Comparison of Minimum Service Cost for Novel Vehicle Parking System using K-Nearest Neighbour Algorithm over Artificial Neural Network Algorithm

Utilizing a K-Nearest Neighbor Algorithm rather than an Artificial Neural Network in order to cut costs while still delivering the required level of service for one-of-a-kind parking systems for motor vehicles would accomplish this. The K-Nearest Algorithm was used to make it possible to construct a new car parking system for the database, and the sample size was set at 20. This made it possible to create a novel car parking system for the database. The purpose of this algorithm is to provide assistance in locating the parking spot that is situated in the immediate neighbourhood of the area in which vehicles are parked. The K-Nearest Neighbor Algorithm is utilised through the utilisation of the anaconda navigator tools in order to give a car parking database with an accuracy improvement in secure accessibility of 87%. The Artificial Neural Network, on the other hand, has just a 75% accuracy rate in its predictions. This is in contrast to the previous example. An SPSS (Statistical Software for the Social Sciences) analysis of the amount of time required to log in and access the database was carried out. This analysis looked at how long it takes to do each of those things. Time and size were the variables that were investigated in this study, and a degree of significance value of 0.02 was utilised throughout the process. (p0.05). When it comes to the performance of parking systems for vehicles, the K-nearest neighbour algorithm provides improved accuracy while maintaining a level of operation that is more cost-efficient.