Ciencias Computacionales

The Neuro-Symbolic Hybrid Systems (NSHS) are used to solve problems where there exists a necessity of combining and integrating the artificial neural networks and the symbolic representations in only one system in order to obtain better results. We developed a NSHS Methodology to integrate the knowledge of a human expert and the numeric knowledge obtained from a computer vision process. We implement the methodology to solve a quality inspection problem in artificial textures. The construction of neuro-symbolic integration strategies allows us defining an adequate type of neuro-symbolic system to obtain an increment of the efficiency of an inspection task, which is shown with the better results obtained compared with other approaches.

Abstract Visual SLAM (simultaneous localization and mapping) refers to the problem of using images, as the only source of external information, in order to establish the position of a robot, a vehicle, or a moving camera in an environment, and at the same time, construct a representation of the explored zone. SLAM is an essential task for the autonomy of a robot. Nowadays, the problem of SLAM is considered solved when range sensors such as lasers or sonar are used to built 2D maps of small static environments. However SLAM for dynamic, complex and large scale environments, using vision as the sole external sensor, is an active area of research. The computer vision techniques employed in visual SLAM, such as detection, description and matching of salient features, image recognition and retrieval, among others, are still susceptible of improvement. The objective of this article is to provide new researchers in the field of visual SLAM a brief and comprehensible review of the state-of-the-art.
Keywords Visual SLAM · Salient feature selection · Image matching · Data association · Topological and metric maps

In this paper a multiplicative regression method to estimate software development effort is presented. This method, which we call MUREM, is a result of, on the one hand, a set of initial conditions to frame the process of estimating software development effort and, on the other hand, a set of restrictions to be satisfied by the development effort as a function of software size. To evaluate the performance of MUREM, it was compared with three regression models which are considered as important methods for estimating software development effort. In this comparison a battery of hypothesis and standard statistical tests is applied to twelve samples taken from well-known public databases. These databases serve as benchmarks for comparing methods to estimate the software development effort. In the experimentation it was found that MUREM generates more accurate point estimates of the development effort than those achieved by the other methods. MUREM corrects the heteroscedasticity and increases the proportion of samples whose residuals show normality. MUREM thus generates more appropriate confidence and prediction intervals than those obtained by the other methods. An important result is that residuals obtained by the regression model of MUREM satisfy the test for zero mean additive white Gaussian noise which is proof that the estimation error of this model is random.

A method to data-mine results of an analog circuit sizing in order to extract knowledge that can be immediately used by designers or students of analog integrated circuit design is presented. The symbolic models, which have been generated using multi-objective genetic programming, are human-interpretable mathematical models. The procedure presented involves two steps: the generation of samples of Pareto-optimal performance sizes of two unity gain cells using the NSGA-II genetic algorithm; and the generation of models of each of the objectives sized by symbolic regression via genetic programming. The functionality of the method to describe circuits is shown in three cases: two current followers and one voltage follower.

In this research work a method for sequencing learning objects based on the SCORM standard using cmi tracking elements from this standard and javascript programming language, is presented. Advanced sequencing rules, dependent on student performance are achieved with SCORM 1.2, surpassing the present capabilities of learning objects in learning management systems. An analysis of a case study is also presented, showing that the configured code works correctly.

This paper presents a binocular eye-to-hand visual servoing system that is able to track and grasp a moving object in real time. Linear predictors are employed to estimate the object trajectory in three dimensions and are capable of predicting future positions even if the object is temporarily occluded. For its development we have used a CRS T475 manipulator robot with six degrees of freedom and two fixed cameras in a stereo pair configuration. The system has a client‐server architecture and is composed of two main parts: the vision system and the control system. The vision system uses color detection to extract the object from the background and a tracking technique based on search windows and object moments. The control system uses the RobWork library to generate the movement instructions and to send them to a C550 controller by means of the serial port. Experimental results are presented to verify the validity and the efficacy of the proposed visual servoing system.

