Identifying Travel Mode with GPS Data Using Support Vector Machines and Genetic Algorithm

Zong, Fang; Bai, Yu; Xiao, Wang; Yang, Yuchong; He, Yanan

doi:10.3390/info6020212

Cited by 15 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies using ML, which do not use further data for bicycle trip identification show accuracy values between 88% (e.g. [25,40]) and 100% [43]. However, the underlying machine learning models are very complex and can hardly be reproduced (see for instance [43]), which hampers model implementation and utilization, especially for practitioners.…”

Section: Discussionmentioning

confidence: 99%

“…They applied machine learning algorithms and reached a rate of 89% of correct identified trips. Following the approach of using machine learning (ML), the identification rate ranged from 82% to 100% using sensor data fusion of GPS, acceleration, magnetometer and further sensors [6,10,40,41,43]. Machine Learning approaches have in common to abstain from using GIS information; because of the problematic data treatment, furthermore they are highly accurate but hard to explain in their classification approaches.…”

Section: State Of Researchmentioning

confidence: 99%

“…Lißner and Huber European Transport Research Review (2021) 13:8 [19,20], Schüssler & Axhausen [26], Zong [43] Zhang et al [42] Biljecki [2,3], and Shen & Stopher [28]. The developed trip segmentation algorithm determines for each GPS point whether it belongs to a trip (e.g.…”

Section: Trip Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

Facing the needs for clean bicycle data – a bicycle-specific approach of GPS data processing

Lißner

Huber

2021

Eur. Transp. Res. Rev.

View full text Add to dashboard Cite

Background GPS-based cycling data are increasingly available for traffic planning these days. However, the recorded data often contain more information than simply bicycle trips. GPS tracks resulting from tracking while using other modes of transport than bike or long periods at working locations while people are still tracking are only some examples. Thus, collected bicycle GPS data need to be processed adequately to use them for transportation planning. Results The article presents a multi-level approach towards bicycle-specific data processing. The data processing model contains different steps of processing (data filtering, smoothing, trip segmentation, transport mode recognition, driving mode detection) to finally obtain a correct data set that contains bicycle trips, only. The validation reveals a sound accuracy of the model at its’ current state (82–88%).

show abstract

Section: Discussionmentioning

confidence: 99%

Section: State Of Researchmentioning

confidence: 99%

See 1 more Smart Citation

Facing the needs for clean bicycle data – a bicycle-specific approach of GPS data processing

Lißner

Huber

2021

Eur. Transp. Res. Rev.

View full text Add to dashboard Cite

show abstract

“…Tsui and Shalaby [21] used the fuzzy logic method to detect these four travel modes and achieved a high accuracy of 91%. Zong et al [49] used SVM combined with a genetic algorithm to recognize the walk, bicycle, subway, bus, and car modes and correctly detected 92.2% of their samples.…”

Section: Discussionmentioning

confidence: 99%

Detecting Travel Modes Using Rule-Based Classification System and Gaussian Process Classifier

2019

View full text Add to dashboard Cite

Travel modes are generally derived from Global Positioning System (GPS) data on the basis of either a rule-based or machine learning classification method. The rule-based classification approach is generally easy to understand, whereas the machine learning classification method has better generalization. However, studies that jointly explore both methods are limited. The present research proposes a two-stage method that aims to impute travel modes from GPS trajectory data. In the first stage, rules are employed to detect subway modes. In the second stage, a Gaussian process classifier based on sequential forward selection methods is utilized to derive the remaining travel modes. On the basis of the four selected features constituting the feature set (i.e., average speed, average acceleration, heading change, and low-speed point rate), over 97% of the samples with subway modes are correctly identified and 93.04% of segments in the walk-based balanced test subset are accurately detected. Over 92% of the car and bus samples are correctly detected for the training and test datasets. Results provide a new perspective in selecting classification methods for the detection of travel modes and other travel characteristics from GPS trajectory data. Furthermore, high differentiation is achieved between the bus and car modes without the bus transit geographic information system sources of bus networks. Therefore, reasonable extracted features contribute to the detection of travel modes, particularly between bus and car modes. INDEX TERMS Gaussian processes, classification algorithms, global positioning system.

show abstract

“…Some studies focused on identifying when a change between two modes occurs (Zheng et al 2008), while others focus on detecting stops while travelling (Zhao et al 2015). Oliver et al split transportation mode in two main categories, motorized and non-motorized vehicles (Oliver et al 2010), as opposed to other studies in which authors aimed to identify the exact transportation mode among more options, such as walking, bicycle, car and bus (Geurs et al 2015;Jahangiri and Rakha, 2015;Sonderen 2016;Zong et al 2015). Other researchers have used GNSS, accelerometer and Bluetooth together with map-matching algorithms to discretize different transportation modes (Chen and Bierlaire 2015).…”

Section: Introductionmentioning

confidence: 99%

Transportation Mode Detection from Low-Power Smartphone Sensors Using Tree-Based Ensembles

Efthymiou

Barmpounakis

Efthymiou

et al. 2019

J. Big Data Anal. Transp.

View full text Add to dashboard Cite

Recently, a considerable amount of research has focused on understanding transportation mobility patterns from crowdsourced smartphone data. To this end, transportation mode detection is an indispensable, yet challenging task towards deriving meaningful information from large datasets collected using smartphones. Most studies to date use Global Navigation Satellite Systems (GNSS) derived data such as speed to detect transportation mode. Limited research relies on sensors that do not depend on external sources, such as accelerometer and gyroscope. The present work proposes a methodological framework based on machine learning for identifying the transportation mode using accelerometer, gyroscope and orientation data in the absence of battery consuming sensors, such as GNSS. Different models are developed and compared based on random forest and gradient boosting machine algorithms. A comparative study between GNSS free and GNSS based algorithms is also established. Results are further discussed and possible research directions are provided.

show abstract

Identifying Travel Mode with GPS Data Using Support Vector Machines and Genetic Algorithm

Cited by 15 publications

References 27 publications

Facing the needs for clean bicycle data – a bicycle-specific approach of GPS data processing

Facing the needs for clean bicycle data – a bicycle-specific approach of GPS data processing

Detecting Travel Modes Using Rule-Based Classification System and Gaussian Process Classifier

Transportation Mode Detection from Low-Power Smartphone Sensors Using Tree-Based Ensembles

Contact Info

Product

Resources

About