检索结果-内蒙古大学图书馆

IEEJ Transactions on Electronics, Information and systems 2024年第4期144卷 328-329页

作者： Sato, Hironobu Abe, Kiyohiko Matsuno, Shogo Ohyama, Minoru College of Science and Engineering Kanto Gakuin University 1-50-1 Mutsuura-higashi Kanazawa-ku Kanagawa Yokohama236-8501 Japan School of System Design and Technology Tokyo Denki University 5 Senju Asahi-cho Adachi-ku Tokyo120-8551 Japan Faculty of Informatics Gunma University 4-2 Aramaki-machi Maebashi Gunma371-8510 Japan

When developing a blink input interface, conscious (voluntary) and natural (involuntary) blink types must be automatically classified. We previously proposed a method for blink type classification using a 3D convolutional neural network (3D CNN). This CNN model outputs a predicted probability that determines three classes: "voluntary blinking," "involuntary blinking," and "not blinking" from a periocular image sequence. Previously, we found that the bias of the eye position in the input image is a factor that reduces the classification accuracy. To address this problem, we employ data augmentation with a shifting 5 or 10 pixels in the horizontal and/or vertical directions. © 2024 The Institute of Electrical Engineers of Japan.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Graded porous scaffold mediates internal fluidic environment for 3D in vitro mechanobiology

引用

Computers in Biology and Medicine 2025年 186卷 109674-109674页

作者： De Rosa, Chiara Angela Wright, Christopher J. Xiong, Yi Del Giudice, Francesco Zhao, Feihu Department of Biomedical Engineering Faculty of Science and Engineering Swansea University Swansea United Kingdom Zienkiewicz Institute for Modelling Data and AI Swansea University Swansea United Kingdom School of System Design and Intelligent Manufacturing Southern University of Science and Technology Guangdong Province Shenzhen China Complex Fluid Research Group Department of Chemical Engineering Faculty of Science and Engineering Swansea University Swansea United Kingdom

Most cell types are mechanosensitive, their activities such as differentiation, proliferation and apoptosis, can be influenced by the mechanical environment through mechanical stimulation. In three dimensional (3D) mechanobiological in vitro studies, the porous structure of scaffold controls the local mechanical environment that applied to cells. Many previous studies have focused on the topological design of homogeneous scaffold struts. However, the impact of scaffold inhomogeneity on the mechanical environment, which is essential in mechanobiological application (e.g. for multi-cells co-culture), remains elusive. In this study, we use a computational fluid dynamics (CFD) approach together with data analysis to study the influence of a porosity gradient (10 %–30 % porosity difference) on the local and global mechanical environment (wall shear stress - WSS) within the commonly used structures of triple periodic minimal surfaces (TPMS). In addition, the anisotropy of internal WSS and scaffold permeability caused by the porosity gradient is investigated. It is found that the influence of anisotropy on the average WSS and permeability is up to 11 % and 31 %, respectively. These results, as theoretical references will be useful to tissue engineers and mechanobiologists for scaffold design and in vitro experiment planning such as integrated use of graded scaffold and bioreactors for specific cell types. © 2025 The Authors

关键词： Shear stress

来源：评论

学校读者我要写书评

暂无评论

Selectivity of CO_(2)reduction reaction to CO on the graphitic edge active sites of Fe-single-atom and dual-atom catalysts:A combined DFT and microkinetic modeling

引用

Carbon Resources Conversion 2024年第1期7卷 21-31页

作者： Ahmad Nuruddin Adhitya Gandaryus Saputro Arifin Luthfi Maulana Febdian Rusydi Fiki Taufik Akbar Hadi Teguh Yudistira Hermawan Kresno Dipojono Advanced Functional Materials Research Group Faculty of Industrial TechnologyInstitut Teknologi BandungJl.Ganesha No.10Bandung 40132Indonesia Research Center for Nanosciences and Nanotechnology Institut Teknologi BandungJl.Ganesha No.10Bandung 40132Indonesia Research Center for Quantum Engineering Design Department of PhysicsFaculty of Science and TechnologyUniversitas AirlanggaSurabaya 60115Indonesia Theoretical High Energy Physics Research Division Faculty of Mathematics and Natural SciencesInstitut Teknologi BandungJl.Ganesha No.10Bandung 40132Indonesia Mechanical Engineering Study Program Institut Teknologi Sumatera(ITERA)South LampungLampungIndonesia Department of Materials Science and Engineering University of CaliforniaBerkeleyBerkeleyCA 94720United States

