Tri-axial Acceleration Signals Research Articles

Quantitative detection of sleep apnea in adults using inertial measurement unit embedded in wristwatch wearable devices.

Sleep apnea (SA) is associated with risk of cardiovascular disease, cognitive decline, and accidents due to sleepiness, yet the majority (over 80%) of patients remain undiagnosed. Inertial measurement units (IMUs) are built into modern wearable devices and are capable of long-term continuous measurement with low power consumption. We examined if SA can be detected by an IMU embedded in a wristwatch device. In 122 adults who underwent polysomnography (PSG) examinations, triaxial acceleration and triaxial gyro signals from the IMU were recorded during the PSG. Subjects were divided into a training group and a test groups (both n = 61). In the training group, an algorithm was developed to extract signals in the respiratory frequency band (0.13-0.70Hz) and detect respiratory events as transient (10-90s) decreases in amplitude. The respiratory event frequency estimated by the algorithm correlated with the apnea-hypopnea index (AHI) of the PSG with r = 0.84 in the test group. With the cutoff values determined in the training group, moderate-to-severe SA (AHI ≥ 15) was identified with 85% accuracy and severe SA (AHI ≥ 30) with 89% accuracy in the test group. SA can be quantitatively detected by the IMU embedded in wristwatch wearable devices in adults with suspected SA.

General spectral characteristics of human activity and its inherent scale-free fluctuations

The scale-free nature of daily human activity has been observed in different aspects; however, the description of its spectral characteristics is incomplete. General findings are complicated by the fact that—although actigraphy is commonly used in many research areas—the activity calculation methods are not standardized; therefore, activity signals can be different. The presence of 1/f noise in activity or acceleration signals was mostly analysed for short time windows, and the complete spectral characteristic has only been examined in the case of certain types of them. To explore the general spectral nature of human activity in greater detail, we have performed Power Spectral Density (PSD) based examination and Detrended Fluctuation Analysis (DFA) on several-day-long, triaxial actigraphic acceleration signals of 42 healthy, free-living individuals. We generated different types of activity signals from these, using different acceleration preprocessing techniques and activity metrics. We revealed that the spectra of different types of activity signals generally follow a universal characteristic including 1/f noise over frequencies above the circadian rhythmicity. Moreover, we discovered that the PSD of the raw acceleration signal has the same characteristic. Our findings prove that the spectral scale-free nature is generally inherent to the motor activity of healthy, free-living humans, and is not limited to any particular activity calculation method.

Daily Posture Behavior Patterns Derived From Multitime-Scale Topic Models Using Wearable Triaxial Acceleration for Assessment of Concern About Falling.

Concern about falling is prevalent in older population. This condition would cause a series of adverse physical and psychological consequences for older adults' health. Traditional assessment of concern about falling is relied on self-reported questionnaires and thus is too subjective. Therefore, we proposed a novel multi-time-scale topic modelling approach to quantitatively evaluate concern about falling by analyzing triaxial acceleration signals collected from a wearable pendent sensor. Different posture segments were firstly recognized to extract their corresponding feature subsets. Then, each selected feature related to concern about falling was clustered into discrete levels as feature letters of artificial words in different time scales. As a result, all older participants' signal recordings were converted to a collection of artificial documents, which can be processed by natural language processing methodologies. The topic modelling technique was used to discover daily posture behavior patterns from these documents as discriminants between older adults with different levels of concern about falling. The results indicated that there were significant differences in distributions of posture topics between groups of older adults with different levels of concern about falling. Additionally, the transitions of posture topics over daytime and nighttime revealed temporal regularities of posture behavior patterns of older adult's active and inactive status, which were substantially different for older adults with different levels of concern about falling. Finally, the level of concern about falling was accurately determined with accuracy of 71.2% based on the distributions of posture topics combined with the mobility performance metrics of walking behaviors and demographic information.

Predicting Adverse Events During Six-Minute Walk Test Using Continuous Physiological Signals.

