Multi-label classification of estimated time of arrival with ensemble neural networks in bus transportation network

Kee, Chee Yau; Wong, Li-Pei; Khader, Ahamad Tajudin; Hassan, Fadratul Hafinaz

doi:10.1109/icite.2017.8056898

Cited by 8 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chen [16] found through experiments that the Random Forest-based traffic event detection model was superior to the multi-layer feedforward neural network method in terms of detection rate, detection time, and classification accuracy. The algorithm decomposed the same problem into multiple different modules, and multiple learners participated in learning to solve the target problem, and effectively improved the generalization ability of the classifier [17,18]. According to the characteristics of traffic monitoring data, the application of this method about travel time analysis and traffic state judgment has a good prospect.…”

Section: Related Workmentioning

confidence: 99%

A Traffic Event Detection Method Based on Random Forest and Permutation Importance

Liu

Zhao

et al. 2022

Mathematics

View full text Add to dashboard Cite

Although the video surveillance system plays an important role in intelligent transportation, the limited camera views make it difficult to observe many traffic events. In this paper, we collect and combine the traffic flow variables from the multi-source sensors, and propose a PITED method based on Random Forest (RF) and Permutation importance (PI) for traffic event detection. This model selects the suitable traffic flow variables by means of permutation arrangement of importance, and establishes the whole process of acquisition, preprocessing, quantization, modeling and evaluation. Moreover, the real traffic data are collected and tested in this paper for evaluating the experiment performance, including the miss/false rate of traffic event, and average detection time. The experimental results show that the detection rate is more than 85% and the false alarm rate is less than 3%. It means the model is effective and efficient in the practical application regardless of both workdays and holidays.

show abstract

Section: Related Workmentioning

confidence: 99%

A Traffic Event Detection Method Based on Random Forest and Permutation Importance

Liu

Zhao

et al. 2022

Mathematics

View full text Add to dashboard Cite

show abstract

“…This issue is addressed as missing data points and can be identified by filling up a monthly report of IOSs (Barabino et al, 2013). Some studies have dropped the stations with missing data while some have used interpolation techniques to retrieve the missing data (Chen et al, 2007; Kee et al, 2017). Interpolating arrival times at only bus stops rather than for some fixed distance can reduce computation significantly while maintaining prediction results (Liu, Xu, et al, 2020).…”

Section: Data In Detailmentioning

confidence: 99%

“…Normally multiple arrivals of buses are seen at the same stop in an hour. This motivated the researchers to see the bus arrival problem as a multilabel classification problem (Kee et al, 2017). Two main ensemble techniques, AdaBoost and Random k‐labelsets (RAkEL) with 2‐labelsets and 3‐labelsets were explored as an ensemble of neural networks.…”

Section: Artificial Intelligence Based Modelsmentioning

confidence: 99%

A review of bus arrival time prediction using artificial intelligence

Singh

Kumar

2022

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Buses are one of the important parts of public transport system. To provide accurate information about bus arrival and departure times at bus stops is one of the main parameters of good quality public transport. Accurate arrival and departure times information is important for a public transport mode since it enhances ridership as well as satisfaction of travelers. With accurate arrival-time and departure time information, travelers can make informed decisions about their journey. The application of artificial intelligence (AI) based methods/algorithms to predict the bus arrival time (BAT) is reviewed in detail. Systematic survey of existing research conducted by various researchers by applying the different branches of AI has been done. Prediction models have been segregated and are accumulated under respective branches of AI. Thorough discussion is presented to elaborate different branches of AI that have been applied for several aspects of BAT prediction. Research gaps and possible future directions for further research work are summarized.

show abstract

“…All three algorithms are capable of adapting to complex systems and are robust in dealing with complex and small data sets. They have shown superior performance in previous research with low processing time [1,2,25,37].…”

Section: Choice Of Learning Algorithmsmentioning

confidence: 99%

“…As we also assume that public holidays have a significant influence on the travel time, we have added features considering the day class of the departure day, the current day, and the next five days. The day of the week is classified into weekday, Saturday or bridge day, and Sunday or public holiday, [33] (p. 2) and [37] (p. 151).…”

Section: Feature Engineering and Data Transformationmentioning

confidence: 99%

Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms

2019

View full text Add to dashboard Cite

Accurate travel time prediction is of high value for freight transports, as it allows supply chain participants to increase their logistics quality and efficiency. It requires both sufficient input data, which can be generated, e.g., by mobile sensors, and adequate prediction methods. Machine Learning (ML) algorithms are well suited to solve non-linear and complex relationships in the collected tracking data. Despite that, only a minority of recent publications use ML for travel time prediction in multimodal transports. We apply the ML algorithms extremely randomized trees (ExtraTrees), adaptive boosting (AdaBoost), and support vector regression (SVR) to this problem because of their ability to deal with low data volumes and their low processing times. Using different combinations of features derived from the data, we have built several models for travel time prediction. Tracking data from a real-world multimodal container transport relation from Germany to the USA are used for evaluation of the established models. We show that SVR provides the best prediction accuracy, with a mean absolute error of 17 h for a transport time of up to 30 days. We also show that our model performs better than average-based approaches.

show abstract

Multi-label classification of estimated time of arrival with ensemble neural networks in bus transportation network

Cited by 8 publications

References 17 publications

A Traffic Event Detection Method Based on Random Forest and Permutation Importance

A Traffic Event Detection Method Based on Random Forest and Permutation Importance

A review of bus arrival time prediction using artificial intelligence

Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms

Contact Info

Product

Resources

About