Patent
1993-12-09
1995-08-22
MacDonald, Allen R.
395 23, 395 11, 395 61, 395900, G06F 1518
Patent
active
054448204
ABSTRACT:
A hybrid fuzzy logic
eural network prediction system and method is disclosed for predicting response times to service requests to a service provider. Data from a historical database of records including customer requests and weather information are input to the hybrid system. The data is filtered to reject faulty data entries and data not necessarily useful for predicting response times to service requests such as customer comments are eliminated. A backpropagation neural network operating in a supervised learning mode is employed to decrease the effects of the inherent system nonlinearities. The prediction error from the neural network is trained to make predictions within a predetermined error limit. The neural network generates a prediction configuration; i.e. a set of neural network characteristics, for every record per geographical area, time frame, and month. A fuzzy logic classifier is used for further data reliability. A fuzzy logic classifier relying upon the Fuzzy Cell Space Predictor (FCSP) method is employed to improve predicted response times from year to year. The fuzzy logic classifier supervises the overall identification scheme and, for every record, computes a prediction configuration for its corresponding month in the preceding year. The fuzzy logic classifier then computes a prediction estimate for its neighboring months in the preceding year and computes the prediction estimate for the next time frame (i.e. morning and evening). The Center of Gravity method is used to smooth the different prediction estimates to obtain a final predicted response time.
REFERENCES:
patent: 5155763 (1992-10-01), Bigus
patent: 5204053 (1993-04-01), Fennern
patent: 5250766 (1993-10-01), Hikita et al.
patent: 5268835 (1993-12-01), Miyogaki et al.
patent: 5269289 (1993-12-01), Takehana et al.
patent: 5274714 (1993-12-01), Hutcheson et al.
patent: 5282261 (1994-01-01), Skeirik
patent: 5307260 (1994-04-01), Watanabe et al.
Choi et al, "Non-Linear System Diagnosis Using Neural Networks & Fuzzy Logic", IEEE Int'l Conf on Fuzzy Systems, Mar. 8-12 1992, pp. 813-820.
Bowen, "Using Neural Nets to Predict Several Sequential & Subsequent Future Values from Time Series Data", 1st Int'l Conf on AI on Wall Street, Oct. 9-11, 1991, pp. 30-34.
Dash et al, "A Fuzzy Adaptive Correction Scheme for Short Term Load Forecasting Using Fuzzy Layered Neural Network", Proc 2nd Int'l Forum on Application of NN to Power Systems, Apr. 19-22 1993, pp. 432-437.
Asar et al, "A Specification of Neural Network Applications in the Load Forecasting Problem", 1st IEEE Conf on Control Applications, Sep. 13-16 1992, pp. 577-582 vol. 1.
"Working with Neural Networks", D. Hammerstrom, IEEE Spectrum, Jul. 1993, pp. 46-53.
Handbook of Intelligent Control, (D. White and D. Sofge, Ed.), Multiscience Press, New York, 1992, pp. 8-11 and pp. 118-123.
"30 Years of Adaptive Neural Networks: Perception, Madaline, and Backpropagation", B. Widrow and M. Lehr, Proceedings of the IEEE, vol. 78, No. 9, Sep. 1990, pp. 1415-1442.
"Networks for Approximation and Learning", T. Poggio and F. Girosi, Proceedings of the IEEE, vol. 78, No. 9, Sep. 1990, pp. 1481-1497.
"Backpropagation Through Time: What It Does and How To Do It", P. Werbos, Proceedings of the IEEE, vol. 78, No. 10, Oct. 1990, pp. 1550-1560.
R. Sedgewick, Algorithms, 2nd Edition, Addison-Wesley Publishing Co., Reading, Mass., 1988, pp. 15-33 and pp. 93-113.
Tsotras Vassilis
Tzes Anthony
Long Island Lighting Company
MacDonald Allen R.
Shapiro Stuart B.
LandOfFree
Adaptive system and method for predicting response times in a se does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Adaptive system and method for predicting response times in a se, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive system and method for predicting response times in a se will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2148049