检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Soomro, Saira Soomro, Arjumand Bano Bhatti, Tarique Gulzar, Yonis Department of Distance Continuing and Computer Education Faculty of Education University of Sindh Hyderabad Pakistan Department of Software Engineering Faculty of Engineering and Technology University of Sindh Sindh Jamshoro Pakistan Department of Psychological Testing Guidance & Research Faculty of Education University of Sindh Hyderabad Pakistan Department of Management Information Systems College of Business Administration King Faisal University Al Ahsa Saudi Arabia

Blended learning (BL) is a recent trend among many options that can best fit learners' needs, regardless of time and place. This study aimed to discover students' perceptions of BL and the challenges faced by them while using technology. This quantitative study used data gathered from 300 students enrolled in four public universities in the Sindh province of Pakistan. The findings show that students were comfortable with the use of technology, and it has a positive effect on their academic experience. The study also showed that the use of technology encourages peer collaboration. The challenges found include: neither teacher support nor a training programme was provided to the students for the courses which needed to shift from a traditional face to face paradigm to a blended format, a lack of specialised skills in laboratory assistants for the courses with a blended format and a shortage of hi-tech computer laboratories/computer units to run these courses. Therefore, it is recommended that authorities must develop and incorporate a comprehensive mechanism for the effective implementation of BL in the teaching-learning process. Heads of departments should also provide additional computing infrastructure to their departments. © 2022, CC BY-NC-ND.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

NER- RoBERTa: Fine-Tuning RoBERTa for Named Entity Recognition (NER) within low-resource languages

arXiv

引用

arXiv 2024年

作者： Abdullah, Abdulhady Abas Abdulla, Srwa Hasan Toufiq, Dalia Mohammad Maghdid, Halgurd S. Rashid, Tarik A. Farho, Pakshan F. Sabr, Shadan Sh. Taher, Akar H. Hamad, Darya S. Veisi, Hadi Asaad, Aras T. Artificial Intelligence and Innovation Centre University of Kurdistan Hewler Erbil Iraq Computer Science and Engineering Department University of Kurdistan Hewler KR Erbil Iraq Department of Horticulture College of Agricultural Engineering Sciences University of Sulaimani- Kurdistan Region Iraq Branch of Basic Medical Science College of medicine University of Sulaimani- Kurdistan Region Iraq Department of Engineering Research Center Deanship of R&D Centers Koya University Kurdistan Region Iraq Department of Kurdish Language Faculty of Education Koya University Kurdistan Region Iraq Department of Kurdish Faculty of Education Koya University Kurdistan Region Iraq Department of Software Engineering Faculty of Engineering Koya University Kurdistan Region Iraq School of Intelligent Systems College of Interdisciplinary Science and Technologies University of Tehran Iran

Nowadays natural Language Processing (NLP) is an important tool for most people’s daily life routines, ranging from understating speech, translation, name entity recognition (ENR), and text categorizing, to the generative text models such as ChatGPT. Due to existing big data and consequently big corpora for the most usable languages including English, Spanish, Turkish, Persia, and many more, these applications have been utilized accurately. However, the Kurdish language still needs more corpora and big datasets to be included in the NLP applications. This is because the Kurdish language has a rich linguistic structure, varied dialects, and a poor dataset, which poses unique challenges for Kurdish NLP (KNLP) application development. While several types of research have been conducted in KNLP for various applications, the Kurdish ENR (KNER) remained a challenge for most of the KNLP applications including text analysis and text classification. In this work, we address this limitation by proposing a methodology for fine-tuning the pre-trained RoBERTa model for KNER1. To this end, first, a Kurdish corpus is created, followed by designing a modified model architecture, and the training procedures are implemented. To evaluate the trained model, a set of experiments is conducted to show the performance of the KNER model using different tokenization methods and trained models. The experimental results showed that fine-tuned RoBERTa with sentence-piece tokenization method substantially improves KNER performance by 12.8% (F1-score improvement) in comparison to traditional models and consequently establishes a new benchmark for KNLP. © 2024, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Smart Healthcare: A GAN-based Approach for Imbalanced Alzheimer's Disease Classification

