检索结果-内蒙古大学图书馆

Iraqi Journal for computer science and mathematics 2022年第2期3卷 95-100页

作者： Kumar, Harish Soh, Ping Jack Ismail, Mohd Arfian Department of Computer Science College of Computer Science King Khalid University Abha61413 Saudi Arabia University of Oulu Finland Faculty of Computing College of Computing and Applied Sciences Universiti Malaysia Pahang Malaysia

Yesterday’s "Big Data" is today’s "data." As technology advances, new difficulties and new solutions emerge. In recent years, as a result of the development of Internet of Things (IoT) applications, the area of Data Mining has been confronted with the difficulty of analyzing and interpreting data streams in real time and at a high data throughput. This situation is known as the velocity element of big data. The rapid advancement of technology has come with an increased use of social media, computer networks, cloud computing, and the IoT. Experiments in the laboratory also generate a large quantity of data, which must be gathered, handled, and evaluated. This massive amount of data is referred to as "Big Data." Analysts have seen an upsurge in data including valuable and worthless elements. In extracting usable information, data warehouses struggle to keep up with the rising volume of data collected. This article provides an overview of big data architecture and platforms, tools for data stream processing, and examples of implementations. Streaming computing is the focus of our project, which is building a data stream management system to deliver large-scale, cost-effective big data services. Owing to this study, the feasibility of large-scale data processing for distributed, real-time computing is improved even when the systems are overwhelmed. © 2022 Autoctonía. Revista de Ciencias Sociales e Historia. All rights reserved.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Model and Computation of traffic Resilience 23

Model and Computation of traffic Resilience

引用

24th International Conference on computer Systems and Technologies, CompSysTech 2023

作者： Rothkrantz, Leon Faculty of Electronic Engineering Mathematics and Computer Science Delft University of Technology Netherlands and Faculty of Transportation Sciences Czech Technical University in Prague Czech Republic

ISBN: (纸本)9798400700477

At many times we observed disturbances of traffic flow on highways. This may be caused by traffic accidents, bad weather conditions, road maintenance or rush hours. The Road Traffic Management takes many rules and regulation, to make road sections more robust to disturbances and improve the recovery from disturbances in traffic flow (traffic resilience). To study the effect and impact of these rules and regulations assessment models of traffic resilience was needed. In this paper, we designed and tested such an assessment model. The model is inspired by the well-known Resilience Triangle. The assessment of traffic resilience was based on measurements of the speed of traffic flow on highways. Neural Networks were used to model and smooth recorded speed data. The Traffic Resilience model has been tested on real life data. © 2023 Owner/Author.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

A computational supervised neural network procedure for the fractional SIQ mathematical model

引用

European Physical Journal: Special Topics 2023年第5期232卷 535-546页

作者： Mukdasai, Kanit Sabir, Zulqurnain Raja, Muhammad Asif Zahoor Singkibud, Peerapongpat Sadat, R. Ali, Mohamed R. Department of Mathematics Faculty of Science Khon Kaen University Khon Kaen 40002 Thailand Department of Mathematics and Statistics Hazara University Mansehra Pakistan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou 64002 Taiwan Department of Applied Mathematics and Statistics Faculty of Science and Liberal Arts Rajamangala University of Technology Isan Nakhon Ratchasima 30000 Thailand Department of Mathematics Faculty of Engineering Zagazig University Zagazig Egypt Faculty of Engineering and Technology Future University in Egypt New Cairo 11835 Egypt Basic Engineering Science Department Benha Faculty of Engineering Benha University Benha Egypt Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon

The purpose of the current work is to provide the numerical solutions of the fractional mathematical system of the susceptible, infected and quarantine (SIQ) system based on the lockdown effects of the coronavirus disease. These investigations provide more accurateness by using the fractional SIQ system. The investigations based on the nonlinear, integer and mathematical form of the SIQ model together with the effects of lockdown are also presented in this work. The impact of the lockdown is classified into the susceptible/infection/quarantine categories, which is based on the system of differential models. The fractional study is provided to find the accurate as well as realistic solutions of the SIQ model using the artificial intelligence (AI) performances along with the scale conjugate gradient (SCG) design, i.e., AI-SCG. The fractional-order derivatives have been used to solve three different cases of the nonlinear SIQ differential model. The statics to perform the numerical results of the fractional SIQ dynamical system are 7% for validation, 82% for training and 11% for testing. To observe the exactness of the AI-SCG procedure, the comparison of the numerical attained performances of the results is presented with the reference Adam solutions. For the validation, authentication, aptitude, consistency and validity of the AI-SCG solver, the computing numerical results have been provided based on the error histograms, state transition measures, correlation/regression values and mean square error. © 2022, The Author(s), under exclusive licence to EDP sciences, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Hybrid LSTM-Attention-CatBoost Model for Complex Energy Behavior Forecasting 3

Leveraging Hybrid LSTM-Attention-CatBoost Model for Complex ...

