A Driver-Centric Carpooling: Optimal Route-Finding Model Using Heuristic Multi-Objective Search

Habibullah, Khan Mohammad; Alam, Ahashan; Saha, Swapnil; Al-Amin, Al-Amin; Das, Amit Kumar

doi:10.1109/ccoms.2019.8821722

Cited by 6 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Road traffic data is normally one of the most accessible information, among different points, for example, population, economic measurements, and geographic data. (Habibullah et al, 2019) and Australia open information inventory, that incorporates constant travel, traffic accidents, and public vehicle time tables.…”

Section: Government and Open Data Sourcesmentioning

confidence: 99%

Road Accident Analysis and Prediction using Machine Learning Algorithmic Approaches

Ballamudi¹

2019

Asian j. humanity, art lit.

View full text Add to dashboard Cite

Ongoing studies have anticipated that in 2030, car crashes will be the fifth driving reason for death around the world. The main cause of car crashes is difficult to decide these days because of a complex mix of qualities like the mental condition of the driver, road conditions, climate conditions, traffic, and infringement of traffic rules to give some examples. The expenses of fatalities and driver wounds because of car crashes incredibly influence the general public. The use of machine learning methods in the field of road accidents is picking up speed nowadays. The organization of machine learning classifiers has swapped conventional data mining methods for creating higher outcomes and exactness. This work presents a review of different existing businesses related to accident prediction utilizing the machine learning area. Wounds because of road accidents are one of the most pervasive reasons for death separated from health-related issues. The investigation of road accident seriousness was finished by running an accident dataset through a few machine learning arrangement calculations to see which model played out the best in characterizing the accidents into severity classes, for example, slight, extreme, and fatal. It was seen that calculated relapse to perform multilevel order gave the most noteworthy exactness score. It was additionally seen that variables, for example, the number of vehicles, lighting conditions, and road highlights assumed a part in deciding the seriousness of the accident. Engineers and analysts in the car business have attempted to plan and manufacture more secure vehicles, yet auto collisions are unavoidable. Examples associated with hazardous accidents could be identified by building up a prediction model that naturally orders the sort of injury severity of different traffic accidents. These social and roadway designs are valuable in the improvement of traffic security control strategies. Significantly, estimates be founded on logical and target reviews of the reasons for accidents and the seriousness of injuries. This paper presents a few models to predict the seriousness of the injury that happened during traffic accidents utilizing machine-learning paradigms. We considered networks prepared to utilize machine learning methods. Analysis results uncover that among the machine learning ideal models considered different standards paradigm approaches.

show abstract

Section: Government and Open Data Sourcesmentioning

confidence: 99%