http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
( Manoj Kushwaha ),( M. S. Abirami ),( Corresponding Author M. S. Abirami ) 한국감성과학회 2021 추계학술대회 Vol.2021 No.0
Accidents occurred usually on roads, which bring enormous losses to society. Road accidents are a universal problem which causes the loss of precious human lives and property. The purpose of this paper is to extract important influence features of road accidents and reduce the dimensionality of datasets for getting better results from machine learning algorithms. Collected datasets from Kaggle and constructed new datasets from existing datasets based on the influence feature of road accidents and perform preprocessing, feature selection and feature extraction. Feature selection is done using heat map and correlation matrix. Feature extraction is done using dimensionality reduction methods such as the Principal Component Analysis (PCA), Linear discriminate analysis (LDA) and t-Distributed Stochastic Neighbor Embedding (t-SNE). The different feature extraction techniques are applied and the results are compared based on the accuracy parameter. It was found that LDA performs better than PCA with accuracy of 85% which uses Random Forest classifier.