检索结果-内蒙古大学图书馆

deep Learning-Based Positioning Error Fault diagnosis of Wire Bonding Equipment and an Empirical Study for IC Packaging

引用

IEEE Transactions on Semiconductor Manufacturing 2023年第4期36卷 619-628页

作者： Kao, Sheng-Xiang Chien, Chen-Fu International Intercollegiate Ph.D. Program National Tsing Hua University Hsinchu30013 Taiwan Intelligent Manufacturing and Circular Economy Research Center National Tsing Hua University Artificial Intelligence for Intelligent Manufacturing Systems Research Center National Science and Technology Council Department of Industrial Engineering and Engineering Management Hsinchu300044 Taiwan

Little research has been done for artificial intelligence applications of semiconductor backend. This study aims to develop a deep learning based fault diagnosis framework as prognostics and health management (phM) solutions with a comprehensive analytics process. A linear encoder sensor is employed to measure position, while data preparation is conducted to convert position information into a signal. Then, signal processing is used to extract the features, in which high pass filter is applied to normalize the signal and emphasize the features. High-dimensional features including time domain statistical features, time-frequency domain features obtained by continuous wavelet transform (CWT), and frequency domain features converted by fast Fourier transform (FFT) are extracted to prepare the dataset. An ensemble neural network model that integrates deep neural network (dNN) and convolutional neural network (CNN) is employed to recognize the pattern and diagnose the positioning errors. The accuracy and false alarm rate are considered to support maintenance decisions. An empirical study was conducted in a world leading IC assembly and testing company for validation. The results have shown that the proposed approach can effectively detect inappropriate installation of the bond head in wire bonding equipment for predictive maintenance and cost reduction. © 1988-2012 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Enhanced deep Learning Model Performance in 3d Multimodal Brain Tumor Segmentation with Gabor Filter

Enhanced Deep Learning Model Performance in 3D Multimodal Br...

引用

International Conference on Applied System Innovation (ICASI)

作者： Nisar Ahmad Yao-Tien Chen International Ph.D. Program in Innovative Technology of Biomedical Engineering and Medical Devices Ming Chi University of Technology New Taipei City Taiwan

ISBN: (数字)9798350394924

ISBN: (纸本)9798350394931

Medical image segmentation plays a crucial role in identifying and analyzing anatomical structures in medical images. This requires an accurate medical segmentation tool to delineate and quantitatively analyze the target regions, diagnose any abnormality, and assist in treatment planning. deep learning approaches have emerged as a promising solution for automating medical segmentation. However, challenges arise when dealing with the complex shapes and spatial variations of some target regions, especially in 3d MRI scans. To deal with such transformations, specific techniques are required to properly analyze and preprocess the dataset and perform image filtering to provide better features for improved prediction performance of deep learning architectures. This study focuses on improving brain tumor segmentation in multimodal 3d MRI images. We observed significant improvements in multimodal brain tumor segmentation results (accuracy, IoU, and mIoU) using an optimized 3d Gabor filter, which helps extract meaningful features. Multichannel input images were preprocessed to remove noise and select an appropriate resolution to reduce computational complexity. An improvement in mean Intersection over Union (mIoU) from 0.714 to 0.804 and accuracy from 0.982 to 0.991 were achieved, which shows a major improvement. This work contributes to the field of medical image segmentation by offering an improved and efficient approach for brain tumor analysis in 3d MRI scans, potentially aiding in diagnosis and treatment planning.

关键词： deep learning Image segmentation Solid modeling Three-dimensional displays Magnetic resonance imaging Feature extraction Planning

来源：评论

学校读者我要写书评

暂无评论

3d Brain Tumor Segmentation in Multimodal MRI Images

3D Brain Tumor Segmentation in Multimodal MRI Images

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Nisar Ahmad Yao-Tien Chen International Ph.D. Program in Innovative Technology of Biomedical Engineering and Medical Devices Ming Chi University of Technology New Taipei City Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

In brain tumor research, the use of machine learning based methods using MRI data to locate brain tumors accurately has significantly increased and new techniques are proposed to facilitate the medical experts. There is still room for improvement as tumors have complex anatomy which requires efforts to explore further and propose new deep learning based solutions. In this research, we propose 3d UNet based multimodal brain tumor segmentation for Non Enhancing Tumor (NET), Peritumoral Edema (PE), and Enhancing Tumor (ET). data preprocessing and augmentation techniques are employed to optimise the model's performance. The dataset used in this study to train, validate, and test the model performance is the BraTS 2020 dataset. The model achieved improved accuracy and IoU after implementing the mentioned techniques. Results before and after data augmentation demonstrate a significant enhancement in model performance. The model achieved an improved mIoU of 0.77 and accuracies of 98.21% and 99.36% for actual data and augmented data for three brain tumor classes, i.e., NET, PE, and ET. Our model performed multiclass brain tumor segmentation with high accuracies, and we aim to enhance this study to propose a valuable medical assistance model.

