检索结果-内蒙古大学图书馆

Joint beamforming and power allocation using deep learning for D2D communication in heterogeneous networks

IET COMMUNICATIONS 2020年第18期14卷 3095-3101页

作者： Wang, Yuejiao Wang, Shenghui Liu, Lu Beijing Jiaotong Univ Inst Informat Sci Beijing Peoples R China

Device-to-device (D2D) communication plays a significant role in cellular networks as it can increase the capacity, spectrum efficiency and energy efficiency of the system. However, the large computational complexity of D2D resource management optimisation algorithms creates a serious gap between theoretical design and real-time processing, which leads to the limited use of D2D communication technology. In this study, a novel deep learning-based optimisation method is proposed to overcome the high computational complexity of joint beamforming design and power allocation optimisation algorithms in D2D communication. Unlike existing approaches, the authors design a convolutional neural network based end-to-end network structure to solve complex computing problems for channel state information under a limited feedback scenario. The Max-SE loss function which indicates quality-of-service (QoS) constraint and interference constraint, together with the mean squared error (MSE) function, are designed to maximise the spectral efficiency of the system while minimising the total transmit power. The simulation results show that the proposed approach can achieve performance comparable to the weighted minimum MSE scheme with low computation time.

关键词： optimisation neural nets computational complexity mean square error methods learning (artificial intelligence) radiofrequency interference MIMO communication cellular radio array signal processing quality of service resource allocation serious gap theoretical design real-time processing D2D communication technology deep learning-based optimisation method high computational complexity joint beamforming design power allocation optimisation algorithms authors design convolutional neural network end-to-end network structure complex computing problems Max-SE loss function interference constraint mean squared error function spectral efficiency low computation time heterogeneous networks Device-to-device communication cellular networks spectrum efficiency energy efficiency D2D resource management optimisation algorithms

来源：评论

学校读者我要写书评

暂无评论

Low light image enhancement with adaptive sigmoid transfer function

引用

IET IMAGE PROCESSING 2020年第4期14卷 668-678页

作者： Srinivas, Kankanala Bhandari, Ashish Kumar Natl Inst Technol Patna Dept Elect & Commun Engn Patna 800005 Bihar India

Low light image enhancement algorithms intent to produce visually pleasant images and target to extract valuable information for computer vision applications. The task of improving the quality of low light images is a challenging one. The existing methods for quality improvement undeniably annoy the visual aesthetics and suffer the major drawback of high computational complexity and less efficiency. To improve the visual quality and lower the distortions, a simple and computationally efficient low light image enhancement framework is presented in this study. To achieve this, an adaptive sigmoid transfer function (ASTF) is used and is derived from the sigmoid activation function of neural networks. By combining ASTF with a Laplacian operator, colour and contrast-enhanced images are obtained. Experiments show the effectiveness of the proposed method with state-of-the-art methods.

关键词： image enhancement computer vision neural nets transfer functions adaptive sigmoid transfer function visually pleasant images computer vision applications low light images visual aesthetics high computational complexity visual quality computationally efficient low light image enhancement framework sigmoid activation function contrast-enhanced images

来源：评论

学校读者我要写书评

暂无评论

A fast method for blindly identifying Reed-Solomon codes based on matrix analysis

引用

IET COMMUNICATIONS 2022年第20期16卷 2414-2421页

作者： Han, Shunan Gao, Mengzhu Yi, Renjie Wu, Chenxi Aviat Univ Air Force Dept Commun Nanhu Rd 2222 Changchun Peoples R China Natl Univ Def Technol Coll Elect Engn Hefei Peoples R China

For the identification of Reed-Solomon (RS) codes, the existing methods need to test the possible codeword length and the primitive polynomials exhaustively. Exhaustive search leads to high computational complexity. To overcome this limitation and fulfill the requirement in practice, a fast blind identification method is proposed. Different with most methods, our identification method is discussed in Galois Field of 2. First, by using Gaussian elimination, the bit matrix is transformed to the simplest upper triangular form. If the assumed codeword length is right, the matrix is of deficient rank, and the parameters of an RS code can be estimated according to the rank. The null space of the matrix, defined as the equivalent binary parity check matrix, can also be obtained from the simplification result. Then, a candidate set of primitive polynomials is constructed according to the estimated codeword length. By using the matrix null space, the correctness of a candidate primitive polynomial is tested through matrix analysis. Finally, by combining the estimated parameters, the generator polynomial of an RS code is identified. To decrease the bit errors in the matrix, soft-decision data is used to select reliable bits. Experimental results show the effectiveness and robustness of our method.

