A modified version of the SEIR model with the effects of vaccination and inter-state movement is proposed to simulate the spread of COVID-19 in Malaysia. A mathematical analysis of the proposed model was performed to derive the basic reproduction number. To enhance the model’s forecasting capabilities, the model parameters were estimated using the Nelder–Mead simplex method by fitting the model outputs to the observed data. Our results showed a good fit between the model outputs and available data, where the model was then able to perform short-term predictions. In line with the rapid vaccination program, our model predicted that the COVID-19 cases in the country would decrease by the end of August. Furthermore, our findings indicated that relaxing travel restrictions from a highly vaccinated region to a low vaccinated region would result in an epidemic outbreak.

Linear models are not always able to sufficiently capture the structure of a dataset. Sometimes, combining predictors in a non-parametric method, such as deep neural networks (DNNs), would yield a more flexible modeling of the response variables in the predictions. Furthermore, the standard statistical classification or regression approaches are inefficient when dealing with more complexity, such as a high-dimensional problem, which usually suffers from multicollinearity. For confronting these cases, penalized non-parametric methods are very useful. This paper proposes two heuristic approaches and implements new shrinkage penalized cost functions in the DNN, based on the elastic-net penalty function concept. In other words, some new methods via the development of shirnkaged penalized DNN, such as ${\mathrm{DNN}}_{\mathrm{elastic-net}}$ and ${\mathrm{DNN}}_{\mathrm{ridge}\&\mathrm{bridge}}$, are established, which are strong rivals for ${\mathrm{DNN}}_{\mathrm{Lasso}}$ and ${\mathrm{DNN}}_{\mathrm{ridge}}$. If there is any dataset grouping information in each layer of the DNN, it may be transferred using the derived penalized function of elastic-net; other penalized DNNs cannot provide this functionality. Regarding the outcomes in the tables, in the developed DNN, not only are there slight increases in the classification results, but there are also nullifying processes of some nodes in addition to a shrinkage property simultaneously in the structure of each layer. A simulated dataset was generated with the binary response variables, and the classic and heuristic shrinkage penalized DNN models were generated and tested. For comparison purposes, the DNN models were also compared to the classification tree using GUIDE and applied to a real microbiome dataset.

The study aimed to investigate the effect of consolidation treatment with fludarabine, high-dose cytarabine and granulocyte colony-stimulating factor or FLAG in older AML patients. The study included 41 eligible patients above 54 years old, who received both induction and consolidation chemotherapy for AML from 2008 to 2013. The study cohort had a minimum 24 months follow-up period. Survival analysis was carried out to assess patients’ overall survival and disease free survival based on types of consolidation regimens. The consolidation treatment with FLAG exerted a protective effect to both overall survival and disease free survival in older patients. Patients who were consolidated with FLAG regimen had a significant longer overall survival (log-rank, p = 0.0025) and disease free survival (log-rank, p = 0.0026). The median overall survival was longer (18.70 months) with the use of FLAG when compared to non-FLAG group (8.09 months). The median disease free survival was also longer (13.84 months) with use of FLAG when compared to the non-FLAG group (4.44 months). Regression analysis with Cox model yielded hazard ratio of 0.245 (p = 0.0094) in overall survival and 0.217 (p = 0.0068) in disease free survival. The use of FLAG as consolidation treatment was associated with approximately 60–80% reduction in hazard rates. The result was adjusted for age, race and gender in regression analysis. Older AML patients had longer remission and survival when consolidated with FLAG regimen after the induction chemotherapy.

Entropy is a nonparametric alternative of variance and has been used as a measure of risk in portfolio analysis. In this paper, the computation of entropy risk for a given set of data is discussed with illustration. A comparison between entropy-based portfolio models is made. We propose a natural extension of the mean entropy portfolio to make it more general and diversified. In terms of performance, this new model is similar to the mean-entropy portfolio when applied to real and simulated data, and offers higher return if no constraint is set for the desired return; also it is found to be the most diversified portfolio model.

This study used a non-linear SEIR model to analyze the spread of COVID-19 in Malaysia. The model considered vaccines, booster doses, hospitalized cases, and various infectious cases. The model was fitted to real data using MATLAB's ode solver and the particle swarm optimization method. The results revealed that booster vaccines significantly reduced the total number of infected cases by 62% when 70% of the population received them. This model can help policymakers to make crucial decisions to prevent future outbreaks.