检索结果-内蒙古大学图书馆

Acupuncture State Detection at Zusanli (ST-36) Based on Scalp EEG and Transformer

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4023-4034页

作者： Wenhao Rao Meiyan Xu Haochen Wang Weicheng Hua Jiayang Guo Yongheng Zhang Haibin Zhu Ziqiu Zhou Jiawei Xiong Jianbin Zhang Yijie Pan Peipei Gu Duo Chen School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Department of Computer Science and the Institute of Human Factors Engineering Minnan Normal University Zhangzhou China National Institute for Data Science in Health and Medicine Xiamen University Xiamen China China Mobile Group Jiangsu Company Ltd Sihong Branch Suqian China Second Affiliated Hospital of Nanjing University of Chinese Medicine Nanjing University of Chinese Medicine Nanjing China Department of Computer Science and Technology Tsinghua University Beijing China Eastern Institute for Advanced Study Eastern Institute of Technology Ningbo China College of Software Engineering Zhengzhou University of Light Industry Zhengzhou China

In clinical acupuncture practice, needle twirling (NT) and needle retention (NR) are strategically combined to achieve different therapeutic effects, highlighting the importance of distinguishing between different acupuncture states. Scalp EEG has been proven significantly relevant to brain activity and acupuncture stimulation. In this work, we designed an acupuncture paradigm to collect scalp EEG to study the differences in EEG changes during different acupuncture states. Since deep learning (DL) has been increasingly used in EEG analysis, we propose the Acupuncture Transformer Detector (ATD), a model based on Convolutional Neural Networks (CNN) and Transformer technology. ATD encapsulates the local and global features of EEG under the acupuncture states of Zusanli acupoint (ST-36) in an end-to-end classification framework. The experiment results from 28 healthy participants show that the proposed model can efficiently classify the EEG in different states, with an accuracy of $85.47\pm 0.73\%$ . In this study, time-frequency analysis revealed that power changes were mainly confined to the delta frequency band under different acupuncture states. Brain topography revealed that ST-36 was activated primarily on the left frontal and parieto-occipital areas. This method provides new ideas for automatic recognition of acupuncture status from the perspective of DL, offering new solutions for standardizing acupuncture procedures.

关键词： Acupuncture Electroencephalography Transformers Convolutional neural networks Needles Brain modeling Medical diagnostic imaging Training Temperature measurement Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Value Stream Mapping for Smart Pharmaceutical Management in a Thai Hospital

引用

Procedia computer science 2025年 253卷 495-504页

作者： Ganda Boonsothonsatit Rardchawadee Silapunt Supachai Vongbunyong Kamol Kaemarungsi Wirachchaya Chanpuypetch Nilubon Chonsawat Graduate School of Management and Innovation King Mongkut’s University of technology Thonburi Thailand Electronic and Telecommunication Engineering King Mongkut’s University of Technology Thonburi Thailand Hospital Automation Research Center Institute of Field Robotics King Mongkut’s University of Technology Thonburi Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Thailand Faculty of Agro-Industry Chiang Mai University Thailand Department of Agricultural Economy and Developement Faculty of Agriculture Chiang Mai University Thailand

The evolution of healthcare systems worldwide necessitates continual improvement in hospital management practices, particularly pharmaceutical management. This paper explores transforming traditional pharmaceutical management systems in large and medium-sized hospitals in Thailand into smart systems using Value Stream Mapping (VSM) as a guiding tool. Traditional systems often face challenges such as inefficiencies and medication errors. VSM, rooted in lean management principles, offers a structured approach to visualize and optimize processes. Additionally, smart technologies like automated inventory systems and electronic health records enhance pharmaceutical management effectiveness. Through a comprehensive research methodology encompassing case studies, data collection, and VSM analysis, this study identifies inefficiencies and proposes evidence-based strategies for improvement. Results from a case study highlight the benefits of VSM implementation in enhancing pharmacy operations, emphasizing improved patient care and operational efficiency. The implementation of a smart medication dispensing system shows promising results in reducing workload and accommodating increased patient arrivals. Continued evaluation and refinement are crucial for maximizing benefits and addressing emerging challenges effectively.

