检索结果-内蒙古大学图书馆

Joint User Activity Identification and Channel Estimation for Grant-Free NOMA: A spatial-temporal structure-Enhanced Approach

引用

IEEE INTERNET OF THINGS JOURNAL 2021年第15期8卷 12339-12349页

作者： Wu, Liantao Sun, Peng Wang, Zhibo Yang, Yang ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China Chinese Univ Hong Kong Sch Sci & Engn Shenzhen 518172 Peoples R China Shenzhen Inst Art Intelligence & Robot Soc Shenzhen 518172 Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310027 Peoples R China ShanghaiTech Univ Shanghai Inst Fog Comp Technol Shanghai 201210 Peoples R China Res Ctr Network Commun Peng Cheng Lab Shenzhen 518000 Peoples R China

Exploiting the sparse nature of user activity, compressed sensing (CS) has been a powerful technique to realize efficient user detection in grant-free nonorthogonal multiple access (NOMA). However, most of the existing CS-based multiuser detection schemes merely independently incorporate the temporal correlation in frame-based transmission or spatial correlation induced by multiantenna reception, leading to unsatisfactory user detection performance. Driven by the observation in the CS theory that the signal recovery performance could be enhanced by an increased number of sparse vectors with a common support set, in this article, we propose a novel joint user activity identification and channel estimation (JUICE) framework by integrating the temporal correlation of active user sets with multiantenna reception, which could achieve superior user detection performance. Specifically, we first formulate the JUICE as a Kronecker CS (KCS) problem to model the CS measurement process, by fully extracting the spatial-temporal structure of user activity. Then, based on the mined spatial-temporal structure of user activity, an adaptive subspace pursuit algorithm is developed, i.e., spatial-temporal structure enhanced adaptive subspace pursuit (STS-ASP), which could realize efficient multiuser detection. A distinct advantage of the proposed algorithm is that it does not require any prior knowledge (e.g., the number of active users and the noise level), by adaptively acquiring the number of active users and employing the cross-validation technique to appropriately terminate the iterative procedures. Extensive experimental evaluation is conducted, and the results corroborate the superiority of the proposed framework compared with the existing CS-based multiuser detection methods.

关键词： NOMA Transmitting antennas Correlation Channel estimation Slot antennas Multiuser detection Antenna measurements Adaptive compressed sensing (CS) channel estimation grant-free nonorthogonal multiple access (NOMA) spatial-temporal structure user activity identification

来源：评论

学校读者我要写书评

暂无评论

ENHANCING QUALITY FOR VVC COMPRESSED VIDEOS BY JOINTLY EXPLOITING spatial DETAILS AND temporal structure 26

ENHANCING QUALITY FOR VVC COMPRESSED VIDEOS BY JOINTLY EXPLO...

引用

26th IEEE International Conference on Image Processing (ICIP)

作者： Meng, Xiandong Deng, Xuan Zhu, Shuyuan Zeng, Bing Hong Kong Univ Sci & Technol Hong Kong Peoples R China Univ Elect Sci & Technol China Hefei Anhui Peoples R China

ISBN: (纸本)9781538662496

In this paper, we propose a quality enhancement network of versatile video coding (VVC) compressed videos by jointly exploiting spatial details and temporal structure (SDTS). The proposed network consists of a temporal structure fusion subnet and a spatial detail enhancement subnet. The former subnet is used to estimate and compensate the temporal motion across frames, and the latter subnet is used to reduce the compression artifacts and enhance the reconstruction quality of compressed video. Experimental results demonstrate the effectiveness of our SDTS-based method.

关键词： versatile video coding spatial-temporal structure motion compensation quality enhancement

来源：评论

学校读者我要写书评

暂无评论

Assessment of summer monsoon precipitation derived from five reanalysis datasets over East Asia

引用

QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY 2016年第694期142卷 108-119页

作者： Huang, Dan-Qing Zhu, Jian Zhang, Yao-Cun Huang, Ying Kuang, Xue-Yuan Nanjing Univ Sch Atmospher Sci 163 Xianlin Ave Nanjing 210023 Jiangsu Peoples R China Hohai Univ State Key Lab Hydrol Water Resources & Hydraul En Nanjing Jiangsu Peoples R China

