During the past few years, various traffic-flow forecasting models, i.e. an ARIMA, an ANN, and so on, .have been developed to predict more accurate traffic flow. . However, these strategies rest on the assumption that the pattern that has been identified will continue into the future. So AMMA or ANN models with its traditional architecture cannot be expected to give good predictions unless this assumption is valid.In this paper, we compared with an ANN model and ARIMA model and tried to combine an ARIMA model and ANN model for obtaining a better forecasting performance. In addition to combining two models, we also introduced judgmental adjustment technique that has an effect on correcting irregular and infrequent future events. Our approach can improve the forecasting power in traffic flow.To prove it, we have compared the performance of the models..

The accuracy with which simulation techniques can be used to predict the performance of an experimental high speed M-QAM testbed in typical indoor wireless environments is studied in this paper. Ray tracing techniques were used to produce impulse responses for specific transmit and receive antenna locations where actual measurements were taken using a highly versatile equalized M-QAM testbed operating at 10 Mbps, 20 Mbps and 30 Mbps [l]. The results obtained using a simulation of the testbed plus the ray-traced channel are compared with those obtained with experimental field trials. The paper presents the results of such comparisons for a total of 2,322 trials, where a trial is defined as a simulation run plus a field test for a given data rate and antenna location. The study shows that when quantization noise is factored into the simulation, the performance predicted using the simulation approach closely matches the experimental data.