Search

This study investigates the application of deep learning, ensemble learning, metaheuristic optimization, and image processing techniques for detecting lung and colon cancers, aiming to enhance treatment efficacy and improve survival rates. We introduce a metaheuristic-driven two-stage ensemble deep learning model for efficient lung/colon cancer classification. The diagnosis of lung and colon cancers is attempted using several unique indicators by different versions of deep Convolutional Neural Networks (CNNs) in feature extraction and model constructions, and utilizing the power of various Machine Learning (ML) algorithms for final classification. Specifically, we consider different scenarios consisting of two-class colon cancer, three-class lung cancer, and five-class combined lung/colon cancer to conduct feature extraction using four CNNs. These extracted features are then integrated to create a comprehensive feature set. In the next step, the optimization of the feature selection is conducted using a metaheuristic algorithm based on the Electric Eel Foraging Optimization (EEFO). This optimized feature subset is subsequently employed in various ML algorithms to determine the most effective ones through a rigorous evaluation process. The top-performing algorithms are refined using the High-Performance Filter (HPF) and integrated into an ensemble learning framework employing weighted averaging. Our findings indicate that the proposed ensemble learning model significantly surpasses existing methods in classification accuracy across all datasets, achieving accuracies of 99.85% for the two-class, 98.70% for the three-class, and 98.96% for the five-class datasets. [ABSTRACT FROM AUTHOR]

Bread scraps with transition metal oxide spinels were utilized to synthesize core–shell magnetic nanocatalyst. The prepared heterogeneous catalyst was characterized using Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), scanning electron microscopy (SEM), Brunauer–Emmett–Teller (BET), thermogravimetric analysis (TGA), and transmission electron microscopy (TEM). This magnetic nanocatalyst opens up a new avenue to introduce a very useful and efficient catalytic system for the one-pot synthesis of tetraketone derivatives via Knoevenagel-Micheal reaction of 1,3 cyclohexanedione and benzaldehyde in ethanol as a green solvent at 50 °C, and one-pot four-component reaction of benzaldehyde, dimedone, ethyl acetoacetate, and hydrazine hydrate via tandem Knoevenagel-Micheal reaction for the synthesis of dihydropyrano[2,3-c] pyrazole derivatives in ethanol. The pharmaceutical properties of dihydropyrano[2,3-c] pyrazole and tetraketones make them both essential compounds. Moreover, the recyclability of the new heterogeneous magnetic catalyst does not significantly deteriorate its catalytic activity, and it can be easily recovered by an external magnet and reused ten times without significant loss of activity, making it environmentally friendly and economically feasible to perform the desired transformations. NBO calculations were carried out at the level of B3LYP/6–311 + + G (d, p) to obtain the atoms' natural charge data to justify the reaction's mechanism. [ABSTRACT FROM AUTHOR]

Magnetic nanoparticles of CuFe2O4 were applied as catalyst system for one-pot thiophosphate synthesis via the reaction of aryl sulfonyl chlorides with H-phosphonates under conventional heating conditions. This is an extremely efficient and green method for thiophosphate synthesis under base- and solvent-free conditions. Various thiophosphates were obtained in good to excellent yields under the optimized reaction conditions in a short time. The catalyst can be easily recycled from the reaction by an external magnetic field and reused for the next run. In this study, TD-DFT B3LYP/6-31 + G(d) calculations are in good accord with the experimental results. A comparison between experimental and theoretical UV-vis absorption spectra of the thiophosphate 3k has been carried out; and a small hypsochromic shift (only ∼ 2 nm) was displayed at maximum absorption. The aim of this work is to investigate the best method and basis set for thiophosphate compounds; therefore, predictions for these compounds can be performed in theoretical studies. [ABSTRACT FROM AUTHOR]