Service disruptions of rail transit systems have become more frequent in the past decade in urban cities, due to various reasons, such as power failures, signal errors, and so on. Smart transit cards provide detailed tapping records of commuters, which enable us to infer their trajectories under both normal and disruptive circumstances. In this article, we study and predict the impact of disruptions on commuters and further evaluate the vulnerability of the rail system. Specifically, we define two metrics, stay ratio and travel delay, to quantify the impact, and we derive the predictor of each metric based on the inferred alternative route choices of commuters under disruptive circumstances. We demonstrate that the alternative route choices contribute to more similar feature distribution among different disruptions, which is crucial to tackling the main challenge of abnormal data scarcity and is beneficial for obtaining more reliable predictors for future disruptions. We evaluate our approach with a real-world transit card dataset. The result demonstrates the effectiveness of our method. Based on the predictors, we further analyse the vulnerability of the rail system. An evaluation with cross validation from taxi GPS trajectory data indicates its efficacy in discovering vulnerable rail stations as well as Origin-Destination pairs.

Spectrum sensing has a very important role in the operation of cognitive radio network. A proper sensing and utilization improve the performance of cognitive radio network (CRN). Different methodologies were developed in past to improve the sensing and utilization performance in CRN. Parallel sensing is used as an optimal approach in spectrum sensing with reduced delay of operation but restraint with multiple requests for spectrum sensing. A random generation of sensing requests results in large time delay and interference in the network. To minimize the interference effect and requesting overhead, this paper presents a new approach of spectrum sensing by centralized monitoring of spectrum engagement of Primary User (PU). The proposed approach operates on a repository monitoring of channel engagement to control the request granting for spectrum sensing in PUs. In addition, the sharing of spectrum usage is controlled by monitoring the spectral efficiency and interference in the network. Simulation results obtained illustrates an enhancement in network throughput, spectrum sensing and spectrum utilization performance where an average network throughput is observed to improve by 80% for varying number of primary channels and varying load conditions. The spectrum sensing is improved by 70% in average for varying primary channels and load conditions and Ideal channel utilization for the proposed approach is observed to improve by 90%.

Supporting a massive amount of Internet of Things applications requires a large pool of spectrum. DSM is a promising ecosystem to improve the spectrum efficiency. In the era of LoRaWAN, the physical hardware constraints, along with the bandwidth-hungry applications pose new challenges. In this article, we investigate a novel deep-reinforcement-learning-based spectrum-sharing paradigm, termed Intelligent Overlapping, that explores partially overlapping channels for concurrent spectrum access in LoRaWAN. Our key insight is to leverage the coding redundancy to expand the available spectrum without complicated data processing algorithms. In particular, we learn the extra coding redundancy from the data on the non-overlapping spectrum via a deep-Q-learning network, and we apply such redundancy to recover the data on the overlapping spectrum. In the Media Access Control layer, we predict the channel condition and strategically learn and assign the appropriate overlapping portion to the concurrent access end devices. In the Physical layer, we harness interleaving to randomize the mutual interference to ensure that all the data remains decodable. Simulation results demonstrate that Intelligent Overlapping greatly improves the spectrum efficiency with a fast convergence rate compared to the conventional DSM mechanisms.

Wireless communication over long distances has become the bottleneck for battery-powered, large-scale deployments. Low-power protocols like Zigbee and Bluetooth Low Energy have limited communication range, whereas long-range communication strategies like cellular and satellite networks are power-hungry. Technologies that use narrow-band communication like LoRa, SigFox, and NB-IoT have low spectral efficiency, leading to scalability issues. The goal of this work is to develop a communication framework that is energy efficient, long-range, and scalable. We propose, design, and prototype WiChronos, a communication paradigm that encodes information in the time interval between two narrowband symbols to drastically reduce the energy consumption in a wide area network with large number of senders. We leverage the low data-rate and relaxed latency requirements of such applications to achieve the desired features identified above. We design and implement chirp spread spectrum transmitter and receiver using off-the-shelf components to send the narrowband symbols. Based on our prototype, WiChronos achieves an impressive 60% improvement in battery life compared to state-of-the-art LPWAN technologies in transmission of payloads less than 10 bytes at experimentally verified distances of over 4 km. We also show that more than 1,000 WiChronos senders can co-exist with less than 5% collision probability under low traffic conditions.

Trajectory planning is the core technology in the field of mobile robot research. However, the traditional trajectory planning algorithm has the problems of low accuracy and high complexity. Therefore, we propose a trajectory planning algorithm for target search mobile robot using transfer learning (TL) and wireless sensor network. First, the mobile robot motion model is constructed and converted into a linear motion model; Second, the robot kinematic constraints such as velocity, acceleration and position are analyzed; Then, the ultrasonic sensor is constructed to sense the robot's self and environmental information, and the path planning is performed by the combination of global planning and local planning. Finally, a combination of global planning and local planning is used for path planning, and the knowledge is learned from global planning based on TL, and the relevant factors of the global planning model are applied to local planning as the initial motion state factors of the robot to realize the trajectory planning of the target-search mobile robot. The results show that the fitting of the proposed algorithm and the optimal trajectory planning results is high, the reward value of robot training is higher, the trajectory planning velocity curve is smoother, and the space complexity of the proposed algorithm is much lower than other algorithms, the highest is only 23%, and the accuracy of trajectory planning is as high as 95.6%, which has practical applicability.

Telecommunications systems with Multi-Input Multi-Output (MIMO) structure using Orthogonal Frequency Division Modulation (OFDM) have great potential for efficient application to a network of Internet of Things (IoT) at a high data rate. When the IoT network is among the underwater sensory devices known as the Internet of Underwater Things (IoUT), the electromagnetic wave cannot play the role of baseband signal due to rapid fall-off inside the water. Thus, acoustic OFDM is a reliable replacement for conventional OFDM inside the water. A blind structure for MIMO acoustic OFDM using Independent Component Analysis (ICA) brings even further advantages in data rate and energy consumption by avoiding the required pilot and preamble data. This research work presents a blind MIMO Acoustic OFDM blind transceiver for IoUT based on Probabilistic Stone’s Blind Source Separation (PS-BSS). The proposed technique has multiple times lower complexity compared to the ICA-based technique while maintaining a comparable efficiency. As observed in the results carried out with 100 Monte Carlo runs of transmission of random data bits over a highly sparse channel that is the common case of an underwater environment, the proposed PS-BSS-based technique dominates the ICA-based one, and as the sparseness of the channel decreases, its efficiency is comparable to the ICA-based technique. Thus, in the case of a highly sparse channel, the proposed technique is superior in both aspects of efficiency and complexity, while over lower sparseness, due to its comparative efficiency, it can be hired as an optimum technique fulfilling a fair tradeoff between efficiency and complexity.

The particularity of the marine underwater environment has brought many challenges to the development of underwater sensor networks (UWSNs) . This research realized the effective monitoring of targets by UWSNs and achieved higher quality of service in various applications such as communication, monitoring, and data transmission in the marine environment. After analysis of the architecture, the marine integrated communication network system (MICN system) is constructed based on the maritime wireless Mesh network (MWMN) by combining with the UWSNs. A distributed hybrid fish swarm optimization algorithm (FSOA) based on mobility of underwater environment and artificial fish swarm (AFS) theory is proposed in response to the actual needs of UWSNs. The proposed FSOA algorithm makes full use of the perceptual communication of sensor nodes and lets the sensor nodes share the information covered by each other as much as possible, enhancing the global search ability. In addition, a reliable transmission protocol NC-HARQ is put forward based on the combination of network coding (NC) and hybrid automatic repeat request (HARQ) . In this work, three sets of experiments are performed in an area of 200 × 200 × 200 m. The simulation results show that the FSOA algorithm can fully cover the events, effectively avoid the blind movement of nodes, and ensure consistent distribution density of nodes and events. The NC-HARQ protocol proposed uses relay nodes for retransmission, and the probability of successful retransmission is much higher than that of the source node. At a distance of more than 2,000 m, the successful delivery rate of data packets is as high as 99.6%. Based on the MICN system, the intelligent ship constructed with the digital twins framework can provide effective ship operating state prediction information. In summary, this study is of great value for improving the overall performance of UWSNs and advancing the monitoring of marine data information.

