The Soil Conservation Service curve number (-) method is one of the most popular methods used to compute runoff amount due to its few input parameters. However, recent studies challenged the inconsistent runoff results obtained by the method which set the initial abstraction ratio as 0.20. This paper developed a watershed-specific - calibration method using non-parametric inferential statistics with rainfall–runoff data pairs. The proposed method first analyzed the data and generated confidence intervals to determine the optimum values for - model calibration. Subsequently, the runoff depth and curve number were calculated. The proposed method outperformed the runoff prediction accuracy of the asymptotic curve number fitting method, linear regression model and the conventional - model with the highest Nash–Sutcliffe index value of 0.825, the lowest residual sum of squares value of 133.04 and the lowest prediction error. It reduced the residual sum of squares by 66% and the model prediction errors by 96% when compared to the conventional - model. The estimated curve number was 72.28, with the confidence interval ranging from 62.06 to 78.00 at a 0.01 confidence interval level for the Wangjiaqiao watershed in China.
Oil palm crop yield is sensitive to heat and drought. Therefore, El Niño events affect oil palm production, resulting in price fluctuations of crude palm oil due to global supply shortage. This study developed a new Fresh Fruit Bunch Index (FFBI) model based on the monthly oil palm fresh fruit bunch (FFB) yield data, which correlates directly with the Oceanic Niño Index (ONI) to model the impact of past El Niño events in Malaysia in terms of production and economic losses. FFBI is derived from Malaysian monthly FFB yields from January 1986 to July 2021 in the same way ONI is derived from monthly sea surface temperatures (SST). With FFBI model, the Malaysian oil palm yields are better correlated with ONI and have higher predictive ability. The descriptive and inferential statistical assessments show that the newly proposed FFBI time series model (adjusted R-squared = 0.9312 and residual median = 0.0051) has a better monthly oil palm yield predictive ability than the FFB model (adjusted R-squared = 0.8274 and residual median = 0.0077). The FFBI model also revealed an oil palm under yield concern of the Malaysian oil palm industry in the next thirty-month forecasted period from July 2021 to December 2023.
Flash floods are known as one of the common natural disasters that cost over billions of Ringgit Malaysia throughout history. Academically, an extreme rainfall model is effective in modelling to predict and prevent the occurrence of flash floods. This paper compares four probability distributions, namely, exponential distribution, generalized extreme value distribution, gamma distribution, and Weibull distribution, with the rainfall data of 10 stations in peninsular Malaysia. The period of the data is from 1975 to 2008. The comparison is based on the descriptive and predictive analytics of the models. The determination of the most effective model is through Kolmogorov-Smirnov, Anderson-Darling, and chi-square test. The result shows that generalized extreme value is the most preferred extreme rainfall model for the rainfall cases in Peninsular Malaysia.
Climate impact assessment models can have outputs that are sensitive to biases on the local scale. Hence, bias correction methods are used to amend the distribution of the climate impact assessment model in order to match the local observations. A great deal of errors can be removed from the model after bias correction is applied. This study focuses on identifying the best bias correction method after applying it on the observed rainfall data over Peninsular Malaysia. The bias correction methods used in this study includes the quantile mapping method, the delta method and the quantile delta mapping method. The rainfall data of 15 rainfall stations were obtained from the Malaysian Meteorological Department, whereas the General Circulation Model data used follows the CNRM-CM5 model. The quantile mapping method is well-known for seasonal forecasting which has grown extensively due to its broad use in correcting climatological biases in studies projecting future climate change. The delta method uses observations as a basis and is a stable and robust method that produces future time series with dynamics similar to current conditions, but it does not take into account the potential future changes in climate dynamics. The quantile delta mapping method is a break from other typical quantile mapping methods whereby it is not constrained by stationary assumptions. The results show that the quantile mapping method is the best bias correction method among the three methods used in this study.
Speech analytics solution is a technology that enables a company to discover customer’s patterns and insights by analyzing relevant data, such as recorded audio files or phone conversations. The accuracy of speech recognition or speech-to-text transcription has been a challenge all along. This paper aims to present a text classification model for the call transcriptions based on the context, and to improve the accuracy of Google Speech API in Malay language. In this study, the accuracy of speech-to-text transcription is measured by word recognition rate and an accuracy scale. Time-cut-point and audio speed are the factors investigated to determine whether these factors affect the accuracy of text transcription. The results obtained from different time-cut-point and audio speed setting have been studied to identify the best combination. Furthermore, the pre-processed text data is utilized to train the text classification model using Support Vector Machine and Naive Bayes algorithms. In this paper, two approaches have been studied to improve Google Speech API. The first approach is to apply speech adaptation, which is the function made by Google. However, it showed that the accuracy dropped when 250 words were added into the speech adaptation, or when the audio speed was lowered. This is because the words error rate for both methods have increased. In the second approach, removing speech adaptation and lowering audio speed simultaneously caused a decrease in words error rate, hence the accuracy increased. In a nutshell, Support Vector Machine has better accuracy score of text classification as compared with Naive Bayes algorithms. As a result, short time-cut-point with normal speed of audio file showed a positive impact to improve Google speech-to-text API, along with Support Vector Machine being more suitable for classification model.