关键词： Solid modeling Image segmentation Three-dimensional displays Accuracy Magnetic resonance imaging Brain modeling data augmentation

来源：评论

学校读者我要写书评

暂无评论

A Survey on the Risk Perception of Slips, Trips, and Falls of Coal Mine Workers in China 2021

A Survey on the Risk Perception of Slips, Trips, and Falls o...

引用

3rd International Conference on Management Science and Industrial Engineering, MSIE 2021

作者： Khaday, Samsiya Li, Kai Way Li, Nailiang Chen, Yunxiu Ph.D. Program of Technology Management Chung Hua University Hsin-Chu Taiwan

ISBN: (纸本)9781450388887

Coal mine industry has been one of the most risky industries in terms of occupational safety and health in China. Slip, trip, and fall (STF) has been one of the most common occupational accidents globally which can lead to fatal and non-fatal accidents. This study investigated coal mine worker risk perception of occupational STF hazard. A survey was administered on 300 coal mine workers. The results showed that the age group has significant effect. The perceived risk of STF on the ramp and on the track were high. Rail track lanes on the roadway had the highest risk ratings. Moreover, underground crossing tracks and ramps were locations with frequent accidents. Workers' perception of the risky locations underground provides targets for safety promotions for coal mine authorities. © 2021 ACM.

关键词： Coal mines

来源：评论

学校读者我要写书评

暂无评论

Faster Groebner bases for Lie derivatives of OdE systems via monomial orderings 49

Faster Groebner bases for Lie derivatives of ODE systems via...

引用

49th International Symposium on Symbolic and Algebraic Computation, ISSAC 2024

作者： Bessonov, Mariya Ilmer, Ilia Konstantinova, Tatiana Ovchinnikov, Alexey Pogudin, Gleb Soto, Pedro Department of Mathematics Cuny Nyc College of Technology New YorkNY United States Ph.D. Program in Computer Science Cuny Graduate Center New YorkNY United States Department of Mathematics Cuny Queens College New YorkNY United States Department of Mathematics Cuny Queens College United States Ph.D. Programs in Mathematics and Computer Science Cuny Graduate Center New YorkNY United States Lix Cnrs École Polytechnique Institute Polytechnique de Paris Paris France

ISBN: (纸本)9798400706967

Symbolic computation for systems of differential equations is often computationally expensive. Many practical differential models have a form of polynomial or rational OdE system with specified outputs. A basic symbolic approach to analyze these models is to compute and then symbolically process the polynomial system obtained by sufficiently many Lie derivatives of the output functions with respect to the vector field given by the OdE system. In this paper, we present a method for speeding up Gröbner basis computation for such a class of polynomial systems by using specific monomial ordering, including weights for the variables, coming from the structure of the OdE model. We provide empirical results that show improvement across different symbolic computing frameworks and apply the method to speed up structural identifiability analysis of OdE models. © 2024 ACM.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Properties of the mixing layer height retrieved from ceilometer measurements in Slovakia and its relationship to the air pollutant concentrations

引用

Environmental Science and Pollution Research 2023年第54期30卷 115666-115682页

作者： Nguyen, duy-Hieu Štefánik, dušan Šedivá, Tereza Lin, Chitsan Ph.D. Program in Maritime Science and Technology College of Maritime National Kaohsiung University of Science and Technology Kaohsiung811213 Taiwan Slovak Hydrometeorological Institute Jeséniova 17 Bratislava833 15 Slovakia Faculty of Mathematics Physics and Informatics Comenius University in Bratislava Mlynská Dolina F1 Bratislava842 48 Slovakia Department of Marine Environmental Engineering National Kaohsiung University of Science and Technology Kaohsiung811213 Taiwan

