Accelerometer Signals Research Articles

Pole placement LMI constraints for stability and transient performance of LPV systems with incomplete state measurement

In this paper, new conditions for the stabilisation and transient performance improvement of linear parameter-varying (LPV) systems considering the gain-scheduling (GS) strategy are proposed. Our work is focused on dealing with LPV systems under the major practical constraint of incomplete state measurement. In that sense, we propose two new control design strategies based on linear matrix inequalities (LMI). First, for coping with the general case where only a subset of the state variables is measured, we propose a new static output feedback (SOF) strategy. Second, for dealing with the particular case where only accelerometers signals are available, we bring new synthesis conditions for the design of state derivative feedback (SDF) controllers. Further from stability, our proposed methods are able to induce better transient response by including pole placement LMI constraints in the control design. For illustrating our contribution efficacy, we present a couple of design examples.

Skin Acceleration Levels Estimated by a Neck-surface Accelerometer during Phonation Are Affected by The Mechanical Properties of The Anterior Cervical Skin

The aim of the present study was to assess whether skin acceleration levels (SAL) estimated by a neck-surface accelerometer (ACC) are affected by the anterior neck skin condition. Each of six healthy non-dysphonic participants wore a headset microphone (MIC), had an ACC sensor fitted on the skin over the cervical trachea, and were subsequently asked to gradually increase the vocal loudness during sustained phonation of the vowel /e:/ (crescendo task), while the sound pressure levels on a sound level meter (SPLSLM) and MIC/ACC signals were simultaneously recorded. Root mean squared values were calculated from the MIC and ACC signals as the sound pressure level (SPLMIC) and SAL, respectively, and the relationships between SPLSLM and SAL were compared between neck anteflexion and retroflexion or between outward and inward skin retraction on both sides of the sensor. In the total samples for the successful crescendo performance in a natural head position, the SPLMIC and SPLSLM showed a strong linear correlation (r=0.980), whereas the correlation between the SAL and SPLSLM showed a distorted regression line (r=0.765) with individual differences. In all participants, the anteflexion and inward skin retraction decreased the SAL value at the same SPLSLM value, whereas the retroflexion increased the SAL value at the same SPLSLM value. These results demonstrate that the signal intensity of a neck-surface ACC is affected by the condition of the anterior cervical skin, perhaps leading to inter-individual variability in SAL measurements.

Seismic imaging using an e-vib — A case study analyzing the signal properties of a seismic vibrator driven by electric linear synchronous motors

Seismic imaging characteristics of a prototype electrically driven, linear synchronous motor-based, vertical-force seismic vibrator (“e-vib”) were evaluated at a site in the Netherlands. The system weighs 1.65 t and excites seismic signals with a peak force of 6.7 kN. Data were recorded along two collocated geophone-based nodal and landstreamer microelectromechanical system - MEMS-based sensor 2D seismic profiles. To obtain a broad bandwidth data set, the e-vib operated with a 1–200 Hz linear sweep. Shot gathers of the merged nodal-landstreamer data set indicated good-quality seismic data of a broadband nature. The processed merged data set demonstrates high-resolution reflections of the stratigraphic members from approximately 200 m to 2 km, with visible reflections as deep as 2.5–2.9 km. As a reference, we also processed a legacy 3D microspread data set acquired at the same site with a magnitude stronger (14.1 t, 67.5 kN) hydraulic vibrator. Comparison of our nodal-landstreamer seismic section versus 2D slices extracted from the processed microspread seismic volume suggested similar signal penetration depth and the same key marker horizons seen in both. Analysis of the reaction mass and base-plate accelerometer signals recorded with the e-vib source operating on grass and on asphalt surfaces indicates that the e-vib has low total harmonic distortion. The results obtained indicate that, although relatively small, the e-vib is capable of generating high-quality broadband seismic data.

Use of a Collar-Mounted Triaxial Accelerometer to Predict Speed and Gait in Dogs.

