检索结果-内蒙古大学图书馆

The role of input imaging combination and ADC threshold on segmentation of acute ischemic stroke lesion using U-Net

European Radiology 2023年第9期33卷 6157-6167页

作者： Li, Ya-Hui Lin, shao-Chieh Chung, Hsiao-Wen Chang, Chia-Ching Peng, Hsu-Hsia Huang, Teng-Yi shen, Wu-Chung Tsai, Chon-Haw Lo, Yu-Chien Lee, Tung-Yang Juan, Cheng-Hsuan Juan, Cheng-En Chang, Hing-Chiu Liu, Yi-Jui Juan, Chun-Jung Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei Taiwan Department of Medical Imaging China Medical University Hsinchu Hospital No. 199 Sec. 1 Xinglong Rd. Zhubei City Hsinchu County 302 Hsinchu Taiwan Ph.D. Program in Electrical and Communication Engineering Feng Chia University Taichung Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan Department of Management Science National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Biomedical Engineering and Environmental Sciences National Tsing Hua University Hsinchu Taiwan Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Radiology School of Medicine College of Medicine China Medical University Taichung Taiwan Department of Medical Imaging Medical University Hospital Taichung Taiwan Department of Neurology China Medical University Hospital Taichung Taiwan Cheng Ching Hospital Taichung Taiwan Master’s Program of Biomedical Informatics and Biomedical Engineering Feng Chia University Taichung Taiwan Department of Automatic Control Engineering Feng Chia University No. 100 Wenhwa Rd. Seatwen Taichung 40724 Taiwan Department of Biomedical Engineering The Chinese University of Hong Kong ERB1112 11/F William M.W. Mong Engineering Building N.T Shatin Hong Kong Multi-Scale Medical Robotics Center The Chinese University of Hong Kong N.T Shatin Hong Kong Department of Biomedical Engineering National Defense Medical Center Taipei Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan

Background: To evaluate the effect of the weighting of input imaging combo and ADC threshold on the performance of the U-Net and to find an optimized input imaging combo and ADC threshold in segmenting acute ischemic stroke (AIs) lesion. Methods: This study retrospectively enrolled a total of 212 patients having AIs. Four combos, including ADC-ADC-ADC (AAA), DWI-ADC-ADC (DAA), DWI-DWI-ADC (DDA), and DWI-DWI-DWI (DDD), were used as input images, respectively. Three ADC thresholds including 0.6, 0.8 and 1.8 × 10–3sup> mm2sup>/s were applied. Dice similarity coefficient (DsC) was used to evaluate the segmentation performance of U-Nets. Nonparametric Kruskal–Wallis test with Tukey–Kramer post-hoc tests were used for comparison. A p <.05 was considered statistically significant. Results: The DsC significantly varied among different combos of images and different ADC thresholds. Hybrid U-Nets outperformed uniform U-Nets at ADC thresholds of 0.6 × 10–3sup> mm2sup>/s and 0.8 × 10–3sup> mm2sup>/s (p <.001). The U-Net with imaging combo of DDD had segmentation performance similar to hybrid U-Nets at an ADC threshold of 1.8 × 10–3sup> mm2sup>/s (p =.062 to 1). The U-Net using the imaging combo of DAA at the ADC threshold of 0.6 × 10–3sup> mm2sup>/s achieved the highest DsC in the segmentation of AIs lesion. Conclusions: The segmentation performance of U-Net for AIs varies among the input imaging combos and ADC thresholds. The U-Net is optimized by choosing the imaging combo of DAA at an ADC threshold of 0.6 × 10–3sup> mm2sup>/s in segmentating AIs lesion with highest DsC. Key Points: • segmentation performance of U-Net for AIs differs among input imaging combos. • segmentation performance of U-Net for AIs differs among ADC thresholds. • U-Net is optimized using DAA with ADC = 0.6 × 10–3sup>mm2sup>/s. © 2023, The Author(s), under exclusive licence to European society of Radiology.

关键词： Deep Learning Diffusion Magnetic Resonance Imaging Ischemic stroke Neural Networks, Computer Retrospective study

来源：评论

学校读者我要写书评

暂无评论

Improving Hydrogeneration Representation in a Production Cost Model Used for Long-Term Transmission studies in the Western Interconnection

Improving Hydrogeneration Representation in a Production Cos...

