检索结果-内蒙古大学图书馆

cognitive computing and complex data (iccd), international conference on the

作者： Chunyun Meng Sai Liang Hongli Li Yuki Todo Division of Electrical Information and Communication Engineering Kanazawa University Kanazawa Japan School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Marketing Department Zhejiang Kefei Technology Co. Ltd Jiaxing China Faculty of Electrical Information and Communication Engineering Kanazawa University Kanazawa Japan

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

Re-identification involves identifying the same person across multiple non-overlapping cameras. Traditional methods rely heavily on pedestrian appearance, assuming consistent clothing in both query and gallery images, which is unrealistic in real-world scenarios where individuals often change clothes. To address this, we propose the Pose and Style Normalization Network (PSN-Net), which handles clothing and pose variations using adversarial generative networks and feature decoupling. Our model includes a Style Normalization (SN) module to eliminate style differences and a dual-channel feature matching module to enhance pedestrian matching. The results of the comparative and ablation experiments demonstrate that our model can effectively improve pedestrian recognition performance under clothing changes.

关键词： Pedestrians Clothing Cameras data mining cognitive systems Identification of persons

来源：评论

学校读者我要写书评

暂无评论

Design of an Intelligent Voice-Controlled Home System Based on Raspberry Pi 25

Design of an Intelligent Voice-Controlled Home System Based ...

引用

25th IEEE international conferences on High Performance computing and Communications, 9th international conference on data Science and Systems, 21st IEEE international conference on Smart City and 9th IEEE international conference on Dependability in Sensor, Cloud and Big data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Wu, Kaiyi Li, Jiaying Yu, Jiabin Hua, Yuhao Xiao, Binggang Wang, Wu College of Information Engineering China Jiliang University Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province Hangzhou China School of Computer Science and Technology Xidian University Xi'an China School of Psychological and Cognitive Sciences Peking University Multisensory Integration Laboratory Beijing China

ISBN: (纸本)9798350330014

A complete intelligent voice-controlled home system should include voice capture, voice recognition, authentication, voice result processing, and other processes. Based on the intelligent voice interaction model of Raspberry Pi 3b+ and Alibaba Cloud platform, this paper realized a high recognition accurate, stable, and efficient intelligent voice-controlled home system. We used the Raspberry Pi to control the hardware interface, collected voice data through an external microphone, and performed command control with external sensors and controllable devices in the hardware part;The software was based on Alibaba Cloud intelligent voice interaction platform to realize voice data recognition. The system constructed can achieve the expected function after repeatedly testing the controlled device. The test results show that the recognition accuracy and recognition efficiency of the system's voice control instructions are both high in a relatively quiet environment. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Multiple Features-Aided Malicious Users Detection in OFDM-based cognitive Radio-Internet of Things

Multiple Features-Aided Malicious Users Detection in OFDM-ba...

引用

2023 international conference on Next-Generation computing, IoT and Machine Learning, NCIM 2023

作者： Miah, Md Sipon Rahman, Md. Mahbubur Niu, Mingbo Armada, Ana Garcia Islamic University Department of Information and Communication Technology Kushtia7003 Bangladesh Universidad Carlos III de Madrid Leganes Department of Signal Theory and Communications Madrid28911 Spain Chang'An University Internet of Vehicle2 to Road Research Laboratory Shaanxi 710018 China

ISBN: (纸本)9798350316001

Cooperative Spectrum Sensing (CSS) is a beneficial approach to alleviate the spectrum scarcity issue by making it possible for the unlicensed users including normal and Malicious Users (MUs) to share the allocated available spectrum in a cognitive Radio-based Internet of Things (CR-IoT). Nevertheless, the detection performance has been compromised due to this approach being responsive to malicious attacks where each MU sends their fake sensing data to a Fusion Center (FC). In this paper, we propose multiple features-aided Machine Learning (ML) to accurately detect MUs in Orthogonal Frequency Division Multiplexing (OFDM)-based CR-IoT networks. Moreover, we solved the sum rate maximization problem for both primary and secondary networks using the golden section search method. Comparing the proposed approach to other conventional schemes, the numerical results demonstrate that it achieves superior detection gains, lower error rate, better system sum rate, and enhanced security where MUs are accurately detected. © 2023 IEEE.

关键词： cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Exploiting MIMO and cognitive Radio for Improved Performance in Indoor Communication Systems

Exploiting MIMO and Cognitive Radio for Improved Performance...

