检索结果-内蒙古大学图书馆

Negative data in data Sets for Machine Learning Training

JOUrNAL OF OrGANIC CHEMISTrY 2023年第9期88卷 5239-5241页

作者： Maloney, Michael P. Coley, Connor W. Genheden, Samuel Carson, Nessa Helquist, Paul Norrby, Per-Ola Wiest, Olaf Department of Chemistry and Biochemistry University of Notre Dame Notre Dame Indiana 46556 United States Department of Chemical Engineering and Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 United States Molecular AI Discovery Sciences R&D AstraZeneca Gothenburg Pepparedsleden 1 SE-431 83 Mölndal Sweden Early Chemical Development Pharmaceutical Sciences R&D AstraZeneca Macclesfield SK10 2NA U.K. Data Science and Modelling Pharmaceutical Sciences R&D AstraZeneca Gothenburg Pepparedsleden 1 SE-431 83 Mölndal Sweden

来源：评论

学校读者我要写书评

暂无评论

Enhanced convolutional neural network methodology for solid waste classification utilizing data augmentation techniques

Waste Management Bulletin

引用

Waste Management Bulletin 2024年第4期2卷 184-193页

作者： Hogan Itam, daniel Chimeme Martin, Ekwueme Taiwo Horsfall, Ibiba Department of Civil and Environmental Engineering Faculty of Engineering & Technology University of Calabar Cross Rivers State Nigeria Department of Agricultural and Bioresources Engineering Michael Okpara University of Agriculture Abia State Umudike Nigeria Department of Research and Development (R&D) Eco-Thrivetide Consulting Ltd Rivers State Port Harcourt Nigeria

The increasing volume of solid waste generated globally necessitates efficient classification systems to enhance recycling and waste management processes. Convolutional Neural Networks (CNNs) have emerged as a powerful tool for image classification tasks, including solid waste identification. However, difficult external variables including changes in illumination, occlusion, and background clutter can have a big impact on CNN performance. Furthermore, pooling procedures frequently cause classic CNNs to lose spatial information, which might impair performance on tasks requiring extremely fine sense of place. This paper presents a comprehensive study on the application of an improved CNN-based models for solid waste classification. In the present study we explored image data resizing, augmentation technique and hyperparameter tuning to improve the performance of the proposed model. The results demonstrate that the improved-CNN model achieved high accuracy of 94.40 % compared to the conventional CNN and other deep learning model such as resNet-50, Inception-V3 and VGG-19 (81.83, 66.67, 52.83 and 56.00 %). © 2024 The Authors

关键词： data augmentation techniques Enhanced convolutional neural network (ECNN) Machine learning in waste management Solid waste classification

来源：评论

学校读者我要写书评

暂无评论

robust bonding at 175°C of pressureless Ag nanoparticle sinter joint on Ni/Au finished Cu substrates in air 22

Robust bonding at 175°C of pressureless Ag nanoparticle sin...

引用

22nd International Conference on Electronics Packaging, ICEP 2023

作者： Kim, Seoah Kim, Min-Su Mhin, Sungwook Kim, dongjin Korea Institute of Industrial Technology Advance Joining and Additive Manufacturing R&D Department Incheon21999 Korea Republic of Kyonggi University Graduate School Department of Advanced Materials Engineering Suwon16227 Korea Republic of

ISBN: (纸本)9784991191152

Ag sinter joining which has exceptional characteristics is promising as a die-attach material for wide band-gap (WBG) power devices in electric vehicles (EVs). So far, many Ag sinter joining technologies in the range of 250 °C to 300 °C have been developed, but the industry still requires lower die-attach temperatures and more accessible processing methods. We have been pursuing technology that minimizes die-attach temperature and pressure to minimize the warpage of the power module structure. In this work, a pressureless Ag sintering was carried out in air at 175 °C without any pressure, and the bonding strength achieved approximately 37 MPa. The robust bonding mechanism of the Ag sinter joining was investigated using EBSd and Xrd analysis on the microscale. This study can provide a solution for the possibility of the diebonding process at 175 °C and effective heat dissipation design of the power module. © 2023 Japan Institute of Electronics Packaging.

