检索结果-内蒙古大学图书馆

International Conference on Intelligent Transportation

作者： M. Elkady A. Elmarakbi D. Crolla Department of Computing Engineering and Technology Faculty of Applied Sciences University of Sunderland Sunderland UK Ain Shams University Egypt University of Leeds UK

The aims of this research are to investigate the effect of the vehicle dynamics control systems on vehicle collision mitigation and to use them to improve vehicle collision performance in full and offset crash scenarios. For this approach, vehicle dynamics are studied together with the vehicle crash structural dynamics. A proposed unique 3-D full-car vehicle dynamics/crash mathematical model is established and developed in this paper to discuss the effect of vehicle dynamics characteristics on different vehicle crash scenarios. In this study, the unavoidable collision and the type of crash (full/offset crash) are detected using the advanced driver assistant systems (ADAS). Validation of the vehicle crash structure in the proposed mathematical model is achieved to ensure that the modeling of crumple zone gives accurate results. It is demonstrated from the simulations that the vehicle dynamic response and crash scenarios are captured and analyzed accurately. It is also shown that the mathematical model is flexible and useful in optimization studies.

关键词： Vehicles Vehicle crash testing Mathematical model Springs Wheels Vehicle dynamics Control systems

来源：评论

学校读者我要写书评

暂无评论

Identifying the Level of Diabetic Retinopathy Using Deep Convolution Neural Network

Identifying the Level of Diabetic Retinopathy Using Deep Con...

引用

computing, Communication and Electronics (ETCCE), Emerging technology in

作者： Rahat Hassan Md Arafatur Rahman Ihsan Ullah Ali Hamdan Alenezi Taha H. Rassem Science & Technology University Gopalganj Bangladesh Faculty of Computing College of Computing and Applied Sciences Universiti Malaysia Pahang Kuantan Malaysia CeADAR Ireland Center for Applied AI Technological University Dublin Northern Border University Arar Saudi Arabia

ISBN: (数字)9781665419628

ISBN: (纸本)9781665419635

Diabetic Retinopathy is the leading cause of blindness in the last 100 years. The traditional screening process for DR and its stages takes a lot of time, and it is not practical. Using machine learning techniques and image processing, we can automate detecting diabetic retinal disease and disease stage with acceptable performance. In this work, we have used multiple deep convolution neural networks (CNN) with the same architecture of InceptionV3. Each of the pre-trained Inception V3 architecture is retrained with 2200 preprocessed and leveled images. The dataset is preprocessed using multiple high performing and effective image processing techniques. Then the newly trained models are used for identifying the level of DR. In the final stage, we use a voting scheme for classifying the level of DR from the output of each model. We have achieved 90.5% accuracy in binary classification (Normal/DR) and 81.1% accuracy in 5-class classification.

关键词： Retinopathy Convolution Image processing Neural networks Computer architecture Retina Diabetes

来源：评论

学校读者我要写书评

暂无评论

Multi-objective VNF Placement Optimization with NSGA-III 1st

Multi-objective VNF Placement Optimization with NSGA-III

引用

1st International Conference on Advances in computing Research, ACR’23

作者： Bekhit, Mahmoud Fathalla, Ahmed Eldesouky, Esraa Salah, Ahmad Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia Kent Institute Australia Melbourne Australia Department of Mathematics Faculty of Science Suez Canal University Ismailia Egypt Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia College of Computers and Informatics Zagazig University Zagazig Egypt College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman

ISBN: (纸本)9783031337420

With the rising acceptance of virtual network functions (VNFs) as a replacement for traditional network functions, the optimal placement of VNFs has become a crucial task for ensuring constant performance within constrained resources. This research investigates the challenge of mapping and scheduling VNFs as a multi-objective optimization problem. The state-of-the-art methods have focused on optimizing the mapping or scheduling of VNFs while considering one or two objectives continuously. In this study, we aim to optimize two objectives: minimizing the link capacity cost and maximizing the average resource utilization of each virtual machine. To address this problem, an adaptation of the NSGA-III optimization algorithm is proposed and thoroughly evaluated through a set of experiments. In terms of objective values, the results outlined that the proposed method outperformed the other methods of comparison by a significant margin. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Classification of Stomach Abnormalities Using Deep Learning

