Perovskite solar cells (PSCs) have drawn significant consideration as a competing solar cell technology because of the drastic advance in their power conversion efficiency (PCE) over the last two decades. The interfaces between the electron transport layer (ETL) and the absorber layer and between the absorber layer and the hole transport layer (HTL) have a major impact on the performance of the PSCs. In this paper, we have investigated the defect interfaces between ETL/absorber layer and absorber layer/HTL of calibrated experimental CH ₃ NH ₃ PbX ₃ lead-based and FASnI ₃ lead-free PSCs. The influence of the defect interfaces is studied in order to find the optimum value for the maximum possible PCE. While the PCE has not been enhanced considerably for the lead-based, it is boosted from 1.76% to 5.35% for lead-free PSCs. Also, bulk traps were found to have minor role in comparison with interface traps for the lead-free cell while they have a significant impact for the lead-based cell. The results presented in this work would shed some light on designing interface defects of various types of practical PSC structures and demonstrates the crucial impact of the interface defects on lead-free vs lead-based PSCs. All simulation studies are performed by using SCAPS-1D simulator.

Security attacks on legitimate websites to steal users’ information, known as phishing attacks, have been increasing. This kind of attack does not just affect individuals’ or organisations’ websites. Although several detection methods for phishing websites have been proposed using machine learning, deep learning, and other approaches, their detection accuracy still needs to be enhanced. This paper proposes an optimized stacking ensemble method for phishing website detection. The optimisation was carried out using a genetic algorithm (GA) to tune the parameters of several ensemble machine learning methods, including random forests, AdaBoost, XGBoost, Bagging, GradientBoost, and LightGBM. The optimized classifiers were then ranked, and the best three models were chosen as base classifiers of a stacking ensemble method. The experiments were conducted on three phishing website datasets that consisted of both phishing websites and legitimate websites—the Phishing Websites Data Set from UCI (Dataset 1); Phishing Dataset for Machine Learning from Mendeley (Dataset 2, and Datasets for Phishing Websites Detection from Mendeley (Dataset 3). The experimental results showed an improvement using the optimized stacking ensemble method, where the detection accuracy reached 97.16%, 98.58%, and 97.39% for Dataset 1, Dataset 2, and Dataset 3, respectively.

In this work, we report on the effect of substituting the active intrinsic i-layer on a conventional pin structure of lead-free perovskite solar cell (PSC) by a homo p-n junction, keeping the thickness of the active layer constant. It is expected that when the active i-layer is substituted by a p-n homo junction, one can increase the collection efficiency of the photo-generated electrons and holes due to the built-in electric field of the homo junction. The impact of the technological and physical device parameters on the performance parameters of the solar cell have been worked out. It was found that p-side thickness must be wider than the n-side, while its acceptor concentration should be slightly lower than the donor concentration of the n-side to achieve maximum efficiency. In addition, different absorber types, namely, i-absorber, n-absorber and p-absorber, are compared to the proposed pn-absorber, showing a performance-boosting effect when using the latter. Moreover, the proposed structure is made without a hole transport layer (HTL) to avoid the organic issues of the HTL materials. The back metal work function, bulk trap density and ETL material are optimized for best performance of the HTL-free structure, giving J_sc = 26.48, V_oc = 0.948 V, FF = 77.20 and PCE = 19.37% for AM1.5 solar spectra. Such results highlight the prospective of the proposed structure and emphasize the importance of using HTL-free solar cells without deteriorating the efficiency. The solar cell is investigated by using SCAPS simulator.

Aim/Purpose: Effective e-learning systems need to incorporate student characteristics such as learning style and knowledge level in order to provide a more personalized and adaptive learning experience. However, there is a need to investigate how and when to provide adaptivity based on student characteristics, and more importantly, to evaluate its value in learning enhancement. This study aims to bridge that gap by examining the effect of different modes of learning material adaptation and their sequences to the learning style and knowledge level of students in e-learning systems. Background: E-learning systems aim to provide acceptability and interactivity between students, instructors, and learning content anytime and anywhere. However, traditional systems are typically designed for generic students irrespective of individual requirements. Successful e-learning systems usually consider student characteristics such as learning style and knowledge level to provide more personalized and adaptive student-system interaction. Methodology: A controlled experiment was conducted in a learning context with 174 subjects to evaluate the learning effectiveness of adaptivity in e-learning systems. Contribution: The main contributions of the paper are threefold. First, a novel adaptive approach is proposed based on a specific learning style model and knowledge level. Second, the approach is implemented in an e-learning system to teach computer security, the application domain. Third, a rigorous experimental evaluation of the learning effect of the adaptive approach is offered. Findings: The results indicate that adaptation according to the combination of learning style and knowledge level produces significantly better learning gains, both in the short-term and medium-term, than adaptation according to either trait individually. Recommendations for Practitioners: Practitioners should consider the combination of learning style and knowledge level when delivering and presenting learning material to their students. Recommendation for Researchers: Researchers should consider sound educational models when designing adaptive e-learning systems. Also, rigorous and carful experimental design evaluations should be taken into account. Impact on Society: Universities and e-learning industries can benefit from the proposed adaptive approach and the findings in designing and developing more personalized and adaptive e-learning systems. The incorporation of student characteristics, especially learning style and knowledge level, may be used to enhance learning. Future Research: The experiment might be duplicated with a focus on longer-term learning gains by including more subjects and more learning resources. Also, the study might be expanded to application domains other than computer security. Moreover, other variables such as student satisfaction, motivation, and affective state might be explored to further the understanding of the effect of adaptivity on learning gains.

The rapid expansion of medical data poses numerous challenges for Machine Learning (ML) tasks due to their potential to include excessive noisy, irrelevant, and redundant features. As a result, it is critical to pick the most pertinent features for the classification task, which is referred to as Feature Selection (FS). Among the FS approaches, wrapper methods are designed to select the most appropriate subset of features. In this study, two intelligent wrapper FS approaches are implemented using a new meta-heuristic algorithm called Sand Cat Swarm Optimizer (SCSO). First, the binary version of SCSO, known as BSCSO, is constructed by utilizing the S-shaped transform function to effectively manage the binary nature in the FS domain. However, the BSCSO suffers from a poor search strategy because it has no internal memory to maintain the best location. Thus, it will converge very quickly to the local optimum. Therefore, the second proposed FS method is devoted to formulating an enhanced BSCSO called Binary Memory-based SCSO (BMSCSO). It has integrated a memory-based strategy into the position updating process of the SCSO to exploit and further preserve the best solutions. Twenty one benchmark disease datasets were used to implement and evaluate the two improved FS methods, BSCSO and BMSCSO. As per the results, BMSCSO acted better than BSCSO in terms of fitness values, accuracy, and number of selected features. Based on the obtained results, BMSCSO as a FS method can efficiently explore the feature domain for the optimal feature set.