Full 1
Full 1

Hamed Habibi Aghdam, Domenec Puig, Agusti Solanas

2014 22nd International Conference on Pattern Recognition, 3357-3362

Description: Segmentation of the breast region is usually the first step in the analysis of mammograms. Due to the non- uniformity of the background, breast segmentation presents several difficulties especially for film based mammograms. Our experimental results show that 50% of digitized film based mammograms in the mini-MIAS database do not have uniform intensity in the background. For this reason, applying a global thresholding method produces inaccurate results. In addition, finding the optimal global threshold value by only using histogram information requires a reliable objective function that charac- terizes the statistics of the background and the mammogram regions in the digitized mammograms. A second way to find the boundary of the breast consists in fitting a deformable model, such as snakes, on the mammogram. However, this method has three main shortcomings. First, the model must be initialized near the boundary. Second, using gradient information in the objective function can push the boundary toward the tissues inside the breast rather than the actual boundary. Third, in some mammograms the breast region is occluded by artifacts, such as labels, that have high gradient values on their boundary and cause the deformable model to be fitted on the artifact. To address these problems we propose a probabilistic adaptive thresholding method that uses texture information and its probability to find the most probable threshold values for specific parts of the mammogram. The experimental results on mini-MIAS database show that our proposed method outperforms the state-of-art methods and improves the accuracy at least 37% in comparison with the best results obtained by contour growing methods.

Agusti Solanas, Arnau Gavalda, Robert Rallo

International Conference on Artificial Neural Networks, 525-535

Description: The protection of personal privacy is paramount, and consequently many efforts have been devoted to the study of data protection techniques. Governments, statistical agencies and corporations must protect the privacy of the individuals while guaranteeing the right of the society to knowledge. Microaggregation is one of the most promising solutions to deal with this praiseworthy task. However, its high computational cost prevents its use with large amounts of data. In this article we propose a new microaggregation algorithm that uses self-organizing maps to scale down the computational costs while maintaining a reasonable loss of information.

Fran Casino, Peio Lopez-Iturri, Leyre Azpilicueta, Erik Aguirre, Francisco Falcone, Agusti Solanas

2016 7th International Conference on Information, Intelligence, Systems & Applications (IISA), 1-5

Description: In order to predict radio propagation behaviour within a context-aware scenario and to make better decisions on the deployment of antennas and sensors for particular purposes, the state of the art proposes plenty of simulation techniques based on deterministic methods like Ray Tracing and Ray Launching, combining Geometric Optics and Uniform Theory of Diffraction. In this context, simulations' quality largely depends on the number of reflections, providing sufficient angular resolution in the ray launching process. Despite of that, the computational cost of simulations in high definition (HD) prevents their use in complex environments and their low definition (LD) counterparts are used. In this article, we study the impact of simulation's parameters in order to discover which is the best possible configuration given a particular scenario. More concretely, we study the number of reflections parameter and its impact on post-processing techniques such as hybrid methods based on Collaborative Filtering techniques.

Fran Casino, Peio Lopez Iturri, Erik Aguirre, Leyre Azpilicueta, Francisco Falcone, Edgar Batista, Agusti Solanas

2016 IEEE International Smart Cities Conference (ISC2), 1-6

Description: Planning the deployment of antennas in complex environments is a difficult task that requires the analysis of each specific scenario. In many cases, real measurements are taken so as to map signal strengths, interferences, and so on. However, taking real measurements is very time consuming and becomes impractical in complex, large scenarios. With the aim to avoid this burden, simulation techniques based on Ray Tracing, combining Geometric Optics and Uniform Theory of Diffraction, are used to predict waves’ behaviour within a given environment. Those simulations depend on a number of parameters, namely angular resolution, number of rebounds, cells size, etc. By tuning these parameters, high-definition (HD) and low-definition (LD) results can be obtained. Although more practical than manual measurements, the computational cost of simulations in HD prevents their use in complex environments and their LD counterparts are applied. In this article we propose a technique based on collaborative filtering (CF) that allows the use of LD simulations (with low computational cost) by lessening their low quality problems. The proposed CF strategy exploits spacial constraints in 2D propagation planes to improve simulation results, which end up being very similar to those of HD, with a fraction of its computational cost.

Rezia Molfino, Giovanni Gerardo Muscolo, Domenec Puig, Carmine Tommaso Recchiuto, Agusti Solanas, A Mark Williams

Conference Towards Autonomous Robotic Systems, 311-312

Description: We are investigating new approaches to design and develop embodied humanoid robots with predictive behaviour in the real world. Our approaches are strongly based on the symbiotic interaction between the concepts of the embodied intelligence and simplexity that enables us to reproduce the artificial body in symbiosis with its intelligence. The research is based on the study of martial arts athletes and their planned movements. In particular, the taekwondo martial art competition where anticipation and adaptive behaviours are key points is used as a vehicle to address conceptual and design issues. The expected outcome will be the development of a robot that will have the capability to anticipate an opponent’s actions by coordinating eyes, head and legs, with a stable body constituted by an embodied platform bioinspired by the taekwondo athletes.

Page 18 of 32

Slide 1
Join us
Follow our last publications and stay connected!
LinkedIn

Av. Països Catalans, 26, 43470 Tarragona, Catalonia, Spain

Publications

Projects

Events