mTeeth

2021 ◽  
Vol 5 (2) ◽  
pp. 1-25
Author(s):  
Sayma Akther ◽  
Nazir Saleheen ◽  
Mithun Saha ◽  
Vivek Shetty ◽  
Santosh Kumar
Keyword(s):  
Machine Learning ◽  
Natural Environment ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Living Environment ◽  
Sensor Data ◽  
Oral Diseases ◽  
Free Living ◽  
Manual Toothbrush ◽  
The Impact

Ensuring that all the teeth surfaces are adequately covered during daily brushing can reduce the risk of several oral diseases. In this paper, we propose the mTeeth model to detect teeth surfaces being brushed with a manual toothbrush in the natural free-living environment using wrist-worn inertial sensors. To unambiguously label sensor data corresponding to different surfaces and capture all transitions that last only milliseconds, we present a lightweight method to detect the micro-event of brushing strokes that cleanly demarcates transitions among brushing surfaces. Using features extracted from brushing strokes, we propose a Bayesian Ensemble method that leverages the natural hierarchy among teeth surfaces and patterns of transition among them. For training and testing, we enrich a publicly-available wrist-worn inertial sensor dataset collected from the natural environment with time-synchronized precise labels of brushing surface timings and moments of transition. We annotate 10,230 instances of brushing on different surfaces from 114 episodes and evaluate the impact of wide between-person and within-person between-episode variability on machine learning model's performance for brushing surface detection.

scholarly journals Classical Machine Learning versus Deep Learning for the Older Adults Free-Living Activity Classification

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4669
Author(s):  
Muhammad Awais ◽  
Lorenzo Chiari ◽  
Espen A. F. Ihlen ◽  
Jorunn L. Helbostad ◽  
Luca Palmerini
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Deep Learning ◽  
Elderly Population ◽  
Inertial Sensor ◽  
Living Environment ◽  
Frame Rate ◽  
Sensor Data ◽  
Support Vector ◽  
Free Living

Physical activity has a strong influence on mental and physical health and is essential in healthy ageing and wellbeing for the ever-growing elderly population. Wearable sensors can provide a reliable and economical measure of activities of daily living (ADLs) by capturing movements through, e.g., accelerometers and gyroscopes. This study explores the potential of using classical machine learning and deep learning approaches to classify the most common ADLs: walking, sitting, standing, and lying. We validate the results on the ADAPT dataset, the most detailed dataset to date of inertial sensor data, synchronised with high frame-rate video labelled data recorded in a free-living environment from older adults living independently. The findings suggest that both approaches can accurately classify ADLs, showing high potential in profiling ADL patterns of the elderly population in free-living conditions. In particular, both long short-term memory (LSTM) networks and Support Vector Machines combined with ReliefF feature selection performed equally well, achieving around 97% F-score in profiling ADLs.

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 Using Machine Learning and Wearable Inertial Sensor Data for the Classification of Fractal Gait Patterns in Women and Men During Load Carriage

2021 ◽  
Vol 185 ◽  
pp. 282-291
Author(s):  
Nizam U. Ahamed ◽  
Kellen T. Krajewski ◽  
Camille C. Johnson ◽  
Adam J. Sterczala ◽  
Julie P. Greeves ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inertial Sensor ◽  
Load Carriage ◽  
Sensor Data ◽  
Gait Patterns

scholarly journals Re-Enactment as a Method to Reproduce Real-World Fall Events Using Inertial Sensor Data: Development and Usability Study

10.2196/13961 ◽  
2020 ◽  
Vol 22 (4) ◽  
pp. e13961
Author(s):  
Kim Sarah Sczuka ◽  
Lars Schwickert ◽  
Clemens Becker ◽  
Jochen Klenk
Keyword(s):  
Real World ◽  
Independent Living ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Center Of Mass ◽  
Fall Detection ◽  
Video Data ◽  
Sensor Data ◽  
Movement Behavior ◽  
The Real

Background Falls are a common health problem, which in the worst cases can lead to death. To develop reliable fall detection algorithms as well as suitable prevention interventions, it is important to understand circumstances and characteristics of real-world fall events. Although falls are common, they are seldom observed, and reports are often biased. Wearable inertial sensors provide an objective approach to capture real-world fall signals. However, it is difficult to directly derive visualization and interpretation of body movements from the fall signals, and corresponding video data is rarely available. Objective The re-enactment method uses available information from inertial sensors to simulate fall events, replicate the data, validate the simulation, and thereby enable a more precise description of the fall event. The aim of this paper is to describe this method and demonstrate the validity of the re-enactment approach. Methods Real-world fall data, measured by inertial sensors attached to the lower back, were selected from the Fall Repository for the Design of Smart and Self-Adaptive Environments Prolonging Independent Living (FARSEEING) database. We focused on well-described fall events such as stumbling to be re-enacted under safe conditions in a laboratory setting. For the purposes of exemplification, we selected the acceleration signal of one fall event to establish a detailed simulation protocol based on identified postures and trunk movement sequences. The subsequent re-enactment experiments were recorded with comparable inertial sensor configurations as well as synchronized video cameras to analyze the movement behavior in detail. The re-enacted sensor signals were then compared with the real-world signals to adapt the protocol and repeat the re-enactment method if necessary. The similarity between the simulated and the real-world fall signals was analyzed with a dynamic time warping algorithm, which enables the comparison of two temporal sequences varying in speed and timing. Results A fall example from the FARSEEING database was used to show the feasibility of producing a similar sensor signal with the re-enactment method. Although fall events were heterogeneous concerning chronological sequence and curve progression, it was possible to reproduce a good approximation of the motion of a person’s center of mass during fall events based on the available sensor information. Conclusions Re-enactment is a promising method to understand and visualize the biomechanics of inertial sensor-recorded real-world falls when performed in a suitable setup, especially if video data is not available.

