- مبلغ: ۸۶,۰۰۰ تومان
- مبلغ: ۹۱,۰۰۰ تومان
Accuracy is one of the most vital factors when dealing with forecast using time series models. Accuracy depends on relative weight of past observations used to predict forecasted value. Method of aggregation of past observations is significant aspect in time series analysis where determination of next observation depends only on past observations. Previous research on fuzzy time series for forecasting treated fuzzy relationship equally important which might not have properly reflected the importance of each individual fuzzy relationship in forecasting that introduced inaccuracy in results. In this paper, we propose ordered weighted aggregation (OWA) for fuzzy time series and further design forecasting model signifying efficacy of the proposed concept. Objective of using fuzzy time series is to deal with forecasting under the fuzzy environment that contains uncertainty, vagueness and imprecision. OWA is utilized to generate weights of past fuzzy observations; thereby eliminating the need for large number of historical observations required to forecast value. OWA weights are determined by employing regularly increasing monotonic (RIM) quantifiers on the basis of fuzzy set importance using priority matrix. Experimental study reveals how OWA coalesced with fuzzy time series for designing of forecasting model. It can be observed from comparative study that use of OWA considerably reduces mean square error (MSE) and average forecasting error rate (AFER). Robustness of proposed model is ascertained by demonstrating its sturdy nature and correctness.
12. Conclusion and future work
The paper attempted to present novel concept of forecasting by amalgamating OWA operators with fuzzy time series to predict number of outpatient visit and ascertained that use of OWA operators is very effective in time series analysis.The proposed concept commenced the designing of proposed model by determining rate change of time series data. So that, increasing and decreasing rate of time series can be captured. The paper proved that accuracy depends on relative weight of past observations and method of aggregation of past observation is important factor where next prediction depends only on past observations. The concept of priority matrix is given whose task is to calculate the priority of each fuzzy set on the basis of number of occurrence of fuzzy set. Henceforth, concept of priority matrix can be utilized in devising new fuzzy time series model. The paper derived 3rd order fuzzy rules. Intent of using 3rd order fuzzy time series model is to obtain FLR, free from ambiguities. Weighted centroid aggregation method has been applied to defuzzify the value. An experiment study is performed to forecast number of outpatient visits due to its significance in health care domain. Values of MSE and AFER obtained by this research indicate the weight determination of fuzzy relationship using OWA can improve prediction accuracy by a considerable factor. We have proved that joint consideration of OWA and fuzzy time series is success to enhance the efficiency of forecasting model.It can be seen that proposed model has shown a considerable improvement in accuracy over conventional models like ARIMA, MA, ARCH, etc. From the comparative study, MSE and AFER are lowest in case of proposed method, clearly indicating its transcendence over existing like Yu, Chen and Cheng forecasting models for number of outpatient visits. In addition, impact of order of model and OWA has been carried out. Also, robustness of proposed model is proved by increasing and decreasing time series data randomly. It is examined and proved that proposed method still performs well if the historical time series data isnot precise. Extensive experiment is performed to forecast TAIEX stock market data. Presented fuzzy-OWA based forecasting model can be used to deal with future trends in health care domain.Presented model can also be considered as a strong standard methodology for planning and management in health care and other domain also.