Real-Time Transportation Mode Detection Using Smartphones and Artificial Neural Networks: Performance Comparisons Between Smartphones and Conventional Global Positioning System Sensors

Byon, Young-Ji; Liang, Steve H. L.

doi:10.1080/15472450.2013.824762

Cited by 41 publications

(27 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The studies find that an ANN-based mode detection approach is effective with reasonable accuracies. Byon et al [20] enhanced the ANN-based mode detection by utilizing directly-measured acceleration values from smartphones and found that accelerometer values from smartphones did improve the mode detection performances. Recently, there are more specialized applications of mode detection.…”

Section: Transportation Mode Detectionmentioning

confidence: 99%

“…They can provide additional assistance in classifying the different modes. Byon et al [20] find that those sensors are beneficial in detecting the transportation modes by producing more raw data in addition to the speed and acceleration values. For example, a boat mode, which usually operates with a wider view of the sky with less influences from buildings that would cause multi-path errors, can often see a greater number of satellites in view.…”

Section: Empirical Analysis On Input Factorsmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Transportation Mode Identification Using Artificial Neural Networks Enhanced with Mode Availability Layers: A Case Study in Dubai

Byon

Cho

et al. 2017

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Traditionally, departments of transportation (DOTs) have dispatched probe vehicles with dedicated vehicles and drivers for monitoring traffic conditions. Emerging assisted GPS (AGPS) and accelerometer-equipped smartphones offer new sources of raw data that arise from voluntarily-traveling smartphone users provided that their modes of transportation can correctly be identified. By introducing additional raster map layers that indicate the availability of each mode, it is possible to enhance the accuracy of mode detection results. Even in its simplest form, an artificial neural network (ANN) excels at pattern recognition with a relatively short processing timeframe once it is properly trained, which is suitable for real-time mode identification purposes. Dubai is one of the major cities in the Middle East and offers unique environments, such as a high density of extremely high-rise buildings that may introduce multi-path errors with GPS signals. This paper develops real-time mode identification ANNs enhanced with proposed mode availability geographic information system (GIS) layers, firstly for a universal mode detection and, secondly for an auto mode detection for the particular intelligent transportation system (ITS) application of traffic monitoring, and compares the results with existing approaches. It is found that ANN-based real-time mode identification, enhanced by mode availability GIS layers, significantly outperforms the existing methods.

show abstract

Section: Transportation Mode Detectionmentioning

confidence: 99%

Section: Empirical Analysis On Input Factorsmentioning

confidence: 99%

Real-Time Transportation Mode Identification Using Artificial Neural Networks Enhanced with Mode Availability Layers: A Case Study in Dubai

Byon

Cho

et al. 2017

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…The reference lists of excluded reviews were reviewed and potential papers were gathered. Finally, 12 published papers matching all the criteria were included in this review [1,31,[38][39][40][41][42][43][44][45][46][47], as shown in Table 2. In particular, we selected [39] because the segment identification method of this study is a significant data preprocessing technique for travel mode detection.…”

Section: Systematic Review Processmentioning

confidence: 99%

“…Among those studies, the majority concentrated on the identification of travel modes. Lots of approaches have been applied in inferring travel modes based on GPS data collected by dedicated GPS devices, such as Rule-based Method [25,26], Bayesian Model with Expectation Maximization [27], Fuzzy Logic Approach [19], Bayesian Belief Network Model [28], Multilayer Perceptron [29], Support Vector Machine [30], Artificial Neural Networks [31,32], and many others. Travel surveys based on dedicated GPS devices have the following disadvantages, however: (1) researchers need to spend huge amounts of money on dedicated GPS devices; (2) forgetting to take the GPS devices results in incomplete data collection; (3) the number of dedicated GPS devices is a limitation of the sample size; (4) in GPS-based travel survey, dedicated GPS devices need to be distributed to and retrieved from participants [33].…”

Section: Introductionmentioning

confidence: 99%

Travel Mode Detection Based on GPS Raw Data Collected by Smartphones: A Systematic Review of the Existing Methodologies

Yang

Jing

2016

Information

View full text Add to dashboard Cite

Abstract:Over the past couple of decades, global positioning system (GPS) technology has been utilized to collect large-scale data from travel surveys. As the precise spatiotemporal characteristics of travel could be provided by GPS devices, the issues of traditional travel survey, such as misreporting and non-response, could be addressed. Considering the defects of dedicated GPS devices (e.g., the need for a large sum of money to buy devices, forgetfulness in the taking of devices to collect data, limiting of the sample size because of the number of devices, etc.), and the fact that the smartphone is becoming one of the necessities of life, there is an opportunity for smartphones to replace dedicated GPS devices. Although several general reviews of GPS travel survey and GPS data-processing methods have been written, a systematic review of smartphone-based GPS data collection and travel mode detection has not be made.. The studies were collected from six databases. The purpose of this review is to critically evaluate the current literature on the existing methodologies of travel mode detection based on GPS raw data collected by smartphones. Meanwhile, according to a systematic comparison of the different methods of data preprocessing for travel mode detection, this paper details the strengths and weaknesses of the existing methods. Furthermore, it is a very important step towards developing methodologies and applications for GPS raw data collected by smartphones.

show abstract

“…Imputation algorithms reported in the literature vary from informal ad-hoc approaches (Wolf, Guensler, and Bachman 2001;Chung and Shalaby 2005;Du and Aultman-Hall 2007) to advanced machine learning methods, such as neural networks, fuzzy logic regression, support vector machines (SVMs), and Bayesian belief networks (BN) (Byon, Abdulhai, and Shalaby 2009;Schuessler and Axhausen 2009;Moiseeva, Jessuren, and Timmermans 2010;Rudloff and Ray 2010;Byon and Liang 2014). The so-called ad-hoc rulebased approaches in general involve a sequential process based on some revealed pattern or correlations, which are extracted empirically from specific data.…”

Section: Introductionmentioning

confidence: 99%

Comparison of advanced imputation algorithms for detection of transportation mode and activity episode using GPS data

Feng

Timmermans

2016

Transportation Planning and Technology

View full text Add to dashboard Cite

Global Positioning System (GPS) technologies have been increasingly considered as an alternative to traditional travel survey methods to collect activity-travel data. Algorithms applied to extract activity-travel patterns vary from informal ad-hoc decision rules to advanced machine learning methods and have different accuracy. This paper systematically compares the relative performance of different algorithms for the detection of transportation modes and activity episodes. In particular, naive Bayesian, Bayesian network, logistic regression, multilayer perceptron, support vector machine, decision table, and C4.5 algorithms are selected and compared for the same data according to their overall error rates and hit ratios. Results show that the Bayesian network has a better performance than the other algorithms in terms of the percentage correctly identified instances and Kappa values for both the training data and test data, in the sense that the Bayesian network is relatively efficient and generalizable in the context of GPS data imputation.

show abstract

Real-Time Transportation Mode Detection Using Smartphones and Artificial Neural Networks: Performance Comparisons Between Smartphones and Conventional Global Positioning System Sensors

Cited by 41 publications

References 7 publications

Real-Time Transportation Mode Identification Using Artificial Neural Networks Enhanced with Mode Availability Layers: A Case Study in Dubai

Real-Time Transportation Mode Identification Using Artificial Neural Networks Enhanced with Mode Availability Layers: A Case Study in Dubai

Travel Mode Detection Based on GPS Raw Data Collected by Smartphones: A Systematic Review of the Existing Methodologies

Comparison of advanced imputation algorithms for detection of transportation mode and activity episode using GPS data

Contact Info

Product

Resources

About