检索结果-内蒙古大学图书馆

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Kun Zhao Yaojie Hou College of Computer Science and Technology (College of Big Data) Taiyuan University of Technology Jinzhong China College of Electrical and Automation Henan Polytechnic University Jiaozuo China

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Traditional speech denoising methods often struggle with low signal-to-noise ratios (SNR) and poor clarity in complex noise environments. To address these limitations, this study introduces an adaptive denoising model that integrates Conv-TasNet with WaveNet enhancements. The proposed model incorporates causal convolution within the Conv-TasNet separator to better capture long-term dependencies and employs WaveNet's gating activation mechanism to effectively handle nonlinear speech features. Additionally, a mask weighting strategy is implemented to emphasize target speech signals while suppressing background noise. Experimental results demonstrate that the enhanced model significantly outperforms the original Conv-TasNet, achieving an SNR improvement from –5 dB to 33.74 dB and reducing mean squared error (MSE) to nearly zero. These findings confirm the model's superior performance and robustness in complex noisy environments, highlighting its potential for advanced speech enhancement applications.

关键词： Adaptation models Convolution Computational modeling Particle separators Noise reduction Speech enhancement Feature extraction Computational efficiency Noise measurement Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Mobility and Privacy-aware Computation Offloading with Energy Harvesting in MEC-enabled Networks

Mobility and Privacy-aware Computation Offloading with Energ...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Bi, Jing Niu, Siyu Yuan, Haitao Zhai, Jiahui Zhang, Jia Zhou, MengChu College of Computer Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Southern Methodist University Dept. of Computer Science DallasTX75275 United States New Jersey Institute of Technology Dept. of Electrical and Computer Engineering NewarkNJ07102 United States

ISBN: (纸本)9781665410205

Many new IoT applications have emerged with the fast evolution of 5G and the Internet of Things (IoT). These applications place higher demands on network energy consumption and processing capabilities. Mobile edge computing (MEC) significantly enhances execution efficiency, while energy harvesting (EH) modules further augment the operational features of IoT devices. However, existing studies mainly concentrate on energy consumption and latency problems, often neglecting issues about user mobility and potential privacy leakage within the MEC environment. Therefore, optimizing computation offloading and resource allocation for MEC-enabled IoT networks is essential. This work proposes an innovative architecture with EH for collaborative computing between multiple mobile devices (MDs) and MEC servers. To tackle the problem, this work also proposes an advanced hybrid algorithm named Self-adaptive Bat Optimizer with Genetic operations and individual update of Grey wolf optimizer (SBG2). With SBG2, this work aims to minimize the energy consumption of MDs while providing user mobility and privacy protection. Simulation experiments show that SBG2 reduces energy consumption by 79.15%, 93.20%, and 89.58%, respectively, compared to the other three typical algorithms. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Generalized Zero-Shot Learning via Implicit Attribute Composition

Generalized Zero-Shot Learning via Implicit Attribute Compos...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Zhou, Lei Liu, Yang Li, Qiang School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China College of Computer Science and Technology Zhejiang University Hangzhou China Institute of Automation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Beijing China

ISBN: (纸本)9798350337020

Zero-shot learning (ZSL) is an important but challenging task in computer vision that aims to identify unseen classes without matching training samples. Current cutting-edge ZSL methods based on locality focus on acquiring the explicit locality of distinguishing characteristics, which could face a lack of adequate supervision at the class attribute level. This paper introduces a novel approach called IAC, which aims to learn Implicit Attribute Composition for ZSL. This method is more comprehensive compared to attribute localization that solely focuses on class-level attribute supervision. IAC utilizes subspace representations that efficiently capture the inherent structure of high-dimensional image features. Then, we learn implicit attribute composition through subspace representation learning. The superiority of the proposed IAC compared to the state-of-the-art is demonstrated through sufficient experiments conducted on three commonly used ZSL datasets, CUB, SUN, and AwA2. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Framework with Improved Variance-Stabilized Multi-Objective Proximal Policy Optimization and NSGA-II

An Evolutionary Framework with Improved Variance-Stabilized ...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Bi, Jing Yue, Caiheng Yuan, Haitao Zhai, Jiahui Zhang, Jia Zhou, MengChu Beijing University of Technology College of Computer Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Southern Methodist University Dept. of Computer Science DallasTX75275 United States New Jersey Institute of Technology Dept. of Electrical and Computer Engineering NewarkNJ07102 United States

