Accelerator-Based Human Activity Recognition Using Voting Technique with NBTree and MLP Classifiers

Abstract

In evolution and ubiquitous computing systems, accelerometer-based human activity recognition has huge potential in a large number of application domains. Accelerometer-based human activity recognition aims to identify physical activities performed by human using accelerometer; a sensor device attached to the body and returns an actual valued estimate of acceleration along the x, y-and z-axes from which the sensor location can be estimated. In this study, an accelerator-based activity recognition model using voting technique was proposed. Two machine learning classifiers, Naïve Bayes Tree (NBTree) and Multilayer Perceptron (MLP), were used as ensemble classifiers in the voting technique. To evaluate the proposed voting technique, the performance of selected individual classifiers and existing voting technique was first examined, followed by the experiment to determine the performance of the proposed model. All of the experiments were performed using a standard dataset called Wireless Sensor Data Mining involving six physical human activities; jogging, walking, walking towards upstairs, walking towards downstairs, sitting and stand still. Results showed that the proposed voting technique with NBTree and MLP ensemble classifiers outperformed other individual classifiers and another previously suggested voting technique for accelerometer-based human activity recognition.

Transformer-based ensemble method for multiple predominant instruments recognition in polyphonic music

“…The experimental results validate the claim in [52]. The advantage of voting is that it is unlikely that all classifiers will make the same mistake, as long as every error is made by a minority of the classifiers, an optimal classification can be achieved [53].…”

Wearable Sensor-Based Human Activity Recognition in the Smart Healthcare System

“…In the DT method, a set of features must be selected correctly to have high accuracy for recognition. This method uses a sliding window [ 83 ], which has an excellent computational performance. Some research work using other sensors in conjunction with inertial sensors uses conceptual information to improve diagnostic accuracy [ 76 ].…”

Classification of Human Daily Activities Using Ensemble Methods Based on Smartphone Inertial Sensors

“…In [19,20,21,22,23,24,25] researchers have implemented the time domain and frequency domain feature extraction as a combined approach. Other researchers in [26,27,28,29,30,31] have used feature extraction in the time domain only, whilst, in [32] researchers applied the frequency domain and time-frequency domain. The authors in [33] have chosen the time domain, frequency domain and time-frequency domain for feature extraction.…”

“…Romero et al [24] have found that One vs. one (OVO), OVO-SVM gives the best overall classification accuracy rate as 96.4%; whilst, Anguita et al [25] managed to gain a little improvement and reported best overall accuracy rate as 96.5% for classification using One vs. all (OVA), OVA-SVM. Researchers in [26,27,28], have analyzed the same dataset for walking, jogging, walking downstairs, walking, upstairs, sitting, and standing activities. A study conducted by Sufyan et al [26] found that classification on voting Multilayer perceptron (MLP) and NBtree give the best accuracy rate for classification based on each activity.…”

“…Researchers in [26,27,28], have analyzed the same dataset for walking, jogging, walking downstairs, walking, upstairs, sitting, and standing activities. A study conducted by Sufyan et al [26] found that classification on voting Multilayer perceptron (MLP) and NBtree give the best accuracy rate for classification based on each activity. This study found that Voting MLP-NBtree gives the best accuracy rate of classification on walking at 99.23%, jogging at 98.86%, walking upstairs at 93.35%, walking downstairs at 90.15%, sitting at 98.37% and standing at 98.37%.…”