检索结果-内蒙古大学图书馆

Pre-Equalization Aided Grant-Free Massive Access in Massive MIMO System

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Yueqing Mei, Yikun Gao, Zhen Wan, Ziwei Ning, Boyu Mi, De Muhaidat, Sami School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology MIIT Key Laboratory of Complex-Field Intelligent Sensing Beijing100081 China Yangtze Delta Region Academy Jiaxing314019 China Beijing Institute of Technology Advanced Technology Research Institute Jinan250307 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Birmingham City University School of Computing and Digital Technology BirminghamB55JU United Kingdom Khalifa University KU 6 G Research Center Department of Computer and Information Engineering Abu Dhabi United Arab Emirates

The spatial diversity and multiplexing advantages of massive multi-input-multi-output (mMIMO) can significantly improve the capacity of massive non-orthogonal multiple access (NOMA) in machine type communications. However, state-of-the-art grant-free massive NOMA schemes for mMIMO systems require accurate estimation of random access channels to perform activity detection and the following coherent data demodulation, which suffers from excessive pilot overhead and access latency. To address this, we propose a pre-equalization aided grant-free massive access scheme for mMIMO systems, where an iterative detection scheme is conceived. Specifically, the base station (BS) firstly activates one of its antennas (i.e., beacon antenna) to broadcast a beacon signal, which facilitates the user equipment (UEs) to perform downlink channel estimation and pre-equalize the uplink random access signal with respect to the channels associated with the beacon antenna. During the uplink transmission stage, the BS detects UEs' activity and data by using the proposed iterative detection algorithm, which consists of three modules: coarse data detection (DD), data-aided channel estimation (CE), and fine DD. In the proposed algorithm, the joint activity and DD is firstly performed based on the signals received by the beacon antenna. Subsequently, the DD is further refined by iteratively performing data-aided CE module and fine DD module using signals received by all BS antennas. Our simulation results demonstrate that the proposed scheme outperforms state-of-the-art mMIMO-based grant-free massive NOMA schemes with the same access latency. © 1967-2012 IEEE.

关键词： Channel estimation

Thermal-Economic Optimization and Working Fluid Selection of Subcritical Organic Rankine System for Low-Temperature Waste Heat Recovery

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Zhang, Chao Li, Yongwang Fu, Wencheng Zhiting, Tong Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China

In the present study, multi-objective optimization is conducted to search for the best operating condition for a subcritical organic Rankine system with the trade-off between system exergy efficiency and dynamic payback period (PBP). A 150°C wastewater heat source is employed as a typical low-temperature heat source. Five decision variables are considered: turbine inlet temperature and pressure, pinch point temperature differences in evaporator and condenser, and condensing temperature. The multi-objective genetic algorithm combined with the backpropagation neural network method is employed as the optimization approach. In addition, the improved Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) is developed to gain the optimal Pareto front solution for either working fluid and find the optimal working fluid among the candidates investigated. The results show that working fluid R236fa is the optimal solution, despite the minimum PBP for working fluid R123 and the maximum system exergy efficiency for working fluid R1234ze. Under the optimal working condition for working fluid R236fa, the system exergy efficiency and the PBP are 0.465 and 7.377 years, respectively. © 2022, The Authors. All rights reserved.

关键词： Multiobjective optimization

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Model Predictive Control Assisted Energy Management Strategy for Hybrid Mining Dump Trucks Based on Speed and Slope Prediction

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Xie, Guojin Qin, Hongmao Xie, Heping Bian, Yougang Ding, Rongjun State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle College of Mechanical and Vehicle Engineering Hunan University Hunan Changsha410082 China School of Mechanical and Automotive Engineering Guangxi University of Science and Technology Guangxi Liuzhou545616 China Wuxi Intelligent Control Research Institute of Hunan University Wuxi214115 China Xuzhou XCMG Mining Machinery Co. Ltd. Xuzhou210009 China

Based on the basic principles of model predictive control, the energy management and optimal control problems of large-scale mining hybrid dump trucks are studied. This paper presents an artificial neural network model to predict the vehicle speed and road slope in the predictive horizon. Based on the predicted information and the vehicle dynamics model, the future power demand of the vehicle is calculated, and a fuel economy optimization objective function is established to minimize the set objective function value under the condition of multiple system constraints, which is solved through dynamic programming algorithm (DP) rolling optimization in the finite predictive horizon to realize optimal energy allocation between the engine generator and battery pack. The vehicle speed and road slope are predicted in 5 different horizons to determine the optimal prediction horizon under the conditions of flat and slope roads. A prediction model is constructed, and combined with the vehicle system and dynamic model, a DP-MPC energy management strategy for series hybrid electric vehicle (SHEV) is designed, and the advantages and disadvantages of the strategy are evaluated through offline simulation testing. Finally, the effectiveness and real-time performance of the energy management strategy are verified through HIL experiments under different operating conditions. © 2024, The Authors. All rights reserved.

