检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Junxiu Wu, Fengxiang Lu, Baoshan Qin, Sheng Fu, Qiang Luo, Yuling Guangxi Key Lab of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin541004 China Guangxi Wireless Broadband Communication and Signal Processing Key Laboratory Guilin University of Electronic Technology Guilin541004 China

Deep learning can significantly enhance student behavior detection in classrooms. However, challenges such as small target recognition, blurry data, occlusion, and multi-scale detection persist. To address these, we propose YOLOv9-SPE, an improved model based on YOLOv9, incorporating Space-to-Depth Convolution (SPD-Conv), Partial Convolution (PConv), and an Efficient Multi-Scale Attention (EMA) Module. SPD-Conv enhances small target recognition and improves feature extraction for blurry data, while PConv, adapted from FasterNet, addresses occlusion issues. EMA is integrated to handle multi-scale targets in classroom student behavior detection. Experimental results on a student behavior dataset show that YOLOv9-SPE achieves a 2.1% improvement in mean average precision over the original YOLOv9. These enhancements provide a more accurate and efficient method for monitoring and analyzing student behavior in educational settings. © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Spectrum Prediction Method for Bursty Frequency Bands

A Spectrum Prediction Method for Bursty Frequency Bands

引用

IEEE wireless communications and networking Conference Workshops (WCNCW)

作者： Chao Yang Tao Peng Peiliang Zuo Xinyue Wang Wireless Signal Processing and Networks Laboratory Key Laboratory of Universal Wireless Communication Ministry of Education Beijing University of Posts and Telecommunications Beijing China

Spectrum prediction is an important technology for spectrum cognition which constitutes the premise of cognitive radio technology. However, most of the existing spectrum prediction methods were proposed for common frequency bands. Based on this philosophy, these methods generally build a mapping model between historical statistical information and future state, and performance of the single model was verified to be limited due to that it cannot match the high burstiness of spectrum. This paper considers the prediction of bursty bands. The previous collected data of 2.4GHz Industrial, Scientific, Medical (ISM) bands is utilized for both feature analysis and method research. Specifically, the deep-reinforcement learning (DRL) method is adopted to address the high-dimensional state and action spaces caused by the classification process using the values of several features. Besides, this paper also employs the upper-limit results of the prediction to refine the classification process, i.e. those groups with better prediction performance using predictors corresponding to other classes will be readjusted. We thus name the proposed method as classification-based deep reinforcement learning (C-DRL). Finally, extensive experiments with the collected real data are conducted to verify the performance of C-DRL. The results suggest that C-DRL significantly outperforms the state-of-the-art algorithms in terms of the prediction performance.

关键词： Conferences Reinforcement learning Predictive models Prediction algorithms Data models Cognition Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Spectrum Efficiency Maximization for Cooperative Power Beacon-Enabled wireless Powered communication Networks

引用

China communications 2021年第12期18卷 230-251页

作者： Wenjun Xu Wei Chen Yongjian Fan Zhi Zhang Xinxin Shi Key Lab of Universal Wireless Communications Ministry of EducationBeijing University of Posts and TelecommunicationsBeijing 100876China Hebei Key Laboratory of Security and Protection Information Sensing and Processing Hebei University of EngineeringHandan 056038China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Telecom Planning&Designing Institute Co. Ltd.Beijing 100048China

