A Comparison of Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) in River Water Quality Prediction

/in /by

River water is a crucial natural resource utilized for various purposes, including agriculture and drinking. Human activities such as mining, industrial discharge, and improper waste management contribute to river water pollution, affecting its quality and posing risks to human health. Monitoring and predicting river water quality are essential for effective management and pollution control. The research focuses on Dissolved Oxygen (DO), and comparing of Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) to developed prediction models. Evaluation of the models’ performance shows that the ANN model outperforms LSTM in predicting Dissolved Oxygen (DO) concentrations, achieving lower Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Although LSTM exhibits lower Mean Squared Error (MSE), the ANN model demonstrates better accuracy in minimizing the average distance between predicted and actual values. The findings suggest that ANN-based models offer good performance in river water quality prediction, with potential for further enhancement through additional variables or model architecture adjustments.

Quality Laying Hen Eggs through Soaking Guava (Psidium guajava) Leaves Extract

/in /by

This study aims to determine the extent to which the concentration of guava leaves extract (Psidium guajava) and storage time affect the quality of laying hen eggs. Food materials such as laying hen eggs are easily perishable, meaning that they will deteriorate in quality within 14 days of being stored at room temperature, and will even rot soon after. This study aims to determine the effect of giving guava leaf extract (Psidium guajava) and soaking time on the quality and shelf life of eggs. The method used was a Completely Randomized Design (CRD) with a factorial pattern consisting of 2 factors. Factor A is the concentration of guava leaves extract (Psidium guajava) solution and factor B is the storage time with 3 replications. The treatments used were: Factor A concentration of guava leaf extract solution A1 = 0%, A2 = 15%, A3 = 30%, and A4 = 45%. Factor B storage time B1 = 0 days, B2 = 7 days B3 = 14 days. The variables analyzed in this study were egg weight loss, egg white index, and yolk index. The data obtained were analyzed using the ANOVA test. If there is a significant difference between treatments, it will be continued with the Duncan Test. The results of the ANOVA analysis showed that the interaction had no significant effect (P>0.05) on the egg white index and egg yolk index. Giving each concentration gave good results in egg weight loss. Meanwhile, the egg white index and egg yolk index showed good results with a concentration of 15%. It is concluded that giving guava leaves extract (Psidium guajava) and storage time can maintain the quality and extend the shelf life of laying hen eggs.