Examples of applications and implementations of self-organising technology (original) (raw)

Besides the applications of commercial GMDH software since 1967 there were a lot of applications of GMDH in very different fields. Many of them are described in the ukrainian journal "Avtomatica" (translated in "Soviet Automatic Control", "Soviet Journal of Automation and Information Sciences" and then in "Journal of Automation and Information Sciences" in full size). Some examples with descriptions are also given at Script Software site. The basic GMDH technique applications include the studies on:

1. Economic systems
   • Identification of the process of British economy inflation [1]
   • Modelling of the British economy for restoration of the governing laws in the object using OSA algorithm [1]
   • German Democratic Republic economy analysis and forecasting by AC algorithm [2]
   • Forecasting and evaluation of the main factors for the USA economy using OSA [1]
   • Decision support for dollar rate for the period of Persian Gulf oil crisis;
   • New York stock market indexes forecasting using TMNN [9,30,34]
   • World dynamics indexes optimization by SLP [7]
   • Normative forecasting of processes in macroeconomy of the Ukraina by COMBI
   • Prediction of stock market using AC
2. Ecological systems analysis and prediction
   • Oil fields forecasting using OSA algorithm [4]
   • Condition of the Bajkal lake ecological system by OSA algorithm [1]
   • Modeling of Kakhovka and Kremenchug reservoirs ecosystems using the rank correlations [1]
   • Forecasting of Dnieper river flow by Harmonical algorithm [25]
   • Temperature of air and soil modeling
   • Water quality forecasting
   • Winter wheat productivity modeling [1]
   • Wheat harvest as a function of different parameters using COMBI [1]
   • Drainage flow optimization
   • Cl- and NO3 -settlement modeling
   • Influence of natural position factors on harvest growth [1]
   • Ionosphere state definition for optimal radio communication frequencies by MIA
   • Forecasting of pesticides destruction process in fruits using probabilistic algorithm of MTSD
3. Environment systems
   • Solar activity forecasting using Harmonical and Two-level (ARIMAD) algorithm [1];
   • Pesticide type recognition for decision support using pair probability MTSD algorithm;
   • Air and water pollution prediction using MIA and COMBI [7];
4. Medical diagnostics
   • Cancer patients diagnostics using PF clusterization algorithm [6];
   • State of human brain identification using MIA
   • Sleep stage classification
   • Crush injury modeling
5. Demographic systems
   • birth-rate forecasting in GDR using Combi
6. Weather modeling [1]
   • An autonomous system of homogeneous difference equations was proposed to describe the change of instantaneous and averaged values of the variables and to include any source function and external disturbances;
   • Two-level climate predictions were done on the basis of several balances (for example year-season and century-year);
   • A two-level algorithm with several balance criteria for climate modeling;
   • The correlation models were used for predicting weather in movable coordinates (to take winds into account);
   • The ecological variables were used in combined system of weather-climate equations to increase prediction accuracy and lead time;
   • The method of group analogues was used for long-range predictions. it is based on analogues complexing algorithm or on objective clustering of the weather into number of clusters; the set of significant variables was set up objectively by the OSA algorithm;
   • climate/crop forecasting models were developed and described in [11];
   • long-term climate changes was investigated by changes of width of trees rings from Bajkal lake shores [19];
7. Econometric modeling and marketing
   • Steel shipment forecasting
   • Cost-estimating relationships modeling
   • Forecasting of bread and drinks delivery using analog complexing AC algorithm [30];
8. Manufacturing
   • Optimization and forecasting of silk production process
   • Forecasting of cement quality by MIA
   • Hot strip steel mill runout table cooling sprays
   • Crystallization process forecasting
   • Fermentation process modelling
9. Physical experiments
   • parameters of nuclear weapon testing were optimized using TMNN and SLP [9];
   • parameters of sharpening angles of cutting tools was optimized recently by COMBI;
10. Materials

• Radiation embrittlement modeling
• Modeling of single-particle erosion of heat shields
• Weld strength estimation

1. Multisensor signal processing

• Physical security systems

1. Microprocessor-based hardware

• "Smart" ultrasonic flaw discriminator

1. Eddy currents

• Automatic bolthole inspection
• Recirculating and once-through steam generator tubing inspection

1. X-ray

• X-ray image analysis for bomb detection in luggage

1. Acoustic and seismic analysis

• Ocean platform detection and classification
• Seismic discrimination
• Oil and water fields detection by OSA

1. Military systems [11]
   Radar
   • Reentry vehicle trajectory prediction
   • Radar imagery target classification
   • Detection and identification of tactical targets
   • Radar pulse classification
     Infrared
   • Target acquisition and aim-point selection
   • LANDSAT scene classification
     Ultrasonics and acoustics emission
   • Ultrasonic imaging
   • Feedwater nozzle detection
   • Turbine rotor inspection
   • Ultrasonic pipe inspection
   • Monitoring of crack-growth activity
     Missile guidance
   • Equation of hyroscope systems dynamics identification using sorting of difference equations;
   • Air-to-air guidance law synthesis