WiPg: Contactless Action Recognition Using Ambient Wi-Fi Signals

Motion recognition has a wide range of applications at present. Recently, motion recognition by analyzing the channel state information (CSI) in Wi-Fi packets has been favored by more and more scholars. Because CSI collected in the wireless signal environment of human activity usually carries a large amount of human-related information, the motion-recognition model trained for a specific person usually does not work well in predicting another person’s motion. To deal with the difference, we propose a personnel-independent action-recognition model called WiPg, which is built by convolutional neural network (CNN) and generative adversarial network (GAN). According to CSI data of 14 yoga movements of 10 experimenters with different body types, model training and testing were carried out, and the recognition results, independent of bod type, were obtained. The experimental results show that the average correct rate of WiPg can reach 92.7% for recognition of the 14 yoga poses, and WiPg realizes “cross-personnel” movement recognition with excellent recognition performance.

Improving the Accuracy of Estimates of Indoor Distance Moved Using Deep Learning-Based Movement Status Recognition

As a result of the development of wireless indoor positioning techniques such as WiFi, Bluetooth, and Ultra-wideband (UWB), the positioning traces of moving people or objects in indoor environments can be tracked and recorded, and the distances moved can be estimated from these data traces. These estimates are very useful in many applications such as workload statistics and optimized job allocation in the field of logistics. However, due to the uncertainties of the wireless signal and corresponding positioning errors, accurately estimating movement distance still faces challenges. To address this issue, this paper proposes a movement status recognition-based distance estimating method to improve the accuracy. We divide the positioning traces into segments and use an encoder–decoder deep learning-based model to determine the motion status of each segment. Then, the distances of these segments are calculated by different distance estimating methods based on their movement statuses. The experiments on the real positioning traces demonstrate the proposed method can precisely identify the movement status and significantly improve the distance estimating accuracy.

Research on robust adaptive sliding film fault-tolerant control under nonlinear distortion of signal transmission in amorphous flat air-to-ground wireless ad-hoc network system

Purpose To solve the above problems and ensure the stability of the ad hoc network node topology in the process of wireless signal transmission, this paper aims to design a robust adaptive sliding film fault-tolerant controller under the nonlinear distortion of signal transmission in an amorphous flat air-to-ground wireless ad hoc network system. Design/methodology/approach This paper designs a robust adaptive sliding film fault-tolerant controller under the nonlinear distortion of signal transmission in an amorphous flat air-to-ground wireless ad hoc network system. Findings The simulation results show that the amorphous flat wireless self-organizing network system has good nonlinear distortion fault-tolerant correction ability under the feedback control of the designed controller, and the system has the asymptotically stable convergence ability; the test results show: the node topology of the self-organizing network structural stability is significantly improved, which provides a foundation for the subsequent realization of long-distance transmission of ad hoc network nodes. Research limitations/implications Because of the chosen research approach, the research results may lack generalizability. Therefore, researchers are encouraged to test the proposed propositions further. Originality/value The controller can extract the fault information caused by nonlinear distortion in the wireless signal transmission process, and at the same time, its feedback matrix K can gradually converge the generated wireless signal error to zero, to realize the stable transmission of the wireless signal.

5G Millimeter-Wave Beamforming System using Substrate Integrated Waveguide

Beamforming is a key element of 5G that uses advanced antenna technologies to focus a wireless signal to a defined direction. Butler Matrix (BM) as a beamforming network is used to control the beam direction by utilizing the amplitude and the output phase. A particular technique for designing BM is through substrate integrated waveguide (SIW), which is used to realize the bilateral edge wall vias where the waveguide mode propagates through to support the current flow and reduce the loss of surface wave. Unlike conventional BM, the proposed design requires only hybrid couplers and phase shifter without any crossover. In this BM structure, the SIW hybrid coupler is designed, with two phase shifters of -90°, and one phase shifter of -180° to control the amplitude and phase shifting. This results in an optimized transmission amplitude and output phase difference. The BM also circumvents any crossover, to provide minimal losses. The hybrid coupler exhibits Sii and Sij characteristics at 28 GHz, with values of -27.35 dB for return loss, -3.9 dB for insertion loss, -3.2 dB for coupling, and -26.54 dB for the isolation. In the BM design, high transmission efficiency is observed where the return loss is less than -10 dB, while minimal transmission amplitudes are obtained within the values of ‒6 ± 3 dB. The three-port BM is designed using SIW with minimal loss and the phase difference at each respective output port of the BM shows values of 0°, -120°, and 120°. The three consecutive beams with the gains of 11.1 dBi for port 1 excitation, 9.06 dBi for port 2 excitation and 10.4 dBi for port 3 excitation is achieved when the antenna array is fed to the BM, and each of the radiated beams has beam angles of 0, -27 and 27 degrees.