Mixing layer height (MLH) is an important meteorological parameter for air quality since it significantly affects ground-level pollution in the atmosphere. This study examined the properties of the MLH on diurnal and seasonal timescales over a 3-year period (2020–2022) using high temporal resolution measurements from eight Vaisala CL31 ceilometers situated around Slovakia. Hourly averaged MLH data was retrieved from the BL-View software using merged method. The highest daily maxima for the MLH occurred mostly in summer and spring, while the lowest values occurred predominantly during winter and autumn. The average MLH daily maximum in summer was 2229 m, and just 859 m in winter. during summer, the spatial distribution of the MLH daily maxima was more uniform compared to winter, when the air masses within the individual valleys did not mix well. Correlations between ground-level pollutant concentrations and hourly mean/daily mean MLH were analyzed. The highest correlation, R≈0.6, was found for O3. For PM10, PM2.5, and NOx, the anticorrelations with MLH were found with maximum in winter (R ≈ − 0.3 for hourly data and R ≈ − 0.5 for daily mean data) but no relation in summer. Lastly, the ceilometer MLH was compared to the radiosonde retrieved MLH for various cloud covers. Our analysis is based on an extensive set of empirical data, which can improve the accuracy and effectiveness of meteorological and atmospheric chemistry models. The findings can support air pollution forecasting and warning systems, providing valuable insights for policymakers and researchers. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Students Learning Performance and Engagement in a Visual programming Environment

Students Learning Performance and Engagement in a Visual Pro...

引用

Proceedings of the 6th International Conference on Innovative Technologies and Learning, ICITL 2023

作者： Wen, Fu-Hsiang Wu, Tienhua Hsu, Wei-Chih Ph.D. Program in Engineering Science and Technology College of Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Management Air Force Institute of Technology Kaohsiung Taiwan Department of Computer and Communication Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan

ISBN: (纸本)9783031401121

This study employed a quasi-experimental method to explore differences in students’ learning performance and engagement between visual and textual language programming environments. Specifically, this study examined how strongly engagement dimensions affect participants’ learning achievement in a Scratch experimental setting. One hundred and thirty-two undergraduate students participated. The results revealed that participants with Scratch intervention outperformed those with text-based language instructions in terms of performance and behavioral, emotional, cognitive, and agentic engagement. The findings indicated that engagement significantly predicted student academic success in a visual learning environment. This study concluded that visual programming tools such as Scratch help novices engaged and effectively learn core aspects of programming concepts. Additionally, student engagement deepens an understanding of predictions of programmers’ behaviors and achievements and mechanisms behind the effectiveness of visualization intervention. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enhanced Thermoelectric Performance of Mg-Sn Thin Films: Role of Mg9Sn5 phase and One-dimensional Electronic Structure

引用

ACS Applied Materials and Interfaces 2024年第3期16卷 3520-3531页

作者： Chen, Cheng-Lung Chen, Sheng-Chi Chou, Ching-Lin Wang, Te-Hsien Chuang, Min-Chen Tang, Bo-Chen Chen, Yang-Yuan Bachelor Program in Semiconductor Materials and Fabrication Ming Chi University of Technology New Taipei City243 Taiwan Department of Materials Engineering and Center for Plasma and Thin Film Technologies Ming Chi University of Technology New Taipei City243 Taiwan College of Engineering and Center for Green Technology Chang Gung University Taoyuan333 Taiwan Department of Physics National Chung Hsing University Taichung40227 Taiwan Institute of Physics Academia Sinica Taipei115 Taiwan International Ph.D. Program in Plasma and Thin Film Technology Department of Materials Engineering and Center for Plasma and Thin Film Technologies Ming Chi University of Technology New Taipei City243 Taiwan

Mg-Sn alloy thin films have garnered significant attention for their outstanding thermoelectric (TE) properties and cost-effective elemental composition, making them potential candidates for wearable energy harvesting devices. While previous studies have explored the properties of these thin films, limited research has been conducted to identify physical factors that can further enhance their performance. In this study, we present a novel approach utilizing a convenient electron beam coevaporation technique to fabricate Mg-Sn alloy thin films. Experimental results revealed that controlling the tin content in the Mg-Sn thin films at 38.9% led to the formation of a mixed-phase structure, comprising Mg2Sn and Mg9Sn5. This dual-phase structure exhibited a notable advantage in enhancing the TE performance. The presence of the Mg9Sn5 phase significantly increased the carrier concentration, while maintaining the original Seebeck coefficient and mobility, thereby improving the conductivity of Mg2Sn. Theoretical calculations indicated that the Mg9Sn5 phase displayed 1d-like characteristics, leading to a highly effective valley degeneracy and consequently a high power factor. Overall, this work introduces a promising approach to fabricate high-performance Mg-Sn alloy thin films through electron beam coevaporation, opening up possibilities for their application in wearable energy harvesting devices. © 2024 American Chemical Society.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

