Search

Crowd counting aims to estimate the number of individuals in targeted areas. However, mainstream vision-based methods suffer from limited coverage and difficulty in multi-camera collaboration, which limits their scalability, whereas emerging WiFi-based methods can only obtain coarse results due to signal randomness. To overcome the inherent limitations of unimodal approaches and effectively exploit the advantage of multi-modal approaches, this paper presents an innovative WiFi and video-fused multi-modal paradigm by leveraging a heterogeneous dual-attentional network, which jointly models the intra- and inter-modality relationships of global WiFi measurements and local videos to achieve accurate and stable large-scale crowd counting. First, a flexible hybrid sensing network is constructed to capture synchronized multi-modal measurements characterizing the same crowd at different scales and perspectives; second, differential preprocessing, heterogeneous feature extractors, and self-attention mechanisms are sequentially utilized to extract and optimize modality-independent and crowd-related features; third, the cross-attention mechanism is employed to deeply fuse and generalize the matching relationships of two modalities. Extensive real-world experiments demonstrate that our method can significantly reduce the error by 26.2%, improve the stability by 48.43%, and achieve the accuracy of about 88% in large-scale crowd counting when including the videos from two cameras, compared to the best WiFi unimodal baseline.

Regarding the passive WiFi sensing based crowd analysis, this paper first theoretically investigates its limitations, and then proposes a deep learning based scheme targeted for returning fine-grained crowd states in large surveillance areas. To this end, three key challenges are coped with: to relieve the influences of the randomness and sparsity induced by passive WiFi sensing, an attention-based deep convolutional autoencoder model is designed to recover accurate crowd density maps in a way similar to image reconstruction; to combat the anonymity caused by MAC randomization, following the identification of local high-density crowds (LHDCs) with the density clustering algorithm, i.e., DM-DBSCAN, a bidirectional convolutional LSTM based model is employed to infer LHDC speeds; to overcome the absence of passive WiFi sensing datasets for model training, three semi-synthetic datasets are produced by emulating passive WiFi sensing with practical pedestrian tracking datasets. Extensive experiments confirm that, the proposed scheme significantly outperforms existing WiFi-based methods in terms of crowd density estimation and provides superior crowd speed estimation. More importantly, the scheme can also produce consistent crowd states on a real-world dataset, revealing that it has the ability to support accurate, visualized and real-time crowd monitoring in large surveillance areas.

Multi-agent Deep Reinforcement Learning (MADRL) based traffic signal control lbecomes a popular research topic in recent years. To alleviate the scalability issue of completely centralized reinforcement learning (RL) techniques and the non-stationarity issue of completely decentralized RL techniques on large-scale traffic networks, some literature utilizes a regional control approach where the whole network is firstly partitioned into multiple disjoint regions, followed by applying the centralized RL approach to each region. However, the existing partitioning rules either have no constraints on the topology of regions or require the same topology for all regions. Meanwhile, no existing regional control approach explores the performance of optimal joint action in an exponentially growing regional action space when intersections are controlled by 4-phase traffic signals (EW, EWL, NS, NSL). In this paper, we propose a novel RL training framework named RegionLight to tackle the above limitations. Specifically, the topology of regions is firstly constrained to a star network which comprises one center and an arbitrary number of leaves. Next, the network partitioning problem is modeled as an optimization problem to minimize the number of regions. Then, an Adaptive Branching Dueling Q-Network (ABDQ) model is proposed to decompose the regional control task into several joint signal control sub-tasks corresponding to particular intersections. Subsequently, these sub-tasks maximize the regional benefits cooperatively. Finally, the global control strategy for the whole network is obtained by concatenating the optimal joint actions of all regions. Experimental results demonstrate the superiority of our proposed framework over all baselines under both real and synthetic scenarios in all evaluation metrics.