引用

IEEE/PEs Power systems Conference and Exposition

作者： C. M. Dennis R. C. Walish H. M. Pacini T. A. Chisholm T. L. Acker Master's of Science in Engineering program at Northern Arizona University in Flagstaff Western Electricity Coordinating Council Bonneville Power Ad-ministration Portland Northern Arizona University in Flagstaff

ISBN: (纸本)9781612847894

The Western Electricity Coordinating Council, recognizing the importance of interconnection-wide transmission planning, formed the Transmission Expansion Planning Policy Committee (TEPPC) in 2006. TEPPC is tasked with conducting regional transmission expansion planning studies involving system modeling;as well as performing analyses of future transmission congestion and operational impacts. TEPPC utilizes the production cost model (PCM) PROMOD IV to model the Western Interconnection for these studies. In certain geographic regions, a high level of hydropower penetration necessitates careful consideration of hydrogeneration models used in the PCM to produce the most accurate system results. This work details the hydro modeling methods utilized by TEPPC for improving hourly hydrogeneration time series representations in transmission planning studies. The justification and benefits for using these methods are outlined in this paper, and the results of a 2019 transmission study are shown to illustrate of the advantages for employing these methods.

关键词： Hydroelectric generators Hydroelectric power generation Production cost model Hydrogeneration shape Power system modeling Proportional load following Hydrothermal co-optimization WECC system transmission studies Hydrogene-ration model

来源：评论

学校读者我要写书评

暂无评论

AUTOMATION OF PROPELLER INsPECTION AND FINIsHING

引用

NAVAL ENGINEERs JOURNAL 1985年第4期97卷 124-131页

作者： sTERN, H METZGER, R Howard K. Stern:is presently vice president of Robotic Vision Systems Inc. He received a bachelor of electrical engineering degree from College of the City of New York in 1960. Mr. Stern joined Dynell Electronics Corporation in 1971 and became part of the Robotic Vision Systems Inc. staff at the time of its spin-off from Dynell. He was program manager of the various three-dimensional sensing and replication systems constructed by Dynell and Robotic Vision Systems. As program manager his responsibilities encompassed technical administrative and operational areas. The first two portrait sculpture studio systems and the first three replication systems built by Robotic Vision Systems Inc. were designed manufactured and operated under his direction. Before joining Dynell Mr. Stern was a senior engineer at Instrument Systems Corporation and chief engineer of the Special Products Division of General Instrument Corporation. Prior to these positions Mr. Stern was chief engineer of Edo Commercial Corporation. At General Instrument and Edo Commercial he was responsible for the design and manufacture of military and commercial avionics equipment. Mr. Stern is presently responsible for directing the systems design and development for all of the company's programs. Robert J. Metzger:is currently engineering group leader at Robotic Vision Systems Inc. He graduated summa cum laude from the Cooper Union in 1972 with a bachelor of electrical engineering degree. Under sponsorship of a National Science Foundation graduate fellowship he graduated from the Massachusetts Institute of Technology in 1974 with the degrees of electrical engineer and master of science (electrical engineering). In 1979 Mr. Metzger graduated from Polytechnic Institute of New York with the degree of master of science (computer science). Since 1974 Mr. Metzger has been actively engaged in the design of systems and software for noncontact threedimensional optical measurement for both military and commercial applications. Of particular note are his c

ship's propellers are currently measured by manual procedures using pitchometers, templates and gauges. This measurement process is extremely tedious, labor intensive and time consuming. In an effort to provide increased accuracy, repeatability and cost effectiveness in propeller manufacture, an automated propeller optical measurement system (APOMs) has been built which rapidly and automatically scans an entire ship's propeller using a 3-D vision sensor. This equipment is integrated with a propeller robotic automated templating system (PRATs) and the propeller optical finishing system (PROFs) which robotically template and grind the propeller to its final shape, using the APOMs-derived data for control feedback. The optical scanning and the final shape are both controlled by CAD/CAM data files describing the desired propeller shape. An automated propeller balancing system is incorporated into the PROFs equipment. The APOMs/PRATs/PROFs equipment is expected to provide lower propeller manufacturing costs.

