indoor vertical farming using Deep Deterministic Policy Gradient (DDPG), a reinforcement learning algorithm well-suited for environments with continuous action spaces. Our study focused on the control and monitoring of key parameters, including nutrient levels (pH and EC), climate conditions (temperature, humidity, light, and CO2 levels), and plant health indicators (biomass accumulation and leaf size structure). By defining a comprehensive state and action space, we simulated an indoor farming environment and trained the DDPG model to maximize crop yield and health. © 2024 IEEE.

关键词： DDPG indoor vertical farming precision agriculture reinforcement learning smart farming

来源：评论

学校读者我要写书评

暂无评论

Balancing Dual DC Voltage Control in Quasi Single-Stage Converter for Low-Voltage Energy Storage System Grid-Connected 20

Balancing Dual DC Voltage Control in Quasi Single-Stage Conv...

引用

20th International Conference on electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2023

作者： Manokum, Warissara Kumsuwan, Yuttana Faculty of Engineering Chiang Mai University Graduate Program in Electrical Engineering Department of Electrical Engineering Chiang Mai Thailand Provincial Electricity Authority Bangkok Thailand Chiang Mai University Faculty of Engineering Department of Electrical Engineering Chiang Mai Thailand

ISBN: (纸本)9798350310467

The aim of a bidirectional quasi single-stage converter (QSSC) for low-voltage energy storage systems that are grid-connected is to reduce the power conversion stage of the dc-dc converter, which results in improved overall efficiency. The QSSC configuration relies on a modified modulation strategy due to the unequal dual dc port (upper and lower dc ports) voltage. The control for ensuring that the dual dc port voltages are equal is presented in this paper. When the lower dc port is varied in response to battery voltage, another is controlled to track in response to the lower dc port, so that the voltage ratio between the upper and lower dc port is always equal to one. Furthermore, power sharing in a dual dc port is equal, which means that a dc-dc converter automatically operates at 50% of the battery power. Thus, the existing modulation can be used and the power stage conversion of the dc-dc converter can be decreased. The proposed control for the QSSC is verified with simulation results. © 2023 IEEE.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

Optimal Location to Use Solar Energy in an Urban Situation

引用

Computers, Materials & Continua 2023年第4期75卷 815-829页

作者： Ngakan Ketut Acwin Dwijendra Indrajit Patra N.Bharath Kumar Iskandar Muda Elsayed M.Tag El Din Faculty of Engineering Udayana UniversityBali80361Indonesia An Independent Researcher NIT DurgapurWest Bengal700027India Department of Electrical and Electronics Engineering Vignan’s Foundation for Science Technology and ResearchGuntur522001India Department of Doctoral Program Faculty Economic and BusinessUniversitas Sumatera UtaraMedan20222Indonesia Electrical Engineering Department Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11835Egypt

This study conducted in Lima, Peru, a combination of spatial decisionmaking system and machine learning was utilized to identify potentialsolar power plant construction sites within the city. Sundial measurementsof solar radiation, precipitation, temperature, and altitude were collectedfor the study. Gene Expression programming (GEP), which is based on theevolution of intelligent models, and Artificial Neural Networks (ANN) wereboth utilized in this investigation, and the results obtained from each werecompared. Eighty percent of the data was utilized during the training phase,while the remaining twenty percent was utilized during the testing phase. Onthe basis of the findings, it was determined that the GEP is the most suitablenetwork for predicting the location. The test state’s Nash-Sutcliffe efficiency(NSE) was 0.90, and its root-mean-square error (RMSE) was 0.04. Followingthe generation of the final map based on the results of the GEP model, itwas determined that 9.2% of the province’s study area is suitable for theconstruction of photovoltaic solar power plants, while 53.5% is acceptable and37.3% is unsuitable. The ANN model reveals that only 1.7% of the study areais suitable for the construction of photovoltaic solar power plants, while 66.8%is acceptable and 31.5% is unsuitable.

关键词： Solar energy renewable energy machine learning

来源：评论

学校读者我要写书评

暂无评论

Syntactic analysis of traditional houses in urban kampung

引用

Built Heritage 2024年第3期8卷 156-174页

作者： Nova Asriana Rendy Perdana Khidmat Meldo Andi Jaya Verarisa Anastasia Ujung Widi Dwi Satria Riza Andriani Architecture Study Program Faculty of Infrastructure and Regional TechnologyInstitut Teknologi SumateraJalan Terusan RyacuduKecamatan Jati AgungKabupaten Lampung SelatanLampung 35365Indonesia Architecture Study Program Faculty of EngineeringUniversitas Muhammadiyah PalembangPalembang 30263Indonesia Heritage Community Palembang 30151Indonesia

