检索结果-内蒙古大学图书馆

Light-Field Imaging Reconstruction Using Deep Learning Enabling Intelligent Autonomous Transportation System

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第2期23卷 1587-1595页

作者： Silva, Juan Casavilca Saadi, Muhammad Wuttisittikulkij, Lunchakorn Militani, Davi Ribeiro Rosa, Renata Lopes Rodriguez, Demostenes Zegarra Al Otaibi, Sattam Pontificia Univ Catolica Peru Dept Sci Lima 15088 Peru Univ Cent Punjab Dept Elect Engn Fac Engn Lahore 54000 Pakistan Chulalongkorn Univ Dept Elect Engn Wireless Commun Ecosyst Res Unit Bangkok 10330 Thailand Univ Fed Lavras Dept Comp Sci BR-37200000 Lavras Brazil Taif Univ Dept Elect Engn Coll Engn At Taif 21944 Saudi Arabia

Light-field (LF) cameras, also known as plenoptic cameras, permit the recording of the 4D LF distribution of target scenes. However, many times, surface errors of a microlens array (MLA) are responsible for degradation in the images captured by a plenoptic camera. Additionally, the limited pixel count of the sensor can cause missing parallax information. The aforementioned issues are crucial for creating accurate maps for Intelligent Autonomous Transport System (IATS), because they cause loss of LF information, and need to be addressed. To tackle this problem, a learning-based framework by directly simulating the LF distribution is proposed. A high-dimensional convolution layer with densely sampled LFs in 4D space and considering a soft activation function based on ReLU segmentation correction is used to generate a superresolution (SR) LF image, improving the convergence rate in the deep learning network. Experimental results show that our proposed LF image reconstruction framework outperforms the existing state-of-the-art approaches;specifically, it is effective for learning the LF distribution and generating high-quality LF images. Different image quality assessment methods are used to evaluate the performance of the proposed framework, such as PSNR, SSIM, IWSSIM, FSIM, GFM, MDFM, and HDR-VDP. Additionally, the computational efficiency was evaluated in terms of number of parameters and FLOPs, and experimental results demonstrated that our proposed framework reached the highest performance in most of the datasets used.

关键词： Light-field imaging deep learning framework low computational complexity autonomous transportation systems intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Maximum eigenvalue-based target detection for the K-distributed clutter environment

引用

IET RADAR SONAR AND NAVIGATION 2018年第11期12卷 1294-1306页

作者： Zhao, Wenjing Liu, Chang Liu, Wenlong Jin, Minglu Dalian Univ Technol Sch Informat & Commun Engn Dalian Peoples R China Univ Elect Sci & Technol China Natl Key Lab Sci & Technol Commun Chengdu Sichuan Peoples R China

Information geometry-based matrix constant false alarm rate (CFAR) detector is an efficient solution to target detection, especially for the K-distributed clutter environment with respect to a small bunch of pulses. The main reason for the matrix CFAR detector to achieve better detection performance is covariance matrix captures the correlations between the data. However, most existing matrix CFAR detectors suffer from heavy computational complexity, which leads to a limitation in practical detection scenarios. Motivated by this, the authors utilise the eigenvalues of the covariance matrix to capture the correlation and propose an eigenvalue-based detection method with lower computational complexity. Based on the Neyman-Pearson criterion, they first analyse the likelihood ratio test (LRT) in the eigenvalue domain and derive the relationship between the LRT test statistic and the maximum eigenvalue. To meet the practical requirement, they further design a totally blind scheme: the maximum eigenvalue-based matrix CFAR detector. By employing the group invariant theory, they show that the proposed detector presents the CFAR property. In addition, the theoretical performance analysis is also provided. Simulation results based on the numerical experiment and real sea clutter data verify that the proposed method with a low computational complexity can achieve a better detection performance.