引用

2023 international conference on Multimedia computing, Networking and Applications, MCNA 2023

作者： Musa, Ahmed Halloush, Rami Salamah, Haythem Bany Bataineh, Zaid Al Suleibi, Rahaf Yarmouk University Department of Telecommunications Engineering Irbid Jordan College of Engineering Al Ain University Al Ain United Arab Emirates Yarmouk University Department of Electronics Engineering Irbid Jordan

ISBN: (纸本)9798350339277

cognitive radio (CR) technology is essential in solving the radio spectrum shortage. It enables unlicensed users to opportunistically share wireless channels with licensed users, which can enhance the performance of emerging wireless networks. To further improve wireless network performance, multiple-Input multiple-Output (MIMO) technology has also been utilized. MIMO antennas can transmit data over multiple independent fading paths, resulting in transmission diversity and multiplexing gains. In this paper, we propose a novel MIMO-aware channel assignment protocol for CR networks (CRNs) with the objective of enhancing the achieved network through-put. The proposed channel assignment selects the best idle channel and MIMO antenna mode for each CR transmission. The proposed protocol aims to increase the number of per-user transmitted packets by jointly utilizing the multiplexing and diversity gains. The proposed protocol's performance is compared to reference protocols, including spatial multiplexing mode (SMM) and spatial diversity mode (SDM). The results indicate that the proposed CR-enabled MIMO-aware channel assignment protocol has significantly enhanced the overall network throughput. © 2023 IEEE.

关键词： cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Deep Heuristic Evolutionary Regression Model Based on the Fusion of BiGRU and BiLSTM

引用

cognitive COMPUTATION 2023年第5期15卷 1672-1686页

作者： Xu, Lixiang Xu, Wei Cui, Qingzhe Li, Mengying Luo, Bin Tang, Yuanyan Hefei Univ Sch Artificial Intelligence & Big Data Hefei 230601 Peoples R China Univ Sci & Technol China Sch Publ Affairs Hefei 230026 Peoples R China Anhui Univ Sch Comp Sci & Technol Hefei 230601 Peoples R China FST Univ Macau Zhuhai UM Sci & Technol Res Inst Macau Peoples R China

The input for stock market prediction is usually a period of stock price data with time series characteristics, which will keep changing over time and have more complex background relationships. How to effectively mine and fuse multiple heterogeneous data of the stock market is difficult to be handled by traditional recurrent neural networks (RNN). To solve this problem, we divide the regression model into an encoder and decoder structure. In this paper, we first use RNN technique for missing value complementation, then use the fusion model of bidirectional gate recurrent unit (BiGRU) and bidirectional long short-term memory network (BiLSTM) as the encoder to extract. Finally, the group method of data handling (GMDH) model is used as a decoder to obtain stock market prediction results based on the time series data features. A deep heuristic evolutionary regression model (BBGMDH) based on the fusion of BiGRU and BiLSTM is proposed by the above process. We have conducted extensive experiments on four real stock data, and the results show that BBGMDH significantly outperforms existing methods, verifying the effectiveness of the encoding-decoding stepwise regression model in stock price prediction tasks. The reason is that the encoding layer utilizes the powerful time series data processing technology of RNN to effectively extract the hidden features of stock data, and the decoding layer utilizes the GMDH heuristic evolutionary computation method to simulate the "genetic mutation selection evolution" process of an organism for the regression task of stock market prediction, making full use of their complementary properties. We provide a new solution to the regression prediction problem.

关键词： cognitive computing Gated recurrent neural network Group method of data handling Long short-term memory Stock prediction

来源：评论

学校读者我要写书评

暂无评论

2023 11th international conference on Control, Mechatronics and Automation, ICCMA 2023

2023 11th International Conference on Control, Mechatronics ...

引用

11th international conference on Control, Mechatronics and Automation, ICCMA 2023

ISBN: (纸本)9798350315684

The proceedings contain 82 papers. The topics discussed include: banking in terms of deposit prediction based on machine learning and big data analytics;enhancing stability and performance of hybrid offshore wind platforms: a novel fuzzy logic control approach with computational machine learning;proposal of an instantaneous cognitive map acquisition method for visual information presentation considering work states and cognitive states in unmanned construction;industrial engineering with large language models: a case study of ChatGPT’s performance on oil & gas problems;reinforcement learning-based response shaping control of dynamical systems;EEG based emotion recognition using variational mode decomposition and convolutional neural network for affective computing interfaces;path planning and formation control for multiple quadrotor UAV leader-follower systems;and adaptive tracking controller with exponential restrictions for robotic manipulators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Back Propagation Neural Network Based Positional Positive Solution for Wave Compensation Device

Back Propagation Neural Network Based Positional Positive So...

引用

cognitive computing and complex data (iccd), international conference on the

作者： Tao Tang Limin Tao Wei Han Jing Zhang Bicheng Jiang School of Mechanical and Marine Engineering Beibu Gulf University Qinzhou China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

In this paper, a method for solving the kinematic positive solution of a wave compensation device based on a rope traction parallel mechanism using a BP neural network is proposed. By using the kinematic inverse solution of the rope traction parallel mechanism derived from the Monte Carlo method as the training sample of the BP neural network, the kinematic positive solution of the position of the load platform based on the rope traction parallel wave compensating device is solved, which overcomes the disadvantage that the accuracy of the solution when using the numerical solution method has a direct relationship with the selection of the initial value, as compared with the traditional numerical method. It not only eliminates the tedious mathematical derivation process, but also obtains the positive solution of the position in accordance with the accuracy requirements. The position solved by neural network can be directly applied in the control system of active wave compensation device.