关键词： lean management smart medication dispensing smart pharmaceutical smart technologies Value Stream Mapping

来源：评论

学校读者我要写书评

暂无评论

GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-Distribution Generalization Perspective

arXiv

引用

arXiv 2022年

作者： Yang, Linyi Zhang, Shuibai Qin, Libo Li, Yafu Wang, Yidong Liu, Hanmeng Wang, Jindong Xie, Xing Zhang, Yue School of Engineering Westlake University China Institute of Advanced Technology Westlake Institute for Advanced Study China School of Computer Science and Engineering Central South University China University of Electronic Science and Technology of China China Microsoft Research Asia China

Pre-trained language models (PLMs) are known to improve the generalization performance of natural language understanding models by leveraging large amounts of data during the pre-training phase. However, the out-of-distribution (OOD) generalization problem remains a challenge in many NLP tasks, limiting the real-world deployment of these methods. This paper presents the first attempt at creating a unified benchmark named GLUE-X for evaluating OOD robustness in NLP models, highlighting the importance of OOD robustness and providing insights on how to measure the robustness of a model and how to improve it. The benchmark includes 15 publicly available datasets for OOD testing, and evaluations are conducted on 8 classic NLP tasks over 21 popularly used PLMs. Our findings confirm the need for improved OOD accuracy in NLP tasks, as significant performance degradation was observed in all settings compared to in-distribution (ID) accuracy. © 2022, CC BY-SA.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Investigation on the dynamic damage process of HfO2/SiO2 anti-reflection coatings under 1064nm nanosecond laser irradiation

Investigation on the dynamic damage process of HfO2/SiO2 ant...

引用

Pacific-Rim Laser Damage 2023: Optical Materials for High-Power Lasers

作者： Xiang, Chengjiang Liu, Xiaofeng Tao, Chunxian Li, Dawei Zhao, Yuan’an Sun, Jian Zhang, Weili Shao, Yuchuan Shao, Jianda School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Laboratory of Thin Film Optics Shanghai Institute of Optics and Fine Mechanics Chinese Academy of Sciences Shanghai201800 China Key Laboratory of High Power Laser Materials Shanghai Institute of Optics and Fine Mechanics Chinese Academy of Sciences Shanghai201800 China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences Beijing100049 China Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou310024 China

ISBN: (纸本)9781510672826

Time-resolved pump-probe technology is an effective method to study the dynamic damage process of optics. In this paper, the dynamic damage process of HfO2/SiO2 anti-reflection coating, for the cases that the coating located on the laser incidence (forward process) and exit (reverse process) surface, irradiated by a 1064nm nanosecond laser was studied based on the time-resolved pump-probe technology of intensified charge-coupled device (ICCD). Under the irradiation of the same fluence (52J/cm2), pits without and with the layer peeling existed in both forward and reverse processes. However, the lateral size and depth of the small pits generated by the reverse process are larger than those of the forward process. The finite element analysis shows that the electric field intensity (EFI) on the substrate-coating interface for the forward and reverse processes is similar, which is not enough to form the difference in damage morphology. These results indicate the develop process of the plasma after its formation under the subsequent laser pulse irradiation determines the damage difference in the above two cases. The time-resolved study of anti-reflective coating damage is of great significance for its damage mechanism analysis and practical application. © 2023 SPIE.

关键词： Laser damage

来源：评论

学校读者我要写书评

暂无评论

Multilayer dielectric grating pillar-removal damage induced by a picosecond laser

引用

High Power Laser science and engineering 2022年第6期10卷 66-74页

作者： Kun Shuai Xiaofeng Liu Yuanan Zhao Keqiang Qiu Dawei Li He Gong Jian Sun Li Zhou Youen Jiang Yaping Dai Jianda Shao Zhilin Xia School of Materials Science and Engineering Wuhan University of TechnologyWuhanChina Laboratory of Thin Film Optics Shanghai Institute of Optics and Fine MechanicsShanghaiChina National Synchrotron Radiation Laboratory University of Science and Technology of ChinaHefeiChina School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghaiChina National Laboratory on High Power Laser and Physics Shanghai Institute of Optics and Fine MechanicsCASShanghaiChina Research Center of Laser Fusion China Academy of Engineering PhysicsMianyangChina Hangzhou Institute for Advanced Study University of Chinese Academy of SciencesHangzhouChina

Multilayer dielectric gratings typically remove multiple-grating pillars after picosecond laser irradiation;however,the dynamic formation process of the removal is still *** this study,the damage morphologies of multilayer dielectric gratings induced by an 8.6-ps laser pulse were closely *** damage included the removal of a single grating pillar and consecutive adjacent grating pillars and did not involve the destruction of the internal high-reflection mirror *** analysis of the two damage morphological characteristics indicated the removal of adjacent pillars was related to an impact process caused by the eruption of localized materials from the left-hand pillar,exerting impact pressure on its adjacent pillars and eventually resulting in multiple pillar removal.A finite-element strain model was used to calculate the stress distribution of the grating after *** to the electric field distribution,the eruptive pressure of the dielectric materials after ionization was also *** results suggest that the eruptive pressure resulted in a stress concentration at the root of the adjacent pillar that was sufficient to cause damage,corresponding to the experimental removal of the adjacent pillar from the *** study provides further understanding of the laser-induced damage behavior of grating pillars and some insights into reducing the undesirable damage process for practical applications.

