Mathematical biosciences and engineering : MBE
-
According to a recently conducted survey on surgical complication mortality rate, 47% of such cases are due to anesthetics overdose. This indicates that there is an urgent need to moderate the level of anesthesia. Recently deep learning (DL) methods have played a major role in estimating the depth of Anesthesia (DOA) of patients and has played an essential role in control anesthesia overdose. ⋯ The developed CNN models were used to predict the DOA based on the EEG spectrum images without the use of handcrafted features which provides intuitive mapping with high efficiency and reliability. The best trained model gives an accuracy of 83.2%. Hence, this provides further scope and research which can be carried out in the domain of visual mapping of DOA using EEG signals and DL methods.
-
A mathematical model is designed and used to study the transmission dynamics and control of COVID-19 in Nigeria. The model, which was rigorously analysed and parametrized using COVID-19 data published by the Nigeria Centre for Disease Control (NCDC), was used to assess the community-wide impact of various control and mitigation strategies in some jurisdictions within Nigeria (notably the states of Kano and Lagos, and the Federal Capital Territory, Abuja). Numerical simulations of the model showed that COVID-19 can be effectively controlled in Nigeria using moderate levels of social-distancing strategy in the jurisdictions and in the entire nation. ⋯ Such substantial reduction is feasible in the jurisdictions (and the entire Nigerian nation) if the public face mask use strategy is complemented with a social-distancing strategy. The community lockdown measures implemented in Nigeria on March 30, 2020 need to be maintained for at least three to four months to lead to the effective containment of COVID-19 outbreaks in the country. Relaxing, or fully lifting, the lockdown measures sooner, in an effort to re-open the economy or the country, may trigger a deadly second wave of the pandemic.
-
A total of more than 27 million confirmed cases of the novel coronavirus outbreak, also known as COVID-19, have been reported as of September 7, 2020. To reduce its transmission, a number of strategies have been proposed. In this study, mathematical models with nonpharmaceutical and pharmaceutical interventions were formulated and analyzed. ⋯ We found that the use of medical masks has the greatest effect in determining the number of new infections. The optimal control problem from the second model was characterized using the well-known Pontryagin's maximum principle and solved numerically. The results of a cost-effectiveness analysis showed that community awareness plays a crucial role in determining the success of COVID-19 eradication programs.
-
An outbreak of rapidly spreading coronavirus established human to human transmission and now became a pandemic across the world. The new confirmed cases of infected individuals of COVID-19 are increasing day by day. Therefore, the prediction of infected individuals has become of utmost important for health care arrangements and to control the spread of COVID-19. ⋯ Along with this, the high transmission rate ensures higher level of endemicity. From the short time prediction, we predict that India may face a crucial phase (approx 6000000 infected individuals within 140 days) in near future due to COVID-19. Finally, numerical results show that COVID-19 may be controllable by reducing the contacts and increasing the efficacy of lockdown.
-
In recent years, there are many research cases for the diagnosis of Parkinson's disease (PD) with the brain magnetic resonance imaging (MRI) by utilizing the traditional unsupervised machine learning methods and the supervised deep learning models. However, unsupervised learning methods are not good at extracting accurate features among MRIs and it is difficult to collect enough data in the field of PD to satisfy the need of training deep learning models. Moreover, most of the existing studies are based on single-view MRI data, of which data characteristics are not sufficient enough. ⋯ Finally, the traditional single-view clustering and multi-view clustering methods are employed on multiple feature views to obtain the results. Experiments show that our proposed method is superior to the state-of-art unsupervised learning models on the clustering effect. As a result, it may be noted that, our work could contribute to improving the effectiveness of identifying PD by previous labeled and subsequent unlabeled medical MRI data in the realistic medical environment.