Great efforts have been devoted to solving the crowd counting problem based on vision or other fine-grained measurements. Popular vision and WiFi channel state information based approaches, though are able to achieve relatively high accuracy, suffer from limited scalability. In contrast, passive WiFi sensing-based approaches are capable of supporting large surveillance areas, but often rely on certain global linear or approximately linear regression models, which cannot accurately capture the complex mapping relationship between WiFi sensing data and the corresponding crowd count, especially in a large surveillance area during a long period of time. This paper addresses the issue from the following three aspects. Firstly, in order to combat with these coarse-grained regression models, the large surveillance is partitioned into grids, such that either a local linear model or other implicit local models can be built with respect to each grid. Secondly, sequential WiFi spatial-temporal matrix (SWSTM) is defined in alignment with grids to encode the spatial-temporal information of crowds based on passive WiFi localization and a sliding time window mechanism. Thirdly, the spatial-temporal correlations among crowd features of different grids are mined to better regress such local models by using a recurrent neural network (RNN) with SWSTMs as inputs. Extensive experiments are conducted in a real campus road network with an area of about $4000m^{2}$ , and demonstrate that the proposed method significantly reduces the counting error rate from 22.54% to 13.44% compared to several state-of-the-art methods.

With the growing number of cars in cities, smart parking is gradually becoming a strategic issue in building a smart city. As the precondition in smart parking, accurate parking prediction can reduce the time drivers spend searching for parking spaces and relieve traffic congestion. Meanwhile, VANET and the Internet-of-things (IoT) are the key elements of the current intelligent transportation system. With the IoT devices based on VANET becoming more extensively employed, a large amount of parking data is generated every day, and various methods are proposed for parking prediction, therefore, it is time to systematically summarize the parking prediction issues and the state-of-the-art prediction methods. In this survey, we first provide a comprehensive review of the existing methods used for parking prediction ranging from conventional statistical methods to the latest graph neural network methods. Then, we classify a variety of parking problems such as parking availability prediction, parking behavior prediction, and parking demand prediction. We also compile all the evaluation metrics, open data, and open-source code of the surveyed literature. Finally, we present the challenges and future directions of the parking prediction technique. As far as we know, this is the first survey exploring parking prediction methods, which will be of interest to both researchers and practitioners engaging in intelligent transportation systems (ITS) and smart cities.

Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone’s Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system’s overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.

Road traffic congestion can inevitably degrade road infrastructure and decrease travel efficiency in urban traffic networks, which can be relieved by employing appropriate congestion control. According to different developmental driving forces, in this paper, the evolution of road traffic congestion control is divided into two stages. The ever-growing number of advanced sensing techniques can be seen as the key driving force of the first stage, called the sensing stage, in which congestion control strategies experienced rapid growth owing to the accessibility of traffic data. At the second stage, i.e., the communication stage, communication and computation capability can be regarded as the identifying symbols for this stage, where the ability of collecting finer-grained insight into transportation and mobility reality improves dramatically with advances in vehicular networks, Big Data, and artificial intelligence. Specifically, as the pre-requisite for congestion control, in this paper, existing congestion detection techniques are first elaborated and classified. Then, a comprehensive survey of the recent advances for current congestion control strategies with a focus on traffic signal control, vehicle route guidance, and their combined techniques is provided. In this regard, the evolution of these strategies with continuous development of sensing, communication, and computation capability are also introduced. Finally, the paper concludes with several research challenges and trends to fully promote the integration of advanced techniques for traffic congestion mitigation in transportation systems.

Cell discontinuous transmission (Cell DTx) is a key technology to mitigate inter-cell interference (ICI) in ultra-dense networks (UDNs). The aim of this work is to understand the impact of Cell DTx on physical-layer sum rates of SBSs and link-layer quality-of-service (QoS) performance in multiuser UDNs. In this work, we develop a cross-layer framework for capacity analysis in multiuser UDNs with Cell DTx. In particular, we first extend the traditional one-dimensional effective capacity model to a new multidimensional effective capacity model to derive the sum rate and the effective capacity. Moreover, we propose a new iterative bisection search algorithm that is capable of approximating QoS performance. The convergence of this new algorithm to a unique QoS exponent vector is later proved. Finally, we apply this framework to the round-robin and the max-C/I scheduling policies. Simulation results show that our framework is accurate in approximating 1) queue length distribution, 2) delay distribution and 3) sum rates under the above two scheduling policies, and further show that with the Cell DTx, systems have approximately 30% higher sum rate and 35% smaller average delay than those in full-buffer scenarios.

