Roadmap to Smart Mobility: Machine Learning in Connected Vehicles

Shridevi Jeevan Kamble

ISBN 10: 620745040X / ISBN 13: 9786207450404

Published by LAP LAMBERT Academic Publishing Dez 2023, 2023

About this Item

Neuware -In the dynamic landscape of Intelligent Transportation Systems, this research pioneers strategies for efficient route prediction, particularly vital for emergency vehicles (EVs). The HL-CTP model employs incremental learning, enhancing accuracy by fine-tuning predictions based on historical data. Complementing this, the SG-TSE model adjusts traffic lights, minimizing the negative impact of congestion on both regular traffic and EV preemption. Recognizing the limitations of traditional machine learning in Internet of Vehicles networks, our third objective utilizes YOLOv4-based traffic monitoring, incorporating the Kalman filter for real-time IoV environment modeling. Policymakers can leverage this data for informed decisions, improving transportation efficiency, reducing congestion, and enhancing safety. Integrating RSUs efficiently manages network resources, contributes to smarter transportation systems, and elevates urban living standards. In conclusion, this research not only advances route prediction and EV preemption but also adds value to the broader landscape of intelligent and responsive transportation systems, benefiting society at large.Books on Demand GmbH, Überseering 33, 22297 Hamburg 64 pp. Englisch.

Seller Inventory # 9786207450404

Bibliographic Details

• Title: Roadmap to Smart Mobility: Machine Learning in Connected Vehicles
• Publisher: LAP LAMBERT Academic Publishing Dez 2023
• Publication Date: 2023
• Language: English
• ISBN 10: 620745040X
• ISBN 13: 9786207450404
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 220W x 150H x 4D millimeters 220 millimeters width by 150 millimeters height by 4 millimeters depth
• Weight: 113 grams

About this title

Synopsis

In the dynamic landscape of Intelligent Transportation Systems, this research pioneers strategies for efficient route prediction, particularly vital for emergency vehicles (EVs). The HL-CTP model employs incremental learning, enhancing accuracy by fine-tuning predictions based on historical data. Complementing this, the SG-TSE model adjusts traffic lights, minimizing the negative impact of congestion on both regular traffic and EV preemption. Recognizing the limitations of traditional machine learning in Internet of Vehicles networks, our third objective utilizes YOLOv4-based traffic monitoring, incorporating the Kalman filter for real-time IoV environment modeling. Policymakers can leverage this data for informed decisions, improving transportation efficiency, reducing congestion, and enhancing safety. Integrating RSUs efficiently manages network resources, contributes to smarter transportation systems, and elevates urban living standards. In conclusion, this research not only advances route prediction and EV preemption but also adds value to the broader landscape of intelligent and responsive transportation systems, benefiting society at large.