检索结果-内蒙古大学图书馆

2024 International Conference on Precision engineering and Mechanical Manufacturing, PEMM 2024

作者： Shiau, Yau-Ren Fang, Jiunn Huang, Yuan-Chi Department of Industrial Engineering and Systems Management Feng Chia University Taichung407 Taiwan Department of Aerospace and Systems Engineering Feng Chia University Taichung407 Taiwan Ph.D. Program of Mechanical and Aeronautical Engineering Feng Chia University Taichung407 Taiwan

ISBN: (纸本)9781510683129

Impellers are extensively employed across various industrial sectors and in different industrial systems, such as ducted-fan modules. The configuration of ducted-fan modules can be optimized to achieve high impeller performance, safe and stable operation, and high operational efficiency. This study designed two ducted-fan modules with axial impellers composed of airfoil cascades by using the Fan Calculator software program to analyze their performance and efficiency. The study discovered that the module efficiency varied with the internal impeller diameter, external impeller diameter, and rotational speed. An increase in the outlet angle of the blade tip caused increases in the power generated by, pressure change produced in, and flow rate of the modules, thereby enhancing fan efficiency and module performance. The study makes two contributions. First, it constructed two ducted-fan modules with axial impellers by using the duct to isolate the blades, thus increasing the safety and stability of the fan. Second, it explored the performance and efficiency of impellers with airfoil cascades to enhance fan efficiency and optimize the design of a ducted-fan module. © 2024 SPIE.

关键词： ducted fan engines

来源：评论

学校读者我要写书评

暂无评论

Eff-SAM: SAM-based Efficient Method for Brain Tumor Segmentation in Multimodal 3d MRI Scans

引用

IEEE Access 2025年 13卷 90063-90087页

作者： Ahmad, Nisar Chen, Yao-Tien Ming Chi University of Technology International Ph.D. Program in Innovative Technology of Biomedical Engineering Medical Devices New Taipei City243303 Taiwan

Accurate brain tumor segmentation in MRI scans is crucial for effective diagnosis and treatment planning, as even minor segmentation errors can lead to significant clinical concerns. However, this task is challenged by the complex anatomy of the brain, variable tumor shapes, and low contrast between tumor sub-regions. Moreover, existing methods often lack generalizability across diverse segmentation tasks and imaging modalities. Large Vision Model (LVM) like the Segment Anything Model (SAM) represents a foundational advancement in tumor segmentation. While SAM has shown impressive performance on natural images, its effectiveness in medical imaging, especially brain tumor segmentation, is limited due to domain differences and indistinct boundaries in MRI scans. To address these challenges, we propose Eff-SAM, a 3d brain tumor segmentation framework that adapts SAM for medical applications through Parameter-Efficient Fine-Tuning (PEFT) technique. The framework incorporates PEFT with adapters into SAM’s encoder to fine-tune the model effectively and optimize its performance for medical imaging while maintaining computational efficiency. Additionally, a Cross-Sliced Attention (CSA) mechanism captures semantic relationships, improves tumor localization, and is introduced into the encoder. Robust data preprocessing further enhances the model’s generalization across datasets. Eff-SAM demonstrates state-of-the-art performance and outperforms benchmark methods on the BraTS 2020 and BraTS 2021 datasets. It achieves dice scores of 0.884 for Whole Tumor (WT), 0.853 for Tumor Core (TC), and 0.818 for Enhancing Tumor (ET) on the BraTS 2020 dataset, and 0.880 (WT), 0.861 (TC), and 0.821 (ET) on the BraTS 2021 dataset. This work highlights the potential of integrating vision models like SAM with lightweight, domain-specific modules to deliver accurate and efficient brain tumor segmentation offering a clinically valuable tool, especially in scenarios with limited data and complex tu

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Meal Image Recognition and Healthy Meal Combination Recommendation System Integrated with Generative Artificial Intelligence 6

Meal Image Recognition and Healthy Meal Combination Recommen...

引用

6th IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Chang, Chin-Chih Wei, Chi-Hung Hsiao, Sean Yang, Chyuan-Huei Thomas Chung Hua University Department of Computer Science and Information Engineering Hsinchu Taiwan Chung Hua University Ph.D. Program in Engineering Science Hsinchu Taiwan Chung Hua University Program in Applied Foreign Language and Smart Commerce Hsinchu Taiwan School of Information Engineering Shandong Vocational and Technical University of International Studies Shandong China

ISBN: (纸本)9798350396133

People increasingly prioritize a balanced diet to enhance well-being, yet making informed dietary choices remains challenging amidst the abundance of options. To address this, we developed a meal image recognition and healthy meal combination recommender system, integrating generative artificial intelligence (AI). Convolutional neural networks were used for precise meal image recognition to identify diverse food items. The generative AI-augmented recommendation engine offers personalized meal suggestions aligned with nutritional goals and dietary preferences, utilizing a nutrition knowledge base to ensure overall well-being. The system's feasibility was validated, illustrating its excellence in meal recognition accuracy, recommendation diversity, and user engagement. By integrating generative AI, the system shows its potential to enhance dietary recommendations and public health. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Visual Field Examination Technology Based on Semi-transparent Elliptical Mirror 6

Visual Field Examination Technology Based on Semi-transparen...

