检索结果-内蒙古大学图书馆

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Rishi Shah Nisarg Chaudhari Tanvi Sheikh Dweepna Garg Parth Goel Department of Computer Engineering Faculty of Technology and Engineering (FTE) Devang Patel Institute of Advance Technology and Research (DEPSTAR) Charotar University of Science and Technology (CHARUSAT) Changa Anand Gujarat Department of Computer Science & Engineering Faculty of Technology and Engineering (FTE) Devang Patel Institute of Advance Technology and Research (DEPSTAR) Charotar University of Science and Technology (CHARUSAT) Changa Anand Gujarat India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

This paper explores the integration of Wav2Lip lip-sync technology into virtual assistants and chatbots, enhancing their interactivity by turning static images into video with synchronized lip movements. By combining text-to-speech (TTS) and video synthesis, the system aims to create more engaging and human-like digital assistants. Current chatbots and virtual assistants, such as those found on websites and devices like Google Assistant and Alexa, lack personalized visual elements, limiting user connection and engagement. Our proposed solution utilizes the Bark AI library to generate personalized and vivid speech from text, converts images to video using MoviePy, and ensures accurate lip-sync with Wav2Lip technology. The final output is a video where the assistant's lips move in sync with the spoken audio, providing a more realistic and personalized user experience.

关键词： Visualization Limiting Virtual assistants Lips Chatbots Ubiquitous computing Turning User experience Text to speech Synchronization

来源：评论

学校读者我要写书评

暂无评论

Cloud-Powered Virtual Doctor Robots for Enhancing Elderly Care and Chronic Disease Management with Recurrent Neural Networks 3

Cloud-Powered Virtual Doctor Robots for Enhancing Elderly Ca...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Ramesh, S. Mohankumar, N. Kovarasan, Rajesh Kambattan Selvamanikandan, R. Yuvaraj, S. Sujatha, S. Srm Institute of Science and Technology School of Computing College of Engineering and Technology Department of Computing Technologies Chennai Tamil Nadu Kattankulathur India Maharashtra Nagpur India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Electrical and Electronics Engineering Tamil Nadu Trichy India Faculty of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350369083

This research introduces cloud-powered virtual doctor robots to improve elderly care and chronic illness management. This system uses recurrent neural networks (RNNs) to give personalized medical care to elderly chronic disease patients. These virtual doctor robots may integrate with cloud computing infrastructure to access huge medical databases for real-time patient data analysis and individualized treatment and care suggestions. Healthcare technology has advanced by using RNNs to learn from patient data, adapt to changing health situations, and predict prospective health issues. RNNs can interpret sequential data, thus virtual doctor robots may identify trends in patient health parameters, forecast illness development, and suggest risk mitigation strategies. Cloud-powered virtual doctor robots provide a scalable solution to conventional healthcare systems rising issues. These robots can work effectively in resource-constrained areas by offloading computational chores to distant servers, providing continuous medical expertise and lowering healthcare staff reliance. This technique might improve aged care and reduce load on overworked healthcare systems. Using proactive monitoring, timely intervention, and personalized guidance, virtual doctor robots with RNNs can improve health outcomes, empower patients to manage chronic conditions, and create a more sustainable healthcare model. © 2024 IEEE.

关键词： Medical robotics

来源：评论

学校读者我要写书评

暂无评论

High-Level Deep Features and Convolutional Neural Network for Evaluating the Classification Performance of File Cluster Types 1

引用

6th International Conference on Innovative Computing and Communication, ICICC 2023

作者： Ali, Rabei Raad Dawd, Lahib Nidhal Mostafa, Salama A. Rachmawanto, Eko Hari Jubair, Mohammed Ahmed National University of Science and Technology Thi-Qar Nasiriyah Iraq Computer Techniques Engineering Department Dijlah University College Baghdad Iraq Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Batu Pahat Malaysia Department of Informatics Engineering Dian Nuswantoro University 207 Imam Bonjol Street Semarang50131 Indonesia Department of Computer Technical Engineering College of Information Technology Imam Ja’afar Al-Sadiq University Al-Muthanna66002 Iraq