Background and Objective: The 6-min walk test (6MWT) is a common functional assessment test, but adverse events during the test can be potentially dangerous and can lead to serious consequences and low quality of life. This study aimed to predict the occurrence of adverse events during 6MWT, using continuous physiological parameters combined with demographic variables. Methods: 578 patients with respiratory disease who had performed standardized 6MWT with wearable devices from three hospitals were included in this study. Adverse events occurred in 73 patients (12.6%). ECG, respiratory signal, tri-axial acceleration signals, oxygen saturation, demographic variables and scales assessment were obtained. Feature extraction and selection of physiological signals were performed during 2-min resting and 1-min movement phases. 5-fold cross-validation was used to assess the machine learning models. The predictive ability of different models and scales was compared. Results: Of the 16 features selected by the recursive feature elimination method, those related to blood oxygen were the most important and those related to heart rate were the most numerous. Light Gradient Boosting Machine (LightGBM) had the highest AUC of 0.874 ± 0.063 and the AUC of Logistic Regression was AUC of 0.869 ± 0.067. The mMRC (Modified Medical Research Council) scale and Borg scale had the lowest performance, with an AUC of 0.733 and 0.656 respectively. Conclusion: It is feasible to predict the occurrence of adverse event during 6MWT using continuous physiological parameters combined with demographic variables. Wearable sensors/systems can be used for continuous physiological monitoring and provide additional tools for patient safety during 6MWT.

A Novel Deep Learning Bi-GRU-I Model for Real-Time Human Activity Recognition Using Inertial Sensors

Wearable sensor based Human Activity Recognition (HAR) has been widely used these years. This paper proposed a novel deep learning model for HAR using inertial sensors. First, a wearable device platform was developed with 6 inertial sensor units to collect triaxial acceleration signals during human movements, and the dataset of Command Actions of Traffic Police (CATP) was acquired. Then, a deep learning model named Bidirectional-Gated Recurrent Unit-Inception (Bi-GRU-I) was designed to improve the accuracy and reduce the amount of parameters. It is consisting of 2 Bi-GRU layers, 3 Inception layers, 1 Global Average Pooling (GAP) layer and 1 softmax layer. Finally, the comparing experiments with other methods were taken on 3 datasets: the self-collected CATP dataset, widely used Wireless Sensor Data Mining (WISDM) and University of California, Irvine (UCI-HAR) dataset. And the proposed method shows better performance and robustness. Moreover, the sensor configuration optimization was analyzed, and it shows that this method can also apply to the task using less sensor units.

A pace recognition method for exoskeleton wearers based on support vector machine-hidden Markov model

In order to improve the motion fluency and coordination of lower extremity exoskeleton robots and wearers, a pace recognition method of exoskeleton wearer is proposed base on inertial sensors. Firstly, the triaxial acceleration and triaxial angular velocity signals at the thigh and calf were collected by inertial sensors. Then the signal segment of 0.5 seconds before the current time was extracted by the time window method. And the Fourier transform coefficients in the frequency domain signal were used as eigenvalues. Then the support vector machine (SVM) and hidden Markov model (HMM) were combined as a classification model, which was trained and tested for pace recognition. Finally, the pace change rule and the human-machine interaction force were combined in this model and the current pace was predicted by the model. The experimental results showed that the pace intention of the lower extremity exoskeleton wearer could be effectively identified by the method proposed in this article. And the recognition rate of the seven pace patterns could reach 92.14%. It provides a new way for the smooth control of the exoskeleton.

Human Posture Detection Method Based on Wearable Devices

The dynamic detection of human motion is important, which is widely applied in the fields of motion state capture and rehabilitation engineering. In this study, based on multimodal information of surface electromyography (sEMG) signals of upper limb and triaxial acceleration and plantar pressure signals of lower limb, the effective virtual driving control and gait recognition methods were proposed. The effective way of wearable human posture detection was also constructed. Firstly, the moving average window and threshold comparison were used to segment the sEMG signals of the upper limb. The standard deviation and singular values of wavelet coefficients were extracted as the features. After the training and classification by optimized support vector machine (SVM) algorithm, the real-time detection and analysis of three virtual driving actions were performed. The average identification accuracy was 90.90%. Secondly, the mean, standard deviation, variance, and wavelet energy spectrum of triaxial acceleration were extracted, and these parameters were combined with plantar pressure as the gait features. The optimized SVM was selected for the gait identification, and the average accuracy was 90.48%. The experimental results showed that, through different combinations of wearable sensors on the upper and lower limbs, the motion posture information could be dynamically detected, which could be used in the design of virtual rehabilitation system and walking auxiliary system.