关键词： Energy gap

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation of Control rod drops Into Perturbed Fuel Assemblies

引用

Journal of Nuclear Engineering and radiation Science 2023年第4期9卷 041801页

作者： Park, Namgyu Kwon, Ohjoon Yoo, Youngik Kim, Taesoon Nuclear Fuel Technology Department R&D Center KEPCO Nuclear Fuel Daedeok-daero 989 beon-gil Yuseong-gu Daejeon34057 Korea Republic of Nuclear Fuel Technology Department R&D Center KEPCO Nuclear Fuel 242 Daedeok-daero 989 beon-gil Yuseong-gu Daejeon34057 Korea Republic of SMR Development Unit Central Research Institute Korea Hydro & Nuclear Power Co. LTD 70 Yuseong-daero 1312 beon-gil Yuseong-gu Daejeon34101 Korea Republic of

This paper discusses permanent deformation of the fuel assembly of pressurized water reactors that have to satisfy a drop time requirement of the control rod assembly. during a seismic event, the fuel assemblies and the reactor core exhibit transient vibration. When the fuel assemblies collide, they develop impact forces in the spacer grids along the fuel assemblies. If the impact forces on some spacer grids of the fuel assembly exceed an allowable strength, the buckling occurs in the corresponding spacer grids, followed by permanent deformation. The geometry change of the buckled spacer grids leads to the movement of the guide tube positions in the fuel assembly. Therefore the geometry change is associated with the distortion of the control rod drop path. In this study, the permanent deformation of the spacer grids was measured during the impact tests, and the maximum deviation of the guide tube from the original position was investigated. Control rod drop tests were also performed to measure the change in drop time according to the deformation of the fuel assembly. Using actuators in the loop test facility, the authors realized the first and second bending mode shapes of the fuel assembly under the flowing water condition. Based on a series of drop tests, the critical fuel assembly deformation was identified that could lead to a violation of an allowable drop time of the control rod. Copyright © 2023 by ASME.

关键词： Control rods

来源：评论

学校读者我要写书评

暂无评论

Arc plasma-deposited Co single-atom catalysts supported on an aligned carbon nanofiber for hydrogen peroxide electrosynthesis and an electro-Fenton process

引用

Carbon Energy 2024年第11期6卷 234-255页

作者： Chang‐Kyu Hwang Sooyeon Kim Ki ro Yoon Thao Thi Le Chinh V.Hoang Jae Won Choi Wenjun Zhang Sae Yane Paek Chung Hyeon Lee Ji Hyun Lee Keun Hwa Chae Sohee Jeong Seung Yong Lee Byeong-Kwon Ju Sang Hoon Kim Sang Soo Han Jong Min Kim Materials Architecturing Research Center Korea Institute of Science and Technology (KIST))seculSecrngbuk-guRepublic of Korea Department of Micro/Nano Systems Korea UniversitySeoulSeongbuk-guRepublic of Korea Computational Science Research Center Korea Institute of Science and Technology (KIST)SeculSecrngbuk-guRepublic of Korea Advanced Textile R&D Department Korea Institute of Industrial Technology (KITECH)AmsanGyeonggi-doRepublic of Korea Extreme Materials Research Center Korea Institute of Science and Technology (KIST)SeoulSeongbuk:guRepubic of Korea Nanoscience and Technology KIST School University of Science and TechnologySeoulRepublic of Korea Advanced Analysis and Data Center Korea Institute of Science and TechnologySeoulSeongbuk-guRepublic of Korea Display and Nanosensor Laboratory School of Electrical Engineering Korea UniversitySeoulSeongbuk guRepublic of Korea KHU-KIST Department of Converging Science and Technology Kyung Hee UniversitySeoulSeongbuk-guRepubic of Korea

Atomically dispersed single-atom catalysts(SACs)on carbon supports show great promise for H_(2)O_(2) electrosynthesis,but conventional wet chemistry methods using particulate carbon blacks in powder form have limited their potential as two-electron(2^(e−))oxygen reduction reaction(Orr)***,we demonstrate high-performance Co SACs supported on a free-standing aligned carbon nanofiber(CNF)using electrospinning and arc plasma deposition(APd).Based on the surface oxidation treatment of aligned CNF and precise control of the deposition amount in a dry-based APd process,we successfully form densely populated Co SACs on aligned *** experimental analyses and density functional theory calculations,we reveal that Co SAC has a Co–N_(2)–O_(2) moiety with one epoxy group,leading to excellent 2^(e−)Orr ***,the aligned CNF significantly improves mass transfer in flow cells compared to randomly oriented CNF,showing an overpotential reduction of 30 mV and a 1.3-fold improvement(84.5%)in Faradaic efficiency,and finally achieves an outstanding production rate of 15.75 mol gcat^(−1) h^(−1) at 300 mA cm^(−2).The high-performance Co SAC supported on well-aligned CNF is also applied in an electro-Fenton process,demonstrating rapid removal of methylene blue and bisphenol F due to its exceptional 2e^(−)Orr activity.

关键词： arc plasma deposition electro-Fenton flow reactor hydrogen peroxide production oxygen reduction reaction single-atom catalysts

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Predictive Modelling of Spot-Welding Process Parameters 6th

Machine Learning-Based Predictive Modelling of Spot-Welding ...

