检索结果-内蒙古大学图书馆

International Conference on Electrostatics 2023

作者： Kalecz, G. Kiss, I. Nemeth, B. Department of Electric Power Engineering Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics MÅ egyetem rkp. 3. BudapestH-1111 Hungary

Upward lightning requires a distinct approach compared to downward (cloud-to-ground) lightning. Some lightning strikes are triggered by objects on the ground itself. The occurrence of such strikes depends on various factors, including the object's geometric dimensions, structure, relative location within its environment, as well as the distribution and location of electrical charges within the thundercloud. This phenomenon takes place more and more often due to the spread of wind farms and higher buildings. In this article, simulation and calculation is carried out regarding the Gaisberg Tower in Austria which is actively used as a measurement and research site for lightning purposes. A finite element simulation is carried out to assess the electric field characteristics in the geometry. The close electric field measurement instruments are located 170 m away from the tower on an enclosure which must be considered during data analysis. The result of the created model is validated by former measurement data which confirms the arrangement of the model and creates the opportunity to directly transform the values of the electric field from the field mill to the tower during appropriate conditions. © Published under licence by IOP Publishing Ltd.

关键词： Towers

来源：评论

学校读者我要写书评

暂无评论

High Efficiency Multiphase Cascaded DC-DC Boost Converters with Inductance Optimization 5

High Efficiency Multiphase Cascaded DC-DC Boost Converters w...

引用

5th International Conference on Power engineering and Renewable Energy, ICPERE 2022

作者： Muzakki, M.F. Furqani, J. Rizqiawan, A. School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9781665455480

This paper presents the design of a multiphase cascaded DC-DC boost converter with high efficiency and optimization of inductance value. The multiphase cascaded DC-DC boost converter is a converter that has a very high gain level and low input current ripple. The study begins with the derivation of the loss equation in the converter, and the results are used for the optimization process. Previous research with the same converter has achieved an efficiency of 85.8%. The selection of inductance value will affect the resistance value of the inductor so that efficiency will increase. However, the winding manufacturing technique and the selection of the inductor core are also determined. By applying the proposed multiphase cascaded DC-DC boost converter with a proper inductor and switching conduction mode, the inverter efficiency can be improved up to 5% which reached 89.19% in laboratory tests. While in critical conduction mode (CRM), at 0.15 mH inductance, efficiency is 86.23%. Experimental work verifies the proposed design and analysis. © 2022 IEEE.

关键词： Inductance

来源：评论

学校读者我要写书评

暂无评论

Interaction Design of Fertility Tracking Application Using User-Centered Design

Interaction Design of Fertility Tracking Application Using U...

引用

2022 International Conference on Data and Software engineering, ICoDSE 2022

作者： Faizzati, Madiha Arifiansyah, Fitra School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (数字)9798350397055

ISBN: (纸本)9798350397055

Fertility tracking application (FTA) is a type of digital health product in the form of a digital tracker that helps women manage their menstruation. Given that every woman has different menstrual characteristics, FTA has the potential to alienate certain groups of users. Thus, the aim of this research is to create an interaction design that can accommodate both normal and outlier users of FTA. The design methodology is user-centered design so that the iteration of design process is driven by feedbacks from existing user groups. Based on the user research, it is found that current FTAs, including but not limited to Flo and MyCalendar, have following problems: lack of ways for users to set up their preferred period tracking, lack of personalization, features with low visibility, and lack of explanation of unfamiliar medical terminologies in the application. Thus, an interaction is designed to address these problems. The solution allows each user to personalize various aspects of menstrual tracking. Usability goals of the interaction design solution are effective to use and easy to learn with helpful as user experience goals. The results of the interaction design evaluation using usability testing show that the solution is usable with a Single Ease Question score of 6.84 out of 7, a System Usability Score of 92 (Grade A/Excellent) out of 100, and an NPS score of +60 out of +100. Usability goal effective to use is achieved with 100% task completion and easy to learn is achieved with a score of 4.6 out of 5. Finally, helpful as user experience goal is achieved with a score of 5 out of 5. © 2022 IEEE.

关键词： User centered design

来源：评论

学校读者我要写书评

暂无评论

Vehicle Detection with YOLOv7 on Study Case Public Transportation and General Classification, Prediction of Road Loads 2

Vehicle Detection with YOLOv7 on Study Case Public Transport...

