Wszystkie pola: inertial sensor

Skocz do pozycji: 1.

Tytuł:: Recognition of sports exercises using inertial sensor technology
Autorzy:: Krutz, Pascal
Rehm, Matthias
Schlegel, Holger
Dix, Martin
Tematy:: human activity recognition
machine learning
neural networks
classifier; Pokaż więcej
Wydawca:: Polskie Towarzystwo Promocji Wiedzy
Powiązania:: https://bibliotekanauki.pl/articles/30148258.pdf Link otwiera się w nowym oknie
Opis:: Supervised learning as a sub-discipline of machine learning enables the recognition of correlations between input variables (features) and associated outputs (classes) and the application of these to previously unknown data sets. In addition to typical areas of application such as speech and image recognition, fields of applications are also being developed in the sports and fitness sector. The purpose of this work is to implement a workflow for the automated recognition of sports exercises in the Matlab® programming environment and to carry out a comparison of different model structures. First, the acquisition of the sensor signals provided in the local network and their processing is implemented. Realised functionalities include the interpolation of lossy time series, the labelling of the activity intervals performed and, in part, the generation of sliding windows with statistical parameters. The preprocessed data are used for the training of classifiers and artificial neural networks (ANN). These are iteratively optimised in their corresponding hyper parameters for the data structure to be learned. The most reliable models are finally trained with an increased data set, validated and compared with regard to the achieved performance. In addition to the usual evaluation metrics such as F1 score and accuracy, the temporal behaviour of the assignments is also displayed graphically, allowing statements to be made about potential causes of incorrect assignments. In this context, especially the transition areas between the classes are detected as erroneous assignments as well as exercises with insufficient or clearly deviating execution. The best overall accuracy achieved with ANN and the increased dataset was 93.7 %.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 2.

Tytuł:: Rat robot motion state identification based on a wearable inertial sensor
Autorzy:: Chen, Yuxin
Xu, Haoze
Yang, Wei
Yang, Canjun
Xu, Kedi
Tematy:: inertial sensor
real-time measurement
rat robot
motion state; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Powiązania:: https://bibliotekanauki.pl/articles/1849133.pdf Link otwiera się w nowym oknie
Opis:: Rat robots have great potential in rescue and search tasks because of their excellent motion ability. However, most of the current rat-robot systems relay on human guidance due to variable voluntary motor behaviour of rats, which limits their application. In this study, we developed a real-time system to detect a rat robot’s transient motion states, as the prerequisite for further study of automatic navigation. We built the detection model by using a wearable inertial sensor to capture acceleration and angular velocity data during the control of a rat robot. Various machine learning algorithms, including Decision Trees, Random Forests, Logistic Regression, and Support Vector Machines, were employed to perform the classification of motion states. This detection system was tested in manual navigation experiments, with detection accuracy achieving 96.70%. The sequence of transient motion states could be further used as a promising reference for offline behaviour analysis.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 3.

Tytuł:: Improving Strapdown Inertial Navigation System Performance by Self-Compensation of Inertial Sensor Errors
Autorzy:: Chernyak, Mycola
Kolesnyk, Vadym
Tematy:: MEMS IMU
autonomous INS
MEMS self-compensation
rotation modulation; Pokaż więcej
Wydawca:: Sieć Badawcza Łukasiewicz - Instytut Lotnictwa
Powiązania:: https://bibliotekanauki.pl/articles/36832242.pdf Link otwiera się w nowym oknie
Opis:: Microelectromechanical systems (MEMS)-based strapdown navigation systems offer advantages such as small size, low cost and minimal power consumption. However, MEMS sensors are prone to significant low-frequency noise and poor bias repeatability, which can lead to navigational errors over time. These errors make them unsuitable for autonomous navigation applications, even with frequent recalibration. One way in which to solve this problem is by using the rotation modulation (RM) method. This approach is widely recognised but has only been successful with precise laser and fiber optic gyroscopes equipped with precise rotating platforms. This article focuses on the potential of adapting the RM method for the case of inexpensive MEMS sensors that can significantly improve navigation performance, while maintaining the benefits of microelectromechanical technologies. Potential issues of implementation were discussed, and corresponding requirements were formulated. The proposed optimal computation scheme was verified during static tests of the developed inertial measurement unit (IMU). Further steps in studying the adaptation of the RM method for MEMS sensors have also been outlined.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 4.