The OnHW Dataset

This paper presents a handwriting recognition (HWR) system that deals with online character recognition in real-time. Our sensor-enhanced ballpoint pen delivers sensor data streams from triaxial acceleration, gyroscope, magnetometer and force signals at 100 Hz. As most existing datasets do not meet the requirements of online handwriting recognition and as they have been collected using specific equipment under constrained conditions, we propose a novel online handwriting dataset acquired from 119 writers consisting of 31,275 uppercase and lowercase English alphabet character recordings (52 classes) as part of the UbiComp 2020 Time Series Classification Challenge. Our novel OnHW-chars dataset allows for the evaluations of uppercase, lowercase and combined classification tasks, on both writer-dependent (WD) and writer-independent (WI) classes and we show that properly tuned machine learning pipelines as well as deep learning classifiers (such as CNNs, LSTMs, and BiLSTMs) yield accuracies up to 90 % for the WD task and 83 % for the WI task for uppercase characters. Our baseline implementations together with the rich and publicly available OnHW dataset serve as a baseline for future research in that area.

Heart Rate Monitoring using Sparse Spectral Curve Tracing.

Heart rate (HR) monitoring under real-world activities of daily living conditions is challenging, particularly, using peripheral wearable devices integrated with simple optical and acceleration sensors. The study presents a novel technique, named as CurToSS: CURve Tracing On Sparse Spectrum, for continuous HR estimation in daily living activity conditions using simultaneous photoplethysmogram (PPG) and triaxial-acceleration signals. The performance validation of HR estimation using the CurToSS algorithm is conducted in four public databases with distinctive study groups, sensor types, and protocols involving intense physical and emotional exertions. The HR performance of this time-frequency curve tracing method is also compared to that of contemporary algorithms. The results suggest that the CurToSS method offers the best performance with significantly (P<0.01) lowest HR error compared to spectral filtering and multi-channel PPG correlation methods. The current HR performances are also consistently better than a deep learning approach in diverse datasets. The proposed algorithm is powerful for reliable long-term HR monitoring under ambulatory daily life conditions using wearable biosensor devices.

Identifying Sheep Activity from Tri-Axial Acceleration Signals Using a Moving Window Classification Model

Behaviour is a useful indicator of an individual animal’s overall wellbeing. There is widespread agreement that measuring and monitoring individual behaviour autonomously can provide valuable opportunities to trigger and refine on-farm management decisions. Conventionally, this has required visual observation of animals across a set time period. Technological advancements, such as animal-borne accelerometers, are offering 24/7 monitoring capability. Accelerometers have been used in research to quantify animal behaviours for a number of years. Now, technology and software developers, and more recently decision support platform providers, are integrating to offer commercial solutions for the extensive livestock industries. For these systems to function commercially, data must be captured, processed and analysed in sync with data acquisition. Practically, this requires a continuous stream of data or a duty cycled data segment and, from an analytics perspective, the application of moving window algorithms to derive the required classification. The aim of this study was to evaluate the application of a ‘clean state’ moving window behaviour state classification algorithm applied to 3, 5 and 10 second duration segments of data (including behaviour transitions), to categorise data emanating from collar, leg and ear mounted accelerometers on five Merino ewes. The model was successful at categorising grazing, standing, walking and lying behaviour classes with varying sensitivity, and no significant difference in model accuracy was observed between the three moving window lengths. The accuracy in identifying behaviour classes was highest for the ear-mounted sensor (86%–95%), followed by the collar-mounted sensor (67%–88%) and leg-mounted sensor (48%–94%). Between-sheep variations in classification accuracy confirm the sensor orientation is an important source of variation in all deployment modes. This research suggests a moving window classifier is capable of segregating continuous accelerometer signals into exclusive behaviour classes and may provide an appropriate data processing framework for commercial deployments.

Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration Images.

Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which is characterized by inattention, hyperactivity and impulsive behaviors. In particular, children have difficulty keeping still exhibiting increased fine and gross motor activity. This paper focuses on analyzing the data obtained from two tri-axial accelerometers (one on the wrist of the dominant arm and the other on the ankle of the dominant leg) worn during school hours by a group of 22 children (11 children with ADHD and 11 paired controls). Five of the 11 ADHD diagnosed children were not on medication during the study. The children were not explicitly instructed to perform any particular activity but followed a normal session at school alternating classes of little or moderate physical activity with intermediate breaks of more prominent physical activity. The tri-axial acceleration signals were converted into 2D acceleration images and a Convolutional Neural Network (CNN) was trained to recognize the differences between non-medicated ADHD children and their paired controls. The results show that there were statistically significant differences in the way the two groups moved for the wrist accelerometer (t-test p-value <0.05). For the ankle accelerometer statistical significance was only achieved between data from the non-medicated children in the experimental group and the control group. Using a Convolutional Neural Network (CNN) to automatically extract embedded acceleration patterns and provide an objective measure to help in the diagnosis of ADHD, an accuracy of 0.875 for the wrist sensor and an accuracy of 0.9375 for the ankle sensor was achieved.