引用

Procedia computer Science 2024年 241卷 146-153页

作者： Hina Tufail Abdul Ahad Ira Puspitasari Ibraheem Shayea Paulo Jorge Coelho Ivan Miguel Pires Department of Computer Science University of Management and Technology Sialkot Pakistan Information System Study Program Faculty of Science and Technology Universitas Airlangga School of Software Northwestern Polytechnical University Xian Shaanxi P.R. China Department of Electronics and Communication Engineering Istanbul Technical University(ITU) Turkey Polytechnic University of Leiria Leiria Portugal Institute for Systems Engineering and Computers at Coimbra (INESC Coimbra) Coimbra Portugal Instituto de Telecomunicações Escola Superior de Tecnologia e Gestão de Águeda Universidade de Aveiro Águeda Portugal

Alzheimer's disease (AD) is a type of dementia that leads to memory loss and impairment, which afects patients’ lives badly. It is not curable yet, but its progression can be slowed down if detected at earlier stages. In this research study, we propose a transfer learning-based convolutional neural network (CNN) model to classify magnetic resonance imaging (MRI) into one of four stages of Alzheimer's disease. One of the major limitations of the deep learning-based classification model is the non-availability of healthcare datasets related to AD. The widely used Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset has a major class imbalance issue. We propose a generative adversarial network (GAN) based data augmentation technique to overcome the data imbalance. This promotes the investigation of applying GANs to generate synthetic samples for minority classes in Alzheimer's disease datasets to enhance classification performance. The results show the progression in the overall classification process of AD.

关键词： Alzheimer disease (AD) Deep learning Convolutional Neural Network (CNN) computer-aided diagnosis (CAD)

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-based Service Chains Scheduling for Medical Emergency in Healthcare

Artificial Intelligence-based Service Chains Scheduling for ...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Mukesh Soni Maher Ali Rusho Haewon Byeon Azzah AlGhamdi Shaikh Abdul Hannan Parth Rameshchandra Dave Dr. D. Y. Patil Vidyapeeth Dr. D. Y. Patil School of Science & Technology Tathawade Pune Marashtra Department of Lockheed Martin Engineering Management University of Colorado Boulder Colorado Department of AI and Software & Medical Big Data Research Centre Inje University Gimhae Republic of Korea Computer Information Systems Department College of Computer Science and Information Technology Imam Abdalrhman Bin Faisal University Khobar Saudi Arabia Faculty of Computing and Information AlBaha University AlBaha Kingdom of Saudi Arabia Department of Computer Engineering L. D. College of Engineering Ahmedabad Gujarat India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

This study analyses the weekly scheduling challenge of health and medical information network service function chains to meet medical emergency categorization and grading needs. Emergency services are divided into four sorts by urgency and service area, with priorities and weights. The health and medical information network architecture, service model, and operation method are built accordingly. To reduce weighted completion time, a service function chain scheduling model is created. The function chain scheduling scheme is solved by matching game and Q -learning reinforcement learning algorithms for different issue scales. Finally, simulation studies demonstrate that this approach can accomplish graded medical emergency service, build health and medical information networks, and progress smart healthcare.

关键词： Schedules Job shop scheduling Service function chaining Hospitals Processor scheduling Reinforcement learning Games Emergency services Network function virtualization Standards

来源：评论

学校读者我要写书评

暂无评论

SGNet: Salient Geometric Network for Point Cloud Registration

SGNet: Salient Geometric Network for Point Cloud Registratio...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Qianliang Wu Yaqing Ding Lei Luo Haobo Jiang Shuo Gu Chuanwei Zhou Jin Xie Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Point Cloud Registration (PCR) is a critical and challenging task in computer vision and robotics. One of the primary difficulties in PCR is identifying salient and meaningful points that exhibit consistent semantic and geometric properties across different scans. Previous methods have encountered challenges with ambiguous matching due to the similarity among patch blocks throughout the entire point cloud and the lack of consideration for efficient global geometric consistency. To address these issues, we propose a new framework that includes several novel techniques. Firstly, we introduce a semantic-aware geometric encoder that combines object-level and patch-level semantic information. This encoder significantly improves registration recall by reducing ambiguity in patch-level superpoint matching. Additionally, we incorporate a prior knowledge approach that utilizes an intrinsic shape signature to identify salient points. This enables us to extract the most salient super points and meaningful dense points in the scene. Secondly, we introduce an innovative transformer that encodes High-Order (HO) geometric features. These features are crucial for identifying salient points within initial overlap regions while considering global high-order geometric consistency. We introduce an anchor node selection strategy to optimize this high-order transformer further. By encoding inter-frame triangle or polyhedron consistency features based on these anchor nodes, we can effectively learn high-order geometric features of salient super points. These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify critical correspondences for successful registration. The experiments conducted on the 3DMatch/3DLoMatch and KITTI datasets demonstrate the effectiveness of our method.

