检索结果-内蒙古大学图书馆

14th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2022

作者： Ugail, Hassan Edwards, Howell Benoy, Timothy Brooke, Christopher Centre for Visual Computing University of Bradford Faculty of Engineering and Informatics Bradford United Kingdom School of Chemistry and Biosciences University of Bradford Faculty of Life Sciences Bradford United Kingdom The de Brécy Trust De Brécy House Norfolk United Kingdom University of Nottingham Department of History Nottingham United Kingdom

ISBN: (纸本)9781665493345

Convolutional neural network (CNN) based deep learning has recently become the standard de facto for computer assisted image analysis and classification. In this work, we use an in-house trained deep face recognition model to extract facial features from images of old portraits to compare their degree of similarity. Taking the well-known visual Geometry Group (VGG) deep learning model as the basis, our in-house trained model is fine-tuned for enhanced facial similarity analysis, providing particular attention to the effects from prominent parts of the face, such as the eyes, nose and mouth features. We show how this model can be efficiently utilised to evaluate faces present in age-old master portraits. More specifically, we undertake facial similarity analysis of the faces in the oil paintings of Madonna and Child of de Brécy Tondo and Sistine Madonna by Raphael, of which the former has been the subject of national and international research for nearly 40 years. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Survey on AI-Enabled Resource Management for 6G Heterogeneous Networks:Recent Research,Challenges,and Future Trends

引用

Computers, Materials & Continua 2025年第6期83卷 3585-3622页

作者： Hayder Faeq Alhashimi Mhd Nour Hindia Kaharudin Dimyati Effariza Binti Hanafi Feras Zen Alden Faizan Qamar Quang Ngoc Nguyen Centre of Advanced Communication Research and Innovation(ACRI)Department of Electrical EngineeringFaculty of EngineeringUniversity of MalayaKuala Lumpur50603Malaysia School of Computing Sciences College of ComputingInformatics and MathematicsUniversiti TeknologiMaraShah Alam40450Malaysia Centre for Cyber Security Faculty of Information Science and Technology(FTSM)Universiti KebangsaanMalaysia(UKM)Bangi43600Malaysia Faculty of Science and Engineering Waseda UniversityTokyo169-8555Japan Faculty of Telecommunications Posts and Telecommunications Institute of TechnologyHanoi11518Vietnam

The forthcoming 6G wireless networks have great potential for establishing AI-based networks that can enhance end-to-end connection and manage massive data of real-time *** Intelligence(AI)advancements have contributed to the development of several innovative technologies by providing sophisticated specific AI mathematical models such as machine learning models,deep learning models,and hybrid ***,intelligent resource management allows for self-configuration and autonomous decision-making capabilities of AI methods,which in turn improves the performance of 6G ***,6G networks rely substantially on AI methods to manage *** paper comprehensively surveys the recent work of AI methods-based resource management for 6G ***,the AI methods are categorized into Deep Learning(DL),Federated Learning(FL),Reinforcement Learning(RL),and Evolutionary Learning(EL).Then,we analyze the AI approaches according to optimization issues such as user association,channel allocation,power allocation,and mode ***,we provide appropriate solutions to the most significant problems with the existing approaches of AI-based resource ***,various open issues and potential trends related to AI-based resource management applications are *** summary,this survey enables researchers to understand these advancements thoroughly and quickly identify remaining challenges that need further investigation.

关键词： Artificial intelligence(AI) resource management deep learning(DL) federated learning(FL) reinforcement learning(RL) evolutionary learning(EL)

来源：评论

学校读者我要写书评

暂无评论

Unprecedented Smart Algorithm for Uninterrupted SDN Services During DDoS Attack

引用

Computers, Materials & Continua 2022年第1期70卷 875-894页

作者： Muhammad Reazul Haque Saw Chin Tan Zulfadzli Yusoff Kashif Nisar Rizaludin Kaspin Iram Haider Sana Nisar J.P.C.Rodrigues Bhawani Shankar Chowdhry Muhammad AslamUqaili Satya Prasad Majumder Danda B.Rawat Richard Etengu Rajkumar Buyya Faculty of Computing&Informatics Multimedia UniversityPersiaranMultimediaCyberjaya63100SelangorMalaysia Faculty of Engineering Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Computing and Informatics University Malaysia SabahJalan UMSKota Kinabalu Sabah88400Malaysia Telekom Malaysia Research&Development TM Innovation Centre63000CyberjayaSelangorMalaysia Federal University of Piauí(UFPI) TeresinaPIBrazil Instituto de Telecomunica珲es 6201-001Covilh?Portugal National Center of Robotics and Automation-Condition Monitoring Systems Lab MUETJamshoroPakistan Department of Electrical and Electronic Engineering BUETDhaka1205Bangladesh Department of Electrical Engineering and Computer Science Data Science and Cybersecurity CenterHoward UniversityWashingtonDCUSA Cloud Computing and Distributed Systems(CLOUDS)Laboratory School of Computing and Information SystemsThe University of MelbourneMelbourneVIC 3053Australia

