Advanced Adaptive Sonar for Mapping Applications

An advanced adaptive sonar module is described, capable of being configured to different circumstances and distances according to reflectors found in the environment. Thanks to the sensory distribution, it is possible to identify three basic types of reflector (planes, edges and corners). Furthermore, a heuristic map of the environment is built. The proposed methods have been computationally optimized, and implemented in a real-time system based on a Field-Programmable Gate Array (FPGA) and a Digital Signal Processor (DSP). Results have been obtained in the detection, classification and mapping of obstacles; and finally testing has been carried out on a commercial vehicle.     

Improving the training time of support vector regression algorithms through novel hyper-parameters search space reductions

The selection of hyper-parameters in support vector machines (SVM) is a key point in the training process of these models when applied to regression problems. Unfortunately, an exact method to obtain the optimal set of SVM hyper-parameters is unknown, and search algorithms are usually applied to obtain the best possible set of hyper-parameters. In general these search algorithms are implemented as grid searches, which are time consuming, so the computational cost of the SVM training process increases considerably. This paper presents a novel study of the effect of including reductions in the range of SVM hyper-parameters, in order to reduce the SVM training time, but with the minimum possible impact in its performance. The paper presents reduction in parameter C, by considering its relation with the rest of SVM hyper-parameters (γ and ε), through an approximation of the SVM model. On the other hand, we use some characteristics of the Gaussian kernel function and a previous result in the literature to obtain novel bounds for γ and ε hyper-parameters. The search space reductions proposed are evaluated in different regression problems from UCI and StatLib databases. All the experiments carried out applying the popular LIBSVM solver have shown that our approach reduces the SVM training time, maintaining the SVM performance similar to when the complete range in SVM parameters is considered.     

A new algorithm to compute conjectured supply function equilibrium in electricity markets

Several types of market equilibria approaches, such as Cournot, Conjectural Variation (CVE), Supply Function (SFE) or Conjectured Supply Function (CSFE) have been used to model electricity markets for the medium and long term. Among them, CSFE has been proposed as a generalization of the classic Cournot. It computes the equilibrium considering the reaction of the competitors against changes in their strategy, combining several characteristics of both CVE and SFE. Unlike linear SFE approaches, strategies are linearized only at the equilibrium point, using their first-order Taylor approximation. But to solve CSFE, the slope or the intercept of the linear approximations must be given, which has been proved to be very restrictive.This paper proposes a new algorithm to compute CSFE. Unlike previous approaches, the main contribution is that the competitors’ strategies for each generator are initially unknown (both slope and intercept) and endogenously computed by this new iterative algorithm.To show the applicability of the proposed approach, it has been applied to several case examples where its qualitative behavior has been analyzed in detail.     

Unsupervised neural models for country and political risk analysis

This interdisciplinary research project focuses on relevant applications of Knowledge Discovery and Artificial Neural Networks in order to identify and analyze levels of country, business and political risk. Its main goal is to help business decision-makers understand the dynamics within the emerging market countries in which they operate. Most of the neural models applied in this study are defined within the framework of unsupervised learning. They are based on Exploratory Projection Pursuit, Topology Preserving Maps and Curvilinear Component Analysis. Two interesting real data sets are analyzed to empirically probe the robustness of these models. The first case study describes information from a significant sample of Spanish multinational enterprises (MNEs). It analyses data pertaining to such aspects as decisions over the location of subsidiary enterprises in various regions across the world, the importance accorded to such decisions and the driving forces behind them. Through a projection-based analysis, this study reveals a range of different reasons underlying the internationalization strategies of Spanish MNEs and the different goals they pursue. It may be concluded that projection connectionist techniques are of immense assistance in the process of identifying the internationalization strategies of Spanish MNEs, their underlying motives and the goals they pursue. The second case study covers several risk categories that include task policy, security, and political stability among others, and it tracks the scores of different countries all over the world. Interesting conclusions are drawn from the application of several business intelligence solutions based on neural projection models, which support data analysis in the context of country and political risk analysis.     

Hybrid nanocomposites for mid-range ballistic protection

This paper focuses on ballistic tests of a new class of composite materials, i.e. hybrid nanocomposites. The two hybrid nanocomposites studied are fiber glass/epoxy/nanoclay and fiber glass/epoxy/nanographite. The fiber glass used is a plain weave 200 g/m², while the nanoclay is an organically modified montmorillonite ceramic (Nanomer I30E). The expandable graphite used to generate the graphene nanosheets was from Graftech (grade 160-80N). Ballistic tests were performed considering two types of ammunition, i.e. 38 caliber and 9 mm full metal jacketed. The results showed that for a 38 revolver projectile a 5 mm thick nanocomposite with additional 5 mm nanoclay layer was able to absorb the energy efficiently. A 9 mm projectile, with speed of 380 m/s, was stopped by a two plates (5 mm each) arrangement with elastic deformation of the second plate less than 18 mm. The energies during the ballistic tests ranged from 316 to 576 J.