检索结果-内蒙古大学图书馆

Predicting the friction angle of clays using a multi-layer perceptron neural network enhanced by yeo-johnson transformation and coral reefs optimization

引用

Journal of Rock Mechanics and Geotechnical Engineering 2024年第10期16卷 3982-4003页

作者： Libing Yang Trung Nguyen-Thoi Trung-Tin Tran College of Civil Engineering and Architecture Hunan Institute of Science and TechnologyYueyang414006China Laboratory for Applied and Industrial Mathematics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh CityViet Nam Faculty of Mechanical-Electrical and Computer Engineering School of TechnologyVan Lang UniversityHo Chi Minh CityViet Nam Department of Information Technology Greenwich VietnamFPT UniversityDa Nang550000Viet Nam

The accurate prediction of the friction angle of clays is crucial for assessing slope stability in engineering *** study addresses the importance of estimating the friction angle and presents the development of four soft computing models:YJ-FPA-MLPnet,YJ-CRO-MLPnet,YJ-ACOC-MLPnet,and *** of all,the Yeo-Johnson(YJ)transformation technique was used to stabilize the variance of data and make it more suitable for parametric statistical models that assume normality and equal *** technique is expected to improve the accuracy of friction angle prediction *** friction angle prediction models then utilized multi-layer perceptron neural networks(MLPnet)and metaheuristic optimization algorithms to further enhance performance,including flower pollination algorithm(FPA),coral reefs optimization(CRO),ant colony optimization continuous(ACOC),and cuckoo search algorithm(CSA).The prediction models without the YJ technique,***-MLPnet,CRO-MLPnet,ACOC-MLPnet,and CSA-MLPnet,were then compared to those with the YJ technique,***-FPA-MLPnet,YJ-CRO-MLPnet,YJ-ACOC-MLPnet,and *** these,the YJ-CRO-MLPnet model demonstrated superior reliability,achieving an accuracy of up to 83%in predicting the friction angle of clay in practical engineering *** improvement is significant,as it represents an increase from 1.3%to approximately 20%compared to the models that did not utilize the YJ transformation technique.

关键词： Natural hazards Slope stability Friction angle Clay Soft computing models Geotechnical engineering

来源：评论

学校读者我要写书评

暂无评论

The Impact of Augmentation and SMOTE Implementation on the Classification Models Performance: A Case Study on Student Academic Performance Dataset

引用

Procedia computer science 2024年 245卷 282-289页

作者： Albert Verasius Dian Sano Faqir M. Bhatti Eka Miranda Mediana Aryuni Alfi Yusrotis Zakiyyah Charles Bernando Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Riphah Institute of Computing and Applied Sciences Riphah Intternational University Raiwind Lahore Pakistan Information Systems Department School of Information Systems Bina Nusantara University Jakarta 11480 Indonesia Mathematics Department School of computer Science Bina Nusantara University Jakarta 11480 Indonesia

This study aims to find out the impact of data augmentation and Synthetic Minority Over-sampling Techniques (SMOTE) implementation on the classification models performance using small and imbalanced dataset of student academic performance. The design of this study involved a comprehensive experiment by comparing four scenarios: 1) comparing classification models without both data augmentation and SMOTE, 2) models with data augmentation, 3) models with SMOTE, and 4) models with both data augmentation and SMOTE. The model's performances were each measured based on standard evaluation metrices such as accuracy, precision, recall, F1-score. To test the results validity, there were three classification algorithms implemented and evaluated for each scenario, that is, Random Forest, XGBoost, and AdaBoost. The finding of this study highlights the significant impact of data augmentation and SMOTE to the increase of classification models performance, particularly over the small and imbalanced dataset. Results showed that the implementation of both techniques simultaneously brought about the most significant increase in the evaluation metrices compared to the implementation of both techniques separately. The originality of this study lies in its comprehensive approach in comparing the effectiveness of data augmentation and SMOTE, as well as the use of student academic performance dataset, which is, a real case in the context of artificial intelligence. This finding gives a valuable insight to the researchers and practitioners in choosing appropriate techniques to handle small and imbalanced class datasets. This study is expected to make an important contribution to the more effective development of classification methodology in various domains.

