检索结果-内蒙古大学图书馆

IEEE International Conference on Consumer Electronics (ICCE)

作者： Wen-Hui Chen Yu-Hung Huang Yu-Chen Lin Graduate Institute of Automation Technology National Taipei University of Technology Taipei Taiwan Department of Automatic Control Engineering Feng Chia University Taichung Taiwan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Traffic accidents pose significant social and economic challenges, making effective accident prediction systems essential. Traditional machine learning methods often struggle to capture the complex, nonlinear patterns in visual accident data. Recent advancements suggest that deep learning offers a promising solution to this challenge. These vision-based systems rely on object detection as a foundational step, identifying key entities in traffic scenes captured by cameras to improve prediction accuracy. Despite its importance, the impact of object detection accuracy on overall accident prediction effectiveness remains underexamined. This study investigates this relationship through cross-dataset analysis. Experimental results show that object detection accuracy directly impacts accident prediction performance, with training dataset choice playing a critical role. Enhancing model generalization is essential to stabilizing accident prediction systems.

关键词： Training Economics Visualization Accuracy Transportation Object detection Predictive models Safety Object recognition Accidents

来源：评论

学校读者我要写书评

暂无评论

A semi-supervised method using cycle consistency and multi-perspective dilated for SAR-to-optical translation

引用

iScience 2025年第5期28卷

作者： Wang, Jinyu Yang, Haitao Liu, Zhengjun Chen, Hang Department of Graduate Management Space Engineering University Beijing China Department of Automation Measurement and Control Harbin Institute of Technology Harbin China

Synthetic aperture radar (SAR) is a powerful imaging sensor capable of operating in any weather and at any time, despite its image interpretation poses challenges. Translating SAR images to optical (S2O) can serve as a beneficial supplement for target detection, image alignment, and image fusion. The existing S2O translation employs solely unsupervised or supervised techniques. This research presents a semi-supervised S2O generating approach that can obtain domain-level and pixel-level mapping relationships. A dual-branch cycle consistency loss has been developed to independently constrain supervised and unsupervised modules. To improve global and sparsity feature extraction, the generator combines sliding dilated convolution with multi-respective parallel branching. Using just 1,100 pairs of training sets, extensive experiments have demonstrated that the suggested strategy outperforms baseline methods in both subjective and objective standards, where Fréchet inception distance (FID) is optimized by 23.41%, 49.25%, 48.57%, 16.73%, and 42.32% on the five land classes. © 2025 The Authors

关键词： Applied sciences Natural sciences Physics

来源：评论

学校读者我要写书评

暂无评论

Qingda Granule Attenuates Hypertension-Induced Cardiac Damage via Regulating Renin-Angiotensin System Pathway

引用

Chinese Journal of Integrative Medicine 2025年第5期31卷 402-411页

作者： LONG Lin-zi TAN Ling XU Feng-qin YANG Wen-wen LI Hong-zheng LIU Jian-gang WANG Ke ZHAO Zhi-ru WANG Yue-qi WANG Chao-ju WEN Yi-chao HUANGMing-yan QU Hua FU Chang-geng CHEN Ke-ji Department of Geriatrics Xiyuan Hospital of China Academy of Chinese Medical SciencesBeijing100091China Department of Traditional Chinese Medicine the Eighth Affiliated Hospital of Sun Yat-Sen UniversityShenzhenGuangdong Province518033China Xiyuan Hospital National Cardiovascular Clinical Medical Research Center of Traditional MedicineBeijing100091China Graduate School of Beijing University of Chinese Medicine Beijing100091China Cardiovascular Department the Second Affiliated HospitalShanxi University of Chinese MedicineTaiyuan030002China Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imagingthe State Key Laboratory of Management and Control for Complex SystemsInstitute of AutomationChinese Academy of SciencesBeijing100090China Cadre 2 Ward Xinjiang Uygur Autonomous Region Institute of Traditional Chinese MedicineUrumqi830000China Academy of Integrative Medicine Fujian Univrsity of Traditional Chinese MedicineFuzhou350122China

