Performance Analysis of Vehicle Detection using Support Vector Machine Comparing with K-Nearest Neighbor Algorithm

In order to achieve the goal of improving vehicle detection in extremely crowded traffic, this project will make use of many machine learning approaches, including the Support Vector Machine algorithm and the K-Nearest Neighbors algorithm, amongst others, in order to achieve the goal. Two examples of categories that are included in the "Materials and Methods" category are the K-Nearest Neighbors method and the Support Vector Machine approach. One further illustration of this would be the category "Instruments and Tools." The results of applying an algorithm known as Support Vector Machine to ten samples and the results of applying an algorithm known as K-Nearest Neighbors to ten samples are combined to give a total sample size of twenty. Support Vector Machine and K-Nearest Neighbors are both types of algorithms. Support Vector Machine and K-Nearest Neighbors are the names given to both of these different kinds of algorithms. Throughout the entirety of the process of calculating the samples, a pre-test power of 80%, a confidence interval of 95%, and an error correction of p 0.05 are utilised throughout. The accuracy that is created by the technique known as Support vector machine is directly superior to the accuracy that is produced by the approach known as K-Nearest Neighbors (92.65%), as a direct result of this. The difference between the two is 95.85%. One is able to make an educated assumption regarding the importance of the Support Vector Machine when p is less than 0.05. The data were analyzed, and the findings showed that the Support vector machine technique is substantially more effective than the K-Nearest Neighbors algorithm when it comes to enhancing new histogram equalisation-based Vehicle recognition in traffic. This was determined by looking at the outcomes of the analysis. The investigation of the findings led to the discovery of this information. This conclusion was reached after conducting research on the ways in which the two approaches are similar to one another as well as the ways in which they differ from one another.