HYBRID NEURAL NETWORK MODELS FOR MONITORING TIME SERIES DATA OF COMPLEX OBJECTS
Annotation
The problem of monitoring the state of complex objects of various natures based on classification and regression analysis of time series data is considered. Hybrid neural network models of classification and regression analysis are developed and studied using data on the functioning of three types of systems: spacecraft, information system and economic system, presented in the form of time series. For all types of systems, the proposed hybrid models demonstrate an advantage in accuracy. A genetic algorithm is developed for the automatic search of hybrid neural network models, with the help of which models of varying complexity are generated with an accuracy no lower than for models developed manually. As a result of the search, it is noted that the generated hybrid neural networks show results close to the maximum value of the fitness function. The fact is considered as experimental confirmation of the constructed solution to be close to optimal for certain search parameters.
Keywords
Постоянный URL
Articles in current issue
- FORMATION OF SETS OF FIVE-FOLD GOLD-TYPE SEQUENCES FOR DIGITAL INFORMATION TRANSMISSION SYSTEMS
- ENTERPRISE TECHNICAL RISKS ASSOCIATED WITH DIGITAL TRANSFORMATION
- METHOD FOR CREATING AN INTEGRAL ASSESSMENT OF THE QUALITY OF DIFFICULT-TO-FORMALIZE OBJECT
- STATIONARY CHARACTERISTICS OF THE M/G/1/m QUEUING SYSTEM WITH REGARD TO SERVICE QUALITY CONTROL
- CONSTRUCTION, MODELING OF SIGNAL FORMATION AND PROCESSING FOR AIR PARAMETERS MEASURING SYSTEM WITH THE INTEGRATED FUSELAGE FLOW RECEIVER
- TOOLKIT FOR PRELIMINARY DESIGN AT THE STAGES OF DEVELOPING A CONTROL SYSTEM FOR A FLEXIBLE PRODUCTION AREA
- RESULTS OF EXPERIMENTAL PROCESSING OF PHASE MEASUREMENTS OF THE GLONASS SYSTEM USING A NON-BRUTE FORCE INTEGER AMBIGUITY RESOLUTION ALGORITHM FOR HIGH-PRECISION ABSOLUTE LOCATION
- INFLUENCE OF PRESSURE ON THE RESULTS OF MEASURING THE VOLUME FRACTIONS OF GAS COMPONENTS USING RAMAN SPECTROSCOPY
- PATTERNS OF MAGNETIC STRAY FIELD DISTRIBUTION ALONG THE SURFACE OF AN UNDERGROUND MAIN GAS PIPELINE AND AN ELASTICALLY BENT PIPE
- WAVE PROCESSES IN MEDIA WITH CYLINDRICAL SURFACES UNDER RIGID CONTACT
- FEATURES OF CONSTRUCTING A BOND GRAPH OF WALKING ROBOTS
- HYBRID NEURAL NETWORK MODELS FOR MONITORING TIME SERIES DATA OF COMPLEX OBJECTS