检索结果-内蒙古大学图书馆

A novel myocarditis detection combining deep reinforcement learning and an improved differential evolution algorithm

引用

CAAI Transactions on Intelligence technology 2024年第6期9卷 1347-1360页

作者： Jing Yang Touseef Sadiq Jiale Xiong Muhammad Awais Uzair Aslam Bhatti Roohallah Alizadehsani Juan Manuel Gorriz Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversiti MalayaKuala LumpurMalaysia Centre for Artificial Intelligence Research(CAIR) Department of Information and Communication TechnologyUniversity of AgderGrimstadNorway Department of Creative Technologies Air UniversityIslamabadPakistan School of Information and Communication Engineering Hainan UniversityHaikouHainanChina Institute for Intelligent Systems Research and Innovation(IISRI) Deakin UniversityWaurn PondsVictoriaAustralia Data Science and Computational Intelligence Institute University of GranadaGranadaSpain

Myocarditis is a serious cardiovascular ailment that can lead to severe consequences if not promptly *** is triggered by viral infections and presents symptoms such as chest pain and heart *** detection is crucial for successful treatment,and cardiac magnetic resonance imaging(CMR)is a valuable tool for identifying this ***,the detection of myocarditis using CMR images can be challenging due to low contrast,variable noise,and the presence of multiple high CMR slices per *** overcome these challenges,the approach proposed incorporates advanced techniques such as convolutional neural networks(CNNs),an improved differential evolution(DE)algorithm for pre-training,and a reinforcement learning(RL)-based model for *** this method presented a significant challenge due to the imbalanced classification of the Z-Alizadeh Sani myocarditis dataset from Omid Hospital in *** address this,the training process is framed as a sequential decision-making process,where the agent receives higher rewards/penalties for correctly/incorrectly classifying the minority/majority ***,the authors suggest an enhanced DE algorithm to initiate the backpropagation(BP)process,overcoming the initialisation sensitivity issue of gradient-based methods like back-propagation during the training *** effectiveness of the proposed model in diagnosing myocarditis is demonstrated through experimental results based on standard performance ***,this method shows promise in expediting the triage of CMR images for automatic screening,facilitating early detection and successful treatment of myocarditis.

关键词： classification differential evolution myocarditis reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

AI Based Automated Food Recognition Using CNN for Fitness Mobile Application

AI Based Automated Food Recognition Using CNN for Fitness Mo...

引用

2023 IEEE Symposium on Industrial Electronics and Applications, ISIEA 2023

作者： Mahmood, Atif Mahmood, Rafay Azzuhri, Saaidal Razalli Azizul Hasan, Zati Hakim Mat Kiah, Miss Laiha University of Central Punjab Faculty of Information Technology and Computer Science Lahore Pakistan Universiti Malaya Faculty of Computer Science and Information Technology Department of Computer System & Technology Kuala Lumpur50603 Malaysia Universiti Malaya Faculty of Computer Science and Information Technology Department of Artificial Intelligence Kuala Lumpur50603 Malaysia

ISBN: (纸本)9798350347494

Eating a healthy, balanced diet with regular exercise is important for maintaining physical and mental health. Healthy diet and exercise promise a healthier lifestyle. Other than that, people competing in different sports need a customized, strict workout and diet plan. Trainees offer their best at gymnasium by following a strict workout plan recommended by their coaches. However, there is no way till now to determine if the trainees are taking the prescribed diet strictly. Therefore, an optimized application with the feature of real time scanning of the prescribed meal can be helpful to overcome this problem. For this purpose, we have used Convolutional Neural Networks (CNN) along with Image Processing. Using ResNet50 with activation functions of ReLU and Softmax, our trained CNN model and the proposed architecture achieved an accuracy of 82.70 percent. We used CNN pre-trained models such as InceptionV3 with LeakyReLU and Softmax, InceptionV3 with ReLU and Softmax, VGG16 with ReLU and Softmax, VGG16 with ReLU and Softmax, and ResNet50 with ReLU and Softmax, so the achieved accuracy, respectively, is 78%, 71%, 58%, 56%, and 82.7%. Therefore, the proposed model has the potential to achieve high performance on real time food scanning which can be used in online fitness platforms(mobile applications and websites) and fitness gadgets. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource-Aware Federated Framework for Secure and Sustainable Learning in Data Sensitive Applications 9

Dynamic Resource-Aware Federated Framework for Secure and Su...

