检索结果-内蒙古大学图书馆

5th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2022

作者： Wang, Yan-Feng Cheng, Chen-Chiou Tsai, Jenn-Kai National Formosa University Department of Electronic Engineering Yunlin Taiwan National Formosa University Doctoral Degree Program in Smart Industry Technology Research and Development Yunlin Taiwan

ISBN: (数字)9781665479295

ISBN: (纸本)9781665479295

As one of the most important economic industries, how to improve the quality and output of the coffee industry is important. Defective coffee beans affect the flavor of coffee after roasting and grinding. In order to reduce the cost of labor and time, it is effective to use a convolutional neural network (CNN) model to identify defective green coffee beans. However, the complexity and huge parameters of the CNN model make the edge computing devices spend too much time on identification. Therefore, we introduced a lightweight deep learning network Slim-CNN to classify green coffee beans. Experiment results show that Slim-CNN achieves 92% accuracy with 6 times fewer parameters than MobileNet and 270 times fewer parameters than VGG16. The Slim-CNN model can be used on different edge computing devices to reduce labor costs in the coffee industry and improve the quality of coffee. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing the bishomolithocholic acid scaffold for selective sialyltransferase inhibition: A targeted approach to suppress breast cancer metastasis

引用

European Journal of Medicinal Chemistry 2025年 292卷 117674页

作者： Perez, Ser John Lynon P. Hsu, Zih-Fan Chang, Tzu-Ting Chen, Chia-Ling Li, Wen-Shan Institute of Chemistry Academia Sinica Taipei 115 Taiwan Department of Applied Chemistry National Yang Ming Chiao Tung University Hsinchu 300 Taiwan Sustainable Chemical Science and Technology Taiwan International Graduate Program Academia Sinica Taipei 115 Taiwan Biomedical Translation Research Center Academia Sinica Taipei 115 Taiwan Department of Chemistry National Taiwan Normal University Taipei 116 Taiwan Department of Medicinal and Applied Chemistry College of Life Science Kaohsiung Medical University Kaohsiung 807 Taiwan Ph.D. Program in Drug Discovery and Development Industry College of Pharmacy Taipei Medical University Taipei 110 Taiwan Doctoral Degree Program in Marine Biotechnology National Sun Yat-Sen University Kaohsiung 804 Taiwan

ST6GAL1 plays a crucial role in the progression of triple-negative breast cancer (TNBC), highlighting its potential as a therapeutic target for this aggressive cancer subtype. Due to the high metastatic potential of TNBC and the limitations of current therapies, selective and potent ST6GAL1 inhibitors are urgently needed. In this study, a scaffold-hopping approach from lithocholic acid to bishomolithocholic acid successfully led to the discovery of novel ST6GAL1 inhibitors, SPP-037 and HZF01, with enhanced biological activity and selectivity. Both compounds significantly inhibited MDA-MB-231 cell migration, HUVEC tube formation, tumor growth, and metastasis in vitro and in vivo. Molecular docking studies revealed key interactions between the ST inhibitors and ST6GAL1, supporting their enhanced selectivity and binding affinity. Additionally, SPP-037 and HZF01 were found to block integrin α2,6-sialylation, disrupting integrin activation and downstream signaling pathways involving the phosphorylation of focal adhesion kinase (FAK) and paxillin, which are critical for cell migration. These results underscore the potential of targeting ST6GAL1 to suppress tumor progression and metastasis, offering a promising avenue for treating aggressive breast cancer. © 2025 Elsevier Masson SAS

关键词： Bishomolithocholic acid Breast cancer metastasis Integrin-FAK-Paxillin axis N-glycan sialylation Sialyltransferase inhibitor ST6GAL1

来源：评论

学校读者我要写书评

暂无评论

A LoRaWAN Enabled Sensor-Based System for Detecting Rodent Activity 21

A LoRaWAN Enabled Sensor-Based System for Detecting Rodent A...