Simple SummaryAccelerometers have been used for several years to monitor activity in free-moving dogs. The technique has particular utility for measuring the efficacy of treatments for osteoarthritis when changes to movement need to be monitored over extended periods. While collar-mounted accelerometer measures are precise, they are difficult to express in widely understood terms, such as gait or speed. This study aimed to determine whether measurements from a collar-mounted accelerometer made while a dog was on a treadmill could be converted to an estimate of speed or gait. We found that gait could be separated into two categories—walking and faster than walking (i.e., trot or canter)—but we could not further separate the non-walking gaits. Speed could be estimated but was inaccurate when speed exceeded 3 m/s. We conclude that collar-mounted accelerometers only allowing limited categorisation of activity are still of value for monitoring activity in dogs.Accelerometry has been used to measure treatment efficacy in dogs with osteoarthritis, although interpretation is difficult. Simplification of the output into speed or gait categories could simplify interpretation. We aimed to determine whether collar-mounted accelerometry could estimate the speed and categorise dogs’ gait on a treadmill. Eight Huntaway dogs were fitted with a triaxial accelerometer and then recorded using high-speed video on a treadmill at a slow and fast walk, trot, and canter. The accelerometer data (delta-G) was aligned with the video data and records of the treadmill speed and gait. Mixed linear and logistic regression models that included delta-G and a term accounting for the dogs’ skeletal sizes were used to predict speed and gait, respectively, from the accelerometer signal. Gait could be categorised (pseudo-R2 = 0.87) into binary categories of walking and faster (trot or canter), but not into the separate faster gaits. The estimation of speed above 3 m/s was inaccurate, though it is not clear whether that inaccuracy was due to the sampling frequency of the particular device, or whether that is an inherent limitation of collar-mounted accelerometers in dogs. Thus, collar-mounted accelerometry can reliably categorise dogs’ gaits into two categories, but finer gait descriptions or speed estimates require individual dog modelling and validation. Nonetheless, this accelerometry method could improve the use of accelerometry to detect treatment effects in osteoarthritis by allowing the selection of periods of activity that are most affected by treatment.

Glottal features for classification of phonation type from speech and neck surface accelerometer signals

Glottal source characteristics vary between phonation types due to the tension of laryngeal muscles with the respiratory effort. Previous studies in the classification of phonation type have mainly used speech signals recorded by microphone. Recently, two studies were published in the classification of phonation type using neck surface accelerometer (NSA) signals. However, there are no previous studies comparing the use of the acoustic speech signal vs. the NSA signal as input in classifying phonation type. Therefore, the current study investigates simultaneously recorded speech and NSA signals in the classification of three phonation types (breathy, modal, pressed). The general goal is to understand which of the two signals (speech vs. NSA) is more effective in the classification task. We hypothesize that by using the same feature set for both signals, classification accuracy is higher for the NSA signal, which is more closely related to the physical vibration of the vocal folds and less affected by the vocal tract compared to the acoustical speech signal. Glottal source waveforms were computed using two signal processing methods, quasi-closed phase (QCP) glottal inverse filtering and zero frequency filtering (ZFF), and a group of time-domain and frequency-domain scalar features were computed from the obtained waveforms. In addition, the study investigated the use of mel-frequency cepstral coefficients (MFCCs) derived from the glottal source waveforms computed by QCP and ZFF. Classification experiments with support vector machine classifiers revealed that the NSA signal showed better discrimination of the phonation types compared to the speech signal when the same feature set was used. Furthermore, it was observed that the glottal features showed complementary information with the conventional MFCC features resulting in the best classification accuracy both for the NSA signal (86.9%) and the speech signal (80.6%).

