The effect of image recognition traffic prediction method under deep learning and naive Bayes algorithm on freeway traffic safety

Yao, Jingxuan; Ye, Yuntao

doi:10.1016/j.imavis.2020.103971

Cited by 20 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In displaying maps using the ArcMap application, the prediction results of the support vector machine and ordinary kriging methods show good maps and achieve 93% accuracy. Compared with previous studies [6], [7], [8], [9] only show prediction results but do not create congestion maps. Meanwhile, research [10] and [11] only show a map of regional congestion but do not display a road map.…”

Section: Congestion Classification Mapmentioning

confidence: 83%

See 1 more Smart Citation

Bandung City Traffic Classification Map With Machine Learning and Ordinary Kriging

Fazry

Prasetyowati

Sibaroni

2022

jipi. jurnal. ilmiah. penelitian. dan. pembelajaran. informatik

View full text Add to dashboard Cite

Congestion is a problem that occurs when the number of vehicles exceeds the capacity of the road and the vehicle speed slows down. This issue is one of the main issues in big cities, including Bandung. In this study, this study aims to reduce traffic congestion in the city of Bandung. The classification process in this study uses the Support Vector Machine (SVM), Naive Bayes, and Ordinary Kriging methods. The data used is traffic counting data from ATCS in Bandung and direct observation. The traffic count data obtained contains 3804 rows. Three experimental scenarios were carried out to validate the effectiveness of the model used, the performance of the first model without oversampling, the performance of the second model with oversampling, and the performance of the third model with hyperparameter adjustment. The experimental results show that the Support Vector Machine method has higher accuracy than the Naive Bayes method, which is 93%, while the Naive Bayes method has an accuracy of 90%. The application of hyperparameter tuning and over-sampling is proven to overcome the problem of data imbalance and get better classification results. In addition, the best classification results are used in making classification maps, namely the Support Vector Machine method, and assisted with ordinary kriging to predict the surrounding area. The results of the congestion classification map show that the southern area of the city of Bandung is more unstable than other areas of the city of Bandung.

show abstract

Section: Congestion Classification Mapmentioning

confidence: 83%

“…The Naïve Bayes method obtained an accuracy rate of 86.62%, while the SVM method obtained an accuracy of 96.29%. Further research [9] uses Naïve Bayes to predict traffic flow. In this study, the Naïve Bayes method obtained an accuracy of 82.7%, but only time and area factors were considered in predicting traffic flow.…”

Section: Introductionmentioning

confidence: 99%

Bandung City Traffic Classification Map With Machine Learning and Ordinary Kriging

Fazry

Prasetyowati

Sibaroni

2022

jipi. jurnal. ilmiah. penelitian. dan. pembelajaran. informatik

View full text Add to dashboard Cite

show abstract

“…e maximum-minimum method is a classic normalization method that is widely used in traffic safety research [44] and data processing prior to clustering [45]. Compared with other normalization methods, this method can distribute the data set selected in this study more evenly in the interval [0, 1] and maintain the relative linear relationships of their values [46].…”

Section: Vehicle Group Categorization Rule Based On Temporal and Spat...mentioning

confidence: 99%

Risk Measurement Model for Vehicle Group Based on Temporal and Spatial Similarities

Wen

Chen

Zhao

2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

Vehicle rear-end collisions are primarily caused by tight car following in a continuous traffic flow, as well as a driver’s incorrect perception of the traffic environment ahead and delayed response. To facilitate an investigation pertaining to rear-end collision mechanisms and accurately measure the risk, the concept of a vehicle group is introduced herein. A risk measurement model for a vehicle group (RMVG) based on temporal and spatial similarities is proposed. First, vehicles are categorized based on their temporal and spatial similarities. Risk measurement metrics are defined based on the traffic composition, movement state, and conflict extent. Subsequently, vehicle group risk identification and risk measurement models based on an isolation forest are established. the rear-end collision risk of the vehicle groups is analyzed both qualitatively and quantitatively. Finally, the RMVG is tested using the vehicle trajectory data set of Longpan South Road, Nanjing City, Jiangsu Province, China, and the results are compared with those of a support vector machine and local outlier factor. The results show that the accuracy of the RMVG is higher than those of other models: its accuracy rate and specificity are 95.68% and 88.89%, respectively, whereas its false alarm rate is only 3.47%.

