Travel mode detection based on GPS raw data collected by smartphones: a systematic review of the existing methodologies

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., need much money to buy devices, forget to take devices to collect data, limit the simple size because of the number of devices, etc.), and the phenomenon that the smartphone is becoming one of necessities of life, there is a great chance for the smartphone to replace dedicated GPS devices. Although, several general reviews have been done about smartphone-based GPS travel survey in the literature review section in some articles, a systematic review from smartphone-based GPS data collection to travel mode detection has none. The included studies were searched from six databases. The purpose of this review is to critically assess the current literature on the existing methodologies of travel mode detection based on GPS raw data collected by smartphones. Meanwhile, according to the systematic comparison among different methods from data-preprocessing to travel mode detection, this paper could carefully provide the Strengths and Weaknesses of existing methods. Furthermore, it is the crucial step to develop the methodologies and applications of GPS raw data collected by smartphones.

Who you are is how you travel: A framework for transportation mode detection using individual and environmental characteristics

“…The main advantages of using such an approach are the ease and cost efficiency of data collection process as well as the relatively high spatial accuracy, as the majority of smart-phones are equipped with GPS receivers and accelerometers. Often, the most common disadvantage that has been reported is the increased battery demand on the user's devices (Xiao et al 2015;Wu et al 2016), especially when both GPS and accelerometer readings are logged. However, for any practical applications, the accuracy and precision of the collected data impose an additional challenge for modelling (Eftekhari & Ghatee 2016;Wu et al 2016).…”

“…Often, the most common disadvantage that has been reported is the increased battery demand on the user's devices (Xiao et al 2015;Wu et al 2016), especially when both GPS and accelerometer readings are logged. However, for any practical applications, the accuracy and precision of the collected data impose an additional challenge for modelling (Eftekhari & Ghatee 2016;Wu et al 2016). This can be especially true for middle to low end smart-phones.…”

CityTracks-RT: Uma aplicação para detecção do modo de transporte em tempo real nos centros urbanos

“…As limitações deste estudo foram o fato de que os autores não consideraram uma deficiência do algoritmo de rede neural tradicional, chamada de local optimum, e o fato de que a comparação de resultados com outros estudos tem pouco valor, uma vez que diferentes estudos utilizam dados de qualidade distinta, o que gera um grande impacto nos resultados. Em estudos realizados com dados de GPS de alta precisão os resultados tendem a ser melhores que em estudos onde os dados coletados não contém alta precisão no posicionamento [13].…”

“…Os resultados mostraram uma precisão na detecção do modo de transporte de 96,91%. Apesar da alta precisão detectada, algumas limitações deste trabalho foram o fato de não terem sido amplamente aplicadas técnicas de reconhecimento de erros de dados e a falta de uma base científica para a seleção do modelo de random forest utilizado [13].…”

Travel mode recognition of urban residents using mobile phone data and MapAPI

“…Among them, GPS data have attracted much attention because of their very high spatial and temporal resolution. However, due to their large size, the collection, calculation and storage of GPS data become extremely complex (Auld et al, 2009;Wu et al, 2016). On the other hand, bus and subway card data can only be used to analyze the travels of residents who use these specific means of public transit, but not those of pedestrians or car drivers (Qi et al, 2019).…”