This paper studies the grey coupled prediction problem of traffic data with panel data characteristics. Traffic flow data collected continuously at the same site typically has panel data characteristics. The longitudinal data (daily flow) is time-series data, which show an obvious intra-day trend and can be predicted using the autoregressive integrated moving average (ARIMA) model. The cross-se...

duce acoustic images of the~seafloor on-line with a Sea Beam multibeam echo-sounder. This ystem uses a stand alone interface between the Sea Beam system and a grey-scale line-scan recorder. The interface is built around a Motorola 68000 microprocessor and has digitizing capabilities. I t digitizes the detected echo signals from each of the 16 preformed beams inside the Sea Beam echo process...

This paper presents a grey–fuzzy predictive controller that is based on fuzzy theory, grey prediction and on-line switching algorithms. The grey predictor is applied to extract key information and reduce the randomness of the measured non-stationary time-series signals from sensors, and send the prediction information to the fuzzy controller. The complete mathematical model is derived and the s...

This paper puts forward a reliability estimation method by the Degradation Amount Distribution (DAD) of products, using a composite time series modeling procedure and grey theory based on a random failure threshold. Product DAD data are treated as a composite time series and described using a composite time series model to predict a long-term trend of degradation. The degradation test is proces...

ii Captain Toolbox CAPTAIN is a MATLAB ® compatible toolbox for non stationary time series analysis, system identification, signal processing and forecasting, using unobserved components models, time variable parameter models, state dependent parameter models and multiple input transfer function models. CAPTAIN also includes functions for true digital control. iii Toolbox Installation CAPTAIN i...

Non-equidistance grey model NGM(1,1) which was proposed by Deng has emerged as a powerful tool for the prediction and analysis of non-equidistance data series under uncertain system. It carries out the system analysis and prediction based on accumulated generating operation (AGO) to reduce the randomness of original series and obtain high accuracy. But the AGO only used observed whitening data,...

in this paper, we propose a new residual analysis method using fourier series transform into fuzzy time series model for improving the forecasting performance. this hybrid model takes advantage of the high predictable power of fuzzy time series model and fourier series transform to fit the estimated residuals into frequency spectra, select the low-frequency terms, filter out high-frequency term...