This research investigates a syntactical study and comparative analysis of the statistical and spatial characteristics of traditional houses in an urban kampung settlement,focusing on a selected case study built by a participatory Arabic community in Palembang,South Sumatra,*** research aims to determine a formal rule basis for spatial confgurations to reveal identical sociospatial structures based on syntactical *** experiment measures spatial layout variation through space syntax analysis to provide a better understand of how the correlation between spatial confguration and sociospatial structures in traditional houses can be *** syntactical analysis applies four distinctive procedures:a selected case study,data collection,statistical and graphical analysis,and graph *** results indicate that the spatiality of all traditional houses in this kampung settlement highlights the spatial hierarchy order as a formal rule-based system,and approximately an average of 10%of this community is concerned with designing intelligible *** Batu and other dwellings have a similarity and *** main dwelling’s function involves more steps to separate public and private functional rooms,but a functional transformation from a dwelling into a public facility creates a short distance for easy access by ***,this separation afects occupants,especially in terms of spatial distribution activities,movement fows,and other social *** approach provides practical and tangible benefts for preservation values related to buildings;this strategy may also change how buildings are perceived in other built environments.

关键词： Syntactical analysis Traditional housing Urban kampung Space syntax

来源：评论

学校读者我要写书评

暂无评论

Web-Based Incentive Calculations System at CV Karya Prima using Prototyping Method 7

Web-Based Incentive Calculations System at CV Karya Prima us...

引用

7th International Conference on New Media Studies, CONMEDIA 2023

作者： Cornelia, Monica Suryasari Universitas Multimedia Nusantara Information Systems Study Program Faculty of Engineering and Informatics Tangerang Indonesia

ISBN: (纸本)9798350307504

Consumption is an essential aspect of daily life, and fulfilling customer needs requires efficient distribution of goods. Therefore, distributors are needed and they frequently set targets for their employees to achieve, and motivation plays a significant role in employee performance. An organization that distributes goods called CV Karya Prima motivates its employees by offering incentives. However, manual incentive calculation sets out problems such as a lack of progress tracking, irregular payout dates, and probable inaccuracies. This study aims to develop a web-based incentive calculation system using the analytical hierarchy process method and a database for data retrieval. The system utilizes PHP, CodeIgniter, and MySQL and adopts the SDLC prototyping method. The developed system is focused on the sales division and variables like total sales, effective calls, calls, and outlets. The web-based system is capable of solving the issues using the features that were built based on user needs and have already been tested through user acceptance testing. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Characteristics of Switched Reluctance Motor Using Operating Area Expandable Drive Circuit in Unexpanded Operating Area 27

Characteristics of Switched Reluctance Motor Using Operating...

引用

27th International Conference on electrical Machines and Systems, ICEMS 2024

作者： Ishizawa, Taisei Sugai, Ryuya Goto, Hiroki Funato, Hirohito Utsunomiya University Graduate program in Information Electrical and Electronic Systems Engineering Japan Utsunomiya University Japan Utsunomiya University Faculty of Engineering Japan

ISBN: (纸本)9784886864406

In driving switched reluctance (SR) motors at high speeds, it is necessary to apply a high voltage during excitation and demagnetization. To clarify the usefulness of the proposed drive circuit, this paper focuses on the reduction of copper loss in motors and confirms the effect of copper loss reduction by comparing it with the conventional drive circuit. We also focused on capacitor voltage fluctuations caused by resonance phenomena and examined the effect of increasing torque by actively utilizing resonance phenomena. © 2024 The Institute of electrical Engineers of Japan.

关键词： Circuit resonance

来源：评论

学校读者我要写书评

暂无评论

Arabic text sentiment analysis and emotion classification using transformers 11

Arabic text sentiment analysis and emotion classification us...

引用

11th International Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2023

作者： Mossad, Nada Mohamed, Youssef Fares, A. Zaky, Ahmed B. Alexandria21934 Egypt Benha University The Computer Systems Engineering Program Faculty of Engineering at Shoubra The Department of Electrical Engineering Egypt

ISBN: (纸本)9798350369328

Sentiment analysis and emotion classification are two crucial components of natural language processing (NLP), which have been widely explored in recent years due to their broad applications. Sentiment analysis aims to identify the polarity of written texts, ranging from positive to negative. Meanwhile, emotion classification is focused on recognizing and categorizing the emotional states expressed in the text. To achieve a deeper understanding of sentiments and emotions, it's essential to utilize models like BERT transformers that can effectively interpret the context. The process begins with data preprocessing, including tokenization and noise removal, followed by fine-tuning techniques to adapt the BERT model to the proposed tasks. We employed the BERT model on four datasets obtained from various sources, including Twitter, news websites, and restaurant reviews, where each dataset represents a distinct Arabic dialect. Our proposed model outperforms commonly used techniques like LSTM and CNN, yielding superior results. Despite the progress made, there are still challenges to overcome, such as dealing with Arabic diacritics, the new Arabic Arabizi, which uses Latin characters, and handling Arabic idioms. Further research is required to address these challenges adequately. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Weed Detection Based on Fine-Tuned YOLOv5 16

