2018 · 36 citations · 9 references
ComputingComputer ScienceMachine LearningMobile ComputingTransportationIntelligent Transportation SystemsLocomotion AnalysisMobile SensingMobility Pattern AnalysisMobility PatternsPattern RecognitionActivity Level AnalysisActivity Level MonitoringHuman Activity RecognitionLocomotionMotion Pattern RecognitionMovement RecognitionOffline Data ProcessingRandom Forest Classification
In this paper, we have used a smartphone sensor-based benchmark Sussex-Huawei Locomotion-Transportation (SHL) dataset for rich locomotion and transportation analytics. We have shown a comparison of different sensor-based features for the identification of a specific activity level. Besides, we have proposed a "Mod technique" method, which increases the accuracy of classifier outputs in offline processing method. We have assumed that the minimum switching time from one transportation activity to another is 1-minute as a base of this technique. Based on this assumption we have been able to correct the wrong prediction of the classifier outputs in each 1-minute data frame. Our proposed method brings 4.56% accuracy increase in the Random Forest (RnF) classifier output. Our team, "Confusion Matrix" has developed this algorithm pipeline for the "Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge".
9
Activity recognition from accelerometer data
Nishkam Ravi, Nikhil Dandekar, Preetham Mysore et al. · 2005 · 1.4K citations
Computing, Data Science, Data Mining +16
Window Size Impact in Human Activity Recognition
Oresti Baños, Juan Manuel Gálvez, Miguel Damas et al. · Sensors · 2014 · 633 citations · Full text