关键词： matrix algebra matrix analysis matrix null space fast blind identification method possible codeword length generator polynomial estimated codeword length Gaussian elimination exhaustive search computational complexity parity check codes RS code different with most methods candidate primitive polynomial equivalent binary parity check matrix Galois Field high computational complexity assumed codeword length polynomials primitive polynomials Reed-Solomon codes bit matrix soft-decision data simplest upper triangular form deficient rank Galois fields

来源：评论

学校读者我要写书评

暂无评论

Deep-learning-based beamforming for rejecting interferences

引用

IET SIGNAL PROCESSING 2020年第7期14卷 467-473页

作者： Ramezanpour, Parham Rezaei, Mohammad Javad Mosavi, Mohammad Reza Iran Univ Sci & Technol Dept Elect Engn Tehran *** Iran

Antenna arrays have been widely used for space and space-time processing to estimate the desired signals in the presence of narrowband and wideband interferences. Estimating the optimal weight vector is a challenging problem in space and space-time processing due to its high computational complexity. The problem escalates when the number of antennas and taps of filters for time-domain processing increases. In this study, a convolutional neural network is employed to estimate nearly-optimal weight vectors even when the number of available snapshots of the received signal is as low as 400 and a signal-to-noise ratio as low as -5 dB. Unlike the conventional processors, the authors proposed method requires no prior knowledge about the direction of arrival of the desired signal. In addition, due to its parallel architecture, the computational complexity of the neural processors is reasonable using a single graphical processing unit on a PC to run the algorithms. Through simulations of the uniform linear array in the presence of narrowband and wideband interferences, they demonstrate that the output signal-to-interference plus noise ratio (SINR) is very close (by <0.5 dB) to the max SINR obtained by the optimal weight vector of antenna arrays.

关键词： array signal processing antenna arrays neural nets parallel architectures learning (artificial intelligence) direction-of-arrival estimation computational complexity interference suppression wideband interferences optimal weight vector space-time processing high computational complexity antennas time-domain processing increases convolutional neural network nearly-optimal weight vectors received signal signal-to-noise ratio single graphical processing unit narrowband interferences output signal-to-interference antenna arrays deep-learning-based desired signal noise figure-5 0 dB noise figure 0 5 dB

来源：评论

学校读者我要写书评

暂无评论

User Grouping Algorithm for Power Minimization in STBC MC-CDMA systems

User Grouping Algorithm for Power Minimization in STBC MC-CD...

引用

21st Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Phasouliotis, Antonis So, Daniel K. C. Univ Manchester Sch Elect & Elect Engn Manchester Lancs England

ISBN: (纸本)9781424480166

In this paper, we propose user grouping algorithms to provide power minimization in grouped STBC MC-CDMA systems. Depending on the channel fading conditions, power control is utilized to minimize the total transmitted power under a BER constraint. When the allocation is performed without a fair data rate requirement, we provide the optimal solution to the minimization problem. However when some fairness is considered, the optimal solution requires high computational complexity. We solve this problem by proposing two suboptimal algorithms. Simulation results illustrate a significantly reduced power consumption in comparison with other techniques.

关键词： BER STBC MC-CDMA system channel fading condition code division multiple access computational complexity data rate requirement error statistics fading channels high computational complexity optimal solution power consumption power control power control power minimization problem power transmission space-time block codes suboptimal algorithm user grouping algorithm

来源：评论

学校读者我要写书评

暂无评论

Software Architecture of high Efficiency Video Coding for Many-Core Systems with Power-Efficient Workload Balancing

Software Architecture of High Efficiency Video Coding for Ma...

引用

Design, Automation and Test in Europe Conference and Exhibition (DATE)

作者： Khan, Muhammad Usman Karim Shafique, Muhammad Henkel, Joerg Karlsruhe Inst Technol CES D-76021 Karlsruhe Germany

ISBN: (纸本)9783981537024

The high Efficiency Video Coding (HEVC) standard aims at providing similar to 50% better compression compared to its predecessor (H.264) at the cost of high computational complexity. To enable HEVC video encoding in real-time scenarios, special coding support for parallelization is provided in HEVC that can be exploited by many-core systems. In this work, we present a HEVC software architecture where a video frame is adaptively divided into independent video frame regions (i.e. so-called video tiles) which are processed concurrently on multiple cores. By balancing the workload of each video tile mapped to a particular core, the total power consumption of a system is reduced (through dynamically scaling the operating frequency) under a given frame-rate constraint. We also exploit user tolerance to further curtail the HEVC workload with insignificant video quality degradation. Experimental results illustrate that the proposed approach results in similar to 43% power savings on a many-core system.

关键词： data compression software architecture video codecs video coding H.264 standard HEVC software architecture HEVC standard frame-rate constraint high computational complexity high efficiency video coding standard independent video frame regions many-core systems power consumption power-efficient workload balancing video quality degradation video tiles complexity theory Encoding Hardware Power demand Quality assessment Tiles Video recording

来源：评论

学校读者我要写书评

暂无评论

A Learning Scheme to Fuzzy C-Means based on a Compromise in Updating Membership Degrees

A Learning Scheme to Fuzzy C-Means based on a Compromise in ...