关键词： PROPELLERs

来源：评论

学校读者我要写书评

暂无评论

superhydrophilic self-cleaning surfaces based on TiO2sub> and TiO2sub>/siO2sub> composite films for photovoltaic module cover glass

引用

Applied Adhesion science 2015年第1期3卷 1-9页

作者： Jesus, Magnum Augusto Moraes Lopes de Neto, João Trajano da silva Timò, Gianluca Paiva, Paulo Renato Perdigão Dantas, Maria sylvia s Ferreira, Angela de Mello Master Program in Materials Engineering Centro Federal de Educação Tecnológica de Minas Gerais – campus I Av. Amazonas 5253 Nova Suiça 30421-169 Belo Horizonte MG Brazil Ricerca Sul Sistema Energetico - RSE S.p.A Le Mose Piacenza 29100 Italy National Institute of Science and Technology on Mineral Resources Water and Biodiversity (INCT-Acqua) - Av. Antônio Carlos 627 Pampulha 31270-901 Belo Horizonte MG Brazil Chemistry Department Centro Federal de Educação Tecnológica de Minas Gerais – campus I Av. Amazonas 5253 Nova Suiça 30421-169 Belo Horizonte MG Brazil

self-cleaning surfaces have excelled in recent years in energy and environmental fields. In particular, in solar energy area, these surfaces are used to avoid soiling accumulation on photovoltaic (PV) modules. so far TiO2sub> has been widely used due to its photocatalytic activity and photo-induced superhydrophilicity. However, this oxide has some limitations since it reduces the glass transmittance and it rapidly reestablish the water contact angle in dark environments. In order to circumvent these limitations, composites TiO2sub>/siO2sub> have been proposed. For photovoltaic application, besides a good transparency in the wavelength region 300–1800 nm and self-cleaning properties, the coating should also present long durability and adequate adhesion to endure the outdoor conditions. Aiming at developing a coating with these properties, in this work, TiO2sub>/siO2sub> composites containing different titanium content have been synthesized and compared with pure TiO2sub> films in relation to adhesion, transparency and hydrophilicity. Both films have been deposited over low iron float glass substrates by sol–gel dip-coating technique and different calcination temperatures (400, 500, 600°C) and si/Ti molar rates (si86sub>Ti14sub>, si40sub>Ti60sub>) have been considered. TiO2sub>/siO2sub> films showed higher transmittance in visible range compared with pure TiO2sub>. TiO2sub>/siO2sub> films showed superhydrophilic character before and after ultraviolet irradiation, with water contact angles near to 0°. Furthermore, as predicted, TiO2sub>/siO2sub> films could keep the superhydrophilic character in dark environments, in contrast with pure TiO2sub> films. Both TiO2sub> and TiO2sub>/siO2sub> films exhibited good adherence and it is shown that higher calcination temperatures and higher titanium content enhance such property. All f

关键词： self-cleaning surfaces sol–gel superhydrophilicity Thin film TiO2 TiO2/siO2 composite

来源：评论

学校读者我要写书评

暂无评论

Prediction of Hydrogen Production Rate in Anaerobic Fermentation Using Grey Relation Analysis and Machine Learning

SSRN

引用

ssRN 2023年

作者： Wang, Yifan Wu, Jinghui Tseng, Yu-Yao Zhao, Chunliang Li, Keqing Wang, Xianze Wang, Ming-Hung Lay, Chyi-How Huo, Mingxin Engineering Research Center of Low-Carbon Treatment Green Development of Polluted Water in Northeast China Ministry of Education Changchun130117 China Science and Technology Innovation Center for Municipal Wastewater Treatment and Water Quality Protection Northeast Normal University Changchun130117 China Key Laboratory of Songliao Aquatic Environment Ministry of Education Jilin Jianzhu University Changchun130118 China Master's Program of Green Energy Science and Technology Feng Chia University Taichung40724 Taiwan Department of Computer Science and Information Engineering National Chung Cheng University Chiayi County Taiwan

Anaerobic fermentation for hydrogen production has many environmental factors that limit microbial activity, but machine learning has enormous potential in handling the complexity of biological processes. This study explores the potential of machine learning in predicting hydrogen production rates (HPR) from anaerobic fermentation of biomass energy. Grey relation analysis was conducted to determine the correlation between operational parameters and HPR. Five machine learning algorithms, such as decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and K-nearest neighbor (KNN), were then paired with operating conditions and water quality performance as features and HPR as a label, with mean squared error (MsE) and R2 as evaluation indexes. Butyric acid, oxidation-reduction potential (ORP), and volatile suspended solids (Vss) were found to play crucial roles in hydrogen production from sucrose anaerobic fermentation. XGBoost had the highest accuracy with R2 of 0.91 and MsE of 0.0052. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Reconstructing suspended sediment concentrations in the Mekong River Basin via semi-supervised-based deep neural networks