引用

Computers, Materials & Continua 2021年第10期69卷 607-625页

作者： Javeria Naz Muhammad Attique Khan Majed Alhaisoni Oh-Young Song Usman Tariq Seifedine Kadry Department of Computer Science HITEC University TaxilaTaxilaPakistanl 2College of Computer Science and EngineeringUniversity of Ha’ilHa’ilSaudi Arabial 3Department of SoftwareSejong UniversitySeoulKoreaGwangjin-guKoreal 4College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabial 5Faculty of Applied Computing and TechnologyNoroff University CollegeKristiansandNorway

An automated system is proposed for the detection and classification of GI *** proposed method operates under two pipeline procedures:(a)segmentation of the bleeding infection region and(b)classification of GI abnormalities by deep *** first bleeding region is segmented using a hybrid *** threshold is applied to each channel extracted from the original RGB ***,all channels are merged through mutual information and pixel-based *** a result,the image is *** and deep learning features are extracted in the proposed classification *** transfer learning(TL)approach is used for the extraction of deep *** Local Binary Pattern(LBP)method is used for texture ***,an entropy-based feature selection approach is implemented to select the best features of both deep learning and texture *** selected optimal features are combined with a serial-based technique and the resulting vector is fed to the Ensemble Learning *** experimental process is evaluated on the basis of two datasets:Private and *** accuracy achieved is 99.8 per cent for the private data set and 86.4 percent for the KVASIR data *** can be confirmed that the proposed method is effective in detecting and classifying GI abnormalities and exceeds other methods of comparison.

关键词： Gastrointestinal tract contrast stretching segmentation deep learning features selection

来源：评论

学校读者我要写书评

暂无评论

How do they like it? Higher education teachers’ professional development preferences for blended learning and technology acceptance profiles

引用

Computers in Human Behavior Reports 2025年 18卷

作者： Garone, Anja Howard, Sarah K. Yang, Jie Tondeur, Jo Pynoo, Bram Bruggeman, Bram Struyven, Katrien Faculty of Psychology and Education Vrije Universiteit Brussel Pleinlaan 2 Brussels 1050 Belgium School of Education University of Leeds Leeds LS2 9JT United Kingdom Faculty of Engineering and Information Sciences School of Computing and Information Technology University of Wollongong Wollongong 2522 NSW Australia Vrije Universiteit Brussel Multidisciplinair Instituut Lerarenopleiding Brussels Research Institute for Teacher Education Pleinlaan 2 Brussels 1050 Belgium Education Policy Department VIVES University of Applied Sciences Doorniksesteenweg 145 Kortrijk 8500 Belgium UHasselt Research on Innovative and Society-engaged Education (U-RISE) School for Educational Studies Hasselt University Martelarenlaan 42 Hasselt 3500 Belgium Teacher Education Department Secondary Education Artevelde University of Applied Sciences Kattenberg 9 Gent 9000 Belgium

Blended learning is useful in higher education for catering to diverse student learning needs, however, higher education teaching staff need to be trained and supported so that it is applied attentively. Higher education teachers are diverse themselves with complex professional development needs. This study aims to examine the relationships between professional development preferences and 217 teaching staff grouped into technology acceptance profiles: high, moderate and low. Association rules analysis was run on an 18-item questionnaire dataset of the teaching staff's professional development preferences for blended learning. Results show that the high group is highly motivated to professionalise themselves collaboratively with added central support. The moderate group prefers centrally organised and guided professional development initiatives. The low group prefers centrally organised initiatives with guidance as well as incentive for professionalisation. These results highlight the differences between the groups, and how these preferences can be useful for designing targeted initiatives along with adapted communication strategies for groups with different technology acceptance levels. © 2025 The Authors

关键词： Association rules analysis Blended learning Data mining Higher education Professional development Teaching staff

来源：评论

学校读者我要写书评

暂无评论

Architecture optimization model for the probabilistic self-organizing maps and classification

Architecture optimization model for the probabilistic self-o...

