scholarly journals What Lies Beneath One’s Feet? Terrain Classification Using Inertial Data of Human Walk

2019 ◽  
Vol 9 (15) ◽  
pp. 3099 ◽  
Author(s):  
Muhammad Zeeshan Ul Hasnain Hashmi ◽  
Qaiser Riaz ◽  
Mehdi Hussain ◽  
Muhammad Shahzad
Keyword(s):  
Inertial Sensors ◽  
Support Vector ◽  
Gait Patterns ◽  
Lower Back ◽  
Segmentation Approach ◽  
Angular Velocities ◽  
Measurement Units ◽  
Normal Human ◽  
Recorded Data ◽  
Validation Strategy

The objective of this study was to investigate if the inertial data collected from normal human walk can be used to reveal the underlying terrain types. For this purpose, we recorded the gait patterns of normal human walk on six different terrain types with variation in hardness and friction using body mounted inertial sensors. We collected accelerations and angular velocities of 40 healthy subjects with two smartphones embedded inertial measurement units (MPU-6500) attached at two different body locations (chest and lower back). The recorded data were segmented with stride based segmentation approach and 194 tempo-spectral features were computed for each stride. We trained two machine learning classifiers, namely random forest and support vector machine, and cross validated the results with 10-fold cross-validation strategy. The classification tasks were performed on indoor–outdoor terrains, hard–soft terrains, and a combination of binary, ternary, quaternary, quinary and senary terrains. From the experimental results, the classification accuracies of 97% and 92% were achieved for indoor–outdoor and hard–soft terrains, respectively. The classification results for binary, ternary, quaternary, quinary and senary class classification were 96%, 94%, 92%, 90%, and 89%, respectively. These results demonstrate that the stride data collected with the low-level signals of a single IMU can be used to train classifiers and predict terrain types with high accuracy. Moreover, the problem at hand can be solved invariant of sensor type and sensor location.

scholarly journals Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1461 ◽  
Author(s):  
Juri Taborri ◽  
Eduardo Palermo ◽  
Stefano Rossi
Keyword(s):  
Machine Learning ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Learning Algorithms ◽  
Automatic Detection ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Support Vector ◽  
Angular Velocities ◽  
Race Walking

The validity of results in race walking is often questioned due to subjective decisions in the detection of faults. This study aims to compare machine-learning algorithms fed with data gathered from inertial sensors placed on lower-limb segments to define the best-performing classifiers for the automatic detection of illegal steps. Eight race walkers were enrolled and linear accelerations and angular velocities related to pelvis, thighs, shanks, and feet were acquired by seven inertial sensors. The experimental protocol consisted of two repetitions of three laps of 250 m, one performed with regular race walking, one with loss-of-contact faults, and one with knee-bent faults. The performance of 108 classifiers was evaluated in terms of accuracy, recall, precision, F1-score, and goodness index. Generally, linear accelerations revealed themselves as more characteristic with respect to the angular velocities. Among classifiers, those based on the support vector machine (SVM) were the most accurate. In particular, the quadratic SVM fed with shank linear accelerations was the best-performing classifier, with an F1-score and a goodness index equal to 0.89 and 0.11, respectively. The results open the possibility of using a wearable device for automatic detection of faults in race walking competition.

scholarly journals Can Trunk Acceleration Differentiate Stroke Patient Gait Patterns Using Time- and Frequency-Domain Features?

2021 ◽  
Vol 11 (4) ◽  
pp. 1541
Author(s):  
Wei-Chun Hsu ◽  
Tommy Sugiarto ◽  
Ying-Yi Liao ◽  
Yi-Jia Lin ◽  
Fu-Chi Yang ◽  
...  
Keyword(s):  
Frequency Domain ◽  
Signal To Noise Ratio ◽  
Feature Selection Method ◽  
Measurement Unit ◽  
Support Vector ◽  
Gait Patterns ◽  
Lower Back ◽  
Trunk Acceleration ◽  
Stroke Group ◽  
Single Sensor

This study classified the gait patterns of normal and stroke participants by using time- and frequency-domain features obtained from data provided by an inertial measurement unit sensor placed on the subject’s lower back (L5). Twenty-three participants were included and divided into two groups: healthy group (young and older adults) and stroke group. Time- and frequency-domain features from an accelerometer were extracted, and a feature selection method comprising statistical analysis and signal-to-noise ratio (SNR) calculation was used to reduce the number of features. The features were then used to train four Support Vector Machine (SVM) kernels, and the results were subsequently compared. The quadratic SVM kernel had the highest accuracy (93.46%), as evaluated through cross-validation. Moreover, when different datasets were used on model testing, both the quadratic and cubic kernels showed the highest accuracy (96.55%). These results demonstrated the effectiveness of this study’s classification method in distinguishing between normal and stroke gait patterns, with only using a single sensor placed on the L5.