ISBN: (纸本)9781665410205

Multi-objective optimization algorithms are essential for addressing real-world challenges characterized by conflicting objectives. Although conventional algorithms are effective in exploring solution spaces and generating non-dominated solutions, solution quality and dynamic adaptability of true Pareto fronts need to be improved. This work proposes a multi-objective algorithm that integrates Non-dominated sorting genetic algorithm II (NSGA-II) and Multi-Objective Reinforcement Learning (N-MORL). N-MORL consists of two parts including upstream and downstream components. In the upstream component, this work improves the Variance-stabilized Multi-objective Proximal Policy Optimization (VMPPO) for enhanced convergence stability by adjusting its iteration mechanism. Additionally, this work optimizes variance networks and action sampling to balance exploration and exploitation, which improves experience sampling efficiency. This work adopts high-quality solution sets yielded by MORL as the initial solution set for downstream NSGA-II, guiding the exploration space and increasing the solution number. High-quality initial solutions significantly accelerate the iterative convergence speed of N-MORL. N-MORL provides the quality and the number of solutions, better covering or approaching the true Pareto front. Experimental results with five benchmark multi-objective functions demonstrate that N-MORL outperforms the other three multi-objective evolutionary algorithms regarding high-quality solutions with the same iterations. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Unified Planning Model for Microgrids Considering Typical Scenarios and Operational Simulations 3

A Unified Planning Model for Microgrids Considering Typical ...

引用

3rd Asia Power and Electrical technology Conference, APET 2024

作者： Su, Mengmeng Peng, Jun Zhang, Yong Li, Min Li, Zhenwei Ban, Mingfei North China Branch of State GRID Corporation of China Beijing China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China College of Computer and Control Engineering Northeast Forestry University Harbin China

ISBN: (纸本)9798350367690

The structure of microgrids and the models considered have a significant impact on the planning and operational outcomes of micro grids. Additionally, micro grids encompass various models of primary equipment, including wind, solar, diesel, and storage, while the demand-side response mechanisms are continually being refined. This necessitates the construction of diverse load types, thereby increasing the complexity of micro grid planning and highlighting the need for further research into microgrid planning models. This paper presents various typical mathematical models for microgrids, employs spectral clustering algorithms to obtain representative scenarios, and constructs a unified planning model for microgrids. Furthermore, it elucidates the model adjustment methods under different planning objectives and conducts case analyses of microgrid planning issues. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

Fault Prediction of High-Speed Train Suspension Systems based on Transformer with Improved Temporal Distribution Matching Algorithm

Fault Prediction of High-Speed Train Suspension Systems base...

引用

第43届中国控制会议

作者： Xuansen Wang Yunkai Wu Yang Zhou Zhiyu Zhu Qingjun Zeng College of Automation Jiangsu University of Science and Technology School of Computer Science and Engineering Jiangsu University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This article investigates the fault trend prediction problem of high-speed train suspension systems in the case of data missing *** the perspective of data distribution,Transformer architecture with improved temporal distribution matching(TDM) algorithm is proposed in this paper to further explore the field of fault trend ***,calculating the sensitivity,degree and location of faults to missing ***,the reorganization of encoder layer in TDM algorithm is ***,experiments in SIMPACK-MATLAB/Simulink co-simulation environment is used to validate the effectiveness of the improved TDM algorithm in fault prediction,especially when missing data leads to significant differences in data distribution.

关键词： High-speed train suspension system fault prediction data missing temporal distribution matching algorithm

来源：评论

学校读者我要写书评

暂无评论

Long-Term Water Quality Prediction with Patch Savitsky-Golay Filtering and Transformer

Long-Term Water Quality Prediction with Patch Savitsky-Golay...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lin, Yongze Qiao, Junfei Bi, Jing Yuan, Haitao Zhai, Jiahui Zhou, MengChu Beijing University of Technology Beijing Laboratory of Smart Environmental Protection Beijing100124 China School of Information Science and Technology Beijing University of Technology Beijing100124 China College of Computer Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China New Jersey Institute of Technology Department of Electrical and Computer Engineering Newark07102 United States

ISBN: (纸本)9781665410205

In many fields, time series prediction is gaining more and more attention, e.g., air pollution, geological hazards, and network traffic prediction. Water quality prediction is based on historical data to predict future water quality. However, it is difficult to learn a representation map from a time series that captures the trends and fluctuations to effectively remove noise from time series data and capture complex nonlinear relationships. To solve these problems, this work proposes a time series prediction model, called PSGT for short, which integrates Patch Savitsky-Golay filtering and Transformer. First, this work adopts a Patching method to embed sub-time series data and obtains the trends and semantic information of the time series. Second, it uses the Savitsky-Golay filtering to effectively remove the noise data in the patch and improve the prediction accuracy. Third, it uses a Transformer mechanism to address the nonlinear problem of water quality time series and improve long-term prediction capability. Two real-world datasets are utilized to evaluate the proposed PSGT, and experiments prove that PSGT performs better than other benchmark models by at least 6%. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multiobjective adaptive car-following control of an intelligent vehicle based on receding horizon optimization

