CSIC - Industrial Automation Institute

Madrid, Spain

CSIC - Industrial Automation Institute

Madrid, Spain

Time filter

Source Type

Burgos-Artizzu X.P.,CSIC - Industrial Automation Institute | Ribeiro A.,CSIC - Industrial Automation Institute | Tellaeche A.,Spanish University for Distance Education (UNED) | Pajares G.,Complutense University of Madrid
Image and Vision Computing | Year: 2010

This work presents several developed computer-vision-based methods for the estimation of percentages of weed, crop and soil present in an image showing a region of interest of the crop field. The visual detection of weed, crop and soil is an arduous task due to physical similarities between weeds and crop and to the natural and therefore complex environments (with non-controlled illumination) encountered. The image processing was divided in three different stages at which each different agricultural element is extracted: (1) segmentation of vegetation against non-vegetation (soil), (2) crop row elimination (crop) and (3) weed extraction (weed). For each stage, different and interchangeable methods are proposed, each one using a series of input parameters which value can be changed for further refining the processing. A genetic algorithm was then used to find the best value of parameters and method combination for different sets of images. The whole system was tested on several images from different years and fields, resulting in an average correlation coefficient with real data (bio-mass) of 84%, with up to 96% correlation using the best methods on winter cereal images and of up to 84% on maize images. Moreover, the method's low computational complexity leads to the possibility, as future work, of adapting them to real-time processing. © 2009 Elsevier B.V. All rights reserved.


Tellaeche A.,Complutense University of Madrid | Pajares G.,Complutense University of Madrid | Burgos-Artizzu X.P.,CSIC - Industrial Automation Institute | Ribeiro A.,CSIC - Industrial Automation Institute
Applied Soft Computing Journal | Year: 2011

This paper outlines an automatic computer vision system for the identification of avena sterilis which is a special weed seed growing in cereal crops. The final goal is to reduce the quantity of herbicide to be sprayed as an important and necessary step for precision agriculture. So, only areas where the presence of weeds is important should be sprayed. The main problems for the identification of this kind of weed are its similar spectral signature with respect the crops and also its irregular distribution in the field. It has been designed a new strategy involving two processes: image segmentation and decision making. The image segmentation combines basic suitable image processing techniques in order to extract cells from the image as the low level units. Each cell is described by two area-based attributes measuring the relations among the crops and weeds. The decision making is based on the Support Vector Machines and determines if a cell must be sprayed. The main findings of this paper are reflected in the combination of the segmentation and the Support Vector Machines decision processes. Another important contribution of this approach is the minimum requirements of the system in terms of memory and computation power if compared with other previous works. The performance of the method is illustrated by comparative analysis against some existing strategies. © 2010 Elsevier B.V. All rights reserved.


Pajares G.,Complutense University of Madrid | Guijarro M.,Centro Superior Of Estudios Felipe Ii Ingenieria Tecnica En Informatica Of Sistemas | Ribeiro A.,CSIC - Industrial Automation Institute
Neural Networks | Year: 2010

In this paper we propose a new method for combining simple classifiers through the analogue Hopfield Neural Network (HNN) optimization paradigm for classifying natural textures in images. The base classifiers are the Fuzzy clustering (FC) and the parametric Bayesian estimator (BP). An initial unsupervised training phase determines the number of clusters and estimates the parameters for both FC and BP. Then a decision phase is carried out, where we build as many Hopfield Neural Networks as the available number of clusters. The number of nodes at each network is the number of pixels in the image which is to be classified. Each node at each network is initially loaded with a state value, which is the membership degree (provided by FC) that the node (pixel) belongs to the cluster associated to the network. Each state is later iteratively updated during the HNN optimization process taking into account the previous states and two types of external influences exerted by other nodes in its neighborhood. The external influences are mapped as consistencies. One is embedded in an energy term which considers the states of the node to be updated and the states of its neighbors. The other is mapped as the inter-connection weights between the nodes. From BP, we obtain the probabilities that the nodes (pixels) belong to a cluster (network). We define these weights as a relation between states and probabilities between the nodes in the neighborhood of the node which is being updated. This is the classifier combination, making the main finding of this paper. The proposed combined strategy based on the HNN outperforms the simple classifiers and also classical combination strategies. © 2009 Elsevier Ltd. All rights reserved.


