Robust Human Activity and Sensor Location Corecognition via Sparse Signal Representation

Performance Analysis of Electromyogram Signal Compression Sampling in a Wireless Body Area Network

The rapid growth in demand for portable and intelligent hardware has caused tremendous pressure on signal sampling, transfer, and storage resources. As an emerging signal acquisition technology, compressed sensing (CS) has promising application prospects in low-cost wireless sensor networks. To achieve reduced energy consumption and maintain a longer acquisition duration for high sample rate electromyogram (EMG) signals, this paper comprehensively analyzes the compressed sensing method using EMG. A fair comparison is carried out on the performances of 52 ordinary wavelet sparse bases and five widely applied reconstruction algorithms at different compression levels. The experimental results show that the db2 wavelet basis can sparse EMG signals so that the compressed EMG signals are reconstructed properly, thanks to its low percentage root mean square distortion (PRD) values at most compression ratios. In addition, the basis pursuit (BP) reconstruction algorithm can provide a more efficient reconstruction process and better reconstruction performance by comparison. The experiment records and comparative analysis screen out the suitable sparse bases and reconstruction algorithms for EMG signals, acting as prior experiments for further practical applications and also a benchmark for future academic research.

fGAAM: A fast and resizable genetic algorithm with aggressive mutation for feature selection

The paper introduces a modified version of a genetic algorithm with aggressive mutation (GAAM) called fGAAM (fast GAAM) that significantly decreases the time needed to find feature subsets of a satisfactory classification accuracy. To demonstrate the time gains provided by fGAAM both algorithms were tested on eight datasets containing different number of features, classes, and examples. The fGAAM was also compared with four reference methods: the Holland GA with and without penalty term, Culling GA, and NSGA II. Results: (i) The fGAAM processing time was about 35% shorter than that of the original GAAM. (ii) The fGAAM was also 20 times quicker than two Holland GAs and 50 times quicker than NSGA II. (iii) For datasets of different number of features, classes, and examples, another number of individuals, stored for further processing, provided the highest acceleration. On average, the best results were obtained when individuals from the last 10 populations were stored (time acceleration: 36.39%) or when the number of individuals to be stored was calculated by the algorithm itself (time acceleration: 35.74%). (iv) The fGAAM was able to process all datasets used in the study, even those that, because of their high number of features, could not be processed by the two Holland GAs and NSGA II.

IMU-to-Segment Assignment and Orientation Alignment for the Lower Body Using Deep Learning

Human body motion analysis based on wearable inertial measurement units (IMUs) receives a lot of attention from both the research community and the and industrial community. This is due to the significant role in, for instance, mobile health systems, sports and human computer interaction. In sensor based activity recognition, one of the major issues for obtaining reliable results is the sensor placement/assignment on the body. For inertial motion capture (joint kinematics estimation) and analysis, the IMU-to-segment (I2S) assignment and alignment are central issues to obtain biomechanical joint angles. Existing approaches for I2S assignment usually rely on hand crafted features and shallow classification approaches (e.g., support vector machines), with no agreement regarding the most suitable features for the assignment task. Moreover, estimating the complete orientation alignment of an IMU relative to the segment it is attached to using a machine learning approach has not been shown in literature so far. This is likely due to the high amount of training data that have to be recorded to suitably represent possible IMU alignment variations. In this work, we propose online approaches for solving the assignment and alignment tasks for an arbitrary amount of IMUs with respect to a biomechanical lower body model using a deep learning architecture and windows of 128 gyroscope and accelerometer data samples. For this, we combine convolutional neural networks (CNNs) for local filter learning with long-short-term memory (LSTM) recurrent networks as well as generalized recurrent units (GRUs) for learning time dynamic features. The assignment task is casted as a classification problem, while the alignment task is casted as a regression problem. In this framework, we demonstrate the feasibility of augmenting a limited amount of real IMU training data with simulated alignment variations and IMU data for improving the recognition/estimation accuracies. With the proposed approaches and final models we achieved 98.57% average accuracy over all segments for the I2S assignment task (100% when excluding left/right switches) and an average median angle error over all segments and axes of 2.91° for the I2S alignment task.

