Simultaneous learning of perception and action in mobile robots

One of the main problems of robots is the lack of adaptability and the need for adjustment every time the robot changes its working place. To solve this, we propose a learning approach for mobile robots using a reinforcement-based strategy and a dynamic sensor-state mapping. This strategy, practically parameterless, minimises the adjustments needed when the robot operates in a different environment or performs a different task.Our system will simultaneously learn the state space and the action to execute on each state. The learning algorithm will attempt to maximise the time before a robot failure in order to obtain a control policy suited to the desired behaviour, thus providing a more interpretable learning process. The state representation will be created dynamically, starting with an empty state space and adding new states as the robot finds new situations that has not seen before. A dynamic creation of the state representation will avoid the classic, error-prone and cyclic process of designing and testing an ad hoc representation. We performed an exhaustive study of our approach, comparing it with other classic strategies. Unexpectedly, learning both perception and action does not increase the learning time.     

Semi-formal transformation of secure business processes into analysis class and use case models: An MDA approach

ContextModel-Driven Development (MDD) is an alternative approach for information systems development. The basic underlying concept of this approach is the definition of abstract models that can be transformed to obtain models near implementation. One fairly widespread proposal in this sphere is that of Model Driven Architecture (MDA). Business process models are abstract models which additionally contain key information about the tasks that are being carried out to achieve the company’s goals, and two notations currently exist for modelling business processes: the Unified Modelling Language (UML), through activity diagrams, and the Business Process Modelling Notation (BPMN).ObjectiveOur research is particularly focused on security requirements, in such a way that security is modelled along with the other aspects that are included in a business process. To this end, in earlier works we have defined a metamodel called secure business process (SBP), which may assist in the process of developing software as a source of highly valuable requirements (including very abstract security requirements), which are transformed into models with a lower abstraction level, such as analysis class diagrams and use case diagrams through the approach presented in this paper.MethodWe have defined all the transformation rules necessary to obtain analysis class diagrams and use case diagrams from SBP, and refined them through the characteristic iterative process of the action-research method.ResultsWe have obtained a set of rules and a checklist that make it possible to automatically obtain a set of UML analysis classes and use cases, starting from SBP models. Our approach has additionally been applied in a real environment in the area of the payment of electrical energy consumption.ConclusionsThe application of our proposal shows that our semi-automatic process can be used to obtain a set of useful artifacts for software development processes.     

A natural-disaster management DSS for Humanitarian Non-Governmental Organisations

Humanitarian Non-Governmental Organisations (NGOs) play a growing role in the response to natural disasters, but despite being largely demanded, there is no available decision support system (DSS) specifically designed to address their problem. In this paper we present a decision support system (DSS) to aid those Humanitarian NGOs concerned with the response to natural disasters. Such a DSS has been designed avoiding sophisticated methodologies that may exceed the infrastructural requirements and constraints of emergency management by NGOs. A data-based, two-level knowledge methodology which allows damage assessment of multiple disaster scenarios is presented in order to address that problem. Validation results show viability of our approach.     

Uniform tree approximation by global optimization techniques

In this paper we present adaptive algorithms for solving the uniform continuous piecewise affine approximation problem (UCPA) in the case of Lipschitz or convex functions. The algorithms are based on the tree approximation (adaptive splitting) procedure. The uniform convergence is achieved by means of global optimization techniques for obtaining tight upper bounds of the local error estimate (splitting criterion). We give numerical results in the case of the function distance to 2D and 3D geometric bodies. The resulting trees can retrieve the values of the target function in a fast way.     

A new fast prototype selection method based on clustering

In supervised classification, a training set T is given to a classifier for classifying new prototypes. In practice, not all information in T is useful for classifiers, therefore, it is convenient to discard irrelevant prototypes from T. This process is known as prototype selection, which is an important task for classifiers since through this process the time for classification or training could be reduced. In this work, we propose a new fast prototype selection method for large datasets, based on clustering, which selects border prototypes and some interior prototypes. Experimental results showing the performance of our method and comparing accuracy and runtimes against other prototype selection methods are reported.     