We consider a spectrum efficiency(SE)maximization problem for cooperative power beacon-enabled wireless powered communication networks(CPB-WPCNs),where each transmitter harvests en-ergy from multi-antenna power beacons(PBs)and transmits data to the corresponding *** data transmission,both orthogonal transmission,i.e.,the time splitting(TS)mode,and non-orthogonal trans-mission,i.e.,the interference channel(IC)mode,are *** to improve the system SE,the energy beamformers of PBs,the transmit power,and the transmit time duration of transmitters are jointly *** the TS mode,the original non-convex problem is transformed into a convex opti-mization problem by means of variable substitution and semidefinite relaxation(SDR).The rank-one na-ture of this SDR is proved,and then a Lagrange-dual based fast algorithm is proposed to obtain the opti-mal solution with much lower *** the IC mode,to conquer the strong non-convexity of the problem,a branch-reduce-and-bound(BRB)mono-tonic optimization algorithm is designed as a ***,a low-complexity distributed suc-cessive convex approximation(SCA)algorithm is ***,simulation results validate the perfor-mance of the proposed algorithms,achieving optimal-ity within only 1%∼2%computation time compared to the CVX solver in the TS mode and achieving 98%of the optimal performance in the IC mode.

关键词： spectrum efficiency power beacon WPCN time splitting interference channel wireless power transfer

来源：评论

学校读者我要写书评

暂无评论

An intelligent self-sustained RAN slicing framework for diverse service provisioning in 5G-beyond and 6G networks

引用

Intelligent and Converged Networks 2020年第3期1卷 281-294页

作者： Jie Mei Xianbin Wang Kan Zheng Electrical and Computer Engineering Western UniversityLondonON N6A 5B9Canada Intelligent Computing and Communication(IC2)Lab Wireless Signal Processing and Network(WSPN)LabKey Laboratory of Universal Wireless CommunicationMinistry of EducationBeijing University of Posts and Telecommunications(BUPT)Beijing 100876China

Network slicing is a key technology to support the concurrent provisioning of heterogeneous Quality of Service(QoS)in the 5th Generation(5G)-beyond and the 6th Generation(6G)***,effective slicing of Radio Access Network(RAN)is very challenging due to the diverse QoS requirements and dynamic conditions in the 6G *** this paper,we propose a self-sustained RAN slicing framework,which integrates the self-management of network resources with multiple granularities,the self-optimization of slicing control performance,and self-learning together to achieve an adaptive control strategy under unforeseen network *** proposed RAN slicing framework is hierarchically structured,which decomposes the RAN slicing control into three levels,i.e.,network-level slicing,next generation NodeB(gNodeB)-level slicing,and packet scheduling level *** the network level,network resources are assigned to each gNodeB at a large timescale with coarse resource *** the gNodeB-level,each gNodeB adjusts the configuration of each slice in the cell at the large *** the packet scheduling level,each gNodeB allocates radio resource allocation among users in each network slice at a small ***,we utilize the transfer learning approach to enable the transition from a model-based control to an autonomic and self-learning RAN slicing *** the proposed RAN slicing framework,the QoS performance of emerging services is expected to be dramatically enhanced.

关键词： Radio Access Network(RAN) network slicing network resource management intelligent network

来源：评论

学校读者我要写书评

暂无评论

Suppression of 802.11 Transmission in 2. 4GHz ISM band: Method and Experimental Verification 91

Suppression of 802.11 Transmission in 2. 4GHz ISM band: Meth...

引用

91st IEEE Vehicular Technology Conference, VTC Spring 2020

作者： Zuo, PeiLiang Peng, Tao Wu, Hao You, Kangyong Jing, Hanbo Guo, Wenbin Wang, Wenbo Beijing University of Posts and Telecommunications Wireless Signal Processing and Networks Laboratory Key Laboratory of Universal Wireless Communication Ministry of Education Beijing China Beijing Institute of Remote Sensing Equipment Beijing China

ISBN: (纸本)9781728152073

Due to the characteristics of being license-free, the ISM (Industrial, Scientific, Medical) bands are frequently utilized by wireless communication systems. However, the ubiquitous and unmanaged IEEE 802.11 systems deployed in the ISM bands may bring non-negligible interference to emergency communications. This paper considers suppressing the transmission of 802.11 systems in 2. 4GHz ISM band for protecting the public safety in emergency scenarios. To this end, two kinds of suppression frames that comply with the 802.11 protocol are analyzed, which respectively borrow the ideas of virtual carrier-sense attack and spoofing. The validity of each of the frames is then verified both qualitatively and quantitatively by the designed experiments with multiple commercial off-the-shelf (COTS) 802.11 devices. Based on which we propose an integrated suppression method that is effective for all tested devices. Further experiments and analysis show that the presented method outperforms the state-of-the-art suppression methods in terms of energy consumption and applicability. © 2020 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Spectrum Prediction for Frequency Bands with High Burstiness: Analysis and Method 91

Spectrum Prediction for Frequency Bands with High Burstiness...

引用

91st IEEE Vehicular Technology Conference, VTC Spring 2020

作者： Zuo, PeiLiang Peng, Tao Wang, Xinyue You, Kangyong Jing, Hanbo Guo, Wenbin Wang, Wenbo Key Laboratory of Universal Wireless Communication Ministry of Education Beijing University of Posts and Telecommunications Wireless Signal Processing and Networks Laboratory Beijing China Beijing Institute of Remote Sensing Equipment Beijing China

ISBN: (纸本)9781728152073

Spectrum prediction has recently gained a lot of attention due to its extensive applications in cognitive radio networks. However, most of the related research assumed that the spectrum occupancy pattern is time-invariant, which limits the performance of proposed prediction methods for the high burst frequency bands, e.g. the ISM (Industrial, Scientific, Medical) bands. In order to improve the prediction accuracy for them, this paper first analyzes the characteristics of the collected real WiFi data in 2.4GHz ISM band, and shows the burstiness of the band from multiple aspects. Based on the analysis, we then propose a MultiLayer Perceptron based Reinforcement Learning (RLMLP) method which could adaptively select the corresponding predicting action according to the state to which any piece of data belongs. The state space of the method consists of multiple data categories that are determined by the results of feature partitioning, while the action space is composed of multiple MLPs with the same mapping structure. Finally, numerical results on the collected data show that the proposed RLMLP method is significantly better than the state-of-the-art algorithms in terms of the prediction performance. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Real-time Embedded Target Tracking System Based on Deep Learning Model

A Real-time Embedded Target Tracking System Based on Deep Le...

引用

International Conference on Computer and communications (ICCC)

作者： Song Jiang Hang Long Tianpeng Yang Wireless Signal Processing and Networks (WSPN) Lab Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications (BUPT) Beijing China

ISBN: (纸本)9781665409513

Target tracking has been arousing increasing attention in current production and life. Usually, target tracking algorithms are deployed on high-performance servers. There are significant challenges in deploying real-time target tracking in embedded systems. Therefore, a real-time embedded target tracking system is studied based on a deep learning model in this paper. Firstly, the hardware implementation of the proposed system is presented in detail. Then, to resolve the problems of high latency and low performance in embedded platforms, we offer an adaptive detection strategy that combines the advantages of deep network model inference and prediction. This strategy makes full use of the target relevance between the front and rear frames of video, reduces the frequency of calling the depth model, and improves the system's speed. Finally, Experiments have proved that the system can effectively reduce the time delays by more than 50% while ensuring the same detection effect. Meanwhile, the system's power consumption and resource occupancy rate are also significantly improved.

关键词： Deep learning Adaptation models Target tracking Adaptive systems Computational modeling Scalability Production

来源：评论

学校读者我要写书评

暂无评论

Multi-antenna Array-based AoA Estimation Using Bluetooth Low Energy for Indoor Positioning

Multi-antenna Array-based AoA Estimation Using Bluetooth Low...

引用

International Conference on Computer and communications (ICCC)

作者： Shuai He Hang Long Wei Zhang Wireless Signal Processing and Networks (WSPN) Lab Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications (BUPT) Beijing China

ISBN: (纸本)9781665409513

In recent years, Bluetooth Low Energy (BLE) has developed into one of the key technologies for indoor positioning in the Internet of Things (IoT). Efficient positioning can be achieved by estimating the signal Angle of Arrival (AoA) of multi-antenna arrays to locate the device. AoA-based approaches are sensitive to noise, multipath, and path loss effects. Furthermore, AoA measurement using a multi-antenna array can also cause errors due to the receiver switching among single antennas. In this paper, an efficient signal processing method combined with nonlinear recursive least squares and unscented Kalman filter is proposed to solve the effect of noise, multipath and antenna switching. Experimental results show that compared with Multiple signal Classification (MUSIC), the average estimation error of the AoA calculated by the proposed method is reduced by 3.9 degrees. The experiment illustrates the proposed method in the paper can effectively improve the accuracy of AoA.

关键词： Antenna measurements Bluetooth Array signal processing Receiving antennas Pattern classification Switches Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

A Low-Latency and High-Performance SCL Decoder with Frame-Interleaving

A Low-Latency and High-Performance SCL Decoder with Frame-In...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Leyu Zhang Yuqing Ren Yifei Shen Wuyang Zhou Alexios Balatsoukas-Stimming Chuan Zhang Andreas Burg CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China (USTC) China Telecommunication Circuits Laboratory École Polytechnique Fédérale de Lausanne (EPFL) Switzerland Department of Electrical Engineering Eindhoven University of Technology Netherlands Lab of Efficient Architectures for Digital-Communication and Signal-Processing (LEADS) Southeast University China

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

In this paper, we describe a frame-interleaving hardware architecture for a generalized node-based successive cancellation list (SCL) decoder. By efficiently reusing otherwise idle computational units, two independent frames can be decoded simultaneously, resulting in a significant throughput gain. Based on this new architecture, we also exploit graph ensembles to diversify the decoding, enhancing the error-correcting performance by 0.28 dB and reducing the worst-case latency for serial graph processing by over 32%. Implementation results show that the proposed SCL decoder with frame-interleaving architecture achieves a throughput of 7.15 Gbps and an area efficiency of 37.63 Gbps/mm 2 , which is 1.56× and 1.11× better than the state-of-the-art node-based SCL decoders.

关键词： Codes Circuits and systems Computer architecture Throughput Hardware Decoding Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Directional Source Localization Based on RSS-AOA Combined Measurements

引用

China communications 2020年第11期17卷 181-193页

作者： Peiliang Zuo Tao Peng Hao Wu Kangyong You Hanbo Jing Wenbin Guo Wenbo Wang Wireless Signal Processing and Network Laboratory Key Laboratory of Universal Wireless CommunicationMinistry of EducationBeijing University of Posts and TelecommunicationsBeijing 100876China Department of Electronic and Communication Engineering Beijing Electronic Science&Technology InstituteBeijing 100070China th Research Institute of China Electronics Technology Group Corporation(CETC) Guangzhou 510310China Beijing Institute of Remote Sensing Equipment Beijing 100854China

Source localization plays an indispensable role in many *** paper addresses the directional source localization problem in a three-dimensional(3D)wireless sensor network using hybrid received-signal-strength(RSS)and angle-of-arrival(AOA)*** the position and transmission orientation of the source are to be *** the considered positioning scenario,the angle and range measurements are respectively corresponding to the AOA model and RSS model that integrates the Gaussian-shaped radiation *** that the localization problem is non-convex and the unknown parameters therein are coupled together,this paper adopts the second-order cone relaxation and alternating optimization techniques in the proposed estimation ***,to provide a performance benchmark for any localization method,the corresponding Cramer-Rao lower bounds(CRLB)of estimating the unknown position and transmission orientation of the source are *** and simulation results demonstrate that the presented algorithm effectively resolves the problem,and its estimation performance is close to the CRLB for the localization with the hybrid measurements.

关键词： localization directional source CRLB RSS AOA wireless sensor network(WSN) second-order cone programming(SOCP)

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：