show abstract

“…Penelitian tentang arus lalu lintas yang dilakukan oleh (Stathopoulos, 2018) tentang analisis risiko kinerja sistem transportasi dan pengembangan metode pengendalian lalu lintas di daerah perkotaan. Adapun yang dilakukan oleh (Yao and Ye, 2020) memprediksi keselamatan lalu lintas jalan bebas hambatan dan mewujudkan arus lalu lintas dalam data besar nonlinier menggunakan algoritma deeplearning dan naive bayes. Dari penelitian tersebut bahwa lalu lintas yang padat dapat menimbulkan resiko kecelakaan dan dapat merugikan penggunanya.…”

Section: Pendahuluanunclassified

Klasifikasi Pembagian Arus Lalu Lintas Menggunakan Alogaritma Naïve Bayes Dan Model Linear

Abdi¹,

Qodarbaskoro²,

Alfani³

et al. 2021

Technologia

View full text Add to dashboard Cite

The density of traffic flow is a problem for every big city, especially as it is easy to have a private vehicle, causing the flow to increase every year. So to overcome traffic flow, a system that can make optimal traffic performance is needed is needed. The purpose of this study is to determine whether the road conditions are empty, smooth, dense and very congested so as to produce a prediction of road options whether to continue passing the road or find another way, as well as to test the accuracy of traffic flow using the naive bayes method and the liner model. The classification stages carried out are data input, data preprocessing, classification, and the results of accuracy, precision, and recall. And the results of this study the naive bayes method obtained higher accuracy than the linear model, namely for naive bayes accuracy 95.70%, precision 95.67%, and recall 100%, while for naive bayes accuracy 92.10%, precision 95.68%, and recall 96.20%. then the result is the naive bayes method is superior in the traffic flow data classification process. And the results of decision making obtained results from traffic flow data obtained that the road is empty so that the road can be passed without having to find another way. Keywords - Classification, Naive Bayes, Traffic, Linear Model, Flow Density AbstrakKepadatan arus lalu lintas menjadi masalah setiap kota-kota besar, apalagi seiring mudah nya dalam memiliki kendaraan pribadi sehingga menimbulkan arus yang meningkat pada setiap tahunnya. Maka untuk penanggulangan arus lalu lintas dibutuhkan sistem yang bisa membuat kinerja lalu lintas yang optimal. Tujuan penelitian ini adalah mengetahui kondisi jalan apakah lengang, lancar, padat dan sangat padat sehingga menghasilkan prediksi opsi jalan apakah tetap melewati jalan tersebut atau mencari jalan lain, serta menguji tingkat akurasi arus lalu lintas menggunakan metode naive bayes dan model liner. Dengan tahapan klasifikasi yang dilakukan yaitu input data, preprocessing data, klasifikasi, dan hasil accuracy, precision, dan recall. Dan hasil penelitian ini metode naive bayes mendapatkan accuracy lebih tinggi dari model linier yaitu untuk naive bayes accuracy 95.70%, precision 95.67%, dan recall 100%, sedangkan untuk naive bayes accuracy 92.10%, precision 95.68%, dan recall 96.20%. maka hasilnya metode naive bayes lebih unggul dalam proses klasifikasi data arus lalu lintas. Dan hasil dari pengambilan keputusan didapat hasil dari data arus lalu lintas didapatkan jalan tersebut lengang sehingga jalan tersebut dapat dilalui tanpa harus mencari jalan lain. Kata Kunci - Klasifikasi, Naive Bayes, Lalu Lintas, Model Linier, Kepadatan Arus

show abstract

The effect of image recognition traffic prediction method under deep learning and naive Bayes algorithm on freeway traffic safety

Cited by 20 publications

References 22 publications

Bandung City Traffic Classification Map With Machine Learning and Ordinary Kriging

Bandung City Traffic Classification Map With Machine Learning and Ordinary Kriging

Risk Measurement Model for Vehicle Group Based on Temporal and Spatial Similarities

Klasifikasi Pembagian Arus Lalu Lintas Menggunakan Alogaritma Naïve Bayes Dan Model Linear

Contact Info

Product

Resources

About