ISBN: (数字)9789819933150

ISBN: (纸本)9789819933143

Accurate file recovery of the corrupted or fragmented file is a very important task when missing the file system, since file recovery procedure involves methods, techniques, and tools that analyze and classify the contents of each data cluster including JPG file or non-JPG file. For classification problems, convolutional neural networks and high-deep learning have been applied to be very efficient and effective in file recovery. This study aims at finding a systematic comparison between a support vector machine (SVM) classifier method and an extreme learning machine (ELM) classifier method for classification issues. The classification methods automatically classify the files in a continuous series of data clusters based on three deep features which are rate of change (RoC), byte frequency distribution (BFD), and entropy. The methods are automatically assigning a class label of JEG file or non-JPG file for fragmented data clusters. The RABEI-2017 dataset was used for evaluating the performance of this study. The results demonstrate that the SVM method outperforms the ELM method with a high accuracy rate to classify fragmented JPG files. The accuracy of classification of the SVM method is 90.15% and of the ELM method is 96.21%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Cuckoo Search-Optimized Deep CNN for Enhanced Cyber Security in IoT Networks

引用

computers, Materials & Continua 2024年第12期81卷 4109-4124页

作者： Brij B.Gupta Akshat Gaurav Varsha Arya Razaz Waheeb Attar Shavi Bansal Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413TaiwanChina Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057MaharashtraIndia Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India University Centre for Research and Development(UCRD) Chandigarh UniversityChandigarh140413India Computer Engineering Ronin InstituteMontclairNJ 07043USA Department of Business Administration Asia UniversityTaichung413TaiwanChina Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon Management Department College of Business AdministrationPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Research and Innovation Insights2TechinfoJaipur302001India Department of Computer Science Faculty of ScienceNorthern Border UniversityArar91431Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)Hong Kong518031China

Phishing attacks seriously threaten information privacy and security within the Internet of Things(IoT)*** phishing attack detection solutions have been developed for IoT;however,many of these are either not optimally efficient or lack the lightweight characteristics needed for practical *** paper proposes and optimizes a lightweight deep-learning model for phishing attack *** model employs a two-fold optimization approach:first,it utilizes the analysis of the variance(ANOVA)F-test to select the optimal features for phishing detection,and second,it applies the Cuckoo Search algorithm to tune the hyperparameters(learning rate and dropout rate)of the deep learning ***,our model is trained in only five epochs,making it more lightweight than other deep learning(DL)and machine learning(ML)*** proposed model achieved a phishing detection accuracy of 91%,with a precision of 92%for the’normal’class and 91%for the‘attack’***,the model’s recall and F1-score are 91%for both *** also compared our approach with traditional DL/ML models and past literature,demonstrating that our model is more *** study enhances the security of sensitive information and IoT devices by offering a novel and effective approach to phishing detection.

关键词： Deep learning phishing Cuckoo Search cable news network(CNN) IoT ANOVA F-test

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation Optimization in 5G Networks Using Variational Quantum Regressor 1

Resource Allocation Optimization in 5G Networks Using Variat...

引用

1st International Conference on Quantum Communications, Networking, and Computing, QCNC 2024

作者： Pathak, Param Oad, Vidhi Prajapati, Aditya Innan, Nouhaila Sardar Vallabhbhai Patel Institute of Technology Dept. of Computer Engineering India Vishwakarma Government Engineering College Dept. of Electronics and Communication India Dhirubhai Ambani Institute of Information and Communication Technology Dept. of Information and Communication Technology India Quantum Physics and Magnetism Team LPMC Faculty of Sciences Ben M'sick Hassan II University of Casablanca Morocco

ISBN: (纸本)9798350366778

Quantum Machine Learning (QML) is a powerful tool for addressing complex telecommunications challenges. As 5G technology continues to evolve, our research provides a roadmap for integrating QML into the resource allocation framework, potentially improving the efficiency and performance of 5G networks. Through the application of the Variational Quantum Regressor (VQR), our study demonstrates the potential for quantum models to enhance predictive accuracy in resource allocation scenarios. Our VQR accurately aligns predicted quantum states with their intended targets, thereby reducing discrepancies. Such precision in regression analysis, particularly in the context of 5G networks, represents a significant breakthrough. A key highlight of our algorithm is its ability to substantially reduce the mean squared error to an impressively low value of 0.0081, indicating near-perfect prediction accuracy. This innovative approach is set against the backdrop of the evolving landscape of communication networks and computational systems, where the challenge of resource allocation is increasingly pronounced due to the rising demand for bandwidth-intensive and computation-heavy services. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