关键词： covariance matrices computational complexity radar detection probability geometry object detection eigenvalues and eigenfunctions radar clutter covariance matrix LRT test statistic maximum eigenvalue-based matrix CFAR detector sea clutter data low computational complexity maximum eigenvalue-based target detection information geometry-based matrix constant false alarm rate detector computational complexity K-distributed clutter environment Neyman-Pearson criterion likelihood ratio test

来源：评论

学校读者我要写书评

暂无评论

Data Dissemination Framework Using low-Rank Approximation in Edge Networks

引用

IEEE ACCESS 2024年 12卷 1266-1279页

作者： Kwon, Jungmin Park, Hyunggon Ewha Womans Univ Dept Elect & Elect Engn Seoul 03760 South Korea Ewha Womans Univ Dept Elect & Elect Engn Smart Factory Multidisciplinary Program Seoul 03760 South Korea

This paper proposes a reliable data dissemination framework for edge networks, leveraging network coding combined with low-rank approximation. We consider an edge network that consists of a server and power-limited mobile devices, where the data is broadcasted by the server. In such networks, broadcasted data may be lost due to poor channel conditions or the interference caused by the mobility of edge mobile devices, particularly without a retransmission mechanism. This can cause application errors in edge devices, lower the Quality of Service (QoS), and compromise network stability. To overcome these challenges, we propose a framework for reliable edge networks in broadcasting without retransmissions. The edge network reliability can be achieved by the approximate decoding of broadcasted data. In the proposed framework, the edge server employs matrix factorization to encode data with principal components, ensuring a lower decoding error rate even with potential packet losses. Furthermore, the proposed framework can shift the computational complexity from mobile edge devices to the edge server using the low-rank approximation at the decoding stage, effectively mitigating power limitations on mobile devices. Through theoretical analysis, we demonstrate that the proposed algorithm outperforms typical broadcasting in terms of decoding accuracy, and present an upper bound error rate for the proposed algorithm. The simulation results confirm that the proposed algorithm outperforms other state-of-the-art algorithms in terms of decoding accuracy, time delay, and complexity.

关键词： Data dissemination edge computing edge network network coding low-rank approximation decoding accuracy low computational complexity complexity shift

来源：评论

学校读者我要写书评

暂无评论

Robust Model Predictive Control of DC-DC Floating Interleaved Boost Converter With Multiple Uncertainties

引用

IEEE TRANSACTIONS ON ENERGY CONVERSION 2021年第2期36卷 1403-1412页

作者： Sartipizadeh, Hossein Harirchi, Farnaz Babakmehr, Mohammad Dehghanian, Payman Univ Texas Austin Inst Computat Engn & Sci Austin TX 78712 USA Clemson Univ Coll Engn & Sci Elect & Comp Engn Clemson SC 29634 USA Washington Univ Elect & Comp Engn Washington DC 20052 USA

DC-DC Floating Interleaved Boost Converter (FIBC) is recently introduced for converting low-level voltage generated by a renewable energy source to high-level voltage required for AC inverters. Although a desired voltage is expected at the output, designing a proper voltage gain for FIBC is challenging due to different types of uncertainties. For instance, the voltage generated by the energy source and, therefore, the input voltage of FIBC may change by a variety of parameters including external load. Furthermore, parametric uncertainty and measurement noise are other sources which can affect the control procedure. As a result, voltage gain for a fixed switching duty cycle may be uncertain. It demands a robust approach to guarantee the control performance under uncertainties without the need for individually tuning controller for each single converter. In this work, a robust model predictive control is employed to regulate the output voltage at the desired level despite the existing uncertainties. Controller parameters are fixed for any FIBC within the uncertainty range and further tuning is not required for individual converters. In addition, unlike the conventional controllers, the suggested controller is able to handle input-output constraints. Performance of the suggested controller is investigated through simulations carried out in MATLAB and the superiority of the proposed approach is verified over non-robust model predictive framework.

关键词： Uncertainty Voltage control Trajectory Measurement uncertainty Tuning Temperature measurement Predictive control Approximate convex hull floating interleaved boost converter low computational complexity measurement uncertainty model uncertainty robust model predictive control

来源：评论

学校读者我要写书评

暂无评论

Fast tracking control of air-breathing hypersonic vehicles with time-varying uncertain parameters

引用

NONLINEAR DYNAMICS 2018年第3期91卷 1835-1852页

作者： An, Hao Wu, Qianqian Xia, Hongwei Wang, Changhong Harbin Inst Technol Space Control & Inertial Technol Res Ctr Harbin 150001 Heilongjiang Peoples R China Harbin Inst Technol Res Ctr Satellite Technol Harbin 150001 Heilongjiang Peoples R China Harbin Inst Technol Ctr Composite Mat & Struct Harbin 150001 Heilongjiang Peoples R China