引用

6th IEEE Eurasian Conference on Educational Innovation, ECEI 2023

作者： Chang, Chao-Kai Chiang, Chun-Yu Yeh, Feng-Ming Lee, Chi-Hung Tien, Chuen-Lin Chen, der-Chin Department of Optometry Yuanpei University of Medical Technology Hsinchu Taiwan Ph.D. Program of Electrical and Communications Engineering Feng Chia University Taichung Taiwan Department of Electrical Engineering Feng Chia University Taichung Taiwan

ISBN: (纸本)9798350334289

In this study, the human visual field test technology is established by using an optoelectrical system consisting of a translucent ellipsoid, an area light source, and a landscape scene with an indicator. during the test, the subjects stared at the indicator directly in front of them with one eye and kept their eyeballs still, scanning the light strip with peripheral vision and using the mouse button plus the playback program to record the start and end positions of the scanning light strip in the landscape scene. This method is tested subjectively, and the subject needs to respond during the test. Therefore, before the test, the subject needs to understand the test process and be trained in advance to improve the exam accuracy. In the experiment, fifteen subjects with normal vision and no eye disease were selected. Their visual fields were confirmed normal after a preliminary assessment. The test results showed that the subjects' eyes were within the normal visual field, indicating that this method was feasible. In this research, a digital optical platform for the near visual field is proposed to establish an optoelectric visual field measurement technology. The proposed method is characterized by small size, rapid operation, and easy portability. With the digital LCd and visual imaging technology, both dynamic and static visual fields can be tested. The test data on the eyes' upper, lower, nasal, and temporal sides were consistent with the normal visual field. This shows that this method is feasible and worthy of promotion in the optometry industry. © 2023 IEEE.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

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

Application of a Self-Assembly Sensing Layer to Grating Sensor Cabinets for Biomedical Sensing of Rheumatoid Arthritis Antigen-Antibodies

引用

IEEE Sensors Journal 2024年第7期24卷 10039-10047页

作者： Wen, Hsin-Yi Hsu, Hsiang-Cheng Feng, Wen-Kai Jhan, Kai-Siang Yeh, Yao-Tsung Chiang, Chia-Chin National Kaohsiung University of Science and Technology Department of Chemical and Materials Engineering Kaohsiung80778 Taiwan National Kaohsiung University of Science and Technology College of Maritime Department of Ph.D. Program in Maritime Science and Technology Kaohsiung807618 Taiwan National Kaohsiung University of Science and Technology Department of Mechanical Engineering Kaohsiung80778 Taiwan Fooyin University Department of Medical Laboratory Science and Biotechnology Kaohsiung83102 Taiwan

In this article, we harnessed biomedical applications in laser-assisted etching long-period fiber gratings (LLPFGs) sensors, subsequently deploying them within the realm of biomedical applications. The primary aim of this study was to devise a sensitive method for the detection of antigen-antibodies associated with rheumatoid arthritis (RA) using LLPFGs. Sensing the antigen binding took place on the surface of the optical fiber through a self-assembling process. Given the inherent limitations of conventional rheumatoid factor (RF) testing in terms of specificity, we introduced an innovative serum-based approach geared toward the identification of anti-cyclic citrullinated peptide (Anti-CCP) antibodies. This method exhibited an impressive diagnostic accuracy rate of approximately 80% for RA cases, coupled with an exceptional specificity level of 98% for individuals without RA. The incorporation of LLPFGs in the detection of RA antigen-antibodies presents a highly promising avenue for enhancing the precision and reliability of RA diagnosis. Furthermore, this research aligns closely with the United Nations Sustainable development Goal (SdG)3, which strives to promote well-being across all age groups and advance sustainable development by addressing health-related challenges, including the accurate diagnosis of diseases like RA. © 2023 IEEE.