A Study on the Essential and Parkinson’s Arm Tremor Classification

In this article, the challenge of discriminating between essential and Parkinson’s tremor is addressed. Although a variety of methods have been proposed for diagnosing the severity of these highly occurring tremor types, their rapid and effective identification, especially in their early stages, proves particularly difficult and complicated due to their wide range of causes and similarity of symptoms. To this goal, a clinical analysis was performed, where a number of volunteers including essential and Parkinson’s tremor-diagnosed patients underwent a series of pre-defined motion patterns, during which a wearable sensing setup was used to measure their lower arm tremor characteristics from multiple selected points. Extracted features from the acquired accelerometer signals were used to train classification algorithms, including decision trees, discriminant analysis, support vector machine (SVM), K-nearest neighbor (KNN) and ensemble learning algorithms, for providing a comparative study and evaluating the potential of utilizing machine learning to accurately discriminate among different tremor types. Overall, SVM related classifiers proved to be the most successful in terms of classifying between Parkinson’s, essential and no tremor diagnosed with percentages reaching up to 100% for a single accelerometer measurement at the metacarpal area. In general and in motion while holding an object position, Coarse Gaussian SVM classifier reached 82.62% accuracy.

Is Human Walking a Network Medicine Problem? An Analysis Using Symbolic Regression Models with Genetic Programming

Human walking is typically assessed using a sensor placed on the lower back or the hip. Such analyses often ignore that the arms, legs, and body trunk movements all have significant roles during walking; in other words, these body nodes with accelerometers form a body sensor network (BSN). BSN refers to a network of wearable sensors or devices on the human body that collects physiological signals. Our study proposes that human locomotion could be considered as a network of well-connected nodes. While hypothesizing that accelerometer data can model this BSN, we collected accelerometer signals from six body areas from ten healthy participants performing a cognitive task. Machine learning based on genetic programming was used to produce a collection of non-linear symbolic models of human locomotion. With implications in precision medicine, our primary finding was that our BSN models fit the data from the lower back's accelerometer and describe subject-specific data the best compared to all other models. Across subjects, models were less effective due to the diversity of human sizes. A BSN relationship between all six body nodes has been shown to describe the subject-specific data, which indicates that the network-medicine relationship between these nodes is essential in adequately describing human walking. Our gait analyses can be used for several clinical applications such as medical diagnostics as well as creating a baseline for healthy walking with and without a cognitive load.

Investigation of the Time Dependence of Wind-Induced Aeroelastic Response on a Scale Model of a High-Rise Building

Experimental wind tunnel test results are affected by acquisition times because extreme pressure peak statistics depend on the length of acquisition records. This is also true for dynamic tests on aeroelastic models where the structural response of the scale model is affected by aerodynamic damping and by random vortex shedding. This paper investigates the acquisition time dependence of linear transformation through singular value decomposition (SVD) and its correlation with floor accelerometric signals acquired during wind tunnel aeroelastic testing of a scale model high-rise building. Particular attention was given to the variability of eigenvectors, singular values and the correlation coefficient for two wind angles and thirteen different wind velocities. The cumulative distribution function of empirical magnitudes was fitted with numerical cumulative density function (CDF). Kolmogorov–Smirnov test results are also discussed.

Design and Testing of Stimulation and Myoelectric Recording Modules in an Implanted Distributed Neuroprosthetic System.

Implantable motor neuroprostheses can restore functionality to individuals with neurological disabilities by electrically activating paralyzed muscles in coordinated patterns. The typical design of neuroprosthetic systems relies on a single multi-use device, but this limits the number of stimulus and sensor channels that can be practically implemented. To address this limitation, a modular neuroprosthesis, the "Networked Neuroprosthesis" (NNP), was developed. The NNP system is the first fully implanted modular neuroprosthesis that includes implantation of all power, signal processing, biopotential signal recording, and stimulating components. This paper describes the design of stimulation and recording modules, bench testing to verify stimulus outputs and appropriate filtering and recording, and validation that the components function properly while implemented in persons with spinal cord injury. The results of system testing demonstrated that the NNP was functional and capable of generating stimulus pulses and recording myoelectric, temperature, and accelerometer signals. Based on the successful design, manufacturing, and testing of the NNP System, multiple clinical applications are anticipated.

Translating Videos into Synthetic Training Data for Wearable Sensor-Based Activity Recognition Systems Using Residual Deep Convolutional Networks

Human activity recognition (HAR) using wearable sensors has benefited much less from recent advances in Deep Learning than fields such as computer vision and natural language processing. This is, to a large extent, due to the lack of large scale (as compared to computer vision) repositories of labeled training data for sensor-based HAR tasks. Thus, for example, ImageNet has images for around 100,000 categories (based on WordNet) with on average 1000 images per category (therefore up to 100,000,000 samples). The Kinetics-700 video activity data set has 650,000 video clips covering 700 different human activities (in total over 1800 h). By contrast, the total length of all sensor-based HAR data sets in the popular UCI machine learning repository is less than 63 h, with around 38 of those consisting of simple mode of locomotion activities like walking, standing or cycling. In our research we aim to facilitate the use of online videos, which exist in ample quantities for most activities and are much easier to label than sensor data, to simulate labeled wearable motion sensor data. In previous work we already demonstrated some preliminary results in this direction, focusing on very simple, activity specific simulation models and a single sensor modality (acceleration norm). In this paper, we show how we can train a regression model on generic motions for both accelerometer and gyro signals and then apply it to videos of the target activities to generate synthetic Inertial Measurement Units (IMU) data (acceleration and gyro norms) that can be used to train and/or improve HAR models. We demonstrate that systems trained on simulated data generated by our regression model can come to within around 10% of the mean F1 score of a system trained on real sensor data. Furthermore, we show that by either including a small amount of real sensor data for model calibration or simply leveraging the fact that (in general) we can easily generate much more simulated data from video than we can collect its real version, the advantage of the latter can eventually be equalized.

Intelligent Fault Diagnosis of Rotary Machinery by Convolutional Neural Network with Automatic Hyper-Parameters Tuning Using Bayesian Optimization.

Intelligent fault diagnosis can be related to applications of machine learning theories to machine fault diagnosis. Although there is a large number of successful examples, there is a gap in the optimization of the hyper-parameters of the machine learning model, which ultimately has a major impact on the performance of the model. Machine learning experts are required to configure a set of hyper-parameter values manually. This work presents a convolutional neural network based data-driven intelligent fault diagnosis technique for rotary machinery which uses model with optimized hyper-parameters and network structure. The proposed technique input raw three axes accelerometer signal as high definition 1-D data into deep learning layers with optimized hyper-parameters. Input is consisted of wide 12,800 × 1 × 3 vibration signal matrix. Model learning phase includes Bayesian optimization that optimizes hyper-parameters of the convolutional neural network. Finally, by using a Convolutional Neural Network (CNN) model with optimized hyper-parameters, classification in one of the 8 different machine states and 2 rotational speeds can be performed. This study accomplished the effective classification of different rotary machinery states in different rotational speeds using optimized convolutional artificial neural network for classification of raw three axis accelerometer signal input. Overall classification accuracy of 99.94% on evaluation set is obtained with the CNN model based on 19 layers. Additionally, more data are collected on the same machine with altered bearings to test the model for overfitting. Result of classification accuracy of 100% on second evaluation set has been achieved, proving the potential of using the proposed technique.

Assessing elderly\u2019s functional balance and mobility via analyzing data from waist-mounted tri-axial wearable accelerometers in timed up and go tests

BackgroundPoor balance has been cited as one of the key causal factors of falls. Timely detection of balance impairment can help identify the elderly prone to falls and also trigger early interventions to prevent them. The goal of this study was to develop a surrogate approach for assessing elderly’s functional balance based on Short Form Berg Balance Scale (SFBBS) score.MethodsData were collected from a waist-mounted tri-axial accelerometer while participants performed a timed up and go test. Clinically relevant variables were extracted from the segmented accelerometer signals for fitting SFBBS predictive models. Regularized regression together with random-shuffle-split cross-validation was used to facilitate the development of the predictive models for automatic balance estimation.ResultsEighty-five community-dwelling older adults (72.12 ± 6.99 year) participated in our study. Our results demonstrated that combined clinical and sensor-based variables, together with regularized regression and cross-validation, achieved moderate-high predictive accuracy of SFBBS scores (mean MAE = 2.01 and mean RMSE = 2.55). Step length, gender, gait speed and linear acceleration variables describe the motor coordination were identified as significantly contributed variables of balance estimation. The predictive model also showed moderate-high discriminations in classifying the risk levels in the performance of three balance assessment motions in terms of AUC values of 0.72, 0.79 and 0.76 respectively.ConclusionsThe study presented a feasible option for quantitatively accurate, objectively measured, and unobtrusively collected functional balance assessment at the point-of-care or home environment. It also provided clinicians and elderly with stable and sensitive biomarkers for long-term monitoring of functional balance.