引用

Science China(Information Sciences) 2023年第4期66卷 301-302页

作者： Hongbo GAO Juping ZHU Fei ZHANG Ruidong YAN Junjie ZHOU Lei JIANG Jianqiang WANG Keqiang LI Department of Automation University of Science and Technology of China Institute of Advanced Technology University of Science and Technology of China Department of Computational Mathematics School of Mathematical Sciences Anhui University School of Traffic and Transportation Beijing Jiaotong University Autonomous Driving Business Unit Chery Automobile School of College of Computer Science and Technology Zhejiang University China North Vehicle Research Institute School of Automotive Engineering Tsinghua University

Dear editor, Vehicle control is one of the key steps of intelligent driving [1]. Algorithms based on receding horizon optimization(RHO) can predict future trajectories and handle multiobjective constraint conditions; therefore, RHO-based methods have attracted considerable attention in the field of vehicle control. Although existing methods use RHO to design controllers, they do not simultaneously meet the multiobjective optimal control performance requirements on tracking, fuel economy, and ride comfort.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Transportation Systems in Smart City: A Systematic Survey

Intelligent Transportation Systems in Smart City: A Systemat...

引用

2023 International Conference on Robotics and automation in Industry, ICRAI 2023

作者： Hassan, Muhammad Abul Javed, Roofia Farhatullah Granelli, Fabrizio Gen, Xin Rizwan, Muhammad Ali, Syed Haider Junaid, Hazrat Ullah, Sana University of Trento Department of Information Engineering and Computer Science Trento Italy Kinnarid College for Women Department of Computer Science Lahore Pakistan School of Automation China University of Geosciences Wuhan China College of Engineering and Technology University of Derby Derby United Kingdom University of Engineering and Technology Department of Electrical Engineering Peshawar Pakistan University of Malakand Department of Computer Science and Information Technology Pakistan Qurtuba University of Science and Technology Department of Computer Science Peshawar Pakistan

ISBN: (纸本)9781665464727

The idea of Smart Cities (SCs) was developed to digitize conventional urban living areas and redevelop using digital equipment to enhance lifestyle and resident security. Smart cities cover a wide range of applications such as smart government, smart energy, smart transportation, smart health, and smart education. In this paper, we have examined the mobility-related application e.g., smart transportation. We have focused on related to smart transportation like traffic safety, passenger and driver safety, obstacle detection, accident prevention, crime prevention, and detection, and more importantly smart vehicles like UAVs which played a key role in making these gadgets easy to use in urban environments. For a brief overview, 63 academic publications are examined in the field of ITS and SC technologies. Furthermore, we have provided possible solutions in terms of security in the smart transportation system. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Frequency Attention Module for Speaker Recognition 5

Frequency Attention Module for Speaker Recognition

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Wu, Yujiao Fang, Zulin Dong, Jianping Zhang, Gexiang Chengdu University of Technology College of Computer Science and Cyber Security Chengdu China Chengdu University of Technology School of Nuclear Technology and Automation Engineering Chengdu China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Speaker recognition is a task of identifying user's individuality from their speech utterances. Most of the text-independent speaker recognition models available directly input the spectrogram into the deep neural network. However, this does not take full advantage of the spectrogram features. In this paper, we propose a frequency attention module (FAM) based on the fact that the frequency axis in the spectrogram is more representative for speaker feature extraction. It aims to assigning higher weights to important frequency bins, and making the network to extract more features to improve speaker recognition performance. Furthermore, FAM is applied on the convolution output in ResBlock of ResNet34 to capture richer features of the speaker. The experimental results under self-attention pooling (SAP) and attentive-statistics pooling (ASP) show that FAM is feasible and effective. Moreover, the extended experimental results on the Free ST Chinese Mandarin Corpus dataset indicate that the proposed FAM (equal error rate (EER) is 1.59%) outperforms the no-attention ResNet34 (EER is 1.97 %) and spatial-CBAM ResNet34 (EER is 1.88%). © 2022 IEEE.

关键词： Deep neural 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：