Wireless sensing-based human-vehicle recognition (WiHVR) methods have become a hot spot for research due to its non-invasiveness and cost-effective advantages. However, existing WiHVR methods shows limited performance and slow execution time on human-vehicle classification task. To address this issue, a lightweight wireless sensing attention-based deep learning model (LW-WADL) is proposed, which consists of a CBAM module and several depthwise separable convolution blocks in series. LW-WADL takes raw channel state information (CSI) as input, and extracts the advanced features of CSI by jointly using depthwise separable convolution and convolutional block attention mechanism (CBAM). Experimental results show that the proposed model achieves 96.26% accuracy on the constructed CSI-based dataset, and the model size is only 5.89% of the state of the art (SOTA) model. The results demonstrate that the proposed model achieves better performance on WiHVR tasks while reducing the model size compared to SOTA model.

The Smart Parking System (SPS) has played an important role in solving the parking problem in urban areas recently, resulting in that the battery-powered Wireless Parking Detectors (WPDs) based on Internet of Things (IoT) technology have been widely used in SPS to collect basic data sets. However, the daily turnover rates of parking spaces are generally less than 10 vehicles in Shanghai, China, so that WPDs waste a lot of energy in collecting and processing of redundant sensor data when the parking space is occupied or free. Hence, an environmental Energy Harvesting-driven Parking Detection (EHPD) method, which includes a vehicle-induced vibration energy harvesting and conditioning circuit, as well as a parking detection algorithm based on the signatures of vehicle-induced seismic signals and wireless energy attenuated by vehicles, is proposed in the paper. In EHPD, the signatures of pulse signals converted from vehicle-induced seismic signals are used to drive the wireless energy features to participate in achieving parking detection. Finally, the proposed EHPD has been evaluated in a real testbed, and the experimental results show that it can achieve the same functions as the existing magnetometer-based WPD devices with lower cost and energy consumption.

A novel quick store-and-forwarding mechanism-based time synchronization method is proposed for strip-based Wireless Sensor Networks(WSNs).Combining store-and-forwarding mechanism with linear regression,this method achieves high accuracy and constant setup time.Experimental results show the method has micro second synchronization accuracy and constant synchronization setup time.

Based on the pilot of VMIMO-OFDM system, this paper proposed a jointly estimation algorithm for solve estimation problem between the multiple carrier frequency offset (CFOs) and channel impulse response (CIRs) at the wireless sensor network's destination node. As each transmitter-to-receiver link in wireless sensor networks had an individual CFO and CIR parameters with its local oscillator, so directly estimation all the parameters had become a multi-dimensional nonlinear problem. Based on the specially designed training sequences, the destination node could decouple the signal from different relay nodes by correlation and simplify the MD nonlinear problem to linear. The multiple CFOs could be identified from the correlation result, so that the CIRs could be estimated according to the maximum-likelihood principle.

This paper presents a new algorithm making use of kurtosis, which is a statistical parameter, to distinguish the seismic signal generated by a person's footsteps from other signals. It is adaptive to any environment and needs no machine study or training. As persons or other targets moving on the ground generate continuous signals in the form of seismic waves, we can separate different targets based on the seismic waves they generate. The parameter of kurtosis is sensitive to impulsive signals, so it's much more sensitive to the signal generated by person footsteps than other signals generated by vehicles, winds, noise, etc. The parameter of kurtosis is usually employed in the financial analysis, but rarely used in other fields. In this paper, we make use of kurtosis to distinguish person from other targets based on its different sensitivity to different signals. Simulation and application results show that this algorithm is very effective in distinguishing person from other targets.

This paper analyzed the features of nighttime complex traffic scenes,and proposed the HLEPT algorithm to collect nighttime traffic information.It contained a headlight extraction algorithm and regulations of pairing and tracking,integrating with two methods: pre-pairing headlights and post-tracking trajectories,pre-tracking headlights and post-pairing trajectories,and finally measured the traffic flow and velocity.Experiment results indicate that this algorithm is robust with low computational complexity and real-time performance,and its detection ratio reaches above 96% in fine condition,88% in a traffic jam at rainy night when inverted reflections of lights exist.

Wireless sensor networks is a network system which includes distributed information collection,information transmission and information management.WSN can inspect and collect information by integrated microsensor,and transmit this information to user through self organization network.There are many applications in WSN.Though analysis of network characteristics and protocol in WSN,simulation model about multihop cluster network in OPNET is implemented.Finally,the simulation results are analyzed.

