Detection of vacant slots in parking area through machine learning techniques using optimized ensemble classification model. (3rd April 2022)

• Record Type: Journal Article
• Authors: Mago, Neeru; Mago, Jagmohan; Garg, Rachit; Joshi, Prabal Kumar
• Is Part Of: Journal of discrete mathematical sciences & cryptography. Volume 25:Number 3(2022)
• Page Start: 705
• Page End: 720
• Publication Date: 2022-04-03
• Subjects: 68W99; Parking system -- Machine learning -- Artificial neural network -- K-nearest neighbor -- Naive bayes classifier -- Support vector machine -- Ensemble model; Computer science -- Mathematics -- Periodicals; Cryptography -- Periodicals; Computer science -- Mathematics; Cryptography; Periodicals; 004.0151
• DOI: 10.1080/09720529.2021.2016221
• Languages: English
• ISSNs: 0972-0529

Abstract

Abstract: Due to insufficiency of parking space, people face many problems in finding a vacant slot to park their vehicles in the parking area. This problem is giving rise to many other problems such as traffic congestion, wastage of fuel, money and time. Therefore, there is a need to develop an intelligent parking management system for better utilization of the resources. The main objective of the paper is to design an efficient parking system to search for the vacant slots in the parking area. In this paper, experiments have been conducted on standard dataset "PKLot" which consists of 695, 899 images of two different parking lots. These images were captured from three different camera views under different climatic conditions like rainy, sunny and cloudy. Various machine learning (ML) techniques like Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), Naïve Bayes Classifier (NBC) and Support Vector Machine (SVM) with different parameters have been applied on the dataset. Further, an ensemble model for classification of occupied and vacant slots in the parking area has been developed which improves the performance of the system as compared with other state-of-the-art systems.