检索结果-内蒙古大学图书馆

Evolutionary Multitask Optimization in Real-World Applications: A Survey

Journal of Artificial Intelligence and Technology 2023年第1期3卷 32-38页

作者： Yue Wu Hangqi Ding Benhua Xiang Jinlong Sheng Wenping Ma Kai Qin Qiguang Miao Maoguo Gong School of Computer Science and Technology Xidian UniversityXi’anChina School of Artificial Intelligence Xidian UniversityXi’anChina Department of Computing Technologies Swinburne University of TechnologyHawthornAustralia School of Electronic Engineering Xidian UniversityXi’anChina

Because of its strong ability to solve problems,evolutionary multitask optimization(EMTO)algorithms have been widely studied *** algorithms have the advantage of fast searching for the optimal solution,but it is easy to fall into local optimum and difficult to *** evolutionary multitask algorithms with evolutionary optimization algorithms can be an effective method for solving these *** the implicit parallelism of tasks themselves and the knowledge transfer between tasks,more promising individual algorithms can be generated in the evolution process,which can jump out of the local *** to better combine the two has also been studied more and *** paper explores the existing evolutionary multitasking theory and improvement scheme in ***,it summarizes the application of EMTO in different ***,according to the existing research,the future research trends and potential exploration directions are revealed.

关键词： evolutionary multitasking evolutionary algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

Information Technology (IT) Governance Framework with Artificial Neural Network and Balance Scorecard to Improve the Success Rate of Software Projects 6

Information Technology (IT) Governance Framework with Artifi...

引用

6th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2022

作者： Ranesh, M. Maria Antony Samuel, S. Justin Natchadalingam, R. Jeyanthi, P. School of Computing Sathyabama Institute of Science and Technology Dept of Information Technology India Psn Engineering College Dept of Computer Science and Engineering Tirunelveli India

ISBN: (纸本)9781665482714

IT governance enables companies to plan and manage their IT investments in order to achieve their strategic objectives. Overall goal of this paper is to discuss about an approach to increase the success of the software projects through Artificial Intelligence. Standard governance standards are analyzed to understand the impact on software project success rates. Enterprise governance is a subset of IT governance that aids in the management of information technology resources. COBIT is a widely used methodology for developing effective enterprise IT governance. ISACA (Information Systems Audit and Control Association) stated implementation solution currently uses a sequentially ordered approach, which has raised issues. Several challenges have arisen as a result of top management's lack of commitment and misplaced solutions. Limitation on this investigation is the customized and confidential governance pattern used across various organization, hence there are very limited real time data for end-to-end analysis. Nonetheless, in combination with the agile project management paradigm, new project life-cycle solutions have evolved. Artificial Intelligence (AI) is an important element to address the increasing demand for machine learning systems. Artificial neural network (ANN) method is highly useful to arrive at best possible solution to improve the project success. This study found that ANN with Balance Score Card was exceptionally effective in providing the optimal solution to increase the project success rates. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Real Time Motion Capture for Physical Rehabilitation Using Kinect

Real Time Motion Capture for Physical Rehabilitation Using K...

引用

Smart Systems for applications in Electrical sciences (ICSSES), International Conference on

作者： Singireddy Srijay Reddy Nagumalla Yasash P. Rama V. Angayarkanni J. Kalaivani Faculty of Engineering and Technology Computing Technologies College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur TN India Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chennai Department of Computing Technologies Faculty of Engineering and Technology SRMIST Kattankulathur

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

This Project is a Kinect-based rehabilitation system designed to assist patients with movement disorders by performing targeted physical exercises at home. This system enables the evaluation of whether patients are correctly executing the prescribed rehabilitation exercises. By utilizing the skeletal tracking capabilities of the Microsoft Kinect sensor, each movement of the patient during the exercises is recognized and *** research introduces a real-time motion capture system designed for physical rehabilitation using Microsoft's Kinect sensor. The system addresses the growing demand for remote, data-driven healthcare solutions that assist in rehabilitation exercises by tracking and analysing skeletal movements. The Kinect's ability to track 25 joints in real time provides a unique opportunity to offer non-intrusive monitoring, real-time feedback, and data collection for therapists and patients. While Kinect offers several advantages, including cost-effectiveness and ease of use, our study identifies several limitations in precision, especially for complex movements and occlusion scenarios. This paper details the system's design, testing, and evaluation, highlighting areas where future improvements are necessary.

