检索结果-内蒙古大学图书馆

Green Energy, Computing and Sustainable Technology (GECOST), International Conference on

作者： Ing Ming Chew W. K. Wong Filbert H. Juwono Teck Chai Tiong Department of Electrical and Computer Engineering Curtin University Malaysia Miri Malaysia Computer Science Program University of Southampton Malaysia Nusajaya Malaysia Department of Electrical and Computer Engineering Curtin University Malaysia Miri Sarawak Malaysia

ISBN: (纸本)9781665486644

This paper aims to analyze the determinant parameters of Genetic Algorithm (GA) analysis for the optimized control performance of a closed control loop. The determinant parameters of GA optimization analysis cover population size (nPop), mutation rate (mu) and iteration (iter.) are analyzed and justified. The control terminology covers the Proportional-Integral-Derivative (PID) controller, a prestigious solution for industrial control applications. Besides, the research proposed stability analysis to determine the upper and lower limit settings for the optimization analysis. The research has begun with model identification, stability analysis and is followed by determining the controller tunings. The performance indexes are applied to compare the response performance of GA with deterministic controller tunings. Analysis results and discussion shows that GA with proper determinant parameters’ settings are performing better than other tuning methods in the closed loop control performance.

关键词： Analytical models Terminology Sociology Process control Stability analysis Performance analysis Statistics

来源：评论

学校读者我要写书评

暂无评论

Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details

arXiv

引用

arXiv 2023年

作者： Hwang, Inwoo Kim, Hyeonwoo Kim, Young Min Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects. Guided by a reference image and text descriptions, our pipeline adds detailed texture on labeled 3D geometries in the room such that the generated colors respect the hierarchical structure or semantic parts that are often composed of similar materials. Instead of applying flat stylization on the entire scene at a single step, we obtain weak semantic cues from geometric segmentation, which are further clarified by assigning initial colors to segmented parts. Then we add texture details for individual objects such that their projections on image space exhibit feature embedding aligned with the embedding of the input. The decomposition makes the entire pipeline tractable to a moderate amount of computation resources and memory. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated datasets with high-quality textures designed by skillful artists. To the best of our knowledge, it is the first practical and scalable approach that can create detailed and realistic textures of the desired style that maintain structural context for scenes with multiple objects. © 2023, CC BY.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

The Effect of Major Depressive Disorder on Producing Intelligible Speech

SSRN

引用

SSRN 2024年

作者： Seneviratne, Nadee Li, Leslie Espy-Wilson, Carol Department of Electrical and Computer Engineering University of Maryland College ParkMD20740 United States Program in Neuroscience and Cognitive Science Department of Linguistics University of Maryland College ParkMD20740 United States

Understanding the characteristics of depressed speech can provide insights on aspects to consider when developing biomarkers for automatic depression detection systems. We present the results of a speech intelligibility study that was conducted to assess the intelligibility of the speech of a female and a male subject when they were severely depressed and when they were in remission. Our analysis shows that, in general, the depressed speech is at least as intelligible as in-remission speech. This is further supported by the underlying "simpler" articulatory coordination of depressed speech as derived from the Articulatory Coordination Features. Acoustically, the simpler articulatory coordination means that there is less variability due to coarticulation in the speech signal. © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distilling BlackBox to Interpretable models for Efficient Transfer Learning

arXiv

引用

arXiv 2023年

作者： Ghosh, Shantanu Yu, Ke Batmanghelich, Kayhan Department of Electrical and Computer Engineering Boston University BostonMA United States Intelligent Systems Program University of Pittsburgh PittsburghPA United States

Building generalizable AI models is one of the primary challenges in the healthcare domain. While radiologists rely on generalizable descriptive rules of abnormality, Neural Network (NN) models suffer even with a slight shift in input distribution (e.g., scanner type). Fine-tuning a model to transfer knowledge from one domain to another requires a significant amount of labeled data in the target domain. In this paper, we develop an interpretable model that can be efficiently fine-tuned to an unseen target domain with minimal computational cost. We assume the interpretable component of NN to be approximately domain-invariant. However, interpretable models typically underperform compared to their Blackbox (BB) variants. We start with a BB in the source domain and distill it into a mixture of shallow interpretable models using human-understandable concepts. As each interpretable model covers a subset of data, a mixture of interpretable models achieves comparable performance as BB. Further, we use the pseudo-labeling technique from semi-supervised learning (SSL) to learn the concept classifier in the target domain, followed by fine-tuning the interpretable models in the target domain. We evaluate our model using a real-life large-scale chest-X-ray (CXR) classification dataset. The code is available at: https://github. com/batmanlab/MICCAI-2023-Route-interpret-repeat-CXRs. © 2023, CC BY.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Assessment of ATH-Filled Silicone Rubber Under DC Dry Band Arcing 24

Assessment of ATH-Filled Silicone Rubber Under DC Dry Band A...