引用

9th IEEE International Conference for Convergence in technology, I2CT 2024

作者： Narula, Manu Meena, Jasraj Vishwakarma, Dinesh Kumar Delhi Technological University Department of Information Technology Delhi India Jawaharlal Nehru University School of Computer And System Sciences Delhi India

ISBN: (纸本)9798350394474

Federated Learning (FL) quickly gained popularity as a secure distributed learning technology based on insights sharing. The client-level privacy provided by FL has enabled its extensive integration in fields dealing with susceptible data such as E-commerce, the Internet of Medical Things, etc. However, the transmitted insights may still be subjected to eavesdropping since the security of the transmission medium cannot be guaranteed. Using complex techniques, this can lead to the inference of the client data. In many cases, quantization is applied over transmitted payload to hinder such attempts but results in drop of accuracy in the global models. Moreover, the capabilities of client nodes are not considered in most implementations which may lead to under or over-utilization of client resources and cause client dropouts due to exhaustion. When combined, the quantization and client dropouts cause a significant performance loss and make the network less stable. In this paper, we propose a Dynamic Resource-Aware Federated Framework for Secure and Sustainable Learning, which layers the quantization process with an active workload management technique based on the capabilities of the client nodes. The framework minimizes the dropout rates significantly while recovering the accuracy lost in quantization to some extent. Through experiments compared against standard FL and Quantized FL over multiple datasets, the DRAFFSS shows gains in security over the former and in accuracy over the latter while keeping client dropouts negligible. © 2024 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Review of National Cybersecurity Policies: A Case Study on Asian Countries 1

Review of National Cybersecurity Policies: A Case Study on A...

引用

1st IEEE Karachi Section Humanitarian technology Conference, Khi-HTC 2024

作者： Noor, Hera Seelro, Dodo Khan Ali, Syed Abbas NED University of Engineering & Technology Department of Computer Information System Engineering Karachi Pakistan Thar Institute of Engineering Science & Technology NED University of Engineering & Technology Karachi Pakistan

ISBN: (纸本)9798350373042

Accelerating the economic advantages of ICT is one of the finest methods for any nation to boost its economy. Due to the unique topography, governing laws, and cultural traditions of each nation, these colossal challenges must be confronted in each country. This comparative analysis aims to examine these aspects in further detail. To achieve the objectives of this study, research was conducted by collecting and analysing data from publicly accessible sources. This research compares Pakistan and other Asian countries' cybersecurity legislation, regulations, CERTs (national computer emergency response teams), CIIPs (computer intrusion prevention programs), and cyber security training and awareness. Among forty-eight Asian countries, the study focus on comparative analysis of major neighboring (developed or developing) countries of Pakistan such as Japan, China, Turkey, Iraq, Saudi Arabia, UAE, Nepal, Iran, Malaysia, Jordan, India, and Bangladesh. Cyber security has not been a major concern in Pakistan for a very long time, perhaps due to the way the government operates and how slowly it adapts to new technology. Many Asian countries have only ever released one version of their national cyber security plan, whilst Pakistan has never released anything;some other Asian countries are also added in this group. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Multi Target Drug Design Method Based on Target Protein Sequence and Feature Similarity

A Multi Target Drug Design Method Based on Target Protein Se...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Haoran Lin, Xiaoli Hu, Jing Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan China

ISBN: (纸本)9798350386226

This paper describes a multi target drug design method based on features of the target proteins. The multi target drug which inhibit multiple proteins have prospective applications, but design is difficult. In this study, the target protein sequences are embedded to obtain target features. The features of each target are independently encoded as target latent vectors, and the features of multiple targets are jointly encoded as target similarity latent vectors. Based on the features of targets and the similarity features among the targets, multi target drugs are efficiently designed. In the experiments, the designed multi target drugs can be docked with target proteins with a proprietary molecular structure according to the requirements of different target pocket structures. The excellent fitness among the molecular structure of multi target drugs and the protein structure of multiple targets confirms the performance of the proposed method. In the molecular docking part of the experi¬ments, the binding affinity of designed multi target drugs is far better than that in the previous studies, which administrates the better performance of this work. © 2024 IEEE.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

On a new fractional integral operator convoluted with a fractional k-symbol Raina function: stability

On a new fractional integral operator convoluted with a frac...

引用

2023 International Conference on Fractional Differentiation and Its Applications, ICFDA 2023

作者： Obaiys, Suzan J. Ibrahim, Rabha W. University of Malaya Faculty of Computer Science and Information Technology Department of Computer System & Technology KL Malaysia Lebanese American University Department of Computer Science and Mathematics Beirut Lebanon

ISBN: (纸本)9798350321685

The fractional k-symbol Raina function (k-FRF) is convoluted with a class of analytic functions in a complex domain to build a new fractional integral operator (FIO) in this attempt. We research the polynomials produced by the suggested FIO in terms of their geometry and stability. On the basis of the Hadamard product's characteristics, sufficient criteria are shown (convolution product). © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Application of Hospital Management information system (SIMRS) in RSUD Dr. Kanujoso Djatiwibowo Using the HOT-Fit Method 3

Evaluation of the Application of Hospital Management Informa...