Precipitation, which is the predominant component of the East Asian summer monsoon (EASM), may have large uncertainties among reanalysis datasets. We comprehensively evaluate the performance of five reanalysis datasets in reproducing the EASM precipitation. These datasets are NCEP/NCAR Reanalysis 1 project (NCEP1), NCEP/US Department of Energy Atmospheric Model Intercomparison Project II reanalysis (NCEP2), Japanese 25-year Reanalysis project (JRA-25), Interim ECMWF Reanalysis (ERA-Interim), and Modern Era Retrospective-analysis for Research and Applications (MERRA). Results show that the five reanalysis datasets can generally reproduce the climatology and interannual variability of EASM precipitation. Especially, MERRA and ERA-Interim have the highest skills. Considering different-class precipitation, large uncertainties exist in the category of non-rainfall and heavy rainfall. The five reanalysis datasets overestimate the non-rainfall frequency, and JRA-25 and NCEP2 overestimate the heavy rainfall frequency. The well-known interdecadal variation around the mid-1990s can also be better depicted by ERA-Interim and MERRA. For the linear trend of precipitation, only MERRA can reasonably reproduce the increasing tendency over southern China and the western Pacific and the decreasing tendency over the Indo-China Peninsula. Based on EOF analysis, the spatial-temporal structure of EASM precipitation has been examined. MERRA, NCEP1 and ERA-Interim can better capture both the spatial patterns and principle components of the first two EOF modes. Based on our evaluation, the preferential reanalysis datasets for investigating the EASM precipitation are ERA-Interim and MERRA, which also permit the more precise investigation of interannual to decadal variability.

关键词： reanalysis datasets East Asian summer monsoon precipitation different-class precipitation spatial-temporal structure

来源：评论

学校读者我要写书评

暂无评论

The performance evaluation of spatial-temporal algorithms in W-CDMA systems

引用

INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS 2005年第8期18卷 731-741页

作者： Jeng, SS Tsung, CW Natl Dong Hwa Univ Dept Elect Engn Hualien 974 Taiwan

Differing from FDMA, TDMA, and CDMA, space division multiple access (SDMA) uses space resources to improve communication system performance. Utilizing the smart antenna system is an approach to realize the SDMA technique. Smart antenna systems using the beamforming technique can reduce the co-channel interference and multipath fading to increase the channel capacity and communication quality. In this study the smart antenna system and rake receiver are integrated. The performance of spatial-temporal structure applied to the W-CDMA system is evaluated. From the cumulative distribution function simulation results, W-CDMA system with spatial-temporal algorithm can exactly provide SINR gain to improve the system performance and capacity. Copyright (c) 2005 John Wiley & Sons, Ltd.

关键词： SDMA smart antenna system spatial-temporal structure W-CDMA

来源：评论

学校读者我要写书评

暂无评论

Seasonal response of fish assemblages to habitat fragmentation caused by an impoundment in a Neotropical river

引用

ENVIRONMENTAL BIOLOGY OF FISHES 2013年第12期96卷 1377-1387页

作者： Iacone Santos, A. B. Albieri, R. J. Gerson Araujo, F. Univ Fed Rural Rio de Janeiro Lab Ecol Peixes BR-23851970 Rio De Janeiro RJ Brazil

Changes in fish assemblages between the zones above and below Funil dam in Southeastern Brazil were investigated to evaluate the possible impacts of this impoundment in two contrasting seasons: summer/wet and winter/dry. We expect differences in fish assemblage structure and in environmental conditions between seasons and between the reservoir and the zone downriver of the dam. A total of 3,579 individuals comprising 38 species, including six non-natives, were collected. As expected, the comparatively high habitat complexity and water flow regime of the downriver zone favored a richer and more abundant fish assemblage compared with the reservoir, especially in the wet season. In this period, water covers part of the riparian vegetation, increasing habitat availability and nutrient input. Additionally, the dam prevents upriver migration of rheophilics fish species such as the Characiformes Prochilodus lineatus and Leporinus copelandii, and the Siluriformes Pimelodus fur and Pimelodus maculatus, thus increasing shoals below the dam. Although the reservoir represents a simplified ecosystem highly influenced by non-native top predator species (e.g. the Perciformes Cichla kelberi and Plagioscion squamosissimus), seasonal processes (e.g. water level fluctuations and flood pulses) seem to play a role in structuring of the fish assemblage. Environmental variables, mainly turbidity, temperature, and conductivity were significantly associated to spatial-temporal patterns of fish assemblage. In this freshwater tropical reservoir, the spatial scale, rather than the seasonal changes in environmental variables, was the dominant factor structuring fish assemblage in the reservoir and in the zone downriver of the dam.

关键词： Funil reservoir Paraiba do Sul River Ichthyofauna spatial-temporal structure Dams River fragmentation

来源：评论

学校读者我要写书评

暂无评论

STEREOSCOPIC VIDEO QUALITY ASSESSMENT MODEL BASED ON spatial-temporal STRUCTURAL INFORMATION

STEREOSCOPIC VIDEO QUALITY ASSESSMENT MODEL BASED ON SPATIAL...

