Spatial-temporal Channel Research Articles

Lightweight TCN-Based Spatial-Temporal Channel Extrapolation for RIS-Aided Communication

Lightweight TCN-Based Spatial-Temporal Channel Extrapolation for RIS-Aided Communication

Counting piglet suckling events using deep learning-based action density estimation

Analysis of piglet suckling behaviour is important for the evaluation of piglet nutrient ingestion, health, welfare, and affinity with the sow. In this study, an action density estimation network (ADEN) was proposed for counting the events of piglet suckling followed by automated analysis of suckling behaviour. ADEN is a two-stream network primarily composed of 1) a network stream that processes video images with a higher frame rate (faster stream) and 2) a network stream that processes video images with a lower frame rate (slower stream). Each stream consists of a ResNet-50 with five convolutional stages. A multi-stage attention connection (MSAC), composed of four Spatial-Temporal-Channel (STC) multi-attention structures, is proposed to bridge Faster Stream and Slower Stream and capture discriminative features. The output attention features from each faster stream stage are laterally fused into the corresponding slower stream stage in a concatenating manner. Following this, the features from the last convolutional stages in the Slow stream and Fast stream are fused using concatenation and are then decoded by using three convolutional layers. The last convolutional layer outputs a heatmap on the action density of piglet suckling behaviour. Finally, the number of suckling events is predicted by integrating all the pixel values in the heatmap. Experimental and comparative tests were conducted to validate the effectiveness of the proposed ADEN with a training dataset and a test dataset from 14 pig pens. The 507 video clips (126,750 images for 7 h) from the 1-9th pens were selected as training datasets. The 143 video clips (35,750 images for 2 h) from the 10-13th pens were selected as short-term test datasets. One untrimmed video (162,000 images for 9 h) from the 14th pen was used to ultimately evaluate the action density estimation performance of the ADEN. ADEN was compared with seven approaches and its superiority was demonstrated with an r = 0.938, an RMSE = 1.080, and a MAE = 0.967 in short video clips and r = 0.982, MAE = 0.161, and RMSE = 0.563 in the untrimmed long video. The ADEN proved it feasible to predict the number of suckling events by using action density estimation.

Channel attention-based spatial-temporal graph neural networks for traffic prediction

PurposeTraffic flow prediction has always been a top priority of intelligent transportation systems. There are many mature methods for short-term traffic flow prediction. However, the existing methods are often insufficient in capturing long-term spatial-temporal dependencies. To predict long-term dependencies more accurately, in this paper, a new and more effective traffic flow prediction model is proposed.Design/methodology/approachThis paper proposes a new and more effective traffic flow prediction model, named channel attention-based spatial-temporal graph neural networks. A graph convolutional network is used to extract local spatial-temporal correlations, a channel attention mechanism is used to enhance the influence of nearby spatial-temporal dependencies on decision-making and a transformer mechanism is used to capture long-term dependencies.FindingsThe proposed model is applied to two common highway datasets: METR-LA collected in Los Angeles and PEMS-BAY collected in the California Bay Area. This model outperforms the other five in terms of performance on three performance metrics a popular model.Originality/value(1) Based on the spatial-temporal synchronization graph convolution module, a spatial-temporal channel attention module is designed to increase the influence of proximity dependence on decision-making by enhancing or suppressing different channels. (2) To better capture long-term dependencies, the transformer module is introduced.

Graph convolutional network with STC attention and adaptive normalization for skeleton-based action recognition

ABSTRACT Graph Convolutional Network (GCN) have been widely used in the field of skeleton-based action recognition and have achieved exciting results. Introducing attention mechanism in the process of extracting skeleton features has always been a hot spot in GCN-related research. In this article, we design a new graph convolutional network, which combines the advanced decoupling graph convolutional network (DC-GCN) with spatial, temporal, channel (STC) series attention module and adaptive normalization (AN). The STC attention module helps the network tend to extract important information from skeleton features. In addition, in order to improve the adaptability of the normalization method to GCN, we design the AN module instead of the BN module, which can train the weights of different normalization methods, so that each normalization layer in the network adopts the most suitable normalization operation. The experimental results show that the accuracy of our method is competitive with the state-of-the-art action recognition methods.

Light-efficient channel attention in convolutional neural networks for tic recognition in the children with tic disorders.

Tic is a combination of a series of static facial and limb movements over a certain period in some children. However, due to the scarcity of tic disorder (TD) datasets, the existing work on tic recognition using deep learning does not work well. It is that spatial complexity and time-domain variability directly affect the accuracy of tic recognition. How to extract effective visual information for temporal and spatial expression and classification of tic movement is the key of tic recognition. We designed the slow-fast and light-efficient channel attention network (SFLCA-Net) to identify tic action. The whole network adopted two fast and slow branch subnetworks, and light-efficient channel attention (LCA) module, which was designed to solve the problem of insufficient complementarity of spatial-temporal channel information. The SFLCA-Net is verified on our TD dataset and the experimental results demonstrate the effectiveness of our method.

Sign Language Recognition Based on R(2+1)D With Spatial–Temporal–Channel Attention

Previous work utilized three-dimensional (3-D) convolutional neural networks (CNNs) tomodel the spatial appearance and temporal evolution concurrently for sign language recognition (SLR) and exhibited impressive performance. However, there are still challenges for 3-D CNN-based methods. First, motion information plays a more significant role than spatial content in sign language. Therefore, it is still questionable whether to treat space and time equally and model them jointly by heavy 3-D convolutions in a unified approach. Second, because of the interference from the highly redundant information in sign videos, it is still nontrivial to effectively extract discriminative spatiotemporal features related to sign language. In this study, deep R(2+1)D was adopted for separate spatial and temporal modeling and demonstrated that decomposing 3-D convolution filters into independent spatial and temporal convolutions facilitates the optimization process in SLR. A lightweight spatial–temporal–channel attention module, including two submodules called channel–temporal attention and spatial–temporal attention, was proposed to make the network concentrate on the significant information along spatial, temporal, and channel dimensions by combining squeeze and excitation attention with self-attention. By embedding this module into R(2+1)D, superior or comparable results to the state-of-the-art methods on the CSL-500, Jester, and EgoGesture datasets were obtained, which demonstrated the effectiveness of the proposed method.

Deep-Learning-Based Spatial–Temporal Channel Prediction for Smart High-Speed Railway Communication Networks

Intelligent channel prediction plays a key role in artificial intelligence (AI)-optimized or AI-native communication networks for smart high-speed railways (HSRs). This paper investigates the spatial-temporal prediction of channel state information (CSI) and channel statistical characteristics (CSCs) based on deep-learning (DL) for the future smart HSR communication network. A propagation-graph simulation method is used to generate datasets of CSI and CSCs for massive multiple-input multiple-output (mMIMO) channels in a HSR cutting scenario, and realistic channel measurements are used to validate the datasets. Then, single-step ahead and multi-step ahead prediction problems are formulated with the consideration of both spatial and temporal information hidden in the datasets. By exploiting the temporal and spatial correlations of the HSR mMIMO channel, a novel spatial-temporal channel prediction model that combines the convolutional neural network (CNN) and convolutional long short-term memory (CLSTM) is proposed and called as Conv-CLSTM. Moreover, the hyper-parameters of the Conv-CLSTM model are determined by autocorrelation and similarity analysis and cross-validation. Finally, the performance of the Conv-CLSTM model is evaluated in terms of prediction accuracy and space and time computational complexity, and is compared with classical DL models. The evaluation results show that the proposed model has high prediction accuracy but acceptable computational complexity.