引用

3rd International Conference on Smart Grids and Energy Systems, SGES 2024

作者： Lu, Lu Shen, Zhengdong Li, Shuting Wang, Weili Faculty of Science and Technology Beijing Normal University·Hong Kong Baptist University United International College Zhuhai China Department of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing China School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology China School of Computer Science South China Normal University Guangzhou China

ISBN: (纸本)9798331539634

We present an advanced energy prediction model that addresses energy imbalance by integrating Long Short-Term Memory (LSTM) with Attention Mechanism for time-series analysis and categorical boosting (CatBoost) for categorical feature optimization. This model accurately predicts the complex energy behaviors of prosumers who both generate and consume energy. Simulation results show that our model outperforms traditional methods with the lowest Mean Absolute Error (MAE) of 48.514. By achieving such a high level of accuracy, this model improves grid operation efficiency, offers a practical solution for smart grid management. © 2024 IEEE.

关键词： Attention Mechanism CatBoost Data Processing Energy Forecasting LSTM

来源：评论

学校读者我要写书评

暂无评论

A Fine-Tuned Large Language Model for Domain-Specific with Reinforcement Learning 3

A Fine-Tuned Large Language Model for Domain-Specific with R...

引用

3rd International Conference on Creative Communication and Innovative Technology, ICCIT 2024

作者： Ismail, Amelia Ritahani Aminuddin, Amira Shazleen Nurul, Afiqa Zakaria, Noor Azura Fadaaq, Wafa Haussain Nasser International Islamic University Malaysia Kulliyyah of Information and Communication Technology Department of Computer Science Kuala Lumpur Malaysia Arab Open University Faculty of Computer Studies Riyadh Saudi Arabia

ISBN: (纸本)9798350367492

Large Language Models (LLMs) like GPT-3 and BERT have significantly shown advancement in natural language processing by providing robust tools for understanding and generating human languages. However, their broad but shallow knowledge across many domains often leads to less effective performance in domain-specific tasks, where detailed and special-ized knowledge is needed. To address this limitation, this paper investigates the effectiveness of fine-tuning LLMs for specific domains. The approach incorporates reinforcement learning to integrate user feedback, allowing the model to dynamically adjust and refine its responses. This will ensure the model adapts iteratively, improving communication and interaction with users. The fine-tuned model's performance is evaluated using two domain-specific datasets - medical and dental. Evaluation metrics such as Levenshtein distance and cosine similarity are used to assess the textual accuracy and semantic relevance of the fine-tuned model. The results from the dental the medical datasets indicate a low level of textual differences and strong semantic alignment, respectively. These suggest that the fine-tuned model effectively processes and preserves the integrity of domain-specific content with the potential of fine-tuning LLMs to enhance their applicability in specific domains. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging ensemble deep models and llm for visual polysemy and word sense disambiguation

引用

Multimedia Tools and Applications 2025年 1-33页

作者： Setitra, Insaf Rajapaksha, Praboda Myat, Aung Kaung Crespi, Noel UMR CNRS 7253 Heudiasyc Sorbonne Université Université de Technologie de Compiègne 57 avenue de Landshut CompiègneCS 60319 - 60203 France Department of Artificial Intelligence Faculty of Computer Science University of Science and Technology Houari Bouemediene USTHB Algiers Algeria Telecom SudParis Institut Polytechnique de Paris Palaiseau91120 France Department of Computer Science Aberystwyth University SY23 3DB Ceredigion Aberys-twyth United Kingdom

Visual Polysemy Disambiguation (VPD) and Visual Word Sense Disambiguation (VWSD) are challenging tasks for both computer vision and NLP since an image can have diverse contextual interpretations, ranging from visual representations to abstract concepts. In this paper, we propose a novel approach to address the challenges of VPD and VWSD by leveraging ensemble deep models from computer vision to alleviate the problem of VPD and using the strength of LLMs to mitigate the problem of WSD. We first generate visually representative images from textual descriptions through a zero-shot text-to-image generation framework using image scrapping and Google search. We then employ an ensemble of classifiers and a deep network to learn feature representations, classify images into contexts and find the best match. Similarly, we perform the reverse process of generating textual descriptions from images using a Vision Transformer model and calculate the cosine distance with the actual text. Experimental evaluation of benchmark datasets demonstrates the effectiveness of our combined approach in strengthening both text-to-image and image-to-text generation, we improve disambiguation accuracy, providing a robust solution for VWSD with an MRR of 95.77% and a Hit rate of 92.00% surpassing state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Image representation

来源：评论

学校读者我要写书评

暂无评论

A sensitivity analysis of parameters in an agent-based model for crowd simulations

A sensitivity analysis of parameters in an agent-based model...

