فهرست مطالب
Journal of Medical Signals and Sensors
Volume:10 Issue: 3, Jul-Sep 2020
- تاریخ انتشار: 1399/04/26
- تعداد عناوین: 9
-
-
Pages 135-144Background
Human gait as an effective behavioral biometric identifier has received much attention in recent years. However, there are challenges which reduce its performance. In this work we aim at improving performance of gait systems under variations in view angles, which present one of the major challenges to gait algorithms.
MethodsWe propose employment of a view transformation model based on sparse and redundant (SR) representation. More specifically, our proposed method trains a set of corresponding dictionaries for each viewing angle, which are then used in identification of a probe. In particular, the view transformation is performed by first obtaining the SR representation of the input image using the appropriate dictionary, then multiplying this representation by the dictionary of destination angle to obtain a corresponding image in the intended angle.
ResultsExperiments performed using CASIA Gait Database, Dataset B, support the satisfactory performance of our method. It is observed that in most tests, the proposed method outperforms the other methods in comparison. This is especially the case for large changes in the view angle, as well as the average recognition rate.
ConclusionAcomparison with state‑of‑the‑art methods in the literature showcases the superior performance of the proposed method, especially in the case of large variations in view angle.
Keywords: Biometrics, gait analysis, human identification, sparse, redundant representation, view transformation model, view‑invariant -
Pages 145-157Background
With the increasing advancement of technology, it is necessary to develop more accurate, convenient, and cost‑effective security systems. Handwriting signature, as one of the most popular and applicable biometrics, is widely used to register ownership in banking systems, including checks, as well as in administrative and financial applications in everyday life, all over the world. Automatic signature verification and recognition systems, especially in the case of online signatures, are potentially the most powerful and publicly accepted means for personal authentication.
MethodsIn this article, a novel procedure for online signature verification and recognition has been presented based on Dual‑Tree Complex Wavelet Packet Transform (DT‑CWPT).
ResultsIn the presented method, three‑level decomposition of DT‑CWPT has been computed for three time signals of dynamic information including horizontal and vertical positions in addition to the pressure signal. Then, in order to make feature vector corresponding to each signature, log energy entropy measures have been computed for each subband of DT‑CWPT decomposition. Finally, to classify the query signature, three classifiers including k‑nearest neighbor, support vector machine, and Kolmogorov–Smirnov test have been examined. Experiments have been conducted using three benchmark datasets: SVC2004, MCYT‑100, as two Latin online signature datasets, and NDSD as a Persian signature dataset.
ConclusionObtained favorable experimental results, in comparison with literature, confirm the effectiveness of the presented method in both online signature verification and recognition objects
Keywords: Dual‑tree complex wavelet packet transform, Kolmogorov–Smirnov test, log energy entropy measure, online handwritten signature verification, signature recognition -
Pages 158-173Background
Deep learning methods have become popular for their high‑performance rate in the classification and detection of events in computer vision tasks. Transfer learning paradigm is widely adopted to apply pretrained convolutional neural network (CNN) on medical domains overcoming the problem of the scarcity of public datasets. Some investigations to assess transfer learning knowledge inference abilities in the context of mammogram screening and possible combinations with unsupervised techniques are in progress.
MethodsWe propose a novel technique for the detection of suspicious regions in mammograms that consist of the combination of two approaches based on scale invariant feature transform (SIFT) keypoints and transfer learning with pretrained CNNs such as PyramidNet and AlexNet fine‑tuned on digital mammograms generated by different mammography devices. Preprocessing, feature extraction, and selection steps characterize the SIFT‑based method, while the deep learning network validates the candidate suspicious regions detected by the SIFT method.
ResultsThe experiments conducted on both mini‑MIAS dataset and our new public dataset Suspicious Region Detection on Mammogram from PP (SuReMaPP) of 384 digital mammograms exhibit high performances compared to several state‑of‑the‑art methods. Our solution reaches 98% of sensitivity and 90% of specificity on SuReMaPP and 94% of sensitivity and 91% of specificity on mini‑MIAS.
ConclusionsThe experimental sessions conducted so far prompt us to further investigate the powerfulness of transfer learning over different CNNs and possible combinations with unsupervised techniques. Transfer learning performances’ accuracy may decrease when the training and testing images come out from mammography devices with different properties.
Keywords: lassification, computer‑assisted image processing, computing methodologies, deep learning, digital mammography -
Pages 174-184Background
Diabetes mellitus (DM) is a chronic disease that affects public health. The prediction of blood glucose concentration (BGC) is essential to improve the therapy of type 1 DM (T1DM).
MethodsHaving considered the risk of hyper‑ and hypo‑glycemia, we provide a new hybrid modeling approach for BGC prediction based on a dynamic wavelet neural network (WNN) model, including a heuristic input selection. The proposed models include a hybrid dynamic WNN (HDWNN) and a hybrid dynamic fuzzy WNN (HDFWNN). These wavelet‑based networks are designed based on dominant wavelets selected by the genetic algorithm‑orthogonal least square method. Furthermore, the HDFWNN model structure is improved using fuzzy rule induction, an important innovation in the fuzzy wavelet modeling. The proposed networks are tested on real data from 12 T1DM patients and also simulated data from 33 virtual patients with an UVa/Padova simulator, an approved simulator by the US Food and Drug Administration.
ResultsA comparison study is performed in terms of new glucose‑based assessment metrics, such as gFIT, glucose‑weighted form of ESODn (gESODn), and glucose‑weighted R2 (gR2). For real patients’ data, the values of the mentioned indices are accomplished as gFIT = 0.97 ± 0.01, gESODn = 1.18 ± 0.38, and gR2 = 0.88 ± 0.07. HDFWNN, HDWNN and jump NN method showed the prediction error (root mean square error [RMSE]) of 11.23 ± 2.77 mg/dl, 10.79 ± 3.86 mg/dl and 16.45 ± 4.33 mg/dl, respectively.