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Burande, dinesh V. Kalita, Kanak Chohan, Jasgurpeet Singh Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi India Department of Mechanical Engineering University Centre for Research and Development Chandigarh University Mohali India

ISBN: (纸本)9783031362453

This research paper presents a comparative study of machine learning (ML) algorithms for the predictive modelling of spot-welding process parameters. The focus is on predicting the nugget diameter (Nd) and nugget height (NH) using four different ML algorithms (namely, linear regression, random forest regression, adaptive boosting regression, and support vector machine regression). An experimental dataset consisting of fifty data points is used in this study. Exploratory data analysis was carried out to investigate the effect of process parameters on the response variables. Performance evaluation metrics were employed to gauge the predictive accuracy of the ML models. The results indicate that the random forest regression demonstrates superior performance in predicting both Nd and NH compared to the other algorithms. This study can serve as a foundation for further research in optimizing the spot-welding process through machine learning techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

ELECTrIC FIELd rELAXATION BY FGM ON PErMITTIVITY TO THrEE-COrE TYPE GIS SPACEr 23

ELECTRIC FIELD RELAXATION BY FGM ON PERMITTIVITY TO THREE-CO...

引用

23rd International Symposium on High Voltage Engineering, ISH 2023

作者： Kato, Katsumi Bito, Soya Nomura, ryuto Masui, Hidetaka Okamoto, Kenji Department of Electrical Engineering and Information Science NIT Niihama College Niihama Japan Advanced Technology Laboratory Corporate R&D Headquarters Fuji Electric Co. Ltd. Hino Japan

ISBN: (纸本)9781839539954

For the relaxation of electric field (E-field) stress around Gas Insulated Switchgears (GIS) spacer, we have proved the effectiveness of an application of spacer with functionally graded materials (FGM) with a spatial distribution of permittivity H (H-FGM). However, we have investigated the effectiveness of the FGM spacer only in the case of single-core type GIS, so far. For wider application of the FGM spacer, it is needed to investigate its effectiveness not only in single-core type but also in three-core type GIS. For this purpose, in this paper, we carried out the three-dimensional electric field analysis for three-core type GIS, in order to investigate the E-field relaxation effect by an application of H-FGM spacer. Firstly as fundamental investigations, we consider a simplified model for a three-core type FGM spacer. The cone-type spacer model for the three-core type GIS is used. We added H distribution into the internal part of the spacer. Then we calculate E-field stress in and around three-core type GIS spacer for various H distributions inside the spacer. Finally, we quantified relaxation effect of the maximum E-field stress. © The Institution of Engineering & technology 2023.

关键词： Permittivity

来源：评论

学校读者我要写书评

暂无评论

Mesoporous SiO_(2)nanoparticles with low surface energy and multi-level roughness as shale wellbore stabilizers in oil-based drilling fluid

引用

Petroleum Science 2025年第1期22卷 384-397页

作者： Hong-Yan du Kai-He Lv Jin-Sheng Sun Mei-Chun Li Yuan Geng Xian-Bin Huang Hao-Kun Shen Muhammad Arqam Khan School of Petroleum Engineering China University of PetroleumEast ChinaQingdao266580ShandongChina Key Laboratory of Unconventional Oil&Gas Development Ministry of EducationQingdao266580ShandongChina CNPC Engineering Technology R&D Company Ltd. Beijing102206China Co-Innovation Center of Efficient Processing and Utilization of Forest Resources College of Materials Science and EngineeringNanjing Forestry UniversityNanjing210000JiangsuChina Department of Petroleum Engineering NED University of Engineering&Technology395007Pakistan

Oil-based drilling fluids possess excellent properties such as shale inhibition, cuttings suspension, and superior lubrication, making them essential in the development of unconventional oil and gas ***, wellbore instability, caused by the invasion of drilling fluids into shale formations, remains a significant challenge for the safe and efficient extraction of shale oil and gas. This work reports the preparation of mesoporous SiO2nanoparticles with low surface energy, utilized as multifunctional agents to enhance the performance of oil-based drilling fluids aimed at improving wellbore stability. The results indicate that the coating prepared from these nanoparticles exhibit excellent hydrophobicity and antifouling properties, increasing the water contact angle from 32°to 146°and oil contact angle from 24°to134.8°. Additionally, these nanoparticles exhibit exceptional chemical stability and thermal *** these nanoparticles into oil-based drilling fluids reduced the surface energy of the mud cake from 34.99 to 8.17 m J·m-2and increased the roughness of shale from 0.26 to 2.39 μm. These modifications rendered the mud cake and shale surfaces amphiphobic, effectively mitigating capillary infiltration and delaying the long-term strength degradation of shale in oil-based drilling fluids. After 28days of immersion in oil-based drilling fluid, shale cores treated with MF-SiO2exhibited a 30.5% increase in compressive strength compared to untreated cores. Additionally, these nanoparticles demonstrated the ability to penetrate and seal rock pores, reducing the API filtration volume of the drilling fluid from11.2 to 7.6 m L. This study introduces a novel approach to enhance the development of shale gas and oil resources, offering a promising strategy for wellbore stabilization in oil-based drilling fluid systems.