THE CURRENT CAPABILITIES AND FUTURE POTENTIAL OF ROBOTIC REHABILITATION

引用

Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University 2023年第2期58卷 576-585页

作者： Khalid, Al Smadi Al-Sharo, Yasser Mohammad Younes, Mohammad Ali Bani Takialddin, Al Smadi Hamzeh, Al Athamneh Computer Science Jadara University Jordan Faculty of Computer Science and Information Technology Ajloun National University Jordan Faculty of Engineering Jerash University Jordan Computer Science Cybernet Jordan

This paper explores Robotic Rehabilitation Devices and their ability to help patients overcome injuries limiting and disrupting lower body and upper body movement, even helping with back injuries. This atomization of therapy enables many patients to be treated at the same time and even from home, in a process called tele-rehabilitation. Data can be collected from the biofeedback mechanisms implemented in the devices are used to analyze performance and improvement in the movement of patients. The most valuable aspect of rehabilitation through robotics is that it increases access to therapy, which is usually unavailable due the large demand for treatment. © 2023 Science Press. All rights reserved.

关键词： Biofeedback

来源：评论

学校读者我要写书评

暂无评论

Monitor the Effectiveness of Cardiovascular Disease Illness Diagnostics Utilizing AI and Supervised Machine Learning Classifiers 7th

Monitor the Effectiveness of Cardiovascular Disease Illness ...

引用

7th International Conference on Information and Communication technology for Intelligent Systems, ICTIS 2023

作者： Rathod, Dushyantsinh B. Patel, Yesha Jethava, Archana Gohel, Namrata Suthar, Dhruvi Varia, Dhaval Shah, Nirav Barot, Janki Computer Engineering Department Ahmedabad Institute of Technology Gujarat Ahmedabad India Department of CSE GLS Institute of Faculty of Engineering & Technology GLS University Gujarat Ahmedabad India Vishwakarma Government Engineering College Gujarat Ahmedabad India Lambton College Toronto Canada Silver Oak University Gujarat Ahmedabad India

ISBN: (纸本)9789819940394

The heart is a crucial component of all living organisms. Greater thoroughness and precision are required for heart disease diagnosis and prognosis since even a little error may result in serious consequences or even death;there are many heart-related fatalities and the number is growing daily (Kumar et al. in Cardiac disease prediction using data mining algorithm. Springer Nature Singapore, Singapore, 2020). An illness awareness prediction system is a crucial component needed to address this issue. Machine learning is an illustration of AI (artificial intelligence). It is quite helpful for predicting all kinds of occurrences related to natural catastrophes. In this work, utilizing benchmark data sets from Kaggle for training and testing, we assess the efficiency of machine learning algorithms for heart disease prediction (Gupta and Vinayaka in Cardiac arrest disease prediction system using classification algorithms. Springer Nature Singapore, Singapore, 2020), including k-proximal neighbors, decision trees, linear regression, and Random Forest Classifier. The Anaconda (Jupyter) notebook, which includes a range of libraries and header files that make the process quick and easy, is the ideal tool for utilizing Python programming. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

A novel Full Multiplicative Data Envelopment Analysis Model for solving Multi-Attribute Decision-Making problems

引用

Decision Analytics Journal 2025年 14卷

作者： Wichapa, Narong Choompol, Atchara Sangmuenmao, Ronnachai Department of Industrial Engineering Faculty of Engineering and Industrial Technology Kalasin University Kalasin 46000 Thailand Department of Computer Engineering Faculty of Engineering and Industrial Technology Kalasin University Kalasin 46000 Thailand

