Intelligent reflecting surface (IRS) is considered a promising solution to manipulate the radio frequency transmission environment in the sixth-generation (6 G) wireless systems. However, little ...attention was received by IRS-aided localization techniques. Among range-free wireless localization strategies, received signal strength indicator (RSSI) fingerprinting-based technique is preferred since it can be easily accessed. Inspired by these and the tremendous success of deep reinforcement learning (DRL), we propose an IRS-enabled fingerprinting-based localization methodology with the aid of DRL. Specifically, we firstly propose an IRS-enabled fingerprinting-based localization system. In this system, RSSI lists are created by periodic IRS configurations and pre-collected as database. When a request of localization from a receiver is sent to the server, the database is compared with the online-measured RSSI data to identify the best receiver position estimate using the nearest neighbor algorithm. In addition, we develop a DRL-based IRS configuration selector to identify the most qualified IRS configurations so as to minimize the localization error. We also propose a communication protocol for the operation of the proposed localization methodology. Extensive simulation under different circumstances have been conducted and the results indicate that the localization accuracy scales with the number of IRS configurations. With the aid of DRL, the localization accuracy is further boosted by more than 40% as compared with previous work.
In this paper, a novel full-duplex cooperative non-orthogonal multiple access (FD CNOMA) system is proposed, where users intend to exchange messages with the assistance of a decode-and-forward relay. ...To characterize the potential performance gain brought by the proposed FD CNOMA scheme, the outage probability and ergodic rate are analyzed. Specifically, the closed-form expressions for the outage probabilities, diversity orders, ergodic rates, and system throughputs in delay-limited and delay-tolerant transmission modes are derived under the realistic assumption of imperfect self-interference cancellation. Furthermore, to present the comprehensive performance evaluation, both perfect and imperfect successive interference cancellations (SICs) are taken into consideration. Simulations are performed to validate the accuracy of the derivation results and to illustrate the outstanding performance of the proposed scheme in low signal-to-noise ratio region compared with half-duplex CNOMA system and cooperative orthogonal multiple access system. Our results show that under the conditions of both perfect and imperfect SICs, outage probability floors and ergodic rate ceilings exist for the proposed FD CNOMA scheme due to the inter-user interference among superimposed NOMA signals and the residual self-interference caused by the imperfect self-interference cancellation.
Routing plays an important role in the overall architecture of the Internet of Things. IETF has standardized the RPL routing protocol to provide the interoperability for low-power and lossy networks ...(LLNs). LLNs cover a wide scope of applications, such as building automation, industrial control, healthcare, and so on. LLNs applications require reliable and energy-efficient routing support. Point-to-point (P2P) communication is a fundamental requirement of many LLNs applications. However, traditional routing protocols usually propagate throughout the whole network to discover a reliable P2P route, which requires large amount energy consumption. Again, it is challenging to achieve both reliability and energy-efficiency simultaneously, especially for LLNs. In this paper, we propose a novel energy-efficient region-based routing protocol (ER-RPL), which achieves energy-efficient data delivery without compromising reliability. In contrast of traditional routing protocols where all nodes are required for route discovery, the proposed scheme only requires a subset of nodes to do the job, which is the key of energy saving. Our theoretical analysis and extensive simulation studies demonstrate that ER-RPL has a great performance superiority over two conventional benchmark protocols, i.e., RPL and P2P-RPL.
In this paper, we analyze the bus transport network (BTN) structure considering the spatial embedding of the network for three cities, namely, Hong Kong (HK), London (LD), and Bengaluru (BL). We ...propose a novel approach called supernode graph structuring for modeling the bus transport network. A static demand estimation procedure is proposed to assign the node weights by considering the points of interests (POIs) and the population distribution in the city over various localized zones. In addition, the end-to-end delay is proposed as a parameter to measure the topological efficiency of the bus networks instead of the shortest distance measure used in previous works. With the aid of supernode graph representation, important network parameters are analyzed for the directed, weighted and geo-referenced bus transport networks. It is observed that the supernode concept has significant advantage in analyzing the inherent topological behavior. For instance, the scale-free and small-world behavior becomes evident with supernode representation as compared to conventional or regular graph representation for the Hong Kong network. Significant improvement in clustering, reduction in path length, and increase in centrality values are observed in all the three networks with supernode representation. The correlation between topologically central nodes and the geographically central nodes reveals the interesting fact that the proposed static demand estimation method for assigning node weights aids in better identifying the geographically significant nodes in the network. The impact of these geographically significant nodes on the local traffic behavior is demonstrated by simulation using the SUMO (Simulation of Urban Mobility) tool which is also supported by real-world empirical data, and our results indicate that the traffic speed around a particular bus stop can reach a jammed state from a free flow state due to the presence of these geographically important nodes. A comparison of the simulation and the empirical data provides useful information on how bus operators can better plan their routes and deploy stops considering the geographically significant nodes.