Mobile Augmented Reality (AR), which overlays digital content on the real-world scenes surrounding a user, is bringing immersive interactive experiences where the real and virtual worlds are tightly coupled. To enable seamless and precise AR experiences, an image recognition system that can accurately recognize the object in the camera view with low system latency is required. However, due to the pervasiveness and severity of image distortions, an effective and robust image recognition solution for “in the wild” mobile AR is still elusive. In this article, we present CollabAR, an edge-assisted system that provides distortion-tolerant image recognition for mobile AR with imperceptible system latency . CollabAR incorporates both distortion-tolerant and collaborative image recognition modules in its design. The former enables distortion-adaptive image recognition to improve the robustness against image distortions, while the latter exploits the spatial-temporal correlation among mobile AR users to improve recognition accuracy. Moreover, as it is difficult to collect a large-scale image distortion dataset, we propose a Cycle-Consistent Generative Adversarial Network-based data augmentation method to synthesize realistic image distortion. Our evaluation demonstrates that CollabAR achieves over 85% recognition accuracy for “in the wild” images with severe distortions, while reducing the end-to-end system latency to as low as 18.2 ms.

The emerging energy-harvesting technology enables charging sensor batteries with renewable energy sources, which has been effectively integrated into Wireless Sensor Networks (EH-WSNs). Due to the limited energy-harvesting capacities of tiny sensors, the captured energy remains scarce and differs greatly among nodes, which makes the data aggregation scheduling problem more challenging than that in energy-abundant WSNs. In this article, we investigate the Minimum Latency Aggregation Scheduling (MLAS) problem in EH-WSNs. First, we identify a new kind of collision in EH-WSNs, named as energy-collision, and design several special structures to avoid it during data aggregation. To reduce the latency, we try to choose the parent adaptively according to nodes’ transmission tasks and energy-harvesting ability, under the consideration of collisions avoidance. By considering transmitting time, residual energy, and energy-collision, three scheduling algorithms are proposed under protocol interference model. Under physical interference model, several approximate algorithms are also designed by taking account of the interference from the nodes several hops away. Finally, the theoretical analysis and simulation results verify that the proposed algorithms have high performance in terms of latency.

Forecasting human poses given a sequence of historical pose frames has several important applications, especially in the domain of smart home safety. Recently, computer vision-based human pose forecasting has made a breakthrough using deep learning technology. However, to implement a practical system deployed on an IoT edge environment, there are still two issues to be addressed. First, existing methods on pose forecasting fail to model the coherent structural information of connected human joints and thus cannot achieve satisfactory prediction accuracy, especially for long-term predictions. Second, a general and static pre-trained prediction model may not perform well in the deployment environment due to the visual domain shift problem. In this article, we propose a hybrid cloud-edge system called GPFS to solve those issues. Specifically, we first introduce a novel graph convolutional neural network (GCN)-based sequence-to-sequence learning method, which enhances the sequence encoder by using a graph to represent both the spatial and temporal connections of the human joints in the input frames. The GCN improves the forecasting accuracy by capturing the motion pattern of each joint as well as the correlations among different human joints over time. Second, to address the domain shift issue and protect data privacy, we extend the system to perform online learning on the IoT edge to adapt the cloud trained general model with online collected on-site domain data. Extensive evaluation on Human 3.6M and Penn Action datasets demonstrates the superiority of our proposed system.