A Channel-Wise Spatial-Temporal Aggregation Network for Action Recognition

A very challenging task for action recognition concerns how to effectively extract and utilize the temporal and spatial information of video (especially temporal information). To date, many researchers have proposed various spatial-temporal convolution structures. Despite their success, most models are limited in further performance especially on those datasets that are highly time-dependent due to their failure to identify the fusion relationship between the spatial and temporal features inside the convolution channel. In this paper, we proposed a lightweight and efficient spatial-temporal extractor, denoted as Channel-Wise Spatial-Temporal Aggregation block (CSTA block), which could be flexibly plugged in existing 2D CNNs (denoted by CSTANet). The CSTA Block utilizes two branches to model spatial-temporal information separately. In temporal branch, It is equipped with a Motion Attention Module (MA), which is used to enhance the motion regions in a given video. Then, we introduced a Spatial-Temporal Channel Attention (STCA) module, which could aggregate spatial-temporal features of each block channel-wisely in a self-adaptive and trainable way. The final experimental results demonstrate that the proposed CSTANet achieved the state-of-the-art results on EGTEA Gaze++ and Diving48 datasets, and obtained competitive results on Something-Something V1&V2 at the less computational cost.

Measurements and Analysis of Radio Propagation at 28 GHz in Vegetated Areas of Typical Residential Environments

This communication presents foliage channel measurements at 28 GHz using a directional channel sounder. The measurements were conducted in vegetated areas of typical residential environments in Daejeon, South Korea. We first propose a pattern matching algorithm that allows us to overcome the angle resolution of a directional antenna and to estimate a more accurate receiving angle. Then propagation paths received from the vegetation and the surrounding buildings are classified and their power ratios are analyzed. Furthermore, foliage attenuation was determined from the measurement data according to the foliage depth, and appropriate models based on the modified exponential decay (MED) model and the maximum attenuation (MA) model are presented. In addition, the effect of foliage attenuation on seasonal variation is studied. These results will be useful for predicting path losses through the vegetated areas at 28 GHz by modeling the foliage loss as an additional path loss term. Finally, spatial-temporal channel characteristics in a vegetated environment were statistically analyzed including delay spread, coherence bandwidth, and angular spreads.

Measurements and analyses of 28 GHz indoor channel propagation based on a synchronized channel sounder using directional antennas

This paper presents measurements and analyses of channel propagation to investigate the channel characteristics of the millimeter wave for the indoor mobile communication system. The candidate for the promising carrier frequency is 28 GHz. We conducted the measurements considering conditions for the line of sight and the obstructed line of sight. The measurement points are located in a typical office room that is one of the main scenarios for the channel model. For channel propagation analysis, a novel channel sounder with a time synchronization scheme is introduced to combine channel measurements from different directions using an automatic scanning measurement system. With this system, omni-like power delay profiles of 28 GHz communication was successfully obtained. Furthermore, we analyze the spatial-temporal channel characteristics of an indoor environment such as path loss, delay and angular distributions, delay and angular spreads, and cross-correlation between the large-scale channel parameters.

Opportunistic Spectrum Access for CR-VANETs: A Game-Theoretic Approach

In this paper, we investigate the opportunistic spectrum access for cognitive radio vehicular ad hoc networks. The probability distribution of the channel availability is first derived through a finite-state continuous-time Markov chain, jointly considering the mobility of vehicles and the spatial distribution and temporal channel usage pattern of primary transmitters. Utilizing the channel availability statistics, we propose a game-theoretic spectrum access scheme for vehicles to opportunistically access licensed channels in a distributed manner. In particular, the spectrum access process is modeled as a noncooperative congestion game. The existence of the Nash equilibrium (NE) is proved, and its efficiency is analyzed when employing the uniform medium access control protocol and slotted ALOHA, respectively. Furthermore, a spectrum access algorithm is devised to achieve a pure NE with high efficiency and fairness. Simulation results validate our analysis and demonstrate that the proposed spectrum access scheme can achieve higher utility and fairness, compared with a random access scheme.

Noncoherent OSTBC-OFDM for MIMO and Cooperative Communications: Perfect Channel Identifiability and Achievable Diversity Order