关键词： Accuracy Target tracking Tracking Smart systems Motors Real-time systems Motion capture Monitoring System analysis and design Testing

来源：评论

学校读者我要写书评

暂无评论

Cross-chain Sharing of Personal Health Records: Heterogeneous and Interoperable Blockchains

Cross-chain Sharing of Personal Health Records: Heterogeneou...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lv, Yongyang Li, Xiaohong Wang, Yingwenbo Chen, Kui Hou, Zhe Feng, Ruitao Tianjin University College of Intelligence and Computing Tianjin China Griffith University School of Information and Communication Technology Brisbane Australia Southern Cross University Faculty of Science and Engineering Gold Coast Australia

ISBN: (纸本)9798350386226

With the widespread adoption of medical informatics, a wealth of valuable personal health records (PHR) has been generated. Concurrently, blockchain technology has enhanced the security of medical institutions. However, these institutions often function as isolated data silos, limiting the potential value of PHRs. As the demand for data sharing between hospitals on different blockchains grows, addressing the challenge of cross-chain data sharing becomes crucial. When sharing PHRs across blockchains, the limited storage and computational capabilities of medical Internet of Things (IoT) devices complicate the storage of large volumes of PHRs and the handling of complex calculations. Additionally, varying blockchain cryptosystems and the risk of internal attacks further complicate the cross-chain sharing of PHRs. This paper proposes a scheme for sharing PHRs across heterogeneous and interoperable blockchains. Medical IoT devices can encrypt and store real-time PHRs in an InterPlanetary File System, requiring only simple operations for data sharing. An enhanced proxy re-encryption(PRE) algorithm addresses the differences in blockchain cryptosystems. Multi-dimensional analysis demonstrates that this scheme offers robust security and excellent performance. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Enhancing Asthma Diagnosis Through Machine Learning: A Stacking Ensemble Approach

Enhancing Asthma Diagnosis Through Machine Learning: A Stack...

引用

Women in computing (InCoWoCo), International Conference for

作者： Manas Goel Manya Gupta C. Jothikumar S. Shanmugam C. Ashokkumar Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798331518943

ISBN: (纸本)9798331518950

Asthma diagnosis remains a major clinical concern since it has diverse symptoms and is caused by various contributory causes. Machine learning was applied in this study to solve these complications in order to analyze such a broad dataset of 2,392 patients with the capture of important variables such as demographics, environmental exposures, allergies, medical history, and clinical indicators. Several machine learning models were implemented, including those such as Random Forest, XGBoost, Decision Tree, LGBM, CatBoost, and AdaBoost. Next, the stacking ensemble strategy was taken to further optimize predictive performance, using the Random Forest model meta-classifier. Our approach proves that stable ensemble learning takes place with an amazing 97% accuracy rate when it comes to difficult clinical data. Recall, precision, and F1-score represent some of the most important measures for model performance evaluation. These results might point out the machine learning potential in improving asthma diagnosis accuracy and might be helpful for a doctor in coping with this complicated disease.

关键词： Performance evaluation Accuracy Stacking Medical services Predictive models Ensemble learning History Random forests Medical diagnostic imaging Asthma

来源：评论

学校读者我要写书评

暂无评论

Advancements in Operating System Design for Cloud computing Environments 4

Advancements in Operating System Design for Cloud Computing ...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Pareek, Shashank Fezaa, Laith H. Al-Jawahry, Hassan M. Singh Chohan, Jasgurpreet Kumar, Jatinder Dey, Protyay Chandigarh University Department of Computer Science and Engineering Mohali India Al-Zahrawi University College Department of Optical Techniques Karbala Iraq College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq School of Mechanical Engineering Rayat Bahra University Mohali India Chandigarh Engineering College Chandigarh Group of Colleges Department of Computer Science Engineering Punjab Mohali India Nims School of Computing Science and Artificial Intelligence Nims University Rajasthan Jaipur India

ISBN: (纸本)9798350387490

This paper provides an analysis of trends in oper-ating system design specific to cloud computing and how these trends address scalability, resource management, security, and fault tolerance. The study also emphasises certain emerging approaches of managing different resources including dynamic provisioning and forecasting models for enhancing the performance of cloud systems. It also covers new developments in security such as new encryption techniques and new way of monitoring for security breach. The study also explores issues to do with integration between different cloud systems as well as cloud architectures and their possible solutions. Reliability and fault tolerance are still vital for further investigation, the works on reliable recovery techniques and adaptive fault detection are still being carried out. Several issues such as scalability, security, or reliability are outlined by the article as research issues as well as the further research directions to solution of these issues. The areas for future research should be found in optimizing resource usage utilizing machine learning approaches, creating more uniform and coherent interoperability models, and in designing stronger security layers against new types of threats. By doing so, the field of cloud computing can move toward solving these challenges and finding better ways of provision and protection of cloud-based systems. This general survey makes the point about the centrality of the operating system design for the advancement of the cloud computing in the future as well has pointed the need for further research upon understanding the dynamics of the cloud infrastructures. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Classification Model on Detecting Cache-Based Side-Channel Attacks 20

A Two-Stage Classification Model on Detecting Cache-Based Si...

