Rajalakshmi Engineering College

Ovarian cancer is a major health concern for women, contributing to substantial mortality and morbidity. Timely identification of ovarian cancer is crucial for enhancing patient health and survival rates. Current diagnostic practices involve the manual analysis of various clinical biomarkers to detect ovarian cancer. However, this approach can be subjective, time-consuming, and dependent on the expertise of the medical professional. To optimize workflow efficiency and improve diagnosis accuracy, we develop an automated deep learning model, called EA-ResMLP, which integrates a residual multilayer perceptron with squeeze-and-excitation attention block and explainable artificial intelligence. The integration of residual connections and attention mechanisms contributes to improved diagnostic accuracy by enabling deeper feature learning and emphasizing the most informative features through adaptive recalibration. The experimental results demonstrated that proposed method achieved an accuracy of 92.05%, indicating a 7.98% improvement over the conventional multilayer perceptron. Furthermore, the predictions of the EA-ResMLP model are analyzed using explainable artificial intelligence techniques such as local interpretable model-agnostic explanations, which generate feature contribution charts to highlight the impact of each input feature on the prediction. By integrating model predictions with feature contribution charts, the proposed model provides an explainable framework for ovarian cancer detection.

Topological indices serve as mathematical descriptors for chemical structures, playing a crucial role in elucidating the physicochemical characteristics of compounds. Ambient- stable electroactive graphene nanoribbons are air-stable, electronically tunable and easily fabricated nanostructures, formed by the elongation of nanographene ribbon segments. This study aimed to develop precise topological formulations for three types of ambient-stable electroactive graphene nanoribbons (AEGNR) using graph-theoretical structural measures, and to evaluate their energetic properties along with their 13C NMR spectral characteristics.

The study employs the cut method, which is based on the Djoković-Winkler θ relation, to calculate topological indices.

In this article, we evaluated selected spectral and energetic properties of AEGNR variants.

The computed topological indices based on distance and vertex degree could provide important chemical insights into the properties of AEGNR(l).

We developed exact mathematical expressions for bond-additive molecular descriptors corresponding to three types of ambient-stable electroactive graphene nanoribbons (AEGNRs). An evaluation of HOMO-LUMO energy gaps was also performed for the AEGNR(l) chains.

In this study, palladium impregnated graphene oxide quantum dots (Pd-GOQD) have been synthesized by biogenic carbonization.The formation of Pd-GOQD and GOQD was confirmed by physicochem. techniques such as Brunauer-Emmett-Teller (BET), photoluminescence spectroscopy, XRD, Raman spectroscopy, XPS anal., and HAADF-STEM anal.TEM anal. revealed that GOQD and Pd-GOQD are spherical, with a mean size of around 2.9 and 3.7 nm, resp.The photocatalytic activities of Pd-GOQD and GOQD using methylene blue (MB) and methyl orange (MO) dye under visible light were investigated using spectroscopic anal.Pd-GOQD showed nearly better dye degradation efficiency as 90% dye was reduced within 75 min compared to 50% efficiency of GOQD.Kinetic of the reduction process of MB and MO was well correlated with first-order kinetics.Besides, the Pd-GOQD exhibited its regeneration and reusability as its photo-degradation performance remained unaffected after five successive reuses.Hence GO-Pd nanocomposite was a promising option for removing synthetic dyes from aqueous solutions