Urban Mobility Pattern Detection: Development of a Classification Algorithm Based on Machine Learning and GPS.

This study introduces an innovative algorithm for classifying transportation modes. It categorizes modes such as walking, biking, tram, bus, taxi, and private vehicles based on data collected through sensors embedded in smartphones. The data include date, time, latitude, longitude, altitude, and speed, gathered using a mobile application specifically designed for this project. These data were collected through the smartphone's GPS to enhance the accuracy of the analysis. The stopping times of each transport mode, as well as the distance traveled and average speed, are analyzed to identify patterns and distinctive features. Conducted in Cuenca, Ecuador, the study aims to develop and validate an algorithm to enhance urban planning. It extracts significant features from mobility patterns, including speed, acceleration, and over-acceleration, and applies longitudinal dynamics to train the classification model. The classification algorithm relies on a decision tree model, achieving a high accuracy of 94.6% in validation and 94.9% in testing, demonstrating the effectiveness of the proposed approach. Additionally, the precision metric of 0.8938 signifies the model's ability to make correct positive predictions, with nearly 90% of positive instances correctly identified. Furthermore, the recall metric at 0.83084 highlights the model's capability to identify real positive instances within the dataset, capturing over 80% of positive instances. The calculated F1-score of 0.86117 indicates a harmonious balance between precision and recall, showcasing the models robust and well-rounded performance in classifying transport modes effectively. The study discusses the potential applications of this method in urban planning, transport management, public transport route optimization, and urban traffic monitoring. This research represents a preliminary stage in generating an origin-destination (OD) matrix to better understand how people move within the city.

GPS Data and Machine Learning Tools, a Practical and Cost-Effective Combination for Estimating Light Vehicle Emissions.

This paper focuses on the emissions of the three most sold categories of light vehicles: sedans, SUVs, and pickups. The research is carried out through an innovative methodology based on GPS and machine learning in real driving conditions. For this purpose, driving data from the three best-selling vehicles in Ecuador are acquired using a data logger with GPS included, and emissions are measured using a PEMS in six RDE tests with two standardized routes for each vehicle. The data obtained on Route 1 are used to estimate the gears used during driving using the K-means algorithm and classification trees. Then, the relative importance of driving variables is estimated using random forest techniques, followed by the training of ANNs to estimate CO2, CO, NOX, and HC. The data generated on Route 2 are used to validate the obtained ANNs. These models are fed with a dataset generated from 324, 300, and 316 km of random driving for each type of vehicle. The results of the model were compared with the IVE model and an OBD-based model, showing similar results without the need to mount the PEMS on the vehicles for long test drives. The generated model is robust to different traffic conditions as a result of its training and validation using a large amount of data obtained under completely random driving conditions.

Influence of mobility restrictions on air quality in the historic center of Cuenca city and its inference on the Covid-19 rate infections.

At the end of 2019 in Wuhan China city, the outbreak of the virus called SARS-CoV 2 was originated, which later became a pandemic. In Ecuador, patient zero arrived on February 14, 2020 and the first mobility restriction imposed by the Government occurred on Tuesday, March 17 of the same year. Throughout the confinement, vehicle mobility restrictions have been modified by government entities depending on the number of infected people. This article presents an air quality study in the historic center of Cuenca city as consequence of mobility changes caused by Covid-19, where a comparison of concentration levels of polluting gases of the first semester of 2018, 2019 and 2020 is made, that allow differentiating and identifying the influence of vehicular flow on air quality. It can also be verified how the decrease in vehicle mobility restrictions influenced the increase in the rate of daily infections. For the study, air quality data published by the public mobility company of the city of Cuenca (EMOV EP) and the communications issued by the Emergency Operations Committee (COE), before and during the confinement, were collected. The acquisition, classification, analysis and interpretation of the data obtained through machine learning techniques was carried out. It can be concluded that while mobility restrictions were more severe, air quality improved and infections rate of decrease. Obtaining that polluting gases such as NO2 and CO produced by vehicular traffic show correlations of 61% and 60% respectively, which means that after 15 days of lifting the restrictive measures, the pollutants increased as well as the number of infected.

Estimation of Pollutant Emissions in Real Driving Conditions Based on Data from OBD and Machine Learning.

This article proposes a methodology for the estimation of emissions in real driving conditions, based on board diagnostics data and machine learning, since it has been detected that there are no models for estimating pollutants without large measurement campaigns. For this purpose, driving data are obtained by means of a data logger and emissions through a portable emissions measurement system in a real driving emissions test. The data obtained are used to train artificial neural networks that estimate emissions, having previously estimated the relative importance of variables through random forest techniques. Then, by the application of the K-means algorithm, labels are obtained to implement a classification tree and thereby determine the selected gear by the driver. These models were loaded with a data set generated covering 1218.19 km of driving. The results generated were compared to the ones obtained by applying the international vehicle emissions model and with the results of the real driving emissions test, showing evidence of similar results. The main contribution of this article is that the generated model is stronger in different traffic conditions and presents good results at the speed interval with small differences at low average driving speeds because more than half of the vehicle's trip occurs in urban areas, in completely random driving conditions. These results can be useful for the estimation of emission factors with potential application in vehicular homologation processes and the estimation of vehicular emission inventories.