Deseasonalised Forecasting Model of Rainfall Distribution Using Fuzzy Time Series

Abstract

Flood is a frequent occurrence which has a high calamity impact on human lifestyle, environment and economics. Although, there are various methods in the vast literature to predict rainfall distributions so as to prevent flood occurrences, the accuracy of these methods still remain a huge concern. Therefore, this study explores the application of the fuzzy time series method in order to obtain more accurate rainfall distribution predictions. Data for the study were collected from the Drainage and Irrigation Department Perlis (DID) of Malaysia. The data were analysed and validated using the mean square error (MSE) and the root mean squared error (RMSE). The result of the validation was compared with selected results in previous methods. The validation analysis depicts that this method has a higher forecasting accuracy than the previous methods.

Técnicas de Minería de datos aplicados a la agricultura: Estado del Arte y análisis bibliométrico

“…La investigación de [23] se enfoca en la predicción de la lluvia por medio de la recopilación de información de sensores remotos para el análisis de precipitación en zonas agrícolas, datos de cultivos y precipitación. En esta área se destaca [24], analiza técnicas estadísticas y de minería de datos con el objetivo de identificar predicciones precisas de lluvia. El conjunto de datos abarca un período de 31 años y se basa en observaciones realizadas en el área de Langat, lo que permite un análisis a largo plazo en esta región.…”

“…Predicción de lluvia [24] Agglomotive Hierarchical Clustering Region based routing [6] Equalized cluster head election routing protocol [6] Terrain based Routing using Fuzzy rules for precision agriculture" [6], [53] Segmentación [48], [40] Segmento de tiempo [73] Clasificación de Bayes ingenuo con distribución gaussiana [46] Reglas de asociación [46], [3] Descomposición de abono verde y Redes de reglas de asociación [43] Recomendación cultivo caña de azúcar [60] Minería de regresión multivariable) [46] Ensemble learning [9] Red neuronal recurrente espaciotemporal (STRNN) [9] Deep learning Toma de decisiones de datos agrícolas [56] Rendimiento de cultivo -QRECF-DFFMPC [59] Estudio del crecimiento de la col [26] Sistemas de recomendación Recomendación cultivo caña de azúcar [60] K-NN [74], [37], [78] , [3], Calidad de agua [22] Predicción del nivel de humedad [38] Naive bayes ( nb) [74], [78] Mejorar la calidad de los cultivos [58] clasificación de hongos comestibles o no comestibles [70] Rendimiento del cultivo de arroz [29] Bayes net clasificación de hongos comestibles o no comestibles [70] [80] ZeroR clasificación de hongos comestibles o no comestibles [70] K-measns clustering [33] Bagged-C4.5 [79] Regresión lineal [72], Calidad de agua [22] ARIMA (Autoregressive Integrated Moving Average) [81] Bagging (BG) [27] Predicción de emisiones de C02…”

Classification of Heart Disease Using Cluster Based DT Learning

“…This ensemble model works by building a shell of call trees and acquiescent the classification. Arbitrary call for trees bent for overfitting to their training set (Othman and Azahari, 2016;Liu et al, 2017). For tree learning, RF applies bagging.…”

Multi-Layer Cluster Based Energy Aware Routing Protocol for Internet of Things

“…Fuzzy inference system (FIS) is a type of input and output mapping system applying fuzzy logic. In FIS, the major important components are fuzzification, inference engine and defuzzification [10,12].…”