检索结果-内蒙古大学图书馆

Two-phase cost-sensitive-learning-based framework on customer-side quality inspection for TFT-LCd industry

Journal of Intelligent Manufacturing 2024年

作者： Shih, Ming-Sung Chen, James C. Chen, Tzu-Li Hsu, Ching-Lan International Intercollegiate Ph.D. Program National Tsing Hua University Hsinchu30013 Taiwan Department of Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu30013 Taiwan Graduate Institute of Intelligent Manufacturing Technology National Taiwan University of Science and Technology Taipei106335 Taiwan

The Covid-19 outbreak in 2020 boosted the stay-at-home economy, causing a surge in electronics industry demand, especially benefiting the LCd panel sector. However, as the pandemic situation improved, countries revised policies, leading to the gradual discontinuation of remote work arrangements in various industries. This resulted in declining dividends for the stay-at-home economy. The decreased demand created intense competition within the TFT-LCd industry, urging panel companies to prioritize product quality enhancement to meet customer expectations. Panel quality inspection heavily relied on manual labor, causing varying inspection levels due to subjective judgments. Understanding and aligning with customer expectations regarding product quality inspections became imperative. Identifying defective products during inspection led to additional costs for the companies. Balancing customer product quality requirements and re-inspection costs became crucial for optimal benefits. This study addresses the binary classification problem of customer-side quality inspection through cost-sensitive learning. The predictive model considers panel process yield, production history, customer feedback, inspection capacity constraints, and cost minimization to predict panel quality as accepted or defective. To tackle the highly imbalanced data, a two-phase cost-sensitive-learning-based framework is proposed, combining data preprocessing methods and models, while considering re-inspection capacity constraints and costs to enhance accuracy. The model’s evaluation uses key performance indicators like AUC and G-mean. Actual inspection cost and defective parts per million (dPPM) are calculated based on the company’s practical assessment. Two products are used for experimentation to validate the proposed model, demonstrating over 50% reduction in inspection cost and over 10% improvement in dPPM. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Spr

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

design of Optical System of Augmented Reality Near Eye device 6

Design of Optical System of Augmented Reality Near Eye Devic...

引用

6th IEEE Eurasian Conference on Educational Innovation, ECEI 2023

作者： Chang, Chao-Kai Yeh, Feng-Ming Lue, Jiann-Hwa Wang, Hsuan-Fu Hsieh, Ya-Hui Chiang, Chun-Yu Chen, der-Chin Tien, Chuen-Lin Department of Optometry Yuanpei University of Medical Technology Hsinchu Taiwan Department of Optometry Taiwan University of Science and Technology Taichung Taiwan Department of Aeronautical Engineering National Formosa University Yunlin Taiwan Department of Healthcare Information and Management Ming Chuan University Taoyuan 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

Augmented reality (AR) is a technology that instantly merges digital pictures with the real scene. The perspective near-eye display is a key module of AR, through which computer-generated pictures or videos can be displayed in the existing environment. The purpose of this research is to establish the system structure of an augmented reality near-eye display device and to design the off-axis two-piece reflective aspherical mirror. Because AR glasses are wearable and are worn close to the eyes, not only the optical performance of the display but also the clear vision of the user needs to be considered. In this study, an off-axis two-piece reflective aspherical mirror is used as the optical system of the AR for displaying the digital image. The micro-display is placed at the focal point of the optical system to form a digital image, and the horizontal movement of the micro-display along the optical axis is controlled by a precise displacement mechanism so that the patient with uncorrected myopia or hyperopia can see the digital picture and real scene. Because the right and left micro-displays move horizontally independently, the user can see the images on the AR device, which becomes the biggest feature of this study. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Structure-guided identification and characterization of potent inhibitors targeting phoP and MtrA to combat mycobacteria

