The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Comparing Machine Learning Models for the Predictions of Speed in Smart Transportation Systems
Abstract
In today's world of advanced technologies in IoT and ITS in smart cities scenarios, there are many different projections such as improved data propagation in smart roads and cooperative transportation networks, autonomous and continuously connected vehicles, and low latency applications in high capacity environments and heterogeneous connectivity and speed. This chapter presents the performance of the speed of vehicles on roadways employing machine learning methods. Input variable for each learning algorithm is the density that is measured as vehicle per mile and volume that is measured as vehicle per hour. And the result shows that the output variable is the speed that is measured as miles per hour represent the performance of each algorithm. The performance of machine learning algorithms is calculated by comparing the result of predictions made by different machine learning algorithms with true speed using the histogram. A result recommends that speed is varying according to the histogram.
Related Content
|
J. Mangaiyarkkarasi, J. Shanthalakshmi Revathy.
© 2024.
34 pages.
|
|
Gummadi Surya Prakash, W. Chandra, Shilpa Mehta, Rupesh Kumar.
© 2024.
22 pages.
|
|
Duygu Nazan Gençoğlan.
© 2024.
35 pages.
|
|
Smrity Dwivedi.
© 2024.
20 pages.
|
|
Pallavi Sapkale, Shilpa Mehta.
© 2024.
21 pages.
|
|
Pardhu Thottempudi, Vijay Kumar.
© 2024.
43 pages.
|
|
Sathish Kumar Danasegaran, Elizabeth Caroline Britto, S. Dhanasekaran, G. Rajalakshmi, S. Lalithakumari, A. Sivasangari, G. Sathish Kumar.
© 2024.
18 pages.
|
|
|