RESUMEN
In the present study, various statistical and machine learning (ML) techniques were used to understand how device fabrication parameters affect the performance of copper oxide-based resistive switching (RS) devices. In the present case, the data was collected from copper oxide RS devices-based research articles, published between 2008 to 2022. Initially, different patterns present in the data were analyzed by statistical techniques. Then, the classification and regression tree algorithm (CART) and decision tree (DT) ML algorithms were implemented to get the device fabrication guidelines for the continuous and categorical features of copper oxide-based RS devices, respectively. In the next step, the random forest algorithm was found to be suitable for the prediction of continuous-type features as compared to a linear model and artificial neural network (ANN). Moreover, the DT algorithm predicts the performance of categorical-type features very well. The feature importance score was calculated for each continuous and categorical feature by the gradient boosting (GB) algorithm. Finally, the suggested ML guidelines were employed to fabricate the copper oxide-based RS device and demonstrated its non-volatile memory properties. The results of ML algorithms and experimental devices are in good agreement with each other, suggesting the importance of ML techniques for understanding and optimizing memory devices.
RESUMEN
Dye-sensitized solar cells (DSSCs) are one of the most versatile and low-cost solar cells. However, DSSCs are prone to low power conversion efficiency (PCE) compared to their counterparts, owing to their different synthesis parameters and process conditions. Therefore, designing efficient DSSCs and identifying the parameters that control the PCE of DSSCs are a critical tasks. We have collected data from hydrothermally synthesized DSSCs in the present work, published from 2005 to 2020. In line with publishing trends in the said period, we evaluate ZnO as a popular photoactive material for DSSC applications. We further analyzed the performance of hydrothermally synthesized ZnO DSSCs using different statistical techniques and provided some significant insights. We further applied the machine-learning technique with a decision tree algorithm to understand and discover the possible set of rules and heuristics that govern the morphology of the hydrothermally grown ZnO. In addition, we also employed supervised and unsupervised machine-learning models using conventional decision trees and classification and regression trees, respectively, to identify the dependence of the PCE of ZnO DSSCs on the different synthesis parameters. The reported work also evidences the PCE predictions of the ZnO DSSCs by using random forest and artificial neural network algorithms. The results substantiate that the random forest and artificial neural network algorithms successfully predict the PCE of the ZnO DSSCs with reasonable accuracy. Thus, we present a novel approach of applying statistical analysis and machine-learning algorithms to understand, discover, and predict the performance of DSSCs. We recommend extending the said know-how to other solar cells to identify rules and heuristics and experimentally realize highly efficient solar cells in shrinking manufacturing windows with a cost-effective approach.