Nested Binary Classifier as an Outlier Detection Method in Human Activity Recognition Systems
Open Access
Abstract
The present article is devoted to outlier detection in phases of human movement. The aim was to find the most efficient machine learning method to detect abnormal segments inside physical activities in which there is a probability of origin from other activities. The problem was reduced to a classification task. The new method is proposed based on a nested binary classifier. Test experiments were then conducted using several of the most popular machine learning algorithms (linear regression, support vector machine, k-nearest neighbor, decision trees). Each method was separately tested on three datasets varying in characteristics and number of records. We set out to evaluate the effectiveness of the models, basic measures of classifier evaluation, and confusion matrices. The nested binary classifier was compared with deep neural networks. Our research shows that the method of nested binary classifiers can be considered an effective way of recognizing outlier patterns for HAR systems.Keywords
This publication has 23 references indexed in Scilit:
- Human activity recognition based on the combined SVM&HMM2014
- In-network approximate computation of outliers with quality guaranteesInformation Systems, 2013
- Design considerations for the WISDM smart phone-based sensor mining architecture2011
- Fault Forecast and Diagnosis of Steam Turbine Based on Fuzzy Rough Set Theory2007
- Human Activity Recognition with User-Free Accelerometers in the Sensor Networks2006
- Mining class outliers: concepts, algorithms and applications in CRMExpert Systems with Applications, 2004
- Outlier detection in chemical data by fractal analysisJournal of Chemometrics, 2004
- Outlier Detection Using Replicator Neural Networks2002
- Distance-based outliers: algorithms and applicationsThe VLDB Journal, 2000
- Identification of Outliers1980