We study the carbon dioxide reduction reaction(CO_(2)RR)activity and selectivity of Fe single-atom catalyst(Fe-SAC)and Fe dual-atom catalyst(Fe-DAC)active sites at the interior of graphene and the edges of graphitic nanopore by using a combination of DFT calculations and microkinetic *** trend of limiting potentials for CO_(2)RR to produce CO can be described by using either the adsorption energy of COOH,CO,or their ***_(2)RR process with reasonable reaction rates can be achieved only on the active site configurations with weak tendencies toward CO *** efficiency of CO_(2)RR on a catalyst depends on its ability to suppress the parasitic hydrogen evolution reaction(HER),which is directly related to the behavior of H adsorption on the catalyst’s active *** find that the edges of the graphitic nanopore can act as potential adsorption sites for an H atom,and in some cases,the edge site can bind the H atom much stronger than the main Fe *** linear scaling between CO and H adsorptions is broken if this condition is *** condition also allows some edge active site configurations to have their CO_(2)RR limiting potential lower than the HER process favoring CO production over H2 production.

关键词： CO_(2)RR FexNy active site Fe-SAC Fe-DAC Graphitic edges DFT Microkinetic

来源：评论

学校读者我要写书评

暂无评论

Development of Cell Membrane Perforator for Large-Scale Application of Photochemical Cell Membrane Perforation by Continuous Processing

Development of Cell Membrane Perforator for Large-Scale Appl...

引用

2024 International Symposium on Micro-NanoMehatronics and Human science, MHS 2024

作者： Ochiai, Sota Kobayashi, Kohei Saito, Takashi Kei Akita Prefectural University Graduate School of Systems Science and Technology Department of Integrated System Engineering 84-4 Tsuchiya Ebinokuchi Yurihonjo-City Akita015-0055 Japan Akita Prefectural University Faculty of Systems Science and Technology Department of Intelligence Mechatronics 84-4 Tsuchiya Ebinokuchi Yurihonjo-City Akita015-0055 Japan

ISBN: (纸本)9798331540579

Photochemical cell membrane perforation is a technique that introduces substances directly into large numbers of cells and has a low cytotoxic effect. Among several cell modification techniques, this method is more efficient, since it can perforate a group of cells rather than an individual cell. It is also characterized by a high cell survival rate because the perforation is performed using oxidative treatment so that cells can repair themselves. To further expand this technology on a larger scale, we aimed to shift from batch processing to flow processing. In particular, the perforator, which had a flat shape in the past, was changed to a cylindrical shape, and a mechanism was developed for cell modification by passing a mixture of cells and transfection components between the perforator and two rotating cylinders on the receiving side. © 2024 IEEE.

关键词： Perforators

来源：评论

学校读者我要写书评

暂无评论

Establishing robust feature point detection and tracking methods for face orientation

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and systems 2021年第3期141卷 367-372页

作者： Sumali, Brian Hamada, Nozomu Mitsukura, Yasue Faculty of Science and Technology System Design Engineering Mitsukura Laboratory Keio University 3-14-1 Hiyoshi Kohoku-ku Yokohama Kanagawa223-8522 Japan

Recently, there has been an increasing need of a face alignment or facial feature point tracking for applying face recognition, facial expression estimation, face attributes prediction, and clinical face observation etc. This study proposes a robust facial feature tracking method against camera shake and face orientation changes. The method applies a cascaded composed learning (CCL) based facial feature point tracking method by incorporating optical flow for improving tracking accuracy and robustness. Experiments are conducted to show that efficient tracking is achieved by performing CCL combined with initial shape estimation via the optical flow. © 2021 The Institute of Electrical Engineers of Japan.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Study on the Applicability Considering on the Relationship between Shape and Flexibility of the Adsorption Gripper Tip 7

Study on the Applicability Considering on the Relationship b...