引用

作者： Crespi, Carolina Scollo, Rocco A. Fargetta, Georgia Pavone, Mario Department of Mathematics and Computer Science University of Catania Viale Andrea Doria 6 CataniaI-95125 Italy

In this research paper, we present a sensitivity analysis of parameters utilized in an agent-based model for crowd simulations. The model is made up of two types of agents that explore a virtual environment to reach an exit from a specified starting point. They behave differently depending on their type, and they may be collaborative, acting carefully to help others reach the exit, or defectors, acting independently and wildly. To simulate the agents’ and environment dynamics we used the Ant Colony Optimization algorithm principles. Three metrics to evaluate the effects of these behaviors have been used: the number of exited agents, the path cost, and the exit time. Furthermore, two different types of analyses have been carried out and are presented: group analysis, in which the performance of the groups into which the agents are split are compared;and types’ analysis, where the performance of the two types of agents, i.e., collaborators and defectors, are investigated and compared. © 2023

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-gradient-direction based deep learning model for arecanut disease identification

引用

CAAI Transactions on Intelligence Technology 2022年第2期7卷 156-166页

作者： S.B.Mallikarjuna Palaiahnakote Shivakumara Vijeta Khare M.Basavanna Umapada Pal B.Poornima Department of Computer Science and Engineering Bapuji Institute of Engineering and TechnologyDavanagereAffiliated to Visvesvaraya Theological UniversityBelagaviKarnatakaIndia Faculty of Computer Science and Information Technology University of MalayaKuala LumpurMalaysia Adani Institute of Infrastructure Engineering AhmedabadIndia Department of Computer Science Davanagere UniversityDavanagereKarnatakaIndia Computer Vision and Pattern Recognition Unit Indian Statistical InstituteKolkataWest BengalIndia

Arecanut disease identification is a challenging problem in the field of image *** this work,we present a new combination of multi-gradient-direction and deep con-volutional neural networks for arecanut disease identification,namely,rot,split and *** to the effect of the disease,there are chances of losing vital details in the *** enhance the fine details in the images affected by diseases,we explore multi-Sobel directional masks for convolving with the input image,which results in enhanced *** proposed method extracts arecanut as foreground from the enhanced images using Otsu ***,the features are extracted for foreground information for disease identification by exploring the ResNet *** advantage of the proposed approach is that it identifies the diseased images from the healthy arecanut *** results on the dataset of four classes(healthy,rot,split and rot-split)show that the proposed model is superior in terms of classification rate.

关键词： deep learning image analysis pattern recognition

来源：评论

学校读者我要写书评

暂无评论

The Classification Model of Learners Based on Diagnostic Assessment Results in E-learning With Machine Learning 1

The Classification Model of Learners Based on Diagnostic Ass...

引用

1st International Conference on Software Engineering and Information Technology, ICoSEIT 2022

作者： Yel, Mesra Betty Zarlis, Muhammad Suwilo, Saib Efendi, Syahril Sihombing, Poltak Universitas Sumatera Utara Graduate Program of Computer Science Department of Computer Science Medan Indonesia Universitas Binus Department of Computer Science Jakarta Indonesia Universitas Sumatera Utara Department of Mathematics Medan Indonesia

ISBN: (纸本)9781665473033

The development of technology and artificial intelligence, especially in the era of Industrial Revolution 4.0 almost covers all fields, one of which is e-learning. In its development, it is very important to determine the factors to produce the quality of e-learning. Machine learning can help to find various solutions in the real world, especially to solve problems for which a specific algorithm has not been found. The implementation of e-learning is often ineffective and not on target which has an impact on learning achievement that is not achieved, this is due to several things namely the learning model is applied in general, the learning materials and weights are applied equally to all users. Seeing these problems, it is necessary to have a model to classify students according to their abilities, talents, and interests before starting learning to achieve their goals to be achieved. This paper aims to create a machine learning approach model to determine the level of ability and needs of students before starting learning which can reduce disparities between students and follow up learning materials. With the machine learning based on learning model, e-learning can provide teaching materials according to the abilities, and interests of students, sustainably and improve the quality of students. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An optimal lightweight cryptography with metaheuristic algorithm for privacy preserving data transmission mechanism and mechanical design in vehicular ad hoc network

引用

Materials Today: Proceedings 2022年 66卷 789-796页

作者： Vinoth Kumar, K. Balaganesh, D. Department of ECE Lincoln University College Malaysia Faculty of Computer Science and Multimedia Lincoln University College Malaysia

Recently, vehicular ad hoc network (VANET) plays a vital part in intelligent transportation system (ITS) that intends to accomplish seamless Internet connectivity amongst the vehicles on the roadway. The VANET can be widely employed to enhance driving safety. But the wireless nature of the network results in challenging issues of security as well as privacy. In this aspect, this study designs an optimal Lightweight Cryptography with Dragonfly Firefly (LWC-DFFF) optimization algorithm to achieve privacy preserving communication in VANET. In addition, the proposed model involves the design of DFFF algorithm to determine the reliable nodes in the network for secured data transmission. Moreover, the LWC technique gets executed to securely transmit the data from source to destination via reliable nodes. The design of reliable node detection using DFFF algorithm helps to considerably improve the privacy preserving communication in VANET. A series of simulation analyses were carried out and the results are inspected interms of different measures. The experimental results highlighted the better performance of the LWC-DFFF algorithm over the recent approaches interms of different dimensions. © 2022

关键词： Vehicular ad hoc networks

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：