A Novel Synthetic Simulation Platform for Validation of Breathing Rate Measurement.

Validation of biosensor algorithms is paramount for regulated medical devices applied to patient monitoring. We present validation of breathing rate (BR) measurement using a patch medical device via a novel synthetic simulation platform, in-hospital data collection and controlled laboratory study. Single-lead ECG and triaxial body acceleration signals with variability and noise are synthetically generated and quantized for a constellation according to the input parameters of heart rate (HR) as a fundamental frequency $( f_{c})$ of ECG and reference BR as a modulating frequency $( f_{r})$. Synthetic signals are input to the BR algorithms and the performance of output BRs are evaluated for a region-of-interest of the constellation $( f_{c}/ f_{r}\,\ge 3$ & $f_{c}/ f_{r}\,\le 8)$ accounting the Nyquist and physiological varability. The performances of patch sensor's BR are also evaluated in 13 post-operative patients with reference to a clinical bedside monitor and in 57 subjects carrying out a controlled laboratory protocol with reference to capnography. The synthetic simulations revealed mean absolute error (MAE) of 0.8±0.6 brpm and standard deviation of absolute error of 0.3±0.2 brpm for the BR algorithms of patch sensor. The controlled laboratory testing revealed MAE of 1.7±0.7 brpm (n=57) for stationary conditions. The proposed simulation platform can be useful for developmental refinement or validation of BR measurement prior to testing in humans at clinical or laboratory conditions and applicable for testing other patient monitoring devices with modular modifications.

Predicting Lameness in Sheep Activity Using Tri-Axial Acceleration Signals.

Simple SummaryMonitoring livestock farmed under extensive conditions is challenging and this is particularly difficult when observing animal behaviour at an individual level. Lameness is a disease symptom that has traditionally relied on visual inspection to detect those animals with an abnormal walking pattern. More recently, accelerometer sensors have been used in other livestock industries to detect lame animals. These devices are able to record changes in activity intensity, allowing us to differentiate between a grazing, walking, and resting animal. Using these on-animal sensors, grazing, standing, walking, and lame walking were accurately detected from an ear attached sensor. With further development, this classification algorithm could be linked with an automatic livestock monitoring system to provide real time information on individual health status, something that is practically not possible under current extensive livestock production systems.Lameness is a clinical symptom associated with a number of sheep diseases around the world, having adverse effects on weight gain, fertility, and lamb birth weight, and increasing the risk of secondary diseases. Current methods to identify lame animals rely on labour intensive visual inspection. The aim of this current study was to determine the ability of a collar, leg, and ear attached tri-axial accelerometer to discriminate between sound and lame gait movement in sheep. Data were separated into 10 s mutually exclusive behaviour epochs and subjected to Quadratic Discriminant Analysis (QDA). Initial analysis showed the high misclassification of lame grazing events with sound grazing and standing from all deployment modes. The final classification model, which included lame walking and all sound activity classes, yielded a prediction accuracy for lame locomotion of 82%, 35%, and 87% for the ear, collar, and leg deployments, respectively. Misclassification of sound walking with lame walking within the leg accelerometer dataset highlights the superiority of an ear mode of attachment for the classification of lame gait characteristics based on time series accelerometer data.

Does arm swing emphasized deliberately increase the trunk stability during walking in the elderly adults?

The purpose of this study was to determine whether trunk stability while walking changes when arm swing is deliberately altered in elderly individuals. Participants included 21 community-dwelling elderly individuals (7 men and 14 women; age, 81.8±5.0 years). We measured trunk acceleration by using a wireless miniature sensor unit containing a tri-axial linear accelerometer under 3 walking conditions: normal walking (normal condition), deliberately walking without any arm swing (no swing condition), and walking with a deliberately emphasized arm swing (over swing condition). To evaluate trunk stability during walking, we calculated harmonic ratios (HRs) based on trunk tri-axial acceleration signals (anteroposterior: AP, vertical: VT, and mediolateral: ML). HR–AP and HR–VT were not significantly different across the 3 conditions, but HR–ML in the over swing condition was significantly higher than that in the other 2 conditions by generalized estimating equations (GEE) adjusted for walking speed (p<0.05). These findings indicate that trunk stability in the ML direction increased when the elderly individuals walked with a deliberately emphasized arm swing.

