Wyniki wyszukiwania - BazTech

1

Deep learning and machine learning techniques to improve hand movement classification in myoelectric control system

Rajapriya R., Rajeswari K., Thiruvengadam S. J.

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 2

554--571

EN

A robust myoelectric control system (MCS) is essential for the design of electromyography (EMG) based human–machine interface (HMI) designs such as prosthetics, exoskeleton, wheelchair and humanoid robots. The functionality of the current pattern recognition (PR) technique in MCS is limited by factors such as variation in the user’s limb position. To overcome the effect of this dynamic variation, an invariant higher order statistics – frequency domain feature set (HOS-FD) is proposed in this paper. EMG data from eight hand movements in five limb positions are considered. When trained with three limb position data, the HOS-FD with three hidden layers deep neural network (DNN) achieved a significantly high classification accuracy of 97.84%±0.22 compared to other classifiers viz., single layer artificial neural network (ANN), linear discriminant analysis (LDA), support vector machine (SVM), k nearest neighbor (kNN), decision tree (DT) and Naive Bayes (NB) classifiers with accuracies of 94.11%±1.63, 95.02%±1.89, 94.63%±2.33, 90.05 ± 4.11, 86.66 ± 4.72 and 78.78%±5.02 respectively. Further, when trained with data from all five limb positions, the proposed feature set with DNN had an accuracy of 99.16%±0.14. The statistical significance of the high classification accuracy obtained using the proposed feature set is also proven using multiple analysis of variance tests (p < 0.001). These results indicate that the proposed method is a promising technique for HMI.

2

The fractional Fourier transform as a biomedical signal and image processing tool: A review

Gómez-Echavarría Alejandro, Ugarte Juan P., Tobón Catalina

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

1081--1093

EN

This work presents a literature review of the fractional Fourier transform (FrFT) investiga-tions and applications in the biomedical field. The FrFT is a time-frequency analysis tool that has been used for signal and image processing due to its capability in capturing the nonstationary characteristics of real signals. Most biomedical signals are an example of such non-stationarity. Thus, the FrFT-based solutions can be formulated, aiming to enhance the health technology. As the literature review indicates, common applications of the FrFT involves signal detection, filtering and features extraction. Establishing adequate solutions for these tasks requires a proper fractional order estimation and implementing the suitable numeric approach for the discrete FrFT calculation. Since most of the reports barely describe the methodology on this regard, it is important that future works include detailed information about the implementation criteria of the FrFT. Although the applications in biomedical sciences are not yet among the most frequent FrFT fields of action, the growing interest of the scientific community in the FrFT, supports its practical usefulness for developing new biomedical tools.

3

Fusing fine-tuned deep features for recognizing different tympanic membranes

Cömert Zafer

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

40--51

EN

Otitis media (OM) refers to a group of inflammatory diseases regarding the middle ear. Although there are a wide variety of disease types regarding OM, the most commonly seen disorders are acute otitis media (AOM), otitis media with effusion (OME) and chronic suppurative otitis media (CSOM). The examination of OM in the clinics is realized subjec-tively. This subjective examination is error-prone and leads to a limited variability among specialist. For these reasons, computer-aided systems are in demand. In this study, we focus on recognizing normal, AOM, CSOM, and earwax tympanic membrane (TM) conditions using fused fine-tuned deep features provided by pre-trained deep convolutional neural networks (DCNNs). These features are applied as the input to several networks, such as an artificial neural network (ANN), k-nearest neighbor (k NN), decision tree (DT) and support vector machine (SVM). Moreover, we release a new publicly available TM data set consisting of totally 956 otoscope images. As a result, the DCNNs yielded promising results. Especially, the most efficient results were provided by VGG-16 with an accuracy of 93.05 %. The fused fine-tuned deep features improved the overall classification success. Finally, the proposed model yielded promising results with an accuracy of 99.47 %, sensitivity of 99.35 %, and specificity of 99.77 % using the combination of the fused fine-tuned deep features and SVM model. Consequently, this study shows that fused fine-tuned deep features are rather useful in recognizing different TMs and these features can provide a fully automated model with high sensitivity.

4

Model of CTG aparatus in LabVIEW environment

Gumkowski P., Lecewicz W., Surtel W.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2016

|

nr 3

75--78

EN

Cardiotocography is now a standard procedure determining the well-being of the fetus. In today's increasing popularity of IoT, there is a need for solutions providing mobility, while maintaining reliability. The article presents the methodology of creating CTG apparatus model, which enables filtration and detection of the basic parameters of the examination.

PL

Kardiotokografia jest obecnie standardowym badaniem określającym dobrostan płodu. W dobie coraz większej popularności IoT potrzeba rozwiązań zapewniających mobilność, przy jednoczesnym zachowaniu niezawodności. Artykuł przedstawia metodykę tworzenia modelu aparatu KTG, który umożliwia filtrację, oraz detekcję podstawowych parametrów badania.

