Abstract

The Car manufacturing sector represents a major focus in the development of the automotive industry. In this research paper, a proposed data mining application for the automotive manufacturing sector is explained and tested. The dataset was retrieved from the machine learning repository at the University of California, Irvine. This research paper aims to create a more reliable classifier for future object classification. Classification is an important technique in data mining. It is a supervised learning process that involves classifying an object into one of the predefined classes based on its attributes. In this paper, we use a large database containing 7 attributes and 1,728 instances. We compare the

results of a simple classification technique (using the J48 decision tree inference algorithm and MONK) with results based on different parameters using WEKA (Waikato Environment Knowledge Analysis), a data mining tool. The results of the experiment show a comparison between three algorithms to see which is the best and least error-prone algorithm. The physical characteristics of a car viz . Engine location ,price, how many doors, stroke, city fuel consumption, and other factors determine a vehicle's performance. Therefore, developing such a classification, although a huge undertaking, is absolutely essential in the car industry. Machine learning techniques can help integrate computer-based systems to predict vehicle quality and improve system efficiency. Classification models were trained using 214 datasets. The predicted values of the classifiers were evaluated using 10-fold cross-validation, and the results were compared.

Keywords: Data mining, Machine learning techniques, J48, decision trees, Car market, WEKA classification.

Abstract

This paper is the report of the first Under-Display Camera (UDC) image restoration challenge in conjunction with the RLQ workshop at ECCV 2020. The challenge is based on a newly-collected database of Under-Display Camera. The challenge tracks correspond to two types of display: a 4k Transparent OLED (T-OLED) and a phone Pentile OLED (P-OLED). Along with about 150 teams registered the challenge, eight and nine teams submitted the results during the testing phase for each track. The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration. Datasets and paper are available at https://yzhouas.github.io/projects/UDC/udc.html.

Keywords

Under-display camera Image restoration Denoising Debluring