Fall-Risk Classification of the Timed Up-And-Go Test with Principle Component Analysis

This study aimed to show that important fall risk measures among the elderly can be classified using multiple parameters obtained from wearable inertial sensors. The timed up-and-go (TUG) test, a well-known standard assessment test, was used to evaluate the risk of falling among elderly individuals. The use of wearable inertial sensors enables extraction of triaxial acceleration and angular velocity signals for offline analysis. Thirty-eight elderly patients from Fujimoto Hayasuzu Hospital participated in this study. Specific results were provided from the signals obtained from acceleration and angular velocity, and analysis was carried out in each phase of various activities, such as sit-to-stand, walking, etc. Seventy-eight parameters were obtained from the extracted acceleration and angular velocity signals in all phases to classify the risk of falling among the elderly. Using principle component analysis, the most important measures were selected from the gathered parameters. The most influential measure in differentiating subjects with high and low fall risks was the turning angular velocity signal.

The Usefulness of a New Gait Symmetry Parameter Derived from Lissajous Figures of Tri-axial Acceleration Signals of the Trunk

The Usefulness of a New Gait Symmetry Parameter Derived from Lissajous Figures of Tri-axial Acceleration Signals of the Trunk

Identification of imperial cormorant Phalacrocorax atriceps behaviour using accelerometers

Animal behaviour is largely defined in terms of movement or lack of it, so precise quan- tification of animal movement is a potentially powerful way of identifying several animal behaviours. Animal-attached tags that record acceleration lend themselves particularly to this. In this work we show how tri-axial acceleration can be used to identify some of the behaviours of imperial cormorants Phalacrocorax atriceps. Based on the assessment of tri-axial acceleration signals, the following behaviours were identified in free-living birds: standing, sitting, floating on water, flying, walking and diving. During diving, the descent, bottom and ascent phases could be distinguished. We consid- ered the factors which coded for the different behaviours and this allowed us to design a key that will allow researchers assessing tri-axial accelerometry data to identify some of the behaviours that imperial cormorants perform.

Development of a Wearable Motion Detector for Telemonitoring and Real-Time Identification of Physical Activity

Characteristics of physical activity are indicative of one's mobility level, latent chronic diseases, and aging process. Current research has been oriented to provide quantitative assessment of physical activity with ambulatory monitoring approaches. This study presents the design of a portable microprocessor-based accelerometry measuring device to implement real-time physical activity identification. An algorithm was developed to process real-time tri-axial acceleration signals produced by human movement to identify targeted still postures, postural transitions, and dynamic movements. Fall detection was also featured in this algorithm to meet the increasing needs of elderly care in free-living environments. High identification accuracy was obtained in performance evaluation. This device is technically viable for telemonitoring and real-time identification of physical activity, while providing sufficient information to evaluate a person's activity of daily living and her/his status of physical mobility. Limitations regarding real-time processing and implementation of the system for telemonitoring in the home environment were also observed.

Improving the Accuracy of Pedometer Used by the Elderly with the FFT Algorithm

The aim of this study was to investigate and improve the accuracy of accelerometer-type pedometers used by the elderly with slow walking speeds, with or without gait disorders, who do or do not use a cane. Eighteen subjects walked with a cane (5 males, 13 females; age, 80.9 +/- 7.7 yr; height, 148.1 +/- 7.7 cm; weight, 51.8 +/- 8.8 kg (mean +/- SD); nine had impaired gait), and 31 subjects walked without a cane (7 males, 24 females; age, 80.9 +/- 7.7 yr; height, 148.1 +/- 7.7 cm; weight, 51.8 +/- 8.8 kg; 15 had impaired gait). Subjects walked for approximately 20 m (10 m in each direction and a turning arc) at their own speed. We determined the number of steps by pedometer (PM), by visually counting the actual number of steps (RM), and by the triaxial acceleration signals. The power spectrum of the accelerometer in each direction calculated by fast Fourier transform (FFT) for a 4-s temporal window was normalized with the maximum power of each window. It was composited, and the frequency at maximum power was considered as the cadence. The number of steps taken (FM) was determined by summing all the estimated steps in each window. PM was significantly less than the RM (P < 0.05), and the error of PM was 53.2 +/- 34.1% of RM. FM did not differ from the RM, and the average error of FM was -0.7 +/- 7.9% of RM (absolute value: 5.8 +/- 5.3%). We suggest that our FFT method is suitable for estimating the number of steps during walking in this population.