Machine learning techniques for anti-money laundering (AML) solutions in suspicious transaction detection: a review

Money laundering has been affecting the global economy for many years. Large sums of money are laundered every year, posing a threat to the global economy and its security. Money laundering encompasses illegal activities that are used to make illegally acquired funds appear legal and legitimate. This paper aims to provide a comprehensive survey of machine learning algorithms and methods applied to detect suspicious transactions. In particular, solutions of anti-money laundering typologies, link analysis, behavioural modelling, risk scoring, anomaly detection, and geographic capability have been identified and analysed. Key steps of data preparation, data transformation, and data analytics techniques have been discussed; existing machine learning algorithms and methods described in the literature have been categorised, summarised, and compared. Finally, what techniques were lacking or under-addressed in the existing research has been elaborated with the purpose of pinpointing future research directions.     

Cytocompatibility of Ar plasma treated and Au nanoparticle-grafted PE

Polyethylene (PE) was irradiated with inert Ar plasma, and the chemically active PE surface was grafted with Au nanoparticles. The composition and the structure of the modified PE surface were studied using X-ray photoelectron spectroscopy (XPS) and Rutherford backscattering spectroscopy (RBS). Changes in the surface wettability were determined from the contact angle measured in a reflection goniometer. The changes in the surface roughness and morphology were followed by atomic force microscopy (AFM). The modified PE samples were seeded with rat vascular smooth muscle cells (VSMC) or mouse NIH 3T3 fibroblasts, and their adhesion and proliferation were studied. We found that plasma discharge and Au grafting lead to dramatic changes in the surface morphology and roughness of PE. The Au nanoparticles were found not only on the sample surface, but also in the sample interior up to the depth of about 100 nm. In addition, plasma modification of the PE surface, followed with grafting Au-nanoparticles, significantly increased the attractiveness of the PE surface for the adhesion and growth of VSMC, and particularly for mouse embryonic 3T3 fibroblasts.     

Improved interfacial adhesion with the help of functional polyhedral oligomeric silsesquioxanes in silicone rubber/rayon fiber composites: Physical,mechanical, thermal,and morphological properties

The aim of this article is to improve the interfacial adhesion between silicone rubber (SR) and Rayon fiber by the help of functional hybrid POSS nanoparticles. Two POSS types were compared, octavinyl-POSS (O-POSS) and methacryl-POSS (M-POSS), having reactive  CC double bonds that can impart in peroxide crosslinking. O-POSS is nonpolar, whereas M-POSS is polar and is able to make H-bond with Rayon fibers. POSS type and their concentrations were examined as the experimental parameters. H-adhesion tests indicated that both POSS types enhanced the adhesion of SR composites to Rayon fibers compared with control recipe. Specifically, slightly higher values were obtained with the use of M-POSS. It was observed that both O-POSS and M-POSS slowed down the curing rate but increased the degree of crosslinking. The cure extent of O-POSS containing composites was found to be higher than that of M-POSS containing ones. Thermal gravimetric analyses revealed that thermal stability of SR composites was significantly improved by the addition of POSS particles. Higher char yield and degradation temperatures were obtained with O-POSS at higher loadings with respect to M-POSS. The POSS distribution at lower loading levels was found to be homogenous for both POSS types as observed from scanning electron microscope and transmission electron microscope.     

Performance Analysis of Full-Duplex Vehicle-to-Vehicle Relay System over Double-Rayleigh Fading Channels

Mobile Networks and Applications - In this paper, we study the performance of a full-duplex (FD) relay system in vehicle-to-vehicle (V2V) communication. In this relay communication system, the...     

Effects of YSZ Additions on Thermoelectric Properties of Nb-Doped Strontium Titanate

The effect of yttria-stabilized zirconia (YSZ) with a low thermal conductivity on the thermoelectric properties of Nb-doped SrTiO₃ bulk materials, which were fabricated by the conventional normal pressure sintering method in an Ar atmosphere, was examined. YSZ additions reduced the thermal conductivity but significantly enhanced the electrical conductivity. However, the Seebeck coefficient was nearly independent of YSZ content. Thus, the ZT value was enhanced, and a sample with 3 wt.% YSZ displayed the maximum ZT value, 0.21, at 900 K. Additionally, the reason for the reduced thermal conductivity and enhanced electrical conductivity by YSZ additions was investigated in detail.     

Confinement-Shear Lattice Model for Concrete Damage in Tension and Compression: II. Computation and Validation

The concrete material model developed in the preceding Part I of this study is formulated numerically. The new model is then verified by comparisons with experimental data for compressive and tensile uniaxial tests, biaxial tests, and triaxial tests, as well as notched tests of mode I fracture and size effect.     

自焙炭砖与焙烧炭块在硅铁电炉上的应用

介绍了硅铁电炉筑炉应用炭质材料自焙炭砖和焙烧炭块的性能和使用效果.     

The vocational hygienic training of the food industry at present

In article the problem of vocational hygienic training of the food industry workers is presented. Offers on perfection of this work are given.     

The Bonding Properties of Solid Steel to Liquid Aluminum

The bonding of solid steel plate to liquid aluminum was studied using rapid solidification. The relationship models of interfacial shear strength and thickness of interfacial layer of bonding plate vs bonding parameters ( such as preheat temperature of steel plate, temperature of aluminum liquid and bonding time ) were respectively established by artificial neural networks perfectly. The bonding parameters for the largest interfacial shear strength were optimized with genetic algorithm successfully. They are 226℃ for preheating temperature of steel plate, 723℃ for temperature of aluminum liquid and 15.8s for bonding time, and the largest interfacial shear strength of bonding plate is 71.6MPa. Under these conditions, the corresponding reasonable thickness of interfacial layer (10.8μm) is gotten using the relationship model established by artificial neural networks.