检索结果-内蒙古大学图书馆

20th International Symposium on distributed Computing and Artificial Intelligence, DCAI 2023

ISBN: (纸本)9783031383175

The proceedings contain 36 papers. The special focus in this conference is on distributed Computing and Artificial Intelligence. The topics include: Using Data Analytic for Social Media Posts to Optimise Recyclable Solid Waste Management Exemplary at the City of Valencia;Detection of Human Falls via Computer Vision for Elderly Care – An I3D/RNN Approach;generic Architecture for Multisource Physiological Signal Acquisition, processing and Classification Based on Microservices;a Novel System Architecture for Anomaly Detection for Loan Defaults;enabling distributed Inference of Large neural networks on Resource Constrained Edge Devices using Ad Hoc networks;Using neural network to Optimize Bin-Picking in the SME Manufacturing Digital Transformation;neural Architecture Search: Practical Key Considerations;leveraging Smart City Services for Citizen Benefits Through a Unified Management Platform;step-Wise Model Aggregation for Securing Federated Learning;estimation of Occlusion Region Using Image Completion by network Model Consisting of Transformer and U-Net;Federated Genetic Programming: A Study About the Effects of Non-IID and Federation Size;cognitive Reinforcement for Enhanced Post Construction Aiming Fact-Check Spread;chatbot Architecture for a Footwear E-Commerce Scenario;a Geolocation Approach for Tweets Not Explicitly Georeferenced Based on Machine Learning;classification of Scenes Using Specially Designed Convolutional neural networks for Detecting Robotic Environments;AMIR: A Multi-agent Approach for Influence Detection in Social networks;extracting Knowledge from Testaments - An Ontology Learning Approach;AI-Based Platform for Smart Cities Urban Infrastructure Monitorization;bitcoin Price Prediction Using Machine Learning and Technical Indicators;RKTUP Framework: Enhancing Recommender Systems with Compositional Relations in Knowledge Graphs;operation of a Genetic Algorithm Using an Adjustment Function;a Classification Method for "Kawaii" Images Using Four Feat

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Dreamer: Extending Single-View Dreamer with Few Shot of Complementary Views 33rd

Dual Dreamer: Extending Single-View Dreamer with Few Shot of...

引用

33rd International Conference on Artificial neural networks and Machine Learning (ICANN)

作者： Zhang, Ziteng Qiao, Peng Yong, Dou Liu, Sidun Li, Wenyu Cao, Li Chen, Luo Natl Univ Def Technol Natl Key Lab Parallel & Distributed Comp Sch Comp Changsha Peoples R China Minist Nat Resources Key Lab Nat Resources Monitoring & Supervis South Changsha Peoples R China

ISBN: (纸本)9783031723377;9783031723384

Recently, diffusion models demonstrate the potential of generating consistent novel views from a single view. Due to the limited object information contained in a single input view, controlling generation of out-of-sight views becomes challenging. In this work, we propose Dual Dreamer, a method of generating novel views with complementary views. Specifically, we focus on fine-tuning the single-view input diffusion model to extract complementary information from additional known views and combine it with the original information for novel view synthesis (NVS). To achieve this, Dual Dreamer introduces a 3D attention mechanism to enable the model to learn common features of the complementary views and enhance information exchange. By utilizing view difference between predefined and target views as weights, predefined views are fused as priors to enhance the consistency of multi-view synthesis. Finally, in order to avoid consuming resources on large-scale datasets, the proposed Dual Dreamer model is trained in a similar way like ControlNet, enabling efficient training on small datasets. Extensive evaluation on various datasets demonstrates that our approach achieves consistent, high-quality generation results compared to methods that rely on a single input view.

