Search results

In this paper, Generalized Hebbian Algorithm (GHA) [5], as an unsupervised neural network for PCA, is adopted to reconstruct the images and predict the adjacent frames, which can avoid computing the covariance matrix from the complete data set in advance based on the inter-frame correlation among the video frames.
Since, this is a dimension reduction process, expressed by linear projection as.
It’s not necessary to compute the covariance matrix from the complete data set in advance; the eigenvectors can be derived directly from the data [9].
is an matrix, and , the th frame data in block ,is -dimensional.
To get the initial image data, of course we also need to add the mean vector to the recovered image.

In response to this shortcoming, many scholars have used a method of combination with PCA and LDA [8], the advantages of the PCA and LDA together fully integration, and it can not only solve the problem of PCA algorithm is not sensitive to the different training sample data problem, but also LDA algorithm when the within-class scatter matrix is singular, and obtain a better classification results.
The sampling time for each sample is 60 seconds and the rinsing time is set as 110 seconds, The interval for data collection was one second.
When the measurement was completed, the obtained data was stored in a computer for later analysis.
The reason is when the difference of sample quality grade is small, there is a big overlap of information or relevance in the differences in the sample that reflect by electronic nose sensor , PCA algorithm to find only the data distribution of spindle orientation, retained after dimensionality reduction by the information is not necessarily the most effective for classification .
Conclusions In this paper, PEN3 electronic nose was used to test Atractylodes samples of three growing areas, data analysis method using LDA algorithm based on MSD criterion to solve the problem of small samples, also distinguish with three Atractylodes from three different growing areas correctly, and the correct recognition rate of all testing samples reaches 97.8%.Furthermore, the classification results clearly superior to the use of PCA or PCA + LDA algorithm.

PPCA model [2-4] is a generated model by adding the noise with the assumption that its variance is isotropic to Factor In fact, PPCA model is also a latent variable model with factor analysis method and its mathematical model is given by the following equation (1) where X is the original variable and represents a matrix sample data with normalized processing, m is the number of samples, and n is the number of original variables, P is a load vector not known previously; e (t) is Gaussian noise.
After the original data X is decomposed into the summary of the outer product of load vector P, the main element model can be expressed by (2) where represents the main element column vector, is the column vector of load.
From Fig. (2), we can see that each main element is the projection of original data X onto the direction of the load, which are selected to reconstruct new data, ultimately a reduction matrix with lower dimension is got and the de-noising purposes.
The test system consists of speed monitor, manual speed governor, acceleration sensors, speed sensors, motors, spindles and computer with VQ data acquisition software.
In the experimental study, the sampling frequency is 25.6 kHz and 327680 data points are collected.

The temperature and the changes of it were consistently recorded using a data logger.
Experimental uncertainty To quantify the uncertainties of measurements, the reduced data obtained experimentally were determined.
The uncertainty in the data calculation was based on Ref. [8].
Data reduction The Reynolds number (Re) is given by (1) The friction factor (f) computed by pressure drop across the length of the test section (L) is (2) In the experiment, the steady state of the convective heat transfer rate is assumed to be equal to the heat loss from the test section.
In the figure, the measured data are in good agreement with the correlation’s data.

Data were collected from the «Rigaku» D/max-2500 diffractometr (Cu Kα1 radiation, λ=1.54 Å).
Analysis of the phase composition and the refining of the XRD data were carried out with the Rietveld method.
The points represent the raw data, the upper continuous line is a calculated profile, the lower continuous line is the difference plot, and the upper and low vertical tick marks show the Bragg positions for the MgH2 and Mg phases respectively.
XRD data obtained for the third set of the samples shows that after several days the samples contain practically only the Mg phase (Fig. 4, Table 1).
The XRD data shows that in our case this reaction ends up with the formation of pure Mg phase, and we do not detect any amounts of MgH2 or Mg(OH)2.

These data contain information on the size, orientation, position or velocity of objects.
Additional to those capabilities that make it advisable to operate with a variety of signals, the program has designated in Matlab Simulink two toolboxes dedicated for operation with signals containing images or video data.
To reduce the volume of information processed, the signal obtained from the video camera is converted in black and white signal that contains only data about the pixel brightness, regardless of their colour.
To adjust the light intensity of the whole image a gain block was used for amplification / reduction in brightness.
The second view, which has the highlighted area, is particularly useful during the calibration application because the overall information on the data provided by the camera.

The variation law of the strength parameters of the soils with water content is studied through analyzing the testing data.
The soil samples are dried and grinded and prepared by layer-compacting method in order to obtain the optimum testing data.
Fig.1 Cohesion of slide body and slide zone soils under different water content w－wp / % c /c0 w－wp / % c /c0 slide body slide zone It is shown in the Fig.1 that the fitting curve coincides with the testing data.
Internal Friction Angle of Slide Zone and Slide Body Soils Through analyzing the testing data of slide zone and slide body soil, the relation of internal friction angle f with water content approximately conforms to the following linear relation through normalizing method
The Fig.2 shows that the fitting curve coincides with the testing data.

We use the dimensionality reduction method to change the three-dimensional problem into one-dimensional question.
Example: According to the following data, design NGW type planetary transmission: The velocity ratio, input rotational speed, input power , the efficiency is not lower than 0.5, the sun gear a is primarily moving part, the involute standard straight spur gear, the precision class 6 levels, this system is used mainly in the power drive.
We can obtain the optimal solution through inputting known data in the data window and operating procedure.
The optimization design data is showed in Table 1.
The following statements are part program of parametric assembly drawing according to the optimization result data, the final assembly drawing is shown in Fig.2.

The modulus of elasticity and the stress-strain diagram used data which is obtained after the miniaturized shear experiment of each solder alloy.
By using this stress-strain curve, the non-linear region data was inputted.
It can be seen a plenarily reliable data.
When comparing with the average data of several test values, the interpretation result is satisfactory.
However, the more effort and researches are necessary to secure a reliable and objective data than FEM analysis.

Vikasonic is an apparatus, which consists of two ultrasonic transducers (transmitter and receiver), measuring cell, vicat ring, thermocouple and data logger.
For the purpose of continuous data recording the apparatus is equipped with the USB flash drive.
Fig. 1: Arrangement of Vikasonic apparatus before (left) and during the measurement with details of display (right) The measured values are shown right on the display of data logger (see Fig. 1) and recorded on the USB flash drive in format “.txt” file during whole time of measurement.
The file contains two data sets – the data collected by direct measurement (date, time of measurement, strength of received pulse, US transit time and internal temperature of the specimen) and data which are in parallel continuously calculated from the measured and preset input values (pulse velocity and dynamic value of elastic modulus).
The figure shows that the addition of the aggregate in to the cement paste reduces the heat released by cement hydration (it is reflected on the reduction of the absolute value of the test specimens’ internal temperature) and shifts the setting time of composite.