A Turf-Based Feature Selection Technique for Predicting Factors Affecting Human Health during Pandemic.

Worldwide, COVID-19 is a highly contagious epidemic that has affected various fields. Using Artificial Intelligence (AI) and particular feature selection approaches, this study evaluates the aspects affecting the health of students throughout the COVID-19 lockdown time. The research presented in this paper plays a vital role in indicating the factor affecting the health of students during the lockdown in the COVID-19 pandemic. The research presented in this article investigates COVID-19's impact on student health using feature selections. The Filter feature selection technique is used in the presented work to statistically analyze all the features in the dataset, and for better accuracy. ReliefF (TuRF) filter feature selection is tuned and utilized in such a way that it helps to identify the factors affecting students' health from a benchmark dataset of students studying during COVID-19. Random Forest (RF), Gradient Boosted Decision Trees (GBDT), Support Vector Machine (SVM), and 2- layer Neural Network (NN), helps in identifying the most critical indicators for rapid intervention. Results of the approach presented in the paper identified that the students who maintained their weight and kept themselves busy in health activities in the pandemic, such student's remained healthy through this pandemic and study from home in a positive manner. The results suggest that the 2- layer NN machine-learning algorithm showed better accuracy (90%) to predict the factors affecting on health issues of students during COVID-19 lockdown time.

Unexpected acceleration of Ultrasonic-Assisted iodide dosimetry in the catalytic presence of ionic liquids.

This study investigates the potential of using small amounts of ionic liquids (IL) to enhance ultrasound-assisted extraction of lipids content from green microalgae. Three imidazolium-based ILs (butyl, octyl and dodecyl), each of them with two anions (bromide and acetate) were tested as additives. Viscosity and surface tension of the ILs aqueous mixtures were analyzed to determine the influence of ILs' anions and alkyl chain length, whereas KI dosimetry experiments were used as an indicator of radicals formation. A key finding suggests that the small addition of ILs improves the ultrasonication either by enhancing the viscosity and reducing the water surface tension, leading to a more powerful acoustic cavitation process or by increasing HO° production likely to oxidize the microalgae cells membranes, and consequently disrupting them on a more efficient manner. KI dosimetry also revealed that long ILs alkyl chain is detrimental. This experimental observation is confirmed thus strengthened as the yield of extracted lipids from green microalgae has shown an incremental trend when the IL concentration also increased. These hypotheses are currently under investigation to spot detailed impact of ILs on cavitation process.

Ionic liquids toxicity on fresh water microalgae, Scenedesmus quadricauda, Chlorella vulgaris &Botryococcus braunii; selection criterion for use in a two-phase partitioning bioreactor (TPPBR).

A promising method of Carbon dioxide (CO2) valorization is to use green microalgae photosynthesis to process biofuel. Two Phase Partitioning Bioreactors (TPPBR) offer the possibility to use non-aqueous phase liquids (NAPL) to enhance CO2 solubility; thus making CO2 available to maximize algae growth. This requires relatively less toxic hydrophobic Ionic Liquids (ILs) that comprise a new class of ionic compounds with remarkable physicochemical properties and thus qualifies them as NAPL candidates. This paper concerns the synthesis of ILs with octyl and butyl chains as well as different cations containing aromatic (imidazolium, pyridinium) and non-aromatic (piperidinum, pyrrolidinium) rings for CO2 absorption studies. The authors measured their respective toxicity levels on microalgae species, specifically, Scenedesmus quadricauda, Chlorella vulgaris and Botryococcus braunii. Results revealed that octyl-based ILs were more toxic than butyl-based analogues. Such was the case for bmim-PF6 at double saturation with an absorbance of 0.11, compared to Omim-PF6 at 0.17, bmim-NTf2 at 0.02, and Omim-NTf2 at 0.14, respectively. CO2 uptake results for ILs bearing octyl-based chains compared to the butyl analog were 54% (nCO2/nIL) (i.e., moles of CO2 moles of IL) and 38% (nCO2/nIL), respectively. Conclusively, 1-butyl-1-methylpiperidinium absorbed 13% (nCO2/nIL) and appeared the least toxic, having an absorbance of 0.25 at 688 nm (double saturation at 7 d) compared to 1-butyl-3-methylimidazolium, which showed the highest toxicity with zero absorbance. Accordingly, these findings suggest that 1-butyl-1-methylpiperidinium is capable of transporting CO2 to a system containing green microalgae without causing significant harm; thus allowing its use in TPPBR technology.