THE PURPOSE OF THIS STUDY WAS TO PREDICT THE BANKRUPTCY OF COMPANIES LISTED IN TEHRAN STOCK EXCHANGE IS USING RADIAL BASIS FUNCTION NEURAL Network (RBF). THIS STUDY IS A QUASI-EXPERIMENTAL BECAUSE LOOKING CAUSAL FACTORS ON THE FACTS AND CIRCUMSTANCES OF RESEARCH. STATISTICAL POPULATION BANKRUPT COMPANIES COVERED BY ARTICLE 141 OF THE COMMERCIAL CODE, 2012 AND 2013 YEARS AND 99 HEALTHY COMPANIES ON THE BASIS OF PROFITABILITY FOR THE TWO YEARS. HEALTHY COMPANIES WERE SELECTED THROUGH RANDOM SAMPLING. 5 INDEPENDENT VARIABLES INVESTIGATED INCLUDE WORKING CAPITAL TO TOTAL ASSETS, THE CUMULATIVE GAIN OR LOSS TO TOTAL ASSETS, EARNINGS BEFORE INTEREST AND TAXES EBIT TO TOTAL ASSETS, BOOK VALUE OF EQUITY TO BOOK VALUE OF TOTAL DEBT TO TOTAL ASSETS, WHOLE SALE AND THE DEPENDENT VARIABLE IS A BINARY VARIABLE EQUAL TO ZERO FOR NORMAL AND HEALTHY TO HAVE ONE. AFTER STATISTICAL SOFTWARE WEKA WITH RADIAL BASIS FUNCTION NEURAL Network TO PREDICT THE RATE OF 91 TO 95.34% AND 90.69% IS EQUAL TO 92 YEARS.

MICROBIAL FUEL CELL IS A NEW TECHNOLOGY AND IT IS A BIOREACTOR FOR ELECTRICITY GENERATION. THIS TECHNOLOGY IS ABLE TO TREAT BIODEGRADABLE ORGANIC MATTER AND GENERATE ELECTRICITY SIMULTANEOUSLY. ELECTRONS AND PROTONS PRODUCE BY OXIDATION OF ORGANIC MATTER AND THEN ELECTRONS MOVE FROM EXTERNAL RESISTANCE WHILE PROTONS TRANSFER ACROSS MEMBRANE AND REACTION BETWEEN ELECTRON, PROTON AND OXYGEN PRODUCE WATER ON CATHODE SURFACE. DIFFERENT KIND OF CONFIGURATION IS PRESENTED FOR MICROBIAL FUEL CELL SUCH AS DUAL AND SINGLE CHAMBER WITH MEMBRANE AND WITHOUT MEMBRANE. IN THIS RECENT STUDY BY APPLYING THE ARTIFICIAL NEURAL Network, WE HAVE PREDICTED BEHAVIOR OF THE MICROBIAL FUEL CELL, SO A MULTILAYER PERCEPTRON (MLP) WAS USED WHICH RESULTS OF Prediction WERE SHOWN A GOOD FIT BETWEEN ACTUAL AND Prediction DATA WITH NEGLIGIBLE MEAN SQUARE ERROR. ARTIFICIAL NEURAL Network (ANN) UTILIZES INTERCONNECTED MATHEMATICAL NODES OR NEURONS TO FORM A Network THAT CAN MODEL COMPLEX FUNCTIONAL RELATIONSHIP.