Objective:To assess the efficacy of Qingda Granule(QDG)in ameliorating hypertensioninduced cardiac damage and investigate the underlying mechanisms ***:Twenty spontaneously hypertensive rats(SHRs)were used to develope a hypertension-induced cardiac damage *** 10Wistar Kyoto(WKY)rats were used as normotension *** were administrated intragastrically QDG[0.9 g/(kg·d)]or an equivalent volume of pure water for 8 *** pressure,histopathological changes,cardiac function,levels of oxidative stress and inflammatory response markers were ***,to gain insights into the potential mechanisms underlying the protective effects of QDG against hypertensioninduced cardiac injury,a network pharmacology study was *** results were validated by Western blot,radioimmunoassay immunohistochemistry and quantitative polymerase chain reaction,***:The administration of QDG resulted in a significant decrease in blood pressure levels in SHRs(P<0.01).Histological examinations,including hematoxylin-eosin staining and Masson trichrome staining revealed that QDG effectively attenuated hypertension-induced cardiac ***,echocardiography demonstrated that QDG improved hypertension-associated cardiac ***-linked immunosorbent assay and colorimetric method indicated that QDG significantly reduced oxidative stress and inflammatory response levels in both myocardial tissue and serum(P<0.01).Conclusion:Both network pharmacology and experimental investigations confirmed that QDG exerted its beneficial effects in decreasing hypertensioninduced cardiac damage by regulating the angiotensin converting enzyme(ACE)/angiotensinⅡ(AngⅡ)/AngⅡreceptor type 1 axis and ACE/AngⅡ/AngⅡreceptor type 2 axis.

关键词： blood pressure cardiac damage hypertension Qingda Granule renin-angiotensin system

来源：评论

学校读者我要写书评

暂无评论

Implementation of a diode-pumped Nd:YAG laser with quick-change output couplers for high-beam quality 1064 or 532 nm wavelength generation

引用

Laser Physics 2009年第6期19卷 1201-1206页

作者： Li, Chun-Hao Tsai, Ming-Jong Graduate Institute of Automation and Control National Taiwan University of Science and Technology Taipei 10672 Taiwan

A novel diode-pumped Nd:YAG laser system that employs a fixed active laser medium and a pair of quick-change output couplers on a precision linear stage for 1064 or 532 nm wavelength generation is presented. Fixed elements include a rear mirror, an acousto-optical Q-switch, and a diode-pumped solid-state laser (DPSSL). Movable elements for 1064 nm generation include an intra-cavity aperture as a mode selection element (MSE) and an output coupler. Movable elements for 532 nm generation include an intra-cavity frequency conversion with KTP, an intra-cavity aperture as a mode selection element (MSE), and an output coupler. Under stable operating conditions, the 1064 nm configuration produced a beam propagation ratio of 1.18 whereas the 532 nm configuration produced a beam propagation ratio of 1.1, both of which used an intra-cavity MSE with an aperture of 1.2 mm and a length of 5 mm. © 2009 Pleiades Publishing, Ltd.

关键词： Yttrium aluminum garnet

来源：评论

学校读者我要写书评

暂无评论

The use of grey relational analysis to determine laser cutting parameters for QFN packages with multiple performance characteristics

引用

Optics and Laser Technology 2009年第8期41卷 914-921页

作者： Tsai, Ming-Jong Li, Chen-Hao Graduate Institute of Automation and Control National Taiwan University of Science and Technology Taipei 10672 Taiwan

This paper reports an application of the grey relational analysis (GRA) to directly optimize laser cutting of a quad flat non-lead (QFN) strip using six performance characteristics. The most important performance characteristics include the cutting depth, the width of heat affected zone (HAZ), and the width of cutting line for both epoxy and Cu+epoxy materials along the cutting path. During the GRA, higher grades are obtained from any of the deeper (more complete) cutting depth, reduced widths of the HAZ and reduced widths of the cutting line. From nine experiments based on the orthogonal array of L9(34), a current of 29 A, a frequency of 2 kHz, and a cutting speed of 2 mm/s were found to be the best parameters for laser cutting of a QFN strip with a thickness of 0.9 mm. Moreover, the analysis of variance (ANOVA) is also employed to determine the contribution of each control parameter on the cutting quality characteristics. The three largest measured contributions on the cutting quality in decreasing order are the frequency, the current, and the cutting speed. Compared with the Taguchi optimization method, the GRA approach is significantly simpler because it directly assigns appropriate weighting factors to the required qualities. Finally, confirmation experiments are performed to ensure the robustness of the GRA predicted optimal configuration for laser cutting a QFN strip. © 2009 Elsevier Ltd. All rights reserved.

