TY  - JOUR
PY  - 2022//
TI  - Employing machine learning techniques for prediction of traffic severity
JO  - International research journal of modernization in engineering technology and science
A1  - Harini, A.
A1  - Surya Sri, S.
A1  - Sai Sreya, Gorsa Datta
A1  - Bala, M. Urjitha
A1  - Basherunnisha, Sk.
A1  - Paul, N. Vivek
SP  - 1412
EP  - 1422
VL  - 4
IS  - 1
N2  - In recent years road accidents became a global problem which has marked prominent cause of the death in the world. Due to the enormous of road accidents we face tragic loss of human lives. Building a model useful for a real-world purpose is highly essential for the wellbeing. Predicting the severity in advance could be used to send the exact required staff and equipment to the place of accidents, thus saving significant amount of lives each year. Here we used algorithms, where we obtained efficiency to finding the risk of prediction of road accidents. The algorithms used are random forest, logistic regression, k-nearest neighbor, supervised vector machine. Among all these algorithms of comparison to obtain accuracy, random forest is best algorithm.   Keywords: Random Forest, Logistic Regression, K-Nearest Neighbor (KNN), Supervised Vector Machine (SVM), Traffic<p /> <p>Language: en</p>
LA  - en
SN  - 2582-5208
UR  - http://dx.doi.org/
ID  - ref1
ER  -