Three-axis Accelerometer Research Articles

Combining Machine Learning and Dynamic Time Wrapping for Vehicle Driving Event Detection Using Smartphones

The detection of driving events could be useful for reducing accidents, fleet management and insurance premiums etc. Currently, top of the range vehicles and large fleets employ expensive driver monitoring systems. However, most drivers do not have access to such systems. The required monitoring platform would have to deliver the required performance while also being affordable and accessible. A candidate with considerable promise is the smartphone with sensors built-in that could be exploited for the detection of driving events. However, to date it has not been possible to achieve the required correct, missed and false detection rates in addition to the computational efficiency for real-time operations. This paper proposes a novel bagging tree and dynamic time warping (DTW) integrated algorithm for the detection of driving events employing acceleration and orientation data from a smartphone's low cost three-axis accelerometers and gyroscopes. The bagging tree-based machine learning algorithm provides the initial maneuver detection results, as well as the location of the event start and end points. Event detection is then achieved by calculating the similarity of the results predicted through the bagging tree algorithm with the corresponding templates extracted from the experience datasets, while also applying a number of constraints to verify the calculated results. Field test results show that the proposed integrated algorithm is superior to the state-of-the-art, achieving a high correct detection accuracy of 97.5%, a low missed detection of 2.5% and a false detection rate of 2.9%. The corresponding results for the best alternative candidate method are 90.2%, 9.8% and 11.7%. Furthermore, the improvement in computational efficiency offered by our proposed approach is three to more than ten times greater than that of the other state-of-the-art algorithms.

Application of Motion Sensor Fusion in Special Competitive Sports

With the advancement of science and technology and the rapid development of the field of intelligence, new sensor technology has also made great progress. The availability and use speed of motion sensor technology are increasing rapidly, while its cost is reduced, the overall performance is also more complete, and the application fields are becoming more and more extensive. Based on the introduction and summary of the human body structure and the characteristics of sports, in order to facilitate the study of human movement, this article establishes a rod‐shaped sports model and a human body coordinate system that is convenient for analysis and calculation. Through the analysis of commonly used sports parameter measurement methods, a method of using acceleration parameters for sports measurement and analysis is proposed. The motion sensor is used to measure the movement of the limbs, and the mathematical relationship between acceleration parameters and speed, displacement, and other parameters is used to solve other motion parameters, so as to analyze the posture and movement trajectory of sports. We developed a motion acquisition system which is divided into two parts: a signal acquisition unit and a data processing unit. With ARM7 and three‐axis accelerometer ADXL330 as the core, it can realize information acquisition and data analysis of up to 5 sensor network nodes. The topology management platform mainly formulates the sleep strategy of suitable nodes according to the changes of the sensor network topology, maintains the connectivity of the network, and ensures the effective transmission of data. On the basis of the performance test of the system, a sports measurement experiment was carried out, and it was applied to the control of competitive sports for reliability testing. The experimental results verified the use of the sports information acquisition system to collect and analyze sports information.

Response of a Tensegrity Simplex in Experimental Tests of a Modal Hammer at Different Self-Stress Levels

The natural frequencies and eigenmodes of the tensegrity simplex are determined experimentally in impact hammer tests. To study an effect of prestressing, the tests are carried out on a physical model 1.2 m high and 0.5 m diameter with build-in transducers for measuring actual values of forces in cables at 13 prestress levels. The recorded data for each pre-stress level from three three-axial accelerometers are combined to extract the first five natural frequencies and modes by means of the method of experimental modal analysis. It was experimentally confirmed that the first rotational frequency depends on the pre-stress level and its sensitivity to the self-stress state is high enough to be successfully used in vibrational health monitoring. A proprietary formula was proposed for the relationship between frequency and the pre-stress level to control the dynamic properties of the simplex. An excellent comparison between the experimental results of the frequency and the formula was obtained. A comparison of numerical results of the finite element method with truss element and experiment is also shown.

Associations between Adherence to Combinations of 24-h Movement Guidelines and Overweight and Obesity in Japanese Preschool Children.

The interactions between movement behaviors (physical activity, screen time, and sleep) affect the health of preschool children. Therefore, we examined the status of adherence to combinations of 24-hour movement guidelines (24-h MG) in Japanese preschool children and determined the associations between overweight/obesity and adherence to these 24-h MG. This cross-sectional study was conducted with 421 children aged 3–5 years (216 boys and 199 girls) living in the northeastern region of Japan. To evaluate the 24-h MG, physical activity over one week was measured using a three-axis accelerometer. For screen time and sleep duration, a questionnaire survey was conducted. Children who failed to meet all the 24-h MG had a higher probability of overweight/obesity than those who met all the 24-h MG (odds ratio 1.139, 95% confidence interval: 1.009, 1.285). The percentage of adherence to the 24-h MG was 91.6% for physical activity, 82.5% for sleep duration, and 33.7% for screen time, and only 21.5% of the children adhered to all three areas of the guidelines. Our findings have important implications for developing public health policies and effective intervention programs for preschool children.

Behavior assessment and applications for BRD diagnosis: beef.

Assessment of behavior is a longstanding strategy to assist the diagnosis of clinical bovine respiratory disease (BRD) in beef cattle. Cattle with systemic inflammation caused by infectious pathogen(s) display predictable behavioral adaptations compared to healthy cohorts. Behavioral alterations in BRD-affected cattle include lethargy, social isolation, and anorexia. However, behavior assessment to support BRD case definition in the production setting is challenging because: (1) other bovine diseases cause behavior alterations similar to BRD; (2) cattle have inherent prey instinct to disguise sickness behavior during human evaluation; (3) labor constraints dictate very brief observation of animal behavior; and (4) traditional behavior assessment is subjective and agreement is often poor. Some of these challenges may be overcome with the use of advanced technologies that allow continuous, remote, and objective behavior assessment of individual cattle. Automated methodologies for behavior assessment include three-axis accelerometers that quantify physical behaviors, systems that document feeding/watering behavior, and triangulation systems that document spatial behavior. Each of these behavior-monitoring approaches generates unique information and may facilitate early detection of BRD compared to traditional methods. Nevertheless, adoption of behavior assessment technologies for BRD diagnosis in beef operations hinges upon improved detection, positive return on investment, and successful integration within existing BRD management practices.

Attitude Output of Strapdown Inertial Navigation System Based on Laser Gyro

Aiming at the real-time problems of signal acquisition, attitude calculation and data exchange of strapdown inertial navigation system, the data exchange between the core device of three-axis screw instrument and three-axis accelerometer sensor inertial unit (IMU) is analyzed. The RS-232 serial interface and can bus interface are adopted, which can not meet the requirements of high-speed sampling and real-time data transmission of each sensor. A new method based on FPGA dual port RAM and dual DSP is proposed Speed data access mode, through the main control CPU clock synchronization, can effectively solve the bottleneck problem of data communication between IMU attitude data and core equipment, and realize the rapid response ability of vehicle navigation system. Experiments and simulations show that the highest frequency attitude update rate of the method can reach 2000kHz, which can effectively solve the input and output data and navigation calculation ability, and improve the maneuverability of the carrier.

Robust Autocalibration of Triaxial Magnetometers

Self-calibration of a magnetometer usually requires controlled magnetic environment as the calibration output can be affected by field distortions from nearby magnetic objects. In this article, we develop a two-stage method that can accurately self-calibrate magnetometer from measurements containing anomalous readings due to local magnetic disturbances. The method proceeds by robustly fitting an ellipsoid to measurement data via L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -norm convex optimization, yielding initial model variables that are less prone to magnetic disruptions. These are then served as a starting point for robust nonlinear least-squares optimization, which refines the magnetometer model to minimize sensor estimation errors while suppressing heavy anomalies. Synthetic and real experimental results are provided to demonstrate improved accuracy of the proposed method in the presence of outliers. We additionally show empirically that the method is directly applicable to self-calibration of three-axis accelerometers.

Relationship between physical activity levels during rehabilitation hospitalization and life-space mobility following discharge in stroke survivors: A multicenter prospective study

ABSTRACT Background Higher physical activity levels during hospitalization may benefit the life-space mobility, defined as the ability to move within environments that expand from one’s home to the greater community, of stroke survivors following their discharge. Objectives This study aimed to evaluate the relationship between physical activity levels during rehabilitation hospitalization and life-space mobility among stroke survivors three months after their discharge. Methods We recruited 84 stroke survivors as prospective participants from four convalescent rehabilitation hospitals. Physical activity levels during hospitalization were assessed using pedometers with a three-axis accelerometer, and their average step count over 14 consecutive days prior to discharge was used as the representative set of values. Pedometers were placed on the participant’s waist or wrist on the non-paretic side. The Life-Space Assessment (LSA), a validated self-reporting measure for assessing community mobility, was implemented three months following participant discharge from rehabilitation hospitals via a mail-in survey method. To determine the relationship between the participants’ level of physical activity during hospitalization and the LSA score following discharge, we performed multivariate regression analysis. Results A total of 75 participants (89.3%) completed the post-discharge survey and were therefore included in the analysis. The multiple regression analysis, controlled for age, balance function, walking endurance, fear of falling, and functional status, revealed that daily step counts were significantly associated with the LSA score three months after discharge (β = 0.241, p = .026). Conclusions Physical activity levels during hospitalization were significantly associated with the life-space mobility of stroke survivors following discharge.

Pose estimation by extended Kalman filter using noise covariance matrices based on sensor output

This paper presents an extended Kalman filter for pose estimation using noise covariance matrices based on sensor output. Compact and lightweight nine-axis motion sensors are used for motion analysis in widely various fields such as medical welfare and sports. A nine-axis motion sensor includes a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer. Information obtained from the three sensors is useful for estimating joint angles using the Kalman filter. The extended Kalman filter is used widely for state estimation because it can estimate the status with a small computational load. However, determining the process and observation noise covariance matrices in the extended Kalman filter is complicated. The noise covariance matrices in the extended Kalman filter were found for this study based on the sensor output. Postural change appears in the gyroscope output because the rotational motion of the joints produces human movement. Therefore, the process noise covariance matrix was determined based on the gyroscope output. An observation noise covariance matrix was determined based on the accelerometer and magnetometer output because the two sensors’ outputs were used as observation values. During a laboratory experiment, the lower limb joint angles of three participants were measured using an optical 3D motion analysis system and nine-axis motion sensors while participants were walking. The lower limb joint angles estimated using the extended Kalman filter with noise covariance matrices based on sensor output were generally consistent with results obtained from the optical 3D motion analysis system. Furthermore, the lower limb joint angles were measured using nine-axis motion sensors while participants were running in place for about 100 s. The experiment results demonstrated the effectiveness of the proposed method for human pose estimation.

Influence of Tool Posture and Position on Stability in Milling with Parallel Kinematic Machine Tool

This paper investigated the machining stability influenced by tool posture and position in ball-end milling with parallel kinematic machine tool (PKM). Initially, the geometric structure was identified, and the machinery stiffness was measured by impulse respond method at several positions with four tool postures. Then, the milling tests were conducted on flat work surface using a ball-end mills. Cutting force and acceleration signals of milling tests were measured by three-axis dynamometer and accelerometer. Furthermore, these signals were analyzed by using Fast-Fourier transform and Hilbert–Huang transform (HHT). The results showed that the length of arm change with tool posture, where the machinery stiffness decreased with the total length of arms for any tool position. The experimental results also demonstrated the machining stability varied with tool posture; the trend of stability corresponds with the machinery stiffness. The vibration analysis by HHT presented the increasing of power level in the time–frequency plot when the length of arm increase during milling process. Therefore, the geometric influence must be considered to support process planning on the PKM.

An open-source research tool to study triaxial inertial sensors for monitoring selected behaviors in sheep.

