Temporal Kohonen Map and the Recurrent Self-Organizing Map: Analytical and Experimental Comparison

This paper compares two Self-Organizing Map (SOM) based models for temporal sequence processing (TSP) both analytically and experimentally. These models, Temporal Kohonen Map (TKM) and Recurrent Self-Organizing Map (RSOM), incorporate leaky integrator memory to preserve the temporal context of the input signals. The learning and the convergence properties of the TKM and RSOM are studied and we show analytically that the RSOM is a significant improvement over the TKM, because the RSOM allows simple derivation of a consistent learning rule. The results of the analysis are demonstrated with experiments.     

The stiffness of laser stake welded T-joints in web-core sandwich structures

The purpose of this paper is to describe experiments carried out on laser stake welded T-joints of web-core steel sandwich structures. A special test setup was developed to measure the shear-induced rotation at the T-joint. The ratio of the shear force to rotation angle gave the joint stiffness. This stiffness was measured for specimens with two different face-plate thicknesses. The influence of weld thickness, root gap and occurrence of contact were further investigated with finite element simulations. Finally, the shear stiffness of the sandwich structure transverse to the web plate direction was determined using the experimentally obtained average joint stiffness value. The validation of the shear stiffness was carried out by considering a beam in four-point bending. The agreement between calculated deflection and stress and experimental results was found to be good.     

Linear classification of low-resolution EEG patterns produced by imagined hand movements.

Electroencephalograph (EEG)-based brain-computer interfaces (BCI's) require on-line detection of mental states from spontaneous EEG signals. In this framework, surface Laplacian (SL) transformation of EEG signals has proved to improve the recognition scores of imagined motor activity. The results we obtained in the first year of an European project named adaptive brain interfaces (ABI) suggest that: 1) the detection of mental imagined activity can be obtained by using the signal space projection (SSP) method as a classifier and 2) a particular type of electrodes can be used in such a BCI device, reconciling the benefits of SL waveforms and the need for the use of few electrodes. Recognition of mental activity was attempted on both raw and SL-transformed EEG data from five healthy people performing two mental tasks, namely imagined right and left hand movements.     

Design of marine structures with improved safety for environment

The paper describes a method for design of marine structures with increased safety for environment, considering also the required investment costs as well as the aspects of risk distribution onto the maritime stakeholders. Practically, the paper seeks to answer what is the optimal amount that should be invested into certain safety measure for any given vessel. Due to the uneven distribution of risk, as well as the differing impact of costs emerging from safety improvements, stakeholders experience conflicting ranking of alternatives. To solve this multi-stakeholder decision-making problem, in which each stakeholder is a decision-maker, the method applies concepts of group decision-making theory, namely the Game Theory. The method fosters axiomatic definition of the optimum solution, arguing that the solution, or the final selected design, should satisfy the non-dominance, efficiency, and fairness. These three are thoroughly discussed in terms of structural design, especially the latter. Considering the coupling of environmental risk and structural design, the method also builds on the preference structure of four maritime stakeholders: yards, owners, oil receivers and the public, who either share the risks or directly influence structural design. Method is presented on a practical study of structural design of a tanker with a crashworthy side structure that is capable of reducing the risk of collision. The outcome of this study outlines a number of possibilities for successful improvement of tanker safety that can benefit, concurrently, all maritime stakeholders.     

A local neural classifier for the recognition of EEG patternsassociated to mental tasks

This paper proposes a novel and simple local neural classifier for the recognition of mental tasks from on-line spontaneous EEG signals. The proposed neural classifier recognizes three mental tasks from on-line spontaneous EEG signals. Correct recognition is around 70%. This modest rate is largely compensated by two properties, namely low percentage of wrong decisions (below 5%) and rapid responses (every 1/2 s). Interestingly, the neural classifier achieves this performance with a few units, normally just one per mental task. Also, since the subject and his/her personal interface learn simultaneously from each other, subjects master it rapidly (in a few days of moderate training). Finally, analysis of learned EEG patterns confirms that for a subject to operate satisfactorily a brain interface, the latter must fit the individual features of the former.     

Bending response of web-core sandwich beams

This paper presents a new analytical solution for the bending response of a web-core sandwich beam. The beam is a transverse cut from the sandwich plate. The method is based on the plane frame analysis, where the response of the beam is divided into local and global components. The Clebsch’s method is used to calculate the deflection of the face plates. The validation of the plane frame method is carried out with FE-analyses based on the shell element formulation. Also a comparison is made with the method based on homogenized beam. Periodic stress distributions in the face plates are revealed with the plane frame analysis and are supported by the FE-analysis. The existing methods based on homogenized beam are not able to predict these stresses. The plane frame analysis can benefit the development of the theory related to web-core sandwich plate.