关键词： Point cloud compression computer vision Accuracy Shape Semantics Transformers Feature extraction Encoding Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Experimental Researches of Biometric Authentication Using Convolutional Neural Networks and Histograms of Oriented Graphs 4

Experimental Researches of Biometric Authentication Using Co...

引用

4th IEEE International Conference on Advanced Information and Communication Technologies, AICT 2021

作者： Kuznetsov, Alexandr Datsenko, Serhii Gorbenko, Yuriy Chupilko, Tetiana Korneyev, Maxim Klym, Victoria V.N. Karazin Kharkiv National University Department of Information Systems and Technologies Security Kharkiv Ukraine University of Customs and Finance Department of Computer Science and Software Engineering Dnipro Ukraine University of Customs and Finance Faculty of Innovative Technologies Dnipro Ukraine University of Customs and Finance Department of Cybersecurity and Information Technologies Dnipro Ukraine

ISBN: (纸本)9781665406185

User authentication technologies are an important component of modern cybersecurity. These technologies are designed to verify the correctness and validity, for example, by verifying the authenticity of entered passwords, identifiers, certain biometric features, and so on. We consider biometric authentication techniques for the human face. Two techniques are used to process biometric features in our work: convolutional neural networks and histograms of directed gradients. We conduct experimental research to study these techniques and compare the results of both in terms of authentication accuracy and the speed of processing biometric images. The obtained results will be useful in the development and implementation of cybersecurity applications that use biometric authentication © 2021 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Smart Harvesting based on Image Processing

Smart Harvesting based on Image Processing

引用

2020 International computer Symposium, ICS 2020

作者： Joseph, S.P Wijerathna, L.L.M.C. Epa, K.G.R.D. Egalla, E.K.W.A.P.K. Abeygunawardhana, P.W.K. De Silva, R Sri Lanka Institute of Information Technology Dep. of Computer Systems Engineering Faculty of Computing Malabe10115 Sri Lanka Sri Lanka Institute of Information Technology Dep. of Software Engineering Faculty of Computing Malabe10115 Sri Lanka

ISBN: (纸本)9781728192550

Vision device is a critical component of fruit harvesting mobile robot which is designed for recognizing and harvesting of tomato fruits. The system of vision device of the moving robot, for a dedicated path identification with the use of colour detection algorithms and contour detection algorithms could be stated as an additional usage of the image-based technology. When the robot operates in real life, varying environmental parameters would not affect its activity, since the robot will be functioning mainly indoors, specifically in a greenhouse. Robust fruit segmentation algorithms for the visual system and the fruit plucking mechanism using a readymade robot arm with a soft gripper where it operates with basic hardware components like motors, controlled by a microcontroller with the intervention of kinematic theories, is being used with the goal of collecting fruit objects efficiently in the natural world. Plucking only the ripe and healthy object fruit without damaging both the fruit and the tree is the intended task of the system. The aim is to reduce human effort by promoting automation concepts in agriculture in developing countries like Sri Lanka with great potential, where agriculture plays a vital role in the development of the economy while indoor plantation and harvesting mechanism are also being developing to cater to the economy of the country as well. The way that this system is implemented will be discussed in this paper. © 2020 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

An Efficient Localization for Indoor Environment using Classification Algorithms

An Efficient Localization for Indoor Environment using Class...

引用

2020 International Conference on Computational Science and Computational Intelligence, CSCI 2020

作者： Mulahuwaish, Aos Towne, Wyatt Ghafoor, Kayhan Zrar Maghdid, Halgurd S. Saginaw Valley State University Dept. of Computer Science and Information Systems Michigan United States Salahaddin University-Erbil Dep. of Software Engineering and Informatics Iraq Koya University Faculty of Engineering Dept. of Software Engineering Kurdistan Region-F.R. Iraq

ISBN: (纸本)9781728176246

The positioning accuracy of various kinds of devices is often calculated by using Wi-Fi fingerprints as a data source of Received Signal Strength (RSS). Through different matching algorithms, these RSS values are related to corresponding positioning coordinates for positioning estimation. In this paper, we compare two well known Machine Learning (ML) structures for calculating positioning accuracy: Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) and a Decision Tree (DT). Both matching algorithms run through a series of datasets in two parts. In the first part, the datasets contain raw, non-normalized RSS values. In the second part, the RSS values are all normalized to remove noise in the datasets. After extensive testing and simulations, the tests showed that as long as RSS values are first normalized, a Decision Tree offers better average positioning accuracy. © 2020 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Emerging case oriented agents for sustaining educational institutions going green towards environmental responsibility

