Prediction the Number of Lamps Required for the Lighting System According to the JKR Lux Standards by Using the Artificial Neural Network Method

This paper aims to develop an advanced neural network-based model for accurately predicting the number of lamps required in lighting system designs, with a focus on cost-effectiveness and compliance with JKR Standards. The scope of the research encompasses the design and evaluation of the model using a comprehensive dataset and a range of parameters. The methodology involves leveraging machine learning techniques, specifically neural networks, to analyze various factors and optimize the lamp prediction process. Extensive testing and validation are conducted to assess the model’s performance and efficiency. The findings demonstrate the superiority of the proposed model in terms of accuracy, efficiency, and cost-effectiveness compared to traditional methods. The study contributes to the field of lighting design by providing a reliable and automated solution that reduces human error and improves energy efficiency, occupant satisfaction, and safety. The findings of this research indicate that the ‘trainlm’ algorithm is the most effective for predicting the number of lamps needed. It achieved a regression value of 1.00 and a low error percentage of only 0.499%. These results demonstrate the algorithm’s accuracy and suitability for the task at hand. The conclusion highlights the significance of the developed model in streamlining the design process and offers recommendations for future work, such as exploring additional factors and evaluating the model on diverse datasets. Overall, this research enhances the understanding and application of neural networks in lamp prediction for optimal lighting system designs.