TiO2 Hole Transport Layer Incorporated in a Thermally Evaporated Sb2Se3 photoelectrode Exhibiting Low Onset Potential for photoelectrochemical Applications

引用

Energy and Fuels 2024年第17期38卷 16936-16948页

作者： Xavier, Thatheyus Peter Piraviperumal, Malar Kuo, Chih-Yu Govindasamy, Mani Thinfilm Photovoltaics Laboratory Department of Physics and Nanotechnology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Chemical Engineering & Biotechnology National Taipei University of Technology Taipei City10608 Taiwan Research Center for Intelligence Medical Devices Ming Chi University of Technology New Taipei City243303 Taiwan Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Taipei10608 Taiwan International Ph.D. Program in Innovative Technology of Biomedical Engineering and Medical Devices Ming Chi University of Technology New Taipei City243303 Taiwan

developing cost-effective photoelectrodes with a low band gap in the NIR-visible regions remains a challenge to achieve effective hydrogen production. We report the details of superstrate-configured photocathodes, consisting of antimony selenide (Sb2Se3) light absorbing layers with titanium dioxide (TiO2) as a hole transport layer, exhibiting the capability for hydrogen evolution with broad range light absorption enabled by the low band gap value of ∼1.2 eV of Sb2Se3. Strong anisotropy is a significant characteristic property of Sb2Se3, allowing superior electrical transportation along the [hkl] crystallographic orientation, which is obtained via close space evaporation of presynthesized bulk material at a growth temperature of 250 °C, over the solution-processed TiO2 film on a fluorine-doped tin oxide (FTO) substrate. The superstrate-configured FTO/TiO2/Sb2Se3 photocathode exhibited a photocurrent density of 100 μA cm-2 at −0.3 V vs RHE in 0.5 M H2SO4 under 1 sun illumination. To further improve photocurrent density, Pt as a cocatalyst was deposited over Sb2Se3 that led to enhanced photocurrent to 3 mA cm-2 at −0.3 V vs RHE in 0.5 M H2SO4 under 1 sun illumination. despite the relatively lower photocurrent observed, which resulted due to a large conduction band offset (ΔECB = 0.99 eV) of the TiO2/Sb2Se3 interface in a superstrate configuration, a significantly lower onset potential of −0.1 V vs RHE was observed. The results are encouraging due to the low band gap of Sb2Se3, photocorrosion stability, and straightforward fabrication, which is expected to assist for significant outcomes. © 2024 American Chemical Society.

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Innovation in Geriatric Care: An AI Assistant with LLM Integration Based on Health Guidelines

Innovation in Geriatric Care: An AI Assistant with LLM Integ...

引用

18th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Basulo-Ribeiro, Juliana Matos, Nádia C. G. Araujo, Sabrina Magalhães Capela, Nuno Bischoff, Francisco Teixeira, Leonor Cruz-Correia, Ricardo University of Aveiro Aveiro Portugal Faculty of Medicine University of Porto Porto Portugal Faculty of Medicine of the University of Porto Health Data Science Ph.D. Program Porto Portugal CINTESIS - Center for Health Technology and Services Research Faculty of Medicine University of Porto Porto Portugal VirtualCare Portugal

With the advance of artificial intelligence and natural language processing technology, a new tool is standing out in the field of understanding and generating natural language in a sophisticated way: the Large Language Model (LLM). According to several authors, LLMs can be used for various types of medical cases, providing access to different sources of information, and have opened up countless opportunities in the healthcare sector. This work aims to share the lessons learned during the process of developing an LLM-based assistant aimed at specific pathologies that are more prevalent in the elderly in order to support caregivers, whether they are private individuals, home care organizations, nursing homes or others. This study has a significant potential impact on the community by providing access to detailed information on developing an LLM-based assistant. © 2025 by SCITEPRESS – Science and technology Publications, Lda.

关键词： Electronic health record

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：