BP Neural Intelligent Residential Demand Volume Data Collection System Based on Improved Genetic Algorithm

dc.contributor.authorZhang, Xiaoxing
dc.contributor.authorJumsai na Ayudhya, Thirayu
dc.date.accessioned2026-08-06T10:43:57Z
dc.date.available2026-08-06T10:43:57Z
dc.date.issued2024-01-01
dc.description.abstractThere are problems with the quality and consistency of traditional residential demand volume data, leading to data inaccuracies and biases, affecting system analysis and decision-making results. In order to solve these problems, this article proposes a BP neural data acquisition system based on an improved genetic algorithm. This study adopts the method of experimental testing, after determining the structure of the network, including the number of nodes in the input layer, hidden layer, and output layer, uses an improved genetic algorithm to initialize and optimize the weights and biases of the network. Through experimental verification, the accuracy range of data collected based on this method is 89–96%. The BP neural intelligent residential demand volume data collection system based on the improved genetic algorithm designed in this study shows high prediction accuracy and efficiency. Compared with traditional methods, this system can better capture the complex relationships between input features and optimize network parameters through an improved genetic algorithm, improving the performance and convergence speed of the model.
dc.identifier.citationLecture Notes on Data Engineering and Communications Technologies, 198, 293-302, 2024
dc.identifier.doi10.1007/978-981-97-1983-9_26
dc.identifier.issn23674512
dc.identifier.other2-s2.0-85203050340
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/15076
dc.sourceLecture Notes on Data Engineering and Communications Technologies
dc.subjectBP neural network
dc.subjectGenetic algorithm
dc.subjectSmart living requirements
dc.subjectVolumetric data collection
dc.titleBP Neural Intelligent Residential Demand Volume Data Collection System Based on Improved Genetic Algorithm
dc.typeConference Paper

Files

Collections