引用

2nd International Seminar on Machine Learning, Optimization, and Data Science, ISMODE 2022

作者： Djula, Edi Johan Syah Yusuf, Rahadian Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9781665455640

The Intelligent Transportation System (ITS) is a part of the application of computer vision to transportation systems, which is nothing more than a form of integration between information systems, telecommunication and transportation infrastructure, vehicles, and road users. As a result, ITS can not only solve traffic problems, but also reduce the use of private vehicles and increase the efficiency of public transportation by the community if road users' comfort and safety continues to improve. The implementation of ITS in several developed countries serves as a model for its achievements. In this study, YOLOv7 was used to classify vehicles using CCTV data from ATCS Bandung City. Taking a number of data to obtain enough data for further separation of data from the CCTV image capture into parts of the vehicle class. A pretraining model is used to identify the target vehicle based on this classification. This data processing allows for the prediction and calculation of road loads, which have long been a source of traffic congestion in Bandung, particularly in the Dago area. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-Criteria Recommender System for Determining Risk Level of Covid-19 9

Multi-Criteria Recommender System for Determining Risk Level...

引用

9th International Conference on Advanced informatics: Concepts, Theory and Applications, ICAICTA 2022

作者： Hikmawati, Erna Maulidevi, Nur Ulfa Surendro, Kridanto Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (数字)9781665456685

ISBN: (纸本)9781665456685

The coronavirus pandemic is a global disease outbreak causing countless loss of lives and also threatening the economic, social, religious, education, and other key sectors of nations. This highly infectious virus continues to spread rapidly and therefore, the need to develop innovative strategies and policies to curb the growing effects becomes very crucial. One significant approach is the introduction of lockdown measures, although this instrument is not completely dependable, due to possible adverse effects on societal activities. Prior to deployment, a number of criteria are taken into account, including demographic conditions, healthcare options, and Covid-19 case data. Depending on the influencing factors, a lockdown decision is typically made by assessing the different danger levels of a certain place. Consequently, this research propose a multi-criteria recommender system to determine the worth and risk of various regions, based on several constraints and databases. The model, which utilized the analytical network process (ANP) to discover interconnectedness and feedback, also included the weighting technique. In this study carried out in 27 districts and cities in West Java, Indonesia, 15% of the selected locations were categorized as high-risk levels. Meanwhile, 63% and 22% were associated with medium and low risk, respectively. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning for Mobile-Based Herbal Leaf Diseases Classification Using CNN-Based Ensemble Learning

Application of Deep Learning for Mobile-Based Herbal Leaf Di...

引用

International Conference on informatics and Computing (ICIC)

作者： Ketut Dionanda Sutrisna Ni Luh Wiwik Sri Rahayu Ginantra I Putu Agus Eka Darma Udayana Christina Purnama Yanti Technology and Informatics Informatics Engineering Institut Bisnis dan Teknologi Indonesia (INSTIKI) Denpasar Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Herbal leaves are an integral part of traditional Balinese medicine, known for their natural healing properties with minimal side effects. However, limited knowledge of the diseases that attack these plants may lead to decreased use and conservation. This research aims to develop a disease classification model on herbal plants using Convolutional Neural Network (CNN) as well as ensemble learning methods. The CNN method used to automatically extract features from leaf images, while ensemble learning using the ensemble averaging method improves the accuracy of classification results. This research identifies various leaf diseases, such as leaf spot, bacterial spot, mosaic virus, powdery mildew, and target spot, as significant threats to these crops. The proposed model was implemented in a mobile application, allowing users to detect diseases directly through their devices, thus supporting the preservation of the Usada Bali treatment tradition. The ensemble model, which incorporates architectures such as ResNet50, DenseNet121, MobileNetV2, and VGG16, achieved high accuracy in validation, with results up to $96.7 \%$. The findings show that this model offers a practical solution for the early classification of diseases in herbal plants, contributing to the conservation of traditional Balinese medicine.

关键词： Visualization Accuracy Computer architecture Feature extraction Convolutional neural networks Ensemble learning Viruses (medical) Diseases Biomedical imaging Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Physical-Chemical Properties Prediction of Chao Phraya River using Deep Learning Methods 10

Physical-Chemical Properties Prediction of Chao Phraya River...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Wayan Aditya Suranata, I. Komang Agus Ady Aryanto, I. Maneetham, Dechrit Nyoman Kusuma Wardana, I. Nyoman Crisnapati, Padma Universitas Pendidikan Nasional Faculty of Engineering and Informatics Bali Indonesia Institut Teknologi dan Bisnis STIKOM Bali Faculty of Informatics and Computers Bali Indonesia Rajamangala University of Technology Thanyaburi Pathum Faculty of Technical Education Udon Thani Thailand Electrical Engineering Politeknik Negeri Bali Bali Indonesia