引用

Computational and Structural Biotechnology Journal 2024年 23卷 1477-1488页

作者： Su, Han-Li Lai, Shu-Jung Tsai, Keng-Chang Fung, Kit-Man Lung, Tse-Lin Hsu, Hsing-Mien Wu, Yi-Chen Liu, Ching-Hui Lai, Hui-Xiang Lin, Jiun-Han Tseng, Tien-Sheng Department of Emergency Medicine Ditmanson Medical Foundation Chia-Yi Christian Hospital Chiayi City600 Taiwan Graduate Institute of Biomedical Sciences China Medical University Taichung Taiwan Research Center for Cancer Biology China Medical University Taichung Taiwan National Research Institute of Chinese Medicine Ministry of Health and Welfare Taipei Taiwan Ph.D. Program in Medical Biotechnology College of Medical Science and Technology Taipei Medical University Taipei Taiwan Academia Sinica Taipei11529 Taiwan Institute of Molecular Biology National Chung Hsing University Taichung Taiwan Department of Industrial Technology Ministry of Economic Affairs Taipei Taiwan Food Industry Research and Development Institute Hsinchu City Taiwan

Mycobacteria are causative agents of tuberculosis (TB), which is a global health concern. drug-resistant TB strains are rapidly emerging, thereby necessitating the urgent development of new drugs. Two-component signal transduction systems (TCSs) are signaling pathways involved in the regulation of various bacterial behaviors and responses to environmental stimuli. Applying specific inhibitors of TCSs can disrupt bacterial signaling, growth, and virulence, and can help combat drug-resistant TB. We conducted a comprehensive pharmacophore-based inhibitor screening and biochemical and biophysical examinations to identify, characterize, and validate potential inhibitors targeting the response regulators phoP and MtrA of mycobacteria. The constructed pharmacophore model phar-PR-n4 identified effective inhibitors of formation of the phoP–dNA complex: ST132 (IC50 = 29 ± 1.6 µM) and ST166 (IC50 = 18 ± 1.3 µM). ST166 (Kd = 18.4 ± 4.3 μM) and ST132 (Kd = 14.5 ± 0.1 μM) strongly targeted phoP in a slow-on, slow-off manner. The inhibitory potency and binding affinity of ST166 and ST132 for MtrAC were comparable to those of phoP. Structural analyses and molecular dynamics simulations revealed that ST166 and ST132 mainly interact with the α8-helix and C-terminal β-hairpin of phoP, with functionally essential residue hotspots for structure-based inhibitor optimization. Moreover, ST166 has in vitro antibacterial activity against Macrobacterium marinum. Thus, ST166, with its characteristic 1,2,5,6-tetrathiocane and terminal sulphonic groups, has excellent potential as a candidate for the development of novel antimicrobial agents to combat pathogenic mycobacteria. © 2024 The Authors

关键词： Antimicrobial agents

来源：评论

学校读者我要写书评

暂无评论

Unveiling Multivariate EEG Features: A Novel Approach to Enhancing AdHd diagnosis Through Visual and Auditory Attention Tests

Unveiling Multivariate EEG Features: A Novel Approach to Enh...

引用

2023 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2023

作者： Fan, Zuo-Cian Lin, Ro-Wei Tsai, Ching-Shu Chou, Wen-Jiun Li, Chia-Jung Huang, Zih-Jun Shih, Bin-Yu Wang, Liang-Jen Ko, Li-Wei Department of Biological Science & Technology Hsinchu300 Taiwan National Yang Ming Chiao Tung University International Ph.D. Program in Interdisciplinary Neuroscience Hsinchu300 Taiwan Kaohsiung Chang Gung Memorial Hospit Department of Child and Adolescent Psychiatry National Yang Ming Chiao Tung University Institute of Electrical and Control Engineering Department of Electronics and Electrical Engineering Hsinchu300 Taiwan

ISBN: (纸本)9798350305791

We sought to revolutionize the classification of Attention-deficit/Hyperactivity disorder (AdHd) by pioneering an innovative approach that seamlessly integrated auditory and visual tests with electroencephalogram (EEG) coherence analysis, forming the foundation for our Support Vector Machine (SVM) models. Our primary objective was to achieve precise differentiation between individuals with AdHd and those without, aiming to reshape the landscape of AdHd diagnosis and early intervention. We constructed an SVM model based on CATA coherence, incorporating a carefully selected set of 180 features, and another grounded in CPT coherence with 70 features. Astonishingly, our exploration uncovered that a model incorporating CATA's coherence and Power Spectral density (PSd) as features achieved an astounding accuracy rate of 97.7%, using only half the number of features. This revelation hints at untapped potential for multivariate advancements in the realm of AdHd classification. The landscape of AdHd diagnosis and intervention is perpetually evolving, most notably with the FdA's approval of game therapy for AdHd. Leveraging the transformative power of our findings, we envision the development of user-friendly game therapies for in-home use, empowering both clinicians and parents alike. This marks a paradigm shift in the realm of AdHd intervention, offering objective, data-driven tools for the early management of AdHd. Gamified therapy not only enhances accessibility but also fosters engagement and compliance, all of which are pivotal in the long-term care of individuals with AdHd. In summary, our study represents a significant advancement in our comprehension and classification of AdHd. By fusing auditory and visual tests with EEG coherence analysis, fortified by state-of-the-art machine learning techniques, we have achieved an unprecedented level of accuracy in identifying individuals with AdHd. Our findings, aligned with the FdA-approved game therapy, offer a glimpse into a

