Narrow Results

With the rapid development of smart devices and WiFi networks, WiFi-based indoor localization is becoming increasingly important in location-based services. Among various localization techniques, the fingerprint-based method has attracted much interest due to its high accuracy and low equipment requirement. Traditional fingerprint-based indoor localization systems mostly obtain positioning by measuring the received signal strength indicator (RSSI). However, the RSSI is affected by environmental influences, thereby limiting the precision of positioning. Therefore, we propose a new indoor fingerprint localization system based on channel state information (CSI). We adopt a novel method, in which the amplitude and phase of the CSI are fused to generate fingerprints in the training phase and apply a weighted $k$-nearest neighbor (KNN) algorithm for fingerprint matching during the estimation phase. The system is validated in an exhibition hall and laboratory and we also compare the results of the proposed system with those of two CSI-based and an RSSI-based fingerprint localization systems. The results show that the proposed system achieves a minimum mean distance error of 0.85m in the exhibition hall and 1.28m in the laboratory, outperforming the other systems.

With the advancement of smart mines, the need for gesture recognition for remote interaction between underground workers and machines has become crucial. However, traditional gesture recognition techniques require complex models that are very difficult to be deployed to the edge. To address this challenge, a gesture recognition method based on knowledge distillation is proposed in this study. First, the CSI ratio model is used to eliminate phase error and environmental noise, followed by the application of discrete wavelet transform to eliminate hardware noise interference. Then, the processed data is adaptively segmented using the principal component analysis and local anomaly factor algorithm to eliminate redundant static components. After that the processed CSI data is transformed into images using the relative position matrix method. Finally, knowledge distillation is employed to migrate knowledge from a teacher model to a student model, reducing the number of model parameters. Experiments conducted on the proposed method showed that it can achieve a recognition accuracy of 94.2% for hand gesture detection, which meets the requirement for gesture recognition in the mining industry.

In this paper, a method that uses RBF-BP neural network to generate fingerprint database (FD) is proposed to improve the quality. The reference points in the database present regular tetrahedron distribution in three-dimensional space. To improve the accuracy of selecting which points are considered to locate currently and estimating their weights, two positioning algorithms based on signal strength difference values (SSDV) are proposed through analyzing the characteristic of difference values between mobile receiver and reference points. The first one is fuzzy logic algorithm (FLA). It uses different fuzzy logic models to calculate the weights of considered points. The second one is RBF-BP neural network algorithm (NNA). It uses different neural network models to estimate the spatial distances between mobile receiver and reference points. The points which have small sum of distances are considered. Their weights are calculated by a newly proposed method. The proposed algorithms use more than one weight to describe the distance to one considered point, which is more accurate. The test results demonstrate the improvement and effectiveness of proposed methods by comparing with other existing methods.

A multi-functional crop intelligent monitoring system, including internet and Arduino micro-controllers, function to upload humiture, soil moisture, light intensity, PM2.5, harmful gas and other real time data. The system's other functions include automatic watering of crops when the humidity data exceeds warning levels, broadcasting the condition of crops by Microblog, remotely controlling the watering and lighting by web and WeChat and remote video monitoring. Data collection of sensor data is conducted by Arduino UNO micro-controller and the data is uploaded real time into the internet by HLK-RM04 WiFi module. Software functions of the system include real time charts by Websocket, JavaScript in PC and mobile internet, and concurrently, the implementation of WeChat control and Microblog broadcast through Tencent micro channel public platform and Sina Microblog.

ACFM is a kind of non-destructive testing technique based on electromagnetic induction principle, whose operation is so simple that can rapidly find surface and near surface defects. However, the interface software of ACFM instrument produced at home needed to run on a computer or laptop for further data analysis and waveform display, which was no convenient for special occasions, such as testing of pressure vessel, large entertainment equipment. In order to develop the advantages of the real-time detection of ACFM, this paper proposes an ACFM interface software based on Android, which can be loaded in portable devices running on Android system and can be operated through the touch screen .Just open Wifi to connect wireless probe can start testing.