关键词： Fluorosilane Wettability Wellbore stability drilling engineering Self-cleaning Antifouling

来源：评论

学校读者我要写书评

暂无评论

Surface modification of Li1.3Al0.3Ti1.7(PO4)3 solid electrolytes by polymethylsiloxane-based polymer for all-solid-state lithium batteries

引用

Ceramics International 2024年第16期51卷 22556-22564页

作者： Liu, Kai-Wen Hsu, Ping-Hsuan Chang, Jeng-Kuei Wang, Fu-Ming Liu, Wei-ren Department of Chemical Engineering Chung Yuan Christian University Taoyuan City32023 Taiwan R&D Center for Membrane Technology Chung Yuan Christian University Taoyuan City32023 Taiwan Sustainable Energy Development Centre Graduate Institute of Applied Science & Technology National Taiwan University of Science and Technology Taipei City10607 Taiwan Department of Materials Science and Engineering National Yang Ming Chiao Tung University 1001 University Road Hsinchu City30010 Taiwan

Lithium all-solid-state batteries (LASSBs) face the challenge of poor performance, interface contact between electrodes, limiting voltage window of solid electrolytes, side reactions between cathode/solid electrolyte, anode/solid electrolyte and so on. To motivate the pursuit of advanced solutions, one of the efficient approaches is to design all-solid-state inorganic/polymer composite electrolytes. This study addresses limitations associated with Li1.3Al0.3Ti1.7(PO4)3 (LATP) as an inorganic solid electrolyte, including instability and short cycle life, by introducing organic-based ethylene glycol methyl ether methacrylate-co-acrylate acid functional groups (AAM950) polymer as a protective interphase between LATP pellet and Li metal. The synergistic effects of LATP pellet and AAM950 reduces the interfacial resistance between LATP pellet and Li metal and significantly suppresses lithium dendrite growth during charge and discharge processes. The ionic conductivity of LATP/AAM950 solid electrolyte exhibits ionic conductivity of 9.3 × 10−4 S/cm at room temperature, while Li stripping/plating tests demonstrates overpotential below 0.2 V over 100 cycles at a current density of 0.63 mA/cm2. Furthermore, the modified LATP/AAM950 solid electrolyte can withstand a current density of 249 mA/cm2 at room temperature, which was a dramatic improvement compared to the LATP pellet's one of only 3 mA/cm2. Finally, we assemble an all-solid-state full cell by using NCM622@LATP||AAM950/LATP/AAM950||Li, which delivers an initial discharge capacity of 165.4 mAh/g and remain 132.9 mAh/g after 100 cycles at 0.1C, achieving a remarkable 80.4 % retention. These advancements contribute significantly to the field of Li all-solid-state batteries, fostering innovation in the energy industry. © 2024 Elsevier Ltd and Techna Group S.r.l.

关键词： Pelletizing

来源：评论

学校读者我要写书评

暂无评论

How well can PPG be an alternative to ECG for acute stress detection in nonresting state?—Comprehensive evaluation using a dNN

How well can PPG be an alternative to ECG for acute stress d...

引用

International Conference on Affective Computing and Intelligent Interaction Workshops and demos (ACIIW)

作者： Yasuhide Hyodo Kiyoshi Yoshikawa Takanori Ishikawa Yota Komoriya Human Technology R&D Department Technology Development Laboratories Sony Corporation Tokyo Japan

Heart rate variability (HrV) analysis in a wristband photoplethysmography (PPG) device is gathering interest for emotion and stress recognition. However, motion artifacts are a critical issue, and comprehensive evaluation from HrV analysis to the model performance and interpretability should be conducted. In this study, we constructed a physiologically interpretable evaluation framework of HrV analysis and acute stress recognition using a deep neural network (dNN) in a wrist-worn PPG device compared with that in a chest-worn electrocardiography (ECG) device, considering motion artifacts, which are an important issue in wild environments. Furthermore, we developed model training and testing methods using a dNN that takes signal quality into account to achieve both accuracy (robustness against motion artifacts) and model interpretability in acute stress recognition in the wrist-worn PPG device. The results suggest that the method we developed improved the acute stress recognition performance of the wrist-worn PPG device throughout our experiments (78.4% accuracy and 77.0% F1 score). In addition, it was observed that the method for the wrist-worn PPG device demonstrated comparable performance and interpretability to the reference method for the chest-worn ECG device.

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：