•The work majorly emphasizes on the study of topological behavior of the bus transport network structure of three cities: Hong Kong, London and Bengaluru.•A novel approach called supernode graph structuring is proposed for modeling the bus transport network.•A static demand estimation procedure is proposed to assign the node weights.•The end-to-end delay is employed to measure the topological efficiency.•The impact of geographically central nodes on local traffic behavior is demonstrated by both simulation and empirical data.
Through connecting intelligent vehicles as well as the roadside infrastructure, the perception range of vehicles can be significantly extended, and hidden objects at blind spots can be efficiently ...detected and avoided. To realize this, accurate road map data must be downloaded in real time to these intelligent vehicles for navigation and localization purposes. Besides, the cloud must be updated with dynamic changes that happened in the road network. These involve the transmissions of high-definition 3D road map data for accurately representing the physical environments. In this work, we propose solutions under the fog computing architecture in a heterogeneous vehicular network to optimize data exchange among intelligent vehicles, the roadside infrastructure, as well as regional databases. Specifically, the efficiency of 3D road map data dissemination at roadside fog nodes is achieved by exploiting index coding techniques to reduce the overall data load, while opportunistic scheduling of heterogeneous transmissions can be done to judiciously manage network resources and minimize operating cost. In addition, 3D point cloud coding and hashing techniques are applied to expedite the updates of various dynamic changes in the network. We empirically evaluate the proposed solutions based on real-world mobility traces of vehicles and 3D LIght Detection And Ranging (LIDAR) data of city streets. The proposed system is also implemented in a multi-robotic testbed for practical evaluation.
Recently, wireless sensing is gaining immense attention in the Internet of Things (IoT) for crowd counting and occupancy detection. As wireless signals propagate, they tend to scatter and reflect in ...various directions depending on the number of people in the indoor environment. The combined effect of these variations on wireless signals is characterized by the channel state information (CSI), which can be further exploited to identify the presence of people. State-of-the-art CSI-based supervised crowd counting systems are vulnerable to temporal and environmental dynamics in practical scenarios as their performance degrades with fluctuations in the indoor environments due to multipath fading. Inspired by the breakthroughs of transfer learning and advancement in edge computing, we have leveraged in this work the concept of transfer learning to minimize this problem via exploiting the trained model from the source environment for other indoor environments to perform device-free crowd counting (CrossCount) at the target rooms. Our results show that this technique can combat the dynamics of the environment and achieves 4.7% better accuracy with 40% reduction in training time as compared to conventional convolutional neural networks. In essence, our results imply the future possibility of harnessing crowdsourced CSI data collected at different indoor environments to boost the accuracy and efficiency of local crowd counting systems.
Sharing up-to-date environment information collected by intelligent connected vehicles is critical in achieving travel comfort, convenience, and safety in vehicular networks. Individually collected ...information should be made available to other vehicular nodes, adjacent or distant, to achieve an informed and well-managed vehicular traffic. The coverage reach of sharing these road data can be maximized by allocating roadside units in strategic positions. In this work, we propose an Enhanced Information SHAring via Roadside Unit Allocation (EISHA-RSU) scheme that strategically determines where RSUs must be deployed from all spatial candidate locations. The urban area is irregularly partitioned into effective regions of movement (ERM) according to vehicular capacity with priority. For each ERM, EISHA-RSU greedily allocates the initial RSU to an effective position and optimally assigns the remaining RSUs to spatial locations that capture the maximum I2V/V2I information sharing based on the area's average road speed. In effect, the proposed deployment scheme addresses both the issues of coverage and connectivity among vehicles and the infrastructure. We evaluate the proposed RSU allocation scheme by employing three urban empirical mobility datasets and compare its network starvation fairness, effectiveness, and efficiency performance measures with three other deployment benchmarks. Overall, EISHA-RSU reduces the number of required RSUs to cover a certain area, exhibits higher connectivity, and achieves maximum I2V/V2I information sharing among the evaluated schemes.