引用

21st International System-on-Chip Design Conference, ISOCC 2024

作者： Wang, Szu-Ting Wu, Shang-Sian Tseng, Kuo-Cheng Hsu, Li-Chuan Ke, Song-Min Lai, Shin-Chi National Formosa University The Doctoral Degree Program in Smart Industry Technology Research and Development Huwei Taiwan National Formosa University Dept. Automation Engineering Huwei Taiwan National Formosa University Dept. Automation Engineering & Smart Machinery Intelligent Manufacturing Research Center Huwei Taiwan

ISBN: (纸本)9798350377088

This study presents the design and implementation of a sensor-based system for detecting rodent activity. The proposed system utilizes infrared (IR) receivers for detecting rodent presence and can incorporate IP cameras to capture intruder images. Data collected by sensor nodes are transmitted to a database via Wi-Fi for web access. The system employs a reflective-type IR sensor comprising an emitter and a receiver aligned in the same direction to discern approaching or receding objects. Power-efficient operation is ensured through the use of the Heltec Wireless Stick Lite MCU and LoRa transceivers for data transmission. Results demonstrate the system's effectiveness in monitoring rodent behavior, with power consumption averaging 67.4mA to 69.5mA, supported by two 18650 batteries for up to 4 days of continuous operation. During the 18-day experiment duration, a total of 1,453 instances were recorded. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Design of a Multilingual Translation System with Personalized Voice Characteristics 21

Design of a Multilingual Translation System with Personalize...

引用

21st International System-on-Chip Design Conference, ISOCC 2024

作者： Chen, Chen-Hua Lai, Guan-Yu Lee, Chuan Wu, Chang-Yu Liu, Kuan-Lin Lai, Shin-Chi Doctoral Degree Program in Smart Industry Technology Research and Development Huwei Taiwan National Formosa University Dept. of Automation Engineering Huwei Taiwan National Yunlin University of Science and Technology Dept. Electronics Engineering Douliu Taiwan National Formosa University Dept. Automation Engineering Smart Machinery and Intelligent Manufacturing Research Center Huwei Taiwan

ISBN: (纸本)9798350377088

This study combines AI voice synthesis with IoT to create a real-time multilingual translation system. Front-end devices capture the speaker's voice, which is then played back in both original and translated forms, enabling consecutive interpreting. This system is ideal for multilingual scenarios. After digitization, audio signals undergo speech-to-text conversion, multilingual translation, and text-to-speech processing. Speech synthesis matches the speaker's voice characteristics, allowing listeners to hear the translation in the speaker's voice. Both voice-to-text conversion and translated audio playback use Wi-Fi for data transmission, facilitating future applications. In validation, the average translation and transmission time for each speech segment were 410 ms and 3.38 s, respectively. The synthesized voice similarity analysis achieved an accuracy of 88%, showcasing the method's potential for system integration and development. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Integrating Noise Classification and Speech Enhancement Model for Hearing Aids 21

Integrating Noise Classification and Speech Enhancement Mode...

引用

21st International System-on-Chip Design Conference, ISOCC 2024

作者： Hung, Ying-Hsiu Chang, Yen-Ching Lai, Shin-Chi Juang, Wen-Ho Sheu, Ming-Hwa Lee, Jeng-Dao National Yunlin University of Science and Technology Dept. Electronics Engineering Douliu Taiwan National Formosa University Doctoral Degree Program in Smart Industry Technology Research and Development Huwei Taiwan National Formosa University Dept. Automation Engineering Smart Machinery and Intelligent Manufacturing Research Center Huwei Taiwan National Formosa University Dept. Computer Science and Information Engineering Huwei Taiwan National Formosa University Dept. Automation Engineering Huwei Taiwan