The use of automated systems for monitoring animal behavior provides information on individual animal behavior and can be used to enhance animal productivity. However, the advancement of this industry is hampered by technology costs, challenges with power supplies, limited data accessibility, and inconsistent testing approaches for confirming the detection of livestock behaviors. Development of open-source research tools similar to commercially available wearable technologies may contribute to the development of more-efficient and affordable technologies. The objective of this study was to demonstrate an open-source, microprocessor-based sensor designed to monitor and enable differentiation among selected behaviors of adult wethers. The sensor was comprised of an inexpensive espressif ESP-32-WROOM-32 microprocessor with Bluetooth communication, a generic MPU92/50 motion sensor that contains a three-axis accelerometer, three-axis magnetometer, a three-axis gyroscope, and a 5-V rechargeable lithium-ion battery. The open-source Arduino IDE software was used to program the microprocessor and to adjust the frequency of sampling, the data packet to send, and the operating conditions. For demonstration purposes, sensors were placed on six housed sheep for three 1-h increments with concurrent visual behavioral observation. Sensor readings (x-, y-, and z-axis) were summarized (mean and SD) within a minute and compared to animal behavior observations (also on a by-minute basis) using a linear mixed-effect model with animal as a random effect and behavioral classifier as a fixed effect. This analysis demonstrated the basic utility of the sensor to differentiate among animal behaviors based on sensed data (P < 0.001). Although substantial additional work is needed for algorithm development, power source testing, and network optimization, this open-source platform appears to be a promising strategy to research wearable sensors in a generalizable manner.

The Attitude Measurement of Horizontal Directional Drilling Equipment Based on Quaternion and Extended Kalman Filtering Method

For the attitude measurement of drilling tool in horizontal directional drilling, a new method for attitude measurement system based on quaternion and extended Kalman filter (EKF) is presented. The attitude measurement system consists of three-axis accelerometer and three-axis gyroscope. Based on the data information obtained by the inertial sensor, the attitude angle of the drilling tool can be calculated. To limit the errors of angle measurement, this research combines the errors of the sensors and the measurement noise and uses EKF method to obtain three angles. Three angles consist of pitch angle, roll angle, drilling angle. The proposed method was tested by two experiments. Results showed that this method could limit the error of drilling tool attitude measurement and reduce the impact of environmental noise on the measurement.

Calibrated non‐contact vibrational harmonics measurement based on self‐vibration compensated 2D‐PSD with MEMS accelerometer using FFT analysis

This study presents a novel fast Fourier transform (FFT)-based non-contact vibrational harmonics measurement system using a position sensitive detector (PSD) along with calibration using a piezoelectric accelerometer. Frequency-domain vibrational analysis is required as the changes in machine dynamics are directly related to its failures and could provide more insight into the vibration signal. In this regard, FFT is used for spectral analysis to detect the harmonics in the vibration signal. The novelty of the applied technique for detecting vibrational harmonics lies in its innate contactless nature where the vibration detection sensor i.e. PSD is placed at a particular distance from the vibrating target. Additionally, the parasitic and external vibrations, which might pose unforeseen errors in the detected vibration data, have been nullified by employing a self-vibration technique using an ADXL-345 three-axis accelerometer. The results obtained through PSD have been calibrated via a standard Bruel & Kjaer (B & K) vibration measurement system which uses a piezoelectric accelerometer (B & K accelerometer). The proposed measurement technique is equipped with NI compact RIO-9074 that features a real-time processor and an FPGA. The system was observed to effectively measure the frequency range 5–600 Hz with a maximum relative error of 2% in FFT amplitudes.

A portable plantar pressure system: Specifications, design, and preliminary results.

In recent years, there has been an increasing interest in developing in-shoe foot plantar pressure systems. Although such devices are not novel, devising insole devices for gait analysis is still an important issue. The goal of this study is to develop a new portable system for plantar pressure distribution measurement based on a three-axis accelerometer. The portable system includes: PJRC Teensy 3.6 microcontroller with 32-bit ARM Cortex-M4 microprocessor with a clock speed of 180MHz; HC-11 radio modules (transmitter and receiver); a battery; a fixing band; pressure sensors; MPU-9150 inertial navigation module; and FFC tape. The pressure insole is leather-based and consists of seven layers. It is divided into 16 areas and the outcome of the system is data concerning plantar pressure distribution under foot during gait. The system was tested on 22 healthy volunteer subjects, and the data was compared with a commercially available system: Medilogic. The SNR value for the proposed sensor is 28.27dB. For a range of pressure of 30-100 N, the sensitivity is 0.0066V/N while the linearity error is 0.05. The difference in plantar pressure from both the portable plantar pressure system and Medilogic is not statistically significant. The proposed system could be recommended for research applications both inside and outside of a typical gait laboratory.

The relationships between three-axis accelerometer measures of physical activity and motor symptoms in patients with Parkinson\u2019s disease: a single-center pilot study

BackgroundVarious wearable devices for objectively evaluating motor symptoms of patients with Parkinson’s disease (PD) have been developed. Importantly, previous studies have suggested protective effects of physical activity in PD. However, the relationships between conventional clinical ratings for PD and three-axis accelerometer measures of physical activity (e.g., daily physical activity levels [PAL] or metabolic equivalents of task [METs]) are still unclear, particularly for METs. In the current study, we sought to elucidate these relationships on a daily basis, and to clarify optimal predictors for clinical states on a 30-min basis.MethodsPatients who were hospitalized for adjustment of drugs or deep brain stimulation were enrolled. Using waist-worn three-axis accelerometers, PAL and METs parameter data were obtained and compared with UPDRS-3[On] and symptom diary data. We extracted data from the patients’ best and worst days, defined by the best and worst UPDRS-3[On] scores, respectively. Thus, 22 data sets from 11 patients were extracted. We examined the correlations and produced scatter plots to represent the relationships, then investigated which METs parameters and activity patterns were the best predictors for “On” and “dyskinesia”.ResultsThe parameter “mean METs value within the 95–92.5 percentile range on a day (95–92.5 percentile value)” exhibited the strongest correlation with conventional daily clinical ratings (Rho: − 0.799 for UPDRS-3[On], 0.803 for On hours [p < 0.001]). Scatter plots suggested that PAL tended to have higher values in patients with involuntary movement. However, METs parameters focusing on higher METs seemed to alleviate this tendency. We clarified that “time over 2.0 METs” and “time over 1.5 METs” could be predictors for “On” and “dyskinesia” on a 30-min basis, respectively (AUROC: 0.779 and 0.959, 95% CI: 0.733–0.824 and 0.918–1.000). The specificity and sensitivity of the optimal activity pattern for “On” were 0.858 and 0.621.ConclusionsThis study suggested feasible activity patterns and METs parameters for objective evaluation of motor symptoms on a 30-min or daily basis. Three-axis accelerometer measures focusing on higher METs may be appropriate for evaluating physical activity. Further larger-scale studies are necessary to clarify the validity, reliability, and clinical utility of these objective measures.

Integration and Testing of a Three-Axis Accelerometer in a Woven E-Textile Sleeve for Wearable Movement Monitoring.

This paper presents a method to integrate and package an accelerometer within a textile to create an electronic textile (e-textile). The smallest commercially available accelerometer sensor (2 mm × 2 mm × 0.95 mm) is used in the e-textile and is fully integrated within the weave structure of the fabric itself, rendering it invisible to the wearer. The e-textile forms the basis of a wearable woven sleeve which is applied to arm and knee joint bending angle measurement. The integrated e-textile based accelerometer sensor system is used to identify activity type, such as walking or running, and count the total number of steps taken. Performance was verified by comparing measurements of specific elbow joint angles over the range of 0° to 180° with those obtained from a commercial bending sensor from Bend Labs and from a custom-built goniometer. The joint bending angles, measured by all three sensors, show good agreement with an error of less than ~1% of reading which provides a high degree of confidence in the e-textile sensor system. Subsequently, knee joint angles were measured experimentally on three subjects with each being tested three times on each of three activities (walking, running and climbing stairs). This allowed the minimum and maximum knee joint angles for each activity to be determined. This data is then used to identify activity type and perform step counting.