关键词： Training Accuracy Monte Carlo methods Neural networks Kinematics Programming Predictive models Control systems Communication cables cognitive systems

来源：评论

学校读者我要写书评

暂无评论

DECICE: Device-Edge-Cloud Intelligent Collaboration Framework 23

DECICE: Device-Edge-Cloud Intelligent Collaboration Framewor...

引用

20th ACM international conference on computing Frontiers (CF)

作者： Kunkel, Julian Martin Boehme, Christian Decker, Jonathan Magugliani, Fabrizio Pleiter, Dirk Koller, Bastian Sivalingam, Karthee Pllana, Sabri Nikolov, Alexander Soyturk, Mujdat Racca, Christian Bartolini, Andrea Tate, Adrian Yaman, Berkay Univ Gottingen Gottingen Germany GWDG Gottingen Germany E4 Comp Engn SpA Scandiano Italy KTH Royal Inst Technol Stockholm Sweden HLRS Stuttgart Germany Huawei Technol Dusseldorf GmbH Dusseldorf Germany Forsch Burgenland GmbH Eisenstadt Austria SYNYO GmbH1 Vienna Austria Marmara Univ Istanbul Turkiye Consorzio TOPIX Torino & Piemonte Exchange Point Turin Italy Univ Bologna Alma Mater Studiorum Bologna Italy Numer Algorithms Grp Ltd Oxford England BigTRI Bilisim AS Istanbul Turkiye

ISBN: (纸本)9798400701405

DECICE is a Horizon Europe project that is developing an AI-enabled open and portable management framework for automatic and adaptive optimization and deployment of applications in computing continuum encompassing from IoT sensors on the Edge to large-scale Cloud / HPC computing infrastructures. In this paper, we describe the DECICE framework and architecture. Furthermore, we highlight use-cases for framework evaluation: intelligent traffic intersection, magnetic resonance imaging, and emergency response.

关键词： AI-enabled computing Continuum Cloud-Edge Orchestration cognitive Cloud Digital Twin KubeEdge

来源：评论

学校读者我要写书评

暂无评论

THE MULTIVARIATE TRANSFORMER NETWORK FOR MILD cognitive IMPAIRMENT IDENTIFICATION 30

THE MULTIVARIATE TRANSFORMER NETWORK FOR MILD COGNITIVE IMPA...

引用

30th IEEE international conference on Image Processing (ICIP)

作者： Qiao, Jianping Liu, Hongjia Wang, Rong Wang, Zhishun Sun, Jiande Shandong Normal Univ Sch Phys & Elect Jinan Peoples R China Columbia Univ Dept Psychiat New York NY USA Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China

ISBN: (纸本)9781728198354

The functional brain network (FBN) has emerged as a promising biomarker for classifying brain diseases. However, most existing studies ignored the extensive interactions between gray matter (GM) and white matter (WM) which would limit the performance of the process. In this paper, we presented a GM and WM FBNs based mild cognitive impairment (MCI) identification method by utilizing spatial independent component analysis (ICA) and transformer network with rs-fMRI data. Specifically, spatial ICA was performed on the GM and WM of the preprocessed fMRI data. Then the time courses of the GM and WM independent components were inputted into the transformer network with attention mechanism, which led to the optimized and extensive inter- and intra-matter functional connectivity. Finally, the fused GM and WM FBNs were constructed for MCI identification. Experimental results on ADNI dataset demonstrated the superior performance of the proposed method over the state-of-the- art methods.

关键词： fMRI ICA brain network transformer networks

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis across Modalities: A Comprehensive Review of Text and Audio Approaches 6

Sentiment Analysis across Modalities: A Comprehensive Review...

引用

6th international conference on Recent Trends in Advance computing, ICRTAC 2023

作者： Elle, Krisha Dhobale, Nikita Deshmukh, Pratiksha Nirne, Sakshi Jarali, Ashwini International Institute of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350394702

Sentiment analysis, an essential component of natural language processing, reveals the complex web of human emotions and viewpoints present in a variety of communication formats. Text-based as well as audio-based sentiment analysis are two areas where this survey that closely examines sentiment analysis. The digital era's explosion of textual and auditory data has sparked a great deal of research in these fields, producing a wide range of methods and models. Sentiment analysis algorithms have become increasingly complex as a result of the availability of textual data from sources like social media and news articles. Concurrently, there has been a surge in interest in audio-based sentiment analysis because of the increasing use of audio content in podcasts, customer service interactions, and multimedia platforms. This survey provides an in-depth understanding of the recent methods, techniques and approaches in sentiment analysis using text and audio. It carefully describes in detail various developments in these fields, encouraging interdisciplinary idea-sharing. This paper presents a comprehensive overview of sentiment analysis advancements by offering a comprehensive review of research papers, with a focus on relevant models and techniques. © 2023 IEEE.

关键词： Sentiment analysis

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：