检索结果-内蒙古大学图书馆

5th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2023

作者： Kamarudin, Noraziahtulhidayu Yusoff, Aiman Basari, Abd Samad Hasan Safar, Noor Zuraidin Bin Mohd Hussin, Mohd Hatta Universiti Tun Hussein Onn Multimedia and Signal Processing Focus Group Faculty of Computer Science and Information Department of Multimedia Malaysia Universiti Tun Hussein Onn Faculty of Computer Science and Information Department of Multimedia Malaysia Universiti Tun Hussein Onn Faculty of Computer Science and Information Technology Department of Software Engineering Malaysia Universiti Tun Hussein Onn Faculty of Computer Science and Information Department of Information Security and Web Technology Malaysia Pertubuhan Peladang Senggarang Johor Darul Takzim Malaysia

ISBN: (纸本)9798350337525

During the application development process, it is important for a developer to analyze user requirements. This is crucial to the success of interactive systems and is an essential component of the design of information systems. User requirement analysis aids developers in understanding and analyzing users' needs and technology requirements. Throughout this case study, it is able to forecast the understanding, and technology acceptance, and at the same time improve the quality of work, reducing training and support costing and perennially improve customer or user satisfaction. The method of research selected is questionnaires that focused on collecting the data directly from Malaysian farmers through Google Forms as an online medium. The method was chosen because it is easy to implement and inexpensive due to the current situation of Covid-19. The questionnaire is designed with two sections where;a) includes the participant's demography to analyze information of the intended audience while b)focused on the knowledge of participants about recognition images. Results demonstrate the farmer's opinion and knowledge of the technology of image recognition in the agriculture sector. The quantitative research was undertaken using an online platform due to the Covid-19 pandemic. From the analysis, it is justified that the Technology Acceptance Model (TAM) together with the mobile farming image recognition app is useful in collecting farmers' feedback and positive results have an outcome on the challenges faced by the durian farmers. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

MeshDMP: Motion Planning on Discrete Manifolds using Dynamic Movement Primitives

arXiv

引用

arXiv 2024年

作者： Vedove, Matteo Dalle Abu-Dakka, Fares J. Palopoli, Luigi Fontanelli, Daniele Saveriano, Matteo Department of Industrial Engineering Università di Trento Trento Italy DRIM Italy Mechanical Engineering Program Division of Engineering New York University Abu Dhabi Abu Dhabi United Arab Emirates Department of Information Engineering and Computer Science Università di Trento Trento Italy

An open problem in industrial automation is to reliably perform tasks requiring in-contact movements with complex workpieces, as current solutions lack the ability to seamlessly adapt to the workpiece geometry. In this paper, we propose a Learning from Demonstration approach that allows a robot manipulator to learn and generalise motions across complex surfaces by leveraging differential mathematical operators on discrete manifolds to embed information on the geometry of the workpiece extracted from triangular meshes, and extend the Dynamic Movement Primitives (DMPs) framework to generate motions on the mesh surfaces. We also propose an effective strategy to adapt the motion to different surfaces, by introducing an isometric transformation of the learned forcing term. The resulting approach, namely MeshDMP, is evaluated both in simulation and real experiments, showing promising results in typical industrial automation tasks like car surface polishing. © 2024, CC BY-SA.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Success Factors of Enterprise Resource Planning: A State-of-the-Art Mini Review

Success Factors of Enterprise Resource Planning: A State-of-...

引用

Artificial Intelligence, Metaverse and Cybersecurity (ICAMAC), International Conference on

作者： Ahmed BaniMustafa Olla Bulkrock Faculty of Computer Information Science Higher Colleges of Technology Abu Dhabi UAE Software Engineering Department Princess Sumaya University for Technology Amman Jordan

ISBN: (数字)9798350353488

ISBN: (纸本)9798350353495

Enterprise Resource Planning Systems (ERP) are vital for today’s businesses. However, the successful implementation of ERP systems faces several challenges, which can determine its success or failure. This paper provides a brief state-of-theart review of the success factors of ERP implementation using various applications that span different contexts. The paper discusses and compares the aims defined and the techniques applied in these studies, as well as the data used and the results obtained from each of these studies. This review paper reviews published work to tackle these challenges, covering the literature published in 2020-2023. A special effort was also made to focus on high-quality papers published in top journals with high-impact factors and indexed in Scopus and Web of Science. The review process is repeatable, as special keywords were used to search the literature using publishers’ databases and three specialized tools. The paper concludes by discussing the future of the successful implementation of ERP systems. The paper argues that ERP systems will continue to have a major impact on the success of today’s businesses. Therefore, they must carefully consider various factors that influence their successful implementation.

关键词： Training Machine learning algorithms Quality assurance Reviews Metaverse Project management Organizations Enterprise resource planning Teamwork Stakeholders

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modeling and Analysis of Patterns in Structured Collections of Big Data

Mathematical Modeling and Analysis of Patterns in Structured...

