检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2023年第3期8卷 742-757页

作者： Niu, Tianyu Li, Honghui Li, Weidong Por, Lip Yee College of Computer and Information Engineering Inner Mongolia Agricultural University Inner Mongolia Hohhot China Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia

With the continuous expansion of the data center, its energy consumption is also increasing. Aiming at the problem that the high redundancy of modern data center network causes low energy-consumption utilization, this paper proposes an energy-saving traffic scheduling algorithm (IMV-MLF) based on improved multi-layer-virtual-topology combined with maximum link-utilization path priority, which realizes more fine-grained control of each layer of virtual topology in data center network. Firstly, the relevant shap-ing linear programming mathematical model is established according to the optimization goal of energy conservation, which can minimize the energy consumption of the whole network as far as possible under the premise of meeting all network-flow requirements;Then, according to the optimization goal, the existing SDN based energy saving multi-layer-virtual-topology (EMV-SDN) method is improved. Whether the network devices in other layers are enabled is determined by the overall traffic level rather than the traffic level of a single link. On the basis of the opened level, the newly arrived network flows are preferentially allocated to the path with the highest link utilization, and overload link set is introduced, we can effectively use the available link routes with sufficient residual bandwidth to reduce congestion when the topology changes by marking the links whose link utilization reaches the critical value, and further count and close the links and switches which no network flows pass through. The experimental results show that the performance of IMV-MLF algorithm is better than multi-layer virtual topology energy saving (EMV-SDN) algorithm and the equivalent multipath (ECMP) algorithm in saving network energy. This result is helpful to provide another new idea for energy conservation of data center. © 2023, Journal of Network Intelligence.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Trust Model for Inter-Domain Routing

引用

computers, Materials & Continua 2025年第3期82卷 4821-4839页

作者： Qiong Yang Li Ma Sami Ullah Shanshan Tu Hisham Alasmary Muhammad Waqas Faculty of Information Technology Beijing University of TechnologyBeijing100124China School of Information Science and Technology North China University of TechnologyBeijing100144China Department of Computer Science Shaheed Benazir Bhutto UniversitySheringal18050Pakistan Department of Computer Science King Khalid UniversityAbha61421Saudi Arabia School of Computing andMathematical Sciences Faculty of Engineering and ScienceUniversity of GreenwichLondonSE109LSUK School of Engineering Edith Cowan UniversityPerthWA 6027Australia

Border Gateway Protocol(BGP),as the standard inter-domain routing protocol,is a distance-vector dynamic routing protocol used for exchanging routing information between distributed Autonomous Systems(AS).BGP nodes,communicating in a distributed dynamic environment,face several security challenges,with trust being one of the most important issues in inter-domain *** research,which performs trust evaluation when exchanging routing information to suppress malicious routing behavior,cannot meet the scalability requirements of BGP *** this paper,we propose a blockchain-based trust model for inter-domain *** model achieves scalability by allowing the master node of an AS alliance to transmit the trust evaluation data of its member nodes to the *** BGP nodes can expedite the trust evaluation process by accessing a global view of other BGP nodes through the master node of their respective *** incorporate security service evaluation before direct evaluation and indirect recommendations to assess the security services that BGP nodes provide for themselves and prioritize to guarantee their security of routing *** forward the trust evaluation for neighbor discovery and prioritize the nodes with high trust as neighbor nodes to reduce the malicious exchange routing *** use simulation software to simulate a real BGP environments and employ a comparative experimental research approach to demonstrate the performance evaluation of our trust *** with the classical trust model,our trust model not only saves more storage overhead,but also provides higher security,especially reducing the impact of collusion attacks.

