Pattern recognition of omicron variants from amalgamated multi-focus EEG signals and X-ray images using deep transfer learning

The World Health Organization (WHO) in March 2020 declared an infectious disease caused by the Sars-CoV-2 virus known as COVID-19 as global epidemic. COVID-19 has many variants, the most recent and lethal being the Omicron variant, which has seen an exponential increase in infected cases. The fast spread of Omicron makes diagnosis a key responsibility for health care practitioners. Moreover, recognizing and isolating infected people helps to control the Omicron's spread. For the diagnosis, RT-PCR test is performed which is time consuming and costly. Moreover, in most of the countries the testing is not available for large number of patients due to the unavailability of resources. This research work presents a deep learning-based approach for effectively diagnosis the virus-infected patients using EEG and X-ray images. Effective layered architecture composed of preprocessing, feature extraction (wavelet transformation and efficientNet) and transfer learning based classification has been designed to identify the Omicron patient. From the experimental analysis, it has been concluded that the proposed model produces 96.98 %accuracy with only 12 percent loss and 96 % correct prediction. In order to validate the proposed model, a dataset of EEG Images as well as chest X-rays based images have been collected from online repositories and further classified into 30 % EEG images of normal COVID and 70 % EEG images of Omicron respectively.

An Improved Machine-Learning Approach for COVID-19 Prediction Using Harris Hawks Optimization and Feature Analysis Using SHAP.

A healthcare monitoring system needs the support of recent technologies such as artificial intelligence (AI), machine learning (ML), and big data, especially during the COVID-19 pandemic. This global pandemic has already taken millions of lives. Both infected and uninfected people have generated big data where AI and ML can use to combat and detect COVID-19 at an early stage. Motivated by this, an improved ML framework for the early detection of this disease is proposed in this paper. The state-of-the-art Harris hawks optimization (HHO) algorithm with an improved objective function is proposed and applied to optimize the hyperparameters of the ML algorithms, namely HHO-based eXtreme gradient boosting (HHOXGB), light gradient boosting (HHOLGB), categorical boosting (HHOCAT), random forest (HHORF) and support vector classifier (HHOSVC). An ensemble technique was applied to these optimized ML models to improve the prediction performance. Our proposed method was applied to publicly available big COVID-19 data and yielded a prediction accuracy of 92.38% using the ensemble model. In contrast, HHOXGB provided the highest accuracy of 92.23% as a single optimized model. The performance of the proposed method was compared with the traditional algorithms and other ML-based methods. In both cases, our proposed method performed better. Furthermore, not only the classification improvement, but also the features are analyzed in terms of feature importance calculated by SHapely adaptive exPlanations (SHAP) values. A graphical user interface is also discussed as a potential tool for nonspecialist users such as clinical staff and nurses. The processed data, trained model, and codes related to this study are available at GitHub.