Using Probe Person Data for Travel Mode Detection
نویسنده
چکیده
Recently GPS data is used in a lot of studies to automatically reconstruct travel patterns for trip survey. The aim is to minimize the use of questionnaire surveys and travel diaries so as to reduce their negative effects. In this paper data acquired from GPS and accelerometer embedded in smart phones is utilized to predict the mode of transportation used by the phone carrier. For prediction, Support Vector Machine (SVM) and Adaptive boosting (AdaBoost) are employed. Moreover a unique method to improve the prediction results from these algorithms is also proposed. Results suggest that the prediction accuracy of AdaBoost after improvement is relatively better than the rest. Keywords—Accelerometer, AdaBoost, GPS, Mode Prediction, Support vector Machine.
منابع مشابه
A New Colorimetric Azo-azomethine Probe for Fluoride Ion Detection Based on the Proton Transfer Signaling Mode: Real-life Applications
Four novel receptors were designed and synthesized for colorimetric detection of F− ions. The introduction of four electron withdrawing groups into the backbone of the receptors makes the two phenolic groups efficient hydrogen bonding sites. The binding properties of receptors with anions were examined for the first time by UV–Vis, 1H NMR and fluorescence spectroscopies. The addition of F− resu...
متن کاملMotor vehicle crash injury rates by mode of travel, United States: using exposure-based methods to quantify differences.
The authors used traffic exposure data to calculate exposure-based fatal and nonfatal traffic injury rates in the United States. Nationally representative data were used to identify fatal and nonfatal traffic injuries that occurred from 1999 to 2003, and the 2001 National Household Travel Survey was used to estimate traffic exposure (i.e., person-trips). Fatal and nonfatal traffic injury rates ...
متن کاملOriginal Contribution Motor Vehicle Crash Injury Rates by Mode of Travel, United States: Using Exposure-Based Methods to Quantify Differences
The authors used traffic exposure data to calculate exposure-based fatal and nonfatal traffic injury rates in the United States. Nationally representative data were used to identify fatal and nonfatal traffic injuries that occurred from 1999 to 2003, and the 2001 National Household Travel Survey was used to estimate traffic exposure (i.e., person-trips). Fatal and nonfatal traffic injury rates ...
متن کاملModelling Departure Time, Destination and Travel Mode Choices by Using Generalized Nested Logit Model: Discretionary Trips (Research Note)
Despite traditional four-step model is the most prominent model in majority of travel demand analysis, it does not represent the potential correlations within different travel dimensions. As a result, some researches have suggested the use of choice modelling instead. However, most of them have represented travel dimensions individually rather than jointly. This research aims to fill this gap t...
متن کاملDesign and fabrication of a high-Q near-field probe for subsurface crack detection
Non-destructive detection and evaluation of invisible cracks in metal structures is an important matter in several critical environments including ground transportation, air transportation and power plants. In this paper, a high-Q near-field Microwave probe is designed and fabricated using defected ground structures for surface and subsurface crack detection in metal structures. For this purpos...
متن کامل