5

Zastosowania analizy ruchu oczu w diagnostyce chorób neurodegeneracyjnych

Borys M.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2015

|

nr 2

55--63

PL

Badania okulograficzne są nieinwazyjne, a sprzęt okulograficzny coraz bardziej dostępny, dlatego też rośnie jego popularność w diagnostyce medycznej oraz innych obszarach zastosowań. Artykuł prezentuje możliwości dotyczący zastosowania badań okulograficznych w diagnostyce chorób neurodegeneracyjnych takich jak Parkinson, czy Alzheimer. Autorka koncentruje się na przestawieniu charakterystyki badania okulograficznego, modelu detekcji podstawowych zdarzeń takich jak fiksacje i sakkady, a także na przykładach badań zaburzeń okoruchowych w wybranych chorobach neurodegeneracyjnych.

EN

Eye-tracking allows for non-invasive examination and the same eyetrackers are becoming more available, thus its popularity in medical diagnosis and other fields of application is increasing. The paper presents the possibilities for using eye-tracking in the diagnosis neurodegenerative disease such as Parkinson or Alzheimer diseases. The autor describes the exetracking experiment, the model of fixations and saccedes detection, as well as the selected examples of eye-tracking research conducted among patients with neurodegenerative diseases.

6

Posturographic methods for body posture symmetry assessment

Łukaszewicz T., Kania D., Kidoń Z., Pethe-Kania K.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2015

|

Vol. 63, nr 4

907--917

EN

The article presents a number of posturographic methods enabling objective postural symmetry assessment in patients undergoing rehabilitation after total hip replacement surgery. The key goal of such rehabilitation is fast restoration of a proper body weight distribution. The postural symmetry measures proposed in the article enable generalized quantification of the CoP (Center of Pressure) trajectories measured during standard static posturography diagnostics and the so-called follow-up posturography examination. The follow-up posturography is a relatively new but promising method of physical rehabilitation. All of the herein discussed posturographic measures have been designed specifically to quantify postural symmetry either in a standing and relaxed upright position, in the absence of any deterministic external stimulation (static posturography) or in the presence of a visual biofeedback stimulation enforcing the coordinated slow swaying movements of the body (the follow-up posturography). The experimental results presented in this paper constitute the outcome of the long-term cooperation between the Institute of Electronics of the Silesian University of Technology and the Silesian Rheumatology and Rehabilitation Hospital. The usefulness of the proposed postural symmetry measures has been verified in a series of clinical trials carried out in a selected group of patients undergoing rehabilitation after total hip replacement surgery.

7

Ocena symetrii postawy w teście stabilografii nadążnej

Łukaszewicz Т., Kania D., Kidoń Z., Pethe-Kania K.

Elektronika : konstrukcje, technologie, zastosowania

|

2014

|

Vol. 55, nr 1

51-54

PL

W artykule przedstawiono metodę oceny symetrii postawy wykorzystującą stabilografię ze wzrokowym sprzężeniem zwrotnym – zwaną stabilografią nadążną. Parametrami określającymi stopień symetrii są odchylenia standardowe składowych х, у różnicy nadążnej trajektorii stabilograficznej zarejestrowanej dla lewoskrętnego bodźca wzrokowego i odbicia lustrzanego względem osi rzędnych trajektorii nadążnej zmierzonej dla bodźca prawoskrętnego.

EN

The paper presents a method for postural symmetry assessment utilizing posturographic examination with visual feedback stimulation, known as the follow-up posturography. Parameters quantifying the degree of symmetry are the standard deviations of x, у components of a difference signal obtained from subtracting the mirror image of the follow-up trajectory acquired for clockwise visual stimulation, with Y being the axis of reflection, from the follow-up trajectory measured during the counterclockwise visual stimulation.

8

Critical exponent analysis applied to surface EMG signals for multifunction myoelectric control

Phinyomark A., Phothisonothai M., Phukpattaranont P., Limsakul C.

Metrology and Measurement Systems

|

2011

|

Vol. 18, nr 4

645-658

EN

Based on recent advances in non-linear analysis, the surface electromyography (sEMG) signal has been studied from the viewpoints of self-affinity and complexity. In this study, we examine usage of critical exponent analysis (CE) method, a fractal dimension (FD) estimator, to study properties of the sEMG signal and to deploy these properties to characterize different movements for gesture recognition. SEMG signals were recorded from thirty subjects with seven hand movements and eight muscle channels. Mean values and coefficient of variations of the CE from all experiments show that there are larger variations between hand movement types but there is small variation within the same type. It also shows that the CE feature related to the self-affine property for the sEMG signal extracted from different activities is in the range of 1.855∼2.754. These results have also been evaluated by analysis-of-variance (p-value). Results show that the CE feature is more suitable to use as a learning parameter for a classifier compared with other representative features including root mean square, median frequency and Higuchi's method. Most p-values of the CE feature were less than 0.0001. Thus the FD that is computed by the CE method can be applied to be used as a feature for a wide variety of sEMG applications.

