Figure 10 - uploaded by Melanie Humphreys
Content may be subject to copyright.
Source publication
Similar publications
Citations
... By substituting Eq. (12) in Eq. (10), the final SE-NLMS is given in Eq. (13) ...
Denoising electrocardiogram (ECG) signals is a challenge because of the unavoidable artifacts. In this paper, an adaptive and effective signed error normalized least mean square algorithm (SE-NLMS) is proposed to improve denoising and reduce the mean square error (MSE). The performance of the SE-NLMS algorithm with unfolding technique (SE-UNLMS) has been compared with that of the normalized least mean square algorithm with unfolding structure (UNLMS) as well as the least mean square algorithm with unfolding structure (ULMS). SE-NLMS has the advantage of NLMS, namely an adaptive convergence rate and reduced computational complexity. We have implemented all three algorithms, namely LMS, NLMS and SE-NLMS, using an unfolding architecture that offers minimum delay and is suitable for real-time applications. Performance metrics such as an MSE of 0.0062 and a signal-to-noise ratio (SNR) improvement of about 10.2% are achieved through the proposed method of SE-UNLMS compared to other denoising methods. Additionally, exploration has been carried out for the application of denoised ECG signals under various arrhythmia conditions. The time-domain features were extracted from various denoised ECG signals and classified with support vector machines (SVM) to yield a good classification accuracy of 96.5%. The SE-UNLMS denoising method is demonstrated to be a valuable implementation for the detection and diagnosis of arrhythmias in real-world medical situations via this classification process. For real-time validation, the proposed method SE-UNLMS was implemented on a field-programmable gate array (FPGA) using Spartan 6 VPTB-20. The FPGA implementation highlights the feasibility of the proposed SE-UNLMS for real-time ECG monitoring applications.
... Examples of the chronic diseases are the chronic obstructive pulmonary disease (COPD) [11], arthritis [12], chronic kidney disease (CKD) [13], human immunodeficiency virus (HIV) [14,15], hypertension or high blood pressure [16], stroke or cerebrovascular accident (CVA) [17][18][19], diabetes [20,21], congestive heart failure [22,23], hepatitis [24], dementia [25], autism spectrum disorder (ASD) [26], hyperlipidemia [27], arrhythmia [28], asthma [29,30], coronary artery disease (CAD) or coronary heart disease (CHD) [31], cancers [32][33][34], depression [35,36], Alzheimer's disease (AD) [37,38], osteoporosis disease or 'silent disease' [39,12] and schizophrenia disease [40,41]. The Corona-Virus disease, a pandemic, [42][43][44][45][46][47] can be a chronic disease depending on the immune system of an individual with some recovering as soon as they contract the disease and others suffering for a long period of time. ...
The percentage of university students currently nursing chronic diseases including but not limited to depression, HIV/AIDs, asthma, stroke and chronic kidney diseases, is alarming, and for a long time, these students are ever thought to be healthy. However, research shows otherwise with up to 30% of the students nursing the diseases. Previous research worldwide shows that up to 30% of university students can be infected at a given time. This research aimed to investigate the issues concerning chronic diseases among university students in Kenya. The specific objectives included estimation of the percentage of students currently suffering from the diseases, determining their effects and factors associated with them. The mixed-study design was applied. Random sampling was done among students in two selected universities in Kenya and a questionnaire was used in data collection. 739 students responded to the research questions. Minitab, SPSS and R software were involved in data management for comparison purpose, especially for statistically significant results. From the analysis, currently, there are approximately 14.6% of the students are suffering from chronic diseases, and this proportion is significant (p-value<0.0001). Among the infected, 60.19% were females and the rest were males. Among the sick, only 43.52% have let the university clinics know about their conditions while more than 50% have concealed the vital information. The factors ‘family history’, ‘involvement in drugs’, ‘adopted life-styles’ and ‘extreme poverty’ were found to be significantly associated with chronic diseases among the students. On the effects, the diseases were found to be negatively affecting the aspects of life of the infected students. Survival of the students was found to be having a mean and median survival time of 29.9472 and 30.27 years respectively. It is concluded that there is need for intervention among university students as 14.6% is not a number to be ignored. It is recommended that the stakeholders to come together and arrest the situation before things slip out of hand.
Worldwide, cardiac arrhythmia disease has become one of the most frequent heart problems, leading to death in most cases. In fact, cardiologists use the electrocardiogram (ECG) to diagnose arrhythmia by analyzing the heartbeat signals and utilizing electrodes to detect variations in the heart rhythm if they show certain abnormalities. Indeed, heart attacks depend on the treatment speed received, and since its risk is increased by arrhythmias, in this chapter the authors create an automatic system that can detect cardiac arrhythmia by using deep learning algorithms. They propose a deep convolutional neural network (CNN) to automatically classify five types of arrhythmias then evaluate and test it on the MIT-BIH database. The authors obtained interesting results by creating five CNN models, testing, and comparing them to choose the best performing one, and then comparing it to some state-of-the-art models. The authors use significant performance metrics to evaluate the models, including precision, recall, sensitivity, and F1 score.
We present a detailed discussion of the implementation strategies for a recently developed w -stacking w -projection hybrid algorithm used to reconstruct wide-field interferometric images. In particular, we discuss the methodology used to deploy the algorithm efficiently on a supercomputer via use of a Message Passing Interface (MPI) k -means clustering technique to achieve efficient construction and application of non-coplanar effects. Additionally, we show that the use of conjugate symmetry can increase the w -stacking efficiency, decrease the time required to construction, and apply w -projection kernels for large data sets. We then demonstrate this implementation by imaging an interferometric observation of Fornax A from the Murchison Widefield Array (MWA). We perform an exact non-coplanar wide-field correction for 126.6 million visibilities using 50 nodes of a computing cluster. The w -projection kernel construction takes only 15 min prior to reconstruction, demonstrating that the implementation is both fast and efficient.