引用

science of the Total Environment 2024年 955卷 176758页

作者： Nguyen, Thi Thu Ha Vu, Duc Quang Doan, Ngoc Phu Chi, Huynh Thi Khanh Li, Peixin Binh, Doan Van An, Yimeng Dung, Pham Tuan Hoang, Tuan A. son, Mai Thai Laboratory of Environmental Sciences and Climate Change Institute for Computational Science and Artificial Intelligence Van Lang University Ho Chi Minh City Viet Nam Faculty of Environment School of Technology Van Lang University Ho Chi Minh City Viet Nam Department of Computer Science and Information System Thai Nguyen University of Education Viet Nam School of Electronics Electrical Engineering and Computer Science Queen's University Belfast United Kingdom College of Economics and Management Nanjing University of Aeronautics and Astronautics China Master program in Water Technology Reuse and Management Faculty of Engineering Vietnamese-German University Binh Duong Province Ben Cat City Viet Nam

The Mekong River Basin (MRB) is crucial for the livelihoods of over 60 million people across six southeast Asian countries. Understanding long-term sediment changes is crucial for management and contingency plans, but the sediment concentration data in the MRB are extremely sporadic, making analysis challenging. This study focuses on reconstructing long-term suspended sediment concentration (ssC) data using a novel semi-supervised machine learning (ML) model. The key idea of this approach is to exploit abundant available hydroclimate data to reduce training overfitting rather than solely relying on sediment concentration data, thus enhancing the accuracy of the employed ML models. Extensive experiments on daily hydroclimate and ssC data obtained from 1979 to 2019 at the three main stations (i.e., Chiang saen, Nong Khai, and Mukdahan) are conducted to demonstrate the superior performance of the proposed method compared to the state-of-the-art supervised techniques (i.e., Random Forest, XGBoost, CatBoost, MLP, CNN, and LsTM), and surpasses existing semi-supervised methods (i.e., CoReg, ⊓ Model, ICT, and Mean Teacher). This approach is the first semi-supervised method to reconstruct sediment data in the field and has the potential for broader application in other river systems. © 2024 The Author(s)

关键词： self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Exploration of Dark Chemical Genomics space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology

Research Square

引用

Research square 2021年

作者： Cai, Tian Xie, Li Chen, Muge Liu, Yang He, Di Zhang, shuo Mura, Cameron Bourne, Philip E. Xie, Lei Ph.D. Program in Computer Science The Graduate Center The City University of New York New York10016 United States Department of Computer Science Hunter College The City University of New York New York10065 United States Master Program in Computer Science Courant Institute of Mathematical Sciences New York University United States School of Data Science Department of Biomedical Engineering University of Virginia VA22903 United States Helen and Robert Appel Alzheimer’s Disease Research Institute Feil Family Brain & Mind Research Institute Weill Cornell Medicine Cornell University New York10021 United States

Advances in biomedicine are largely fueled by exploring uncharted territories of human biology. Machine learning can both enable and accelerate discovery, but faces a fundamental hurdle when applied to unseen data with distributions that differ from previously observed ones—a common dilemma in scientific inquiry. We have developed a new deep learning framework, called Portal Learning, to explore dark chemical and biological space. Three key, novel components of our approach include: (i) end-to-end, step-wise transfer learning, in recognition of biology’s sequence-structure-function paradigm, (ii) out-of-cluster meta-learning, and (iii) stress model selection. Portal Learning provides a practical solution to the out-of-distribution (OOD) problem in statistical machine learning. Here, we have implemented Portal Learning to predict chemical-protein interactions on a genome-wide scale. systematic studies demonstrate that Portal Learning can effectively assign ligands to unexplored gene families (unknown functions), versus existing state-of-the-art methods. Compared with AlphaFold2-based protein-ligand docking, Portal Learning significantly improved the performance by 79% in PR-AUC and 27% in ROC-AUC, respectively. The superior performance of Portal Learning allowed us to target previously "undruggable" proteins and design novel polypharmacological agents for disrupting interactions between sARs-CoV-2 and human proteins. Portal Learning is general-purpose and can be further applied to other areas of scientific inquiry. © 2021, CC BY.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Exploration of dark chemical genomics space via portal learning: Applied to targeting the undruggable genome and COVID-19 anti-infective polypharmacology