Assessment of Active Wheelset Steering System Using Computer Simulations and Roller Rig Tests

The paper is created within a project which aims to design a system of active wheelset steering for an electric four-axle locomotive. The wheelset steering system enables reduction in forces acting in the wheel-rail contacts in a curved track and consequently a reduction in wear and maintenance costs of both vehicles and rails is achieved. The project consists of three main parts: computer simulations, scaled roller rig experiments, and field tests. The paper is focused on the fundamental aspects of the first and the second part on the project. Track curvature estimation based on the rotation of the bogies towards the car body is proposed and assessed by computer simulations across varying track radiuses, vehicle speeds, and friction conditions. The scaled roller rig has been innovated in order to simulate bogie run in a curved track with uncompensated value of lateral acceleration and instrumented with a system of measurement of lateral wheel-rail forces. The experimental bogie has been equipped with systems of active wheelset steering and measurement of axle-box forces. The experiment setup, newly developed and applied systems of forces measurement and wireless signal transmission, and results of the first experiments are described in detail. Performed computer simulations and scaled roller rig experiments show that active wheelset steering is effective and practically implementable method of reducing guiding forces acting between railway vehicle wheels and rails in a curved track.

Federated learning enables intelligent reflecting surface in fog-cloud enabled cellular network

The intelligent reflecting surface (IRS) is a ground-breaking technology that can boost the efficiency of wireless data transmission systems. Specifically, the wireless signal transmitting environment is reconfigured by adjusting a large number of small reflecting units simultaneously. Therefore, intelligent reflecting surface (IRS) has been suggested as a possible solution for improving several aspects of future wireless communication. However, individual nodes are empowered in IRS, but decisions and learning of data are still made by the centralized node in the IRS mechanism. Whereas, in previous works, the problem of energy-efficient and delayed awareness learning IRS-assisted communications has been largely overlooked. The federated learning aware Intelligent Reconfigurable Surface Task Scheduling schemes (FL-IRSTS) algorithm is proposed in this paper to achieve high-speed communication with energy and delay efficient offloading and scheduling. The training of models is divided into different nodes. Therefore, the trained model will decide the IRSTS configuration that best meets the goals in terms of communication rate. Multiple local models trained with the local healthcare fog-cloud network for each workload using federated learning (FL) to generate a global model. Then, each trained model shared its initial configuration with the global model for the next training round. Each application’s healthcare data is handled and processed locally during the training process. Simulation results show that the proposed algorithm’s achievable rate output can effectively approach centralized machine learning (ML) while meeting the study’s energy and delay objectives.

Construction of New Intelligent Teaching Scene Based on Multimodal Wireless Sensing Technology

With the continuous development of computer technology and the gradual popularization of information technology application, the construction of intelligent teaching scene based on wireless sensing technology plays a more and more important role in modern information education. Taking a primary school as an example, this paper introduces multimodal wireless sensing technology into the construction of intelligent teaching system. The purpose of this paper is to explore the construction of a new teaching scene. Firstly, this paper deeply analyzes the sensing mechanism of wireless signal and optimizes the sensing mode, deployment structure, and signal processing in practical application, so that the system can run more effectively in the actual environment. Then, based on multimodal wireless sensing technology, this paper designs and optimizes the basic architecture and functions of intelligent teaching scene. The results show that combining the characteristic information of each mode to get the information conducive to identity confirmation, which can get better recognition performance and improve the accuracy. Combining the information of multiple modes can greatly improve the recognition performance. The user interest model combined with dynamic and static is used to optimize the system recommended resources, so that students can obtain high-quality and highly matched learning resources more quickly and accurately, so as to improve students’ learning efficiency in resource acquisition.

Robot Face and Its Integration to the Mobile Robot for Wireless Signal Collection in the Fingerprinting-Based Indoor Positioning System

The wireless data collection for instance the Received Signal Strength (RSS) of the Wireless Fidelity (Wi-Fi) remained unfavourable in the Indoor Positioning System utilizing the signal fingerprinting approach. This is because the enormous sampling time and routines works making it tedious human labour. To alleviate this issue, we propose to use a robot for wireless data collection. The robot, named ‘ICSiBOT’ is a service robot with multiple purpose such as assisting human in daily lives, guest or hospitality robot and man others. This paper mainly describes the ICSiBOT robot face with speech recognition technology and the integration of the robot face to the motion controller. The experimental was conducted to see the correlation between the synthesized instructions from the speech in terms of distance need to be travelled i.e., the location for wireless signal collection and translate them into actual distance travelled. The results showed that the robot is able to travel to the specific distance as instructed to the robot face.