Biomedical Engineering: Applications, Basis and Communications

This article proposes a computer-aided diagnostic system for feature-based selection classification (CAD-FSC) to detect arrhythmia, atrial fibrillation and normal sinus rhythm. The CAD-FSC methodology encompasses of ECG signal processing phases: ECG pre-processing, R-peak detection, feature extraction, feature selection and ECG classification. Digital filters are used to pre-process the ECG signal and the R-peak is detected by using the Pan-Tompkin’s algorithm. The heart rate variability (HRV) features are extracted in time and frequency domains. Among them, the prominent features are selected with analysis of variance (ANOVA) using Statistical Package for the Social Sciences (SPSS) tool. Cubic support vector machine (C-SVM), coarse Gaussian support vector machine (CG-SVM), cubic k-nearest neighbor (C-kNN) and weighted k-nearest neighbor (W-kNN) classifiers are utilized to validate the CAD-FSC system for three-stage classification. The C-SVM outperforms all other classifiers by giving higher overall accuracy of 98.4% after feature selection of time domain and frequency domain.

A brain–computer interface (BCI) can be used for people with severe physical disabilities such as ALS or amyotrophic lateral sclerosis. BCI can allow these individuals to communicate again by creating a new communication channel directly from the brain to an output device. BCI technology can allow paralyzed people to share their intent with others, and thereby demonstrate that direct communication from the brain to the external world is possible and that it might serve useful functions. BCI systems include machine learning algorithms (MLAs). Their performance depends on the feature extraction and classification techniques employed. In this paper, we propose a system to exploit the P300 signal in the brain, a positive deflection in event-related potentials. The P300 signal can be incorporated into a spelling device. There are two benefits behind this kind of research. First of all, this work presents the research status and the advantages of communication via a BCI system, especially the P300 BCI system for disordered people, and the related literature review is presented. Secondly, the paper discusses the performance of different machine learning algorithms. Two different datasets are presented: the first dataset 2004 and the second dataset 2019. A preprocessing step is introduced to the subjects in both datasets first to extract the important features before applying the proposed machine learning methods: linear discriminant analysis (LDA I and LDA II), support vector machine (SVM I, SVM II, SVM III, and SVM IV), linear regression (LREG), Bayesian linear discriminant analysis (BLDA), and twin support vector machine (TSVM). By comparing the performance of the different machine learning systems, in the first dataset it is found that BLDA and SVMIV classifiers yield the highest performance for both subjects “A” and “B”. BLDA yields 98% and 66% for 15th and 5th sequences, respectively, whereas SVMIV yields 98% and 54.4% for 15th and 5th sequences, respectively. While in the second dataset, it is obvious that BLDA classifier yields the highest performance for both subjects “1” and “2”, it achieves 90.115%. The paper summarizes the P300 BCI system for the two introduced datasets. It discusses the proposed system, compares the classification methods performances, and considers some aspects for the future work to be handled. The results show high accuracy and less computational time which makes the system more applicable for online applications.

Detection of mental stress has been receiving great attention from the researchers for many years. Many studies have analyzed electroencephalogram signals in order to estimate mental stress using linear methods. In this paper, a novel nonlinear stress assessment method based on multivariate multiscale entropy has been introduced. Since the multivariate multiscale entropy method characterizes the complexity of nonlinear time series, this research determines the mental stress of human during cognitive workload using complexity of electroencephalogram (EEG) signals. To perform this work, 36 subjects including 9 men and 27 women were participated in the cognitive workload experiment. Multivariate multiscale entropy method has been applied to electroencephalogram data collected from those subjects for estimating mental stress in terms of complexity. The complexity feature of brain electroencephalogram signals collected during resting and cognitive workload has shown statistically significant ($p<0.01$) differences across brain regions and mental tasks which can be implemented practically for building stress detection system. In addition, the complexity profile of electroencephalogram signals has shown that higher stress is reflected in good counting compared to bad counting. Moreover, the support vector machine (SVM) has shown promising classification between resting and mental counting states by providing 80% sensitivity, 100% specificity and 90% classification accuracy.

This paper presents the survey on different techniques which can be used to detect congenital heart disease using palm patterns. The congenital heart disease is one of the heart diseases which starts from birth. Research works are carried out towards detecting congenital heart disease before symptom appears using palm patterns so that it avoids critical health problems in future. Researchers have collected palm prints from normal people who are not suffering from any kind of heart disease and from patients who are suffering from different types of congenital heart diseases. These palm prints are collected from different hospitals. The palm prints are taken using ink and paper method. These palm patterns are analyzed to determine the role of palm pattern while detection of the disease. Few researchers have considered only triradius of palm and most of the researchers have considered palm patterns such as whorl, loop, arch and hypothenar pattern. In case of triradius, researchers have calculated position of axial triradius and it is categorized into three types. In case of whorl, loop and arch, they have considered how often they appear in palm of normal people and patients. Few researchers have analyzed both left and right hands of normal people and patients.

