Porous carbon derived from grape marc (GM) was synthesized via carbonization and chemical activation processes. Extrinsic nitrogen (N)-dopant in GM, activated by KOH, could render its potential use in supercapacitors effective. The effects of chemical activators such as potassium hydroxide (KOH) and zinc chloride (ZnCl2) were studied to compare their activating power toward the development of pore-forming mechanisms in a carbon electrode, making them beneficial for energy storage. GM carbon impregnated with KOH for activation (KAC), along with urea as the N-dopant (KACurea), exhibited better morphology, hierarchical pore structure, and larger surface area (1356 m2 g−1) than the GM carbon activated by ZnCl2 (ZnAC). Moreover, density functional theory (DFT) investigations showed that the presence of N-dopant on a graphite surface enhances the chemisorption of O adsorbates due to the enhanced charge-transfer mechanism. KACurea was tested in three aqueous electrolytes with different ions (LiOH, NaOH, and NaClO4), which delivered higher specific capacitance, with the NaOH electrolyte exhibiting 139 F g−1 at a 2 mA current rate. The NaOH with the alkaline cation Na+ offered the best capacitance among the electrolytes studied. A multilayer perceptron (MLP) model was employed to describe the effects of synthesis conditions and physicochemical and electrochemical parameters to predict the capacitance and power outputs. The proposed MLP showed higher accuracy, with an R2 of 0.98 for capacitance prediction.
Deep learning (DL) has achieved superior classification in many applications due to its capability of extracting features from the data. However, the success of DL comes with the tradeoff of possible overfitting. The bias towards the data it has seen during the training process leads to poor generalisation. One way of solving this issue is by having enough training data so that the classifier is invariant to many data patterns. In the literature, data augmentation has been used as a type of regularisation method to reduce the chance for the model to overfit. However, most of the relevant works focus on image, sound or text data. There is not much work on numerical data augmentation, although many real-world problems deal with numerical data. In this paper, we propose using a technique based on Fuzzy C-Means clustering and fuzzy membership grades. Fuzzy-related techniques are used to address the variance problem by generating new data items based on fuzzy numbers and each data item's belongings to different fuzzy clusters. This data augmentation technique is used to improve the generalisation of a Deep Neural Network that is suitable for numerical data. By combining the proposed fuzzy data augmentation technique with the Dropout regularisation technique, we manage to balance the classification model's bias-variance tradeoff. Our proposed technique is evaluated using four
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.