关键词： Data augmentation Imbalanced class Small dataset, SMOTE

来源：评论

学校读者我要写书评

暂无评论

Data and Ensemble Machine Learning Fusion Based Intelligent Software Defect Prediction System

引用

computers, Materials & Continua 2023年第6期75卷 6083-6100页

作者： Sagheer Abbas Shabib Aftab Muhammad Adnan Khan Taher MGhazal Hussam Al Hamadi Chan Yeob Yeun School of Computer Science National College of Business Administration&EconomicsLahore54000Pakistan Department of Computer Science Virtual University of PakistanLahore54000Pakistan Department of Software Faculty of Artificial Intelligence and SoftwareGachon UniversitySeongnam13120Korea Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan School of Information Technology Skyline University CollegeUniversity City SharjahSharjahUAE Center for Cyber Security Faculty of Information Science and TechnologyUKMBangiSelangor43600Malaysia College of Engineering and IT University of Dubai14143UAE EECS Department Center for Cyber Physical SystemsKhalifa UniversityAbu Dhabi127788UAE

The software engineering field has long focused on creating high-quality software despite limited *** defects before the testing stage of software development can enable quality assurance engineers to con-centrate on problematic modules rather than all the *** approach can enhance the quality of the final product while lowering development *** defective modules early on can allow for early corrections and ensure the timely delivery of a high-quality product that satisfies customers and instills greater confidence in the development *** process is known as software defect prediction,and it can improve end-product quality while reducing the cost of testing and *** study proposes a software defect prediction system that utilizes data fusion,feature selection,and ensemble machine learning fusion techniques.A novel filter-based metric selection technique is proposed in the framework to select the optimum features.A three-step nested approach is presented for predicting defective modules to achieve high *** the first step,three supervised machine learning techniques,including Decision Tree,Support Vector Machines,and Naïve Bayes,are used to detect faulty *** second step involves integrating the predictive accuracy of these classification techniques through three ensemble machine-learning methods:Bagging,Voting,and ***,in the third step,a fuzzy logic technique is employed to integrate the predictive accuracy of the ensemble machine learning *** experiments are performed on a fused software defect dataset to ensure that the developed fused ensemble model can perform effectively on diverse *** NASA datasets are integrated to create the fused dataset:MW1,PC1,PC3,PC4,and *** to the results,the proposed system exhibited superior performance to other advanced techniques for predicting software defects,achieving a remarkable accuracy rate of 92.08%.

关键词： Ensemble machine learning fusion software defect prediction fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Hybrid Algorithm for Secure Routing in MANET Using Cryptographic Applications

Hybrid Algorithm for Secure Routing in MANET Using Cryptogra...

引用

2024 IEEE International Conference on Electronic systems and Intelligent Computing, ICESIC 2024

作者： Muruganandam, S. Gnanavel, S. Narayana, K.E. Jaeyalakshmi, M. Antony Kumar, K. Panimalar Engineering College Department of Computer Science and Business Systems Chennai India SRM Institute of Science and Technology Kattankulathur Campus Faculty of Engineering and Technology Department of Computing Technologies Chengalpattu India Rajalakshmi Engineering College Department of Information Technology Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331522988

In Mobile sensor Networks, Each and every wireless node dynamically changes its location due to its mobility nature. The routing information is maintained by the master node to deliver a data packet from source to destination. The attackers easily hack this wireless network. The performance of the complete networks is dropped by packets transmission attacks. Attacker node drops the packet. An enhanced protection technique in response to packets transmission misbehaviour attacks is provided to increase the energy efficiency of mobile nodes. This paper proposed the Cryptographic formed Malicious Node Detection and Secure Routing framework (CMNDSR). This model incorporates three various strategies specially algorithm for control of access, to protects initial illegal node in the network. The suspected identification and prevention techniques based on hop count value. Secure routing method with a private key generated at random like one time password (OTP). The proposed methods are power efficient, by operating a minimum number of nodes in challenging environment. The misbehaviour nodes are promptly identified and isolated using this proposed approach. The Cryptographic based Secure routing algorithm is applied to provide secure transmission in wireless networking environment. The outcomes of the simulation display how effectively the recommended approach can identify malicious nodes in a MANET. In comparison with previous methods, the energy consumption is 10% lower and the suspicious node detection rate is increased by 95%. © 2024 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Giving Voice to Nature: Participatory Design with Non-Human Stakeholders for Sustainable Development 24

Giving Voice to Nature: Participatory Design with Non-Human ...

引用

18th Biennial Participatory Design Conference - Reaching Out: Connecting Beyond Participation, PDC 2024

作者： Usanga, Chidi Storni, Cristiano Light, Ann Huybrechts, Liesbeth Teli, Maurizio Interaction Design Centre Department of Computer Science & Information Systems University of Limerick Ireland University of Sussex United Kingdom Malmö University United Kingdom Faculty of Architecture University of Hasselt Belgium Department of Sustainability and Planning Aalborg University Denmark

ISBN: (纸本)9798400706547

In this workshop, we aim to explore, discuss, and debate ways to engage and connect beyond the traditional human stakeholder in Participatory Design and to co-design with animals, plants, micro-organisms, and their ecosystems. We intend to collaboratively investigate how we can possibly expand participation to these more-than-human stakeholders which we have ignored so far and whose involvement in the design process is unexplored in relation to what is now needed in sustainable development. Acknowledging the limits of current PD theories, methods, and experiences in co-designing with more-than-human stakeholders, we invite participants to contribute with ideas, methods, case studies, and stories of "giving voice"to nature in PD: something we believe is key to rethink the field in light of the environmental crisis we are facing today. © 2024 Owner/Author.

