Self-Organising Map Based Framework for Investigating Accounts Suspected of Money Laundering

There has been an emerging interest by financial institutions to develop advanced systems that can help enhance their anti-money laundering (AML) programmes. In this study, we present a self-organising map (SOM) based approach to predict which bank accounts are possibly involved in money laundering cases, given their financial transaction histories. Our method takes advantage of the competitive and adaptive properties of SOM to represent the accounts in a lower-dimensional space. Subsequently, categorising the SOM and the accounts into money laundering risk levels and proposing investigative strategies enables us to measure the classification performance. Our results indicate that our framework is well capable of identifying suspicious accounts already investigated by our partner bank, using both proposed investigation strategies. We further validate our model by analysing the performance when modifying different parameters in our dataset.

Implementing Self Organising Map to Organise the Unstructured Data

Surface reconstruction is significant in reverse engineering because it should present the correct surface with minimum error using the data available. It has become a challenging process when the data are in the unstructured type and the existing methods are still suffering from accuracy issues. The unstructured data will produce an incorrect surface because there is no connectivity information among the data. So, the unstructured data should undergo the organising process to obtain the correct shape. The Self Organising Map (SOM) has been extensively applied in previous works to solve surface reconstruction problems. However, the performance of the SOM models has remained uncertain. It can be evaluated and tested using different types of data sets. The objectives of this research are to examine the performance and to determine the weaknesses of SOM models. 2D SOM, 3D SOM, and Cube Kohonen (CK) SOM models are investigated and tested using three data sets in this research. As shown in the experimental results, the CKSOM model has proved to perform better because it can represent the correct closed surface with the lowest minimum error.

One- and multivariable characteristics of spring barley (Hordeum vulgare L.) cultivars breed at the Nagradowice Plant Breeding Station of the Poznańska Hodowla Roślin, studied in experiments in 2017-2018

The aim of this study was to evaluate the yield variability of spring barley families grown at the Nagradowice Plant Breeding Station of Poznan Plant Breeding against other families studied in years 2017‒2018 in Team Breeding Experiments. Research material included 250 spring barley families cultivated in 2017 and 2018 in 6 locations. Selection of spring barley families for preliminary experiments was based on synthesis of results obtained in inter-plant experiments established in 2016 and 2017 in 5 locations. Combined (due to location) analysis of variance for experimental data was performed for each year and each series of experiments separately. Best Weighted Linear Unbiased Estimators (BWLUE) for the effects of individual sources of variation were included in ANOVA model. Significant effect of location on mean yield was observed in each research year and each series of experiments. Crucial differences were also observed between tested varieties and breeding lines. Moreover, significant interaction between locations and varieties or breeding families was also observed. Self-organising map (SOM) was applied to develop multivariable characteristic of tested families and cultivars of spring barley. Analyses results, i.e. ranking of BWLUE effects as well as SOM segmentation revealed seven breading lines from Breeding Station Nagradowice, which may be considered for further breeding process.

Analysis of Whole-Body Coordination Patterning in Successful and Faulty Spikes Using Self-Organising Map-Based Cluster Analysis: A Secondary Analysis

This study investigated the whole-body coordination patterning in successful and faulty spikes using self-organising map-based cluster analysis. Ten young, elite volleyball players (aged 15.5 ± 0.7 years) performed 60 volleyball spikes in a real-game environment. Adopting the cluster analysis, based on a self-organising map, whole-body coordination patterning was explored between successful and faulty spikes of individual players. The self-organising maps (SOMs) portrayed whole body, lower and upper limb coordination dissimilarities during the jump phase and the ball impact phases between the successful and faulty spikes. The cluster analysis illustrated that the whole body, upper limb and lower limb coordination patterning of each individual’s successful spikes were similar to their faulty spikes. Range of motion patterning also demonstrated no differences in kinematics between spike outcomes. Further, the upper limb angular velocity patterning of the players’ successful/faulty spikes were similar. The SPM analysis portrayed significant differences between the normalized upper limb angular velocities from 35% to 45% and from 76% to 100% of the spike movement. Although the lower limb angular velocities are vital for achieving higher jumps in volleyball spikes, the results of this study portrayed that the upper limb angular velocities distinguish the differences between successful and faulty spikes among the attackers. This confirms the fact that volleyball coaches should shift their focus toward the upper limb velocity and coordination training for higher success rates in spiking for volleyball attackers.

Behaviour Learning System for Robot Soccer Using Neural Network

Technological developments have raised the promise of a human{robot symbiotic society. A soccer game has characteristics similar to those expected in such a society. Soccer is a multiagent game in which the strategy employed depends on each agent's position and actions. This study discusses the results of the development of a learning system that uses a self-organising map to select behaviours depending on the situation. This system can reproduce the action selection algorithm of all players in a certain team, and the robot can instantly select the next cooperative action from the information obtained during the game. In this manner, common sense rules can be shared to learn an action selection algorithm for a set of both human and robot agents as opposed to robots alone.

Circular dichroism for secondary structure determination of proteins with unfolded domains using a self-organising map algorithm SOMSpec

Circular dichroism secondary structure fitting by analysing derandomized spectra using the SOMSpec approach then regenerating data for the original spectrum.