引用

7th International Conference on Control and Robotics engineering, ICCRE 2022

作者： Ofuchi, Akira Fujiwara, Daisuke Iizuka, Kojiro Shibaura Institute of Technology Graduate School of Systems Engineering and Science Saitama Japan Suwa University of Science Faculty of Engineering Department of Mechanical & Electrical Engineering Chino Japan Shibaura Institute of Technology Department of Machinery and Control System Saitama Japan

ISBN: (纸本)9781665468404

This study considers automatic scallop harvesting using the drone with the robot arm as the new scallop fishery. The fishery needs the dedicated gripper attaching the robot arm. This study judges the adsorption gripper as the dedicated gripper. The adsorption gripper must push itself to the object during gripping motion. If the pushing force is too large, there are some problems with the grasping. This study focuses on the flexibility of the gripper tip contacting object to solve those problems. Then, we investigate the applicability considering on the relationship between shape and flexibility of the adsorption gripper tip from the experiment. From these considerations, the dedicated gripper has been developed. © 2022 IEEE.

关键词： Adsorption

来源：评论

学校读者我要写书评

暂无评论

Comparative Modular Product Development Using TRIZ, AI, and VA++ 24th

Comparative Modular Product Development Using TRIZ, AI, and ...

引用

24th IFIP WG 5.4 International TRIZ Future Conference, TFC 2024

作者： Mysior, Marek Iniotakis, Christian Iwan, Dominik Faculty of Mechanical Engineering Department of Machine and Vehicle Design and Research Wroclaw University of Science and Technology Ul. Lukasiewicza 7/9 Wroclaw50-371 Poland Ulm University of Applied Sciences Prittwitzstr. 10 Ulm89075 Germany

ISBN: (纸本)9783031759222

The study explores the cost implications of different product designs: modular, adaptive, and uniform, focusing on ideality metrics across three products with the same primary function. Through a systematic innovation toolkit that utilizes TRIZ and AI in the concept generation phase, this research conducts a comparative analysis of workshop cranes, assessing material use, assembly time, and reconfiguration time. Considering further input parameters, namely cost factors specific to the workshop and job distributions representing the overall market, allows us to determine the design of the highest ideality for the constellation. Each design has its domain of being the most ideal solution. The results offer insights into the practical applications of AI tools in modular product design and provide a systematic framework for optimizing cost-effectiveness and sustainability in product development. Moreover, exploring ideality and resource consumption being different among the designs contributes to developing more sustainable and adaptable manufacturing practices. © IFIP International Federation for Information Processing 2025.

关键词： Product development

来源：评论

学校读者我要写书评

暂无评论

Robust Tweets Classification Using Arithmetic Optimization with Deep Learning for Sustainable Urban Living

引用

SN Computer science 2024年第5期5卷 1-11页

作者： Hamza, Manar Ahmed Hashim, Aisha Hassan Abdalla Motwakel, Abdelwahed Elhameed, Elmouez Samir Abd Osman, Mohammed Kumar, Arun Singla, Chinu Munjal, Muskaan Department of Electrical and Computer Engineering International Islamic University Malaysia Kuala Lumpur 53100 Malaysia Department of Computer and Self Development Preparatory Year Deanship Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia Department of Management Information Systems College of Business Administration in Hawtat bani Tamim Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia Department of Computer Science College of Post-Graduated Studies University of Science and Technology Omdurman Sudan Department of Information System Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan Department of Electronics and Communication Engineering New Horizon College of engineering Bengaluru India Computer Engineering Thapar Institute of Engineering and Technology Punjab Patiala India

Natural Language Processing (NLP) with Deep Learning (DL) for Tweets Classification includes use of advanced neural network designs to analyse and classify Twitter messages. DL techniques like recurrent neural network (RNN) or transformer-based frameworks like BERT are used to mechanically learn difficult linguistic patterns and contextual info from tweet data. These techniques able to capture subtleties of language with sarcasm, sentiment, and context-specific meanings and making them suitable for tasks like sentiment analysis or topic classification in realm of social media. Leveraging deep symbols learned from great amounts of textual data, these NLP techniques permit precise and nuanced classification of tweets, donating to enhanced information retrieval, sentiment tracking, and trend analysis in dynamic and fast-paced world of social media communication. In this view, this research develops an arithmetic optimization algorithm with deep learning based tweets classification (AOADL-TC) approach for sustainable living. The goal of the AOADL-TC technique is to identify and discriminate different kinds of sentiments that exist in the tweet data. At the initial stage, the AOADL-TC model pre-processes tweet data to convert uniform data into a useful format. For sentiment detection, the AOADL-TC technique applies a parallel bidirectional gated recurrent unit (BiGRU) model. At last, tuning of parameters related to parallel BiGRU model performed by AOA. An wide set of tests carried out to illustrate better performance of AOADL-TC model. The experimental outcomes portrayed that AOADL-TC technique demonstrates the supremacy of the AOADL-TC technique in terms of different evaluation metrics. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Machine learning Natural language processing Sentiment analysis Social media