关键词： Heat affected zone

来源：评论

学校读者我要写书评

暂无评论

Gray relational analysis approach for the optimization of process setting in textile calendering

引用

Textile Research Journal 2009年第11期79卷 981-992页

作者： Kuo, Jeffrey Chung-Feng Tu, Hung-Min Graduate Institute of Automation and Control National Taiwan University of Science and Technology Taipei 106 Taiwan

Calenders are mainly applied in fabric surface processing to improve the surface gloss. This paper proposes an advanced quality control strategy for calendering, employing the gray relational analysis based on Taguchi method to plan a series of calendering experiments, setting the robust process parameters for calender. Our study focused on the use of gray relational analysis to deal with a fundamental limitation of the standard Taguchi approach in respect of optimization problems having multiple quality characteristics. The quality characteristics included reflectance, water vapor permeability, and color difference of calendered fabrics. In order to estimate the optimization parameters with multiple quality characteristics, gray relational analysis was also incorporated to set quality characteristics as reference sequences and decide the optimal parameter combinations. The results showed that the calendered qualities were greatly improved and effectively determined the process parameters through this study.

关键词： Taguchi methods

来源：评论

学校读者我要写书评

暂无评论

Global and local information combined to detect singular points in fingerprint images

引用

Science China(Information Sciences) 2013年第6期56卷 203-215页

作者： FAN LingLing WANG ShuGuang GUO TianDe Institute of System Engineering and Control Beijing Jiaotong University Institute of Automation Chinese Academy of Sciences School of Mathematical Sciences of Graduate University Chinese Academy of Sciences

An algorithm is proposed,which combines global and local information of fingerprint images to detect singular ***’s mathematically proven that normal lines of gradient of double orientation field(GDOF) pass through singular *** lines of GDOF use rather global information to detect candidate singular *** image is divided into blocks and normal lines of GDOF are *** number of normal lines that pass through each block is *** block that has the maximum number corresponds to a candidate singular *** can be seen as a kind of Hough transform(HT).As candidate singular points detected by global information may have a little warp from their real positions,it’s necessary to use local information to refine their *** index is chosen,and uses local information to refine the candidate singular *** makes our algorithm more robust to noise than methods that only use local ***’s more,the pairs of the detected singular points are used to classify *** results show that our algorithm performs well and fast enough for real time application in databases NIST-4.

关键词： global information local information normal lines of GDOF Poincare index singular points

来源：评论

学校读者我要写书评

暂无评论

Investigating the dynamic memory effect of human drivers via ON-LSTM

引用

Science China(Information Sciences) 2020年第9期63卷 83-93页

作者： Shengzhe DAI Zhiheng LI Li LI Dongpu CAO Xingyuan DAI Yilun LIN Department of Automation Tsinghua University Shenzhen International Graduate School Tsinghua University Department of Mechanical and Mechatronics Engineering University of Waterloo State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

It is a widely accepted view that considering the memory effects of historical information(driving operations) is beneficial for vehicle trajectory prediction models to improve prediction accuracy. However,many commonly used models(e.g., long short-term memory, LSTM) can only implicitly simulate memory effects, but lack effective mechanisms to capture memory effects from sequence data and estimate their effective time range(ETR). This shortage makes it hard to dynamically configure the most suitable length of used historical information according to the current driving behavior, which harms the good understanding of vehicle motion. To address this problem, we propose a modified trajectory prediction model based on ordered neuron LSTM(ON-LSTM). We demonstrate the feasibility of ETR estimation based on ON-LSTM and propose an ETR estimation method. We estimate the ETR of driving fluctuations and lane change operations on the NGSIM I-80 dataset. The experiment results prove that the proposed method can well capture the memory effects during trajectory prediction. Moreover, the estimated ETR values are in agreement with our intuitions.

