Classical signal processing techniques when combined with pattern classification analysis can provide an automated fault detection procedure for machinery diagnostics. Artificial neural networks have recently been est...
详细信息
Classical signal processing techniques when combined with pattern classification analysis can provide an automated fault detection procedure for machinery diagnostics. Artificial neural networks have recently been established as a powerful method of pattern recognition. The neural network-based fault detection approach usually requires pre-processing algorithms which enhance the fault features, reducing their number at the same time. Various time-invariant and time-variant signal pre-processing algorithms are studied here. These include spectral analysis, time domain averaging, envelope detection, Wigner-Ville distributions and wavelet transforms. A neural network pattern classifier with pre-processing algorithms is applied to experimental data in the form of vibration records taken from a controlled tooth fault in a pair of meshing spur gears. The results show that faults can be detected and classified without errors.
A laboratory-made malodour sensing system including 12 commercial tin oxide gas sensors (Figaro Engineering) is used to identify five typical sources of olfactive annoyance: printing houses, paint shop in a coachbuild...
详细信息
A laboratory-made malodour sensing system including 12 commercial tin oxide gas sensors (Figaro Engineering) is used to identify five typical sources of olfactive annoyance: printing houses, paint shop in a coachbuilding, wastewater treatment plant, urban waste composting facilities and rendering plant. In this work, all the samples are collected in the field from real malodours in uncontrollable conditions. The ability of the system to predict the origin of unknowns odoriferous samples is investigated. The test of various pre-processing data algorithms shows that the best classification results are obtained with a parameter free of the sensor base-line. The differences in sensor responses among the five odours are shown by icon plots and confirmed by principal component analysis, which highlights four representative clusters. Classification models calibrated by discriminant analysis and artificial neural network are validated on unknowns samples. Chemical relationships between the sensors and the classification results proves that the recognition is not fortuitous. In spite of the influence of environmental parameters, results demonstrate the ability of a simple system to detect and identify typical olfactive annoyances. (C) 2000 Elsevier Science S.A. All rights reserved.
To enhance detection probability and to reduce false alarms, infrared imagery is pre-processed before subjecting it to detection algorithms in infrared search and track systems. pre-processing algorithms are used to p...
详细信息
To enhance detection probability and to reduce false alarms, infrared imagery is pre-processed before subjecting it to detection algorithms in infrared search and track systems. pre-processing algorithms are used to predict the complex background and then to subtract the predicted background from the original image. The difference image is passed to the detection algorithm to further distinguish between the target and the background and/or noise more accurately. A number of pre-processing algorithms have been reported in literature, with their relative advantages and disadvantages. This paper brings out the computational complexities and simulation results of various algorithms for assessing their relative performances. Based on these parameters, statistical algorithms in general and max-min algorithms in particular, are recommended to be used for infrared search and track systems.
Unobstructed, large RCS targets, similar radar targets surrounded by moving foliage, and small targets in severe clutter have been used as test cases for two pre-processing algorithms and several threshold levels in a...
详细信息
Unobstructed, large RCS targets, similar radar targets surrounded by moving foliage, and small targets in severe clutter have been used as test cases for two pre-processing algorithms and several threshold levels in an experimental millimeter wave radar system. The rather conventional "six-out-of-eight" pulse radar selection method with binary output has been compared to an algorithm that accepts a target. if the pre-defined trigger level is crossed by the average of the eight consecutive pulses. In this case, however, the output is an analog value corresponding to the relative average video amplitude. In terms of plotted video, this process seems to give a slightly better combination of false alarm rate and detection probability. Large targets are easier to detect from foliage clutter with the conventional method.
Today real-time studying and tracking of movement dynamics of various biological objects is important and widely researched. Features of objects, conditions of their visualization and model parameters strongly influen...
详细信息
ISBN:
(数字)9781510608269
ISBN:
(纸本)9781510608252;9781510608269
Today real-time studying and tracking of movement dynamics of various biological objects is important and widely researched. Features of objects, conditions of their visualization and model parameters strongly influence the choice of optimal methods and algorithms for a specific task. Therefore, to automate the processes of adaptation of recognition-tracking algorithms, several Labview project trackers are considered in the article. Projects allow changing templates for training and retraining the system quickly. They adapt to the speed of objects and statistical characteristics of noise in images. New functions of comparison of images or their features, descriptors and pre-processing methods will be discussed. The experiments carried out to test the trackers on real video files will be presented and analyzed.
The main aim of this study was to evaluate the feasibility of hyperspectral imagery for determining the correlation between fish skin changes and different diets. Rainbow trout (Oncorhynchus mykiss) were fed either a ...
详细信息
The main aim of this study was to evaluate the feasibility of hyperspectral imagery for determining the correlation between fish skin changes and different diets. Rainbow trout (Oncorhynchus mykiss) were fed either a commercial based diet (N = 80) or a 100% plant-based diet (N = 80). Hyperspectral images were made using a push-broom hyperspectral imaging system in the spectral region of 394-1009 nm. All images were calibrated using dark and white reference, and the average spectral data from the region of interest were extracted. Seven spectral pre-treatment methods were used, including Savitzky-Golay (SG), First Derivative (FD), Second Derivative (SD), Standard Normal Variate (SNV), Multiplicative Scatter Correction(MSC) and Continuum removal (CR) then a support vector machine (SVM) with linear kernel was applied to establish the classification models. Overall classification models developed from full wavelengths with different preprocessing methods showed good performance (Correct Classification Rate (CCR) = 0.83, Kappa = 0.66) when coupled with SG and SD or SG and MSC. The overall results indicate that the integration of Vis/NIR hyperspectral imaging system and machine learning algorithms have promise for discriminating different diets based on the live fish skin. These procedures can be used to not only identify the diet used for fish feeding in the case where we are not sure but also monitor different diets impacts on live fish skin for more precise monitoring of fish status during cultivation and ultimately for better implementation of precision fish farming.
暂无评论