引用

International Conference on Intelligent Systems: Theories and Applications (SITA)

作者： Z. En-naimani M. Lazaar M. Ettaouil Faculty of Science and Technology Modeling and Scientific Computing Laboratory Fez MOROCCO National School of Applied Sciences Abdelmalek Essaadi University Tetouan MOROCCO

In the present paper we describe a recent approach of probabilistic self-organizing maps (PRSOM). The PRSOM become more and more interesting in many fields such as: pattern recognition, clustering, classification, speech recognition, data compression, medical diagnosis. The PRSOM give an estimation of the density probability function of the data, this density dependent on the parameters of the PRSOM, such as the architecture. Associated with a given problem, it is one of the most important research problems in the neural network research. Also, we implemented and evaluated the proposed method; the numerical results are powerful and show the practical interest of our approach.

关键词： Accuracy Pattern recognition Testing Neurons

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based Approach for Janya Raga Classification in Carnatic Music

A Deep Learning Based Approach for Janya Raga Classification...

引用

Artificial Intelligence (SLAAI-ICAI), SLAAI International Conference on

作者： P. Kavitha J. Charles L. S. Lekamge Department of Computing and Information Systems Faculty of Applied Sciences Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka Department of Physical Sciences and Technology Faculty of Applied Sciences Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka

ISBN: (纸本)9781665476089

Janya Ragas are Carnatic music ragas derived from the fundamental ragas called Melakarta Raga, by the permutation and combination of various ascending and descending swaras. Raga recognition is an important task, essential to research in Music Information Retrieval in Indian Classical Music. Even though the automatic raga recognition methods have been widely adopted in Carnatic music, most of the existing methods are restricted only to Melakarta Ragas. It is an important task to identify the Melakarta Raga of a Janya Raga, especially for improved music recommendation performance. In this study, we used deep learning-based approach to address this problem. Music files were collected for 65 Janya Ragas belonging to seven Melakarta Ragas. Classification-based supervised deep learning models: 1D CNN, LSTM and 1D CNN-LSTM were used in the study. The models were implemented to learn similarities from 1–20 mean values of Mel-Frequency Cepstral Coefficients (MFCCs) features of audio samples, by using TensorFlow and Keras APIs. The results revealed that the 1D CNN-LSTM model outperformed the other models with an accuracy of 82.0%. In the future, 1D CNN-LSTM based Siamese neural networks can be introduced to reduce the dependence on large amounts of labeled audio data.

关键词： Deep learning Cepstral analysis Neural networks Convolutional neural networks Task analysis Music information retrieval Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Fast Mumford-Shah Two-Phase Image Segmentation Using Proximal Splitting Scheme

引用

Journal of applied Mathematics 2021年第none期2021卷 1-13页

作者： Shah, Nilima Patel, Dhanesh Fränti, Pasi Department of Applied Mathematics Faculty of Technology and Engineering Maharaja Sayajirao University of Baroda Vadodara Gujarat India School of Computing University of Eastern Finland Joensuu Finland Shenzhen China

The Mumford-Shah model is extensively used in image segmentation. Its energy functional causes the content of the segments to remain homogeneous and the segment boundaries to become short. However, the problem is that optimization of the functional can be very slow. To attack this problem, we propose a reduced two-phase Mumford-Shah model to segment images having one prominent object. First, initial segmentation is obtained by the k-means clustering technique, further minimizing the Mumford-Shah functional by the Douglas-Rachford algorithm. Evaluation of segmentations with various error metrics shows that 70 percent of the segmentations keep the error values below 50%. Compared to the level set method to solve the Chan-Vese model, our algorithm is significantly faster. At the same time, it gives almost the same or better segmentation results. When compared to the recent k-means variant, it also gives much better segmentation with convex boundaries. The proposed algorithm balances well between time and quality of the segmentation. A crucial step in the design of machine vision systems is the extraction of discriminant features from the images, which is based on low-level segmentation which can be obtained by our approach. © 2021 Nilima Shah et al.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enterprise problems and proposed solutions using the concept of E-commerce 2

Enterprise problems and proposed solutions using the concept...

