Detection Precision of Seedmeter for Large-granule Seeds

A detecting method based on machine vision was put forward to test the performance of seedmeter with corn and soybean seeds as test samples,in which MATLAB software was applied to process image data and analyze the results.The experimental results showed that the mean value of absolute error of the sowing speed for soybean was 0.004-0.68 seed ？ s-1;the mean value of relative error was from 6.5% to 130%,and there were no significant differences of mean value,standard deviation and coefficient of variation of flowing seeds between manual statistics and MATLAB statistics.The machine vision method was proved to be time-saving,labor-saving and no-touching in the seedmeter precision detecting.

BP neural networks and random forest models to detect damage by Dendrolimus punctatus Walker

The construction of a pest detection algorithm is an important step to couple"ground-space"characteristics,which is also the basis for rapid and accurate monitoring and detection of pest damage.In four experimental areas in Sanming City,Jiangle County,Sha County and Yanping District in Fujian Province,sample data on pest damage in 182 sets of Dendrolimus punctatus were collected.The data were randomly divided into a training set and testing set,and five duplicate tests and one eliminating-indicator test were done.Based on the characterization analysis of the host for D.punctatus damage,seven characteristic indicators of ground and remote sensing including leaf area index,standard error of leaf area index(SEL)of pine forest,normalized difference vegetation index(NDVI),wetness from tasseled cap transformation(WET),green band(B2),red band(B3),near-infrared band(B4)of remote sensing image are obtained to construct BP neural networks and random forest models of pest levels.The detection results of these two algorithms were comprehensively compared from the aspects of detection precision,kappa coefficient,receiver operating characteristic curve,and a paired t test.The results showed that the seven indicators all were responsive to pest damage,and NDVI was relatively weak;the average pest damage detection precision of six tests by BP neural networks was 77.29%,the kappa coefficient was 0.6869 and after the RF algorithm,the respective values were 79.30%and 0.7151,showing that the latter is more optimized,but there was no significant difference(p>0.05);the detection precision,kappa coefficient and AUC of the RF algorithm was higher than the BP neural networks for three pest levels(no damage,moderate damage and severe damage).The detection precision and AUC of BP neural networks were a little higher for mild damage,but the difference was not significant(p>0.05)except for the kappa coefficient for the no damage level(p<0.05).An"over-fitting"phenomenon tends to occur in BP neural networks,while RF method is more robust,providing a detection effect that is better than the BP neural networks.Thus,the application of the random forest algorithm for pest damage and multilevel dispersed variables is thus feasible and suggests that attention to the proportionality of sample data from various categories is needed when collecting data.

Ultralow-noise single-photon detection based on precise temperature controlled photomultiplier with enhanced electromagnetic shielding

We demonstrate an ultralow-noise single-photon detection system based on a sensitive photomultiplier tube（PMT） with precise temperature control, which can capture fast single photons with intervals around 10 ns.By improvement of the electromagnetic shielding and introduction of the self-differencing method, the dark counts（DCs） are cut down to ~1%. We further develop an ultra-stable PMT cooling subsystem and observe that the DC goes down by a factor of 3.9 each time the temperature drops 10°C. At -20°C it is reduced 400 times with respect to the room temperature（25°C）, that is, it becomes only 2 counts per second, which is on par with the superconducting nanowire detectors. Meanwhile, despite a 50% loss, the detection efficiency is still 13%. Our detector is available for ultra-precise single-photon detection in environments with strong electromagnetic disturbances.

Highly precise micro torsion angle detection by fringe array

Pringe array is proposed as the cooperated target in the precise torsion angle detection. The target fringe array image is generated according to the structure of the optical system, and the torsion angle detection algorithm is analyzed in response to the gray distribution of the image. The factors affecting the detection precision of the fringe torsion angle are analyzed theoretically and numerically. It indicates that the detection precision of the torsion angle is 1 angular second or even less, carefully selecting the detector array. Significantly, experiments are performed to demonstrate the precision and the results match well with the simulations.