IoT Based Fall Detection System for Elderly Population in Pakistan

A Fall is defined as an event that results in a person coming to rest inadvertently on the ground or floor or other lower level. Fall-related injuries may be fatal or non-fatal. It puts the elderly population, i.e., people of 65 years old, and over, in a dangerous situation. It is why we need a fast and efficient fall detection system to provide first aid and rescue the patient. The existing fall detection devices are not widely used because they do not meet the expectations of the users like the effectiveness of detecting a fall, time to inform guardian to provide necessary precautions and rescue the affected person on time. This device differs from other devices firstly in a way that it is a cheap portable device; secondly, as it was designed and assembled in a Muslim majority country, it should be able to distinguish fall from different movements of Salah. The tool uses a three-axis Accelerometer and Gyroscope sensor, which measures the acceleration and rotational motion in the X, Y, and Z-axis, respectively, which is controlled by a microcontroller called Arduino. The board uses a Wi-Fi module to send data wirelessly through the internet.

Respiration Rate Estimation Based on Independent Component Analysis of Accelerometer Data: Pilot Single-Arm Intervention Study.

BackgroundAs the mobile environment has developed recently, there have been studies on continuous respiration monitoring. However, it is not easy for general users to access the sensors typically used to measure respiration. There is also random noise caused by various environmental variables when respiration is measured using noncontact methods in a mobile environment.ObjectiveIn this study, we aimed to estimate the respiration rate using an accelerometer sensor in a smartphone.MethodsFirst, data were acquired from an accelerometer sensor by a smartphone, which can easily be accessed by the general public. Second, an independent component was extracted to calibrate the three-axis accelerometer. Lastly, the respiration rate was estimated using quefrency selection reflecting the harmonic component because respiration has regular patterns.ResultsFrom April 2018, we enrolled 30 male participants. When the independent component and quefrency selection were used to estimate the respiration rate, the correlation with respiration acquired from a chest belt was 0.7. The statistical results of the Wilcoxon signed-rank test were used to determine whether the differences in the respiration counts acquired from the chest belt and from the accelerometer sensor were significant. The P value of the difference in the respiration counts acquired from the two sensors was .27, which was not significant. This indicates that the number of respiration counts measured using the accelerometer sensor was not different from that measured using the chest belt. The Bland-Altman results indicated that the mean difference was 0.43, with less than one breath per minute, and that the respiration rate was at the 95% limits of agreement.ConclusionsThere was no relevant difference in the respiration rate measured using a chest belt and that measured using an accelerometer sensor. The accelerometer sensor approach could solve the problems related to the inconvenience of chest belt attachment and the settings. It could be used to detect sleep apnea through constant respiration rate estimation in an internet-of-things environment.

Hand Gesture Recognition by a MMG-Based Wearable Device

A novel wearable human machine interface based on mechanomyogram (MMG) signals was presented in this study. A three-axis accelerometer was fixed to a customized watch strap to measure the MMG signals that were generated by the end of the extensor digitorum muscle. Eight gaming gestures, including clapping, index figure flicking, finger snapping, coin flipping, shooting, wrist extension, wrist flexion and fist-making, were identified in real time. This study extracted the features from both the time signals and the coefficients of the wavelet packet decomposition (WPD), and sequential forward selection (SFS) was used to identify the significant features to improve the classification accuracy and reduce the processing time. The performances of the classifiers such as the k-nearest neighbors (KNN), the support vector machine (SVM), linear discriminant analysis (LDA), and deep neural network (DNN) were compared. After testing the system on 35 subjects aged from 16 to 55 years old, the proposed system has advantages with respect to its convenient portability, stable signal acquisition, low power consumption, and high classification accuracy.

A Single-Step Method for Accelerometer and Magnetometer Axes Alignment

In this work, we introduce a single-step method for axes alignment of a three-axis accelerometer and a three-axis magnetometer. The proposed method is based on the magnetic inclination to derive the inclination angle and the axes alignment rotation matrix, both in closed form. It is applied when the two sensors are fixed on the same rigid platform and requires no special piece of equipment. In contrast to the existing algorithms, it does not rely on an iterative optimization or estimation method; instead, it is executed in a single step. It is two orders of magnitude faster than the existing iterative algorithms based on the same principle. Multiple measurement sets are used to demonstrate the algorithm's computational efficiency, while its accuracy is evaluated through a series of simulated measurements.