Sensor-data augmentation for human activity recognition with time-warping and data masking

Human activity recognition (HAR) using an accelerometer can provide valuable information for understanding user context. Therefore, several studies have been conducted using deep learning to increase the recognition rate of activity classification. However, the existing dataset that is publicly available for HAR tasks contains limited data. Previous works have applied data augmentation methods that simply transform the entire accelerometer-signal dataset. However, the label of the augmented signal cannot be easily recognized by humans, and the augmentation methods cannot ensure that the label of the signal is preserved. Therefore, we propose a novel data augmentation method that reflects the characteristics of the sensor signal and can preserve the label of the augmented signal by generating partially occluded data of the accelerometer signals. To generate the augmented data, we apply time-warping, which deforms the time-series data in the time direction. We handle jittering effects and subsequently apply data masking to drop out a part of the input signals. We compare the performance of the proposed augmentation method with that of conventional methods by using two public datasets and an activity recognition model based on convolutional neural networks. The experimental results show that the proposed augmentation method improves the recognition rate of the activity classification model, regardless of the dataset. Additionally, the proposed method shows superior performance over conventional methods on the two datasets.

Assessment of trunk flexion in arm reaching tasks with electromyography and smartphone accelerometry in healthy human subjects

Trunk stability is essential to maintain upright posture and support functional movements. In this study, we aimed to characterize the muscle activity and movement patterns of trunk flexion during an arm reaching task in sitting healthy subjects and investigate whether trunk stability is affected by a startling acoustic stimulus (SAS). For these purposes, we calculated the electromyographic (EMG) onset latencies and amplitude parameters in 8 trunk, neck, and shoulder muscles, and the tilt angle and movement features from smartphone accelerometer signals recorded during trunk bending in 33 healthy volunteers. Two-way repeated measures ANOVAs were applied to examine the effects of SAS and target distance (15 cm vs 30 cm). We found that SAS markedly reduced the response time and EMG onset latencies of all muscles, without changing neither movement duration nor muscle recruitment pattern. Longer durations, higher tilt angles, and higher EMG amplitudes were observed at 30 cm compared to 15 cm. The accelerometer signals had a higher frequency content in SAS trials, suggesting reduced movement control. The proposed measures have helped to establish the trunk flexion pattern in arm reaching in healthy subjects, which could be useful for future objective assessment of trunk stability in patients with neurological affections.