引用

24th International Middle East Power System Conference, MEPCON 2023

作者： Mehmood, Basharat Ghunem, Refat El-Hag, Ayman Hassan, Mohammad K. Al-Sulaiti, Leena Abdala, Ahmed University of Waterloo Electrical & Computer Engineering Department 200 University Avenue W WaterlooONN2L 3G1 Canada OttawaONK1A0R6 Canada Qatar University Center for Advanced Materials Qatar Texas A&m University at Qatar Chemical Engineering Program Doha Qatar

ISBN: (纸本)9798350358469

This paper investigates the tracking and erosion performance of silicone rubber filled with alumina trihydrate under DC dry band arcing in the inclined plane tracking and erosion test (IPT). Alumina trihydrate is incorporated into silicone rubber at 50 wt.% loading level for preparing silicone rubber composites, which are exposed to DC dry band arcing under mild and severe voltage levels in the inclined plane tracking and erosion test. Test outcomes indicate that the mechanism of silicone rubber deterioration changes with respect to the severity of the DC dry band arcing. It is found that dry band arcing tends to stimulate surface tracking under mild voltage levels and erosion due to thermal degradation under relatively higher voltage levels (critical). Moreover, test results indicate that silicone rubber erosion is not solely influenced by the dry band arcing power derived from the leakage current, but also dependent on additional contributing mechanisms leading to elevated surface temperatures and severe erosion. © 2023 IEEE.

关键词： Erosion

来源：评论

学校读者我要写书评

暂无评论

Defect Detection of Agricultural Commodities using Image Processing and Artificial Neural Networks

Defect Detection of Agricultural Commodities using Image Pro...

引用

2022 International Seminar on Application for Technology of Information and Communication, iSemantic 2022

作者： Suprijono, Herwin Kartikadarma, Etika Yusianto, Rindra Marimin, Marimin Dian Nuswantoro University Faculty of Engineering Department of Electrical Engineering Semarang53192 Indonesia Dian Nuswantoro University Study Program of Information Technology Faculty of Computer Science Semarang53192 Indonesia Dian Nuswantoro University Faculty of Engineering Department of Industrial Engineering Semarang53192 Indonesia Faculty of Agricultural Engineering and Technology Department of Agro-Industrial Technology West Java Bogor16002 Indonesia

ISBN: (数字)9781665488396

ISBN: (纸本)9781665488396

Production losses of agricultural commodities on agricultural land due to product defects depend on the level of pest and disease attacks. Defects cause the product not to be harvested or rejected by the market. Data from the Ministry of Agriculture of the Republic of Indonesia in 2021 shows the percentage of defective products for this commodity is 5%. This study aims to detect defects in agricultural products using image processing and artificial neural networks. We used the screening threshold method with potato research samples from Dieng, Indonesia. The study results for spot defects showed that from 100 training data, there were five incorrect identification data, so the accuracy of the training process was 95%. At the same time, the hole defect accuracy is better, which is 97%. It shows that defects in agricultural commodities can be detected using this method. For further research, the development of agricultural product sorting can combine sorting techniques with this method. © 2022 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Graph Coordinates and Conventional Neural Networks - An Alternative for Graph Neural Networks

Graph Coordinates and Conventional Neural Networks - An Alte...

引用

IEEE International Conference on Big Data

作者： Zheyi Qin Randy Paffenroth Anura P. Jayasumana Electrical and Computer Engineering Colorado State University Fort Collins USA Department of Data Science Program Worcester Polytechnic Institute Worcester MA USA

Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through message passing for neighborhood aggregation, have been a leading solution. However, these networks often require substantial computational resources and may not optimally leverage the information contained in the graph’s topology, particularly for large-scale or complex *** propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel and efficient alternatives to message passing GNNs, that directly leverage the graph’s topology, sidestepping the computational challenges presented by competing algorithms. Our proposed methods can be viewed as a reprise of classic techniques for graph embedding for neural network feature engineering, but they are novel in that our embedding techniques leverage ideas in Graph Coordinates (GC) that are lacking in current *** results, benchmarked against the Open Graph Benchmark Leaderboard, demonstrate that TCNN and DVCNN achieve competitive or superior performance to message passing GNNs. For similar levels of accuracy and ROC-AUC, TCNN and DVCNN need far fewer trainable parameters than contenders of the OGBN Leaderboard. The proposed TCNN architecture requires fewer parameters than any neural network method currently listed in the OGBN Leaderboard for both OGBN-Proteins and OGBN-Products datasets. Conversely, our methods achieve higher performance for a similar number of trainable parameters. These results hold across diverse datasets and edge features, underscoring the robustness and generalizability of our methods. By providing an efficient and effective alternative to message passing GNNs, our work expands the toolbox of techniques for graph-based machine learning. A significantly lower number of tunable parameters for a given evaluation metric makes TCNN and DVCNN especiall

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Dual-channel Converter with a Positive Output and a Negative Voltage Output

A Dual-channel Converter with a Positive Output and a Negati...

引用

International Symposium on computer, Consumer and Control (IS3C)

作者： Yau Yeu-Torng Luu Thanh-Phu Ph.D. Program Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung Taiwan Department of Electrical Engineering National Chin-Yi University of Technology Taichung Taiwan

In this paper, a dual-channel converter with a positive output and negative voltage output is proposed. It integrates a positive voltage output converter and a negative voltage output converter, and shares the same switches. The number of active components can be reduced. In addition, the circuit can achieve dual output voltage control with a single controller and PWM drive signal by appropriately designing the ratio of the number of windings of the coupling inductor. A regulated positive voltage output and negative voltage output can be achieved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reduced KPCA based Ensemble Learning Approach for Fault Diagnosis of Grid-Connected PV Systems 19

Reduced KPCA based Ensemble Learning Approach for Fault Diag...

引用

19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

作者： Dhibi, Khaled Mansouri, Majdi Bouzrara, Kais Nounou, Hazem Nounou, Mohamed Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir 5019 Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha23874 Qatar Department of Mathematics and Sciences Prince Sultan University Riyadh11586 Saudi Arabia Chemical Engineering Program Texas A&M University at Qatar Doha23874 Qatar

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

The main objective of this work is to develop novel fault diagnosis techniques using ensemble learning and multivariate statistical techniques. The proposed methods are capable of identifying and classifying PV faults. First, an ensemble learning (EL) method that combines several base models is proposed. Next, kernel principal components analysis (KPCA) and reduced KPCA are proposed to extract and select the pertinent characteristics from raw data. Then, the extracted significant characteristics are transmitted to the EL model for classification purposes. The main idea behind these proposals is to provide the best accuracy and also improve the results in terms of computation time. The diagno-sis results demonstrated the efficiency of the proposed frameworks. © 2022 IEEE.

关键词： Multivariant analysis

来源：评论

学校读者我要写书评

暂无评论

MathReader: Text-to-Speech for Mathematical Documents

arXiv

引用

arXiv 2025年

作者： Hyeon, Sieun Jung, Kyudan Kim, Nam-Joon Ryu, Hyun Gon Do, Jaeyoung Department of Electrical and Computer Engineering Seoul National University Korea Republic of Department of Mathematics Chung-Ang University Korea Republic of NVIDIA United States Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

TTS (Text-to-Speech) document reader from Microsoft, Adobe, Apple, and OpenAI have been serviced worldwide. They provide relatively good TTS results for general plain text, but sometimes skip contents or provide unsatisfactory results for mathematical expressions. This is because most modern academic papers are written in LaTeX, and when LaTeX formulas are compiled, they are rendered as distinctive text forms within the document. However, traditional TTS document readers output only the text as it is recognized, without considering the mathematical meaning of the formulas. To address this issue, we propose MathReader, which effectively integrates OCR, a fine-tuned T5 model, and TTS. MathReader demonstrated a lower Word Error Rate (WER) than existing TTS document readers, such as Microsoft Edge and Adobe Acrobat, when processing documents containing mathematical formulas. MathReader reduced the WER from 0.510 to 0.281 compared to Microsoft Edge, and from 0.617 to 0.281 compared to Adobe Acrobat. This will significantly contribute to alleviating the inconvenience faced by users who want to listen to documents, especially those who are visually impaired. The code is available at https://***/hyeonsieun/MathReader. Copyright © 2025, The Authors. All rights reserved.

关键词：

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：