Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends

Veres, Matthew; Moussa, Medhat

doi:10.1109/tits.2019.2929020

Cited by 263 publications

(140 citation statements)

References 66 publications

Supporting

Mentioning

122

Contrasting

Unclassified

Order By: Relevance

“…They are denoted as the following vector: D = para, hdt , where para represents parameters of the model and hdt represents historical data of IoT nodes. hdt is represented by the following vector: hdt = d (1) , d (2) (N) , where Sensory data are gathered to the cloud without lowering the satisfiability of certain requirements. 1: for each IoT node nd i do 2:…”

Section: Adaptive Sample Rate Adjustmentmentioning

confidence: 99%

“…We confirm that the content of the manuscript has not been published or submitted for publication elsewhere. 1 The school of Information Engineering, China University of Geosciences (Beijing), Xueyuan Road, 100083, Beijing, China. 2 The department of computer science and IT, Qurtuba University of Science and Technology Peshawar, Hayatabad, 25000, Peshawar, Pakistan.…”

Section: Abbreviationsmentioning

confidence: 99%

“…The Internet of Things (IoT) networks, as a promising and fast-developing research area in recent years, have been applied to support various kinds of domain applications, like traffic flow monitoring in Intelligent Transportation Systems (ITS) [1], where continuous sensory data gathering is fundamental to support the environmental monitoring and anomaly detection in industrial applications. Intuitively, smart things in IoT networks, also known as sensor nodes in W ireless Sensor Networks (WSN), are necessary to periodically sense environment variables, and gather and route sensory data packets to the center, like the sink node in WSN, for anomaly examination and source determination.…”

Section: Introductionmentioning

confidence: 99%

“…Intuitively, smart things in IoT networks, also known as sensor nodes in W ireless Sensor Networks (WSN), are necessary to periodically sense environment variables, and gather and route sensory data packets to the center, like the sink node in WSN, for anomaly examination and source determination. Considering the fact that the *Correspondence: zbzhou@cugb.edu.cn 1 The school of Information Engineering, China University of Geosciences (Beijing), Xueyuan Road, 100083, Beijing, China Full list of author information is available at the end of the article majority of monitoring durations may reflect a healthy situation for most applications and relatively large energy consumption of sensor nodes for transmitting sensory data packets along routing paths, the reduction of sensory data volume to be transmitted in the network is essential for prolonging the lifetime of WSN, where sensor nodes are mostly constrained in their computational capacity, and their energy is provided by the battery, which is usually inconvenient to be recharged or replaced. Besides, to examine whether an anomaly has occurred or not, as well as the degree of severity of the anomaly, an accurate value of environmental variables maybe not interesting, whereas the interval scale that sensory data belong to is relevant.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Energy-efficient sensory data gathering based on compressed sensing in IoT networks

Zhou

Zhang

et al. 2020

J Cloud Comp

View full text Add to dashboard Cite

The Internet of Things (IoT) networks have become the infrastructure to enable the detection and reaction of anomalies in various domains, where an efficient sensory data gathering mechanism is fundamental since IoT nodes are typically constrained in their energy and computational capacities. Besides, anomalies may occur occasionally in most applications, while the majority of time durations may reflect a healthy situation. In this setting, the range, rather than an accurate value of sensory data, should be more interesting to domain applications, and the range is represented in terms of the category of sensory data. To decrease the energy consumption of IoT networks, this paper proposes an energy-efficient sensory data gathering mechanism, where the category of sensory data is processed by adopting the compressed sensing algorithm. The sensory data are forecasted through a data prediction model in the cloud, and sensory data of an IoT node is necessary to be routed to the cloud for the synchronization purpose, only when the category provided by this IoT node is different from the category of the forecasted one in the cloud. Experiments are conducted and evaluation results demonstrate that our approach performs better than state-of-the-art techniques, in terms of the network traffic and energy consumption.

show abstract

Section: Adaptive Sample Rate Adjustmentmentioning

confidence: 99%

Section: Abbreviationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Energy-efficient sensory data gathering based on compressed sensing in IoT networks

Zhou

Zhang

et al. 2020

J Cloud Comp

View full text Add to dashboard Cite

show abstract

“…In another survey [30], the authors focus on the utilization of deep learning models for various traffic state prediction like traffic speed and flow in Intelligent Transportation Systems (ITS). Another recent comprehensive survey [31] focused on utilization of deep learning methods for various ITS problems including traffic flow prediction, traffic signal control, travel time estimation etc. The authors in [32] investigated ML based ITS techniques, applications and services, such as co-operative driving and road hazard warning and expanded the concepts of various ITS tasks but lacks human driving behavior recognition techniques.…”

Section: Introductionmentioning

confidence: 99%

Detecting Human Driver Inattentive and Aggressive Driving Behavior Using Deep Learning: Recent Advances, Requirements and Open Challenges

2020

View full text Add to dashboard Cite

Human drivers have different driving styles, experiences, and emotions due to unique driving characteristics, exhibiting their own driving behaviors and habits. Various research efforts have approached the problem of detecting abnormal human driver behavior with the aid of capturing and analyzing the face of driver and vehicle dynamics via image and video processing but the traditional methods are not capable of capturing complex temporal features of driving behaviors. However, with the advent of deep learning algorithms, a significant amount of research has also been conducted to predict and analyze driver's behavior or action related information using neural network algorithms. In this paper, we contribute to first classify and discuss Human Driver Inattentive Driving Behavior (HIDB) into two major categories, Driver Distraction (DD), Driver Fatigue (DF), or Drowsiness (DFD). Then we discuss the causes and effects of another human risky driving behavior called Aggressive Driving behavior (ADB). Aggressive driving Behavior (ADB) is a broad group of dangerous and aggressive driving styles that lead to severe accidents. Human abnormal driving behaviors DD, DFD, and ADB are affected by various factors including driver experience/inexperience of driving, age, and gender or illness. The study of the effects of these factors that may lead to deterioration in the driving skills and performance of a human driver is out of the scope of this paper. After describing the background of deep learning and its algorithms, we present an in-depth investigation of most recent deep learning-based systems, algorithms, and techniques for the detection of Distraction, Fatigue/Drowsiness, and Aggressiveness of a human driver. We attempt to achieve a comprehensive understanding of HIADB detection by presenting a detailed comparative analysis of all the recent techniques. Moreover, we highlight the fundamental requirements. Finally, we present and discuss some significant and essential open research challenges as future directions.

show abstract

Significance of Consuming 5 G ‐Built Artificial Intelligence in Smart Cities

Jinila

Joy

Thomas

et al. 2022

Artificial Intelligence in Industry 4.0 and 5G Technology

View full text Add to dashboard Cite

Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends

Cited by 263 publications

References 66 publications

Energy-efficient sensory data gathering based on compressed sensing in IoT networks

Energy-efficient sensory data gathering based on compressed sensing in IoT networks

Detecting Human Driver Inattentive and Aggressive Driving Behavior Using Deep Learning: Recent Advances, Requirements and Open Challenges

Significance of Consuming 5 G ‐Built Artificial Intelligence in Smart Cities

Contact Info

Product

Resources

About