Abstract
The world's population is expanding, and people want to live in cities, making city administration a difficult task. Traditional cities, with their shared characteristics, will be unable to provide human demands. Machine learning (ML) techniques are being used to increase an application's understanding and capabilities as the volume of data received rises. Smart transportation is defined as an umbrella concept that describes route optimization, parking, street lighting, and infrastructure applications in this evaluation. The purpose of this research is to present a self-contained assessment of machine learning techniques and internet of things applications in intelligent transportation to provide a clear picture of the current state of circumstances. In this chapter, the authors attempt to explain several features of smart transportation in greater depth.
TopBackground
Several industry demands, as well as extensive research employing machine learning algorithms, have prepared the way for the developing topic of intelligent transportation (Karami & Kashef, 2020). Several researchers have been interested in the field of intelligent transportation, which was investigated using both machine learning and IoT approaches. Smart transportation networks are evolving with the exponential increase in the usage of IoT devices as well as the advantages obtained by applying Machine Learning methods over different applications of the smart transportation system.
Key Terms in this Chapter
IoT: The internet of things is a network formed by things so that they can share information among them to provide IT-based services.
WLAN: Wireless local area network is a LAN network formed within a building between two or more devices using wireless communication technology.
VANET: Vehicular ad hoc network is a wireless network formed among stationary and/or moving objects such as vehicles.
LSTM: Long short-term memory is a sub-class of RNNs (recurrent neural networks). It consists of both feed-forward and feed-back connections and handles gradient vanishing or exploding issues better than RNN.
RFID: Radio frequency identification is a technology in which an RFID tagged device is identified using electromagnetic signals by the RFID reader.
ML: Machine learning is a branch of AI (artificial intelligence) in which the system exhibits the ability to learn from the data and experience without explicitly programming it.
LPWAN: Low power wide area network is wireless communication technology to connect low power devices over long-range with low data rate such as sensors operating on batteries, etc.