Placing few heterogeneous nodes in wireless sensor network is an effective way to increase network lifetime and reliability. In this paper, we address the deployment problem of heterogeneous wireless sensor networks. We present an algorithm to decide how many and where heterogeneous nodes should be deployed in the wireless sensor network. The core algorithm, based on the locations of all sensor nodes, can optimize placement of heterogeneous nodes in an arbitrary sensor network. Finally, the evaluation results of this algorithm are shown in this paper.

A new vehicle detection algorithm, called the adaptive window distance (AWD) algorithm using magnetic wireless sensor node, is presented. The algorithm can detect the occurrence of the end point in the vehicle signal by calculating the signal feature distance between the background window and the current window and by separating vehicle-coming and vehicle-leaving events from geomagnetic background to realize vehicle detection. Moreover, based on the energy requirement in WSN application, This algorithm uses 'Duty-cycling' policy to decrease energy consuming of the sensor node. Experimental evaluation on dataset collected by Honeywell HMC1051Z and NVE GMR magnetometer is given. Compared with ATA, the detecting result of AWD shows that the algorithm has higher accuracy (97%), stronger robustness and better power efficiency.

This paper designs and realizes a distributed map-matching system for massive GPS data.In this system,there are two kinds of nodes:dispatcher node and matching node.The dispatcher node receives massive GPS data from outer GPS data sources and periodically dispatches GPS data to the matching nodes,where the data is map-matched.An actual project shows,this system is well designed for massive GPS data and has strong adaptability and portability.

A traffic-adaptive MAC protocol (TA-MAC) for wireless sensor networks was proposed. Traffic variation was predicted based on the number of packets queued. The traffic-adaptive duty cycle scheme in the listen-sleep schedule and the adaptive listening scheme were adopted to reduce the latency. Simulation results showed that TA-MAC can obtain low latency under different traffic load and get improvement on energy efficiency and throughput.

In linear wireless sensor networks, an energy-efficient node deployment scheme (EENDS) was proposed to minimize the average energy consumption per node. The analysis of EENDS and the comparison of performance with the equal-spaced scheme showed that EENDS scheme can significantly decrease the average energy consumption per node, which can prolong the lifetime of sensor nodes and sensor networks effectively.

A residual-energy aware MAC protocol(REA-MAC) for wireless sensor networks was(proposed).REA-MAC modifies the contention mechanism of SMAC,takes the node's residual energy into(consideration) to adaptively select the deferring time and let the nodes who have more residual energy to(access) the channel with priority,thus the network load is balanced and the network lifetime is prolonged.A(traffic) adaptive duty cycle scheme is also adopted and the overhead of synchronous frame is reduced.The(simulation) results show that,compared to SMAC,REA-MAC can decrease the total number of collisions by 79%,achieve an increase of 17% in the network lifetime and an increase of 51% in the total number of packets that are correctly received.

The virtual backbone is an approach for solving routing problems in wireless ad hoc networks. Recently, a connected dominating set (CDS) has been proposed as a virtual backbone to improve the performance of wireless networks. The quality of a virtual backbone is measured not only by approximation factor, which is the ratio of its size to that of minimum CDS, but also time complexity and message complexity. In this paper, we present a distributed algorithm to construct a minimum CDS (MCDS) for ad hoc networks. By destroying triangular loops in the virtual backbone, the proposed algorithm can effectively construct a CDS with smaller size. Moreover, our algorithm, which is fully localized, has a constant approximation ratio, linear message and time complexity, and low implementation complexity. Simulation results and theoretical analysis show that our algorithm has better efficiency and performance than conventional approaches

Wireless Sensor Networks (WSN) is a temporary autonomous system of nodes equipped with wireless transmitters and receivers. Batteries typically power hosts in WSN, so energy efficiency strategy is critical problem in research of WSN. Node level energy efficiency strategies were analyzed. Design method about software and hardware combined with design strategy in system level to minimize the power consumes in sensor node, and key simulation results were provided by OPNET.

In this paper, we propose GROUP, a grid-clustering routing protocol that provides scalable and efficient packet routing for large-scale wireless sensor networks. The sink proactively, dynamically and randomly builds a cluster grid structure in GROUP. Only small part of all sensor nodes will participate in election of cluster heads. GROUP can distribute the energy load among the sensors in the network, and provide in-network processing support to reduce the amount of information that must be transmitted to the sink. We have evaluated the performance of GROUP through simulation experiments. The results of simulations show that GROUP is an energy-efficient and scalable routing protocol for large-scale wireless sensor networks