关键词： grating pillar removal laser-induced damage multilayer dielectric gratings picosecond laser

来源：评论

学校读者我要写书评

暂无评论

Benchmarking GPT-4 against Human Translators: A Comprehensive Evaluation Across Languages, Domains, and Expertise Levels

arXiv

引用

arXiv 2024年

作者： Yan, Jianhao Yan, Pingchuan Chen, Yulong Li, Jing Zhu, Xianchao Zhang, Yue Zhejiang University Zhejiang China School of Engineering Westlake University Zhejiang China University College London London United Kingdom Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom LanBridge Group Sichuan China Institute of Advanced Technology Westlake Institute for Advanced Study China

This study presents a comprehensive evaluation of GPT-4’s translation capabilities compared to human translators of varying expertise levels. Through systematic human evaluation using the MQM schema, we assess translations across three language pairs (Chinese←→English, Russian←→English, and Chinese←→Hindi) and three domains (News, technology, and Biomedical). Our findings reveal that GPT-4 achieves performance comparable to junior-level translators in terms of total errors, while still lagging behind senior translators. Unlike traditional Neural Machine Translation systems, which show significant performance degradation in resource-poor language directions, GPT-4 maintains consistent translation quality across all evaluated language pairs. Through qualitative analysis, we identify distinctive patterns in translation approaches: GPT-4 tends toward overly literal translations and exhibits lexical inconsistency, while human translators sometimes over-interpret context and introduce hallucinations. This study represents the first systematic comparison between LLM and human translators across different proficiency levels, providing valuable insights into the current capabilities and limitations of LLM-based translation systems. © 2024, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Citrus Limon L. Ripeness Identification Using Feature Extraction of Mean RGB, HSV, LBP and K-Nearest Neighbor

Citrus Limon L. Ripeness Identification Using Feature Extrac...

引用

International Seminar on Application for technology of Information and Communication (ISemantic)

作者： Ade Cahyo Priyo Utomo Christy Atika Sari Eko Hari Rachmawanto Heru Pramono Hadi Salama A. Mostafa Wisam Subhi Talib Al-Dayyeni Study Program in Informatics Engineering University of Dian Nuswantoro Semarang Indonesia Study Program in Information Systems University of Dian Nuswantoro Semarang Indonesia Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia School of Information Technologies and Engineering ADA University Baku Azerbaijan

Citrus Limon L. (Lemon) is a type of fruit that is currently widely consumed, because it contains abundant vitamin C, fiber, and antioxidants. This fruit have high potential in the agribusiness sector and is widely cultivated by traditional farmers. However, during harvest time, traditional farmers generally still use manual methods using the human eye in distinguishing the maturity level of lemons which is less efficient because it has a low accuracy. Digital image processing is one solution to this problem. In the research on the classification of lemon maturity levels using digital image processing with the feature extraction method of the Mean RGB, HSV, and LBP methods and the K-Nearest Neighbor classification algorithm in this study, a total of 120 lemon images were used which were divided into 80 training image data and 40 image data. testing. The results of model performance measurements in the form of the highest accuracy level in the Mean RGB method of 100%, the highest accuracy in the HSV method of 98%, and the highest accuracy in the LBP method of 82.5%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A biosensing system employing nanowell microelectrode arrays to record the intracellular potential of a single cardiomyocyte

引用

Microsystems & Nanoengineering 2022年第3期8卷 185-198页

作者： Yuting Xiang Haitao Liu Wenjian Yang Zhongyuan xu Yue Wu Zhajian Tang Zhjing Zhu Zhiyong Zeng Depeng Wang Tianxing Wang Ning Hu Diming Zhang Department of Obstetrics and Gynecology Affiliated Dongguan People's HospitalSouthern Medical UniversityDongguan 523058China Research Center for Inelligent Sensing Systems Zhejiang LaboratoryHangzhou 311100China Research Center for Humanoid Sensing Zhejiang LaboratoryHangzhou 311100China Key Laboratory of Novel Target and Drug Study for Neural Repair of Zhejiang Province School of MedicineSchool of Computer&Computing ScienceZhejiang University City CollegeHangzhou 310015China School of Brain Science and Brain Medicine Zhejiang UniversityHangzhou 310058China School of Automation Nanjing University of Science and TechnologyNanjing 210094China College of Energy and Power Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China E-Link Care Meditech Co. LtdHangzhou 310011China ZJU-Hangzhou Global Scientific and Technological Innovation Center Department of ChemitryZhejiang UniversityHangzhou 310058China