In the design and planning of next-generation Internet of Things(IoT),telecommunication,and satellite communication systems,controller placement is crucial in software-defined networking(SDN).The programmability of the SDN controller is sophisticated for the centralized control system of the entire ***,it creates a significant loophole for the manifestation of a distributed denial of service(DDoS)attack ***,recently a Distributed Reflected Denial of Service(DRDoS)attack,an unusual DDoS attack,has been ***,minimal deliberation has given to this forthcoming single point of SDN infrastructure failure ***,recently the high frequencies of DDoS attacks have increased *** this paper,a smart algorithm for planning SDN smart backup controllers under DDoS attack scenarios has *** proposed smart algorithm can recommend single or multiple smart backup controllers in the event of DDoS *** obtained simulated results demonstrate that the validation of the proposed algorithm and the performance analysis achieved 99.99%accuracy in placing the smart backup controller under DDoS attacks within 0.125 to 46508.7 s in SDN.

关键词： SDN smart algorithm RTZLK-DAASCP DDoS attack DRDoS

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of visuals: A Captivating Exploration of Scientific Data visualization Methods and Techniques 8th

Unleashing the Power of Visuals: A Captivating Exploration o...

引用

8th International visual informatics Conference, IVIC 2023

作者： Baharum, Aslina Ismail, Rozita Ismail, Ismassabah Mat Noor, Noorsidi Aizuddin Deris, Farhana Diana Halamy, Suhaida Computing and Information System School of Engineering and Technology Sunway University Jalan Universiti Selangor Bandar Sunway Malaysia College of Computing and Informatics Universiti Tenaga Nasional Putrajaya Campus Kajang Malaysia Centre of Foundation Studies Universiti Teknologi MARA Cawangan Selangor Kampus Dengkil Selangor Dengkil Malaysia Mass Appraisal Housing and Planning Research Group Centre for Real Estate Studies Real Estate Department Faculty of Built Environment and Surveying Universiti Teknologi Malaysia Johor Johor Bahru Malaysia Faculty of Social Sciences and Humanities Universiti Teknologi Malaysia Johor Johor Bahru Malaysia School of Information Science College of Computing Informatics and Mathematics Universiti Teknologi MARA Cawangan Sarawak Kota Samarahan Malaysia

ISBN: (纸本)9789819973385

Scientific visualizations are the building blocks for conveying results and ideas to a wide range of audiences. It is one of the steps in the data science process, and it should be done before the data presentation phase. Because some data is not easy to read for humans, visualization can help transform the data into visual content such as graphs or plots, as the requirement for scientific visualization techniques and methods is increasing greatly. Reviewing various visualization methods is necessary to increase knowledge about it. In this paper, an overview of scientific data visualization methods and techniques has been reviewed. To conduct the experiment, a total of five peer-reviewed articles relating to scientific visualization techniques were chosen. The problem with this study is that people still do not have a clear idea of how to use or what is the importance of scientific visualization. The findings of this paper show that the occurrence of visualization techniques improves the effectiveness of reading data and helps people to understand data in a more vivid way. A systematic literature review has been adopted in this study to assist the author in doing a study without bias. Finally, this paper can help readers increase their knowledge of the scientific visualization technique. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Autonomous Baby Monitoring System Using Mobile App Control 1

引用

8th International Conference on Computational Science and Technology, ICCST 2021

作者： Chung, Gwo Chin Teong, Khan Vun Tan, Soo Fun Sundarajoo, Ruven A/L Faculty of Engineering Multimedia University Cyberjaya63100 Malaysia Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu88400 Malaysia Preparatory Centre for Science and Technology Universiti Malaysia Sabah Kota Kinabalu88400 Malaysia

ISBN: (数字)9789811685156

ISBN: (纸本)9789811685149

In this modern world, almost 80% of parents have to work in order to balance their financial demands. The probability of providing better childcare, especially for babies is reducing. Although hiring a guardian or sending babies to daycare centers can temporarily solve the issue, it does not reduce the anxiety and stress of the parents due to more and more child abuses being reported every year. During this Covid19 pandemic, the need for an alternative better solution is urgent when some parents are forced to undergo quarantine for at least a few weeks. In this paper, we propose to develop a long-ranged baby monitoring and controlling system. The system consists of hardware architecture that is inter-connected with an IoT network to monitor the real-time condition of the baby such as crying, awakening and cleanliness, and its surrounding environment such as temperature, humidity and motion. In the proposal, the overall system operation involves four different phases: data collection, information sharing and processing, output display and notification, and user control. At the end of the project, a prototype has been successfully constructed to collect the monitoring data, and then share and display them to the users accurately via mobile app. In addition, users can also remotely perform basic control over any components or devices that are connected to the system. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Human–Computer Interaction: Unraveling the Power of Deep Learning Convolutional Neural Networks in Face Recognition 4th

Revolutionizing Human–Computer Interaction: Unraveling the ...