关键词： Design for manufacturability

来源：评论

学校读者我要写书评

暂无评论

Czech Dataset for Complex Aspect-Based Sentiment Analysis Tasks 30

Czech Dataset for Complex Aspect-Based Sentiment Analysis Ta...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Šmíd, Jakub Přibáň, Pavel Pražák, Ondřej Král, Pavel Department of Computer Science and Engineering University of West Bohemia Faculty of Applied Sciences Univerzitní 2732/8 Pilsen301 00 Czech Republic NTIS - New Technologies for the Information Society Univerzitní 2732/8 Pilsen301 00 Czech Republic

ISBN: (纸本)9782493814104

In this paper, we introduce a novel Czech dataset for aspect-based sentiment analysis (ABSA), which consists of 3.1K manually annotated reviews from the restaurant domain. The dataset is built upon the older Czech dataset, which contained only separate labels for the basic ABSA tasks such as aspect term extraction or aspect polarity detection. Unlike its predecessor, our new dataset is specifically designed for more complex tasks, e.g. target-aspect-category detection. These advanced tasks require a unified annotation format, seamlessly linking sentiment elements (labels) together. Our dataset follows the format of the well-known SemEval-2016 datasets. This design choice allows effortless application and evaluation in cross-lingual scenarios, ultimately fostering cross-language comparisons with equivalent counterpart datasets in other languages. The annotation process engaged two trained annotators, yielding an impressive inter-annotator agreement rate of approximately 90%. Additionally, we provide 24M reviews without annotations suitable for unsupervised learning. We present robust monolingual baseline results achieved with various Transformer-based models and insightful error analysis to supplement our contributions. Our code and dataset are freely available for non-commercial research purposes. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Statistical Features and PageRank Scoring Fusion for Arabic Text Summarization

Statistical Features and PageRank Scoring Fusion for Arabic ...

引用

2022 International Conference on Intelligent Technology, System and Service for Internet of Everything, ITSS-IoE 2022

作者： Bahakam, Omer Salim Binwahlan, Mohammed Salem Farag Mogaibel, Hassen A. Al-Ahgaff University Faculty of Computer Science and Engineering Department of Information Technology Hadhramout Yemen Seiyun University College of Applied Sciences Department of Information Technology Hadhramout Yemen

ISBN: (数字)9781665459983

ISBN: (纸本)9781665459983

online text content is increasing daily, making it a big challenge for readers to find the required information. So, providing a gist of the available text content can help those readers save their time and effort. This operation is completed by Automatic Text Summarization (ATS), which creates a summary for the entire text. Automatic Text Summarization can be achieved by many techniques, such as graph theory, statistics, machine learning, and clustering methods. Each of the above techniques takes care of a specific issue of text which other techniques do not. Text summarization for the Arabic language suffers from a lack of resources and language complexity. So, it is worthwhile to take the advantages of two or more text summarization techniques and fuse them together to improve their performance and enhance their summary quality. This study proposes a method that combines two of the ATS methods, which are the statistical based method and the graph-based modified PageRank algorithm. Graph-based techniques take care of relationships among document sentences, whereas statistical-based techniques take care of signalizing important sentences. Experiment results show that proposed method achieved a good performance. The Essex Arabic Summaries Corpus (EASC) was used as evaluation data. © 2022 IEEE.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Improving Performance and Explainability of Sensor-Based Human Activity Recognition 9

Improving Performance and Explainability of Sensor-Based Hum...

引用

Joint 9th International Conference on Digital Arts, Media and Technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering, ECTI DAMT and NCON 2024

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350318241

Significant progress has been made in developing systems that can automatically recognize human activities, largely thanks to deep learning models and sensor data. However, high performance and comprehensibility are often at odds in these systems. The aim of this research is to enhance both the accuracy and understandability of models that use sensors for human activity recognition (HAR). We present a new convolutional neural network design which takes input from accelerometers and gyroscopes across multiple data streams. This allows efficient capture of time and frequency characteristics. Additionally, we put forward an attention module that identifies informative patterns in the sensor signals to shed light on the model's predictions. Experiments were conducted on a benchmark dataset of common daily movements gathered from ubiquitous sensors. Our model achieves state-of-the-art accuracy exceeding prior deep learning techniques. The attention visuals provide transparency into which sensor segments are most relevant for accurate activity classification. This validates improved model interpretability. Our multi-channel architecture pushes sensor-based HAR forward through heightened predictive performance. We offer original perspectives to create reliable, precise systems for HAR. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Big Data-Enabled Federated Learning for Secure and Collaborative Industrial IoT in Industry 4.0

