A cost-sensitive decision tree approach for fraud detection

With the developments in the information technology, fraud is spreading all over the world, resulting in huge financial losses. Though fraud prevention mechanisms such as CHIP&PIN are developed for credit card systems, these mechanisms do not prevent the most common fraud types such as fraudulent credit card usages over virtual POS (Point Of Sale) terminals or mail orders so called online credit card fraud. As a result, fraud detection becomes the essential tool and probably the best way to stop such fraud types. In this study, a new cost-sensitive decision tree approach which minimizes the sum of misclassification costs while selecting the splitting attribute at each non-terminal node is developed and the performance of this approach is compared with the well-known traditional classification models on a real world credit card data set. In this approach, misclassification costs are taken as varying. The results show that this cost-sensitive decision tree algorithm outperforms the existing well-known methods on the given problem set with respect to the well-known performance metrics such as accuracy and true positive rate, but also a newly defined cost-sensitive metric specific to credit card fraud detection domain. Accordingly, financial losses due to fraudulent transactions can be decreased more by the implementation of this approach in fraud detection systems.     

A comprehensive study on mid-level representation and ensemble learning for emotional analysis of video material

Multimedia Tools and Applications - In today’s society where audio-visual content such as professionally edited and user-generated videos is ubiquitous, automatic analysis of this content is...     

Pre-service teachers' perspectives of the diffusion of information and communications technologies (ICTs) and the effect of case-based discussions (CBDs)

This study investigates pre-service teachers' perspectives of the diffusion of information and communication technologies (ICTs) in elementary education and the effect of case-based discussions (CBDs). The sample consisted of 170 first-year pre-service teachers from elementary teacher education programs of the largest teacher education college in Turkey. The cases used in the study were obtained from a case repository at http://ornekolay.org, indexing teaching cases from elementary classrooms of the capital city of Turkey. The cases were mainly text-based and presented stories of elementary teachers' in-class usage of ICTs. A quasi-experimental pretest-posttest design was executed to test the effect of pre-service teachers' perspectives on ICTs diffusion in elementary teaching. Three scales were developed based on Rogers' Diffusion of Innovation Theory (2003) to measure pre-service teachers' preferred innovativeness, innovation perceptions, and innovation decisions in the use of ICTs. The results showed that pre-service teachers had pre-established perspectives, mainly positive, about the diffusion of ICTs in elementary teaching; their perceptions about innovativeness and relative advantage were the main indicators of persuasion and decision; and CBDs positively affected their perceptions such that their computer-related persuasion and decisions positively increased.     

Salt and pepper noise filtering with fuzzy-cellular automata

A new image denoising algorithm is proposed to restore digital images corrupted by impulse noise. It is based on two dimensional cellular automata (CA) with the help of fuzzy logic theory. The algorithm describes a local fuzzy transition rule which gives a membership value to the corrupted pixel neighborhood and assigns next state value as a central pixel value. The proposed method removes the noise effectively even at noise level as high as 90%. Extensive simulations show that the proposed algorithm provides better performance than many of the existing filters in terms of noise suppression and detail preservation. Also, qualitative and quantitative measures of the image produce better results on different images compared with the other algorithms.     

Determination of radiation attenuation coefficients of heavyweight- and normal-weight concretes containing colemanite and barite for 0.663 MeV γ-rays

Accurate measurements have been made to determine radiation transmission of concretes produced with barite, colemanite and normal aggregate by using beam transmission method for 0.663 MeV γ-rays energy of ¹³⁷Cs radioactive isotopes by using NaI(Tl) scintillation detector. Linear and mass attenuation coefficients of thirteen heavy- and four normal-weight concretes were calculated. It was determined that the linear attenuation coefficient (μ, cm⁻¹) decreased with colemanite concentration and increased with barite concentration in both type of the concretes. Mass attenuation coefficient values of our concretes were compared with the values proposed by the United States National Institute of Standards and Technology (NIST).     

Smart structures and their applications on active vibration control: Studies in the Department of Aerospace Engineering, METU

This work presents the theoretical and experimental studies conducted in Aerospace Engineering Department of Middle East Technical University on smart structures with particular attention given to the structural modelling characteristics and active suppression of in-vacuo vibrations. The smart structures considered in these analyses are finite and flat aluminium cantilever beam-like (called as smart beam) and plate-like (called as smart fin) structures with surface bonded lead–zirconate–titanate patches. Finite element models of smart beam and smart fin are obtained. Then the experimental studies regarding open loop behaviour of the structures are performed by using strain gauges and laser displacement sensor to determine the system models. Further studies are carried out to obtain H _∞ and μ-synthesis controllers which are intended to be used in the suppression of free and forced vibrations of the smart structures. It is observed that satisfactory attenuation levels are achieved and robust performance of the systems in the presence of uncertainties is ensured. In that respect a comparative study involving H _∞ and sliding mode controls is also conducted. Recently, the studies involving aerodynamic loading are also gathering pace.     

Palladium-Catalyzed Suzuki–Miyaura Reaction Using Saturated N-Heterocarbene Ligands

Recent studies have pointed to the heptamethylbenzenium cation as a prominent intermediate in the methanol to hydrocarbons (MTH) reaction. The reactions of the heptamethylbenzenium cation in a H-beta zeolite was studied at 300 °C by feeding its corresponding base (WHSV = 0.4 h^?1). The reactant was converted completely into aliphatic products, polymethylbenzenes and coke under the employed conditions. The results testify that the proposed reaction intermediate yields the same product spectrum as methanol. The composition of the material retained in the catalyst micropores after 15 min of reaction was determined by dissolving the catalyst in 15% HF. Polymethylated benzenes (predominantly pentamethylbenzene), dihydro-trimethylnaphthalenes, and hexamethylnaphthalene were the major components. The results also support the idea that the lowest naphthalene derivative is formed from the heptamethylbenzenium cation by a molecular rearrangement. Hence, the heptamethylbenzenium cation is inherently linked to both product formation and catalyst deactivation in the MTH reaction.