Classroom teaching, as the basic form of provides students with an important channel to acquire information and skills. The academic performance can be evaluated predicted objectively based on data their classroom behaviors. Considering complexity environment, this paper firstly envisages a moving target detection algorithm for student behavior recognition in class. Based region interest (ROI) face tracking, authors proposed two algorithms recognize standing Moreover, was developed hand...

Flow control can effectively improve lift and delay flow separation. Sweeping jet (SWJ) actuators have attracted increasing interest for as active actuators. In this paper, the characteristics of SWJ actuator were studied through large-eddy simulation experiments. It was discovered that oscillation frequency is directly proportional to mass rate, its working principle determined. Subsequently, with [Formula: see text], 1.9%, 6.6% applied on hump airfoil. observed an increase in momentum...

This work presents a spectral matching algorithm of missile plume detection that based on neural network. The radiation value the characteristic spectrum tail flame is taken as input network's structure including number nodes and layers determined according to bands types. We can get network weight matrixes threshold vectors through training using samples, we determine performance testing test samples. A small amount data cause has advantages simple practicality. Network composed matrix...

An ultraviolet detecting system for electrical faults is designed and built to locate the fault precisely classify its pattern level as few studies have been done on. Self-organizing feature extraction method devotes itself state recognition approach in high-voltage discharge. The established including filter system, image collection preprocessing extraction, could identify device operation conditions accurately tested by simulation.

Kernels play a crucial role in Gaussian process regression. Analyzing kernels from their spectral domain has attracted extensive attention recent years. mixture models (GMM) are used to model the spectrum of kernels. However, number components GMM is fixed. Thus, this suffers overfitting or underfitting. In paper, we try combine with nonparametric Bayesian models. Dirichlet processes resolve problem by changing according data size. Multiple experiments have been conducted on and it shows...

According to the problem of corona discharge, a new image fusion rule based on wavelet transform was proposed, making double spectrums imaging system about spectrum characteristic high-voltage electrical corona. The validity and feasibility has been approved by using Matlab as experiment platform in paper. experimental results show that proposed algorithm is very effective fusion, which fuses more details input images improve locating precision detection system.

The Article analyzed the gas-liquid-solid flow characteristics during sewage suction process of fish tank pipeline pneumatic lifting device, and studied influence structural form device on performance.According to data analysis results, following conclusions can be drawn: When particles reach a stable state in tank, sedimentary account for about 26.7% total particles, suspended 14.5%, turbulent 58.8%;The three-phase gas stripping is divided into initial stage, pressure relief stage stage;...

With the modern development of city, highspeed train traffic plays a significant role in public transportation. However, high-speed trains run frequently through long routes. Once fault occurs, personal safety passengers will be danger. Therefore, diagnosis becomes particularly important. In order to speed up detection, bottom is scanned by 3D camera before enters station so that can detected enter station. It buy more time for staff carry corresponding tools repair if faults are detected....