ДИАГНОСТИРОВАНИЕ МНОГОКАНАЛЬНОЙ ИЗМЕРИТЕЛЬНОЙ СИСТЕМОЙ С ГИБКОЙ СТРУКТУРОЙ ФОРСУНОК ФИРМЫ BOSCH

At the CR-Jet 4E stand, the vibroacoustic signals of BOSCH injectors were studied using a multichannel system with a flexible structure in the BGATU Educational Institution. They were processed in the Mathcad system with spectral analysis and wavelet transformations in MATLAB programs. (Research purpose) The research purpose is in analyzing the vibration characteristics of BOSCH injectors, identifying possible malfunctions and predict their service life. (Materials and methods) The article presents testing results of a new and working nozzle at an injection pressure of 158, 200 and 1000 bar. In five tests it were used the MPU6050 vibration sensors, the INMP621 microphone, and the temperature sensor. The vibration signals were displayed along the xyz axes according to the amplitude-frequency response with the Fourier transform. (Results and discussion) The article presents graphs of wavelet transformations and amplitude-frequency characteristics from five binary files of accelerometer signals and sound files of injectors. The article presents the accelerometer signals on the y-axis at the top of the graphs, the spectrum of their constancy in the middle, and the scalogram at the bottom. For worn-out injectors, the spectrum of constancy is less expressed, the main signal peaks are in the frequencies of 150 and 300 hertz, they are less than in the new nozzle, and the amplitudes are higher up to 800 units. For the new nozzle, the uniform peaks are less than 200 units. The acoustic amplitude of the worn–out nozzle is 150 units, and the new one at frequencies up to 250 hertz is up to 120 units. (Conclusion) Studies of BOSCH injectors with signal processing in the Mathcad system, followed by spectral analysis and wavelet transformations using the MATLAB software package, have shown that the worn-out injectors are characterized by a less expressed spectrum of oscillation constancy. The research goals have not been achieved, but they deepen the traditional diagnosis.

The statistical properties of raw knock signal time histories

Traditional processing of knock signals reduces each recorded time history to a single scalar knock intensity metric for each engine firing, thereby losing all information relating to the phasing and evolution of knock over the combustion period. In this work, a statistical analysis of raw knock cylinder pressure and accelerometer signal time histories has been performed showing how the nonstationary stochastic characteristics of these signals evolve as a function of crank angle, and as a function of spark timing. The data are shown to closely approximate a cyclically independent process whose 2-dimensional covariance function captures both the non-stationary deterministic processes taking place within a cycle as well as the stationary random variations from one cycle to the next. A (time-varying) dual-Gaussian model for the distribution of these cyclic variations was fitted to the data, thereby enabling them to be characterized as the sum of knocking and non-knocking populations. The parameters of the model, which describe these populations separately, provide further empirical insight into the knock process.

Clustering of Experimental Seismo-Acoustic Events Using Self-Organizing Map (SOM)

The analogue experiments that produce seismo-acoustic events are relevant for understanding the degassing processes of a volcanic system. The aim of this work is to design an unsupervised neural network for clustering experimental seismo-acoustic events in order to investigate the possible cause-effect relationships between the obtained signals and the processes. We focused on two tasks: 1) identify an appropriate strategy for parameterizing experimental seismo-acoustic events recorded during analogue experiments devoted to the study of degassing behavior at basaltic volcanoes; 2) define the set up of the selected neural network, the Self-Organizing Map (SOM), suitable for clustering the features extracted from the experimental events. The seismo-acoustic events were generated using an ad hoc experimental setup under different physical conditions of the analogue magma (variable viscosity), injected gas flux (variable flux velocity) and conduit surface (variable surface roughness). We tested the SOMs ability to group the experimental seismo-acoustic events generated under controlled conditions and conduit geometry of the analogue volcanic system. We used 616 seismo-acoustic events characterized by different analogue magma viscosity (10, 100, 1000 Pa s), gas flux (5, 10, 30, 60, 90, 120, 150, 180 × 10−3 l/s) and conduit roughness (i.e. different fractal dimension corresponding to 2, 2.18, 2.99). We parameterized the seismo-acoustic events in the frequency domain by applying the Linear Predictive Coding to both accelerometric and acoustic signals generated by the dynamics of various degassing regimes, and in the time domain, applying a waveform function. Then we applied the SOM algorithm to cluster the feature vectors extracted from the seismo-acoustic data through the parameterization phase, and identified four main clusters. The results were consistent with the experimental findings on the role of viscosity, flux velocity and conduit roughness on the degassing regime. The neural network is capable to separate events generated under different experimental conditions. This suggests that the SOM is appropriate for clustering natural events such as the seismo-acoustic transients accompanying Strombolian explosions and that the adopted parameterization strategy may be suitable to extract the significant features of the seismo-acoustic (and/or infrasound) signals linked to the physical conditions of the volcanic system.