Sanchez D.G.,CSIC - Industrial Automation Institute | Diaz D.G.,CSIC - Industrial Automation Institute | Hiesgen R.,Esslingen University of Applied Sciences | Wehl I.,Esslingen University of Applied Sciences | Friedrich K.A.,German Aerospace Center
Journal of Electroanalytical Chemistry | Year: 2010

Oscillatory fluctuations of a single polymer electrolyte fuel cell appear upon operation with a dry cathode air supply and a fully humidified anode stream. Periodic transitions between a low and a high current operation point of the oscillating state are observed. The transition time of 20-25 s for the change from the low to the high operation is fast and does not depend on the operating parameters. Contrasting with this behavior, the downward transition depends strongly on the operating conditions. Impedance measurements indicate a high ionic resistance with low water content for the low current operation and a low ionic resistance of the membrane with high water content for the high current operation. An insight into the transitions is obtained by current density distributions at distinct times indicating a propagating active area with defined boundaries. The observations are in agreement with assuming a liquid water reservoir at the anode with a downward transition period depending on the operation conditions. The high current operation possesses a high electro-osmotic drag and a high permeation rate (corresponding to liquid-vapor permeation) leading to a large water flux to the cathode. Subsequently, the liquid reservoir at the anode is consumed leading to an anode drying. The system establishes a new quasi-stable operation point associated with a low current, low electro-osmotic drag coefficient, and a low water permeation (corresponding to vapor-vapor permeation). When liquid water is formed at the anode interface after some time the fast transition to the high current operation occurs. This interpretation is supported by conductive atomic force microscopy current images of the membrane showing a strong dependence of the ionic conductivity on the activation procedures with or without liquid water and also showing oscillatory behavior after the membrane is activated. Specifically, activation with liquid water yields a high conductivity with currents larger by three orders of magnitude. © 2009 Elsevier B.V. All rights reserved.


Gajate A.,CSIC - Industrial Automation Institute | Haber R.,CSIC - Industrial Automation Institute | Toro R.D.,CSIC - Industrial Automation Institute | Vega P.,University of Salamanca | Bustillo A.,University of Burgos
Journal of Intelligent Manufacturing | Year: 2012

Tool wear detection is a key issue for tool condition monitoring. The maximization of useful tool life is frequently related with the optimization of machining processes. This paper presents two model-based approaches for tool wear monitoring on the basis of neuro-fuzzy techniques. The use of a neuro-fuzzy hybridization to design a tool wear monitoring system is aiming at exploiting the synergy of neural networks and fuzzy logic, by combining human reasoning with learning and connectionist structure. The turning process that is awell-knownmachining process is selected for this case study. A four-input (i.e., time, cutting forces, vibrations and acoustic emissions signals) single-output (tool wear rate)model is designed and implemented on the basis of three neuro-fuzzyapproaches(inductive, transductiveandevolving neuro-fuzzy systems). The tool wear model is then used for monitoring the turning process. The comparative study demonstrates that the transductive neuro-fuzzy model provides better error-based performance indices for detecting tool wear than the inductive neuro-fuzzy model and than the evolving neuro-fuzzy model. © Springer Science+Business Media, LLC 2010.


Galan-Arriero I.,Hospital Nacional Of Paraplejicos | Avila-Martin G.,Hospital Nacional Of Paraplejicos | Ferrer-Donato A.,Hospital Nacional Of Paraplejicos | Gomez-Soriano J.,Hospital Nacional Of Paraplejicos | And 4 more authors.
Pain | Year: 2014

The p38α mitogenous activated protein kinase (MAPK) cell signaling pathway is a key mechanism of microglia activation and has been studied as a target for neuropathic pain. The effect of UR13870, a p38α MAPK inhibitor, on microglia expression in the anterior cingulate cortex (ACC) and spinal dorsal horn was addressed after T9 contusion spinal cord injury (SCI) in the rat, in addition to behavioral testing of pain-related aversion and anxiety. Administration of intravenous UR13870 (1 mg/kg i.v.) and pregabalin (30 mg/kg i.v.) reduced place escape avoidance paradigm (PEAP) but did not affect open-field anxiety behavior 42 days after SCI. PEAP behavior was also reduced in animals administered daily with oral UR13870 (10 mg/kg p.o.) and preserved spinal tissue 28 days after SCI. Although UR13870 (10 mg/kg p.o.) failed to reduce OX-42 and glial fibrillar acid protein immunoreactivity within the spinal dorsal horn, a reduction toward the control level was observed close to the SCI site. In the anterior cingulate cortex (ACC), a significant increase in OX-42 immunoreactivity was identified after SCI. UR13870 (10 mg/kg p.o.) treatment significantly reduced OX-42, metabotropic glutamate type 5 receptor (mGluR5), and NMDA (N-methyl-d-aspartate) 2B subunit receptor (NR2B) expression in the ACC after SCI. To conclude, oral treatment with a p38α MAPK inhibitor reduces the affective behavioral component of pain after SCI in association with a reduction of microglia and specific glutamate receptors within the ACC. Nevertheless the role of neuroinflammatory processes within the vicinity of the SCI site in the development of affective neuropathic pain cannot be excluded. © 2014 International Association for the Study of Pain. Published by Elsevier B.V. All rights reserved.