引用

3rd Borneo International Conference on Applied Mathematics and Engineering 2020, BICAME 2020

作者： Setiorini, Adani Natasia, Sri R Wiranti, Yuyun Tri Ramadhan, Dean A Department of Information System Majoring in Mathematics and Information Technology Kalimantan Institute of Technology Balikpapan Indonesia Department of Computer Science Faculty of Mathematics and Natural Sciences IPB University Bogor Indonesia

Hospital Management information system (SIMRS) is a system that can process and integrate the entire hospital service process flow in the form of a network of coordination, reporting and administrative procedures to obtain accurate data and information. At the RSUD Dr. Kanujoso Djatiwibowo (RSKD) of Balikpapan City, the application of SIMRS experienced problems such as the high number of troubleshooting cases and the redundancy of patient medical record numbers. This case is consideredto inhibit the performance of hospital services related to efficiency. Based on this problem, the evaluation of SIMRS in the RSKD was carried out by using the constructed Human, Organization, technology-Fit (HOT-Fit) model. This model involves eight variables which consists of system Quality, information Quality, and Service Quality, system Use, User Satisfaction, Structure, and Environment, and Net Benefits. The results indicate that the proposed model either directly or indirectly affectsthe benefits obtained from implementing the SIMRS. Further implications of the results toward improvement of the system are provided. © Published under licence by IOP Publishing Ltd.

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Deep Learning Models for Stock Price Prediction 5

A Comparative Study on Deep Learning Models for Stock Price ...

引用

5th Asia-Pacific Conference on Image Processing, Electronics and computers, IPEC 2024

作者： He, Zhexin Zhang, Huan Por, Lip Yee Chongqing College of Architecture and Technology Chongqing401331 China Chongqing Academy of Science and Technology Chongqing401123 China Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia

ISBN: (纸本)9781643685243

With the advancement of deep learning technology, researchers have begun employing deep neural network models such as LSTM, MLP, CNN, and GRU to tackle nonlinear prediction problems in stock markets. This study harnesses these deep learning models, including LSTM, MLP, CNN, and GRU, to investigate the nonlinear forecasting of stock market price indices. The experiment selects globally representative stock indices and, through analyzing short-term, mid-term, and long-term data, discovers that the GRU model demonstrates exceptional performance in both prediction accuracy and generalization capabilities. To further enhance precision, the research constructs a filtering ensemble decision-making system based on multiple GRU models. This strategy reduces the error by at least 0.3% in medium to long-term predictions, significantly outperforming a single standalone GRU model. Consequently, the GRU-filtered ensemble decision model has been empirically proven as an effective tool for predicting stock indices, not only broadening the methods available for stock market prediction but also deepening the understanding and application of the generalization abilities of deep learning models within financial markets. © 2024 The Authors.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Congestion Control Mechanisms and Techniques in computer Network: A Review

Congestion Control Mechanisms and Techniques in Computer Net...

引用

2022 International Conference on Data Science and Intelligent Computing, ICDSIC 2022

作者： Altameemi, Ahmed Malik Nassar, Khulood A. College of Computer Science and Information Technology University of Basrah Department of Computer Information System Basrah Iraq

ISBN: (纸本)9798350334883

One of the most important and most pioneering topics in the field of networks is congestion and how to control it or avoid its occurrence because this topic has a huge impact on the network and the quality of service (QoS). Congestion reduces the efficiency of the network and stops the service in many cases. Therefore, there is an urgent need to develop techniques and mechanisms to avoid congestion or reduce its impact to the extent possible to maintain the permanence of data flow in the network. Congestion is avoided at two levels, node and link, by using different techniques, including closed loop or open loop. This paper reviews an explanation of congestion, how it occurs, and its impact on the network, and then shows the mechanisms through which congestion eliminated can be bed or avoided before it occurs. It also reviews a set of algorithms previously used by researchers in various types of networks and compares the performance between them. © 2022 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Intelligent Risk-Identification Algorithm with Vision and 3D LiDAR Patterns at Damaged Buildings

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 2315-2331页

作者： Dahyeon Kim Jiyoung Min Yongwoo Song Chulsu Kim Junho Ahn Computer Information Technology Korea National University of TransportationChungju27469Korea Department of Railway Vehicle System Engineering Korea National University of TransportationUiwang16106Korea

Existingﬁreﬁghting robots are focused on simple storage orﬁre sup-pression outside buildings rather than detection or *** a large number of robots using expensive equipment is *** study aims to increase the efﬁciency of search and rescue operations and the safety ofﬁreﬁgh-ters by detecting and identifying the disaster site by recognizing collapsed areas,obstacles,and rescuers on-site.A fusion algorithm combining a camera and three-dimension light detection and ranging(3D LiDAR)is proposed to detect and loca-lize the interiors of disaster *** algorithm detects obstacles by analyzingﬂoor segmentation and edge patterns using a mask regional convolutional neural network(mask R-CNN)features model based on the visual data collected from a parallelly connected camera and 3D *** as objects are detected using you only look once version 4(YOLOv4)in the image data to localize persons requiring *** point cloud data based on 3D LiDAR cluster the objects using the density-based spatial clustering of applications with noise(DBSCAN)clustering algorithm and estimate the distance to the actual object using the center point of the clustering *** proposed artiﬁcial intelligence(AI)algorithm was veriﬁed based on individual sensors using a sensor-mounted robot in an actual building to detectﬂoor surfaces,atypical obstacles,and persons requiring ***,the fused AI algorithm was comparatively veriﬁed.

关键词： Three-dimension light detection and ranging vision risk identiﬁcation damaged building robot

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：