来源：评论

学校读者我要写书评

暂无评论

Studying of Machine Learning Models for Forecasting Macroeconomic Indicators 27

Studying of Machine Learning Models for Forecasting Macroeco...

引用

27th International Conference on Advanced Communications technology, ICACT 2025

作者： Ngoc, Lan Dong Thi Ngo-Thi-Thu-Trang Kim, Kyoung-Mok Pham, Vung Nguyen, Ha-Nam Department of Economic Information System Academy of Finance Hanoi Viet Nam Faculty of Information Technology University of Engineering and Technology Vietnam National University Hanoi Viet Nam Posts and Telecommunications Institute of Technology Hanoi122300 Viet Nam Computer Science Department Sam Houston State University HuntsvilleTX77340 United States Department of Medical Information Sahmyook Health University Seoul Korea Republic of Faculty of Information Technology Electric Power University Hanoi Viet Nam

ISBN: (纸本)9791188428137

This study explores the application of machine learning models in forecasting macro-economic indicators, including GDP, inflation rate, unemployment rate, and exchange rate across 11 Southeast Asian countries. The models used include Linear Regression, ARIMA, Random Forest, XGBoost, LSTM, and SVM. We conducted a performance comparison of each model based on MAE, RMSE, and R2 metrics to evaluate the accuracy of the forecasts. The experimental results indicate that Random Forest and XGBoost models excel in predicting nonlinear and complex indicators such as GDP and unemployment rate, while ARIMA and Linear Regression models perform better in time series with clear regular patterns, like inflation rate. The LSTM model shows inconsistent effective-ness, requiring large data volumes and complex optimization processes. SVM demonstrates potential in handling nonlinear data but requires careful tuning. This study concludes that using machine learning models presents significant potential for improving the accuracy of macroeconomic forecasting. However, model tuning and optimization are essential to match the characteristics of each type of economic indicator. Future research directions include developing hybrid models and integrating additional factors such as market sentiment, social and environmental indicators (ESG) to enhance forecasting outcomes. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.

关键词： Inflation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Deep Convolutional Neural Network Based Object DetectionModel for Visually Challenged People

引用

Computer systems science & engineering 2023年第9期46卷 3191-3207页

作者： S.Kiruthika Devi Amani Abdulrahman Albraikan Fahd N.Al-Wesabi Mohamed K.Nour Ahmed Ashour Anwer Mustafa Hilal Department of Computing Technology SRM Institute of Science and TechnologyIndia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Computer Science College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Engineering Mathematics and Physics Faculty of Engineering and TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Artificial Intelligence(AI)and Computer Vision(CV)advancements have led to many useful methodologies in recent years,particularly to help visually-challenged *** detection includes a variety of challenges,for example,handlingmultiple class images,images that get augmented when captured by a camera and so *** test images include all these variants as *** detection models alert them about their surroundings when they want to walk *** study compares four CNN-based pre-trainedmodels:ResidualNetwork(ResNet-50),Inception v3,DenseConvolutional Network(DenseNet-121),and SqueezeNet,predominantly used in image recognition *** on the analysis performed on these test images,the study infers that Inception V3 outperformed other pre-trained models in terms of accuracy and *** further improve the performance of the Inception v3 model,the thermal exchange optimization(TEO)algorithm is applied to tune the hyperparameters(number of epochs,batch size,and learning rate)showing the novelty of the *** accuracy was achieved owing to the inclusion of an auxiliary classifier as a regularizer,hyperparameter optimizer,and factorization ***,Inception V3 can handle images of different *** makes Inception V3 the optimum model for assisting visually challenged people in real-world communication when integrated with Internet of Things(IoT)-based devices.

关键词： Pre-trained models object detection visually challenged people deep learning Inception V3 DenseNet-121

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：