引用

2nd International Conference on Smart computing and Electronic Enterprise, ICSCEE 2021

作者： Mohamad, Mohaizi Bin Kanaan, Anas Ghassan Aseh, Khairi Alawi, Nahg Abdulmajid Amayreh, Khalid Thaher Moaiad, Yazeed Al Al-Hodiany, Zakarya Mohsen Pathmanathan, P. Ravindran El-Ebiary, Yousef A. Baker North Borneo University College Malaysia Petra University Faculty of Management and Financial Sciences Business and E-commerce Department Amman Jordan International Institute of Applied Science Swiss School of Management Netherlands Malaysia and University of Aden Geomatika University College Yemen Irbid National University Faculty of Financial and Business Science Administration Department Irbid Jordan MEDIU Faculty of Computer and Information Technology Malaysia MEDIU Faculty of Finance and Admin. Sciences Malaysia UniSZA Faculty of Informatics and Computing Malaysia

ISBN: (纸本)9781665432221

The noise of e-commerce businesses has seen the extension of number of the online businesses global. Buyers now are opted with online business commerce which is greatly benefit compared to traditional businesses. It is undeniable e-commerce enterprises contribute more profits, comparing to "bricks-and-mortal"traditional enterprises, but not to be avoided the problems and challenges faced by the e- commerce marketplace. This study emphasizes the problems and challenges of e-commerce and a set of recommended solutions to those problems and challenges. Those problems are trust, readiness and security. For each of the problems, proposed solutions are presented. Companies have conducted business electronically by applying a range of electronic commerce solutions. In the current situation, a corporation enters the electronic market by building trading partner agreements with sellers or wholesalers of their choice. These deals may include any items that cannot be agree electronically, like terms of transfer, payment devices, or implementation rules. After discovering the right market relationships, a company must choose the elements of their electronic commerce system. In this paper have been formulate current ecommerce problems, challenges and their effective solutions. In future, e-commerce marketplace should concentrate more on securing payment, e-banking and e-government. With that, problems and challenges in e-commerce can be reduce. © 2021 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Acknowledging insufficiency in the evaluation of legal knowledge-based systems: Strategies towards a broadbased evaluation model 01

Acknowledging insufficiency in the evaluation of legal knowl...

引用

8th International Conference on Artificial Intelligence and Law, ICAIL '01

作者： Hall, Maria Jean J. Zeleznikow, John Donald Berman Laboratory for Information Technology and Law Applied Computing Research Institute La Trobe University Bundoora VIC 3083 Australia Centre for Forensic Statistics and Legal Reasoning Faculty of Law University of Edinburgh Old College South Bridge Edinburgh EH89YL United Kingdom

ISBN: (纸本)1581133685

This paper considers the need for evaluation of knowledge-based systems in general and legal knowledge-based systems in particular. Some special features of legal knowledge-based systems pertinent to their evaluation are presented. The expected benefits of such evaluations are discussed. and some of the difficulties likely to be encountered are *** proceedings of four International Conferences on Artificial Intelligence and Law are analysed to determine the rate of reporting evaluations in non-theoretical papers. These papers had a low rate of consideration of evaluation issues reflecting common practice in research biased development environments. These results confirm that more attention to evaluation is needed in the legal knowledge based systems *** paper foreshadows the development of an evaluation methodology tailored specifically for legal knowledge-based systems. Evaluation strategies beyond verification and validation are drawn upon, both from the international ISO/IEC 14598 and 9126 standards and also from previous work on evaluation models for knowledge-based systems. Copyright 2001 ACM.

关键词： Knowledge based systems

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：