IEEE Sensors Journal · 2017 · 55 citations · 5 references
ComputingComputer ScienceHealth InformaticsData MiningFeature EngineeringMachine LearningAction RecognitionGait AnalysisGait AssessmentMovement Pattern AnalysisPattern RecognitionSupport Vector MachinesGait RecognitionHuman Movement ClassificationMovement RecognitionStair AscentStair Descent BehaviorSupport Vector ClassificationSupport Vector Machine ClassificationWalking
Plantar pressure sensors can capture data for level walking, stair descent, and stair ascent. The study proposes a novel method for classifying ambulatory activities using eight plantar pressure sensors embedded in smart shoes. The method extracts new features from pressure patterns and then applies a multi‑class support vector machine after selecting critical features to classify the activities. When applied to an experimental database, the approach achieves recognition rates of up to 95.2% after six steps.
In this letter, we propose a novel method for classifying ambulatory activities using eight plantar pressure sensors within smart shoes. Using these sensors, pressure data of participants can be collected regarding level walking, stair descent, and stair ascent. Analyzing patterns of the ambulatory activities, we present new features with which to describe the ambulatory activities. After selecting critical features, a multi-class support vector machine algorithm is applied to classify these activities. Applying the proposed method to the experimental database, we obtain recognition rates up to 95.2% after six steps.
5
Dean M. Karantonis, Michael R. Narayanan, M. Mathie et al. · IEEE Transactions on Information Technology in Biomedicine · 2006 · 1.2K citations
Engineering, Health Informatics, Mechatronics Engineering +17
Stride Counting in Human Walking and Walking Distance Estimation Using Insole Sensors
Phuc Huu Truong, Jinwook Lee, Ae‐Ran Kwon et al. · Sensors · 2016 · 61 citations · Full text