ISBN: (纸本)9798350377088

As the global population ages, the number of elderly people needing hearing aids is increasing. This paper proposed an architecture designed to enhance speech based on noise conditions. After noise types are identified by a Convolutional Neural Network (CNN) noise classification model, these noise conditions are combined with the noisy speech and input into a conditional Generative Adversarial Network (cGAN) for speech enhancement. The CNN noise classification model achieves an average recognition accuracy of nearly 92%, with a Kappa value as high as 0.88. The cGAN speech enhancement achieves lower error values in the Mel-Cepstral Distortion (MCD) measure. Although some parts of the human voice may be filtered out, the results demonstrate the potential development of the proposed algorithm. © 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

A LoRaWAN Enabled Sensor-Based System for Detecting Rodent Activity

A LoRaWAN Enabled Sensor-Based System for Detecting Rodent A...

引用

International SoC Design Conference, ISOCC

作者： Szu-Ting Wang Shang-Sian Wu Kuo-Cheng Tseng Li-Chuan Hsu Song-Min Ke Shin-Chi Lai The Doctoral Degree Program in Smart Industry Technology Research and Development National Formosa University Huwei Taiwan Dept. Automation Engineering National Formosa University Huwei Taiwan Dept. Automation Engineering & Smart Machinery and Intelligent Manufacturing Research Center National Formosa University Huwei Taiwan

ISBN: (数字)9798350377088

ISBN: (纸本)9798350377095

关键词： Wireless communication Wireless sensor networks Rodents Receivers Cameras Transceivers IP networks Reliability Monitoring Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

Design of a Multilingual Translation System with Personalized Voice Characteristics

Design of a Multilingual Translation System with Personalize...

引用

International SoC Design Conference, ISOCC

作者： Chen-Hua Chen Guan-Yu Lai Chuan Lee Chang-Yu Wu Kuan-Lin Liu Shin-Chi Lai Doctoral Degree Program in Smart Industry Technology Research and Development Huwei Taiwan Dept. of Automation Engineering National Formosa University Huwei Taiwan Dept. Electronics Engineering National Yunlin University of Science and Technology Douliu Taiwan Dept. Automation Engineering & Smart Machinery and Intelligent Manufacturing Research Center National Formosa University Huwei Taiwan

ISBN: (数字)9798350377088

ISBN: (纸本)9798350377095

关键词： Accuracy System integration Real-time systems Text to speech Data communication Artificial intelligence Wireless fidelity Speech to text

来源：评论

学校读者我要写书评

暂无评论

Insect Classification Using Spatial Pyramid Pooling and Convolution Neural Network

Insect Classification Using Spatial Pyramid Pooling and Conv...

引用

IEEE Asia-Pacific Conference on Circuits and Systems

作者： Chang-Yu Wu Song-Min Ke Hoh-Siang Liao Chen-Hua Chen Ying-Hsiu Hung Shin-Chi Lai Department of Automation Engineering Master’s Program National Formosa University Huwei Taiwan Department of Automation Engineering National Formosa University Huwei Taiwan Doctoral Degree Program in Smart Industry Technology Research and Development National Formosa University Huwei Taiwan Dept. Automation Engineering & Smart Machinery and Intelligent Manufacturing Research Center National Formosa University Huwei Taiwan

ISBN: (数字)9798350378771

ISBN: (纸本)9798350378788

This study aims to enhance the accuracy and efficiency of insect classification using spatial pyramid pooling convolutional neural networks (SPP-CNN). Improving traditional convolutional neural networks has resulted in poor performance when dealing with the diversity of insects and images of various sizes. The dataset, provided by a collaborating company, includes six different insect categories. Given the relatively limited number of samples in the existing dataset, we employed various data augmentation techniques to enrich our training samples, such as sharpening, adding noise, resizing, adjusting brightness, and randomly rotating images. Experiments demonstrate that SPP-CNN shows superior performance in insect classification tasks compared to efficientNetV2. The proposed architecture has achieved an accuracy rate of $83.8 \%$, which is $3.9 \%$ higher than the $79.9 \%$ accuracy of EfficientNetV2 architectures. This improvement indicates that incorporating the spatial pyramid pooling layer significantly enhances the accuracy of insect image classification. Moreover, the adaptability of SPP-CNN to various image resolutions without the need for retraining significantly boosts its practicality for real-world applications.