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Assessment of air pollution emitted during cooking using biomass and cleaner fuels in the Shiselweni region of Eswatini (Swaziland)

引用

Clean Technologies and Environmental Policy 2024年第9期26卷 3003-3020页

作者： Neumann, Melinda dlamini, Wonder Nathi Sallah-Ud-din, Rasham Berekute, Abiyu Kerebo Siregar, Sepridawati Getnet, Mastewal Endeshaw Maulana, Muchsin Pan, Wen-Chi Lung, Shih-Chun Candice Yu, Kuo-Pin International Health Program National Yang Ming Chiao Tung University No.155 Sec. 2 Li-Nong Street Taipei112304 Taiwan Institute of Environmental and Occupational Health Sciences National Yang Ming Chiao Tung University No.155 Sec. 2 Li-Nong Street Taipei112304 Taiwan International Ph.D. Program in Environmental Science and Technology National Yang Ming Chiao Tung University No.155 Sec. 2 Li-Nong Street Taipei112304 Taiwan Department of Chemistry College of Natural and Computational Sciences Arba Minch University Arbaminch Ethiopia Research Center for Environmental Changes Academia Sinica No. 128 Academia Road Section 2Nangang Taipei11529 Taiwan Faculty of Mineral Technology AKPRIND Institute of Science and Technology Yogyakarta Indonesia

In Eswatini, 62.3% of households still rely on solid fuel for cooking, especially wood (61.8%). Smoke emissions during biomass burning remain the primary source of indoor air pollution, comprising pollutants detrimental to health. This study provides a quantitative exposure assessment of fuels used in the Shiselweni region with the objectives of monitoring the carbon monoxide (CO) and carbon dioxide (CO2) concentrations during cooking events and evaluating cancer and noncancer risks due to exposure to particulate-bound polycyclic aromatic hydrocarbons (PAHs) during cooking events among cooking personnel in households that cook indoors by burning biomass. Real-time CO, CO2, and particulate matter (PM) monitoring was performed in seventeen kitchens during cooking events across the Shiselweni region using different cooking methods: biomass in open fires and stoves, liquefied petroleum gas (LPG), and electric stoves. PM2.5, PM10, and CO exceeded indoor exposure guidelines for biomass fuel-related homesteads. Particulate PAH intake concentrations were evaluated, and biomass fuel users exhibited high cancer risks and low embryo survival chances due to particulate PAH exposure. The average total cost of reducing the incremental lifetime cancer risk (ILCR) and hazard quotient (HQ) to acceptable levels was lower when shifting from biomass to LPG stoves than when shifting to electric stoves. Graphical abstract: (Figure presented.) © The Author(s) 2024.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Selective detection of explosive nitro-aromatic compounds using the 2d organic nanosheets (2dONs) synthesize via 2d click chemistry directed by ultrasonication

引用

Journal of Industrial and Engineering Chemistry 2024年 134卷 504-513页

作者： dabur, deepak Chiu, Yun Cheih Wu, Hui-Fen International Ph.D. Program for Science National Sun Yat-Sen University Kaohsiung80424 Taiwan Department of Chemistry National Sun Yat-Sen University Kaohsiung 70 Lien-Hai Road Kaohsiung80424 Taiwan Institute of Medical Science and Technology National Sun Yat-Sen University Kaohsiung80424 Taiwan School of Pharmacy College of Pharmacy Kaohsiung Medical University Kaohsiung80708 Taiwan Institute of Precision Medicine College of Medicine National Sun Yat-Sen University Kaohsiung80424 Taiwan School of Medicine College of Medicine National Sun Yat-Sen University Kaohsiung80424 Taiwan

