High Accuracy WiFi-Based Human Activity Classification System with Time-Frequency Diagram CNN Method for Different Places

Older people are very likely to fall, which is a significant threat to the health. However, falls are preventable and are not necessarily an inevitable part of aging. Many different fall detection systems have been developed to help people avoid falling. However, traditional systems based on wearable devices or image recognition-based have many disadvantages, such as user-unfriendly, privacy issues. Recently, WiFi-based fall detection systems try to solve the above problems. However, there is a common problem of reduced accuracy. Since the system is trained at the original signal collecting/training place, however, the application is at a different place. The proposed solution only extracts the features of the changed signal, which is caused by a specific human action. To implement this, we used Channel State Information (CSI) to train Convolutional Neural Networks (CNNs) and further classify the action. We have designed a prototype to test the performance of our proposed method. Our simulation results show an average accuracy of same place and different place is 93.2% and 90.3%, respectively.

Classification of cracking sources of different engineering media via machine learning

Complex civil structures require the cooperation of many building materials. However, it is difficult to accurately monitor and evaluate the inner damage states of various material systems. Based on a convolutional neural network (CNN) and the acoustic emission (AE) time-frequency diagram, we used the transfer learning method for classifying the AE signals of different materials under external loads. The results show the CNN model can accurately classify cracks that come from different materials based on AE signals. The recognition accuracy can reach 90% just by re-training the full connection layer of the pre-trained model, and its accuracy can reach 97% after re-training the top 2 convolutional layers of this model. A realization of cracking source identification mainly depends on the differences in mineral particles in materials. This work highlights the great potential for real-time and quantitative monitoring of the health status of composite civil structures.

Nonlinear Analysis of CCM Superbuck Converter Using Wigner-Ville Distribution

In order to analyze the bifurcation and chaos of Superbuck converter in Continuous Current Mode (CCM), a new method of time-frequency diagram based on Wigner-Ville distribution is proposed. The method is used to analyze the variation of the energy component of the output voltage with frequency and time. It reveals that the Superbuck converter exhibits period-1 bifurcation, period-2 bifurcation, period-4 bifurcation and chaos under different reference current. The results of the time-frequency diagram are consistent with the results of the bifurcation diagram, time-domain diagram, phase diagram and Poincare section. It proves that the method can deeply understand the nature of bifurcation and chaos in Superbuck converter, and it provides a new way to analyze the nonlinear phenomena of DC-DC converter

Study on the Relationship between Electrical Tree Development and Partial Discharge of XLPE Cables

Based on the slice materials of 35 kV and 110 kV XLPE cables, an experimental platform is built to study the relationship between electrical tree and PDs in XLPE with different voltage levels. There are three significant statistical characteristics of the PDs during the growth of electrical trees. The analysis of the results shows that each growth stage has certain characteristics. Different features existed between the growth of the electrical trees and the PD in the insulation of the 35 and 110 kV cables. Evident characteristics such as large spans of time and frequency were present as the electrical trees grew violently in the equivalent time-frequency diagram at every stage. These results could provide criteria for the identification of the deterioration using PD to monitor cables in service at rated voltages. The results are important for the identification of defects in cable insulation in order to provide an early warning of insulation breakdown in the cables.

SPATIAL ANALYSIS OF EROSIVE PROCESSES IN PLATEAUS AND DEPRESSIONS OF THE UPPER PARAGUAI RIVER BASIN

Natural characteristics may contribute to the erosion of the soil and to environmental imbalances, and in most cases, they initiate the imbalances that will be exacerbated by human activities. The presence of asymmetry in a frequency diagram is a valuable fact, and may indicate irregularity in the occurrence of events or aggregation of events in preferred locations. Thus, this work aims to demonstrate the use of Geographic Information Systems (GIS) of statistical analysis based on patterns of frequency, density, distribution and spatial dependence of sample points through a cutout of the mapping of the geotechnical aspects conducted for the State of Mato Grosso, generated for the entire area of plateaus and depressions of the Upper Paraguai river basin and its internal units of drainage basins. In most cutouts used in the analysis, the values indicated that is void the possibility that the distribution patterns of erosive events were resulted of chance. The aggregate pattern shown may tend to attract new points, facilitating the transmission of the sample.s qualities through these, favored by your proximity and by the characteristics of the occurrence area