9

Independent component analysis and adaptive filtering as successful tools for an improvement of normogastric rhythm extraction in electrogastrographic signals

Tkacz E., Mika B.

Journal of Medical Informatics & Technologies

|

2010

|

Vol. 16

27--34

EN

The aim of this study was to investigate the possibility of combining two methods: Independent Component Analysis (ICA) and Adaptive Signal Enhancement for the improvement of normogastric rhythm extraction from multichannel recording of electrogastrographic signals (EGG). Unfortunately the electrogastrogram, is a transcutaneous measurement of gastric electrical activity, does not contain pure signal but usually is a sort of mixture from both electrical activity of stomach as well as other organs surrounding it and random noise. In order to benefit the diagnostic power of multichannel recording of EGG, which can provide deeper understanding of gastric disorders, it is necessity to extract gastric slow wave in each channel. One of the parameters, which are analyzed and require proper registration is so called normogastric rhythm. According to the literature, the normogastric rhythm should cover around 70% of rhythmic behavior of signal for a healthy man. Proper extraction of basic 3-cpm normogastric rhythm in each channel is a subject of this paper. Independent Component Analysis is applied for extracting the reference signal for adaptive filtering what next result in obtaining less contaminated signal in each channel. Analysis has been perform for two postprandial phases with five minutes break between them. In both mention cases proposed procedure gives a promising results.

10

Nowe metody pomiaru i analizy patologicznego drżenia kończyn górnych

Izworski A., Michałek M., Rudzińska M.

Bio-Algorithms and Med-Systems

|

2005

|

Vol. 1, no. 1/2

297--300

PL

Patologiczne drżenia ludzkiego ciała objawiają się rytmicznym i naprzemiennym skurczem mięśni, co w głównej mierze jest następstwem tzw. chorób pozapiramidowych, do których należy choroba Parkinsona. Efektem zaburzeń w PD jest drżenie niektórych części ciała, w dominującej zaś części okolic twarzy, barku i kończyn górnych. Obecne metody pomiarowe tego typu drżenia, wykorzystujące głównie tablety cyfrowe jako urządzenia peryferyjne komputera, umożliwiając akwizycję danych z dwuwymiarowej powierzchni i dodatkowej informacji w postaci nacisku, nie potrafią wiernie zarejestrować swobodnych drgań parkinsonowskich. Biorąc pod uwagę konieczność pomiaru wszystkich cech choroby, zdecydowano się na projekt nowej, całkowicie nieinwazyjnej metody z wykorzystaniem kamer cyfrowych i punktowych źródeł światła umieszczonych bezpośrednio na badanym i będącym w ruchu obiekcie.

EN

Pathological tremor of human body manifests itself by periodic, alternating muscle contractions, and is mainly caused by the so-called extra-pyramidal disorders, including Parkinson's disease. The paper describes a 3D method for measurement and visualization of upper limbs tremor, making use of digital camcorders for registration of moving point light sources. The measurement is performed separately for the three principal planes of the Cartesian coordinate system. The present work contains a description of the measurement stand and measurement method, the obtained results, and the prospects for application of the method helpful in medical diagnosis. In the long term prospect the described method will assist in examinations and evaluation of the upper limbs tremor in patients with Parkinson's disease. The presented method of tremor measurement considerably enhances the currently applied acquisition techniques, which usually reduce the measurement space to 2D.

11

Wireless transmission of photoplethysmographic signals

Hulewicz A., Cysewska-Sobusiak A., Boltrukiewicz M.

Elektronika : konstrukcje, technologie, zastosowania

|

2004

|

Vol. 45, nr 8-9

142-145

EN

A system that allows wireless transmitting photoplethysmographic signals (PPG signals) with the use of the GPRS network has been performed. The examined analog pulse waveforms were converted to digital signals and delivered to a transceiver RS232C-GPRS. Selected examples of results, which were obtained during investigations made on a number of real PPG signals, are presented.

PL

Zaproponowano system do transmisji sygnału fotopletyzmograficznego (PPG) drogą bezprzewodową z wykorzystaniem sieci GPRS. Badane przebiegi fali tętna, po przetworzeniu na postać cyfrową, są przesyłane do transceivera RS232C-GPRS. Przedstawione wyniki przykładowych transmisji otrzymano podczas badań dotyczących rzeczywistych przebiegów fali tętna.