Search

The upcoming 5G communication is committed to providing ultra-high throughput and ultra-low delay service. However, digital signal processing technologies will be a critical challenge with the increasing bandwidth and transmitting streams. Especially, traditional fast Fourier transform (FFT) architectures are hard to meet the high-speed, high-performance, and low-overhead requirements. To overcome this issue, this article proposes a reconfigurable hyper-parallel bit-serial (HPBS) FFT processor. A bit-serial paradigm implements the datapath to reduce the hardware cost due to high parallelism as high as 64 to support FFT size from 64 to 2048. The HPBS design brings several significant advantages. Firstly, the hyper-parallel architecture supports large FTT radix with lower computation complexity, e.g., fewer processing stages and constant multipliers than conventional multipliers. Secondly, the bit-serial design enables the hyper-parallel FFT implemented by an acceptable hardware cost. Thirdly, the HPBS design supports the flexible and dynamic adjusting between latency and precision, which provides an additional optimization dimension. Based on the 55-nm process, the proposed 2048-point FFT can provide 32.128 Gbps throughput at 502MHz frequency with an average 12-bit word length. Besides, the normalized hardware efficiency can be up to 46.630 Gbps/mm2, which is at least 2X that of the traditional design.

The pedestrian trajectory prediction is critical for autonomous driving, intelligent navigation, and abnormal behavior detection. With the booming of artificial intelligence (AI), many researchers have employed deep learning technologies to solve the pedestrian trajectory prediction problem and obtained relatively better performance in the short-term trajectory prediction. However, long-term trajectory prediction is still challenging to achieve high prediction accuracy. In this work, we propose a space-time tree search (STTS) method for long-term pedestrian trajectory prediction. Compared with existing methods only considering the problem from the space dimension, the proposed method formulates the trajectory prediction problem as a joint space-time tree search process by mapping the environment to a grid map. Since the human’s trajectory is relative to space and time dimensions, the trajectory prediction accuracy can be improved by the two dimensions. Then, a space-time reward trained neural network is employed to extract the pedestrian’s intent with both the scene image and the historical trajectory as input and outputs the prior search probabilities. Finally, the tree search can obtain the optimal predicted trajectory according to the prior probabilities, significantly improving the tree search efficiency. After testing, our proposed method can perform better than existing methods.

Ultra-densely deploying access points (APs) to support the increasing data traffic would significantly escalate the cell-edge problem resulting from traditional cellular networks. By removing the cell boundaries and coordinating all APs for joint transmission, the cell-edge problem can be alleviated, which in turn leads to unaffordable system complexity and channel measurement overhead. A new scalable clustered cell-free network architecture has been proposed recently, under which the large-scale network is flexibly partitioned into a set of independent subnetworks operating parallelly. In this paper, we study the energy-efficient clustered cell-free networking problem with AP selection. Specifically, we propose a user-centric ratio-fixed AP-selection based clustering (UCR-ApSel) algorithm to form subnetworks dynamically. Following this, we analyze the average energy efficiency achieved with the proposed UCR-ApSel scheme theoretically and derive an effective closed-form upper-bound. Based on the analytical upper-bound expression, the optimal AP-selection ratio that maximizes the average energy efficiency is further derived as a simple explicit function of the total number of APs and the number of subnetworks. Simulation results demonstrate the effectiveness of the derived optimal AP-selection ratio and show that the proposed UCR-ApSel algorithm with the optimal AP-selection ratio achieves around 40% higher energy efficiency than the baselines. The analysis provides important insights to the design and optimization of future ultra-dense wireless communication systems.

Millimeter-wave (mmWave) communication has been recognized as a key technology to improve the rate performance of the next-generation wireless networks. However, the mmWave signals suffer from severe path loss and penetration attenuation due to the extremely high frequency characteristics. As a result, a massive number of small base stations (SBSs) would be deployed in mmWave networks to provide seamless coverage. To overcome obstacle blockages, the multi-connectivity technology that enables a user to associate with multiple SBSs simultaneously has been proposed by 3GPP, which brings new challenges to resource allocation. This paper investigates the joint user association and power allocation problem in such a multi-connectivity enabled mmWave network aiming at maximizing the system sum rate while considering the backhaul capacity limit and users’ individual rate requirements. The optimization problem is highly non-convex and NP-hard to solve. By decoupling it into user association subproblem and power allocation subproblem, we first propose a novel swapping algorithm on top of the classic many-to-many matching scheme to perform user association, and then apply the difference of convex functions (D.C.) programming approach to transform the non-convex power allocation subproblem into a convex one and solve it by an iterative algorithm. Simulation results demonstrate the superior performance of the proposed multi-connectivity user association and power allocation schemes over the existing ones.

Federated learning is a promising paradigm for achieving distributed intelligence by protecting user privacy in vehicular networks. Considering limited computing and communication resources, it is important to select appropriate clients from a huge number of users to participate in the training process. In vehicular networks, the problem of choosing proper clients is particularly complex due to the heterogeneity of network users, including the differences in the data, computation capability, available throughput, and samples freshness. We design a fuzzy logic based client selection scheme to address this issue. The proposed scheme considers the number of local samples, samples freshness, computation capability, and available network throughput based on a fuzzy logic approach. Extensive simulation results show that the proposed scheme outperforms other baselines.

Sarcasm is widely used in social communities and e-commerce platforms, failing to detect it in natural language processing tasks leads to false positives, e.g., opinion mining and sentiment classification. Recent works have indicated that the two linguistic characteristics, sentiment and incongruity information are beneficial to sarcasm detection. However, sarcasm datasets with sentiment labels are usually unavailable, and researchers consider little semantic information while modeling incongruity. In this paper, we propose a multi-task learning framework that incorporates sentiment clues by soft sentiment labels and integrates semantic information while modeling context incongruity. Experimental results on datasets show that the model we proposed yields better performance for the sarcasm detection task with the help of sentiment clues and incongruity information.

