Architecture of a multi-modal dialogue system oriented to multilingual question-answering

In this paper, a proposal of a multi-modal dialogue system oriented to multilingual question-answering is presented. This system includes the following ways of access: voice, text, avatar, gestures and signs language. The proposal is oriented to the question-answering task as a user interaction mechanism. The proposal here presented is in the first stages of its development phase and the architecture is presented for the first time on the base of the experiences in question-answering and dialogues previously developed. The main objective of this research work is the development of a solid platform that will permit the modular integration of the proposed architecture.

Multi-agent system for control of robots inspired on the distributed activity and hormonal regulation of humans

Robotics is an emerging field with great activity. Robotics is a field that presents several problems because it depends on a large number of disciplines, technologies, devices and tasks. Its expansion from perfectly controlled industrial environments toward open and dynamic environment presents a many new challenges. New uses are, for example, household robots or professional robots. To facilitate the low cost, rapid development of robotic systems, reusability of code, its medium and long term maintainability and robustness are required novel approaches to provide generic models and software systems who develop paradigms capable of solving these problems. For this purpose, in this paper we propose a model based on multi-agent systems inspired by the human nervous system able to transfer the control characteristics of the biological system and able to take advantage of the best properties of distributed software systems. Specifically, we model the decentralized activity and hormonal variation.

Parallel Computational Intelligence-Based Multi-Camera Surveillance System

In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.

Profitability analysis of a femtosecond laser system for cataract surgery using a fuzzy logic approach

AIM: To define the financial and management conditions required to introduce a femtosecond laser system for cataract surgery in a clinic using a fuzzy logic approach. METHODS: In the simulation performed in the current study, the costs associated to the acquisition and use of a commercially available femtosecond laser platform for cataract surgery (VICTUS, TECHNOLAS Perfect Vision GmbH, Bausch & Lomb, Munich, Germany) during a period of 5y were considered. A sensitivity analysis was performed considering such costs and the countable amortization of the system during this 5y period. Furthermore, a fuzzy logic analysis was used to obtain an estimation of the money income associated to each femtosecond laser-assisted cataract surgery (G). RESULTS: According to the sensitivity analysis, the femtosecond laser system under evaluation can be profitable if 1400 cataract surgeries are performed per year and if each surgery can be invoiced more than $500. In contrast, the fuzzy logic analysis confirmed that the patient had to pay more per surgery, between $661.8 and $667.4 per surgery, without considering the cost of the intraocular lens (IOL). CONCLUSION: A profitability of femtosecond laser systems for cataract surgery can be obtained after a detailed financial analysis, especially in those centers with large volumes of patients. The cost of the surgery for patients should be adapted to the real flow of patients with the ability of paying a reasonable range of cost.