Despite advantages of air-breathing hypersonic vehicles (AHVs) over turbojet-powered or rocket-powered vehicles, the control system design is still a challenge. In particular, the existing control methods lack an effective mechanism to handle time-varying uncertain parameters in the control-oriented AHV model. This study proposes a longitudinal control strategy for AHVs focusing on time-varying uncertain parameters, fast tracking and low computational complexity. The adaptive law is designed to estimate the norm bound of the vector of uncertain parameters, in which case parametric variations are accommodated with a large reduction on the dimension of the resulting control algorithm. By utilizing sliding mode exact differentiators, the analytic differential computation on virtual controls is avoided in the adaptive back-stepping design for altitude tracking. It is shown that both velocity and altitude tracking errors converge into the prescribed sets in finite time. A simulation study on the high-fidelity AHV model is provided to verify the proposed control strategy.

关键词： Air-breathing hypersonic vehicle Fast adaptive tracking Time-varying uncertain parameter External disturbance low computational complexity

来源：评论

学校读者我要写书评

暂无评论

A low-complexity Laguerre wideband beamformer

引用

DIGITAL SIGNAL PROCESSING 2018年 83卷 35-44页

作者： Zhang, Shurui Sheng, Weixing Han, Yubing Ma, Xiaofeng Kirubarajan, Thia Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing Jiangsu Peoples R China McMaster Univ Dept Elect & Comp Engn Hamilton ON Canada

Laguerre spatial-temporal processing is a well-known method used to design a wideband beamformer. In this paper, a generalized wideband reduced-rank Laguerre beamformer (RRLB) is proposed. The RRLB uses a reduced-rank transform matrix to estimate the signal subspace and reduces the scale of the received data, which reduces the complexity of obtaining the adaptive weights. The reduced-rank matrix is usually constructed by the eigenvector of the covariance matrix, while the eigenvectors are obtained via eigen decomposition with a high computational load. To reduce the complexity of eigen-decomposition, a fast reduced-rank Laguerre beamforming (FRRLB) algorithm is proposed. In the estimated covariance matrix case, a set of received data vectors is used to construct the reduced-rank matrix for an approximate but fast estimate of the interference subspace. With undistorted response to the desired signal and satisfactory anti-jamming capability, the FRRLB reduces the computational complexity of the adaptive weight approach. The simulation results highlight the validity and effectiveness of the proposed methods. (C) 2018 Elsevier Inc. All rights reserved.

关键词： Wideband beamforming Spatial-temporal processing Laguerre beamformer low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Efficient T-EMS Based Decoding Algorithms for High-Order LDPC Codes

引用

IEEE ACCESS 2019年 7卷 50980-50992页

作者： Tian, Jing Song, Suwen Lin, Jun Wang, Zhongfeng Nanjing Univ Sch Elect Sci & Engn Nanjing 210023 Jiangsu Peoples R China

Non-binary low-density parity-check (NB-LDPC) codes show larger coding gain and lower error floor than their binary counterparts in many cases. However, the existing soft decoding algorithms of NB-LDPC codes generally suffer from high computational complexity. Recently, the trellis-based extended min-sum (T-EMS) decoding algorithm has attracted much attention since it can achieve good decoding performance with high parallelism and low computational complexity. In this paper, we propose two new methods to further reduce the computational complexity and enhance the decoding performance. Firstly, we introduce, with theoretical justification, a universal scheme called threshold-based shrinking (TS) scheme, which facilitates significant reduction of computational complexity for decoding of NB-LDPC codes. Secondly, we present a modified two-extra-column (TEC) scheme and apply it to the T-EMS. Furthermore, a high-performance low-complexity decoding algorithm, named TEC-TEMS algorithm, is obtained. Combining the TS scheme with the TEC-TEMS, the new algorithm, named TS-TEC-TEMS algorithm, achieves much lower computational complexity and has negligible performance loss compared to the TEC-TEMS. For a 256-ary (256, 203) example code, compared to the T-EMS, the computational complexities of the TEC-TEMS and TS-TEC-TEMS algorithms are reduced by more than 50% and nearly 90%, respectively. Moreover, the TEC-TEMS and TS-TEC-TEMS both outperform the T-EMS by about 0.3dB when the frame error rate (FER) is around 10(-5).