Efficient embedded sleep wake classification for open-source actigraphy

This study presents a thorough analysis of sleep/wake detection algorithms for efficient on-device sleep tracking using wearable accelerometric devices. It develops a novel end-to-end algorithm using convolutional neural network applied to raw accelerometric signals recorded by an open-source wrist-worn actigraph. The aim of the study is to develop an automatic classifier that: (1) is highly generalizable to heterogenous subjects, (2) would not require manual features’ extraction, (3) is computationally lightweight, embeddable on a sleep tracking device, and (4) is suitable for a wide assortment of actigraphs. Hereby, authors analyze sleep parameters, such as total sleep time, waking after sleep onset and sleep efficiency, by comparing the outcomes of the proposed algorithm to the gold standard polysomnographic concurrent recordings. The relatively substantial agreement (Cohen’s kappa coefficient, median, equal to 0.78 ± 0.07) and the low-computational cost (2727 floating-point operations) make this solution suitable for an on-board sleep-detection approach.

ДИАГНОСТИРОВАНИЕ МНОГОКАНАЛЬНОЙ ИЗМЕРИТЕЛЬНОЙ СИСТЕМОЙ С ГИБКОЙ СТРУКТУРОЙ ФОРСУНОК ФИРМЫ BOSCH

At the CR-Jet 4E stand, the vibroacoustic signals of BOSCH injectors were studied using a multichannel system with a flexible structure in the BGATU Educational Institution. They were processed in the Mathcad system with spectral analysis and wavelet transformations in MATLAB programs. (Research purpose) The research purpose is in analyzing the vibration characteristics of BOSCH injectors, identifying possible malfunctions and predict their service life. (Materials and methods) The article presents testing results of a new and working nozzle at an injection pressure of 158, 200 and 1000 bar. In five tests it were used the MPU6050 vibration sensors, the INMP621 microphone, and the temperature sensor. The vibration signals were displayed along the xyz axes according to the amplitude-frequency response with the Fourier transform. (Results and discussion) The article presents graphs of wavelet transformations and amplitude-frequency characteristics from five binary files of accelerometer signals and sound files of injectors. The article presents the accelerometer signals on the y-axis at the top of the graphs, the spectrum of their constancy in the middle, and the scalogram at the bottom. For worn-out injectors, the spectrum of constancy is less expressed, the main signal peaks are in the frequencies of 150 and 300 hertz, they are less than in the new nozzle, and the amplitudes are higher up to 800 units. For the new nozzle, the uniform peaks are less than 200 units. The acoustic amplitude of the worn-out nozzle is 150 units, and the new one at frequencies up to 250 hertz is up to 120 units. (Conclusion) Studies of BOSCH injectors with signal processing in the Mathcad system, followed by spectral analysis and wavelet transformations using the MATLAB software package, have shown that the worn-out injectors are characterized by a less expressed spectrum of oscillation constancy. The research goals have not been achieved, but they deepen the traditional diagnosis.

Classification of the Korean Sign Language Alphabet Using an Accelerometer with a Support Vector Machine

Recognition and understanding of sign language can aid communication between nondeaf and deaf people. Recently, research groups have developed sign language recognition algorithms using multiple sensors. However, in everyday life, minimizing the number of sensors would still require the use of a sign language interpreter. In this study, a sign language classification method was developed using an accelerometer to recognize the Korean sign language alphabet. The accelerometer is worn on the proximal phalanx of the index finger of the dominant hand. Triaxial accelerometer signals were used to segment the sign gesture (i.e., the time period when a user is performing a sign) and recognize the 31 Korean sign language letters (producing a chance level of 3.2%). The vector sum of the accelerometer signals was used to segment the sign gesture with 98.9% segmentation accuracy, which is comparable to that of previous multisensor systems (99.49%). The system was able to classify the Korean sign language alphabet with 92.2% accuracy. The recognition accuracy of this approach was found to be higher than that of a previous work in the same sign language alphabet classification task. The findings demonstrate that a single‐sensor accelerometer with simple features can be reliably used for Korean sign language alphabet recognition in everyday life.