Electrophysiological recording is a widely used method to investigate cardiovascular pathology,pharmacology and developmental *** arrays record the electrical potential of cells in a minimally invasive and highthroughput ***,commonly used microelectrode arays primarily employ planar microelectrodes and cannot work in applications that require a recording of the intracellular action potential of a single *** this study,we proposed a novel measuring method that is able to record the intracellular action potential of a single cardiomyocyte by using a nanowell patterned microelectrode array(NWMEA).The NWMEA consists of five nanoscale wells at the center of each circular planar *** pulse electroporation was applied to the NWMEA to penetrate the cardiomyocyte membrane,and the intracellular action potential was continuously *** intracellular potential recording of cardiomyocytes by the NWMEA measured a potential signal with a higher quality(213.76±25.85%),reduced noise root-mean-square(~33%),and higher signal-to-noise ratio(254.36±12.61%)when compared to those of the extracellular *** to previously reported nanopillar microelectrodes,the NWMEA could ensure single cell electroporation and acquire high-quality action potential of cardiomyocytes with reduced fabrication *** NWMEA-based biosensing system is a promising tool to record the intracellular action potential of a single cell to broaden the usage of microelectrode arrays in electrophysiological investigation.

关键词： arrays potential record

来源：评论

学校读者我要写书评

暂无评论

Data Transformation for Super-Resolution on Ocean Remote Sensing Images 12th

Data Transformation for Super-Resolution on Ocean Remote Sen...

引用

12th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2022

作者： Yang, Yuting Lam, Kin-Man Sun, Xin Dong, Junyu Jian, Muwei Luo, Hanjiang Shandong University of Science and Technology Qingdao266590 China Department of Electronic and Information Engineering The Hong Kong Polytechnic University 999077 Hong Kong Department of Information Science and Engineering Ocean University of China Qingdao266100 China Haide College Ocean University of China Qingdao266100 China Institute of Advanced Ocean Study Ocean University of China Qingdao266100 China School of Computer Science and Technology Shandong University of Finance and Economics 7366 Li Xia Jinan250000 China

ISBN: (纸本)9783031039478

High-resolution ocean remote sensing imaging is of vital importance for research in the field of ocean remote sensing. However, the available ocean remote sensing images are often averaged data, whose resolution is lower than the instant remote sensing images. In this paper, we propose a data transformation method to process remote sensing images in different locations and resolutions. We target satellite-derived sea surface temperature (SST) images as a specific case-study. In detail, we use a modified very deep super-resolution (VDSR) model as our baseline model and propose a data transformation method to improve the robustness of the model. Furthermore, we also illustrates how the degree of difference in the data distribution influences the model’s robustness and also, how our proposed data transformation method can improve the model’s robustness. Experiment results prove that our method is effective and our model is robust. © 2022, IFIP International Federation for Information Processing.

关键词： Atmospheric temperature

来源：评论

学校读者我要写书评

暂无评论

Laser Differential Confocal Interference Surface Automatic Measurement Method

SSRN

引用

SSRN 2023年

作者： Zhao, Jiahao Zheng, Dezhi Yang, Shuai Wang, Shuai Yang, Zheng Cui, Jian Qiu, Lirong Zhao, Weiqian MIIT Key Laboratory of Complex-field Intelligent Exploration Beijing Institute of Technology School of Optics and Photonics Beijing100081 China Beijing Institute of Technology Advanced Research Institute of Multidisciplinary Sciences Beijing100081 China Beihang University School of Computer Science and Engineering Beijing102206 China

Considering the low accuracy and slow speed of measuring an object with a spherical surface using traditional interferometry owing to manually adjusting the posture of the object, an automatic laser differential confocal interferometric measurement method is proposed to measure the surface shapes, which achieves the high-precision confocal axial positioning of the measured object through a precise differential confocal fixed-focus technology. The posture of the measured object is adjusted through a five-dimensional adjustment workbench. Subsequently, the Zernike fitting is used to reduce the defocus and tilt errors, and a zero-order fringe adjustment of the interferometric surface shape is achieved, automatically determining the surface shape. A laser differential confocal interferometric measurement system for surface shapes was constructed. Experiments demonstrate that the difference between the automatic interference measurement results and the Zygo interferometer measurement results is 0.0004 λ, the repeated measurement accuracy of this method can reach 0.0019 λ, the average measurement time of a single interferometric surface shape is 20.1 s, and the measurement efficiency is improved by 1.5 times compared to the manual adjustment to the zero-order fringe. This method provides an effective measurement method for the rapid and high-precision measurement of interferometric surface shapes. © 2023, The Authors. All rights reserved.

关键词： Interferometry

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：