Tytuł:: Rozpoznawanie gestów z wykorzystaniem czujników inercyjnych o 9 stopniach swobody
Gesture recognition based on 9DOF inertial sensor
Autorzy:: Barczewska, K.
Drozd, A.
Folwarczny, Ł.
Tematy:: rozpoznawanie gestów
czujnik inercyjny
DTW
gesture recognition
inertial sensor; Pokaż więcej
Wydawca:: Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Powiązania:: https://bibliotekanauki.pl/articles/155769.pdf Link otwiera się w nowym oknie
Opis:: Rozpoznawanie gestów za pomocą czujników inercyjnych może być alternatywą dla standardowych interfejsów człowiek-komputer. Do śledzenia gestów wykorzystano czujnik zawierający trójosiowy akcelerometr, magnetometr i żyroskop. W dotychczasowych badaniach bazowano na sygnałach przyspieszenia. Autorzy zaproponowali i porównali rozwiązania wykorzystujące zarówno analizę przyspieszenia, jak i orientacji w przestrzeni, a także umożliwili badanym osobom wykonywanie gestów w sposób naturalny. Wyniki pokazują, że za pomocą algorytmu DTW (Dynamic Time Warping) możliwa jest klasyfikacja indywidualna dla danej osoby (ze skutecznością 92%), a także klasyfikacja uogólniona - na podstawie uniwersalnego wzorca (ze skutecznością 83%).
Gesture recognition may be applied to control of computer applica-tions and electronic devices as an alternative to standard human-machine interfaces. This paper reports a method of gesture classification based on analysis of data from 9DOF inertial sensor - NEC-TOKIN, Motion Sensor MDP-A3U9S (Fig.1). Nine volunteers were asked to perform 10 different gestures (shown in Fig.2) in a natural way with a sensor attached to their hand. The gesture data base consisting of 2160 files with triaxial acceleration and orientation signals was created. In the first step the data were divided into training and testing sets. The designed system uses the Dynamic Time Warping (DTW) algorithm to calculate similarity of signals (formulas (1)-(3)). Using this method the authors chose representative signals to indi-vidual and generalized exemplars data base from the training set. The DTW algorithm was also used in the classification process. Different recognition approaches were tested basing on acceleration-only, orientation-only and acceleration-orientation signals. The results listed in Tab.4 show that the best recognition efficiency of 92% was obtained in the individual recognition (only one person gestures taken into account) for modified exemplars data base. The modification proposed by the authors (Section 3) improved the recognition rate by 10 percentage points. The efficiency rate of 83% (Tab. 5) was reached in the generalized case. The next step of im-proving the designed recognition system is application of an inertial system with a bluetooth module and real-time gesture classification.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 5.

Tytuł:: Absolute and relative reliability of several measures of static postural stability calculated using a GYKO inertial sensor system
Autorzy:: Jaworski, Janusz
Ambroży, Tadeusz
Lech, Grzegorz
Spieszny, Michał
Bujas, Przemysław
Żak, Michał
Chwała, Wiesław
Tematy:: balance
postural stability
accelerometer
test-retest reliability
intraclass correlation coefficient
balans
stabilność postawy
akcelerometr
niezawodność testu-retestu
współczynnik korelacji wewnątrzklasowej; Pokaż więcej
Wydawca:: Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
Powiązania:: https://bibliotekanauki.pl/articles/27324151.pdf Link otwiera się w nowym oknie
Opis:: The aim of this study was to analyse absolute and relative reliability of a number of postural static stability measures obtained from a GYKO inertial sensor system in young adults. Methods: The study examined 29 healthy non-athlete young adults. A test was performed for 30 s while standing on one foot, without moving, with eyes open and arms relaxed along the sides of the body. The examinations were performed twice, with a one-week interval. Relative reliability was measured using the intraclass correlation coefficient (ICC) and the 95% confidence interval (95% CI), whereas the absolute reliability was evaluated based on the standard error of measurement (SEM) and the minimal detectable change (MDC). Results: The results of this study showed moderate to good relative reliability scores for all the postural stability measures, with ICC values ranging from 0.62 to 0.70. For most of the analysed variables, SEM% ranged from ca. 10 to 14%. Relatively high SEM% values were obtained only for two variables (Area, Convex Hull Area). Conclusions: The low costs of GYKO inertial sensor systems, the fast and easy installation, the mobility and high reliability of the measurement of postural stability show that it can be effective alternative to stabilographic platforms.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 6.

Tytuł:: A feedback weighted fusion algorithm with dynamic sensor bias correction for gyroscope array
Autorzy:: Yuan, Ding
Qin, Yongyuan
Shen, Xiaowei
Wu, Zongwei
Tematy:: inertial sensor
gyroscope array
weighted fusion
bias correction; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Powiązania:: https://bibliotekanauki.pl/articles/1848956.pdf Link otwiera się w nowym oknie
Opis:: Low-cost Micro-Electromechanical System (MEMS) gyroscopes are known to have a smaller size, lower weight, and less power consumption than their more technologically advanced counterparts. However, current low-grade MEMS gyroscopes have poor performance and cannot compete with quality sensors in high accuracy navigational and guidance applications. The main focus of this paper is to investigate performance improvements by fusing multiple homogeneous MEMS gyroscopes. These gyros are transformed into a virtual gyro using a feedback weighted fusion algorithm with dynamic sensor bias correction. The gyroscope array combines eight homogeneous gyroscope units on each axis and divides them into two layers of differential configuration. The algorithm uses the gyroscope array estimation value to remove the gyroscope bias and then correct the gyroscope array measurement value. Then the gyroscope variance is recalculated in real time according to the revised measurement value and the weighted coefficients and state estimation of each gyroscope are deduced according to the least square principle. The simulations and experiments showed that the proposed algorithm could further reduce the drift and improve the overall accuracy beyond the performance limitations of individual gyroscopes. The maximum cumulative angle error was -2.09 degrees after 2000 seconds in the static test, and the standard deviation (STD) of the output fusion value of the proposed algorithm was 0.006 degrees/s in the dynamic test, which was only 1.7% of the STD value of an individual gyroscope.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 7.

Tytuł:: Badanie czujników inercjalnych z wykorzystaniem metody analizy widmowej
Testing inertial sensors with use of the spectral analysis method
Autorzy:: Paszek, J.
Kaniewski, P.
Tematy:: sensor inercjalny
zakłócenia losowe
gęstość widmowa mocy
inertial sensor
random noise
power spectral density; Pokaż więcej
Wydawca:: Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Powiązania:: https://bibliotekanauki.pl/articles/156707.pdf Link otwiera się w nowym oknie
Opis:: W artykule przedstawiono wyniki badań losowych zakłóceń pomiarów czujników inercjalnych z wykorzystaniem metody analizy widmowej. Do uzyskania wyników wykorzystano metodę analizy Gęstości Widmowej Mocy (GWM) sygnału z czujnika w celu wyznaczenia charakterystyk źródeł zakłóceń. Przedstawione zostały wyniki badań eksperymentalnych oraz ich porównanie z wynikami uzyskanymi metodą wariancji Allana (AV). Na koniec dokonano porównania wyników graficznej interpretacji krzywych GWM i AV analizowanych danych.
The accuracy of Inertial Navigation Systems (INS) is limited by the performance of used inertial sensors. The measurement precision of gyroscopes and accelerometers is limited due to systematic and random errors. The systematic errors are deterministic and can be easily removed from measurements using mathematical modeling and calibration. The origin of the random errors is electronic noise which interferes in the full measurement spectrum. Thus, this error cannot be fully removed from the acquired data using filtering. Estimation of the random noise errors can be done using Power Spectral Density (PSD) or Allan Variance (AV) method [1, 2, 4, 6]. Both methods are used to decompose noise to its basic sources described by the power spectral model 1/fn [2, 3]. In this paper, the estimation of random noises using the PSD method is shown. The error model used for sensor analysis and the methodology of experiment are described. The spectral analysis of the random errors of the inertial sensors allows comparing the performance of the sensors made in different technologies i.e. microelectro-mechanical gyroscopes (MEMS) and fiber optic gyroscopes (FOG). The PSD and AV methods give information about noise sources which can be used to model and simulate the inertial sensors noise.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 8.

Tytuł:: Modelling of Influence of Hypersonic Conditions on Gyroscopic Inertial Navigation Sensor Suspension
Autorzy:: Korobiichuk, I.
Karachun, V.
Mel'nick, V.
Kachniarz, M.
Tematy:: hypersonic technologies
gimbals
oscillation modes
acoustic transparency
navigation system; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Powiązania:: https://bibliotekanauki.pl/articles/221303.pdf Link otwiera się w nowym oknie
Opis:: The upcoming hypersonic technologies pose a difficult task for air navigation systems. The article presents a designed model of elastic interaction of penetrating acoustic radiation with flat isotropic suspension elements of an inertial navigation sensor in the operational conditions of hypersonic flight. It has been shown that the acoustic transparency effect in the form of a spatial-frequency resonance becomes possible with simultaneous manifestation of the wave coincidence condition in the acoustic field and equality of the natural oscillation frequency of a finite-size plate and a forced oscillation frequency of an infinite plate. The effect can lead to additional measurement errors of the navigation system. Using the model, the worst and best case suspension oscillation frequencies can be determined, which will help during the design of a navigation system.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 9.

Tytuł:: Weryfikacja pomiarowa wyników badań symulacyjnych modelu czujnika inercyjnego o zmiennej dynamice
Laboratory testing of electronic model of inertial sensor with variable parameter to verify results of its simulation analysis
Autorzy:: Sidor, T.
Żegleń, T.
Tematy:: symulacja
czujnik o zmiennej dynamice
korekcja
simulation
sensor with variable parameter
correction; Pokaż więcej
Wydawca:: Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Powiązania:: https://bibliotekanauki.pl/articles/157242.pdf Link otwiera się w nowym oknie
Opis:: Niektóre czujniki np. temperatury z zadowalającą dokładnocią przybliża się modelem inercyjnym pierwszego rzędu. Jeśli czujnik taki pracuje w zmiennych warunkach wymiany ciepła, jego model musi uwzględniać zależność parametrów dynamicznych od niezależnych, zmiennych w czasie wielkości. Dla wykonania badań symulacyjnych systemów pracujących w takich warunkach zbudowano odpowiedni model czujnika. Przeprowadzono również badania eksperymentalne mające na celu stwierdzenie czy możliwa jest praktyczna realizacja takiego modelu i zastosowanie go w komputerowym systemie korekcji "w ciemno" [1] właściwości dynamicznych czujników.
The dynamics of some sensors i.e. temperature sensors can be satisfactorily described by model of inertial system of first order. If such a sensor operates in variable heat transfer condition its model parameter must be made dependent on it. For research purposes of such system the suitable electronic model of the sensor has been designed and tested by simulation. The real circuit experiments have been also carried on to verify whether the practical use of the electronic model is possible, and whether it can be employed in a computer system of "blind correction" of sensor dynamic errors.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 10.

Tytuł:: Pomiary kątów ugięcia kończyny w stawie z wykorzystaniem inercyjnego systemu Motion Capture
Measurements of bend angles of the limb in a joint with the use of an inertial motion capture system
Autorzy:: Kopniak, P.
Tematy:: rejestracja ruchu
grafika 3D
animacja
rehabilitacja
czujnik inercyjny
motion capture
3D graphics
animation
rehabilitation
inertial sensor; Pokaż więcej
Wydawca:: Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Powiązania:: https://bibliotekanauki.pl/articles/152530.pdf Link otwiera się w nowym oknie
Opis:: Artykuł dotyczy zastosowań systemu rejestracji ruchu wykorzystującego inercyjne czujniki MEMS do badań aparatu ruchu człowieka. Badania tego typu umożliwią dokładniejsze diagnozy ortopedyczne oraz weryfikację postępów rehabilitacji. W artykule opisano budowę, właściwości i zasadę działania systemu Xsens Xbus Kit opartego na czujnikach MTx, metody wyznaczania kąta ugięcia kończyny w stawie na podstawie danych otrzymywanych z czujników oraz przykładowe wyniki badań ruchliwości kończyny. W artykule zawarto także badania dokładności pomiaru kątów poprzez czujniki MTx.
This paper concerns applications of a motion capture system based on MEMS inertial sensors to research of the human locomotion system. Such research will enable more accurate diagnosis and verification of progress of orthopedic rehabilitation. The aper describes the construction, properties and the principle of operation of the Xsens Xbus Kit based on MTx sensors (Fig. 1). It depicts the method of determining the angle of bend of the limb in a joint on the basis of data received from the sensors and sample results of the mobility of the limb, too. Each sensor of Xbus Kit system includes an integrated three-axis accelerometer, gyroscope and magnetometer. In addition, inside there is a signal processor that uses several profiles for the Kalman filter (Fig. 2). As a result, the sensors can return raw or processed data of acceleration or the Euler angles describing the orientation of the sensor in 3D space [7]. The research described in the paper deals with the measurement of the angle of band of the elbow. To measure the band of limb in the joint is sufficient to calculate the difference of yaw angles measured by two MTx sensors (Fig. 2). As a result of tests, the maximum error of the sensor measurement was determined. It was 1°. The sensors measured the angles accurately, consistently and done it in real time (Figs. 6 and 7). The performed studies also showed that the measurement deviations of MTx sensors did not depend on the position of the limb with the exception of the vertical orientation in which the X-axis sensor coincided with the direction of gravity. Then there is a mathematical singularity [7].
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Informacja

Wyszukujesz frazę "inertial sensor" wg kryterium: Wszystkie pola