ISBN: (纸本)9798350363104

This research aims to develop a predictive model for the water quality of the Chao Phraya River, focusing on the pH, Dissolved Oxygen (DO), and Electrical Conductivity (EC) values. The methods employed in this study include Long Short-Term Memory (LSTM), Artificial Neural Network (ANN), Gated Recurrent Unit (GRU), and One-Dimensional Convolutional Neural Network (1D-CNN). The data used to build the model were obtained from public data published by the Pollution Control Department of Thailand for the period from 2015 to 2020. Model evaluation processes utilize metrics such as RMSE, MAE, MSE, MAPE, and R2. The prediction results for pH, DO, and EC are separated based on each station along the Chao Phraya River. For example, the best model evaluation for predicting pH quality at the Bang Sai station using the 1D-CNN method yielded an RMSE of 0.039 pH. Meanwhile, the DO quality at the Bang Sai station obtained an RMSE of 0.586 mg/l with the GRU method, and the EC quality at the Bang Sai station achieved an RMSE of 9.183 uS/cm with the GRU method. Overall, the model evaluation indicates performance differences between the methods used to measure water quality at each station along the river. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Feature-preserving color pencil drawings from photographs

引用

Computational Visual Media 2023年第4期9卷 807-825页

作者： Dong Wang Guiqing Li Chengying Gao Shengwu Fu Yun Liang College of Mathematics and Informatics South China Agricultural UniversityGuangzhouChina School of Computer Science&Engineering South China University of TechnologyGuangzhouChina School of Data and Computer Science Sun Yat-sen UniversityGuangzhouChina

Color pencil drawing is well-loved due to its rich *** paper proposes an approach for generating feature-preserving color pencil drawings from *** mimic the tonal style of color pencil drawings,which are much lighter and have relatively lower saturation than photographs,we devise a lightness enhancement mapping and a saturation reduction *** lightness mapping is a monotonically decreasing derivative function,which not only increases lightness but also preserves input photograph *** saturation is usually related to lightness,so we suppress the saturation dependent on lightness to yield a harmonious ***,two extremum operators are provided to generate a foreground-aware outline map in which the colors of the generated contours and the foreground object are *** experiments show that color pencil drawings generated by our method surpass existing methods in tone capture and feature preservation.

关键词： non-photorealistic rendering pencil drawings image editing feature preservation

来源：评论

学校读者我要写书评

暂无评论

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of O...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Lu, Xiaotian Li, Jiyi Takeuchi, Koh Kashima, Hisashi Department of Intelligence Science and Technology Graduate School of Informatics Kyoto University Kyoto Japan Department of Computer Science and Engineering University of Yamanashi Kofu Japan

ISBN: (纸本)9798891761681

Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlike close-ended questions with definitive answers. While large language models (LLMs) have demonstrated strong capabilities across various tasks, they exhibit relatively weaker performance in evaluating answers to open-ended questions. In this study, we propose a method that leverages LLMs and the analytic hierarchy process (AHP) to assess answers to open-ended questions. We utilized LLMs to generate multiple evaluation criteria for a question. Subsequently, answers were subjected to pairwise comparisons under each criterion with LLMs, and scores for each answer were calculated in the AHP. We conducted experiments on four datasets using both ChatGPT-3.5-turbo and GPT-4. Our results indicate that our approach more closely aligns with human judgment compared to the four baselines. Additionally, we explored the impact of the number of criteria, variations in models, and differences in datasets on the results. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Analysis Cryptocurrency Prediction Price Using Recurrent Neural Network (RNN) Gate Recurrent Unit (GRU) Long Short-Term Memory (LSTM)

Analysis Cryptocurrency Prediction Price Using Recurrent Neu...

引用

International Conference on informatics and Computing (ICIC)

作者： Muhammad Patriot Bayu Santosa Ni Luh Wiwik Sri Rahayu Ginantra Ida Bagus Ary Indra Iswara Desak Made Dwi Utami Putra Technology and Informatics Informatics Engineering Institut Bisnis dan Teknologi Indonesia (INSTIKI) Denpasar Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Cryptocurrencies, which are digital assets intended to function as a medium of electronic exchange, have garnered significant global attention, with Bitcoin standing out as the most recognized example. A variety of neural network models, including Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU), have been employed in the quest to predict Bitcoin’s price movements. Numerous experiments have been conducted using different training configurations, specifically with epochs set at $100,200,300$, and 500, along with batch sizes of 32,64, and 128. These tests have consistently demonstrated that the GRU model surpasses both the RNN and LSTM models in terms of prediction accuracy and overall consistency. The results indicate that GRU presents a more reliable framework for forecasting trends in Bitcoin prices, offering greater stability and precision. Consequently, the GRU model is emerging as a preferred choice for those aiming to refine predictive analytics within the cryptocurrency market.

关键词： Training Analytical models Accuracy Computational modeling Bitcoin Predictive models Stability analysis Reliability Predictive analytics Long short term memory

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：