Simultaneous algorithm for trajectory planning

This paper addresses the solution of smooth trajectory planning for industrial robots in environments with obstacles using a direct method, creating the trajectory gradually as the robot moves. The presented method deals with the uncertainties associated with the lack of knowledge of kinematic properties of intermediate via‐points since they are generated as the algorithm evolves looking for the solution. Several cost functions are also proposed, which use the time that has been calculated to guide the robot motion. The method has been applied successfully to a PUMA 560 robot and four operational parameters (execution time, computational time, distance travelled and number of configurations) have been computed to study the properties and influence of each cost function on the trajectory obtained. Copyright © 2010 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

Poly-bagging predictors for classification modelling for credit scoring

Credit scoring modelling comprises one of the leading formal tools for supporting the granting of credit. Its core objective consists of the generation of a score by means of which potential clients can be listed in the order of the probability of default. A critical factor is whether a credit scoring model is accurate enough in order to provide correct classification of the client as a good or bad payer. In this context the concept of bootstraping aggregating (bagging) arises. The basic idea is to generate multiple classifiers by obtaining the predicted values from the fitted models to several replicated datasets and then combining them into a single predictive classification in order to improve the classification accuracy. In this paper we propose a new bagging-type variant procedure, which we call poly-bagging, consisting of combining predictors over a succession of resamplings. The study is derived by credit scoring modelling. The proposed poly-bagging procedure was applied to some different artificial datasets and to a real granting of credit dataset up to three successions of resamplings. We observed better classification accuracy for the two-bagged and the three-bagged models for all considered setups. These results lead to a strong indication that the poly-bagging approach may promote improvement on the modelling performance measures, while keeping a flexible and straightforward bagging-type structure easy to implement.     

A parameterized shared-memory scheme for parameterized metaheuristics

This paper presents a parameterized shared-memory scheme for parameterized metaheuristics. The use of a parameterized metaheuristic facilitates experimentation with different metaheuristics and hybridation/combinations to adapt them to the particular problem we are working with. Due to the large number of experiments necessary for the metaheuristic selection and tuning, parallelism should be used to reduce the execution time. To obtain parallel versions of the metaheuristics and to adapt them to the characteristics of the parallel system, a unified parameterized shared-memory scheme is developed. Given a particular computational system and fixed parameters for the sequential metaheuristic, the appropriate selection of parameters in the unified parallel scheme eases the development of parallel efficient metaheuristics.     

MELM-GRBF: A modified version of the extreme learning machine for generalized radial basis function neural networks

In this paper, we propose a methodology for training a new model of artificial neural network called the generalized radial basis function (GRBF) neural network. This model is based on generalized Gaussian distribution, which parametrizes the Gaussian distribution by adding a new parameter τ. The generalized radial basis function allows different radial basis functions to be represented by updating the new parameter τ. For example, when GRBF takes a value of τ=2, it represents the standard Gaussian radial basis function. The model parameters are optimized through a modified version of the extreme learning machine (ELM) algorithm. In the methodology proposed (MELM-GRBF), the centers of each GRBF were taken randomly from the patterns of the training set and the radius and τ values were determined analytically, taking into account that the model must fulfil two constraints: locality and coverage. An thorough experimental study is presented to test its overall performance. Fifteen datasets were considered, including binary and multi-class problems, all of them taken from the UCI repository. The MELM-GRBF was compared to ELM with sigmoidal, hard-limit, triangular basis and radial basis functions in the hidden layer and to the ELM-RBF methodology proposed by Huang et al. (2004) [1]. The MELM-GRBF obtained better results in accuracy than the corresponding sigmoidal, hard-limit, triangular basis and radial basis functions for almost all datasets, producing the highest mean accuracy rank when compared with these other basis functions for all datasets.     

Designing adaptive learning itineraries using features modelling and swarm intelligence

In this paper, Bayesian network (BN) and ant colony optimization (ACO) techniques are combined in order to find the best path through a graph representing all available itineraries to acquire a professional competence. The combination of these methods allows us to design a dynamic learning path, useful in a rapidly changing world. One of the most important advances in this work, apart from the variable amount of pheromones, is the automatic processing of the learning graph. This processing is carried out by the learning management system and helps towards understanding the learning process as a competence-oriented itinerary instead of a stand-alone course. The amount of pheromones is calculated by taking into account the results acquired in the last completed course in relation to the minimum score required and by feeding this into the learning tree in order to obtain a relative impact on the path taken by the student. A BN is used to predict the probability of success, by taking historical data and student profiles into account. Usually, these profiles are defined beforehand; however, in our approach, some characteristics of these profiles, such as the level of knowledge, are classified automatically through supervised and/or unsupervised learning. By using ACO and BN, a fitness function, responsible for automatically selecting the next course in the learning graph, is defined. This is done by generating a path which maximizes the probability of each user??s success on the course. Therefore, the path can change in order to adapt itself to learners?? preferences and needs, by taking into account the pedagogical weight of each learning unit and the social behaviour of the system.