Big Data-Enabled Federated Learning for Secure and Collabora...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Asia Bataineh Hamzah Alqudah Hazem Bani Abdoh Fuad Fataftah Computer Science Department Faculty of Information Technology University of Petra (UoP) Amman Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology American University of Madaba (AUM) Amman Jordan Computer Science Department Faculty of Computer Science and Information Technology Jerash university Jerash Jordan Mutlimedia systems and Virtual Reality School of Computer science Universiti Sains Malaysia (USM) Penang Malaysia

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Integrating the Internet of Things (IoT), Artificial Intelligence and big data analytics in Industry 4.0 has revolutionized industrial processes, enabling enhanced operational efficiency, predictive maintenance, and innovation. However, the increasing volume of sensitive and decentralized data generated by Industrial IoT (IIoT) devices introduces significant challenges, including data fragmentation, privacy concerns, and interoper-ability issues. Traditional centralized data analysis methods often fail to address these challenges effectively. This paper proposes a novel privacy-preserving federated learning framework tailored for IIoT environments to bridge these gaps. The framework enables secure and decentralized distributed big data analysis while ensuring data sovereignty and minimizing communication overhead. The proposed approach enhances predictive maintenance and anomaly detection by integrating advanced deep learning models with edge-fog-cloud architectures, fostering cross-company collaboration and scalability. Experimental evaluations using real-world predictive maintenance datasets demonstrate the framework's effectiveness in achieving high accuracy, optimized resource utilization, and reduced runtime. Additionally, incor-porating clustering techniques improves model personalization, enhancing performance without compromising data privacy. This research establishes FL as a transformative solution for secure, collaborative intelligence in Industry 4.0 ecosystems, paving the way for sustainable and intelligent manufacturing environments.

关键词： Data privacy Technological innovation Biological system modeling Scalability Collaboration Big Data Fourth Industrial Revolution Optimization Industrial Internet of Things Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

A Global Best-guided Firefly Algorithm for Engineering Problems

引用

Journal of Bionic Engineering 2023年第5期20卷 2359-2388页

作者： Mohsen Zare Mojtaba Ghasemi Amir Zahedi Keyvan Golalipour Soleiman Kadkhoda Mohammadi Seyedali Mirjalili Laith Abualigah Department of Electrical Engineering Faculty of EngineeringJahrom UniversityJahrom***FrasIran Department of Electronics and Electrical Engineering Shiraz University of TechnologyShiraz***Iran Department of Electrical and Computer Engineering Tarbiat Modares UniversityTehran***Iran Department of Computer Engineering Sari BranchIslamic Azad UniversitySari***Iran Department of Electrical Engineering Urmia BranchIslamic Azad UniversityUrmia571696896Iran Centre for Artificial Intelligence Research and Optimisation Torrens University AustraliaBrisbaneQLD4006Australia Yonsei Frontier Lab Yonsei UniversitySeoul03722South Korea Computer Science Department Prince Hussein Bin Abdullah Faculty for Information TechnologyAl Al-Bayt UniversityMafraq25113Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman UniversityAmman19328Jordan Faculty of Information Technology Middle East UniversityAmman11831Jordan School of Computer Sciences Universiti Sains Malaysia11800George TownPulau PinangMalaysia University Research and Innovation Center Obuda University1034BudapestHungary School of Engineering and Technology Sunway University MalaysiaPetaling Jaya27500Malaysia Applied science research center Applied science private universityAmman11931Jordan

The Firefly Algorithm(FA)is a highly efficient population-based optimization technique developed by mimicking the flashing behavior of fireflies when *** article proposes a method based on Differential Evolution(DE)/current-to-best/1 for enhancing the FA's movement *** proposed modification increases the global search ability and the convergence rates while maintaining a balance between exploration and exploitation by deploying the global best ***,employing the best solution can lead to premature algorithm convergence,but this study handles this issue using a loop adjacent to the algorithm's main ***,the suggested algorithm’s sensitivity to the alpha parameter is reduced compared to the original *** GbFA surpasses both the original and five-version of enhanced FAs in finding the optimal solution to 30 CEC2014 real parameter benchmark problems with all selected alpha ***,the CEC 2017 benchmark functions and the eight engineering optimization challenges are also utilized to evaluate GbFA’s efficacy and robustness on real-world problems against several enhanced *** all cases,GbFA provides the optimal result compared to other *** that the source code of the GbFA algorithm is publicly available at https://***/projects/gbfa.

关键词： Firefly algorithm New movement vector Global best-guided firefly algorithm Global optimization Engineering design

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：