关键词： Training Accuracy Image resolution Insects Noise Neural networks Data models Convolutional neural networks Integrated circuit modeling Image classification

来源：评论

学校读者我要写书评

暂无评论

Integrating Noise Classification and Speech Enhancement Model for Hearing Aids

Integrating Noise Classification and Speech Enhancement Mode...

引用

International SoC Design Conference, ISOCC

作者： Ying-Hsiu Hung Yen-Ching Chang Shin-Chi Lai Wen-Ho Juang Ming-Hwa Sheu Jeng-Dao Lee Dept. Electronics Engineering National Yunlin University of Science and Technology Douliu Taiwan Doctoral Degree Program in Smart Industry Technology Research and Development National Formosa University Huwei Taiwan Dept. Automation Engineering & Smart Machinery and Intelligent Manufacturing Research Center National Formosa University Huwei Taiwan Dept. Computer Science and Information Engineering National Formosa University Huwei Taiwan Dept. Automation Engineering National Formosa University Huwei Taiwan

ISBN: (数字)9798350377088

ISBN: (纸本)9798350377095

关键词： Accuracy Noise Noise reduction Speech recognition Speech enhancement Hearing aids Classification algorithms Convolutional neural networks Human voice Older adults

来源：评论

学校读者我要写书评

暂无评论

Biological Evaluation of Sulfonate and Sulfate Analogues of Lithocholic Acid: A Bioisosterism-Guided Approach Towards the Discovery of Potential Sialyltransferase Inhibitors for Antimetastatic Study

SSRN

引用

SSRN 2023年

作者： Perez, Ser John Lynon P. Chen, Chia-Ling Chang, Tzu-Ting Li, Wen-Shan Institute of Chemistry Academia Sinica Taipei115 Taiwan Department of Applied Chemistry National Yang Ming Chiao Tung University Hsinchu300 Taiwan Sustainable Chemical Science and Technology Taiwan International Graduate Program Academia Sinica Taipei115 Taiwan Biomedical Translation Research Center Academia Sinica Taipei115 Taiwan Department of Medicinal and Applied Chemistry College of Life Science Kaohsiung Medical University Kaohsiung807 Taiwan Ph.D. Program in Drug Discovery and Development Industry College of Pharmacy Taipei Medical University Taiwan Doctoral Degree Program in Marine Biotechnology National Sun Yat-Sen University Kaohsiung804 Taiwan Department of Chemistry College of Science Tamkang University New Taipei City251 Taiwan

The naturally occurring bile acid lithocholic acid (LCA) has been a crucial core structure for many non-sugar-containing sialyltranferase (ST) inhibitors documented in literature. With the aim of elucidating the impact of the terminal carboxyl acid substituent of LCA on its ST inhibition, in this present study, we report the (bio)isosteric replacement-based design and synthesis of sulfonate and sulfate analogues of LCA. Among these compounds, the sulfate analogue SPP-002 was found to selectively inhibit N-glycan sialylation by at least an order of magnitude, indicating a substantial improvement in both potency and selectivity when compared to the unmodified parent bile acid. Molecular docking analysis supported the stronger binding of the synthetic analogue in the enzyme active site. Treatment with SPP-002 also hampered the migration, adhesion, and invasion of MDA-MB-231 cells in vitro by suppressing the expression of signaling proteins involved in the cancer metastasis-associated FAK/paxillin pathway. In totality, these findings offer not only a novel structural scaffold but also valuable insights for the future development of more potent and selective ST inhibitors with potential therapeutic effects against tumor cancer metastasis. © 2023, The Authors. All rights reserved.

关键词： Sulfur compounds

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：