Nosov, K.Zholtkevych, G.Georgiyants, M.Vysotska, O.Balym, Yu.Porvan, A.2018-06-072018-06-072017Nosov K., Zholtkevych G., Georgiyants M., Vysotska O., Balym Y., Porvan A. Development of the descriptive binary model and its application for identification of clumps of toxic cyanobacteria // Eastern-European Journal of Enterprise Technologies. 2017. Vol 4. № 4 (88). С. 4-11. http://journals.uran.ua/eejet/article/view/108285/104194 (Scopus)http://openarchive.nure.ua/handle/document/5974In the paper, a descriptive model of system dynamics for binary data is presented. Binary or dichotomous data are widely spread across various fields of research - in decision making and data mining, marketing, solving of many natural, social and technical problems. The initial data for building the model is a set of states of an autonomous dynamical system with components taking binary values. At the same time, the time order of the states is permissible. The following objectives were stated: to identify the relationships between the components of the system defining its dynamics; on the basis of the identified dynamics, to recover the true order of the system states; to apply the developed model to the problem of visual identification of cyanobacteria in water areas using digital photography. To solve the problem, we used a mathematical model that enables to describe the relationships between components and transitions between the system states at a simple-forunderstanding level. The principle of parsimony underlies the model. According to this principle, the most appropriate model is described by the simplest relations in the sense defined in the work. As the case study, the problem of recognizing clumps of cyanobacteria from digital satellite imagery was considered. This is a complex, practically important problem that does not have a satisfactory experimental and theoretical solution at the moment. Applying system approaches to the measured colorimetric parameters of digital photography, we developed the index for identification of such clumps. This index uses the parameters of the digital RGB model of (various parts of) an image and allows us to reveal clumps of cyanobacteria on digital images obtained by aerospace methods. Additionally, digital photography can be performed in the conditions of insufficient visibility (due to precipitation, fog, and other factors), for imitation of which in the case study the original image was distorted by the digital noise. The studied model can find useful applications in the areas requiring binary dynamical data insights. Представлена дескриптивна динамічна модель бінарних даних, що дозволяє по вихідним спостереженнями з порушеним часовим порядком відновити вихідний порядок на підставі принципу парсимонії. Модель застосована для знаходження системних колориметричних параметрів, використовуваних для обробки зображень скупчень токсичних ціанобактерій на основі аналізу компонентів RGB-моделі цифрової фотографії Представлена дескриптивная динамическая модель бинарных данных, позволяющая по исходным наблюдениям с нарушенным временным порядком восстановить исходный порядок на основании принципа парсимонии. Модель применена для нахождения системных колориметрических параметров, используемых для обработки изображений, скоплений токсических цианобактерий на основе анализа компонентов RGB-модели цифровой фотографии.en-USBinary dataClumps of toxic cyanobacteriaData miningDescriptive modelsDynamical systemsParsimonyArticle