检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ogunleye, Bayode Zakariyyah, Kudirat Ibilola Ajao, Oluwaseun Olayinka, Olakunle Sharma, Hemlata School of Architecture Technology & Engineering University of Brighton BrightonBN2 4GJ United Kingdom Department of Computing & Mathematics Manchester Metropolitan University ManchesterM1 5GD United Kingdom School of Computer Science The University of Sheffield SheffieldS1 4DP United Kingdom Department of Computing Sheffield Hallam University SheffieldS1 2NU United Kingdom

The use of generative artificial intelligence (GenAI) in academia is a subjective and hotly debated topic. Currently, there are no agreed guidelines towards the usage of GenAI systems in higher education (HE) and, thus, it is still unclear how to make effective use of the technology for teaching and learning practice. This paper provides an overview of the current state of research on GenAI for teaching and learning in HE. To this end, this study conducted a systematic review of relevant studies indexed by Scopus, using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. The search criteria revealed a total of 625 research papers, of which 355 met the final inclusion criteria. The findings from the review showed the current state and the future trends in documents, citations, document sources/authors, keywords, and co-authorship. The research gaps identified suggest that while some authors have looked at understanding the detection of AI-generated text, it may be beneficial to understand how GenAI can be incorporated into supporting the educational curriculum for assessments, teaching, and learning delivery. Furthermore, there is a need for additional interdisciplinary, multidimensional studies in HE through collaboration. This will strengthen the awareness and understanding of students, tutors, and other stakeholders, which will be instrumental in formulating guidelines, frameworks, and policies for GenAI usage. © 2024, CC BY.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Applications and advances in tio2 based photocatalytic building materials 5

Applications and advances in tio2 based photocatalytic build...

引用

2021 5th International Conference on Green Composite Materials and Nanotechnology, GCMN 2021

作者： Liu, Chongyang Bai, Jitao Zhang, Simiao Yang, Zewen Luo, Ming School of Civil Engineering Tianjin University Tianjin300072 China State Key Laboratory of Hydraulic Engineering Simulation and Safety Tianjin University Tianjin300072 China College of Intelligence and Computing Tianjin University Tianjin300072 China Department of Naval Architecture and Ocean Engineering Tianjin University Tianjin300072 China

TiO2 is currently the most widely used photocatalytic material. Compared with traditional building materials, TiO2-based photocatalytic building materials have unique and significant advantages, which endows them with great potential in application. By summarizing the current application and research status of photocatalytic building materials, the existing problems of photocatalytic building materials and corresponding solutions were pointed out, and current research progress of photocatalytic building materials in terms of carbon emission reduction in buildings was introduced. Finally, some prospects were made on photocatalytic building materials, which would provide a reference for the study on the next generation of photocatalytic building materials. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Building materials

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Augmented Hybrid Optimization for Crop Classification using Hyperspectral images

Deep Learning-Augmented Hybrid Optimization for Crop Classif...

引用

Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC), International Conference on

作者： J. Mohana G. Nirmala Praveen Damacharla Mohammad Bdair R. Logarasu S. Karpagam Dept of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai India Dept of Electronics & Communication Engineering Mahendra Institute of Technology Namakkal India KineticAI Inc. The Woodlands TX USA School of Architecture Computing and Engineering University of East London London United Kingdom Department of ECE Paavai Engineering College (Autonomous) Namakkal India Department of Mathematics Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

Precise and efficient solutions are necessary for the essential job of classifying crops using hyperspectral images in precision agriculture. The paper introduces a framework called Deep Learning-Augmented Hybrid Optimization (DLAHO), which combines a CNN for feature extraction with a hybrid optimization technique that combines Genetic Algorithms (GA) and Gradient-Based Optimization (GBO) to optimize model parameters. The Hyperspectral Image Database (HID) preprocesses hyperspectral images by using normalization and PCA to reduce dimensionality. The CNN utilizes both spectral and spatial data, which are then enhanced by the hybrid GA-GBO method. The improved model accurately identifies crops with a high level of precision. The results indicate that DLAHO obtains an accuracy of 95.4% for wheat, 92.1% for maize, 94.3% for soybean, 93.2% for barley, 96.0% for rice, 91.5% for sugarcane, 93.8% for potato, and 92.7% for cotton. DLAHO outperforms baseline models and state-of-the-art algorithms, achieving an F1-score of 93.1%, recall of 93.5%, precision of 92.8%, and total accuracy of 93.6%. The findings show that the recommended DLAHO architecture significantly increases the precision and dependability of crop categorization, thereby making it a viable tool for precision agriculture.

关键词： Precision agriculture Accuracy Scalability Crops Spatial databases Resource management Optimization Hyperspectral imaging Genetic algorithms Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Emotion Recognition through Galvanic Skin Response and ECG Analysis for Improved Accuracy and Reliability

AI-Enhanced Emotion Recognition through Galvanic Skin Respon...

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Mathan Kumar Mounagurusamy Parvinder Kaur Mohammad Bdair Pavithra G S. Thenappan G. Kalpanadevi Department of Computing Technologies SRM University Kattankulathur Campus Chennai Tamil Nadu India Department of Electronics and Communication Engineering Chandigarh College of Engineering and Technology Chandigarh India School of Architecture Computing & Engineering University of East London London United Kindom Department of AIML Bannari Amman Institute of Technology Sathyamangalam Tamil Nadu India Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of ECE K. Ramakrishnan College of Engineering Turuchirapalli Tamil Nadu India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Traditional methods of emotion detection, including the problem of recognizing seven basic emotions, have issues such as occlusion, noise, and self-reporting. Besides text mining there are voices, facial and gesture recognition algorithms as well. The indicated acoustics-based difficulties are resolved in the proposed system by employing the previously mentioned signals - less forgery and interferences for ECG and GSR. When noise from signals is removed, characteristic properties such as pace fluctuation and skin conductance are obtained. All of these features are organized using modern machine learning models such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN). Measurements of labelled datasets are utilized to verify the system's accuracy levels, and better performance is reported in the dimension of emotion identification resilience. The proposed methodology in this research is more accurate than other existing systems, with an accuracy rate of 90%, recall rate of 88 percent, and F1-Score of 87.5%. Similar to feature metrics, the level of accuracy for particular parameters has improved. HCl technology will improve learning and mental health features such as recognition, emotion, and social interaction. The established goal of physiological ones is to serve as a solid and steady foundation for identifying emotions.

关键词： Support vector machines Emotion recognition Accuracy Machine learning algorithms Noise Mental health Electrocardiography Skin Physiology Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Elliptical Contact Enhances Adhesion Strength Under Shear Loads

SSRN

引用

SSRN 2023年

作者： Wu, Fa Wang, Qingao Li, Chun Li, Qunyang Gao, Huajian Department of Engineering Mechanics School of Mechanics Civil Engineering and Architecture Northwestern Polytechnical University Shaanxi Xi’an710129 China Research & Development Institute of Northwestern Polytechnical University Guangdong Shenzhen518057 China AML & CNMM Development of Engineering Mechanics Tsinghua University Beijing100084 China School of Mechanical and Aerospace Engineering College of Engineering Nanyang Technological University Singapore Singapore Institute of High Performance Computing A*STAR Singapore138632 Singapore

Adhesion under a shear load parallel to the contact interface is a common issue in engineering and biological systems, such as when insects and adhesion devices crawl on vertical walls. A question of interest is whether and how the shear load influences the adhesion behavior between an elliptical punch and an elastic medium. Here, we derive lower- and upper-bound limiting analytical solutions to this problem based on the local and global energy balances. Numerical results indicate that the lower- and upper-bounds are very close to each other, and their ratio depends only on the ellipse eccentricity in the absence of shear load. The lower-bound solution yields the location of the initial detachment, which is influenced by the contact area, ellipse eccentricity, shear load, and Poisson's ratio, but not Young's modulus. The presence of a shear load reduces the pull-off force and can also alter the position where the detachment is nucleated. Furthermore, there exists an optimal elliptical shape that gives rise to the maximum adhesion strength in the presence of a shear load. The theoretical findings are validated through experiments involving the pull-off of a rigid punch from an adhesive polymer substrate subjected to a shear load. The present study sheds insight and may provide helpful guidelines for designing biomimetic adhesive systems. © 2023, The Authors. All rights reserved.

关键词： Adhesion

来源：评论

学校读者我要写书评

暂无评论

Bridging gender and human-centered design: A design verification study 30

Bridging gender and human-centered design: A design verifica...

引用

30th CIRP Design on Design, CIRP Design 2020

作者： Esfahani, Bahar Khayamian School of Architecture Computing and Engineering University of East London LondonE16 2RD United Kingdom

This article highlights the importance of adding gender awareness in human-centered design. Aspects of both paradigms are presented, and a lack of understanding of gender in the human-centered design approach was identified. Human-centered design sees gender as static and stable regarding male or female such that the implication of principles in products, systems or services appeals to one gender or another linking gender differences, and stereotypes. Evidence is provided through a design verification study, conducted in the context of fostering sun protection behavior in young men age 18 to 24. The results verify gender-aware sun protection interventions for young men. It also shows the inclusion of gender has great potential to bridge the gap between the world of designers and users. It also presents a discussion of the analytical procedures and the findings which emerged in this investigation led to the verification of design recommendations for sun protection interventions. Evidence is further presented for increasing emphasis on the influence of the designer's own gender and their gendered perceptions in their designs. Finally, the implication of gender-aware human-centered design would address the low levels of sun protection in young men. © 2017 The Authors. Published by Elsevier B.V.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of Digital Financial Technology Adoption Research

Statistical Analysis of Digital Financial Technology Adoptio...

引用

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Temiloluwa Iyanuoluwa Ajibade Olamide Emmanuel Ayodele Samuel-Soma M. Ajibade Nanet A. Goles Johnry P. Dayupay Anthonia Oluwatosin Adediran Department of Business Management Scholar School System Birmingham United Kingdom Department of Banking and Finance Ekiti State University Ado Ekiti Ekiti State Department of Computing and Information Systems School of Engineering and Technology Sunway University Selangor Malaysia Cebu Technological University Moalboal Cebu Philippines Faculty of Architecture and Urban Design Federal University of Uberlandia Uberlandia Brazil

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

Digital financial technology adoption (DFTA) studies published in Scopus between 2019 and 2022 were examined in this study. After that, we assessed relevant literature, did bibliometric studies, and examined publication and citation patterns. The statistics showed 2643 citations and 176 publications. DFTA research has gained popularity when time-varying TP and TC values increased gradually. This topic's most popular sources are "articles" and "Sustainability (Switzerland)". A search of DFTA research stakeholders revealed several authors, organizations, and nations. Most famously associated with the University of Johannesburg in South Africa, David Mhlanga has produced more publications than anyone else. The National Natural Science Foundation and other Chinese donors who dominate DFTA research funding contributed to researchers' and affiliations' output. Cluster and hotspot analysis revealed two themes, "Digital financial technology adoption" and "Sustainable Banking Inclusion," and three keywords, Digital financial technology adoption, monetary inclusion, and finance. According to the examined literature, DFTA's effects on international financial stability and GDP growth are understudied. Future research should examine DFTA's environmental impact, long-term profitability, and commercial strategies for low-income and rural communities.

