IEEE Sensors Journal · 2014 · 38 citations · 12 references
ComputingKinesiologyMobile ComputingMovement AnalysisSensor FusionGait AnalysisMobile Human-computer InteractionMobile SensingMobility AssessmentMobility Pattern AnalysisMobility PatternsAccuracyActivitiesActivity RecognitionHuman Activity RecognitionMotion SensingMultimodal SensorsWearable Force SensorsWearable Sensors
Recent advances in the development of multimodal wearable sensors enable us to gather richer contexts of mobile user activities. The combination of foot force sensor (FF) and GPS is able to afford fine-grained mobility activity recognition. We derive and identify 12 (out of 31) maximally informative FF features, and the minimal most effective insole positions (two per foot) for sensing, to improve the use of FF + GPS methods for mobility activity recognition. We tested the improved FF + GPS method using over 7000 samples collected from ten volunteers in a natural, unconstrained, environment. The results show that the improved FF + GPS can achieve an average accuracy of over 90% when detecting five different mobility activities, including walking, cycling, bus-passenger, car-passenger, and car-driver.
12
A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection
Ron Kohavi · 1995 · 10.7K citations · Full text
An Introduction to Variable and Feature Selection.
2003 · 6.6K citations
Using mobile phones to determine transportation modes
Sasank Reddy, Min Mun, Jeff Burke et al. · ACM Transactions on Sensor Networks · 2010 · 858 citations