scholarly journals Practical Considerations for Accuracy Evaluation in Sensor-Based Machine Learning and Deep Learning

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3491 ◽  
Author(s):  
Issam Hammad ◽  
Kamal El-Sankary
Keyword(s):  
Machine Learning ◽  
Thermal Noise ◽  
Error Resilience ◽  
Sensor Data ◽  
Accuracy Evaluation ◽  
Sensor Failure ◽  
Learning Models ◽  
Analog To Digital ◽  
The Impact ◽  
Machine Learning Models

Accuracy evaluation in machine learning is based on the split of data into a training set and a test set. This critical step is applied to develop machine learning models including models based on sensor data. For sensor-based problems, comparing the accuracy of machine learning models using the train/test split provides only a baseline comparison in ideal situations. Such comparisons won’t consider practical production problems that can impact the inference accuracy such as the sensors’ thermal noise, performance with lower inference quantization, and tolerance to sensor failure. Therefore, this paper proposes a set of practical tests that can be applied when comparing the accuracy of machine learning models for sensor-based problems. First, the impact of the sensors’ thermal noise on the models’ inference accuracy was simulated. Machine learning algorithms have different levels of error resilience to thermal noise, as will be presented. Second, the models’ accuracy using lower inference quantization was compared. Lowering inference quantization leads to lowering the analog-to-digital converter (ADC) resolution which is cost-effective in embedded designs. Moreover, in custom designs, analog-to-digital converters’ (ADCs) effective number of bits (ENOB) is usually lower than the ideal number of bits due to various design factors. Therefore, it is practical to compare models’ accuracy using lower inference quantization. Third, the models’ accuracy tolerance to sensor failure was evaluated and compared. For this study, University of California Irvine (UCI) ‘Daily and Sports Activities’ dataset was used to present these practical tests and their impact on model selection.

scholarly journals An Evaluation of Wearable Inertial Sensor Configuration and Supervised Machine Learning Models for Automatic Punch Classification in Boxing

IoT ◽  
2020 ◽  
Vol 1 (2) ◽  
pp. 360-381
Author(s):  
Matthew T. O. Worsey ◽  
Hugo G. Espinosa ◽  
Jonathan B. Shepherd ◽  
David V. Thiel
Keyword(s):  
Machine Learning ◽  
Prediction Accuracy ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Supervised Machine Learning ◽  
Learning Models ◽  
Significant Statistical Difference ◽  
Sensor Configuration ◽  
Wearable Inertial Sensors ◽  
Machine Learning Models

Machine learning is a powerful tool for data classification and has been used to classify movement data recorded by wearable inertial sensors in general living and sports. Inertial sensors can provide valuable biofeedback in combat sports such as boxing; however, the use of such technology has not had a global uptake. If simple inertial sensor configurations can be used to automatically classify strike type, then cumbersome tasks such as video labelling can be bypassed and the foundation for automated workload monitoring of combat sport athletes is set. This investigation evaluates the classification performance of six different supervised machine learning models (tuned and untuned) when using two simple inertial sensor configurations (configuration 1—inertial sensor worn on both wrists; configuration 2—inertial sensor worn on both wrists and third thoracic vertebrae [T3]). When trained on one athlete, strike prediction accuracy was good using both configurations (sensor configuration 1 mean overall accuracy: 0.90 ± 0.12; sensor configuration 2 mean overall accuracy: 0.87 ± 0.09). There was no significant statistical difference in prediction accuracy between both configurations and tuned and untuned models (p > 0.05). Moreover, there was no significant statistical difference in computational training time for tuned and untuned models (p > 0.05). For sensor configuration 1, a support vector machine (SVM) model with a Gaussian rbf kernel performed the best (accuracy = 0.96), for sensor configuration 2, a multi-layered perceptron neural network (MLP-NN) model performed the best (accuracy = 0.98). Wearable inertial sensors can be used to accurately classify strike-type in boxing pad work, this means that cumbersome tasks such as video and notational analysis can be bypassed. Additionally, automated workload and performance monitoring of athletes throughout training camp is possible. Future investigations will evaluate the performance of this algorithm on a greater sample size and test the influence of impact window-size on prediction accuracy. Additionally, supervised machine learning models should be trained on data collected during sparring to see if high accuracy holds in a competition setting. This can help move closer towards automatic scoring in boxing.