This paper considers the context of orthogonal space-time block coded OFDM (OSTBC-OFDM) without channel state information at the receiver. Assuming noncoherent maximum-likelihood detection, the interest herein lies in detection within one OSTBC-OFDM block, motivated by its capability of accommodating relatively fast block fading channels. Our investigation focuses on analysis aspects, where we seek to establish practical noncoherent BPSK/QPSK OSTBC-OFDM schemes that have provably good channel identifiability and diversity properties. We consider perfect channel identifiability (PCI), a strong condition guaranteeing unique noncoherent channel identification for any (nonzero) channel. Through a judicious design involving special OSTBCs and pilot placement, we propose an OSTBC-OFDM scheme that is PCI-achieving and consumes fewer pilots compared to conventional pilot-aided channel estimation methods. We further our analysis by showing that a PCI-achieving scheme also achieves maximal noncoherent spatial diversity for the Kronecker Gaussian spatial-temporal channel fading model, which covers the popular i.i.d. Rayleigh fading channel and a variety of correlated and sparse multipath channels. All these results are developed in parallel for the centralized point-to-point MIMO scenario and a distributed relay communication scenario. For the latter scenario, our diversity analysis shows that the PCI-achieving scheme can also achieve maximal noncoherent cooperative diversity. The performance merits of the proposed PCI-achieving scheme are demonstrated by simulations.

Abnormal Achromatic and Chromatic Contrast Sensitivity in Neurofibromatosis Type 1

Neurofibromatosis type 1 (NF1) is a monogenic disorder with the majority of patients presenting subtle to moderate cognitive impairments. Visuospatial deficits are considered to be one of the hallmark characteristics of their cognitive profile. However, low-level visual processing has not been previously investigated. Our aim was to study contrast perception in these patients to assess the function of early visual areas. Contrast sensitivity was tested in 19 children and adolescents with NF1 and 33 control children and adolescents and 12 adults with NF1 and 24 control adults. The tasks used probed two achromatic spatiotemporal frequency channels and chromatic red-green and blue-yellow pathways. Individuals with NF1 showed significant contrast sensitivity deficits for the achromatic higher spatial frequency channel [F(₁,₈₃) = 36.1, P < 0.001] and for the achromatic low spatial high temporal (magnocellular) frequency channel [F(₁,₇₂) = 8.0, P < 0.01]. Furthermore, individuals with NF1 presented a significant deficit in chromatic red-green (parvocellular) contrast sensitivity (P < 0.01) but not in blue-yellow (koniocelular) sensitivity. The decrease in achromatic sensitivity for higher spatial frequency was observed throughout the visual field, in both central and peripheral locations. In contrast, central contrast sensitivity for the magnocellular-biased condition was relatively preserved and only peripheral sensitivity was affected. Interestingly, the same pattern of deficits was found in both age groups tested. These findings showed that contrast sensitivity is impaired in patients with NF1, associating for the first time abnormal low-level vision to the cognitive profile of this disorder.

A Comprehensive Spatial-Temporal Channel Propagation Model for the Ultrawideband Spectrum 2–8 GHz

Despite the potential for high-speed communications, stringent regulatory mandates on ultrawideband (UWB) emission have hindered its commercial success. By combining resolvable UWB multipath from different directions, multiple-input multiple-output (MIMO) technology can drastically improve link robustness or range. In fact, a plethora of algorithms and coding schemes already exist for UWB-MIMO systems, however these papers use simplistic channel models in simulation and testing. While the temporal characteristics of the UWB propagation channel have been well documented, surprisingly there currently exists but a handful of spatial-temporal models to our knowledge, and only two for bandwidths in excess of 500 MHz. This paper proposes a comprehensive spatial-temporal channel propagation model for the frequency spectrum 2-8 GHz, featuring a host of novel parameters. In order to extract the parameters, we conduct an extensive measurement campaign using a vector network analyzer coupled to a virtual circular antenna array. The campaign includes 160 experiments up to a non line-of-sight range of 35 meters in four buildings with construction material varying from sheetrock to steel.

A macro-cell statistical location estimation method for TD-SCDMA networks

TD-SCDMA is an innovative wireless radio standard for a physical layer 3G air interface, approved as one 3GPP standards by ITU in May 2000. Based on the unique advantages of the physical layer, this paper investigates network-based methods to obtain the angle of arrival (AOA) and time of arrival (TOA) via subspace tracking and channel impulsive estimation. By incorporating the spatial–temporal channel of radio propagation, this paper proposes a unified objective function to extract mobile location information from the statistical distribution of AOA and TOA data in a TD-SCDMA cellular network. The proposed method may estimate mobile position even using one base station. The location performances are analyzed in detail in macro-cell scenarios. This method can be easily extended to other networks except TD-SCDMA, provided that the statistical information of the local radio propagation channel is available as pre-knowledge. Simulation comparing several hybrid location methods in two macro-cell scenarios show that the proposed method has a high accuracy; but it has a relatively high complexity.