Weed Detection Based on Fine-Tuned YOLOv5

引用

16th International Conference on Information Technology and electrical engineering, ICITEE 2024

作者： Agustian, Indra Wibirama, Sunu Ardiyanto, Igi Anggraini, Ika Novia Noviansyah, Pariyanto Universitas Gadjah Mada Department of Electrical and Information Engineering Yogyakarta Indonesia Universitas Bengkulu Study Program of Electrical Engineering Bengkulu Indonesia Universitas Gadjah Mada Department of Electrical and Information Engineering Yogyakarta55281 Indonesia Universitas Gadjah Mada Department of Electrical and Information Engineerig Yogyakarta Indonesia

ISBN: (纸本)9798350375817

Conventional weed control often ignores weed locations, potentially causing land damage. AI-based weed detection offers a modern solution. Unfortunately, little attention has been paid to how an augmentation technique improves performance of AI-based weed detection. To address this research gap, we proposed a weed detection model based on fine-tuned YOLOv5 to detect weeds in corn fields aged 1 to 3 weeks. YOLOv5 offers computational benefits, includes auto-augmentation capabilities, and presents a more organized visualization of the outcomes from the training data. The primary dataset used in this study comprised 3,437 images with a total of 18,267 annotated objects, including corn plants and weeds. We observed the effect of mosaic augmentation on the dataset images based on auto-augmentation in YOLOv5. We found that mosaic augmentation with a 0.75 probability outperformed 0.5 and 1.0. The best mAP performance was at the level @0.5 with score of 0.776 for all classes. Meanwhile, the mAP@0.5:0.95 was 0.573 for all classes, indicating that the model's performance requires further improvement. Our study is promising as a guidance for future development of AI-based weed detection. © 2024 IEEE.

关键词： weed deep learning Weed detection weed-yolo yolov5

来源：评论

学校读者我要写书评

暂无评论

Impact of different kinds of biomass mixtures on combustion performance, interaction and synergistic effects in cofiring of coal and biomass in steam power plants

引用

Clean Energy 2023年第5期7卷 1136-1147页

作者： Mochamad Soleh Azaria Haykal Ahmad Firman Bagja Juangsa Prihadi Setyo Darmanto Ari Darmawan Pasek Mechanical Engineering Doctoral Program Study Faculty of Mechanical and Aerospace EngineeringInstitut Teknologi BandungJl.Ganesha 10Bandung40132 Indonesia Mechanical Engineering Master Program Study Faculty of Mechanical and Aerospace EngineeringInstitut Teknologi BandungJl.Ganesha 10Bandung40132 Indonesia Energy Conversion Research Group Faculty of Mechanical and Aerospace EngineeringInstitut Teknologi BandungJl.Ganesha 10Bandung40132 Indonesia Research Center for New and Renewable Energy Institut Teknologi BandungJl.Ganesha 10Bandung40132 Indonesia Research and Development Center PT.PLN Indonesia Power

The cofiring of biomass and coal may be one of the most effective methods to improve energy utilization efficiency and reduce greenhouse gas *** study aims to investigate combustion performance,interaction and synergistic effects in the cofiring of coal and three types of *** fuel consisting of coal and three types of biomass such as sawdust,rice husk and solid recovery fuel was selected as the research *** and proximate analysis and differential thermogravimetric analysis with heating rates of between 10°C and 40°C/minute are used to analyse combustion *** of combustion in a 600-MWe steam power plant with a Carolina-type boiler is also carried out with the help of computational fluid dynamic(CFD)analysis to see the effect of the interaction and synergy of the mixed fuel on the performance of the steam *** effect on the com-bustion process in the combustion chamber of a steam power plant is also *** on the analysis of several test results of parameters such as ignition temperature,burnout temperature,calorific value of the fuel mixtures as well as CFD simulation,the results of the study show a strong indication of a positive synergy in mixing some of these biomasses as compared with a fuel mix-ture consisting only of coal and one type of *** no power derating of the boiler occurs until the biomass content in the fuel mixture is~30%on a mass *** reduction in greenhouse gas emissions also appears significant from the results of the CFD simulation of this study,which is characterized by a decrease in the fraction of CO_(2) in flue gas from 21.5%for coal alone as fuel to 15.9%in the case of cofiring excluding the CO_(2) attributed to the biomass.

关键词： biomass sawdust cofiring coal-fired power plant combustion decarbonization computational fluids dynamic

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：