引用

4th International Conference on Advances in Computational Science and engineering, ICACSE 2023

作者： Baharum, Aslina Halamy, Suhaida Ismail, Rozita Abdul Rahim, Emelia Mat Noor, Noorsidi Aizuddin Deris, Farhana Diana Department of Computing and Information Systems School of Engineering and Technology Sunway University Bandar Sunway Selangor Malaysia School of Information Science College of Computing Informatics and Mathematics Universiti Teknologi MARA Cawangan Sarawak Kota Samarahan Malaysia College of Computing and Informatics Universiti Tenaga Nasional Putrajaya Campus Kajang Malaysia Faculty of Business Management Universiti Teknologi MARA Cawangan Sarawak Sarawak Kota Samarahan94300 Malaysia Mass Appraisal Housing and Planning Research Group Centre for Real Estate Studies Real Estate Department Faculty of Built Environment and Surveying Universiti Teknologi Malaysia Johor Johor Bahru Malaysia Faculty of Social Sciences and Humanities Universiti Teknologi Malaysia Johor Johor Bahru Malaysia

ISBN: (纸本)9789819729760

Face recognition, being one of the most effective applications of image analysis, has recently received a lot of attention due to the huge implication in human–computer interaction (HCI). As the availability and eligibility to detect a person’s facial features, face recognition technology has been used in biometric detection applications as uses certain aspects of a person’s physiology to identify them. In addition, Deep Learning, under the subset of machine learning, can solve various problems, especially in image processing and face recognition. The advancement and development of Deep Learning can also enhance the use of the Convolution Neural Network (CNN) as the predominant model in the field of face recognition. The paper discusses the systems based on CNN approaches and algorithms and provides a review of the CNN face recognition approach. Furthermore, each paper’s details, such as used datasets, techniques, architecture, and obtained findings, hence the application are fully summarized and analyzed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A One-Class Autoencoder for Porcelain Art Authentication

A One-Class Autoencoder for Porcelain Art Authentication

引用

IEEE International Conference on Signal and Image Processing Applications (ICSIPA)

作者： Hassan Ugail Howell Edwards Zaid Omar Centre for Visual Computing University of Bradford Bradford United Kingdom Faculty of Life Sciences University of Bradford Bradford United Kingdom Faculty of Electrical Engineering Universiti Teknologi Malaysia Johor Bahru Malaysia

ISBN: (数字)9798350352368

ISBN: (纸本)9798350352375

This preliminary study explores the application of machine learning techniques, specifically autoencoders, for the authentication of porcelain artworks. By focusing on the works of William Billingsley, we demonstrate how auto encoders can accurately reconstruct normal artworks and identify deviations in potentially misattributed pieces through higher reconstruction errors. We trained the chosen auto encoder by using five handcrafted image features-entropy, energy, contrast, homogeneity, and Hausdorff-Besicovitch dimension. The preliminary experimental results indicate that the auto encoder architecture selected and trained effectively distinguishes genuine Billingsley works from forgeries, providing a reliable tool for porcelain art attribution and authentication. This approach can potentially create a complementary tool for porcelain art authentication, adding reliability and objectivity to the world of art authentication, traditionally dominated by expert opinions as opposed to independent objectivity.

关键词： Training Porcelain Art Accuracy Authentication Forgery Robustness

来源：评论

学校读者我要写书评

暂无评论

Struct2Hair: A hair shape descriptor for hairstyle modeling

Struct2Hair: A hair shape descriptor for hairstyle modeling

引用

作者： Zhang, Wenshu Nie, Yinyu Guo, Shihui Chang, Jian Zhang, Jianjun Tong, Ruofeng Faculty of Arts and Media Norwich University of the Arts Norfolk United Kingdom The Visual Computing & Artificial Intelligence Lab Technical University of Munich München Germany School of Informatics Xiamen University Fujian China National Centre for Computer Animation Bournemouth University Dorset United Kingdom College of Computer Science and Technology Zhejiang University Zhejiang China

