RESUMEN
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.
RESUMEN
Severe deterioration of water quality occurs during jute retting in ponds, canals, floodplain lakes, and other inland water bodies in the rural areas of West Bengal in India. Attempts were made to evaluate changes in the physicochemical parameters of water caused by jute retting, and their impact on the survival of two species of freshwater fish (Labeo rohita and Hypophthalmicthys molitrix) and two species of freshwater invertebrate (Daphnia magna, a Cladocera, and Branchiura sowerbyi, an Oligochaeta). Results showed that jute retting in a pond for 30 days resulted in a sharp increase in the BOD (>1,000 times) and COD (>25 times) of the water, along with a sharp decrease in dissolved oxygen (DO). Free CO(2), total ammonia, and nitrate nitrogen also increased (three to five times) in water as a result of jute retting. Ninety-six-hour static bioassays performed in the laboratory with different dilutions of jute-retting water (JRW) revealed that D. magna and B. sowerbyi were not susceptible to even the raw JRW whereas fingerlings of both species of fish were highly susceptible, L. rohita being more sensitive (96 h LC(50) 37.55% JRW) than H. molitrix (96 h LC(50) 57.54% JRW). Mortality of fish was significantly correlated with the percentage of JRW.