Search

Streamflow prediction has a significance influence on improving water supply management and flood prevention. The applications of artificial intelligence (AI) have been proved to have better performance as compared to conventional statistical method in streamflow prediction. Therefore, this study proposed on the development of streamflow prediction model AI techniques namely Bat algorithm (BA) and backpropagation neural network (BPNN). BA is an optimization technique, which is to optimize BPNN in deciding optimum parameters and then improve the prediction accuracy. The study area chosen is Kuantan river and Kenau river, located in Kuantan, Malaysia. Two prediction models are proposed in this study which are BPNN and hybrid Bat-BPNN. Monthly historical rainfall data, antecedent river flow data and meteorology parameters data for two different rivers were used as the input to the proposed models. The performance of the proposed prediction models for Kuantan river and Kenau river are then being compared and evaluated in term of RMSE and R². It is found that hybrid model, Bat-BPNN yields lower RMSE and provides higher R² as compared to BPNN model at both Kuantan river and Kenau river. Therefore, it can be concluded that, proposed hybrid model yields better performances as compared to BPNN model for monthly streamflow prediction. [ABSTRACT FROM AUTHOR]

Thermoplastic elastomer SEBS foams were prepared by using carbon dioxide (CO2) as a blowing agent and the process is classified as physical foaming method. During the foaming process, the diffusivity of CO2 need to be controlled since it is one of the parameter that will affect the final cellular structure of the foam. Conventionally, the rate of CO2 diffusion was measured experimentally by using a highly sensitive device called magnetic suspension balance (MSB). Besides, this expensive MSB machine is not easily available and measurement of CO2 diffusivity is quite complicated as well as time consuming process. Thus, to overcome these limitations, a computational method was introduced. Particle Swarm Optimization (PSO) is a part of Swarm Intelligence system which acts as a beneficial optimization tool where it can solve most of nonlinear complications. PSO model was developed for predicting the optimum foaming temperature and CO2 diffusion rate in SEBS foam. Results obtained by PSO model are compared with experimental results for CO2 diffusivity at various foaming temperature. It is shown that predicted optimum foaming temperature at 154.6 °C was not represented the best temperature for foaming as the cellular structure of SEBS foamed at corresponding temperature consisted pores with unstable dimension and the structure was not visibly perceived due to foam shrinkage. The predictions were not agreed well with experimental result when single parameter of CO2 diffusivity is considered in PSO model because it is not the only factor that affected the controllability of foam shrinkage. The modification on the PSO model by considering CO2 solubility and rigidity of SEBS as additional parameters needs to be done for obtaining the optimum temperature for SEBS foaming. Hence stable SEBS foam could be prepared. [ABSTRACT FROM AUTHOR]