scholarly journals Ablation Analysis to Select Wearable Sensors for Classifying Standing, Walking, and Running

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 194
Author(s):  
Sarah Gonzalez ◽  
Paul Stegall ◽  
Harvey Edwards ◽  
Leia Stirling ◽  
Ho Chit Siu
Keyword(s):  
Activity Recognition ◽  
Principal Components ◽  
Classification Accuracy ◽  
Wearable Sensors ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Techniques ◽  
Measurement Units ◽  
The Difference

The field of human activity recognition (HAR) often utilizes wearable sensors and machine learning techniques in order to identify the actions of the subject. This paper considers the activity recognition of walking and running while using a support vector machine (SVM) that was trained on principal components derived from wearable sensor data. An ablation analysis is performed in order to select the subset of sensors that yield the highest classification accuracy. The paper also compares principal components across trials to inform the similarity of the trials. Five subjects were instructed to perform standing, walking, running, and sprinting on a self-paced treadmill, and the data were recorded while using surface electromyography sensors (sEMGs), inertial measurement units (IMUs), and force plates. When all of the sensors were included, the SVM had over 90% classification accuracy using only the first three principal components of the data with the classes of stand, walk, and run/sprint (combined run and sprint class). It was found that sensors that were placed only on the lower leg produce higher accuracies than sensors placed on the upper leg. There was a small decrease in accuracy when the force plates are ablated, but the difference may not be operationally relevant. Using only accelerometers without sEMGs was shown to decrease the accuracy of the SVM.

Systematic Calibration Method for FOG Inertial Measurement Units

2013 ◽  
Vol 662 ◽  
pp. 717-720 ◽  
Author(s):  
Zhen Yu Zheng ◽  
Yan Bin Gao ◽  
Kun Peng He
Keyword(s):  
Inertial Measurement Unit ◽  
Inertial Sensors ◽  
Calibration Method ◽  
State Equation ◽  
Measurement Unit ◽  
Observation System ◽  
Body Frame ◽  
Inertial Measurement ◽  
Measurement Units ◽  
Error Coefficients

As an inertial sensors assembly, the FOG inertial measurement unit (FIMU) must be calibrated before being used. The paper presents a one-time systematic IMU calibration method only using two-axis low precision turntable. First, the detail error model of inertial sensors using defined body frame is established. Then, only velocity taken as observation, system 33 state equation is established including the lever arm effects and nonlinear terms of scale factor error. The turntable experiments verify that the method can identify all the error coefficients of FIMU on low-precision two-axis turntable, after calibration the accuracy of navigation is improved.

Abnormalities Detection of IMU Based on PCA in Motion Monitoring

2012 ◽  
Vol 224 ◽  
pp. 533-538 ◽  
Author(s):  
Jing Zhou ◽  
Steven Su ◽  
Ai Huang Guo ◽  
Wei Dong Chen
Keyword(s):  
Measurement Method ◽  
Degrees Of Freedom ◽  
Inertial Sensors ◽  
Principal Component ◽  
Body Sensor Networks ◽  
Remote Measurement ◽  
Micro Electro Mechanical Systems ◽  
Inertial Measurement ◽  
Multiple Degrees Of Freedom ◽  
Measurement Units

Inertial measurement units (IMU) are used as an affordable and effective remote measurement method for health monitoring in body sensor networks (BSNs) based on tracking people’s daily motions and activities. These inertial sensors are mostly micro-electro-mechanical systems with a combination of multi-axis combinations of precision gyroscopes, accelerometers, and magnetometers to sense multiple degrees of freedom (DoF).Unfortunately in the process of motion monitoring actual sensor outputs may contain some abnormalities, which might result in the misinterpretations of activities. In this paper, we use Principal component analysis (PCA) combined with Hotelling’s T2 and SPE statistic to detect abnormal data in the process of motion monitoring with IMU to ensure the reliability and accuracy in application. The simulated results prove this method is effective and feasible.