scholarly journals Fusing Object Information and Inertial Data for Activity Recognition

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4119 ◽  
Author(s):  
Alexander Diete ◽  
Heiner Stuckenschmidt
Keyword(s):  
Activity Recognition ◽  
Pervasive Computing ◽  
Human Activities ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Arm Movement ◽  
Sensor Data ◽  
Object A ◽  
Camera View ◽  
Different Types

In the field of pervasive computing, wearable devices have been widely used for recognizing human activities. One important area in this research is the recognition of activities of daily living where especially inertial sensors and interaction sensors (like RFID tags with scanners) are popular choices as data sources. Using interaction sensors, however, has one drawback: they may not differentiate between proper interaction and simple touching of an object. A positive signal from an interaction sensor is not necessarily caused by a performed activity e.g., when an object is only touched but no interaction occurred afterwards. There are, however, many scenarios like medicine intake that rely heavily on correctly recognized activities. In our work, we aim to address this limitation and present a multimodal egocentric-based activity recognition approach. Our solution relies on object detection that recognizes activity-critical objects in a frame. As it is infeasible to always expect a high quality camera view, we enrich the vision features with inertial sensor data that monitors the users’ arm movement. This way we try to overcome the drawbacks of each respective sensor. We present our results of combining inertial and video features to recognize human activities on different types of scenarios where we achieve an F 1 -measure of up to 79.6%.

Methods for Improving Foot Displacement Measurements Calculated from Inertial Sensors

2011 ◽  
pp. 93-116 ◽  
Author(s):  
Edgar Charry ◽  
Daniel T.H. Lai
Keyword(s):  
Measurement System ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Human Movement ◽  
Sensor Data ◽  
Band Pass Filter ◽  
Pass Filter ◽  
Band Pass ◽  
Sensor Errors ◽  
Displacement Measurements

The use of inertial sensors to measure human movement has recently gained momentum with the advent of low cost micro-electro-mechanical systems (MEMS) technology. These sensors comprise accelerometer and gyroscopes which measure accelerations and angular velocities respectively. Secondary quantities such as displacement can be obtained by integration of these quantities, a method which presents challenging issues due to the problem of accumulative sensor errors. This chapter investigates the spectral evaluation of individual sensor errors and looks at the effectiveness of minimizing these errors using static digital filters. The primary focus is on the derivation of foot displacement data from inertial sensor measurements. The importance of foot, in particular toe displacement measurements is evident in the context of tripping and falling which are serious health concerns for the elderly. The Minimum Toe Clearance (MTC) as an important gait variable for falls-risk prediction and assessment, and therefore the measurement variable of interest. A brief sketch of the current devices employing accelerometers and gyroscopes is presented, highlighting the problems and difficulties reported in literature to achieve good precision. These have been mainly due to the presence of sensor errors and the error accumulative process employed in obtaining displacement measurements. The investigation first proceeds to identify the location of these sensor errors in the frequency domain using the Fast Fourier Transform (FFT) on raw inertial sensor data. The frequency content of velocity and displacement measurements obtained from integrating the inertial data using a well known strap-down method is then explored. These investigations revealed that large sensor errors occurred mainly in the low frequency spectrum while white noise exists in all frequency spectra. The efficacy of employing a band-pass filter to remove a large portion of these errors and their effect on the derived displacements is elaborated on. The cross-correlation of the FFT power spectra from a highly accurate optical measurement system and processed sensor data is used as a metric to evaluate the performance of the band-pass filter at several stages of the processing stage. The motivation is that a more fundamental method would require less computational demand and could lead to more efficient implementations in low-power and systems with limited resources, so that portable sensor based motion measurement system would provide a good degree of measurement accuracy.

Human Motion Capture with Sparse Inertial Sensors and Video

2020 ◽  
Author(s):  
Timo von Marcard
Keyword(s):  
Global Optimization ◽  
Optimization Problem ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Hybrid Approach ◽  
Human Motion ◽  
The Body ◽  
Sensor Data ◽  
Discrete Optimization Problem ◽  
Global Optimization Problem

This thesis explores approaches to capture human motions with a small number of sensors. In the first part of this thesis an approach is presented that reconstructs the body pose from only six inertial sensors. Instead of relying on pre-recorded motion databases, a global optimization problem is solved to maximize the consistency of measurements and model over an entire recording sequence. The second part of this thesis deals with a hybrid approach to fuse visual information from a single hand-held camera with inertial sensor data. First, a discrete optimization problem is solved to automatically associate people detections in the video with inertial sensor data. Then, a global optimization problem is formulated to combine visual and inertial information. The propose  approach enables capturing of multiple interacting people and works even if many more people are visible in the camera image. In addition, systematic inertial sensor errors can be compensated, leading to a substantial in...

Sign in / Sign up

Export Citation Format

Share Document