Meta-Heuristic Optimization of LSTM-Based Deep Network for Boosting the Prediction of Monkeypox Cases

Abstract

Recent technologies such as artificial intelligence, machine learning, and big data are essential for supporting healthcare monitoring systems, particularly for monitoring Monkeypox confirmed cases. Infected and uninfected cases around the world have contributed to a growing dataset, which is publicly available and can be used by artificial intelligence and machine learning to predict the confirmed cases of Monkeypox at an early stage. Motivated by this, we propose in this paper a new approach for accurate prediction of the Monkeypox confirmed cases based on an optimized Long Short-Term Memory (LSTM) deep network. To fine-tune the hyper-parameters of the LSTM-based deep network, we employed the Al-Biruni Earth Radius (BER) optimization algorithm; thus, the proposed approach is denoted by BER-LSTM. Experimental results show the effectiveness of the proposed approach when assessed using various evaluation criteria, such as Mean Bias Error, which is recorded as (0.06) using BER-LSTM. To prove the superiority of the proposed approach, six different machine learning models are included in the conducted experiments. In addition, four different optimization algorithms are considered for comparison purposes. The results of this comparison confirmed the superiority of the proposed approach. On the other hand, several statistical tests are applied to analyze the stability and significance of the proposed approach. These tests include one-way Analysis of Variance (ANOVA), Wilcoxon, and regression tests. The results of these tests emphasize the robustness, significance, and efficiency of the proposed approach.

The study of human monkeypox disease in 2022 using the epidemic models: herd immunity and the basic reproduction number case

“…Some countries applied multiple procedures for limiting the spreading of the 2022 human MPOX. The use of the epidemic models 36 – 39 for the study of the 2022 MPOX disease spreading is an important tool because these models include lots of important indicators of the disease. Although lots of the recent studies about the outbreak of the 2022 human MPOX diseases focused on the reporting of cases or possible prevention of the disease 40 – 48 , in this study, the simple SIR (Susceptible compartment S, Infectious compartment I, Recovered compartment R) model with mortality is employed for the discussion of herd immunity and the basic reproduction number of the 2022 human MPOX disease.…”

Monkeypox detection from skin lesion images using an amalgamation of CNN models aided with Beta function-based normalization scheme

“…We observe the literature to have some brainstorming ideas for solutions to the challenges in the domain of medical image processing. In particular, there have been some preliminary studies performed in this domain [24][25][26]. However, deep learning-based architectures as we see them in the literature do not provide ultimate reliability most of the time [4,16,17].…”

Deep transfer learning approaches for Monkeypox disease diagnosis

“…Therefore, a TL-based model also needs to be evaluated with various optimizers on different datasets in order to understand the model’s stability as well. Most of the previous research also did not provide any clear explanation as to whether they had used generalization and regularization approaches ( Eid et al, 2022 , Haque, Islam et al, 2022 , Islam and Shin, 2022 , Sahin et al, 2022 ). Therefore, it is also not clear if their proposed model is suffering from overfitting issues or not, even though the reported accuracy is much higher ( Akin et al, 2022 , Haque, Ahmed et al, 2022 ).…”