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Han, Jingjing Jiang, Tingting Ma, Siwei Peking Univ Sch EECS Natl Engn Lab Video Technol Key Lab Machine Percept MOE Beijing 100871 Peoples R China

ISBN: (纸本)9781467344050;9781467344067

Most of the existing 3D video quality assessment methods estimate the quality of each view independently and then pool them into unique objective score. Besides, they seldom take the motion information of adjacent frames into consideration. In this paper, we propose an effective stereoscopic video quality assessment method which focuses on the inter-view correlation of spatial-temporal structural information extracted from adjacent frames. The metric jointly represents and evaluates two views. By selecting salient pixels to be processed and discarding the others, the processing speed is significantly improved. Experimental results on our stereoscopic video database show that the proposed algorithm correlates well with subjective scores.

关键词： Stereoscopic video quality assessment spatial-temporal structure inter-view correlation human-visual system (HVS) asymmetric coding

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition with Identity and spatial-temporal Integrated Learning 8

Facial Expression Recognition with Identity and Spatial-temp...

引用

8th International Conference on Affective Computing and Intelligent Interaction (ACII)

作者： Teng, Halting Zhang, Dong Li, Ming Huang, Yudong Sun Yat Sen Univ Sch Elect & Informat Technol Guangzhou Peoples R China Duke Kunshan Univ Kunshan Peoples R China

ISBN: (纸本)9781728138916

spatial-temporal structure of expression frames plays a critical role in the task of video based facial expression recognition (FER). In this paper, we propose a 3D CNN based framework to learn the spatial-temporal structure from expression frames for video-based FER. First, we use the data labeled with identities to train an identity network to capture the facial biometric features from expression frames. Second, we remove the impact of facial biometric features from the expression features and construct typical facial expression (TFE) features. Then, we feed the TFE features to a 3D network to discover spatial-temporal structure of expression frames. In the end, we feed the spatial-temporal vector to a fully-connected layer to get a vector for classification. The proposed method achieves comparable accuracy with the state-of-art of 88.54% on Oulu-CASIA, and is efficient to be used for the task of video-based FER.

关键词： Facial expression recognition identity spatial-temporal structure 3D convolution

来源：评论

学校读者我要写书评

暂无评论

MixHop Graph WaveNet for Traffic Forecasting 40th

MixHop Graph WaveNet for Traffic Forecasting

引用

40th National Conference of Theoretical Computer Science (NCTCS)

作者： Ba, Bing Fu, Qi Hang, Chongjing Jiang, YunXia Hunan Univ Sci & Technol Xiangtan Peoples R China

ISBN: (纸本)9789811981517;9789811981524

Traffic forecasting is fundamental to realizing intelligent transportation systems (ITS) and challenging due to the complicated spatial dependencies of traffic data and nonlinear temporal trends. Graph convolutional networks (GCNs) have been employed in the latest studies to capture the intricate spatial relationships of roadways. However, due to the intrinsic restrictions of traditional GCNs, these methods cannot represent high-order or mixed neighborhood information. TheMixHop GraphWaveNet (MH-GWN), a novel graph neural network architecture for traffic forecasting, is proposed in this research. In MH-GWN, a spatial-temporal convolutional layer that effectively integrates the MixHop graph convolutional layer and the dilated causal convolutional layer is designed, which can aggregate arbitrary-order neighborhood information and model the complex spatial-temporal dependencies of traffic data. Furthermore, via stacking spatial-temporal convolutional layers, the model's receptive field in the spatial-temporal domain can be exponentially improved. Extensive experiments on two real-world road network traffic datasets show that MH-GWN model is better than other baselines.

关键词： Graph convolution neural network Traffic forecasting MixHop graph convolution spatial-temporal structure

来源：评论

学校读者我要写书评

暂无评论

spatial-temporal Neural Networks for Action Recognition 14th

Spatial-Temporal Neural Networks for Action Recognition

引用

14th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations (AIAI)

作者： Jing, Chao Wei, Ping Sun, Hongbin Zheng, Nanning Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian Peoples R China State Key Lab Math Engn & Adv Comp Wuxi Jiangsu Peoples R China

ISBN: (纸本)9783319920078;9783319920061

Action recognition is an important yet challenging problem in many applications. Recently, neural network and deep learning approaches have been widely applied to action recognition and yielded impressive results. In this paper, we present a spatial-temporal neural network model to recognize human actions in videos. This network is composed of two connected structures. A two-stream-based network extracts appearance and optical flow features from video frames. This network characterizes spatial information of human actions in videos. A group of LSTM structures following the spatial network describe the temporal information of human actions. We test our model with data from two public datasets and the experimental results show that our method improves the action recognition accuracy compared to the baseline methods.

关键词： Action recognition spatial-temporal structure LSTM

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：