关键词： Inter-domain routing BGP security blockchain trust model trust mechanisms trust evaluation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Transportation Mode Prediction: A Comparative Analysis

引用

Informatica (Slovenia) 2024年第6期48卷 117-130页

作者： Murrar, Samer Alhaj, Fatima Qutqut, Mahmoud H. Faculty of Information Technology Applied Science Private University Amman Jordan Faculty of Computer Science University of New Brunswick FrederictonNBE3B 5A3 Canada

This study investigates the performance of various machine learning (ML) algorithms in predicting transportation modes from large datasets. The investigated algorithms include Multilayer Perceptron (MLP), K-Nearest Neighbors (KNN), Decision Tree (DT), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Logistic Regression. We rigorously evaluated each algorithm’s performance using a robust set of metrics such as precision, recall, and F1-score. This study comprehensively explains the algorithm’s capabilities, strengths, and potential weaknesses across seven transportation categories:’walk’,’bike’,’bus’,’car’,’taxi’,’train’, and’subway’. The DT model consistently outperformed the others, demonstrating superior accuracy and an adequate balance of precision and recall across all modes of transportation. Specifically, it achieved precision, recall, and F1 scores of around 83% to 94% across all categories. These findings underline the suitability of the DT model for this classification task and its potential for further applications in transportation mode prediction based on large datasets. However, other algorithms like LSTM and RNN also showed promising results in certain categories, suggesting the value of continued exploration of different models depending on specific use cases. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Identifying Tajweed Rules: A Case Study on Noon Saakin and Tanween 1

Machine Learning Techniques for Identifying Tajweed Rules: A...

引用

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Al-Hagree, Salah Alawdi, Ala'a Alsayadi, Hamzah A. Alsurori, Muneer Abdo Al Sabri, Muaadh Computer Science Department Faculty of Computer and Information Technology Sana’a University Yemen Computer Science Department Faculty of Sciences Ibb University Yemen Aljazeera University Yemen Faculty of Computer and Information Sciences Ain Shams University Egypt

ISBN: (纸本)9798331533557

This study focuses on the classification of Tajweed rules from audio data and evaluates the effectiveness of various machine learning (ML) algorithms in emotion classification from speech. The dataset was created using audio samples, with a special focus on the Tajweed rules of Noon Saakinah and Tanween. The dataset exhibited class imbalance, and various data augmentation (DA) techniques were employed to address this. Preprocessing involved silence removal, normalization, and noise reduction to enhance the data's quality. Comprehensive feature extraction, covering both time-domain and frequency-domain features, was performed to capture the audio's key characteristics. Several ML models, including Random Forest (RF), support vector machines (SVM), K-Nearest Neighbors (KNN), and Multi-Layer Perceptron (MLP), were applied, and their performance was evaluated using metrics such as accuracy, precision, recall, and F1-score. The RF model achieved the highest accuracy (0.8222), outperforming other models such as MLP (0.7905) and Gradient Boosting (GB) (0.7746). Traditional models such as Naive Bayes (NB) and Logistic Regression (LR) exhibited lower performance, highlighting the limitations of simpler methods in complex classification tasks. © 2024 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Coexistence of Wi-Fi 6E with LTE-U/LAA in the 5 GHz Frequency Band 8th

Coexistence of Wi-Fi 6E with LTE-U/LAA in the 5 GHz Frequen...

引用

8th International Congress on information and Communication technology, ICICT 2023

作者： Ibrahim, Mohamed M. Azzuhri, Saaidal R. Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia

ISBN: (纸本)9789819932351

This work is how to achieve high user throughput with high performance in congested areas by amending the existing coexistence methods and enhancing the performance metrics by updating some input metrics such as duty cycle period, energy detection threshold, data transfer period, etc. The simple topology will verify the basic concept of LTE-U/LAA coexistence with Wi-Fi. Then the indoor-crowded coexistence scenarios of LTE-LAA/U and Wi-Fi 6E in the 5 GHz will be the main idea of this study using the enhanced CAT-4 LBT algorithm design. The proposed model evaluated the coexistence performance based on CDF of throughput and latency. The transport layer of wireless communication will play a worthy role. When using the TCP protocol, the Wi-Fi throughput and latency will be more effective than the LAA operator. When using the UDP protocol, the LTE-LAA network has better throughput and latency than the Wi-Fi network. The throughput and latency for LTE-U and Wi-Fi operators are roughly identical using the FTP protocol. Overall, the throughput improved by 20%, and an approximately 2 ms delay time of the handover compared to the previous research results. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

High performance of Dengue shock syndrome detection using extreme gradient boosting with ANOVA feature selection

