检索结果-内蒙古大学图书馆

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Wenzhe Li Xinhang Zhang Wenxuan Jia Zhuohan Chen Guojun Yuan Zhan Wang Peiheng Zhang High Performance Computing Center Institute of Computing Technology CAS Beijing China Department of Intelligent Science and Technology Hangzhou Institute of Advanced Study UCAS Hangzhou China Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou China

We enhance our prior all-optical reconfigurable network to accelerate the data loading with minimized commu-nication distance between compute and storage nodes. A novel corresponding data loading scheme is proposed to... 详细信息

ISBN: (数字)9798350379266

ISBN: (纸本)9798350379273

关键词： Training Deep learning Simulation Loading Distributed databases Encyclopedias Optical fiber networks Internet Online services Photonics

来源：评论

学校读者我要写书评

暂无评论

Analysis of Cardiac Disease based on AI Prediction Techniques using data analytics approach

Analysis of Cardiac Disease based on AI Prediction Technique...

引用

Soft computing for Security Applications (ICSCSA), International Conference on

作者： R. Sivanathbabu S. Kamalakkannan Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

Patients who have an increased likelihood of coronary heart disease can reduce their consequences by changing their lifestyle, with the support of early diagnosis. Healthcare expenses are rising above, both company budgets and the average cost of medical treatment nationally, due to asymptomatic conditions like cardiovascular disorders. Early detection and treatment of these illnesses are essential. Utilizing the data that is accessible in healthcare systems has been significantly impacted by recent technological advancements. As part of this, patients' Heart Disease (HD) may be predicted using the massive amount of data. However, due to concerns with prediction and diagnosis performance and accuracy, projecting HD has emerged as one of the main obstacles facing the healthcare sector. The main challenges were to apply homogeneous data mining techniques to define the most significant causes of heart disease and to accurately predict the overall risk. Using Data Analytics (DA) to speed up the prediction process is one way to make use of massive amounts of health care data. Selecting the optimal analytical methods, however, is the most crucial step as it will impact the final result of the diagnostic and forecasting. In order to assess the effectiveness of the methods for HD forecasting, this study intends to implement DA approach in collecting of databases. In this research work, Best First Search (BFS) has been used to identify the most important attributes for HD prediction. This study employs a range of ML approaches based on AI to predict HD. The Random Forest (RF) method, which uses specific characteristics, has the highest accuracy rate (98.63%) in this experiment. The BFS extracted 14 relevant features and then compared them using AI approaches. Based on the analysis, feature selection has enhanced the DA technique by improving the efficiency and precision of the classification model's prediction.

关键词： Heart Radio frequency Analytical models Accuracy Data analysis Medical services Predictive models Feature extraction Forecasting Diseases

来源：评论

学校读者我要写书评

暂无评论

Hybrid feature selection technique for prediction of cardiovascular diseases

引用

Materials Today: Proceedings 2023年 81卷 336-340页

作者： Pavithra V Jayalakshmi V School of Computing Sciences Vels Institute of Science Technology and Advanced Studies (VISTAS) India

Diagnosing a disease consumes a part of time, needs high technical methods but nowadays the smart technologies have been grown rapidly in the field of healthcare industries and also it improves the routine life of the patients, reduces the amount of work, treatment cost in the health care organization. Diseases prediction is one of the major challenges faced by society nowadays. The recent survey also stated that the death rate is remarkably high in CAD because most of the people are affected by cardiovascular diseases. Prediction and diagnosis of cardiovascular diseases is very essential nowadays to reduce the death rate and diagnosing it preliminary stage itself. In earlier studies, they worked with machine learning techniques to predict the diseases, but they are not given proper attention to identifying the feature with the help of proper feature selection methods. This paper proposed a new-found feature selection technique HRFLC (RANDOM FOREST + ADABOOST + PEARSON COEFFICIENT). This method helps to predict the diseases in a very efficient manner, and it improves the accuracy level in prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards practical data alignment in production federated learning

引用

Frontiers of Computer Science 2025年第1期19卷 167-169页

作者： Yexuan SHI Wei YU Yuanyuan ZHANG Chunbo XUE Yuxiang ZENG Zimu ZHOU Manxue GUO Lun XIN Wenjing NIE State Key Laboratory of Complex&Critical Software Environment and Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang UniversityBeijing 100191China Zhongguancun Pan Connected Mobile Communication Technology Innovation and Application Research Institute Beijing 100088China China Mobile Research Institute Beijing 100053China School of Data Science City University of Hong KongHong Kong 999077China

1 Introduction Federated learning has emerged as a promising par-adigm for collaborative model training that facilitates cooperation among multiple parties while ensuring data privacy[1].Successful alignment of data across parties is crucial for effective federated learning[2].This alignment involves harmonizing heterogeneous data from different parties to identify shared data for joint model *** set intersection(PSI)is a technique that allows the alignment of common entities between parties without revealing additional ***,efficiently performing data alignment with PSI in federated learning[3],especially when dealing with highly unbalanced data,remains challenging due to the low efficiency.

关键词： alignment dealing parties

来源：评论

学校读者我要写书评

暂无评论

Self-attention Convolutional Neural Network-based SLA Decomposition for Network Slicing 3

Self-attention Convolutional Neural Network-based SLA Decomp...

引用

3rd International Conference on Neural Networks, Information and Communication Engineering, NNICE 2023

作者： Ji, Haidong Wang, Yuanyuan Tian, Lin Sun, Qian Zhang, Zongshuai Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Beijing Key Laboratory of Mobile Computing and Pervasive Device China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350335972

In 5G networks, a network slice is an independent end-to-end logical network running on a shared physical infrastructure, capable of guaranteeing a negotiated service level agreement (SLA) to deliver customized service. An end-to-end network slice includes three logical networks in the subnets: an access network (AN) sub-slice, a transport network (TN) sub-slice and a core network (CN) sub-slice. The network slice SLA needs to be decomposed into the corresponding sub-slice SLAs. In this paper, the SLA decomposition for network slicing is modelled as a constrained optimization problem and solved in two steps: building the sub-slice SLA acceptance probability models and solving the constrained optimization problem. The sub-slice SLA acceptance probability models are built by a self-attention convolutional neural network, and the constrained optimization problem is solved by a differential evolution algorithm based on the optimal acceptance probability of the SLA decomposition for network slicing. The simulation results show that the proposed self-attention convolutional neural network-based sub-slice SLA acceptance probability models (SACNN-SSAPMs) fit better with the ground truths, and the errors between the optimal acceptance probabilities of the SLA decomposition for network slicing based on the SACNN-SSAPMs and those based on the ground truths are smaller. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Emotion-Aware Talking Face Generation Based on 3DMM

Emotion-Aware Talking Face Generation Based on 3DMM

引用

Neural Networks, Information and Communication Engineering (NNICE), International Conference on

作者： Xinyu Chen Sheng Tang Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Chinese Academy of Sciences Institute of Computing Technology Beijing China

Current methods for generating videos of talking face based on deep learning mainly focus on the correlation between lip movements and audio content. Although these methods have high generation quality and good audio-visual synchronization, they ignore facial expressions in talking face videos. To solve this problem, Audio to Expression Network (A2ENet), an emotional talking face video generation framework based on 3DMM, is proposed in this paper to generate talking face videos with facial expressions in an audio-driven way. Firstly, A2ENet uses two Transformer based encoders to extract audio features, and uses a cross-reconstruction emotion disentanglement method to decompose audio into potential space of content information and potential space of emotion information, and then uses a Transformer Decoder to integrate these two feature spaces. After that, the Proposed method predict the 3D expression coefficient that matches the emotion of the audio, and finally uses the renderer to generate the talking face video. By using the eye control parameters, A2ENet can realize the eye movements control of talking face. A2ENet associating the initial 3D expression coefficients with specific individuals to retain the identity information of the reference face. Experimental results show that our method can generate talking face videos with appropriate facial expressions, and achieve more accurate lip movements and better video quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CR-DIS: An Efficient Heuristic Algorithm for Minimum Weighted Vertex Cover Problem

CR-DIS: An Efficient Heuristic Algorithm for Minimum Weighte...

引用

New Trends in Computational Intelligence (NTCI), International Conference on

作者： Chenkai Hao Enqiang Zhu Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China Institute of Computing Science and Technology Guangzhou University Guangzhou China

ISBN: (数字)9798331517021

ISBN: (纸本)9798331517038

The minimum weighted vertex cover (MWVC) problem is a well-known NP-hard combinatorial optimization problem. In this problem, each vertex of the graph is assigned a positive weight, and the objective is to identify a set of vertices such that every edge is covered by at least one vertex from the set, while minimizing the sum of all vertices' weights in the set. It has greater generality and broader applications than the minimum vertex cover (MVC) problem. Due to its NP-hard nature, efficiently solving the MWVC problem is a significant challenge. This paper introduces a highly efficient heuristic algorithm named CR-DIS for MWVC, which consists of two components: a construction with reductions and a dynamic improvement search framework. We compare CR-DIS with three state-of-the-art algorithms on a large number of graphs. Experimental results indicate that CR-DIS performs at a superior level, especially on large sparse graphs, yielding more best solutions and, in many instances, achieving smaller solutions with similar running times.

