Ferhat Attal

Physical Human Activity Recognition Using Wearable Sensors.

This paper presents a review of different classification techniques used to recognize human activities from wearable inertial sensor data. Three inertial sensor units were used in this study and were worn by healthy subjects at key points of upper/lower body limbs (chest, right thigh and left ankle). Three main steps describe the activity recognition process: sensors’ placement, data pre-processing and data classification. Four supervised classification techniques namely, k-Nearest Neighbor (k-NN), Support Vector Machines (SVM), Gaussian Mixture Models (GMM), and Random Forest (RF) as well as three unsupervised classification techniques namely, k-Means, Gaussian mixture models (GMM) and Hidden Markov Model (HMM), are compared in terms of correct classification rate, F-measure, recall, precision, and specificity. Raw data and extracted features are used separately as inputs of each classifier. The feature selection is performed using a wrapper approach based on the RF algorithm. Based on our experiments, the results obtained show that the k-NN classifier provides the best performance compared to other supervised classification algorithms, whereas the HMM classifier is the one that gives the best results among unsupervised classification algorithms. This comparison highlights which approach gives better performance in both supervised and unsupervised contexts. It should be noted that the obtained results are limited to the context of this study, which concerns the classification of the main daily living human activities using three wearable accelerometers placed at the chest, right shank and left ankle of the subject.

Physical activity recognition using inertial wearable sensors — A review of supervised classification algorithms

The goal of this paper is to compare the performances of various supervised algorithms in classifying physical daily living activities. Six healthy subjects were asked to perform twelve static and dynamic activities such as walking, running, sitting down, standing-up, lying, climbing stairs, etc. Three triaxial accelerometers are used to measure the human movements resulting from each activity. Seven supervised classification techniques are used: K-Nearest Neighbors (K-NN), Support Vector Machine (SVM), Random Forest (RF), Multi-Layer Perceptron (MLP), Classification And Regression Tree (CART), Naive Bayes (NB), and Gaussian Mixture Model (GMM). These methods are compared in terms of correct classification rate (Accuracy), Recall, Precision, F-measure and execution time. The 10-fold cross validation is used as a validation procedure. The obtained results show that K-NN gives the best results with 96.26 % of correct classification rate.

Riding patterns recognition for Powered two-wheelers users' behaviors analysis

In this paper, we develop a simple and efficient methodology for riding patterns recognition based on a machine learning framework. The riding pattern recognition problem is formulated as a classification problem aiming to identify the class of the riding situation by using data collected from three-accelerometer and three-gyroscope sensors mounted on the motorcycle. These measurements constitute experimental database which is valuable to analyze Powered Two Wheelers (PTW) rider behavior. Five well known machine learning techniques are used: the Gaussian mixture models (GMMs), k-Nearest Neighbors (k-NN), Support Vector Machines (SVMs), Random Forests (RFs) and the Hidden Markov Models (HMMs) in both (discrete and continuous) cases. The HMMs are widely applied for studying time series data which is the case of our problem. The data preprocessing consists of filtering, normalizing and manual labeling in order to create the training and testing sets. The experimental study carried out on a real dataset shows the effectiveness of the proposed methodology and more particularly of the HMM approach to perform such riding pattern recognition. These encouraging results work in favor of developing such methodologies in the naturalistic riding studies (NRS).

Powered Two-Wheeler Riding Pattern Recognition Using a Machine-Learning Framework

In this paper, a machine-learning framework is used for riding pattern recognition. The problem is formulated as a classification task to identify the class of riding patterns using data collected from 3-D accelerometer/gyroscope sensors mounted on motorcycles. These measurements constitute an experimental database used to analyze powered two-wheeler rider behavior. Several well-known machine-learning techniques are investigated, including the Gaussian mixture models, the k-nearest neighbor model, the support vector machines, the random forests, and the hidden Markov models (HMMs), for both discrete and continuous cases. Additionally, an approach for sensor selection is proposed to identify the significant measurements for improved riding pattern recognition. The experimental study, performed on a real data set, shows the effectiveness of the proposed methodology and the effectiveness of the HMM approach in riding pattern recognition. These results encourage the development of these methodologies in the context of naturalistic riding studies.

The Powered Two Wheelers Fall Detection Using Multivariate Cumulative SUM (MCUSUM) Control Charts

This paper presents a simple and efficient methodology that uses both acceleration and angular velocity signals to detect a fall of Powered Two Wheelers (PTW). Detecting the riders fall (before the impact of the rider on the ground) can indeed be used to provide a signal in order to trigger inflation of an airbag jacket worn by the rider, reducing thus the injury severity. The fall detection is therefore formulated as a sequential anomaly detection problem. The paper investigates the popular method namely Multivariate CUmulative SUM (MCUSUM) control charts to detect such anomalies. The MCUSUM algorithm was applied on the data collected from three-accelerometer and three-gyroscope sensors mounted on the motorcycle. Experiments were performed on different scenarios from naturalistic to extreme (near fall and fall scenarios) riding situations. In the latter case, the riding scenarios were replayed by a stuntman. The results show the ability of the proposed methodology to analyze and understand the motorcycle fall behavior as well as to detect the fall with enough time to inflate an airbag jacket.