关键词： Novel Views Synthesis Few Shot Diffusion Model

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Learning Rate Schedule for SIGNSGD Optimizer in neural networks

引用

neural processing LETTERS 2022年第2期54卷 803-816页

作者： Wang, Kang Sun, Tao Dou, Yong Natl Univ Def Technol Sch Comp Natl Lab Parallel & Distributed Proc Changsha 410073 Hunan Peoples R China

SIGNSGD is able to dramatically improve the performance of training large neural networks by transmitting the sign of each minibatch stochastic gradient, which achieves gradient communication compression and keeps standard stochastic gradient descent (SGD) level convergence rate. Meanwhile, the learning rate plays a vital role in training neural networks, but existing learning rate optimization strategies mainly face the following problems: (1) for learning rate decay method, small learning rates produced lead to converge slowly, and extra hyper-parameters are required except for the initial learning rate, causing more human participation. (2) Adaptive gradient algorithms have poor generalization performance and also utilize other hyper-parameters. (3) Generating learning rates via two-level optimization models is difficult and time-consuming in training. To this end, we propose a novel adaptive learning rate schedule for neural network training via SIGNSGD optimizer for the first time. In our method, based on the theoretical inspiration that the convergence rate's upper bound has minimization with the current learning rate in each iteration, the current learning rate can be expressed by a mathematical expression that is merely related to historical learning rates. Then, given an initial value, learning rates in different training stages can be adaptively obtained. Our proposed method has following advantages: (1) it is a novel automatic method without additional hyper-parameters except for one initial value, thus reducing the manual participation. (2) It has faster convergence rate and outperforms the standard SGD. (3) It makes neural networks achieve better performance with fewer gradient communication bits. Three numerical simulations are conducted on different neural networks with three public datasets: MNIST, Cifar-10 and Cifar-100 datasets, and several numerical results are presented to demonstrate the efficiency of our proposed approach.

关键词： SIGNSGD optimizer An adaptive learning rate strategy Communication Fast convergence neural networks

来源：评论

学校读者我要写书评

暂无评论

20th International Symposium on distributed Computing and Artificial Intelligence, DCAI 2023

20th International Symposium on Distributed Computing and Ar...

引用

20th International Symposium on distributed Computing and Artificial Intelligence, DCAI 2023

ISBN: (纸本)9783031386152

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Segmentation of brain tumor in multi-contrast magnetic resonance using deep neural network 18

Automatic Segmentation of brain tumor in multi-contrast magn...

引用

18th International Symposium on Medical Information processing and Analysis

作者： Cavieres, Eduardo Tejos, Cristian Salas, Rodrigo Sotelo, Julio Univ Valparaiso Sch Biomed Engn Valparaiso Chile Millennium Inst Intelligent Healthcare Engn iHLTH Santiago Chile Pontificia Univ Catolica Chile Dept Elect Engn Santiago Chile Pontificia Univ Catolica Chile Biomed Imaging Ctr Santiago Chile

ISBN: (纸本)9781510662544;9781510662551

Among all the tumors that can affect the brain, gliomas are the most frequent, thus is important to get a correct characterization and delimitation of this malformation to provide the best diagnosis and treatment possible. Nevertheless, there are some issues when dealing with segmenting tumors, it can be a long and tedious labor, which makes it prone to mistakes. To solve those problems, several techniques were proposed, including automatic and semiautomatic segmentation. In this work, we propose the use of a U-net architecture-based deep neural network to automatically realize segmentations of tumors on magnetic resonance brain images obtained from the BRATS 2020 database, which provides T1, T1 contrast enhancement (T1ce), T2, and FLAIR images for each subject. The database has a total of 1476 images distributed in 369 patients, that were shuffled into the training set with 70% of the subjects, and the test set with a percentage of 30%. Our results got a 91.6% DICE value for the validation, from a 91.6% for necrotic core (NET), 91.7% for peritumoral edema (PE), and a 91.4% for enhancing tumor (ET). After the training, we got 55.5%,66.5%, and 68.6% DICE values for NET, PE and ET respectively. We also calculated the whole tumor (WT) segmentation performance, reaching a 78.8% precision and the tumor core (TC) segmentation which reach 75,5% precision.

关键词： Glioma Brain Tumor Deep Learning Segmentation neural network Cancer

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Generative Adversarial network for Artistic Style Transfer 20

A Lightweight Generative Adversarial Network for Artistic St...