关键词： Error correction codes nonbinary low-density parity-check (NB-LDPC) codes min-sum decoding algorithm low computational complexity forward error correction (FEC)

来源：评论

学校读者我要写书评

暂无评论

Broadcast Levels: Efficient and Lightweight Schedule Construction for Push-Based Data Broadcasting Systems

引用

IEEE TRANSACTIONS ON BROADCASTING 2015年第3期61卷 470-481页

作者： Mavridopoulos, Stathis Nicopolitidis, Petros Papadimitriou, Georgios Sarigiannidis, Panagiotis Aristotle Univ Thessaloniki Dept Informat Thessaloniki 54124 Greece Univ Western Macedonia Dept Informat & Telecommun Engn Kozani 50100 Greece

In wireless push-based systems traffic is asymmetric meaning that the server has much more bandwidth available, as compared to the clients. Since it is often not possible or desirable for the clients to send any requests, the server should broadcast the data periodically. The performance of this system relies heavily on the proper scheduling of the broadcast data. The well known algorithm proposed by Vaidya and Hameed battles this challenge and achieves state-of-the-art performance. However, this performance comes with a computational complexity linear to the number of data items that are broadcast. Furthermore, Vaidya's and Hameed's proposed solution for this time complexity degenerates performance. This paper proposes a scheduling algorithm for wireless push-based data broadcasting systems, which performs near optimal and has low computational complexity. Performance evaluation results are presented to demonstrate its efficient performance despite its low computational demands.

关键词： Broadcast push-based system wireless low computational complexity adaptive multiple channels

来源：评论

学校读者我要写书评

暂无评论

Hardware Resource Optimized Detection of LFM Signals with Unknown Start Frequency and Frequency Rate

引用

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2020年第6期92卷 541-553页

作者： Shokouhmand, Arash Norouzi, Yaser Oveis, Amir H. Dezfuli, Ali A. Amirkabir Univ Technol Tehran Iran Ferdowsi Univ Mashhad Mashhad Razavi Khorasan Iran

Detection of very low-SNR LFM signals with unknown start frequency and frequency rate is of great interest both in electronic support measure (ESM), and radio astronomy. The direct method for LFM signal detection needs a bank of matched-filters which is a really hardware consuming solution. As another solution, a bank of de-ramping blocks, followed by FFT units, can be used with the same performance as matched-filters bank. In such an alternative solution, with no optimization constraint, it is quite likely to reach a hardware extensive solution with limited processing gain. In this paper, a novel method based on de-ramping bank is proposed. Also, an optimization problem is developed, which could determine the optimum values for detection structure's parameters, e.g. number of channels, as well as FFT length. It is shown that, the optimized detector features better processing gain in comparison to the non-optimized versions. Furthermore, adding a moving average at the output of the FFT could make remarkable improvement on detection performance. Moreover, the proposed detector is compared against the conventional methods in terms of detection performance and computational complexity characteristic, which aptly prove the superiority of the proposed method.

关键词： LFM signal LPI detection Hardware-optimized implementation low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Speech Enhancement Using MLP-Based Architecture With Convolutional Token Mixing Module and Squeeze-and-Excitation Network

引用

IEEE ACCESS 2022年 10卷 119283-119289页

作者： Song, Hyungchan Kim, Minseung Shin, Jong Won Gwangju Inst Sci & Technol Sch Elect Engn & Comp Sci Gwangju 61005 South Korea

The Conformer has shown impressive performance for speech enhancement by exploiting the local and global contextual information, although it requires high computational complexity and many parameters. Recently, multi-layer perceptron (MLP)-based models such as MLP-mixer and gMLP have demonstrated comparable performances with much less computational complexity in the computer vision area. These models showed that all-MLP architectures may perform as good as more advanced structures, but the nature of the MLP limits the application of these architectures to the input with a variable length such as speech and audio. In this paper, we propose the cgMLP-SE model, which is a gMLP-based architecture with convolutional token mixing modules and squeeze-and-excitation network to utilize both local and global contextual information as in the Conformer. Specifically, the token-mixing modules in gMLP are replaced by convolutional layers, squeeze-and-excitation network-based gating is applied on top of the convolutional gating module, and additional feed-forward layers are added to make the cgMLP-SE module a macaron-like structure sandwiched by feed-forward layers like a Conformer block. Experimental results on the TIMIT-DNS noise dataset and the Voice Bank-DEMAND dataset showed that the proposed method exhibited similar speech quality and intelligibility to the Conformer with a smaller model size and less computational complexity.

关键词： Speech enhancement local and global information low computational complexity

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：