引用

Journal of systems and Information Technology 2019年第2期21卷 186-214页

作者： Anthony Jnr, Bokolo Abdul Majid, Mazlina Romli, Awanis Department of Computer Science Norwegian University of Science and Technology NTNU Trondheim Norway Universiti Malaysia Pahang Faculty of Computer Systems and Software Engineering Kuantan Malaysia

Purpose: The purpose of this paper is to design a system deployment model that integrates case-based agent technique to develop an eco-responsibility decision support tool for greening educational institutions toward environmental responsibility. Design/methodology/approach: Data were collected through questionnaires distributed among a statistical population that comprised practitioners across educational institutions in Malaysia that implement green practices. The questionnaire measured the feasibility of the developed tool based on factors derived from the literature. Accordingly, descriptive, exploratory and factor analysis approach using statistical package for social sciences (SPSS) was used to test the feasibility of the developed tool. Findings: Results from descriptive analysis confirm the tool is feasible based on mean values that range from 4.1619 to 3.6508 on a five-point scale, indicating that the tool is effective in sustaining educational institutions going green. Besides, results from exploratory analysis verify the reliability of the tool based on the acceptable Cronbach’s alpha reliability coefficient score higher than 0.7 and Kaiser–Meyer–Olkin value being above 0.5. Finally, results from factor analysis reveal that the developed tool is usable, efficient, helpful, flexible and credible and supports educational institutions in going green at 88.44 per cent of the total variance, suggesting that the respondents are satisfied with the tool. Research limitations/implications: The sample population in this study comprises only practitioners from educational institutions in Malaysia. Theoretically, this research provides feasibility factors and associated items that can be used in evaluating developed information systems. Practical implications: Practically, this study develops an eco-responsibility decision support tool to facilitate green strategies and provides information on how practitioners in educational institutions can improve green growth. So

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

An intelligent framework for sarcasm detection in Arabic tweets using deep learning with Al-Biruni earth radius optimization algorithm

引用

Alexandria engineering Journal 2025年 127卷 562-572页

作者： AL-anazi, Reema G. A. Alzaidi, Muhammad Swaileh Eltahir, Majdy M. Almukadi, Wafa Sulaiman Alajmani, Samah Hazzaa Darem, Abdulbasit A. Alshahrani, Mohammed Alhebaishi, Nawaf Department of Arabic Language and Literature College of Humanities and Social Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of English Language College of Language Sciences King Saud University P. O. Box 145111 Riyadh Saudi Arabia Department of Information Systems Applied College at Mahayil King Khalid University Saudi Arabia Department of Software Engineering College of Engineering and Computer Science University of Jeddah Saudi Arabia Department of Information Technology College of Computers and Information Technology Taif University P.O. Box 11099 Taif21944 Saudi Arabia Department of Computer Science College of Science Northern Border University Arar Saudi Arabia Computer Department Applied College Najran University Najran66462 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

Social media networks play a major role in expressing people's feelings, reviews, and thoughts. One of the popular linguistic patterns to express or criticize one's ideas with ridicule is sarcasm, where they have unintended and intended meanings in written text. The sarcastic text is used to reverse the polarity of the sentiment. As a result, sarcasm detection in the text positively affects the sentimental analysis (SA) tasks and improves accuracy. The sarcasm recognition of Arabic content is constrained even though Arabic is the most popular language for web content sharing, and yet still naive owing to various challenges, such as the insufficient data sources, the multiple dialects, and the morphological structure of the Arabic language. This study presents an Artificial Intelligence Driven Sarcasm Detection using Optimal Deep Learning (AIDSD-ODL) technique on Arabic tweets. In the AIDSD-ODL technique, a hyperparameter-tuned DL model is utilized to identify sarcastic or non-sarcastic Arabic tweets. At the initial stage, the AIDSD-ODL method undergoes data pre-processing to convert the input tweets into a compatible format. In the next phase, the Glove word embedding process is used in the AIDSD-ODL technique. The self-attention bidirectional long short-term memory (SA-BiLSTM) model is utilized for sarcasm detection. The Al-Biruni Earth Radius (BER) model is implemented for the hyperparameter selection process to enhance the performance of the SA-BiLSTM network. The experimental results of the AIDSD-ODL method are examined under the Arabic tweets dataset. The comparison study of the AIDSD-ODL method portrayed a superior accuracy value of 94.20 % over existing models. © 2025 The Authors

关键词： Deep learning

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：