This study presents a novel Full Multiplicative Data Envelopment Analysis (FMDEA) for solving Multi-Attribute Decision-Making (MADM) problems. The proposed model offers an innovative approach to solving MADM problems by integrating the principles of Data Envelopment Analysis (DEA) with Full Multiplicative Form (FMF). This approach effectively addresses the significant limitations of traditional MADM methods, particularly concerning data normalization and computational complexity. We demonstrate the robustness and reliability of the proposed FMDEA model through its application across various decision-making scenarios. We demonstrate the perfect alignment of FMDEA with various decision-making scenarios, such as Multi-Objective Optimization with Full Multiplicative Form (MOOFMF), Multi-Objective Optimization by Ratio Analysis (MOORA), Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), Weighted Aggregated Sum Product Assessment (WASPAS), and Complex Proportional Assessment (COPRAS) in flexible manufacturing. The model exhibited high correlations with MOORA, MOOFMF, TOPSIS, WASPAS, and COPRAS. The FMDEA model consistently aligned with MOORA, MOOFMF, TOPSIS, WASPAS, and COPRAS in computer Numerical Control (CNC) lathe selection. These results confirm the FMDEA model's effectiveness in addressing MADM challenges by offering a simple, versatile, and user-friendly framework compatible with various optimization solvers, thus enhancing its practical applicability in complex decision-making contexts. © 2025 The Author(s)

关键词： computer Numerical Control Data Envelopment Analysis Flexible manufacturing Full Multiplicative Data Envelopment Analysis Full multiplicative form Multi-Attribute Decision-Making Performance Appraisal

来源：评论

学校读者我要写书评

暂无评论

Managing and Orchestrating Cross-Cloud VNFs with Deployable Sidecar VNF Coordinators

Managing and Orchestrating Cross-Cloud VNFs with Deployable ...

引用

IEEE Conference on Network Softwarization (NetSoft)

作者： Movsun Kuy Laurent Schumacher Sokchenda Sreng Faculty of Computer Science University of Namur Namur Belgium Faculty of Electrical Engineering Institute of Technology of Cambodia Phnom Penh Cambodia

ISBN: (数字)9798350369588

ISBN: (纸本)9798350369595

This work presents a novel approach for managing and orchestrating Virtual Network Functions (VNFs) across cloud domains. We introduce deployable Sidecar VNF (S-VNF) coordinators designed for seamless integration into existing infrastructure, enabling operators to leverage infrastructure services provided by different providers. This approach offers several advantages beyond flexibility: domain-specific adaptation to diverse environments, non-intrusive deployment minimizing disruption to existing NFV Management and Orchestration (MANO) systems, enhanced MANO interoperability, and improved security through proxying and shielding the underlying MANO management interface. Experiments confirm that the delay introduced by our S-VNF coordinators has a negligible impact on overall performance, making it a viable solution for cross-cloud VNF management.

关键词： Cloud computing Packaging Delays Security Interoperability

来源：评论

学校读者我要写书评

暂无评论

Hybrid Schrödinger-Ginzburg-Landau (Sch-GL) approach in study of superconducting integrated structures

arXiv

引用

arXiv 2023年

作者： Stojewski, Bartosz Pomorski, Krzysztof Cracow University of Technology Faculty of Electrical and Computer Engineering Poland Cracow University of Technology Faculty of Computer Science and Telecommunications Poland Quantum Hardware Systems

Various superconducting lattices were simulated and can be treated as lattices of superconducting atoms with preimposed symmetry in 1, 2 and 3 dimensions. Hybrid Schrödinger-Ginzburg-Landau approach is based on the fact of the mathematical similarity of Ginzburg-Landau (GL) and Schrödinger formalisms. Starting from Schrödinger approach by change of term V (x) - E with term α(x) + β(x)|ψ(x)|2we arrived at the Ginzburg-Landau equation. In the presented relaxation algorithm we use one and two dimensional ground energy solutions of Schrödinger equation and placed them as starting trial solution for GL relaxation method. In consecutive steps we increase the nonlinear term in the GL equation which results in achieving a stable approach of solution of GL equation. The obtained numerical results and used methodology form simulation platform bases for study of superconducting integrated structures that can model various superconducting devices. In general, one can model time-dependent geometry of superconducting structures. © 2023, CC0.

关键词： Simulation platform

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：