Human Actions Analysis: Templates Generation, Matching and Visualization Applied to Motion Capture of Highly-Skilled Karate Athletes

The aim of this paper is to propose and evaluate the novel method of template generation, matching, comparing and visualization applied to motion capture (kinematic) analysis. To evaluate our approach, we have used motion capture recordings (MoCap) of two highly-skilled black belt karate athletes consisting of 560 recordings of various karate techniques acquired with wearable sensors. We have evaluated the quality of generated templates; we have validated the matching algorithm that calculates similarities and differences between various MoCap data; and we have examined visualizations of important differences and similarities between MoCap data. We have concluded that our algorithms works the best when we are dealing with relatively short (2–4 s) actions that might be averaged and aligned with the dynamic time warping framework. In practice, the methodology is designed to optimize the performance of some full body techniques performed in various sport disciplines, for example combat sports and martial arts. We can also use this approach to generate templates or to compare the correct performance of techniques between various top sportsmen in order to generate a knowledge base of reference MoCap videos. The motion template generated by our method can be used for action recognition purposes. We have used the DTW classifier with angle-based features to classify various karate kicks. We have performed leave-one-out action recognition for the Shorin-ryu and Oyama karate master separately. In this case, 100% actions were correctly classified. In another experiment, we used templates generated from Oyama master recordings to classify Shorin-ryu master recordings and vice versa. In this experiment, the overall recognition rate was 94.2%, which is a very good result for this type of complex action.

Micromagnetometer calibration for accurate orientation estimation

Micromagnetometers, together with inertial sensors, are widely used for attitude estimation for a wide variety of applications. However, appropriate sensor calibration, which is essential to the accuracy of attitude reconstruction, must be performed in advance. Thus far, many different magnetometer calibration methods have been proposed to compensate for errors such as scale, offset, and nonorthogonality. They have also been used for obviate magnetic errors due to soft and hard iron. However, in order to combine the magnetometer with inertial sensor for attitude reconstruction, alignment difference between the magnetometer and the axes of the inertial sensor must be determined as well. This paper proposes a practical means of sensor error correction by simultaneous consideration of sensor errors, magnetic errors, and alignment difference. We take the summation of the offset and hard iron error as the combined bias and then amalgamate the alignment difference and all the other errors as a transformation matrix. A two-step approach is presented to determine the combined bias and transformation matrix separately. In the first step, the combined bias is determined by finding an optimal ellipsoid that can best fit the sensor readings. In the second step, the intrinsic relationships of the raw sensor readings are explored to estimate the transformation matrix as a homogeneous linear least-squares problem. Singular value decomposition is then applied to estimate both the transformation matrix and magnetic vector. The proposed method is then applied to calibrate our sensor node. Although there is no ground truth for the combined bias and transformation matrix for our node, the consistency of calibration results among different trials and less than 3(°) root mean square error for orientation estimation have been achieved, which illustrates the effectiveness of the proposed sensor calibration method for practical applications.

Designing a robust activity recognition framework for health and exergaming using wearable sensors

Detecting human activity independent of intensity is essential in many applications, primarily in calculating metabolic equivalent rates and extracting human context awareness. Many classifiers that train on an activity at a subset of intensity levels fail to recognize the same activity at other intensity levels. This demonstrates weakness in the underlying classification method. Training a classifier for an activity at every intensity level is also not practical. In this paper, we tackle a novel intensity-independent activity recognition problem where the class labels exhibit large variability, the data are of high dimensionality, and clustering algorithms are necessary. We propose a new robust stochastic approximation framework for enhanced classification of such data. Experiments are reported using two clustering techniques, K-Means and Gaussian Mixture Models. The stochastic approximation algorithm consistently outperforms other well-known classification schemes which validate the use of our proposed clustered data representation. We verify the motivation of our framework in two applications that benefit from intensity-independent activity recognition. The first application shows how our framework can be used to enhance energy expenditure calculations. The second application is a novel exergaming environment aimed at using games to reward physical activity performed throughout the day, to encourage a healthy lifestyle.