Cancer is one of the most common dreadful diseases prevailing worldwide, and patients with cancer are rescued only when the cancer is detected at a very early stage. Early detection of cancer is appropriate as in the fourth stage, but the chance of survival is limited. The symptoms of cancers are rigorous, and therefore, all the symptoms should be studied properly before the diagnosis. Thus, an automatic prediction system is necessary for classifying the tumor, i.e. malignant or benign tumor. Over the past few years, cancer classification is increased rapidly, but there is no general technique to find novel cancer classes (class discovery) or to assign tumors to known classes. Accordingly, this survey analyzes distinct cancer classification techniques. Thus, this review article provides a detailed review of 50 research papers presenting the suggested cancer classification techniques, like Deep learning-based techniques, Neural network-based techniques, and Hybrid techniques. Moreover, an elaborative analysis and discussion are made based on the year of publication, utilized datasets, accuracy range, evaluation metrics, implementation tool, and adopted classification methods. Eventually, the research gaps and issues of various cancer classification schemes are presented for extending the researchers towards a better future scope.

This study identifies a correlation between low-frequency heart rate variability (LF-HRV) and encephalographic (EEG) complexity to differentiate internally operative attention (INT) and externally operative attention (EXT). Electrophysiological fluctuations in response to Posner’s spatial orienting paradigm were explored in 14 healthy volunteers who participated in 6 alternating sessions of attention tasks. HRV analysis was used to measure heart rate fluctuations, and approximate entropy (ApEn) was used to measure changes in the irregularity of EEG and HRV. Power spectral analysis of HRV revealed that there was found to be a significant difference between INT and EXT for HRV-low frequency (HRV-LF) and LH/HF ratio. ApEn for RR-interval time series increased for both attention tasks as compared to baseline and recovery session. The relationship between HRV-LF and EEG spectral power measured at F4 revealed significant negative correlation during ($r=-0.613$, with $p<0.05$) EXT than ($r=-0.116$, with $p>0.05$) INT. Furthermore, a significant positive correlation, yet of moderate strength was noted between HRV-LF and ApEn of EEG signal measured at POz ($r=0.591$, with $p<0.05$) during EXT as compared to INT ($r=0.007$, with $p>0.05$) and, a significant negative correlation was observed between ApEn of RR-interval and ApEn of EEG signal measured at POz ($r=-0.574$, with $p<0.05$) during EXT as compared to INT ($r=-0.490$, with $p>0.05$). Thus, it is evident that EXT leads to more irregularity in parietal regions of the brain than the INT. During EXT, the irregularity over the parietal region linked to increased sympathetic activity as compared to INT and corresponds to decreased heart rate. These results may benefit in designing robust human-computer interfaces and accelerated training paradigm to raise an athlete’s performance.

The paper proposes a novel methodology of de-noising raw electroencephalogram (EEG) data from ocular artifacts (OAs) and alpha waves extraction from motor imagery-based signals that could be further utilized for brain–computer interface (BCI)-based applications. An algorithm based on discrete wavelet transform (DWT) and nonlinear adaptive filtering for the removal of OA is advocated, with an aim of making the process computationally intelligent. This algorithm has been tested on pre-recorded EEG dataset for BCI (Dataset IIIa; obtained from the website of the BCI Competition III). To further validate the competence of the proposed method, synthetic EEG signals were created, which were fused with white Gaussian noise. A total of 20 EEG signals were generated, half of which had added noise with a signal-to-noise ratio (SNR) of 10dB and other half had added noise of 5 dBSNR. Each signal contained 1000 samples with a sampling frequency of 250Hz. An optimum bandpass filter (FIR and IIR) for extraction of alpha waves has been suggested. FIR Equiripple filter is found most appropriate for the task as it has highest SNR and computes the response faster when compared with other filters. Among different mother wavelets, Daubechies 4 wavelet obtained using statistical thresholding denoises the EEG data most successfully. Correlation and root mean square error (RMSE) parameters show that the performance of nonlinear adaptive filter developed using nonlinear Volterra series has an edge over conventional adaptive filters for the intended purpose.

Falling is one of the leading causes of accidental injury and death among elderly adults and construction workers, with costs exceeding US$31 billion each year. Having good balance reduces the likelihood of falling — therefore it is important to determine which possible factors might influence balance. The purpose of this study was to determine if consuming three different types of breakfast altered blood glucose levels in such a way that young healthy individual’s balance control was compromised. Balance was then measured while the subjects completed single- and dual-task standing trials with eyes open and closed. Although changing blood glucose did alter quiet standing balance — as measured by the separation distance between the COG and COP, the velocity of the COM, and the total distance traveled by the COG and COP along the anterior–posterior (AP) and medial–lateral (ML) axes — the results were contradictory to what was hypothesized. Subjects with lower blood glucose swayed less than those with higher blood glucose. This could potentially be due to the habitual skipping of breakfast in young adults. Though the changing of blood glucose did influence quiet standing balance of young healthy adults, it was not in a way which increased the risk of falling.