引用

IEEE International Conference on Fuzzy Systems

作者： Wu, Shang-Lin Lin, Yang-Yin Liu, Yu-Ting Chen, Chih-Yu Lin, Chin-Teng Natl Chiao Tung Univ Inst Elect Control Engn Hsinchu 300 Taiwan Natl Chiao Tung Univ Brain Res Ctr Hsinchu 300 Taiwan Natl Chiao Tung Univ Inst Biomed Engn Hsinchu 300 Taiwan

ISBN: (纸本)9781479920723

Fuzzy C-Means (FCM) clustering is the most well-known clustering method according to fuzzy partition for pattern classification. However, there are some disadvantages of using that clustering method, such as computational complexity and execution time. Therefore, to solve these drawbacks of FCM, the two-phase FCM procedure has been proposed in this study. Compared with the conventional FCM, the usage of a compromised learning scheme makes more adaptive and effective. By performing the proposed approach, the unknown data could be rapidly clustered according to the previous information. A synthetic data set with two dimensional variables is generated to estimate the performance of the proposed method, and to further demonstrate that our method not only reduces computational complexity but economizes execution time compared with the conventional FCM in each example.

关键词： Fuzzy C-Means (FCM) Clustering Data classification high computational complexity Long execution time

来源：评论

学校读者我要写书评

暂无评论

Fast algorithm for moving target localisation using FDA-MIMO radar

引用

JOURNAL OF ENGINEERING-JOE 2019年第19期2019卷 5749-5752页

作者： Xu, Jian Wang, Wen-Qin Cui, Can Huang, Bang Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu Sichuan Peoples R China Nanjing Univ Sci & Technol Sch Elect Engn & Optoelect Technol Nanjing Jiangsu Peoples R China

Target localisation using frequency diverse array (FDA) has drawn much attention owing to the additional degree of freedom in the range dimension. However, the Doppler effect was often ignored in previous FDA works because of the stationary target assumption, and in contrast, even stationary target localisation could be of quite a high computational complexity. In this study, a method is proposed that can jointly estimate range, angle, and Doppler for FDA multiple-input-multiple-output radar with low computational complexity. First, Doppler is estimated independently by utilising unstructured maximum likelihood method. Next, traditional two-dimensional (2D) MUSIC is divided into multiple one-dimensional (1D) MUSIC to estimate the angle. Then substituting the estimated angle into the former 2D MUSIC results in a 1D searching over range dimension to get the range estimation. The advantage of the proposed method was verified by simulation results.

关键词： computational complexity direction-of-arrival estimation MIMO radar Doppler effect radar signal processing MIMO communication maximum likelihood estimation fast algorithm FDA-MIMO radar frequency diverse array range dimension Doppler effect previous FDA works stationary target assumption stationary target localisation high computational complexity FDA multiple-input-multiple-output radar low computational complexity maximum likelihood method two-dimensional MUSIC one-dimensional MUSIC estimated angle 2D MUSIC results range estimation

来源：评论

学校读者我要写书评

暂无评论

A Joint Decoding Algorithm for Turbo Product Codes Applied in PCM/FM Telemetry System

A Joint Decoding Algorithm for Turbo Product Codes Applied i...

引用

International Congress on Image and Signal Processing

作者： Li Wang Manxi Wang Liandong Wang Fu Yuan State Key Lab. of Complex Electromagn. Environ. Effects on Electron. & Inf. Syst. Luoyang China

ISBN: (纸本)9781479958368

For decreasing the high computational complexity of Turbo product code in PCM/FM telemetry system, a joint decoding algorithm based on syndrome-based decoding and a correlation operation to substitute for searching the competing codeword was proposed. Simulation results show that the proposed algorithm can effectively reduce the decoding complexity with less coding gain degradation.

关键词： computational complexity telemetry turbo codes PCM-FM telemetry system correlation operation decoding complexity high computational complexity joint decoding algorithm syndrome-based decoding turbo product codes Algorithm design and analysis complexity theory Decoding Frequency modulation Iterative decoding Phase change materials Product codes Chase decoding PCM/FM telemetry system Turbo product code

来源：评论

学校读者我要写书评

暂无评论

A Learning Scheme to Fuzzy C-Means based on a Compromise in Updating Membership Degrees

A Learning Scheme to Fuzzy C-Means based on a Compromise in ...

引用

IEEE International Conference on Fuzzy Systems

作者： Shang-Lin Wu Yang-Yin Lin Yu-Ting Liu Chih-Yu Chen Chin-Teng Lin Institute of Electrical Control Engineering National Chiao Tung University Brain Research Center National Chiao Tung University Institute of Biomedical Engineering National Chiao Tung University

ISBN: (纸本)9781479920747

关键词： Fuzzy C-Means (FCM) Clustering Data classification high computational complexity Long execution time

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：