关键词： Productivity Statistical analysis Profitability Bibliometrics Banking Stability analysis Stakeholders

来源：评论

学校读者我要写书评

暂无评论

Reliable Multihop Routing and Congestion Aware Chicken Swarm Optimization in Vehicular Ad-Hoc Network 3

Reliable Multihop Routing and Congestion Aware Chicken Swarm...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Anitha, Cuddapah Al-Tarazi, Dalia Vignesh, G.D. Vasuki, A. Vinotha Giri, Jayant Dinesh, M. School of Computing Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College Department of Computer Science and Engineering Tirupati India Zarqa University Faculty of Engineering Department of Architecture Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia St. Joseph's College of Engineering Department of Electronics and Communication Engineering Chennai India J.P. College of Engineering Department of Computer Science and Engineering Tenkasi India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India Department of Vlsi Microelectronics Chennai India

ISBN: (纸本)9798331508456

Background: Vehicular Ad Hoc Networks (VANETs) play a crucial role in intelligent transportation by facilitating communication between vehicles and vehicles with infrastructure-based models. They encounter problems such as significant movement, overcrowding, and loss of data. This research presents a novel deep reinforcement learning-based resource allocation and congestion optimization (DRLRCO) framework aimed at improving communication efficiency and high reliability using an effective learning process. Method Used: The DRLRCO framework employs agent-based learning to ensure precise data transmission, AdMAC Protocol for dynamic packet delivery, and Congestion-Aware Chicken Swarm Optimization (CSO) to enhance network performance. Result: The DRLRCO framework surpasses reinforcement learning models for comprehensive testing. Significant enhancements involve improved accuracy, reduced data loss, minimized overhead, increased throughput, and shorter average delays for real-time communication. Conclusion: The DRLRCO framework successfully tackles congestion and data loss in vehicular communication. Future studies might involve Artificial Intelligence (AI) for traffic forecasting, experimentation among high-speed vehicles and investigating blockchain for enhanced security. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Complete Path Model for the Carbon Emission Prediction of Urban District Heating Based on System Dynamics

SSRN

引用

SSRN 2023年

作者： Wei, Cun Zhou, Zhigang Zheng, Jinfu Wang, Ruixin Cong, Mingyang Yang, Dayi Liu, Jing School of Architecture Harbin Institute of Technology Key Laboratory of Cold Region Urban and Rural Human Settlement Environment Science and Technology Ministry of Industry and Information Technology Harbin China School of Environmental and Municipal Engineering Qingdao University of Technology Qingdao China Faculty of Computing Harbin Institute of Technology Harbin China

High-carbon-emission heating technologies are unsustainable;thus, district heating with low carbon emissions is a crucial alternative for decarbonizing the heating sector. Early studies have frequently demonstrated the impact of one or more variables on carbon emissions;however, they have frequently disregarded the integrity, dynamism, and complexity of different urban heating subsystems. This study constructed a complete method with high flexibility and applicability to predict carbon emissions from urban district heating based on system dynamics. This study identified the main factors affecting carbon emissions from the building, heating, and power subsystems. Each subsystem was assigned to one of three development models: high, medium, or low. There were 27 scenarios, and the objectives and tasks of each scenario were suggested separately based on the development models. Then, the carbon emissions from urban district heating over the next 40 years (2020–2060) in Heilongjiang Province were simulated. The research results show that urban heating carbon emissions can be effectively reduced by at least 60% compared to 2020 in the low-speed scenario, and by up to 80% or more in the case of the high-speed scenario by 2060, in combination with China's current policies. © 2023, The Authors. All rights reserved.

关键词： District heating

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm 29

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zeng, Yan Huang, Chengchuang Ni, Yijie Zhou, Chunbao Zhang, Jilin Wang, Jue Zhou, Mingyao Xue, Meiting Zhang, Yunquan Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Ministry of Education Key Laboratory for Modeling and Simulation of Complex Systems Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Hangzhou Dianzi University School of ITMO Joint Institute Hangzhou310018 China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing100086 China HuaWei China Institute of Computing Technology of the Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100086 China

ISBN: (纸本)9798350330717

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network's dataflow graph and device cluster's topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method. © 2023 IEEE.

关键词： Auto-Parallel Distributed machine learning Genetic algorithm Integer linear programming Model parallelism

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：