This article is considered Immunological method of the railway vehicle's parts localization based on the clonal selection algorithm. The advantage of this approach is the use of one-class support vector machine, which allows classifier training with only positive examples. The suggested approach significantly reduces complexity and formation of the training sample set. Immunological localization method has high performance characteristics due to the hybrid application one-class support vector machine and clonal selection algorithm. This allows to optimize the procedure of objects finding in the analyzed image

Keywords: Immunological localization method, clonal selection algorithm, one-class support vector machine

Developed a rapid method for evaluation of the homogeneity of mixtures hardly separated granular materials, the analysis of which is the use of known methods is impossible or time-consuming. The method is based on the separation of mixture components by color using computer processing of pictures of her samples. To implement the developed computer program that can calculate the values of the coefficient of heterogeneity of the mixture, as well as other dispersion parameters.

Keywords: express method, the concentration of the mixture, component, granular material, image, distribution, shade of gray, the coefficient of heterogeneity

The analysis of existing methods of warming up the "old" asphalt with regard to its further use. Found that known methods of heat grinding are energy-intensive, which limits their use in industry. A new method of thermal regeneration based inkjet influence of coolant with subsequent classification of the particles.

Keywords: asphalt, grinding, heating, classification, agglomerate, device, analysis, method, jet, coolant, air

This paper proposes a new approach to railway vehicles localization based on image processing method consists in the recognition of the railway car coupler on the graphical images obtained by cameras of versatile automatic recognition system for railway cars’ numbers (versatile ARS-RCN system). A model based on the recognition of the coupling of the real-valued negative selection algorithm with variable-sized detectors was developed. Computational experiments that showed the effectiveness of developed model in comparison with the classical support vector machine on real data collected on one the versatile ARS-RCN system object were performed. The effectiveness of the proposed approach in the duplicated mode (using two cameras) and in combination with the basic method of localization of mobile units on the basis of inductive sensors passing wheels was showed.

Keywords: artificial immune system, soft computing, localization of railway vehicles , identification of cars’ numbers

This paper presents a new neuroimmune-based method for block recognition of railway rolling stock inventory numbers. The advantage of such approach is  classification without using of negative samples. Developed technique combines segmentation and classification that allows to achieve higher noise robustness, segmentation possibility of fuzzy combined digits which have different fonts and typeface, and invariance of existing numbers to scale changes. Proposed method allows to constantly increase the training set for the improvement in classification accuracy by new committee classifiers statistics due to the data reduction property achieved by using the immune clustering mechanism. Research results were implemented in the software system of automatic recognition of cars numbers (ARNV), which is operated on the JSC Russian Railways.

Keywords: Method for letters block recognition, the committee neuroimmune classification model, identification, automatic recognition car number, duplicate number