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

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4132 ◽  
Author(s):  
Ku Ku Abd. Rahim ◽  
I. Elamvazuthi ◽  
Lila Izhar ◽  
Genci Capi
Keyword(s):  
Activity Recognition ◽  
Inertial Sensors ◽  
Wearable Sensors ◽  
Ensemble Methods ◽  
Daily Activities ◽  
Support Vector ◽  
Random Subspace ◽  
Ensemble Classifiers ◽  
Accuracy Rate

Increasing interest in analyzing human gait using various wearable sensors, which is known as Human Activity Recognition (HAR), can be found in recent research. Sensors such as accelerometers and gyroscopes are widely used in HAR. Recently, high interest has been shown in the use of wearable sensors in numerous applications such as rehabilitation, computer games, animation, filmmaking, and biomechanics. In this paper, classification of human daily activities using Ensemble Methods based on data acquired from smartphone inertial sensors involving about 30 subjects with six different activities is discussed. The six daily activities are walking, walking upstairs, walking downstairs, sitting, standing and lying. It involved three stages of activity recognition; namely, data signal processing (filtering and segmentation), feature extraction and classification. Five types of ensemble classifiers utilized are Bagging, Adaboost, Rotation forest, Ensembles of nested dichotomies (END) and Random subspace. These ensemble classifiers employed Support vector machine (SVM) and Random forest (RF) as the base learners of the ensemble classifiers. The data classification is evaluated with the holdout and 10-fold cross-validation evaluation methods. The performance of each human daily activity was measured in terms of precision, recall, F-measure, and receiver operating characteristic (ROC) curve. In addition, the performance is also measured based on the comparison of overall accuracy rate of classification between different ensemble classifiers and base learners. It was observed that overall, SVM produced better accuracy rate with 99.22% compared to RF with 97.91% based on a random subspace ensemble classifier.

scholarly journals A correction in feedback loop applied to two-axis gimbal stabilization

2015 ◽  
Vol 63 (1) ◽  
pp. 217-219
Author(s):  
C. Zych ◽  
A. Wrońska-Zych ◽  
J. Dudczyk ◽  
A. Kawalec
Keyword(s):  
Working Conditions ◽  
Input Signal ◽  
Pid Controller ◽  
Feedback Loop ◽  
Measurement Unit ◽  
Observation System ◽  
Proportional Integral Derivative ◽  
Earned Value ◽  
Angular Velocities ◽  
Measurement Units

Abstract A two-axis gimbal system can be used for stabilizing platform equipped with observation system like cameras or different measurement units. The most important advantageous of using a gimbal stabilization is a possibility to provide not disturbed information or data from a measurement unit. This disturbance can proceed from external working conditions. The described stabilization algorithm of a gimbal system bases on a regulator with a feedback loop. Steering parameters are calculated from quaternion transformation angular velocities received from gyroscopes. This data are fed into the input of Proportional Integral Derivative (PID) controller. Their input signal is compared with earned value in the feedback loop. The paper presents the way of increasing the position’s accuracy by getting it in the feedback loop. The data fusion from a positioning sensor and a gyroscope results in much better accuracy of stabilization.

Gyroscope-Free Link Parameter Measurement Using Accelerometers and Magnetometer

2014 ◽  
Author(s):  
Vishesh Vikas ◽  
Carl D. Crane
Keyword(s):  
Angular Velocity ◽  
Joint Angle ◽  
Inertial Sensors ◽  
Angular Acceleration ◽  
Parameter Measurement ◽  
Joint Angles ◽  
Symmetry Constraint ◽  
Estimation Techniques ◽  
Angular Velocities ◽  
Joint Parameters

Knowledge of joint angles, angular velocities is essential for control of link mechanisms and robots. The estimation of joint angles and angular velocity is performed using combination of inertial sensors (accelerometers and gyroscopes) which are contactless and flexible at point of application. Different estimation techniques are used to fuse data from different inertial sensors. Bio-inspired sensors using symmetrically placed multiple inertial sensors are capable of instantaneously measuring joint parameters (joint angle, angular velocities and angular acceleration) without use of any estimation techniques. Calibration of inertial sensors is easier and more reliable for accelerometers as compared to gyroscopes. The research presents gyroscope-less, multiple accelerometer and magnetometer based sensors capable of measuring (not estimating) joint parameters. The contribution of the improved sensor are four-fold. Firstly, the inertial sensors are devoid of symmetry constraint unlike the previously researched bio-inspired sensors. However, the accelerometer are non-coplanarly placed. Secondly, the accelerometer-magnetometer combination sensor allows for calculation of a unique rotation matrix between two link joined by any kind of joint. Thirdly, the sensors are easier to calibrate as they consist only of accelerometers. Finally, the sensors allow for calculation of angular velocity and angular acceleration without use of gyroscopes.

Sign in / Sign up

Export Citation Format

Share Document