引用

20th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2023

作者： Xinchen, Jiang Ailing, Deng Yuxi, Peng Yanping, Xiang Jianwei, Xiang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China Hunan University of Technology Department of Computer and Communication Zhuzhou China

ISBN: (纸本)9798350318982

Cache-based side-channel attacks in cloud environments have attracted widespread attention. Many studies have successfully proved that sensitive data can be stolen from co-resident virtual machines by launching these attacks. Relatively various detection and defense methods are also proposed. To address such problems, this paper proposes a novel two-stage classification model that combines random forest and XGBoost, which can classify the samples collected from one process into attack samples, noise samples and normal samples. In the experiments, the accuracy of attack samples and normal samples produced results of 98.89% and 99.83%, respectively, demonstrating that our model is not inferior compared to the current methods in terms of classification performance and outperforms them in terms of implementation difficulty and classification speed. © 2023 IEEE.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

Real-Time Stock Price Prediction and Visualization Using LSTM and Matplotlib

Real-Time Stock Price Prediction and Visualization Using LST...

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： James J. Koduppanapolackal Ahamed Akash Suresh U.A. Adwaith P. Gouthaman Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology India Department of Networking and Communications School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

In this paper, we present a big data-based stock price prediction method to analyze market trends better. Investors and market analysts need to predict correctly as the stock market is getting more complex, and volatile. To solve this problem, we use historical stock data that has been prepared and processed with Apache Spark in conjunction with real-time signals collected from the Alpha Vantage API. There are two main types of information available from stock data: financial and technical. In this proposed work, we have tried to create a predictive time series model using Long Short-Term Memory (LSTM) neural network. The model is then tested based on some key metrics i.e., Mean Squared Error (MSE) and Root Mean Squared Error (RMSE), to illustrate how well the model performs in predicting upcoming stock prices. Another key aspect the paper focuses on is how big data can be integrated with machine learning to analyze massive datasets such that runtime effectively decreases. In other words, this is a wholesale service for stock market trend analysis and institutional-level investment decisions. The results of this experiment suggest that the prediction accuracy of stock prices based on machine learning models, specifically LSTM can greatly improve market analysis.

关键词： Accuracy Time series analysis Pipelines Machine learning Predictive models Market research Real-time systems Stock markets Long short term memory Investment

来源：评论

学校读者我要写书评

暂无评论

Implementation and Analysis of Image Compression Using Ramanujan's Sum 13

Implementation and Analysis of Image Compression Using Raman...

引用

13th International Conference on computing Communication and Networking Technologies, ICCCNT 2022

作者： Das, Kunal Radha, D. Dept. of Computer Science & Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

In today's world, there are many types of data. The text files, the images, the audio, and the videos are all data and have been integrated into everyone's life. But the storage requirement of data is huge as all data is stored whether they are useful data or useless data. Data compression is the process of compressing the data such as an image, text, or audio, in such a way that the file is easier to store, takes less space, can be transferred over the network with less bandwidth, etc. Image Compression, especially, has evolved in many aspects. A new mathematical concept has started gaining traction. The paper shares an implementation of Ramanujan's Sum-based transformation on bitmap images and tries to compress it with available algorithms. The image is transformed with Ramanujan's Sum Matrix, then quantized, and then compressed. Then the results are compared with the existing algorithms available, in terms of storage space, compression percentage, and Peak Signal to Noise Ratio PSNR. The findings are pretty much fascinating, that how a simple change in the mathematical equation can make a difference in the results of compression. © 2022 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Detecting and Extracting Information of Medicines from a Medical Prescription Using Deep Learning and Computer Vision

Detecting and Extracting Information of Medicines from a Med...

引用

2022 IEEE International Conference on Knowledge engineering and Communication Systems, ICKES 2022

作者： Palani, Nivetha Sampath, Nalini Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita Viswa Vidyapeetham India

ISBN: (纸本)9781665456371

Usually, reading any person's handwriting becomes slightly a challenging task for one. Similarly, when it comes to a doctor's handwriting in their medical prescription it becomes the most challenging task to the patients, general people and few medical related workers encountering this as an issue, in certain cases, it heads towards wrong concerns or results due to incorrect decoding of any medical prescription written by a doctor. Out of all things the main reason one cannot interpret a doctor's handwriting in their medical prescription isthat doctors use the Greek and other foreign medical terms andabbreviations that any person won't recognize or understand. This paper establishes how Long Short-Term Memory (LSTM) based Convolutional Neural Network (CNN) is used to develop a model that can distinguish doctor's handwriting in their medical prescriptions. Utilizing the Deep Convolution Recurrent Neural Network (RNN) to train this supervising model, input pictures are segmented using Otsu segmentation and handled to identify the letters and words and categorize them into the 56 various defined characters © 2022 IEEE.

关键词： Long short-term memory

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：