Deteriorating water quality leads to the freshwater biodiversity crisis. The interrelationships among water quality parameters and the relationships between these parameters and taxa groups are ...complicated in affecting biodiversity. Nevertheless, due to the limited types of Internet-of-Things (IoT) sensors available on the market, a large number of chemical and biological parameters still rely on laboratory tests. With the latest advancement in Artificial intelligence and the IoT (AIoT), this technique can be applied to real-time monitoring of water quality, and further conserving biodiversity. In this article, we conducted a comprehensive literature review on water quality parameters that impact the biodiversity of freshwater and identified the top-10 crucial water quality parameters. Among these parameters, the interrelationships between the IoT measurable parameters and IoT unmeasurable parameters are estimated using a general regression neural network (GRNN) model and a multivariate polynomial regression (MPR) model based on historical water quality monitoring data. Conventional field water sampling and in-lab experiments, together with the developed IoT-based water quality monitoring system were jointly used to validate the estimation results along an urban river in Hong Kong. The GRNN can successfully distinguish the abnormal increase of parameters against normal situations. For the MPR model of degree 8, the coefficients of determination results are 0.89, 0.78, 0.87, and 0.81 for NO3-N, BOD 5 , PO4, and NH3-N, respectively. The effectiveness and efficiency of the proposed systems and models were validated against laboratory results and the overall performance is acceptable with most of the prediction errors smaller than 0.2 mg/L, which provides insights into how AIoT techniques can be applied to pollutant discharge monitoring and other water quality regulatory applications for freshwater biodiversity conservation.
In this paper, we investigate a joint resource allocation problem based on cognitive radio (CR) techniques for user equipment with multi-homing capabilities. We consider a heterogeneous wireless ...medium where users in overlapping coverage areas simultaneously communicate with different base stations and access points. Currently, existing works assume that the working frequency bands of different networks are separated. Unlike these works, this paper focuses on the multi-homing networks, which can share spectrum resources of each other to enhance the resource utilization efficiency. Based on spectrum sensing and spectrum sharing techniques in CR, we propose and then formulate an uplink joint original bandwidth, detected hole bandwidth and power allocation method. Specifically, the formulated optimization problem is a mixed integer nonlinear optimization problem. We adopt the continuity relaxation method to further transform it into a convex optimization problem and then solve it by Lagrange dual solution. A suboptimal method is further proposed with a reduced system overhead. Simulation results demonstrate the significantly improved performance of our proposed methods (both optimal and suboptimal) in terms of system throughput and energy efficiency over a joint resource allocation benchmark. Our results also indicate that the suboptimal strategy can indeed reduce the system overhead remarkably.
Accurate localization is a critically important issue for autonomous vehicles as it is closely related to the safety and efficiency of autonomous driving. However, current technologies for autonomous ...vehicle localization face many challenges. To provide accurate and robust localization services to autonomous vehicles, we propose a novel solution by employing a newly designed pavement marking. This marking operates on color contrast, temperature contrast, and binary code with some special features. We also trained and customized an object detector based on a deep learning model: YOLOv5, and integrated it with the decoding algorithm. The localization system is capable of running at a steady frame rate of more than 50 FPS. Road trials up to 80 km/h were conducted, and satisfactory results confirmed the feasibility and robustness of the localization system. Specifically, with a common onboard camera, more than four continuous frames can be detected and decoded correctly when the speed is slower than 30 km/h. At least one frame can be detected and decoded correctly at a higher speed (i.e., 30- 50 km/h). With a high-speed camera, more than 18 frames can be detected and decoded even at 80 km/h. The findings suggest that the specially designed road marking and associated algorithms can provide a viable and economical option for accurate localization of autonomous vehicles. The performance of the system has potentials for further improvement by using better hardware such as faster CPUs, GPUs, and thermal imaging techniques.