In recent years, it becomes possible to extract hair information for hair reconstruction from multiple cameras or monocular camera. Using a single image as the input avoids the high cost setups and complex calibration compared to multiviewed reconstruction. Taking advantage of an extendible hairstyle database, this paper introduced Struct2Hair, a novel single-viewed hair modelling approach by extracting hair shape descriptor (HSD). The HSD is defined as the fundamental structure-aware feature, which is a combination of critical shapes in a hairstyle. A complete dataset of critical hair shapes is constructed from a known database of three-dimensional (3D) hair models. We first analyze the input two-dimensional (2D) image to extract the orientation information and 2D hair sketch automatically. The extracted information is then used to retrieve the corresponding critical shapes with optimization to build the robust HSD. Finally, the HSD constructs a weighted 3D hair orientation field to guide full-head hair model generation. Our method can preserve local geometric features of hair and retain the whole shape of the hairstyle globally owing to the HSD, which will benefit further hair editing and stylization. © 2022 John Wiley & Sons Ltd.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Bidirectional LSTM-Based Energy Consumption Forecasting:Advancing AI-Driven Cloud Integration for Cognitive City Energy Management

引用

Computers, Materials & Continua 2025年第5期83卷 2907-2926页

作者： Sheik Mohideen Shah Meganathan Selvamani Mahesh Thyluru Ramakrishna Surbhi Bhatia Khan Shakila Basheer Wajdan Al Malwi Mohammad Tabrez Quasim Department of Computer Science and Engineering Srinivasa Ramanujan CentreSASTRA Deemed UniversityKumbakonam612001India Department of Computer Science and Engineering Faculty of Engineering and TechnologyJAIN(Deemed-to-be University)Bangalore562112India School of Science Engineering and EnvironmentUniversity of SalfordManchesterM54WTUK University Centre for Research and Development Chandigarh UniversityMohali140413PunjabIndia Centre for Research Impact and Outcome Chitkara University Institute of Engineering and TechnologyChitkara UniversityRajpura140401PunjabIndia Department of Information Systems College ofComputer and Information SciencePrincessNourah bintAbdulrahmanUniversityP.O.Box 84428Riyadh11671Saudi Arabia College of Computer Science Informatics and Computer Systems Department King Khalid UniversityAbha61421Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia

Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and *** study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory(LSTM)*** a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear *** bidirectional LSTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LSTMs consider only a single temporal *** design,combined with dropout regularization,leads to a 20.6%reduction in RMSE and an 18.8%improvement in MAE over conventional unidirectional LSTMs,demonstrating a substantial enhancement in prediction accuracy and *** to existing models—including SVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMSE of 0.2213 during testing,significantly outperforming these *** results highlight the model’s superior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive *** integrating advanced machine learning techniqueswith IoT and cloud infrastructure,this research contributes to the development of intelligent,sustainable urban environments.

关键词： Deep learning bidirectional LSTM energy consumption forecasting time-series analysis predictive modeling machine learning in energy management

来源：评论

学校读者我要写书评

暂无评论

A Diagnostic Method for Detecting Tomato Leaf Diseases Based on a Deep Learning Approach 9th

A Diagnostic Method for Detecting Tomato Leaf Diseases Base...

引用

9th International Conference on Computational Science and Technology, ICCST 2022

作者： Singkui, Zizie Vanessa Alfred, Rayner Fui, Florence Sia Gobilik, Januarius Moung, Ervin Gubin Iswandono, Zamhar Aziz, Azrina Abd Badruddin, Nasreen Drieberg, Micheal Creative Advanced Machine Intelligence Research Centre Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Sabah Malaysia Higher Colleges of Technology Abu Dhabi United Arab Emirates Department of Electrical and Electronic Engineering Universiti Teknologi PETRONAS Perak Seri Iskandar Malaysia

ISBN: (纸本)9789811984051

Nowadays, the agricultural area has been enhancing every day due to the innovation that makes farming far more effective and efficient in the production of crops. The Industrial Revolution 4.0 (IR4.0) plays a major role in ensuring that Smart Farming concept can be realized. For instance, a plant diagnostic tool using a deep learning approach can be developed to monitor the growth of plant or to investigate the health of the plant based on its leaf conditions. This study aims to investigate the feasibility of optimizing the deep learning algorithm to diagnose the quality of tomato crops using an optimized Convolutional Neural Network (CNN) model. In other words, this paper investigates the effects of varying the parameter settings used in the CNN architecture on the prediction accuracy of the tomato diseases. The objective of this project is to formulate a deep learning model, specifically a CNN model, that can be used to learn tomato leaf images to detect tomato diseases and also to optimize the proposed CNN model by utilizing the CNN parameters such as number of epochs, batch size and learning rate. The methodology used in this work can be divided into three main tasks which are Data Capturing and Fusion, Data Modelling and Model Assessment. Based on the obtained results, the combination of all three parameters has a great influence on the performance accuracy of the proposed deep learning algorithm. For instance, the highest performance accuracy of the CNN model could be obtained by setting the parameters as follows;Epoch = 500, Batch Size = 16, Learning Rate = 1e − 1, accuracy of 95.54% for the training dataset and 65.0% for the test dataset. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolutional neural 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：