Recent advancements in click chemistry have made it an effective method for quickly and easily assembling extremely stable nanomaterial assemblies onto surfaces. Therefore, a new class of fluorescent sensor utilizing two-dimensional organic nanosheets (2dONs) for the selective sensing of 2,4-dinitrophenylhydrazine (2,4-dNph) has been proposed by using the click chemistry directed by the probe ultrasonication method (CCdPS) which is driven by the π-π stacking interactions with the aid of dMF solvent. Prolonged human exposure to 2, 4-dNph has been associated with various detrimental health consequences, including skin conditions, liver issues, and disturbances to the central nervous and cardiovascular systems. Fluorescence titration tests with nanomolar scale limit of detection (LOd, 100 nM or 0.1 μM) and limit of quantification (LOQ, 0.4 μM) for 2,4-dNph showed fluorescence quenching reactions and excellent reversibility. Additionally, zeta potential and UV-absorption spectroscopy were used to validate the interaction and binding characteristics of 2d ONs with 2,4-dNph. In contrast to the widely reported ground-state charge transfer or FRET-based probes for nitroaromatics detection, the signal response for 2,4-dNph was achieved by a strong inner filter effect with the combination of FRET (IFE-FRET). © 2024 The Korean Society of Industrial and Engineering Chemistry

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Robust Feature Learning Against Noisy Labels

Robust Feature Learning Against Noisy Labels

引用

IEEE International Conference on Image Processing

作者： Tsung-Ming Tai Yun-Jie Jhang Wen-Jyi Hwang Free University of Bozen-Bolzano NVIDIA AI Technology Center International Intercollegiate Ph.D. Program National Tsing Hua University Department of Computer Science and Information Engineering National Taiwan Normal University

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples, further learning erroneous associations of data contents to incorrect annotations. To this end, this paper proposes an efficient approach to tackle noisy labels by learning robust feature representation based on unsupervised augmentation restoration and cluster regularization. In addition, progressive self-bootstrapping is introduced to minimize the negative impact of supervision from noisy labels. Our proposed design is generic and flexible in applying to existing classification architectures with minimal overheads. Experimental results show that our proposed method can efficiently and effectively enhance model robustness under severely noisy labels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of deepLabCut and Other Open-Source Pupillometry data Analysis Algorithms – Which to Choose?

引用

Machine Graphics and Vision 2024年第2期33卷 77-90页

作者： Badkul, Amitesh Mishra, Sonakshi Kommajosyula, Srinivasa P. Department of Electrical & Electronics Engineering Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Department of Pharmacy Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Ph.D. Program in Computer Science The Graduate Center The City University of New York New YorkNY United States

Pupillometry measures pupil size, and several open-source algorithms are available to analyse pupillometry data. However, only a few studies compared these algorithms’ accuracy and computational resources. This study aims to compare the accuracy of computer vision-based algorithms (Swirski, Starburst, PuRe, ElSe, ExCuSe algorithms) and the machine learning algorithm, deepLabCut, to the double-blinded human examiners (gold-standard). Training of deepLabCut with different architectures and a variable number of markers (2-9 markers) was done on an open-source dataset. The duration of training was statistically longer for the ResNet152 model compared to the MobileNet model. The pupil diameters in computer vision-based software such as PuRe, Starburst, and Swirski were statistically different from human measurements. MobileNet 2 and 3 marker models were the closest to the human measurements. In conclusion, this work highlights the efficiency of lower marker models based on MobileNet architecture in deepLabCut, which consumes fewer computational resources and is more accurate. © 2024 Institute of Information technology, Warsaw University of Life Sciences - SGGW. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A mini-review on plasticrusts: occurrence, current trends, potential threats, and recommendations for coastal sustainability