Resumen. En la actualidad han surgido nuevos modelos computacionales que intentan superar a los modelos clásicos de optimización, este es el caso de la Computación Evolutiva, la cual se ha popularizado por los Algoritmos Genéticos y sus diferentes variantes que prometen ser mejores. En este artículo analizaremos las bondades y/o deficiencias del Algoritmo Genético básico y del algoritmo de Aprendizaje Incremental Basado en Población, el cual es un algoritmo de estimación de distribuciones que forma parte del paradigma de la Computación Evolutiva. Se presenta un estudio comparativo de ambos algoritmos que permite establecer, a partir de la experimentación realizada con 7 funciones objetivo, que el algoritmo de Aprendizaje Incremental Basado en Población presenta ventaja significativa en tiempo de ejecución de todas las pruebas, así como en la precisión obtenida en 6 de las 7 funciones objetivo analizadas. Aunque esta ventaja ya había sido reportada, en este artículo se ha experimentado con funciones multimodal con dos incógnitas y en tres dimensiones, que en la actualidad son consideradas difíciles de resolver. Palabras clave: Optimización de funciones, computación evolutiva, algoritmos genéticos, algoritmo de estimación de distribuciones, aprendizaje incremental basado en población. Population-Based Incremental Learning as Good Alternative for Genetic Algorithms Abstract. At present, new computational models that attempt to overcome to the classical optimization models have emerged, this is the case of Evolutionary Computation, which has been popularized by Genetic Algorithms and their different variants that promise to be better. In this article we will discuss the benefits and/or shortcomings of basic Genetic Algorithm and Population-Based Incremental Learning algorithm, which is an estimation of distributions

A method to data-mine results of an analog circuit sizing in order to extract knowledge that can be immediately used by designers or students of analog integrated circuit design is presented. The symbolic models, which have been generated using multi-objective genetic programming, are human-interpretable mathematical models. The procedure presented involves two steps: the generation of samples of Pareto-optimal performance sizes of two unity gain cells using the NSGA-II genetic algorithm; and the generation of models of each of the objectives sized by symbolic regression via genetic programming. The functionality of the method to describe circuits is shown in three cases: two current followers and one voltage follower.

Solution to the identification and control problems for linear and non linear systems is found using statespace theory and tools of artificial intelligence. We review previous results using the Hybrid State Transition Kernel, which has as distinctive features 1) requires little a priori information, 2) is independent of the approximation or learning method, 3) uses the same data for identification and control, 4) it implements inverse plant control with finite convergence time. The structures necessary to treat plants with and without zeroes are derived, showing simulation results for linear and nonlinear systems.

In this paper the implementation of PID controllers for the development of passive rehabilitation exercises are presented. For which it is designed and built an ankle rehabilitation prototype based on a structure of parallel robot with a mechanism of the type 2-RRSP (two closed kinematic chains and consisting of joints: revolute-revolute-sphere in slotfixed post with sphere). Free software is used to develop the computer programs associated with rehabilitation exercises. Regarding the laboratory testing stage, the results of passive exercises are reported, in these exercises path planning is included and PID control is used, for inversion-eversion, dorsalplantar flexion and combined movements.

In this paper the implementation of impedance controllers to develop active rehabilitation exercises are presented. For which it is used a parallel structure ankle rehabilitation prototype with a mechanism of the type 2-RRSP (two closed kinematic chains and consisting of joints: revoluterevolute-sphere in slot-fixed post with sphere). Free software is used to develop the computer programs associated with rehabilitation exercises. The results of active rehabilitation exercises are reported, wich involves the effect of resistance from the rehabilitation prototype to the user operation: low, medium and high opposition effects are considered.

In this research work, the results obtained from the SCORM Cloud module verification in a learning platform (Learning Management System) Moodle 1.9.19, are presented. For this module verification, learning objects based on standard SCORM 2004 Fourth Edition were used, with sequencing according to ADL proposed template 10 and whose sequencing process was developed in a previous, published, research work. Due to scarce information, coupling a Learning Management System (Moodle 1.9.19 in this case) with SCORM Cloud becomes complicated, this paper presents a full description of how to couple SCORM Cloud into a Learning Management System.

The enormous growth of stored images in the Internet creates a new and unexpected opportunity for the advancement of science and technology. However, to make an optimal use of this tremendous volume of information, substantial progress is required in the way that current computers process images. There are several efforts in this direction, one of which is to standardize the whole process, thus emerging the Moving Picture Experts Group (MPEG). In this paper we introduce the MPEG-7 standard, and present and analyze some representative works of the state of the art in this area, with emphasis on Visual Descriptors for Content-Based Image Retrieval (CBIR), and finally discuss some trends.

Recent advances in text detection allow for finding text regions in natural scenes rather accurately. Global features in content based image retrieval, however, typically do not cover such a high level information. While haracteristics of text regions may be reflected by texture or color properties, the respective pixels are not treated in a different way. In this contribution we investigate the impact of text detection on content based image retrieval using global features. Detected text regions are preprocessed to allow for different treatment by feature extraction algorithms, and we show that for certain domains this leads to a much higher precision in content based retrieval.

Software development processes recognize importance of software architecture, but it seems not to have influence on software design and implementation. Current software industry requires an agile development process performed within organized groups, but it could better promote and integrate groupwork. We propose the AGD (Architectural and Group Development) software development method allocating a product set with explicit software architecture as primary element, and integrating in a process four group-work modes (Team, Collaborative, Cooperative, and Control) as secondary element.