引用

20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024

作者： Qiao, Ping'an He, Tongtong College of Computer Science Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (纸本)9798350356328

Currently, image style transfer is one of the hotspots in image processing. Generative adversarial networks have been successfully applied in many fields by virtue of their advantages, and the technology of image style transfer has also seen improvements. However, there are still some problems with the existing artistic style transfer models. For example, the generated images will contain noisy textures, the style and color effects are not ideal, and the model has many parameters, which is easy to cause model breakdown and unstable training. To overcome these problems, an image transfer method that improves the cycleconsistent generative adversarial network (CycleGAN) is presented in this paper. According to its structural characteristics, distributed shift convolution (DSConv) is introduced through the quantized neural network, and the reverse residual block is used to optimize the generator network structure, which can greatly reduce the calculation amount of the model while also improving the model's perception ability and accuracy and the quality of the generated images. Experiments show that the proposed approach can improve the content details of the generated image andthe color effect of the style texture, significantly reduces the number of model parameters, reduces the computational cost, improves the transfer rate, upgrading the model performance, and has strong style transfer capabilities. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Survey of Recent Advances in Optimization Methods for Wireless Communications

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2024年第11期42卷 2992-3031页

作者： Liu, Ya-Feng Chang, Tsung-Hui Hong, Mingyi Wu, Zheyu So, Anthony Man-Cho Jorswieck, Eduard A. Yu, Wei Chinese Acad Sci Inst Computat Math & Sci Engn Comp Acad Math & Syst Sci State Key Lab Sci & Engn Comp Beijing 100190 Peoples R China Chinese Univ Hong Kong Shenzhen Sch Sci & Engn Shenzhen 518172 Peoples R China Shenzhen Res Inst Big Data Shenzhen 518172 Peoples R China Univ Minnesota Dept Elect & Comp Engn Minneapolis MN 55455 USA Chinese Univ Hong Kong Dept Syst Engn & Engn Management Hong Kong Peoples R China Tech Univ Carolo Wilhelmina Braunschweig Inst Commun Technol D-38106 Braunschweig Germany Univ Toronto Edward S Rogers Sr Dept Elect & Comp Engn Toronto ON M5S 3G4 Canada

Mathematical optimization is now widely regarded as an indispensable modeling and solution tool for the design of wireless communications systems. While optimization has played a significant role in the revolutionary progress in wireless communication and networking technologies from 1G to 5G and onto the future 6G, the innovations in wireless technologies have also substantially transformed the nature of the underlying mathematical optimization problems upon which the system designs are based and have sparked significant innovations in the development of methodologies to understand, to analyze, and to solve those problems. In this paper, we provide a comprehensive survey of recent advances in mathematical optimization theory and algorithms for wireless communication system design. We begin by illustrating common features of mathematical optimization problems arising in wireless communication system design. We discuss various scenarios and use cases and their associated mathematical structures from an optimization perspective. We then provide an overview of recently developed optimization techniques in areas ranging from nonconvex optimization, global optimization, and integer programming, to distributed optimization and learning-based optimization. The key to successful solution of mathematical optimization problems is in carefully choosing or developing suitable algorithms (or neural network architectures) that can exploit the underlying problem structure. We conclude the paper by identifying several open research challenges and outlining future research directions.

关键词： Tutorials Array signal processing Optimization methods Power control Resource management Wireless communication Scheduling distributed computing Beamforming distributed optimization global optimization learning-based optimization integer optimization nonconvex nonsmooth optimization power control resource allocation scheduling sparse optimization wireless communications

来源：评论

学校读者我要写书评

暂无评论

P-SCADA - A novel area and energy efficient FPGA architectures for LSTM prediction of heart arrthymias in biot applications

引用

EXPERT SYSTEMS 2022年第3期39卷

作者： Varadharajan, Senthil Kumaran Nallasamy, Viswanathan Mahendra Engn Coll Autonomous Dept Elect & Commun Engn Namakkal Tamil Nadu India