引用

International Conference on Advanced computer Information Technologies (ACIT)

作者： Olena Syrotkina Ziad Kobti Mykhailo Aleksieiev Borys Moroz Iryna Udovyk Hennadii Shvachych School of Computer Science University of Windsor Windsor Canada Department of Software Engineering Dnipro University of Technology Dnipro Ukraine

This paper addresses the issue of creating and applying mathematical models and methods for finding generalized solutions when working with structured collections of “big data”. We reviewed the modern methodologies used to solve problems of this class. The mathematical model presented describes an ordered set of all subsets formed from a finite ordered base set of arbitrary size and data type. We explored a set of functional dependencies of five discrete input variables to work with this mathematical model. Some of these functional dependencies are derived for specific solutions with specified boundary conditions. The paper also presents examples of how the derived functional dependencies are applied in the implementation of mathematical methods using this model. This required us to conduct a comparative assessment of the search time for a solution with and without the use of these mathematical methods. Comparative graphs are demonstrated to show the rate of increase in the number of operations depending on the size of the original finite base set with and without the use of these mathematical methods. As a result of this, logical conclusions are drawn regarding the impact of mathematical methods for working with structured collections on minimizing time and computational resources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Peel-and-Bound: Generating Stronger Relaxed Bounds with Multivalued Decision Diagrams

arXiv

引用

arXiv 2022年

作者： Rudich, Isaac Cappart, Quentin Rousseau, Louis-Martin Mathematics and Industrial Engineering Department Polytechnique Montréal Canada Computer Engineering and Software Engineering Department Polytechnique Montréal Canada

Decision diagrams are an increasingly important tool in cutting-edge solvers for discrete optimization. However, the field of decision diagrams is relatively new, and is still incorporating the library of techniques that conventional solvers have had decades to build. We drew inspiration from the warm-start technique used in conventional solvers to address one of the major challenges faced by decision diagram based methods. Decision diagrams become more useful the wider they are allowed to be, but also become more costly to generate, especially with large numbers of variables. We present a method of peeling off a sub-graph of previously constructed diagrams and using it as the initial diagram for subsequent iterations that we call peel-and-bound. We test the method on the sequence ordering problem, and our results indicate that our peel-and-bound scheme generates stronger bounds than a branch-and-bound scheme using the same propagators, and at significantly less computational *** Codes 90-08 © 2022, CC BY.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

The Open Source Threat Intelligence Relational Dataset and Its Optimal Implementation

The Open Source Threat Intelligence Relational Dataset and I...

引用

Innovation in Technology (APCIT), Asia Pacific Conference on

作者： Yaru Yang Junyu Li Ronghua Zhang Abhishek Pratap Sah Amit Yadav Asif Khan Department of Computer and Software Chengdu Neusoft University Chengdu China School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China College of Engineering IT and Environment Charles Darwin University NT Australia Department of Computer Application Integral University Lucknow India

ISBN: (数字)9798350361537

ISBN: (纸本)9798350361544

Threat intelligence provides a platform for cybersecurity engineers for attack traceability, which provides substantial knowledge database logs to defend against future security threats. Threat intelligence relationship extraction based on deep learning solves the challenge of threat knowledge construction to a certain extent but still faces problems such as lack of open-source datasets and the inability of the model to accurately correlate threat entities with potential relationships. Therefore, for cybersecurity research work, this paper designs a threat ontology, constructs the threat relationship dataset TreatRE by remote supervision, and opens this dataset. The dataset contains 12000 utterances and 12 threat relations from 500 CTIs, and it performs well in multiple relation models trained on deep learning methods. Meanwhile, we propose a multisensory attention-based threat intelligence relationship extraction method MAtt, which combines location perception, self-attention perception, and neuronal memory perception to further improve the threat relationship extraction effect. Experimental results show that the trained model based on TreatRE can more accurately extract the knowledge objects and their relationships described in threat intelligence. An accuracy score of 95.4% can be obtained using the MAtt method, which is 3.48% more than the best baseline compared with the same type of relationship extraction model.

关键词： Deep learning Knowledge engineering Technological innovation Databases Buildings Asia Ontologies

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Segmentation on 3d Images with Pseudo Label Calibration and Neural Process

SSRN

引用

SSRN 2024年

作者： Zhang, Tianlun Luo, Yuxuan Kwong, Sam Wang, Xizhao College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Lingnan University Hong Kong

Pseudo supervision has demonstrated empirical success in semi-supervised segmentation tasks by effectively leveraging unlabeled data, but it unavoidably encounters the problem caused by noisy pseudo labels. Existing methods against noisy pseudo labels heavily rely on the model confidence which may be unreliable in some cases. In this work, we mitigate the impact of noisy pseudo label from two aspects. First, we propose a new uncertainty-guided mutual supervision mechanism that can weaken the supervision from the noisy pseudo labels with high-level confidence. This mechanism can make the segmentation model more robust to the unreliable confidence. Second, to improve the quality of pseudo labels, we propose a novel regularization method for calibrating the noisy pseudo labels. Different from existing works, this regularization is independent of the model confidence, it focuses on the distribution consistency between labeled and pseudo-labeled data. To this end, a joint optimization based on the theory of neural process is introduced into the pseudo label calibration. We verify the effectiveness of the proposed method on the left atrium (LA) segmentation that is important for the treatment of atrial fibrillation. It experimentally shows that our method can bring a practical improvement to the LA segmentation task in comparison with the existing state-of-the-art semi-supervised learning methods. Our method provides some insight into the pseudo supervision. The code will be available online. © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Classification of Lung CT Scan for Accurate Cancer Diagnosis