A Comprehensive Evaluation of Joint Range and Angle Estimation in Indoor Ultrawideband Location Systems

Fine time resolution enables ultrawideband (UWB) ranging systems to extract the first multipath arrival corresponding to the range between a transmitter and receiver, even when attenuated in strength compared to later arrivals. Bearing systems alone lack any notion of time and in general select the strongest arrival which is rarely the first one in nonline-of-sight conditions. Complementing UWB ranging systems with bearing capabilities allows indexing the arrivals as a function of both time and angle in order to isolate the first, providing precision range and angle. However, that precision degrades with the increasing presence of walls and other objects which distort the properties of the first arrival. In order to gauge the physical limits of the joint UWB system, we design and assemble a spatial-temporal channel sounder using a vector network analyzer coupled to a virtual antenna array, and conduct 200 experiments to measure the time- and angle-of-flight. The experiments are carried out in both line-of-sight and nonline-of-sight conditions up to an unprecedented 45 meters throughout four separate buildings with dominant wall material varying from sheet rock to steel. In addition, we report performance for varying bandwidth and center frequency of the system. We find that operating at a bandwidth of 4 GHz suffices in resolving multipath in most buildings and in excess shows virtually no improvement. While the range error decreases at lower center frequencies, the higher frequencies offer better angular resolution and so smaller angle error.

A Markov-Kronecker model for analysis of closed-loop MIMO systems

Closed-loop MIMO systems have gained much interest recently due to their ability in improving performance. Although many spatial-temporal MIMO channel models have been proposed, system limitations are not considered and the effects of a time varying channel on MIMO systems with a realistic feedback delay are also not available in an analytically tractable form. In this letter, we propose a composite model where both propagation and system factors are considered thus providing a simple and analytically tractable model for the performance evaluation and design of closed-loop MIMO systems

Capacity, throughput, and delay of slotted ALOHA DS-CDMA links with adaptive space-time auxiliary-vector receivers

We investigate the user capacity, throughput, and delay characteristics of a mobile slotted ALOHA direct-sequence code-division-multiple-access (DS-CDMA) link with dedicated signatures under multipath fading and packet-rate adaptive antenna array signal reception. For a given system transmission bit rate, the packet size is designed to be sufficiently small to conform with the coherence time of the channel. Then, on an individual packet-by-packet basis, a phase-ambiguous spatial-temporal channel estimate is produced by a blind (unsupervised) eigensubspace procedure. The space-time channel estimate is phase corrected via a few pilot packet mid-amble bits and used for joint spatial-temporal multiple-access-interference suppression according to the principles of auxiliary-vector filtering. Subsequently, packet success probabilities are derived in the presence or absence of forward error correction and are used to evaluate the throughput and delay characteristics of the link.

Signal distribution in the azimuth, elevation, and time-delay domains in urban radio communication links

We investigate the mutual power-spectra distributions in the azimuth, elevation, and time-delay domains in different urban environments with randomly distributed arrays of buildings placed on rough terrain. This is done for various orientations of street guiding structures in the urban scene, and for different elevations of the terminal antenna, the base station, and the subscriber, whether mobile or not, and with respect to the buildings' overlay profile. A combination of the stochastic multi-parametric and crossing-street waveguide models, created earlier, is used to describe a total probability-density function (PDF) of mutual azimuth time-delay, elevation time-delay, and azimuth-elevation distribution of multiply reflected signals arriving at the receiver after multiple reflection, diffraction, and scattering from the numerous obstructions surrounding both terminal antennas. Comparisons with some high-resolution three-dimensional measurements, as well as with the corresponding three-dimensional numerical ray-tracing model, are done to describe directional and spatial-temporal urban channel characteristics, and to predict propagation situations in the urban scene for various locations and directional properties of the terminal antennas.