引用

Environmental Monitoring and Assessment 2024年第2期196卷 1-14页

作者： Nguyen, Minh-Ky Rakib, Md. Refat Jahan Nguyen, Hoang-Lam Lin, Chitsan Malafaia, Guilherme Idris, Abubakr M. Faculty of Environment and Natural Resources Nong Lam University of Ho Chi Minh City Hamlet 6 Linh Trung Ward Thu Duc City Ho Chi Minh City700000 Viet Nam Ph.D. Program in Maritime Science and Technology National Kaohsiung University of Science and Technology Kaohsiung81157 Taiwan Department of Fisheries and Marine Science Faculty of Science Noakhali Science and Technology University Sonapur Noakhali3814 Bangladesh Department of Civil Engineering McGill University Montreal Canada Department of Marine Environmental Engineering National Kaohsiung University of Science and Technology Kaohsiung81157 Taiwan Post-Graduation Program in Ecology Conservation and Biodiversity Federal University of Uberlândia MG Uberlândia Brazil Post-Graduation Program in Biotechnology and Biodiversity Federal University of Goiás GO Goiânia Brazil Post-Graduation Program in Conservation of Cerrado Natural Resources Goiano Federal Institute GO Urutaí Brazil Department of Chemistry College of Science King Khalid University Abha62529 Saudi Arabia King Khalid University Abha62529 Saudi Arabia

Plasticrusts manifest as a coating on intertidal rocks due to environmental exposure. They refer to crushed plastic debris that blankets rocks found along intertidal shorelines. This study significantly contributes to a better understanding of the occurrence of these novel plastic formations, shedding light on their potential pathways of formation during the Anthropocene era. The research provides comprehensive insights into the composition, origins, challenges, and effective management strategies for removing coastal plastic litter. The findings of this investigation offer valuable evidence regarding the formation and impact of these recently discovered plastic items in coastal regions, prompting discussions about their formation processes and their effects on the marine ecosystem. Recognizing that these newly emerged plastic litter pose a considerable threat to the marine environment is crucial. With their emergence, we face an environmental challenge, especially concerning the health of coastal ecosystems. Plasticrusts, when degraded, can release microplastics (MPs) and nanoparticles (NPs) into the surrounding environment. These micro- and nano-sized plastic particles pose significant ecological risks as they persist in ecosystems, potentially harming wildlife and entering the food chain, causing widespread environmental contamination. Significantly, it outlines strategies to minimize the impact of this emerging plastic debris and its source. © 2024, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Enhanced removal of viral aerosols using nanosilver/TiO2-chitosan filters combined with a negative air ionizer

引用

Journal of Environmental Chemical Engineering 2024年第3期12卷

作者： dlamini, Wonder Nathi Yao, Ting-Ching Lee, Hsin-Jui Berekute, Abiyu Kerebo Sallah-Ud-din, Rasham Siregar, Sepridawati Yu, Kuo-Pin Institute of Environmental and Occupational Health Sciences National Yang-Ming Chiao-Tung University Taipei Taiwan Department of International Ph.D. Program in Environmental Sciences and Technology University System of Taiwan Taipei Taiwan Department of Chemistry College of Natural and Computational Sciences Arba Minch University Arbaminch Ethiopia Faculty of Mineral Technology AKPRIND Institute of Science & Technology Yogyakarta Indonesia

The presence of airborne viruses in bioaerosols is a significant and ongoing public health concern. In this context, this study aimed to develop a new filter that integrates nanosilver into a TiO2-chitosan matrix (nano-Ag/TiO2-CS) to inactivate the non-enveloped bacteriophage MS2 as a viral aerosol surrogate. The materials were characterized using various techniques, such as X-ray diffraction (XRd), scanning electron microscopy (SEM), high-resolution transmission electron microscopy (HR-TEM), and X-ray photoelectron spectroscopy (XPS). The SEM images showed that the nano-Ag particles were spheres with a high surface area for virus interactions and that the fiber surfaces were covered by nano-Ag, which enhanced contact with viruses. The optimal 5 wt% nano-Ag/TiO2-CS filter combined with a negative air ionizer (NAI) showed the highest viral aerosol removal efficiency, which reached 97 %. The use of an NAI during filtration enhanced the inactivation of the viral aerosols. A long-term antiviral efficacy assessment showed that the nano-Ag/TiO2-CS filter demonstrated robust durability, which is vital for real-world applications. The nanofilter proposed in this work is simple, safe, and cost-effective for inactivating viral aerosols to improve indoor air quality. © 2024 Elsevier Ltd

关键词： Aerosols

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：