关键词： Model predictive control

Experimental Study on Microstructure and Mechanical Properties of Dissimilar Cu/Al Welds by Hybrid Coaxial Blue-Ir Laser

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Zhang, Mingjun Zhang, Yuxuan Zhang, Jian Li, Heqing Cheng, Bo Wu, Xiang Zhou, Dianwu Mao, Cong Hu, Yongle Li, Wen Hunan Provincial Key Laboratory of Intelligent Manufacturing Technology for High-performance Mechanical Equipment Changsha University of Science and Technology Changsha410114 China Institute of Metals College of Materials Science and Engineering Changsha University of Science & Technology Changsha410114 China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Hunan SANY Tower lifting Machinery Co. Ltd. Changsha410600 China

A hybrid blue-infrared (IR) laser is proposed to weld 5052 Al with T2 Cu to investigate the impact of processing parameters on the quality of Cu/Al overlap joints in terms of microstructures, mechanical properties, and failure modes. The experiments show that combining an infrared laser and a blue laser enlarges an opening channel of weld and stabilizes the convention on edge of the weld pool, this eases the escapes of bubbles and prevents the formations of pores. When a hybrid coaxial blue-IR with a power less than 500 W is used, and the weld strengths of the specimens are increased significantly, while the plasticity is decreased slightly in comparison with the specimens welded by an infrared laser. When the power of the blue laser is increased to 800 W, the strength and plasticity of a lapped weld are decreased significantly. Moreover, the welds by an infrared laser were fractured in a mixed fracture mode When a hybrid coaxial blue-IR laser is used, the weld is ruptured by a ductile fracture and a brittle fracture when the blue laser power is lower 500W and over 800 W, respectively. © 2023, The Authors. All rights reserved.

关键词： Microstructure

Model Predictive Control Assisted Energy Management Strategy for Hybrid Mining Dump Trucks Based on Speed and Slope Prediction

学校读者我要写书评

暂无评论

SSRN 2024年

关键词： Model predictive control

Modelling and analysis of haemoglobin catalytic reaction kinetic system

学校读者我要写书评

暂无评论

Mathematical & Computer Modelling of Dynamical Systems 2020年第4期26卷 306-321页

作者： Liu, Yanhong Lv, Hui Wang, Bin Yang, Deyun Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Dalian University Dalian China Department of Information Science and Technology Taishan University Taian China

In order to study whether haemoglobin (Hb) can replace peroxidase and has good catalytic properties. The key to exploring the characteristics of Hb peroxidase is to establish a suitable kinetic model, which is studied in this paper. First, according to the Hb catalytic reaction, a nonlinear system is established and improved. It is proved that the established system is in line with the practical significance. The stability of the original system is judged by analysing the stability of the simplified system. Then, considering the effect of time delay on Hb catalytic reaction, a nonlinear time-delay catalytic reaction system is obtained. For convenient application, the system is linearized using Taylor's formula, and the dynamic characteristics of Hopf bifurcation are analysed. The response diagrams of three system are plotted by setting perturbation parameters, and their variations are observed to analyse the differences among them. The results show that the nonlinear time-delay system can better describe the characteristics of the catalytic reaction. [ABSTRACT FROM AUTHOR]

关键词： central manifold theorem haemoglobin Hopf bifurcation Nonlinear system model time delay

End-to-end speech emotion recognition based on one-dimensional convolutional neural network 2019

学校读者我要写书评

暂无评论

End-to-end speech emotion recognition based on one-dimension...

3rd International Conference on Innovation in Artificial Intelligence, ICIAI 2019

作者： Gao, Mengna Zhang, Qiang Dong, Jing Yang, Deyun Zhou, Dongsheng Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116024 China School of Information Science and Technology Taishan University Tai'an Shandong Province271000 China Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116024 China

ISBN: (纸本)9781450361286

Real-time speech emotion recognition has always been a problem. To this end, we proposed an end-to-end speech emotion recognition model based on one-dimensional convolutional neural network, which contains only three convolution layers, two pooling layers and one full-connected layer. Through Adam optimization algorithm and back propagation mechanism, more discriminative features can be extracted continuously. Our model is quite simple in structure and easy to quickly complete the emotional classification task. Compared with traditional methods, there is no need to carry out the complex process of manually extracting features, and the model can automatically learn the emotional features from raw speech signals. In the emotional recognition experiments with EMODB, CASIA, IEMOCAP, and CHEAVD four speech databases, relatively high recognition rates were obtained. Experiments show that the proposed algorithm is of great benefit to the implementation of real-time speech emotion recognition. © 2019 ACM

关键词： Emotion Recognition

UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Chen, Chuang Sun, Xiao Liu, Zhi School of Artificial Intelligence Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machines School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Department of Computer and Network Engineering The University of Electro-Communications Chofu-shi Tokyo182-8585 Japan

Visual emotion analysis holds significant research value in both computer vision and psychology. However, existing methods for visual emotion analysis suffer from limited generalizability due to the ambiguity of emotion perception and the diversity of data scenarios. To tackle this issue, we introduce UniEmoX, a cross-modal semantic-guided large-scale pretraining framework. Inspired by psychological research emphasizing the inseparability of the emotional exploration process from the interaction between individuals and their environment, UniEmoX integrates scene-centric and person-centric low-level image spatial structural information, aiming to derive more nuanced and discriminative emotional representations. By exploiting the similarity between paired and unpaired image-text samples, UniEmoX distills rich semantic knowledge from the CLIP model to enhance emotional embedding representations more effectively. To the best of our knowledge, this is the first large-scale pretraining framework that integrates psychological theories with contemporary contrastive learning and masked image modeling techniques for emotion analysis across diverse scenarios. Additionally, we develop a visual emotional dataset titled Emo8. Emo8 samples cover a range of domains, including cartoon, natural, realistic, science fiction and advertising cover styles, covering nearly all common emotional scenes. Comprehensive experiments conducted on six benchmark datasets across two downstream tasks validate the effectiveness of UniEmoX. The source code is available at https://***/chincharles/u-emo. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics