An incident detection algorithm using artificial neural networks and traffic information

Ki, Yong-Kul; Heo, Nak-Won; Choi, Jinwook; Ahn, Gye-Hyeong; Park, Kil-Soo

doi:10.1109/cyberi.2018.8337551

Cited by 14 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of cellular network optimisation, various machine learning algorithms including decision tree [21], k-means algorithm [22,23], and artificial neural networks [24] have been employed for predicting user mobility patterns in order to perform network resource optimisation patterns. In the context of road networks, NN algorithms [25,26] have been used for short-term traffic flow prediction, as well for reduce road congestion by analysing traffic information and further relaying the message back to the vehicles [27]. A smartphone based software to recognise traffic flows with high accuracy was proposed by using the Random Forests (RF) classification model and positioning technology in [26,28].…”

Section: Related Workmentioning

confidence: 99%

Mobility Prediction-Based Optimisation and Encryption of Passenger Traffic-Flows Using Machine Learning

Asad

Ahmad

Hussain

et al. 2020

Sensors

View full text Add to dashboard Cite

Information and Communication Technology (ICT) enabled optimisation of train’s passenger traffic flows is a key consideration of transportation under Smart City planning (SCP). Traditional mobility prediction based optimisation and encryption approaches are reactive in nature; however, Artificial Intelligence (AI) driven proactive solutions are required for near real-time optimisation. Leveraging the historical passenger data recorded via Radio Frequency Identification (RFID) sensors installed at the train stations, mobility prediction models can be developed to support and improve the railway operational performance vis-a-vis 5G and beyond. In this paper we have analysed the passenger traffic flows based on an Access, Egress and Interchange (AEI) framework to support train infrastructure against congestion, accidents, overloading carriages and maintenance. This paper predominantly focuses on developing passenger flow predictions using Machine Learning (ML) along with a novel encryption model that is capable of handling the heavy passenger traffic flow in real-time. We have compared and reported the performance of various ML driven flow prediction models using real-world passenger flow data obtained from London Underground and Overground (LUO). Extensive spatio-temporal simulations leveraging realistic mobility prediction models show that an AEI framework can achieve 91.17% prediction accuracy along with secure and light-weight encryption capabilities. Security parameters such as correlation coefficient (<0.01), entropy (>7.70), number of pixel change rate (>99%), unified average change intensity (>33), contrast (>10), homogeneity (<0.3) and energy (<0.01) prove the efficacy of the proposed encryption scheme.

show abstract

Section: Related Workmentioning

confidence: 99%

Mobility Prediction-Based Optimisation and Encryption of Passenger Traffic-Flows Using Machine Learning

Asad

Ahmad

Hussain

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Despite the technologies adopted, most of the incident detection algorithms are essentially built on the same fundamental observation that, during a traffic incident, the traffic flow upstream of congestion is characterised by slower speed, longer travelling time and shorter distance for lane changing. Thus, the speed and travel time patterns of vehicles become the common features used for incident detection algorithms [5,6].…”

Section: Real-time Incident Detection and Eta Improvementmentioning

confidence: 99%

“…Fixed location sensors are able to collect traffic flow rate, speed and time occupancy at a certain location, and have been utilised for the development of well-known algorithms such as SND [13], California [14], and UBC [15]. With the development of remote sensors and technologies, more data and details of the traffic are now available, which leads to further development of data-driven algorithms, such as rule-based [16], wavelet-based [17], shockwave theory-based [18], and machine learning-based algorithms [6,19,20]. Recently, Xiao (2019) [20] further boosted the robustness of incident detection through an ensemble learning method.…”

Section: Incident Detectionmentioning

confidence: 99%

“…In terms of the area of application, most studies focused on incident detection on freeways [5,6,[21][22][23][24], which feature relatively controlled road conditions due to fixed entrances and exits without the many intersections and traffic control measures found on urban roads. For urban road systems, Pan and Wu [25] designed a traffic incident detection method to recognise the abnormal traffic state based on support vector machine (SVM).…”

Section: Incident Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Data‐driven next destination prediction and ETA improvement for urban delivery fleets

Bing

Teo

et al. 2019

IET Intelligent Transport Systems

View full text Add to dashboard Cite

“…e machine learning methods for dealing with the traffic signal control problems also were comprehensively pondered [43]. For optimizing the traffic signal at a single intersection, neural networks methods and convolution neural networks approaches were utilized to optimize the traffic signal plans [44][45][46][47]. In addition, deep reinforcement learning techniques were applied to solve the traffic signal schemes [48][49][50][51].…”

Section: Introductionmentioning

confidence: 99%

MTGPLP Approach for Traffic Signal Intelligent Control

Liu

Zou

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In this paper, we state a combining programming approach to optimize traffic signal control problem. The objective of the model is to minimize the total queue length with weight factors at the end of each phase. Then, modified Twin Gaussian Process (MTGP) is employed to predict the arrival rates for the traffic signal control problem. For achieving automatic control of the traffic signal, an intelligent control method of the traffic signal is proposed in view of the combining method, that is to say, the combining method of MTGP and LP, called MTGPLP, is embraced in the intelligent control system. Furthermore, some numerical experiments are proposed to test the validity of the model and the MTGPLP approach. In particular, the results of numerical experiments show that the model is effective with different arrival rates, departure rates, and weight factors and the combining method is successful.

show abstract

An incident detection algorithm using artificial neural networks and traffic information

Cited by 14 publications

References 11 publications

Mobility Prediction-Based Optimisation and Encryption of Passenger Traffic-Flows Using Machine Learning

Mobility Prediction-Based Optimisation and Encryption of Passenger Traffic-Flows Using Machine Learning

Data‐driven next destination prediction and ETA improvement for urban delivery fleets

MTGPLP Approach for Traffic Signal Intelligent Control

Contact Info

Product

Resources

About