Deep Learning-based Classification of Lung CT Scan for Accur...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： D.Christy Sujatha T.R. Vijaya Lakshmi Surya G U. Surendar Rajendiran M Ramya Maranan Department of Software Engineering Periyar Maniammai Institute of Science and Technology Thanjavur Tamail Nadu India Department of Electronics and Communication Engineering Mahatma Gandhi Institute of Technology Hyderabad Telangana India Department of Computer Science and Engineering K. Ramakrishnan College of Engineering Tiruchirappalli Tamil Nadu India Department of Electronics and Communication Engineering SRM Institute of Science and Technology - Ramapuram Campus Chennai Tamil Nadu India Department of Computer Science And Engineering Panimalar Engineering College Poonamallee Chennai Tamil Nadu India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

This paper investigates the suitability of advanced deep learning models for precise diagnosis of lung cancer from MRI images. Recurrent neural networks (RNN), K-Nearest Neighbors (KNN), ResNet50, and convolutional neural networks (CNN) were all carefully evaluated to determine their unique contributions. The CNN showed off its good performance and capacity to recognize intricate patterns in lung images, achieving an accuracy of 92.3%. KNN demonstrated competitive results, demonstrating the adaptability of non-parametric methods for medical image classification. Remarkably, ResNet50 fared extremely well, exhibiting a remarkable accuracy of 94.8% and verifying the value of deep residual networks in differentiating between intricate features. RNNs gave the analysis a temporal dimension and contributed to its 89.5% accuracy. Information from confusion matrices containing comprehensive classification results was useful in refining the model. Spatial representations of expected cancer cell locations showed the effectiveness of the models by giving doctors visual cues for targeted interventions. Comparisons with the literature show that the results are in line with recent developments in deep learning for medical image analysis. Because of its comprehensive assessment of different deep learning architectures, which provides fresh perspectives that advance the field of lung cancer detection technologies, this work is an invaluable resource for future research.

关键词： Deep learning Visualization Recurrent neural networks Magnetic resonance imaging Lung cancer Lung Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Active Impedance Compression Network for IPT EV Charging

A Novel Active Impedance Compression Network for IPT EV Char...

引用

Wireless Power Week (WPW)

作者： Cody Liu Duleepa Thrimawithana Grant Covic Morris Kesler Department of Electrical Computer and Software Engineering Tie University of Auckland Auckland New Zealand WiTricity Corporation Watertown Massachusetts

Passive impedance compression networks (ZCNs) are commonly used in IPT EV charging systems for battery voltage tolerance. However, additional costly tunable matching networks (TMNs) are required in order for such systems to handle variations in coupling. In response, this paper proposes an Active Impedance Compression Network (AZCN) that can handle changes in both battery voltage and coupling. In doing so, the TMNs can be eliminated simply by replacing four diodes in the ZCN with switches. Moreover, these switches can be synchronised by measuring their own drain-source voltages, thus avoiding the need for wireless communication with the primary, sensing coils or current measurement. The concept is supported by simulations of a 7 kW design. Results show high DC-DC efficiency over a large range of battery voltages and coupling factors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Learning Framework for Construction Costs Forecasting

SSRN

引用

SSRN 2024年

作者： Habib, Omar Abouhamad, Mona Bayoumi, AbdElMoniem Integrated Engineering Design in Construction Projects Program Faculty of Engineering Cairo University Gamaa Street Al-Jizah12613 Egypt Department of Structural Engineering Faculty of Engineering Cairo University Gamaa Street Al-Jizah12613 Egypt Department of Computer Engineering Faculty of Engineering Cairo University Gamaa Street Al-Jizah12613 Egypt

Construction cost forecasting is a crucial problem due to the need to automate the pricing of construction projects to predict expected revenues. However, traditional approaches rely on human experts leading to subjective judgment. This paper introduces a novel ensemble learning decision support framework to automate construction cost estimation using a combination of regression random forests and gradient-boosting regression trees via regression voting to overcome current cost estimation shortcomings for residential and commercial projects. We evaluated our approach on the dataset of San Francisco's building inspection department in the USA. Furthermore, we compared the performance of our approach to the recommended pricing practices of the Association for the Advancement of Cost engineering (AACE), showing that our model significantly outperforms the AACE's practices for tendering and bidding phases, corresponding to the level of detail of our given data. Moreover, we showed that our approach significantly outperformed support vector regression. © 2024, The Authors. All rights reserved.

关键词： Cost engineering

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：