Dr. Ammar Mohammed

Abstract Formal concept analysis (FCA) visualizes formal concepts in terms of a concept lattice. Usually, it is an NP-problem and consumes plenty of time and storage space to update the changes of the lattice. Thus, introducing an efficient way to update and maintain such lattices is a significant area of interest within the field of FCA and its applications. One of those vital FCA applications is the association rule mining (ARM), which aims at generating a loss-less nonredundant compact Association Rule-basis (AR-basis). Currently, the real-world data rapidly overgrow that asks the need for updating the existing concept lattice and AR-basis upon data change continually. Intuitively, updating and maintaining an existing concept-lattice or AR-basis is much more efficient and consistent than reconstructing them from scratch, particularly in the case of massive data. So far, the area of updating both concept lattice and AR-basis has not received much attention. Besides, few noncomprehensive studies have focused only on updating the concept lattice. From this point, this article comprehensively introduces basic knowledge regarding updating both concept lattices and AR-basis with new illustrations, formalization, and examples. Also, the article reviews and compares recent remarkable works and explores the emerging future research trends. This article is categorized under: Algorithmic Development > Association Rules Fundamental Concepts of Data and Knowledge > Knowledge Representation Technologies > Association Rules

Over the last decade Deep learning-based models surpasses classical machine learning models in a variety of text classification tasks. The primary challenge with text classification is determining the most appropriate deep learning classifier. Numerous research initiatives incorporated ensemble learning to boost the performance, minimize errors and avoid overfitting. However, the performance of the ensemble-methods is limited by the baseline classifiers and the fusion method. The current study makes the following contributions: First, it proposes a new meta-learning ensemble method that fuses baseline deep learning models using 2-tiers of meta-classifiers. Second, it conducts several experiments on six public benchmark datasets to evaluate the performance of the proposed ensemble. For each benchmark dataset, committees of different deep baseline classifiers are trained, and their best performance is compared with the performance of the proposed ensemble. Furthermore, the paper extends the results by comparing the performance of the proposed ensemble method to other state-of-the-art ensemble methods. The findings indicate that the proposed ensemble method significantly improve the classification accuracy of the baseline deep models. Furthermore, the proposed method outperforms the state-of-art ensemble methods. Finally, using the probability distributions for each class label of the deep baseline models improves the performance of the proposed ensemble method.