This study introduces a new algorithm to optimize the pattern recognition of different white blood cell types in flow cytometry. The behavior of parametric data clusters in a multidimensional space is analyzed using the learning system known as Support Vector Machines (SVM). Beckman‐Coulter Corporation supplied flow cytometry data of numerous patients to be used as training and testing sets for the algorithm. Subsequently, the characteristics of the cells provided in these sets were used to train a SVM based classifier. The objective in developing this algorithm was to identify the category of a given blood sample and provide information to medical doctors in the form of diagnostic references for a specific disease state, lymphocytic leukemia. With the application of the hypothesis space, the learning bias and the learning algorithm, the SVM classifier was successfully trained to evaluate misclassification ratios in flow cytometry data in an effort to recognize abnormal blood cell patterns and address the ubiquitous problem of data overlap through the use of the maximal margin classifier. 相似文献
In this letter,we propose and demonstrate a simple and novel method for fiber chromatic dispersion(CD) measurement based on microwave photonic technique.The radio frequency(RF) signal is modulated simultaneously on two light-waves with different wavelengths,and the light-wave carrying RF signals transmit through the dispersive medium under test.CD can be obtained by monitoring the power changing of the interference RF signals after photo detector.The CD values of the single-mode and dispersion compensation fibers are both measured within the wavelength range from 1 525 to 1 605 nm,which verifies the feasibility of this method. 相似文献
The synergic effect of sawdust (SD) and a lignite can be observed by analyzing their co-pyrolysis behavior. The co-pyrolysis behavior of SD and lignite mixtures was investigated by thermo-gravimetric analysis, and their sulfur transformation was measured by X-ray absorption spectroscopy (XAS). The pyrolysis process can be divided into three stages for SD and lignite, while four their mixtures. The experimental mass loss of SD and lignite mixture during co-pyrolysis is higher than its theoretically calculated mass loss, especially at the mixing ratio of 1:1. This indicates that synergy occurs during SD and lignite co-pyrolysis process. XAS spectra of sulfur show that SD can promote FeS to decompose before 900 °C during co-pyrolysis, as the peak of FeS decreases in the mixture’s char. However, the experimental sulfur removal of mixtures is lower than the theoretically calculated one. This indicates that synergic effect has no effect on sulfur removal, which is very corresponding to more thiophenes gathering in the mixture’s char, because the peak of thiophenes is very steep for the mixture after pyrolysis. And other sulfurs transformation in the mixture is very similar to that of CF coal. For CF coal and its mixture, sulfate peak increases obviously after pyrolysis, which is mostly caused by absorbing SO2 of alkaline minerals during pyrolysis. This also suggests SD cannot prevent sulfate from forming during co-pyrolysis. Therefore, SD can be added to promote high-pyrite coal to increase sulfur removal, since the decomposition of FeS needs higher temperatures.
We propose and demonstrate a photonic approach to instantaneous frequency measurement with an extended range based on phase modulation.In the measurement system,two optical wavelengths and two dispersion fiber segments are used to construct the frequency-dependent amplitude comparison functions(ACFs).Several ACFs can be utilized jointly to determine the microwave frequency without ambiguities beyond a monotonic region of the lone conventional ACF.The measurable range of microwave frequency can be extended and the accuracy can be improved by selecting an ACF with a large slope.The experimental results show that the errors are limited within ±140 MHz of a frequency measuremental range from 8 to 20 GHz. 相似文献