Raya R.,CSIC - Industrial Automation Institute | Roa J.O.,CSIC - Industrial Automation Institute | Rocon E.,CSIC - Industrial Automation Institute | Ceres R.,CSIC - Industrial Automation Institute | Pons J.L.,CSIC - Industrial Automation Institute
Sensors and Actuators, A: Physical | Year: 2010

People with multiple physical and cognitive impairments have difficulties for using properly conventional pointing devices, what reduces their possibilities to communicate and improve their cognitive and physical skills through computers. This paper proposes a head control mouse based on a triaxial inertial sensor particularly focused on infants with cerebral palsy (CP). The system consists of a real-time head tracker that translates the head orientation into pointer positions and measures kinematic parameters through the 3D inertial sensor. The algorithm to estimate the angular head orientation is presented and validated with an accuracy about 1°. The experimental results with five healthy users demonstrated that the inertial pointer succeeds what was validated according to the ISO 9241-Part9. The experimental results with two infants with CP (athetoid and dystonic cases) demonstrated that the infants are capable of placing the pointer around the target but they have difficulties for fine motor control. The inertial sensor offers interesting kinematic parameters of the pathological movement. These parameters can be directly obtained by the inertial signals and are very useful to design filtering techniques to extract voluntary intentions. A research technique for filtering some patterns of the involuntary movements is presented. The inertial interface constructed and validated in this paper will allow increasing the knowledge about the pathological motion of the infants with CP. © 2010 Elsevier B.V. All rights reserved.


Haber R.E.,CSIC - Industrial Automation Institute | Del Toro R.M.,CSIC - Industrial Automation Institute | Gajate A.,CSIC - Industrial Automation Institute
Information Sciences | Year: 2010

This paper focuses on the optimal tuning of fuzzy control systems using the cross-entropy precise mathematical framework. The design of an optimal fuzzy controller for cutting force regulation in a network-based application and applied to the drilling process is described. The key issue is to obtain optimal fuzzy controller parameters that yield a fast and accurate response with minimum overshoot by minimising the integral time absolute error (ITAE) performance index. Simulation results show that the cross-entropy method does find the optimal solution (i.e. input scaling factors) very accurately, and it can be programmed and implemented very easily (few setting parameters). The results of a comparative study demonstrate that optimal tuning with the cross-entropy method provides a good transient response (without overshoot) and a better error-based performance index than simulated annealing [17], the Nelder-Mead method [14] and genetic algorithms [33]. The experimental results demonstrate that the proposed optimal fuzzy control provides outstanding transient response without overshoot, a small settling time and a minimum steady-state error. The application of optimal fuzzy control reduces rapid drill wear and catastrophic drill breakage due to the increasing and oscillatory cutting forces that occur as the drill depth increases. © 2010 Published by Elsevier Inc.


Estremera J.,CSIC - Industrial Automation Institute | Cobano J.A.,CSIC - Industrial Automation Institute | Gonzalez de Santos P.,CSIC - Industrial Automation Institute
Robotics and Autonomous Systems | Year: 2010

Autonomous robots are leaving the laboratories to master new outdoor applications, and walking robots in particular have already shown their potential advantages in these environments, especially on a natural terrain. Gait generation is the key to success in the negotiation of natural terrain with legged robots; however, most of the algorithms devised for hexapods have been tested under laboratory conditions. This paper presents the development of crab and turning gaits for hexapod robots on a natural terrain characterized by containing uneven ground and forbidden zones. The gaits we have developed rely on two empirical rules that derive three control modules that have been tested both under simulation and by experiment. The geometrical model of the SILO-6 walking robot has been used for simulation purposes, while the real SILO-6 walking robot has been used in the experiments. This robot was built as a mobile platform for a sensory system to detect and locate antipersonnel landmines in humanitarian demining missions. © 2009 Elsevier B.V. All rights reserved.


Ponticelli R.,CSIC - Industrial Automation Institute | de Santos P.G.,CSIC - Industrial Automation Institute
Mechatronics | Year: 2010

Effective automatic terrain recognition in a natural environment is a challenging task. The work presented in this article, part of the results obtained in a 6-year project devoted to the development of a hexapod robot for humanitarian demining missions, aims at finding a simple, reliable terrain-recognition solution based on a sensor head, a device that is associated with a landmine detector and is employed to gather terrain-related data. The goal is to construct a processed representation of the main terrain features as an obstacle-contour and terrain-elevation map. The methods and algorithms presented herein have been tested in a fully operative robot composed of several subsystems. © 2009 Elsevier Ltd. All rights reserved.

Loading CSIC - Industrial Automation Institute collaborators
Loading CSIC - Industrial Automation Institute collaborators