Biblio

Frauds are known to be dynamic and have no patterns, hence they are not easy to identify. Fraudsters use recent technological advancements to their advantage. They somehow bypass security checks, leading to the loss of millions of dollars. Analyzing and detecting unusual activities using data mining techniques is one way of tracing fraudulent transactions. transactions. This paper aims to benchmark multiple machine learning methods such as k-nearest neighbor (KNN), random forest and support vector machines (SVM), while the deep learning methods such as autoencoders, convolutional neural networks (CNN), restricted boltzmann machine (RBM) and deep belief networks (DBN). The datasets which will be used are the European (EU) Australian and German dataset. The Area Under the ROC Curve (AUC), Matthews Correlation Coefficient (MCC) and Cost of failure are the 3-evaluation metrics that would be used.

Having significant role in the storing, delivering and conversion of the energy, the permanent magnets are key elements in the actual technology. In many applications, the gap between ferrites and rare earths (RE) based sintered permanent magnets is nowadays filled by RE bonded magnets, used in more applications, below their magnetic performances. Therewith, the recent trends in the RE market concerning their scarcity, impose EU to consider alternative magnets (without RE) to fill such gap. The paper presents the chemical synthesis of the exchange coupled SrFe12O19/CoFe2O4 nanocomposites, based on nanoferrites. The appropriate annealing leads to the increasing of the main magnetic characteristics, saturation magnetization MS and intrinsic coercivity Hc, in the range of 49 - 53 emu/g, respectively 126.5 - 306 kA/m. The value reached for the ratio between remanent magnetization and saturation magnetization is higher than 0.5, fact that proved that between the two magnetic phases occurred exchange interaction.