ConclusionFurthermore, the generalized estimating equation and post hoc tests show that proposed models perform better compared with other proposed methods
Keywords: Blood glucose prediction, diabetes mellitus, fuzzy rule induction, fuzzy wavelet neural network, wavelet neural network -
Pages 185-195Background
As people get older, muscles become more synchronized and cooperate to accomplish an activity, so the main purpose of this research is to determine the relationship between changes in age and the amount of muscle synergy. The presence of muscle synergies has been long considered in the movement control as a mechanism for reducing the degree of freedom of the motor system.
MethodsBy combining these synergies, a wide range of complex movements can be produced. Muscle synergies are often extracted from the electromyogram (EMG) signal. One of the most common methods for extracting synergies is the nonnegative matrix factorization. In this research, the EMG signal is obtained from individuals from different age groups (namely 15–20 years, 25–30 years, and 35–40 years), and after preprocessing, the muscular synergies are extracted. By processing and studying these synergies.
ResultsIt was observed that there is a significant difference between the muscular synergy of different age groups. Furthermore, there was a significant difference in the mean value of synergy coefficients in each group, especially in motions that were accompanied by force.
ConclusionThis result candidates this parameter as a biomarker to differentiate and recognize the effects of age on the individual’s muscular signal. In the best case, using the synergy tool, classification of the age of persons can be done by 77%
Keywords: Age groups, electromyogram, nonnegative matrix decomposition, synergy -
Pages 196-200Background
The aim of this study was to compare the image quality and radiation doses in various digital radiography systems using contrast‑detail radiography (CDRAD) phantom.
MethodsThe image quality and radiation dose for seven different digital radiography systems were compared using the CDRAD phantom. Incident air kerma (IAK) values were measured for certain exposure settings in all digital radiography systems. The images from the CDRAD phantom were evaluated by three observers. The results were displayed in the form of a contrast‑detail (CD) curve. In addition, the inverse image quality figure (IQFinv)‑to‑IAK ratios were used for quantitative comparison of different digital radiography system performance.
ResultsResults of this study showed that the CD curves cannot be suitable criterion for determining the performance of digital radiography systems. For this reason, IQFinv‑to‑radiation dose (IAK) ratios in a fixed radiation condition were used. The highest performance in terms of producing high‑quality images and low radiation dose was related to X‑ray unit 1 and the lowest performance was for X‑ray unit 5.
ConclusionThe ratio of IQFinv to IAK for performance evaluation of digital radiography systems is an innovation of this study. A digital radiography system with a higher IQFinv‑to‑IAK ratio is associated with lower patient dose and better image quality. Therefore, it is recommended to equip the new imaging centers with the systems that have higher IQFinv‑to‑IAK ratios.
Keywords: Contrast detail, contrast‑detail radiography phantom, digital radiography, image quality, radiation dose -
Pages 201-207Background
None of the molecular imaging modalities can produce imaging with both anatomical and functional information. In recent years, to overcome these limitations multimodality molecular imaging or combination of two imaging modalities can provide anatomical and pathological information.
MethodsMagnetic iron oxide nanoparticles were prepared by co‑precipitation method and then were coated with silica according to Stober method. Consequently, silica‑coated nanoparticles were amino‑functionalized. Finally, gold nanoparticles assembled onto the surfaces of the previous product. Cytotoxicity effects of prepared Fe3O4@Au nanoparticles were evaluated by 3‑(4,5‑dimethylthiazol‑2‑yl)‑2,5‑diphenyltetrazolium bromide assay on human hepatocellular carcinoma cells. Their ability as a dual‑mode contrast agent was investigated by magnetic resonance (MR) and computed tomography (CT) imaging.
ResultsFe3O4@Au nanoparticles were spherical undersize of 75 nm. X‑ray diffraction analysis confirmed the formation of Fe3O4@Au nanoparticles. The magnetometry result confirmed the superparamagnetism property of prepared nanoparticles, and the saturation magnetization (Ms) was found to be 33 emu/g. Fe3O4@Au nanoparticles showed good cytocompatibility up to 60 μg/mL. The results showed that the Fe3O4@Au nanoparticles have good r2relaxivity (135.26 mM−1s−1) and good X‑ray attenuation property.
ConclusionThese findings represent that prepared Fe3O4@Au nanoparticles in an easy and relatively low‑cost manner have promising potential as a novel contrast agent for dual‑modality of MR/CT imaging
Keywords: Computed tomography, gold nanoparticles, iron oxide nanoparticles, magnetic resonance imaging -
Pages 208-216
This article summarizes the first and second Iranian brain–computer interface competitions held in 2017 and 2018 by the National Brain Mapping Lab. Two 64‑channel electroencephalography (EEG) datasets were contributed, including motor imagery as well as motor execution by three limbs. The competitors were asked to classify the type of motor imagination or execution based on EEG signals in the first competition and the type of executed motion as well as the movement onset in the second competition. Here, we provide an overview of the datasets, the tasks, the evaluation criteria, and the methods proposed by the top‑ranked teams. We also report the results achieved with the submitted algorithms and discuss the organizational strategies for future campaigns.
Keywords: Brain–computer interface, electroencephalography, motor execution, motor imagery, movement onset -
Page 217
n the article titled “The recognition of persian phonemes using PPNet”, published on pages 86-93, Issue 2, Volume 10 of Journal of Medical Signals & Sensors[1], the affiliation of Saber Malekzadeh is written incorrectly as " Department of Electrical Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran; Khazar University, Baku, Azerbaijan " instead of " Department of Electrical Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran ".