for Journals by Title or ISSN for Articles by Keywords help
 Subjects -> ENGINEERING (Total: 2282 journals)     - CHEMICAL ENGINEERING (192 journals)    - CIVIL ENGINEERING (186 journals)    - ELECTRICAL ENGINEERING (102 journals)    - ENGINEERING (1204 journals)    - ENGINEERING MECHANICS AND MATERIALS (385 journals)    - HYDRAULIC ENGINEERING (55 journals)    - INDUSTRIAL ENGINEERING (68 journals)    - MECHANICAL ENGINEERING (90 journals) ENGINEERING (1204 journals)                  1 2 3 4 5 6 7 | Last
 Australasian Physical & Engineering Sciences in Medicine   [SJR: 0.293]   [H-I: 19]   [1 followers]  Follow         Hybrid journal (It can contain Open Access articles)    ISSN (Print) 0158-9938 - ISSN (Online) 1879-5447    Published by Springer-Verlag  [2353 journals]
• Position paper: recommendations for a digital mammography quality
assurance program V4.0
• Authors: J. C. P. Heggie; P. Barnes; L. Cartwright; J. Diffey; J. Tse; J. Herley; I. D. McLean; F. J. Thomson; R. K. Grewal; L. T. Collins
PubDate: 2017-09-15
DOI: 10.1007/s13246-017-0583-x

• Heartbeat detection in multimodal physiological signals using signal
quality assessment based on sample entropy
• Abstract: Abstract This paper presents a novel technique to identify heartbeats in multimodal data using electrocardiogram (ECG) and arterial blood pressure (ABP) signals. Multiple physiological signals such as ECG, ABP, and Respiration are often recorded in parallel from the activity of heart. These signals generally possess related information as they are generated by the same physical system. The ECG and ABP correspond to the same phenomenon of contraction and relaxation activity of heart. Multiple signals acquired from various sensors are generally processed independently, thus discarding the information from other measurements. In the estimation of heart rate and heart rate variability, the R peaks are generally identified from ECG signal. Efficient detection of R-peaks in electrocardiogram (ECG) is a key component in the estimation of clinically relevant parameters from ECG. However, when the signal is severely affected by undesired artifacts, this becomes a challenging task. Sometimes in clinical environment, other physiological signals reflecting the cardiac activity such as ABP signal are also acquired simultaneously. Under the availability of such multimodal signals, the accuracy of R peak detection methods can be improved using sensor-fusion techniques. In the proposed method, the sample entropy (SampEn) is used as a metric for assessing the noise content in the physiological signal and the R peaks in ECG and the systolic peaks in ABP signals are fused together to enhance the efficiency of heartbeat detection. The proposed method was evaluated on the 100 records from the computing in cardiology challenge 2014 training data set. The performance parameters are: sensitivity (Se) and positive predictivity (PPV). The unimodal R peaks detector achieved: Se gross = 99.40%, PPV gross = 99.29%, Se average = 99.37%, PPV average = 99.29%. Similarly unimodal BP delineator achieved Se gross = 99.93%, PPV gross = 99.99%, Se average = 99.93%, PPV average = 99.99% whereas, the proposed multimodal beat detector achieved: Se gross = 99.65%, PPV gross = 99.91%, Se average = 99.68%, PPV average = 99.91%.
PubDate: 2017-09-08
DOI: 10.1007/s13246-017-0585-8

• Cell-shaped silicon-on-insulator microdosimeters: characterization and
• Abstract: Abstract This work tested the feasibility of a silicon-on-insulator microdosimeter, which mimics the size and shape of specific cells within the human body, to determine dose equivalent from neutron irradiation. The microdosimeters were analyzed in terms of their basic diode characteristics, i.e., leakage current as a function of bias voltage. Lineal energy spectra were acquired using two different converter layers placed atop the microdosimeter: a tissue-substitute converter made from high-density polyethylene, and a boron converter consisting of epoxy coated with boron powder. The spectra were then converted into absorbed dose and dose equivalent. Experimental results were compared to Monte Carlo simulations of the neutron irradiations, revealing good agreement. Uncertainty in the dose equivalent determinations was 7.5% when using the cell-shaped microdosimeter with the tissue-substitute converter and 13.1% when using the boron converter. This work confirmed that the SOI approach to cell-mimicking microdosimetry is feasible.
PubDate: 2017-09-08
DOI: 10.1007/s13246-017-0576-9

• Diagnosis of multiple sclerosis from EEG signals using nonlinear methods
• Abstract: Abstract EEG signals have essential and important information about the brain and neural diseases. The main purpose of this study is classifying two groups of healthy volunteers and Multiple Sclerosis (MS) patients using nonlinear features of EEG signals while performing cognitive tasks. EEG signals were recorded when users were doing two different attentional tasks. One of the tasks was based on detecting a desired change in color luminance and the other task was based on detecting a desired change in direction of motion. EEG signals were analyzed in two ways: EEG signals analysis without rhythms decomposition and EEG sub-bands analysis. After recording and preprocessing, time delay embedding method was used for state space reconstruction; embedding parameters were determined for original signals and their sub-bands. Afterwards nonlinear methods were used in feature extraction phase. To reduce the feature dimension, scalar feature selections were done by using T-test and Bhattacharyya criteria. Then, the data were classified using linear support vector machines (SVM) and k-nearest neighbor (KNN) method. The best combination of the criteria and classifiers was determined for each task by comparing performances. For both tasks, the best results were achieved by using T-test criterion and SVM classifier. For the direction-based and the color-luminance-based tasks, maximum classification performances were 93.08 and 79.79% respectively which were reached by using optimal set of features. Our results show that the nonlinear dynamic features of EEG signals seem to be useful and effective in MS diseases diagnosis.
PubDate: 2017-09-08
DOI: 10.1007/s13246-017-0584-9

• Winning images from the Photography in Medical Physics (PiMP) competition
• PubDate: 2017-09-04
DOI: 10.1007/s13246-017-0581-z

• A comprehensive dose assessment of irradiated hand by iridium-192 source
• Authors: S. M. Hosseini Pooya; M. R. Dashtipour; R. Paydar; F. Mianji; B. Pourshahab
Abstract: Abstract Among the various incidents in industrial radiography, inadvertent handling of sources by hands is one of the most frequent incidents in which some parts of the hands may be locally exposed to high doses. An accurate assessment of extremity dose assists medical doctors in selecting appropriate treatments, preventing the injury expansion in the region. In this study, a phantom was designed to simulate a fisted hand of a radiographer when the worker holds a radioactive source in their hands. The local doses were measured using implanted TLDs in the phantom at different distances from a source. Furthermore, skin dose distribution was measured by Gaf-chromic films in the palm region of the phantom. The reliability of the measurements has been studied via analytical as well as Monte-Carlo simulation methods. The results showed that the new phantom design can be used reliably in extremity dose assessments, particularly at the points next to the source.
PubDate: 2017-09-04
DOI: 10.1007/s13246-017-0568-9

• GATE Monte Carlo simulation of dose distribution using MapReduce in a
cloud computing environment
• Authors: Yangchuan Liu; Yuguo Tang; Xin Gao
Abstract: Abstract The GATE Monte Carlo simulation platform has good application prospects of treatment planning and quality assurance. However, accurate dose calculation using GATE is time consuming. The purpose of this study is to implement a novel cloud computing method for accurate GATE Monte Carlo simulation of dose distribution using MapReduce. An Amazon Machine Image installed with Hadoop and GATE is created to set up Hadoop clusters on Amazon Elastic Compute Cloud (EC2). Macros, the input files for GATE, are split into a number of self-contained sub-macros. Through Hadoop Streaming, the sub-macros are executed by GATE in Map tasks and the sub-results are aggregated into final outputs in Reduce tasks. As an evaluation, GATE simulations were performed in a cubical water phantom for X-ray photons of 6 and 18 MeV. The parallel simulation on the cloud computing platform is as accurate as the single-threaded simulation on a local server and the simulation correctness is not affected by the failure of some worker nodes. The cloud-based simulation time is approximately inversely proportional to the number of worker nodes. For the simulation of 10 million photons on a cluster with 64 worker nodes, time decreases of 41× and 32× were achieved compared to the single worker node case and the single-threaded case, respectively. The test of Hadoop’s fault tolerance showed that the simulation correctness was not affected by the failure of some worker nodes. The results verify that the proposed method provides a feasible cloud computing solution for GATE.
PubDate: 2017-08-31
DOI: 10.1007/s13246-017-0580-0

• Best of both worlds
• Authors: Stéphanie Corde
PubDate: 2017-08-29
DOI: 10.1007/s13246-017-0582-y

• Estimation of effective brain connectivity with dual Kalman filter and EEG
source localization methods
Abstract: Abstract Effective connectivity is one of the most important considerations in brain functional mapping via EEG. It demonstrates the effects of a particular active brain region on others. In this paper, a new method is proposed which is based on dual Kalman filter. In this method, firstly by using a brain active localization method (standardized low resolution brain electromagnetic tomography) and applying it to EEG signal, active regions are extracted, and appropriate time model (multivariate autoregressive model) is fitted to extracted brain active sources for evaluating the activity and time dependence between sources. Then, dual Kalman filter is used to estimate model parameters or effective connectivity between active regions. The advantage of this method is the estimation of different brain parts activity simultaneously with the calculation of effective connectivity between active regions. By combining dual Kalman filter with brain source localization methods, in addition to the connectivity estimation between parts, source activity is updated during the time. The proposed method performance has been evaluated firstly by applying it to simulated EEG signals with interacting connectivity simulation between active parts. Noisy simulated signals with different signal to noise ratios are used for evaluating method sensitivity to noise and comparing proposed method performance with other methods. Then the method is applied to real signals and the estimation error during a sweeping window is calculated. By comparing proposed method results in different simulation (simulated and real signals), proposed method gives acceptable results with least mean square error in noisy or real conditions.
PubDate: 2017-08-29
DOI: 10.1007/s13246-017-0578-7

• Differences in grip force control between young and late middle-aged
• Authors: Lianrong Zheng; Kunyang Li; Qian Wang; Wenhui Chen; Rong Song; Guanzheng Liu
Abstract: Abstract Grip force control is a crucial function for human to guarantee the quality of life. To examine the effects of age on grip force control, 10 young adults and 11 late middle-aged adults participated in visually guided tracking tasks using different target force levels (25, 50, and 75% of the subject’s maximal grip force). Multiple measures were used to evaluate the tracking performance during force rising phase and force maintenance phase. The measurements include the rise time, fuzzy entropy, mean force percentage, coefficient of variation, and target deviation ratio. The results show that the maximal grip force was significantly lower in the late middle-aged adults than in the young adults. The time of rising phase was systematically longer among late middle-aged adults. The fuzzy entropy is a useful indicator for quantitating the force variability of the grip force signal at higher force levels. These results suggest that the late middle-aged adults applied a compensatory strategy that allow allows for sufficient time to reach the required grip force and reduce the impact of the early and subtle degenerative changes in hand motor function.
PubDate: 2017-08-22
DOI: 10.1007/s13246-017-0567-x

• Estimation of entrance surface air kerma due to diagnostic X-ray
examinations of adult patients in Uttarakhand, India and establishment of
local diagnostic reference levels
• Authors: Satish C. Uniyal; Vineet Chaturvedi; Sunil D. Sharma; Shailendra Raghuvanshi
Abstract: Abstract It is well established that diagnostic X-ray practices must be optimised to keep patient radiation dose as low as compatible with providing the diagnostic information required. For effective optimisation of diagnostic exposures, the International Commission on Radiological Protection (ICRP) introduced the concept of diagnostic reference levels (DRLs) in 1996. The present study aimed to carry out an extensive dose survey of diagnostic radiography installations in the Uttarakhand region of India to establish local DRL Values for the different diagnostic practices. During the survey, air kerma values were measured for 297 diagnostic X-ray machines installed at 270 medical centres in the region and the entrance surface air kerma (K a,e) was estimated for ten commonly performed radiographic projections. These included chest posterior-anterior (PA), cervical spine anterior-posterior (AP), skull PA, abdomen AP, KUB (kidney, ureter and bladder), lumbar spine AP, lumbar spine lateral (LAT), pelvis AP, thoracic spine AP, and thoracic spine LAT. Wide variations were observed in the estimated values of K a,e for individual projections. The third quartile of the distribution of the median values of the estimated K a,e for a given projection was calculated to establish local DRL Values. The majority of the acquired dose data were found to be comparable to or less than the proposed national and international DRLs. The local DRL Values reported in this study may be used to improve radiological practice by reducing patient doses during radiography examinations. The obtained data may also contribute to a national patient dose database for establishing future national DRLs.
PubDate: 2017-08-17
DOI: 10.1007/s13246-017-0577-8

• Authors: Yao Ai; Xiaobin Tang; Diyun Shu; Wencheng Shao; Chunhui Gong; Changran Geng; Xudong Zhang; Haiyan Yu
Abstract: Abstract This work aims to determine the relationship between Cerenkov photon emission and radiation dose from internal radionuclide irradiation. Water and thyroid phantoms were used to simulate the distribution of Cerenkov photon emission and dose deposition through Monte Carlo method. The relationship between Cerenkov photon emission and dose deposition was quantitatively analyzed. A neck phantom was also used to verify Cerenkov photon detection for thyroid radionuclide therapy. Results show that Cerenkov photon emission and dose deposition exhibit the same distribution pattern in water phantom, and this relative distribution relationship also existed in the thyroid phantom. Moreover, Cerenkov photon emission exhibits a specific quantitative relation to dose deposition. For thyroid radionuclide therapy, only a part of Cerenkov photon produced by thyroid could penetrate the body for detection; therefore, the use of Cerenkov radiation for measurement of radionuclide therapy dose may be more suitable for superficial tumors. This study demonstrated that Cerenkov radiation has the potential to be used for measuring radiation dose for radionuclide therapy.
PubDate: 2017-08-14
DOI: 10.1007/s13246-017-0579-6

• A simple and efficient algorithm operating with linear time for MCEEG data
compression
• Authors: Geevarghese Titus; M. S. Sudhakar
Abstract: Abstract Popularisation of electroencephalograph (EEG) signals in diversified fields have increased the need for devices capable of operating at lower power and storage requirements. This has led to a great deal of research in data compression, that can address (a) low latency in the coding of the signal, (b) reduced hardware and software dependencies, (c) quantify the system anomalies, and (d) effectively reconstruct the compressed signal. This paper proposes a computationally simple and novel coding scheme named spatial pseudo codec (SPC), to achieve lossy to near lossless compression of multichannel EEG (MCEEG). In the proposed system, MCEEG signals are initially normalized, followed by two parallel processes: one operating on integer part and the other, on fractional part of the normalized data. The redundancies in integer part are exploited using spatial domain encoder, and the fractional part is coded as pseudo integers. The proposed method has been tested on a wide range of databases having variable sampling rates and resolutions. Results indicate that the algorithm has a good recovery performance with an average percentage root mean square deviation (PRD) of 2.72 for an average compression ratio (CR) of 3.16. Furthermore, the algorithm has a complexity of only O(n) with an average encoding and decoding time per sample of 0.3 ms and 0.04 ms respectively. The performance of the algorithm is comparable with recent methods like fast discrete cosine transform (fDCT) and tensor decomposition methods. The results validated the feasibility of the proposed compression scheme for practical MCEEG recording, archiving and brain computer interfacing systems.
PubDate: 2017-07-31
DOI: 10.1007/s13246-017-0575-x

• Feasibility of 3D printed air slab diode caps for small field dosimetry
• Authors: Benjamin Perrett; Paul Charles; Tim Markwell; Tanya Kairn; Scott Crowe
Abstract: Abstract Commercial diode detectors used for small field dosimetry introduce a field-size-dependent over-response relative to an ideal, water-equivalent dosimeter due to high density components in the body of the detector. An air gap above the detector introduces a field-size-dependent under-response, and can be used to offset the field-size-dependent detector over-response. Other groups have reported experimental validation of caps containing air gaps for use with several types of diodes in small fields. This paper examines two designs for 3D printed diode air caps for the stereotactic field diode (SFD)—a cap containing a sealed air cavity, and a cap with an air cavity at the face of the SFD. Monte Carlo simulations of both designs were performed to determine dimensions for an air cavity to introduce the desired dosimetric correction. Various parameter changes were also simulated to estimate the dosimetric uncertainties introduced by 3D printing. Cap layer dimensions, cap density changes due to 3D printing, and unwanted air gaps were considered. For the sealed design the optimal air gap size for water-equivalent cap material was 0.6 mm, which increased to 1.0 mm when acrylonitrile butadiene styrene in the cap was simulated. The unsealed design had less variation, a 0.4 mm air gap is optimal in both situations. Unwanted air pockets in the bore of the cap and density changes introduced by the 3D printing process can potentially introduce significant dosimetric effects. These effects may be limited by using fine print resolutions and minimising the volume of cap material.
PubDate: 2017-07-31
DOI: 10.1007/s13246-017-0570-2

• Lower limb muscle activity during gait in individuals with hearing loss
Abstract: Abstract The objective of this study was to investigate the electrical activity of lower limb muscles during gait in an able-bodied control group and in deaf individuals. Thirty male children were equally divided into a control group and a group of deaf children. A portable EMG system was used to record the activity of the bilateral tibialis anterior, gastrocnemius medialis and vastus lateralis muscles during barefoot walking with and without dual task. For EMG analysis, the average root mean square (RMS) values of the five trials were calculated and then normalized based on the peak RMS obtained by the maximum isometric voluntary contraction. MANOVA test was used for between group comparisons. The significance level was set at p < 0.05 for all analyses. The findings indicated that gait speed in children with hearing loss was smaller than that in control group. Dual task resulted in a decreased walking speed of children with hearing loss. The activities of tibialis anterior muscle in terminal stance phase (p = 0.040), medial gastrocnemius muscle in loading response and initial swing phases (p < 0.05), and vastus lateralis muscle in the terminal stance and pre swing phases (p < 0.05) were greater in deaf group. In deaf children the gait speed was reduced and the muscle activity was increased with respect to those in control group. This altered gait speed and muscle activity is suggestive of a lower mechanical efficiency of gait in deaf children.
PubDate: 2017-07-27
DOI: 10.1007/s13246-017-0574-y

• Polymer gel dosimeters with PVA–GA matrix
Abstract: Abstract Properties of a new polymer gel with cross-linked polyvinyl alcohol as a gelatinous matrix were investigated. The new polymer gel dosimeter was named PVABAT. The irradiation was performed using a calibrated 60Co beam. The dose responses of the PVABAT formulations were quantified with MRI transverse relaxation rate (R2) measurements. The results show that the PVABAT gel responds linearly to the absorbed dose for doses from 30 up to 45 Gy. The maximal amount of $${\text{D}}_{\Delta }^{{95{{\% }}}}$$ of PVABAT polymer gel dosimeter was about 0.19 Gy which was indicated on a better resolution in comparison with previously reported acrylamide-based polymer gel dosimeters formulations. Furthermore, the gel response remains stable in the investigated time (192 h) after the irradiation. The effective atomic number and electron density of the new gel showed a maximum difference of 3.2 and 2% with soft tissue respectively. The melting point also increased significantly for new formulation. Furthermore, the new gel formulation has an elemental tissue equivalency for dosimetry applications involving nuclear reactions.
PubDate: 2017-07-27
DOI: 10.1007/s13246-017-0573-z

• A new scoring system for evaluating coronary artery disease by using blood
pressure variability
• Authors: Wei Zhu; Jian Qiu; Liheng Ma; Hongqiang Lei; Zekun Cai; Hui Zhao; Yu Deng; Jun Ma; Lin Xu
Abstract: Abstract The aim of this study was to develop a new scoring system using ambulatory blood pressure monitoring (ABPM) to assist in the evaluation of coronary artery disease (CAD). One hundred twenty-five subjects (53.1 ± 9.6 years of age) were included. Pearson’s tests were first performed to identify the parameters that correlated with Duke Treadmill Score (DTS). Blood test parameters and blood pressure variability (BPV) measures that were extracted from the ABPM were included. Next, a multiple linear regression analysis was performed to train a new scoring system in the 84 patients from the 125 patients. Then, a correlation analysis was conducted to validate the correlation between the new scoring system and DTS in the remaining 41 subjects. A further correlation analysis was used to verify the clinical value of the new scoring system using ultrasonic cardiogram (UCG) and brachial-ankle pulse wave velocity (baPWV). Our new scoring system, which had a 24.096 − 0.083 × residual standard deviation of night systolic blood pressure (SBP) − 0.130 × age − 0.206 × average real variability of night SBP, was correlated with DTS (r = 0.312, P = 0.047). Moreover, our new scoring system was also correlated with various markers of cardiac function (r = −0.290, P = 0.001; r = −0.262, P = 0.004; r = −0.303, P = 0.001; r = −0.306, P = 0.001, respectively) measured by UCG and with baPWV (r = 0.529, P = 0.001). Furthermore, the r-values for the BPV Score versus the markers were closer to −1 than the corresponding r-values for the Duke Score vs the same parameters. And the differences in r-values between Duke Score and BPV Score were statistically significant (P = 0.022). In conclusion, the new scoring system based on ABPM has potential as a non-invasive tool for evaluating CAD.
PubDate: 2017-07-27
DOI: 10.1007/s13246-017-0563-1

• A new algorithm for ECG interference removal from single channel EMG
recording
• Authors: Shayan Yazdani; Mahmood Reza Azghani; Mohammad Hossein Sedaaghi
Abstract: Abstract This paper presents a new method to remove electrocardiogram (ECG) interference from electromyogram (EMG). This interference occurs during the EMG acquisition from trunk muscles. The proposed algorithm employs progressive image denoising (PID) algorithm and ensembles empirical mode decomposition (EEMD) to remove this type of interference. PID is a very recent method that is being used for denoising digital images mixed with white Gaussian noise. It detects white Gaussian noise by deterministic annealing. To the best of our knowledge, PID has never been used before, in the case of EMG and ECG separation or in other 1D signal denoising applications. We have used it according to this fact that amplitude of the EMG signal can be modeled as white Gaussian noise using a filter with time-variant properties. The proposed algorithm has been compared to the other well-known methods such as HPF, EEMD-ICA, Wavelet-ICA and PID. The results show that the proposed algorithm outperforms the others, on the basis of three evaluation criteria used in this paper: Normalized mean square error, Signal to noise ratio and Pearson correlation.
PubDate: 2017-07-21
DOI: 10.1007/s13246-017-0564-0

• Performance assessment of a programmable five degrees-of-freedom motion
platform for quality assurance of motion management techniques in
• Authors: Chen-Yu Huang; Paul Keall; Adam Rice; Emma Colvill; Jin Aun Ng; Jeremy T. Booth
Abstract: Abstract Inter-fraction and intra-fraction motion management methods are increasingly applied clinically and require the development of advanced motion platforms to facilitate testing and quality assurance program development. The aim of this study was to assess the performance of a 5 degrees-of-freedom (DoF) programmable motion platform HexaMotion (ScandiDos, Uppsala, Sweden) towards clinically observed tumor motion range, velocity, acceleration and the accuracy requirements of SABR prescribed in AAPM Task Group 142. Performance specifications for the motion platform were derived from literature regarding the motion characteristics of prostate and lung tumor targets required for real time motion management. The performance of the programmable motion platform was evaluated against (1) maximum range, velocity and acceleration (5 DoF), (2) static position accuracy (5 DoF) and (3) dynamic position accuracy using patient-derived prostate and lung tumor motion traces (3 DoF). Translational motion accuracy was compared against electromagnetic transponder measurements. Rotation was benchmarked with a digital inclinometer. The static accuracy and reproducibility for translation and rotation was <0.1 mm or <0.1°, respectively. The accuracy of reproducing dynamic patient motion was <0.3 mm. The motion platform’s range met the need to reproduce clinically relevant translation and rotation ranges and its accuracy met the TG 142 requirements for SABR. The range, velocity and acceleration of the motion platform are sufficient to reproduce lung and prostate tumor motion for motion management. Programmable motion platforms are valuable tools in the investigation, quality assurance and commissioning of motion management systems in radiation oncology.
PubDate: 2017-07-17
DOI: 10.1007/s13246-017-0572-0

• Fusion of heart rate variability and pulse rate variability for emotion
recognition using lagged poincare plots
• Authors: Atefeh Goshvarpour; Ataollah Abbasi; Ateke Goshvarpour
Abstract: Abstract Designing an efficient automatic emotion recognition system based on physiological signals has attracted great interests within the research of human–machine interactions. This study was aimed to classify emotional responses by means of a simple dynamic signal processing technique and fusion frameworks. The electrocardiogram and finger pulse activity of 35 participants were recorded during rest condition and when subjects were listening to music intended to stimulate certain emotions. Four emotion categories, including happiness, sadness, peacefulness, and fear were chosen. Estimating heart rate variability (HRV) and pulse rate variability (PRV), 4 Poincare indices in 10 lags were extracted. The support vector machine classifier was used for emotion classification. Both feature level (FL) and decision level (DL) fusion schemes were examined. Significant differences have been observed between lag 1 Poincare plot indices and the other lagged measures. The mean accuracies of 84.1, 82.9, 79.68, and 76.05% were obtained for PRV, DL, FL, and HRV measures, respectively. However, DL outperformed others in discriminating sadness and peacefulness, using SD1 and total features, correspondingly. In both cases, the classification rates improved up to 92% (with the sensitivity of 95% and specificity of 83.33%). Totally, DL resulted in better performances compared to FL. In addition, the impact of the fusion rules on the classification performances has been confirmed.
PubDate: 2017-07-17
DOI: 10.1007/s13246-017-0571-1

JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327

Home (Search)
Subjects A-Z
Publishers A-Z
Customise
APIs