关键词： Social networking (online) Heuristic algorithms Memory Search problems Market research Object recognition Optimization Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Boosting the generation rate of squeezed single-photon states by generalized photon subtraction

引用

Physical Review A 2024年第3期110卷 033717页

作者： Hiroko Tomoda Akihiro Machinaga Kan Takase Jun Harada Takahiro Kashiwazaki Takeshi Umeki Shigehito Miki Fumihiro China Masahiro Yabuno Hirotaka Terai Daichi Okuno Shuntaro Takeda Department of Applied Physics School of Engineering Optical Quantum Computing Research Team NTT Device Technology Labs Advanced ICT Research Institute

In optical quantum information processing with continuous variables, optical non-Gaussian quantum states are essential for universal and fault-tolerant quantum computation. Experimentally, their most typical generation method is photon subtraction (PS), where single-photon detection by an on/off detector probabilistically heralds the generation of squeezed single-photon states. In PS, however, trying to avoid unwanted multiphoton detection inevitably limits the generation rate, hindering the application of squeezed single-photon states. Here, we theoretically show that generalized photon subtraction (GPS), a simple extension of PS, can improve the generation rate while maintaining the quality of the generated states. Furthermore, we experimentally demonstrate the generation rate improvement for 2-dB- and 4-dB-squeezed single-photon states compared to PS, by more than one order of magnitude, particularly for the case of 2 dB. Our results will accelerate the application of squeezed single-photon states to more advanced quantum information protocols.

关键词： Quantum information processing Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Deep Generative Decision Neural Network Approach for Effective Early Prediction of Meninges

Deep Generative Decision Neural Network Approach for Effecti...

引用

Sustainable computing and Smart Systems (ICSCSS), International Conference on

作者： A. Shabana P. Kavitha S. Kamalakkannan Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

Meningitis is a contagious disease that leads to neurocognitive impairment. It is caused by inflammation in the protective membranes surrounding the brain and spinal cord and can be caused by various pathogens, such as viruses and bacteria. It is necessary to make predictions and classify meninges diseases. The conventional techniques for forecasting meninges are time-consuming and prone to errors, resulting in low accuracy rates with high false classifications. To tackle these problems, this study presents a Deep Learning (DL) method to aid in predicting meningitis. The novel introduces a Deep Generative Decision Neural Network (DGDN2) algorithm for predicting meninges. The Box-Plot Standardization (BPS) algorithm eliminates null and missing values to prepare the dataset. Next, the Mutual Gain Genetic Algorithm (MG2A) is utilized to select essential features of meninges diseases. Finally, the DGDN2 algorithm is used to predict meninges diseases efficiently. According to experimental results, the proposed model achieves higher accuracy, precision, recall, and F-measure than previous methods.

关键词： Pathogens Accuracy Spinal cord Computational modeling Standardization Medical services Predictive models

来源：评论

学校读者我要写书评

暂无评论

Estimation of Trust in Clustered Mobile Ad hoc Networks

Estimation of Trust in Clustered Mobile Ad hoc Networks

引用

2022 International Conference on Electronics and Renewable Systems, ICEARS 2022

作者： Sarumathi, R. Jayalakshmi, V. Vistas Chennai India Technology and Advanced Studies Vistas School of Computing Sciences Vels Institute of Science Chennai India

ISBN: (纸本)9781665484251

Mobile devices form a self-organizing network constructs a Mobile ad-hoc network (MANET). A network without infrastructure is often described as spontaneous, real-time, and dynamic. MANETs have difficulty establishing trust among nodes because of the temporary cooperation and lack of knowledge in advance. An Inter-cluster recommendation trust concept is introduced based on the trust of each cluster in this paper. Also, a cluster consists of a group of mobile devices present in the network containing a special node, which establishes a trust relationship between clusters and based on the results of previous transactions, clusters are created dynamically. We have done some basic experiments on the models, and The results show that the model can be applied successfully in mobile ad hoc networks since it is dynamic and efficient enough. Researchers can consider this model, which helps them resolve any ambiguity issues with nodes incoming and leaving in spontaneous Ad-hoc environments. © 2022 IEEE.

关键词： Mobile 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：