arXiv

引用

arXiv 2021年

Advances in biomedicine are largely fueled by exploring uncharted territories of human biology. Machine learning can both enable and accelerate discovery, but faces a fundamental hurdle when applied to unseen data with distributions that differ from previously observed ones—a common dilemma in scientific inquiry. We have developed a new deep learning framework, called Portal Learning, to explore dark chemical and biological space. Three key, novel components of our approach include: (i) end-to-end, step-wise transfer learning, in recognition of biology’s sequence-structure-function paradigm, (ii) out-of-cluster meta-learning, and (iii) stress model selection. Portal Learning provides a practical solution to the out-of-distribution (OOD) problem in statistical machine learning. Here, we have implemented Portal Learning to predict chemical-protein interactions on a genome-wide scale. systematic studies demonstrate that Portal Learning can effectively assign ligands to unexplored gene families (unknown functions), versus existing state-of-the-art methods, thereby allowing us to target previously "undruggable" proteins and design novel polypharmacological agents for disrupting interactions between sARs-CoV-2 and human proteins. Portal Learning is general-purpose and can be further applied to other areas of scientific *** Codes 68T07 © 2021, CC BY.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Pearl Harbor Naval Base's donut-free bilge and oily wastewater disposal program

引用

NAVAL ENGINEERs JOURNAL 1995年第6期107卷 65-77页

作者： Gensure, JR Lieutenant John R. Gensure USN:is an Engineering Dufy Officer attached to Pearl Harbor Naval Shipyard and is currently serving as the Business and Strategic Planning Office's Submarine Business Operations Division Officer. Since 1992 he has played a major role in the development of the shipyaRD's bilge and oily wastewater disposal program. Previously he served aboard the USS Benjamin Franklin (SSBN 640) where he qualified for his Submarine Gold Dolphins and received two Navy Achievement Medals and the Battle Efficiency “E.” Lt. Gensure graduated with a Bachelor of Science degree in Physics from the U.S. Naval Academy in 1986 and a Master of Science degree in Electrical Engineering from the Naval Postgraduate School in 1992. He is a member of Sigma Pi Sigma and Eta Kappa Nu hmoraries a member of the U.S. Naval Institute and a life member of the American Sociefy of Naval Engineers (ASNE).

In April 1991, the Chief of Naval Operations directed all Naval activities to eliminate the use of Oil Disposal Rafts (donuts) as soon as possible for the disposal of bilge and oily wastewater. Pearl Harbor Naval shipyard removed its donuts from service in 1991, and as of 1 October 1994, all donuts have been removed from service throughout the Pearl Harbor Naval Complex. Bilge and oily wastewater are composed of approximately 96 percent water, 3 percent oil, and 1 percent sludge. Oils and metals in suspension prevent bilge and oily wastewater from being processed via conventional indus trial wastewater or used oil treatment facilities. In December 1992, Pearl Harbor Oily Waste/Waste Oil (OWWO) Task Force initiated a Bilge and Oily Wastewater Management Plan based on the utilization of Bilge and Oily Wastewater Treatment Trains for the treatment of bilge and oily wastewater. The Treatment Trains processes influent wastewater, producing solidified sludge, used oil, and treated effluent wastewater that meets federal and state discharge limits for sewage disposal. During the period December 1992 to July 1995, Pearl Harbor Naval Base's Treatment Trains successfully processed over 11.6 million gallons of bilge and oily wastewater realizing an estimated cost savings of between $2.0 and $5.0 million over contracting out for the same service.

关键词： Wastewater disposal

来源：评论

学校读者我要写书评

暂无评论

The gap values in the profile matching method by fuzzy logic

引用

Journal of Physics: Conference series 2018年第1期978卷

作者： s A sitepu s Efendi Z situmorang Master Program (S2) of Informatics Engineering Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia. Master Program of Informatics Engineering Faculty of Computer Science and Information Technology Universitas of Sumatera Utara Medan Indonesia. Department of Computer Science Faculty of Computer Science and Information Technology Universitas St. Thomas Medan Indonesia.

In this research, the determination of the appropriate values of Gap for the assessment of promotion criteria of position in an institution / company. In this study the authors use Fuzzy sugeno logic on the determination of Gap values used in Profile Matching method. Test results of 5 employees obtained the eligibility of promotion with the position of Z* values between in 3.20 to 4.11.

关键词：

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：