Journal of Biotech Research

引用

Journal of Biotech Research 2024年 16卷 22-31页

作者： Muflikhah, Lailil Iskandar, Agustin Yudistira, Novanto Nadlori, Isbat Uzzin Dewanto, Bambang Nur Faculty of Computer Science Brawijaya University Malang India Faculty of Medicine Brawijaya University Malang India Department of Informatics Engineering and Computer Politeknik Elektronika Negeri Surabaya India Faculty of Technology Information Merdeka University Malang India

Dengue shock syndrome (DSS) is an infectious disease that affects millions of people every year all over the world. Early detection of DSS is essential for providing effective therapy and promoting patient recovery. In this work, we proposed a method to enhance DSS detection by combining the Extreme Gradient Boosting (XGBoost) algorithm with variance (ANOVA) feature selection analysis. We used a clinical dataset that contained important information gleaned from people with dengue virus infection. The dataset used for the research was collected from patients at Syaiful Anwar Hospital and consisted of 501 instances. Of these, 401 cases were related to DSS, while the other instances were unrelated to this specific medical condition. An analysis of variance (ANOVA) evaluated the most significant factors that distinguished persons with DSS from those with other dengue diseases. After that, the XGBoost model gave the characteristics of the selected features. For evaluation, we split the data into 80% and 20% for training and testing, respectively. The experimental result showed that the created model had a high degree of performance evaluation in detecting DSS. The highest performance achieved an accuracy of 0.839, precision of 0.875, recall of 0.92, and f1-score of 0.897. Most importantly, the model could detect DSS early on, enabling more proactive therapy and faster responses for individuals at risk of developing the condition. © (2024), (Bio Tech System). All Rights Reserved.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Recommendation Model for Learning Material Using the Felder Silverman Learning Style Approach

HighTech and Innovation Journal

引用

HighTech and Innovation Journal 2023年第4期4卷 811-820页

作者： Hasibuan, M.S. Abdul Aziz, R.Z. Dewi, Deshinta Arrova Kurniawan, Tri Basuki Syafira, Nasywa Aliyah Faculty Computer Science Institute Informatics and Business Darmajaya Bandar Lampung35136 Indonesia Faculty of Data Science and Information Technology INTI International University Nilai Malaysia Faculty of Technology and Information Science University Kebangsaan Malaysia Malaysia Faculty of Education Yogyakarta State University Yogyakarta Indonesia

The biggest obstacle that students have when participating in a virtual learning environment (e-learning) is discovering a platform that has functionalities that can be customized to fit their needs. This is usually accomplished in several ways using educational resources such as learning materials and virtual classroom design elements. Our research has tried to meet this demand by suggesting an extra element in the virtual classroom design, i.e., classifying the students’ learning styles through machine-learning techniques based on information gathered from questionnaires. This feature allows teachers or instructors to modify their lesson plans to better suit the learning preferences of their students. Additionally, this feature aids in the creation of a learning path that serves as a guide for students as they choose their course materials. In this study, we have selected the Felder-Silverman Learning Style Model (FSLSM) in the questionnaire design, which focuses on identifying the students' learning styles. After that, we employ several machine learning algorithms to create a prediction model for the students’ learning styles. The algorithms include Decision Tree, Support Vector Machines, K-Nearest Neighbors, Naïve Bayes, Linear Discriminant Analysis, Random Forest, and Logistic Regression. The best prediction model from this exercise contributes to the recommendation model that was created using a collaborative filtering algorithm. We have carried out a pre-test and post-test method to evaluate our suggestions. There were 138 learners who were following a learning path and participated in this study. The findings of the pretest and post-test indicated a notable increase in students' motivation to study. This is confirmed by the fact that learners' satisfaction with online learning climbed to 87% when the learning style was considered, from 60% when it wasn't. © 2023, Ital Publication. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Assessing the Teachers’ Readiness for Integrating Augmented Reality in K-12 Education: A Comparative Analysis

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第5期19卷 22-44页

作者： Ewais, Ahmed Dalipi, Fisnik Abualrob, Marwan Ferati, Mexhid Kurti, Arianit Computer Science Department Faculty of Information Technology Arab American University Jenin Palestine Department of Informatics Faculty of Technology Linnaeus University Växjö Sweden Elementary Education Department Faculty of Arts Arab American University Jenin Palestine

The integration of augmented reality (AR) into educational environments will depend on its perceived effectiveness in enhancing teaching practices and the attitudes toward the use of this technology. Therefore, the main objective is to investigate the teachers’ attitude and motivation to adopt AR in educational settings, which also looks at a cross-cultural context. Furthermore, this research reveals different aspects that have an impact on teachers’ attitudes toward adopting AR in the teaching process. To investigate this, we conducted a study with 87 K-12 teachers belonging to two different education systems, i.e., Sweden and Palestine. The mixed-methods approach enhances the validity of the study and provides a broad understanding through numerical data, while qualitative insights offer deeper explanations of the findings. The results indicate a statistically significant difference in teachers’ attitudes about AR, with a mean 3.99 for teachers coming from Palestine showing a more positive attitude towards AR-supported learning. Therefore, it is important for educational institutions and application developers to consider a range of learning and teaching methods, as well as specific needs, throughout the process of developing and incorporating AR into the curriculum. © 2025 by the authors of this article.

关键词： attitudes augmented reality (AR) education learning schools teachers

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning in Mental Diseases Diagnosis 25

Application of Machine Learning in Mental Diseases Diagnosis

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Alsawi, Rahaf Alazaidah, Raed Samara, Ghassan Alzoui, Haneen Alidmat, Omar Elsoud, Esraa Abu Talat Khouj, Mohammed Katrawi, Anwar Alluwaici, Mo'Ath Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Applied Science Private University Faculty of Information Technology Department of Computer Science Amman Jordan Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Zarqa University Faculty of It Department of Computer Science Zarqa Jordan

ISBN: (纸本)9798331540012

Mental diseases, mental disorders, or psychological disorders is a large group of symptoms which causes changes to the state of mood and reflect this on the behavior of the person with the mental disorder. It affects the patient's way of thinking, which limits his ability to perform his simple daily needs, and thus, becomes a burden on the individual, and on the surrounding society as well. There are common types of mental disorders such as depression, anxiety disorders, schizophrenia, and bipolar disorder. In this research, two main objectives are considered. The first objective is determining which is the best classifier for predicting a person's mental disorder among six well-known classifiers. The second objective is determining what is the best feature selection technique to use with mental disorders datasets considering six popular techniques, and with respect to several evaluation metrics. The results revealed that Logistic Regression and Naïve Bayes are the two best classification models, while Info Gain Ratio is the best feature selection method. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi Label Classification Based on Ensemble Learning: Investigative Study 25

Multi Label Classification Based on Ensemble Learning: Inves...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Nasir, Ola Alazaidah, Raed Hadi, Wael Samara, Ghassan Al Daoud, Essam Owaida, Suhaila Abu Elrashidi, Ali Elsoud, Esraa Abu Alzoubi, Haneen Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Petra University Faculty of Information Technology Department of Cyber Security Amman Jordan Zarqa University Faculty of Information Technolog Department of Computer Science Zarqa Jordan Al-al-Bayt University Faculty of Information Technology Department of Computer Science Mafraq Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Applied Science Private University Faculty of It Department of Computer Science Amman Jordan

ISBN: (纸本)9798331540012

In the big data technology nowadays, activities associated with Multi-Label Classification (MLC) pose big and complex challenges, receiving terrific interest in diverse fields. Existing MLC algorithms suffer from low overall performance. This paper considers four well-known Problem Transformation Methods (PTMs). Two of these PTMs are based on the frequency of the labels (MFL and LFL) while the last two PTMs are based on the positive correlations among labels. These PTMs have been implemented and compared against four multi label datasets of various sizes to identify the best one that fits the nature of MLC datasets. Moreover, six popular ensemble learning models have been carried out and compared on the four datasets with respect to several evaluation metrics such as Accuracy, Hamming loss, and Exact Match and using SMO, DecisionStump, Random Forest, and Random Commission classifiers. The results revealed that MFL accomplished the quality performance amongst the four PTMs, and Stacking SVM is the best ensemble learning technique. © 2024 IEEE.

关键词： Contrastive 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：