关键词： driving behavior memory effect trajectory prediction historical information ON-LSTM

来源：评论

学校读者我要写书评

暂无评论

YOLOv5 based Intelligent Defect Detection of Dual-color Gradient Object Fabricated by Fused Deposition Modeling Additive Manufacturing System

YOLOv5 based Intelligent Defect Detection of Dual-color Grad...

引用

2023 International Automatic control Conference, CACS 2023

作者： Yeh, C.R. Yan, S.Q. Tsai, M.J. National Taiwan University of Science and Technology Graduate Institute of Automation and Control Taiwan

ISBN: (纸本)9798350306354

Quality insurance is a critical process in the manufacturing industry. Additive manufacturing (AM) has gained rapid development due to its capability of producing complex parts. Among various additive manufacturing, Fused Deposition Modeling (FDM) is widely used by consumers and businesses. In recent years, deep learning has been applied to enhance quality inspection in the manufacturing sector by combining traditional AOI with AI, particularly in multi-class defect detection. This paper proposes an intelligent defect detection system for FDM dual-color gradient objects based on the YOLOv5. Traditional inspection methods may struggle to detect defects caused by uneven colors from the shape or material incompatibility of dual-color gradient objects. By integrating an intelligent defect detection system into the production process, accuracy checks and classification can be performed to detect and address issues promptly, thus reducing costs. In this study, an image database for FDM dual-color gradient objects with curved surfaces is established by an automated imaging system equipped with two cameras and two controllable lighting sources to enable multi-angle observation and quickly acquire the image data of training and test samples. The primary objective is to detect nine different samples, categorized into six defect classes: good(normal), curling, break, foreign, gap, and uneven defects. A total of 1914 images are obtained. The images are split into training (80%, 1531 images) and validation (20%, 383 images) sets. Testing sets are also used to evaluate the model's performance. The YOLOv5 model is built and the performance among different depth (s, m, l, x) is compared after training for 100 epochs. The built model achieves performance of over 90% (Mean Average Precision mAP@0.5) for the validation set. Furthermore, the model is tested under on-line FDM fabricating process to verify the application in real-time defect detection in the future. © 2023 IEEE.

关键词： Deposition

来源：评论

学校读者我要写书评

暂无评论

3D laser trimming technology for regulating embedded thick-film carbon resistors on a random access memory module

引用

Journal of Materials Processing Technology 2009年第4期209卷 2057-2067页

作者： Li, Chun-Hao Tsai, Ming-Jong Graduate Institute of Automation and Control National Taiwan University of Science and Technology No. 43 Keelung Road Section 4 Taipei 10672 Taiwan

This study presents a novel solution for regulating embedded thick-film carbon resistors on random access memory (RAM) modules using 3D laser trimming technology. The embedded passive components, which are printed on a substrate using liquid-polymer ink, are employed due to their rapid response time. The original resistance of such resistors, however, is less than the target value. Hence, a 3D laser trimming technology is proposed for etching thick-film resistors and reaching a target resistance value with online assistance of a four-wire resistance measurement device. A laser beam deflection path with a spiral cycle is manufactured on the printed thick-film to superficially thin the resistor using a wobble-grinding function in a layer-by-layer manner. Resistance material was removed by each laser pulse until the target resistance was obtained. Twelve RAM modules were tested. Experimental results demonstrate that the resistance value of the trimmed resistors was an averaged accredited percentage of 88.54% with a tolerance of 5%. All trimmed resistors with a tolerance of 10% were obtained. Furthermore, 144,000 embedded thick-film carbon resistors on 1800 RAM modules were trimmed in a factory using the proposed scheme. Measurement results indicate that an average accredited rate of 95.67% with tolerances of 5-20% was obtained for industrial applications. Therefore, the proposed technology is a practical and efficient solution for regulating thick-film carbon resistors on RAM modules and other related products. © 2008 Elsevier B.V. All rights reserved.

关键词： Resistors

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：