The crown jewel of intelligent transportation is achieving autonomous driving that can ultimately become accident- and congestion-free through CAVs and the associated traffic management systems. Recently, this vision has sparked huge research interest, such as IoV, LTE-V2X, and 5G. However, the huge amount of traffic data generated by CAVs poses challenges for the current networks and even the upcoming 5G communication networks.In this article, we first analyze the communication requirements of CAVs and present the progress of vehicular communication networks, and on that basis propose the novel concept of VMBS and a VMBS-CCNA for CAVs. The VMBS plays multiple roles of a user node and edge computing node for external communication networks, and a base station and information caching node for CAVs, thus achieving the fusion of communication and computing for CAVs. To this end, we present both the VMBS-enabled wireless communication and computing for CAVs, and the VMBS-assisted wireless communication for other wireless devices. Several research challenges and some open research issues are highlighted and discussed. Finally, simulation results reveal that the proposed VMBS-CCNA can bring a significant improvement in terms of throughput, delay, and average number of links.

Information security is an important issue in vehicular networks as the accuracy and integrity of information is a prerequisite to the satisfactory performance of virtually all vehicular network applications. We study the information security of a vehicular Ad hoc network whose message could be tampered by malicious vehicles. An analytical framework is developed to analyze the process of message dissemination in a vehicular network with malicious vehicles randomly distributed in the network. The probability that a destination vehicle at a fixed distance can receive the message correctly from the source vehicle is obtained. Simulations are conducted to validate the accuracy of the theoretical analysis. Our results demonstrate the impact of network topology and the distribution of malicious vehicles on the correct delivery of a message in vehicular Ad hoc networks, and provides insight on the design of security mechanisms to improve the security of message dissemination in vehicular networks.

To satisfy the recent growth of mobile data usage, small cells are recommended to deploy into conventional cellular networks. However, the massive backhaul traffic is a troublesome problem for small cell networks, especial in wireless backhaul transmission links. In this study, backhaul traffic models are first presented considering the Gauss–Markov mobile models of mobile stations in small cell networks. Furthermore, an energy efficiency model of small cell backhaul networks with Gauss–Markov mobile models has been proposed. Numerical results indicate that the energy efficiency of small cell backhaul networks can be optimised by trade-off the number and radius of small cells in cellular networks.

The IEEE/CIC International Conference on Communication in China (ICCC) has been globally recognized as one of the important annual international conference held by the IEEE Communication Society (ComSoc) and China Institute of Communication (CIC) in China. The sixth IEEE/CIC ICCC 2017 was held in the magnificent city of Qingdao, China, 22-24 October, 2017.

In this article, a new framework of mobile converged networks is proposed for flexible resource optimization over multi-tier wireless heterogeneous networks. Design principles and advantages of this new framework of mobile converged networks are discussed. Moreover, mobile converged network models based on interference coordination and energy efficiency are presented, and the corresponding optimization algorithms are developed. Furthermore, future challenges of mobile converged networks are identified to promote the study in modeling and performance analysis of mobile converged networks.

The articles in this special section focus on artificial intelligence-driven fog radio access networks. To satisfy the explosively increasing demands of highspeed data applications and access requirements from a massive number of Internet-of-Things (IoT) devices, a paradigm of fog computing-based radio access network (F-RAN) has emerged as a promising evolution path for the fifth generation (5G) radio access networks. By taking full advantage of distributed caching and centralized processing, F-RANs provide great flexibility to satisfy the quality-of-service requirements of various 5G services. With the rapid deployment of 5G communication networks, the application of F-RANs to the envisioned sixth-generation (6G) mobile network has attracted extensive attention from academia, industry, and government agencies. The 6G network progress in enhanced mobile broadband, massive machine-type communications and ultra-reliable and low-latency communications will lead to the fast development of new applications, including augmented reality (AR), virtual reality (VR), holographic communications, vehicle-to-everything (V2X), self-driving cars, massive sensors connective on the ground and several tens of thousands of satellites connective in the sky.

With the popularization of wireless multimedia communications, the wireless traffic is predicated to be increased more than 1000 time in the next decade. Some new technologies, e.g., massive multi-input multi-output antennas, millimeter wave and small cell networks are developed to support high speed wireless transmission in future fifth generation (5G) mobile communication systems. On the other hand, it is a great challenge how to face the quick growth of energy consumption in 5G mobile communication networks due to the massive wireless traffic. However, detailed investigation of the energy efficiency of 5G mobile communication networks from three aspects of theory models, technology developments and applications is surprisingly rare in the open literature. Fortunately, the scholarly writing, 5G Green mobile communication networks, published by Publishing House of Electronics Industry in November 2016, points out the directions and research advance of 5G green mobile communication networks.