关键词： Antibodies

来源：评论

学校读者我要写书评

暂无评论

An Anti-Plasma Etching Film of Y2O3 Film 10

An Anti-Plasma Etching Film of Y2O3 Film

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Wei, Chia-Chih Chen, Hsuan-Jung Lee, Yi-Mu Chang, Shao-Fu Chen, Chien-Chon College of Engineering and Science Ph.D. Program in Materials and Chemical Engineering National United University Miaoli Taiwan Michigan State University Department of Chemistry MI48824 United States National United University Department of Electronic Miaoli Taiwan National United University Department of Energy Engineering Miaoli Taiwan

ISBN: (纸本)9798350394924

In this paper, we have presented our experiment results including (a) use a slowly thermal spray process deposition an yttrium oxide (Y2O3) film with thickness of $200\ \mu\mathrm{m}$ on the aluminum alloy (AA6061). The image analysis showed that the porosity of Y2O3 film can be reduced to less than 2%. The further aerosol deposition can be used filling the pores and can reduce the porosity of the film to less than 0.5%. This low-porosity Y2O3 film will be able to meet the increasingly stringent requirements for surface coating protection of semiconductor vacuum chamber. (b) Compared the corrosion characterization in 3.5 wt. % NaCl solution between naked AA6061 and AA6061 with Y2O3 coating, a high corrosion reactivity ($\mathrm{I}_{\text{corr}}=10^{-3.3}\mathrm{A}/\text{cm}^{2}$) of naked AA6061 then AA6061 with Y2O3 coating ($\mathrm{I}_{\text{corr}}=10^{-5.8}\mathrm{A}/\text{cm}^{2}$). The corrosion reactivity of AA6061 with Y2O3 is reduced by 316 times to a naked AA6061. © 2024 IEEE.

关键词： Porosity

来源：评论

学校读者我要写书评

暂无评论

A Fitness Movement Evaluation System Using deep Learning 15

A Fitness Movement Evaluation System Using Deep Learning

引用

15th International Conference on Knowledge and Systems engineering, KSE 2023

作者： Chang, Chin-Chih Wei, Chi-Hung Wu, Hao-Wei Hsiao, Sean Chung Hua University Department of Computer Science and Information Engineering Hsinchu City Taiwan Ph.D. Program in Engineering Science Chung Hua University Hsinchu City Taiwan Bachelor Program in Applied Foreign Language and Smart Commerce Chung Hua University Hsinchu City Taiwan

ISBN: (纸本)9798350329742

This paper proposes a fitness movement evaluation system using deep learning. The system uses a deep convolutional neural network (CNN) to extract features from pictures of fitness movements. The features are then used to classify the movements into different categories. The system is evaluated on a dataset of pictures of fitness movements. The results show that the system can accurately classify the movements into different categories. The system is designed to provide feedback to users on their fitness movements. The proposed system is a valuable tool for fitness enthusiasts. The main contribution of this paper is to propose a way to give users a score for their fitness movement. It can help users improve their fitness and track their progress over time. The system is also a valuable tool for fitness professionals. It can help professionals develop new fitness programs and provide feedback to their clients. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Improvement of A Lightweight NFC Authentication Algorithm Based on Modified Hash Function 14

An Improvement of A Lightweight NFC Authentication Algorithm...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Hwang, Min-Shiang Li, Hou-Wen Yang, Cheng-Ying Asia University Department of Computer Science and Information Engineering Taichung354 Taiwan Asia University The Ph.D. Program in Artificial Intelligence Taichung354 Taiwan University of Taipei Department of Computer Science Taipei Taiwan

ISBN: (纸本)9798350313277

In NFC applications, user privacy information must be protected first. Cao and Liu recently proposed a lightweight NFC authentication scheme based on an improved hash function to ensure that the user's private information will not be leaked. Although their method is highly efficient and has Mutual Authentication, Forward Security, Backward Security, and security against attacks such as Replay, Location, and Fake, once out of synchronization occurs, the method must reestablish synchronization data. Therefore, this article will propose a lightweight synchronization method. © 2023 IEEE.

关键词： authentication algorithm hash function near field communication privacy

来源：评论

学校读者我要写书评

暂无评论

PEMF device with Bipolar Pulse Waves Based on Single Chip Computer 8

PEMF Device with Bipolar Pulse Waves Based on Single Chip Co...

引用

2022 8th International Conference on Mechanical engineering, Materials and Automation Technology, MMEAT 2022

作者： Tai, Au-Zou Fang, Jiunn Ph.D. Program of Mechanical and Aeronautical Engineering Feng Chia University Taichung40724 Taiwan Department of Aerospace and Engineering Feng Chia University Taichung City Taiwan

PEMF therapy, a non-invasive technology, is frequently reported in medical journals. It can send electric and magnetic fields to the body through induction coils [1,2], so as to provoke cells to stimulate nerves and muscles. Based on performances of large PEMF equipment on the market, on average, the low frequency emitted by most PEMF equipment is 0-300HZ An appropriate single chip is selected to make an extremely low frequency 0-30HZ that can be easily developed and easily changed. And has bipolar pulse wave so that simple equipment can also get enough effect. © Published under licence by IOP Publishing Ltd.

关键词： Condensed matter physics

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：