Recurrent neural networks (RNN) are extensively used to determine the optimal solutions to the various class recognition problems such as image processing, prediction of biomedical data and speech recognition. With the gradient problems, RNN is slowing losing its shade which is replaced by the Long short term memory (LSTM). However the hardware implementation of the LSTM requires more challenge due to its complexity and high power consumption which makes it unsuitable for implementing in Biological Internet of things networks for prediction of heart diseases. Several algorithms were proposed for an effective implementation of LSTM, but hand-offs between the performance and utilization still needs improvisation. The paper proposes the novel energy efficient and high performance architecture Pipelined Stochastic Adaptive distributed Architectures (P-SCADA) for LSTM networks. In this architecture, hybrid structure has been developed with the help of new distributed arithmetic stochastic computing (DSC) along with the binary circuits to advance the performance of the FPGA such as energy, area and accuracy. The proposed system has been implemented in ARTIX-7 FPGA with special purpose software has been designed and evaluated with different ECG datasets. For the different series data, area utilization is about 40%-44% and power consumption is about 20%-25% with the prediction of accuracy of 98%. Moreover the proposed architecture has been compared with the other existing architecture such as SPARSE architectures, normal stochastic architectures in which the proposed architecture excels in terms area, power and efficiency.

关键词： long short term memory (LSTM) recurrent neural network (RNN) SPARSE architectures stochastic computing

来源：评论

学校读者我要写书评

暂无评论

network Traffic Anomaly Detection Method Based on Improved Clustering Analysis

Network Traffic Anomaly Detection Method Based on Improved C...

引用

2022 International Conference on Signal processing, Computer networks, and Communications, SPCNC 2022

作者： Xu, Chao Liu, Ying Zhang, Wenjie Meng, Meng Teng, Ziyi Tian, Yunjia State Grid Liaoning Electric Power Supply Co. LTD. Information & Telecommunication Branch Shenyang110000 China

ISBN: (纸本)9781510664616

With the surge in the amount of data transmitted on the network, intelligent learning and other technologies have emerged to solve the problem of anomaly detection of streaming data in large data. For network security issues, based on the extraction of network traffic characteristics, network traffic classification or clustering is an important technical means to discover network faults and network attacks. In this paper, a distributed detection framework for detecting anomalous behaviors of encrypted network traffic is proposed. The intelligent router is adopted to obtain the encrypted network traffic monitoring stub, and then the neural network codec is used to adaptively learn the characteristics of the encrypted traffic and identify the abnormal behavior of the encrypted protocol traffic. A wide coverage traffic pattern extraction algorithm based on the network state sequence is designed to obtain the traffic patterns that represent the network conditions of the data center. Finally, the simulation test verifies that the model has frequent traffic patterns with priority. The performance of the network anomaly detection model is better than other detection methods, which improves the accuracy of detection and has a better recognition effect. © 2023 SPIE.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

ROCK-CNN: a distributed RockPro64-based Convolutional neural network Cluster for IoT. Verification and Performance Analysis 26

ROCK-CNN: a Distributed RockPro64-based Convolutional Neural...

引用

26th Conference of Open Innovations Association FRUCT

作者： Khaydarova, Rezeda Fishchenko, Vladislav Mouromtsev, Dmitriy Shmatkov, Vladislav Lapaev, Maksim ITMO Univ St Petersburg Russia TPP Lab LTD St Petersburg Russia

ISBN: (纸本)9789526924427

The paper is dedicated to optimization of machine learning and neural networks applications by replacing common servers with Single Board Computer (SBC) clusters to minimize mounting and service expenses, simplify node mounting process and organize parallel computing in IoT applications. Authors focus on former experience of using distributed computing, mainly, light-weight and cost-optimized SBCs to classify use cases, then, choose an appropriate hardware platform enabling sufficient data processing and easy hot-replacement of nodes. This task requires organizing an efficient software architecture to make use of advantages of SBCs. A comparison for various SBSs is presented. Authors suggest their formerly-designed architecture with changes allowing using it for neural network applications. Authors pay attention to thorough parameter examination based on numerous tests. Parameter timelines are presented. The paper describes a number of test-cases to validate the efficiency of suggested architecture based on common use-cases. Performance analysis and cluster scalability potential estimation are conducted as well to estimate an efficient number of nodes required for future tasks.

关键词： Mountings

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：