In power grid construction projects, ensuring the safety of construction workers by eliminating potential risks has always been important yet difficult. Thanks to the breakthrough in deep learning, it becomes possible to adopt deep learning based object detection technologies to enable intelligent safety monitoring on power grid construction sites. However, due to the complex terrain of the power grid construction site, there is a lack of a dataset of power grid construction scenes. In this paper, a high-quality power grid construction dataset is constructed. In order to reduce the expensive annotation work, we propose to adopt contrastive self-supervised learning to pretrain a feature extraction encoder and integrate it with YOLOv5 by modifying its backbone network for safety-related object detection. The proposed network is referred to as Contrastive Res-YOLOv5 Network (CORY-Net). Experimental results show that contrastive self-supervised pretraining can efficiently improve the object detection performance on the power grid construction dataset and speed up the convergence of the model. With only 1400 pretraining epochs, the proposed CORY-Net outperforms the original YOLOv5 by contributing 1.32% to the mAP@.5 and 3.54% to the mAP@.5:.95. Compared to the supervised object detection benchmarks, the proposed CORY-Net achieves the highest mAP@.5 in 9 out of 22 categories of targets and the highest overall mAP@.5.

Driving behavior analysis has diverse applications in intelligent transportation systems (ITSs). The naturalistic driving data potentially contain rich information regarding human drivers' habits and skills in practical and natural driving conditions. But mining knowledge from them is challenging. In this paper, we propose a novel approach for analyzing driving stability using naturalistic driving data. Our method can extract features, based on the random matrix theory, to reflect the statistical difference between actual driving data and the data that would be generated by a theoretically ideal driver, and thus imply the skillful level of a driver in terms of vehicle control in both longitudinal and lateral directions. The execution of our method on a practical ITS dataset is conducted. Using the extracted features, a driving behavior analysis application that partitions drivers into clusters to identify common driving stability characteristics is demonstrated and discussed.

In recent years, there have been many deep learning research projects based on two-dimensional object detection and three-dimensional point cloud recognition. However, relatively few of these combine the two, and the number of projects based on a three-dimensional workpiece recognition method for the industrial field is even fewer. In this paper, to perform the recognition task for polishing workpieces in manufacturing, we use RGB-D images as input, and propose our designed PolishNet-2d for two-dimensional workpiece detection and our designed PolishNet-3d for three-dimensional workpiece recognition. The two deep neural networks are employed together in series to first detect and then recognize polishing workpieces in an industrial environment. For this paper, a large number of experiments have been carried out on deep learning datasets of polishing workpieces. These datasets were created by us to contain diverse combinations of real and simulated workpieces in real and simulated industrial environments. The contributions of this paper are as follows: (1) A rotation parameter learning network is proposed and a two-dimensional workpiece detection neural network, named PolishNet-2d, which was constructed by integrating our designed algorithms with the backbone networks ResNet101 and region proposal network (RPN), is introduced; (2) A hierarchical feature extraction network is proposed and a three-dimensional workpiece recognition neural network, named PolishNet-3d, which was constructed by integrating our designed algorithms with the backbone network PointNet, is introduced; (3) PolishNet-2d and PolishNet-3d are employed in series, with the detection output of PolishNet-2d being used as the input for PolishNet-3d for its recognition tasks: the workpiece regions are detected in the RGB image; the workpiece point cloud is segmented in the corresponding regions in the depth image, and lastly the segmented point cloud is placed into PolishNet-3d to identify the workpiece; (4) For the experiments in this paper, datasets containing rich and diverse data types of polishing workpieces for industrial fields have been constructed; (5) Numerous experimental results on polishing workpiece datasets show that the conjunction of PolishNet-2d and PolishNet-3d can achieve exemplary recognition results on polishing workpiece datasets.

We study the performance of a cooperative vehicular communication system in a highway traffic scenario, where the locations of co-channel interfering vehicles are modeled by a one-dimensional Poisson point process (PPP). Wireless channel modeling campaigns have shown that the statistical patterns of vehicle-to-vehicle (V2V) channels can often be modeled by the Weibull distribution. Due to the complex characteristics of random fading and interference, system performance analysis is involved. To address this issue, we establish a framework for performance analysis in vehicular networks under Weibull fading and one-dimensional Poisson field of interference, where the Weibull probability density function (PDF) is approximated by a finite exponential mixture. By this means, the approximation expressions of the successful/unsuccessful message transmission probabilities for both direct V2V communication and the three-node cooperative vehicular communication are derived through stochastic geometry. Monte-Carlo simulations verify the accuracy of our derivation, as well as the advantages of encouraging cooperation among vehicles. Our methods and results can potentially be used to facilitate stochastic geometric analysis in many other complex vehicular networks under Weibull fading.

Molecular communication is a novel inter-disciplinary communication methodology at the nanoscale, which uses chemical or biological molecules as the information carriers. For many prospective molecular communication applications, the clock synchronization is a major issue. However, the existing solutions use the molecule releasing time for the clock synchronization schemes but ignore the molecule synthesizing time, which is not practical. To overcome this issue, in this paper, we propose a reference broadcast synchronization scheme. One nanomachine sends a broadcast beacon and the other two nanomachines records their receiving times. The receiving times are exchanged by that two nanomachines, then, the clocks between these two nanomachines can be synchronized. Owing to the fact that the information molecules propagate slowly with a large propagation delay, which also depends on the transmitter-receiver distance, so a delay estimation method is adopted in the synchronization scheme. The simulation results evaluate proposed synchronization scheme and show that the proposed scheme outperforms other clock synchronization schemes for molecular communication.