David Vallejo

A highly adaptive recommender system based on fuzzy logic for B2C e-commerce portals

Past years have witnessed a growing interest in e-commerce as a strategy for improving business. Several paradigms have arisen from the e-commerce field in recent years which try to support different business activities, such as B2C and C2C. This paper introduces a prototype of e-commerce portal, called e-Zoco, of which main features are: (i) a catalogue service intended to arrange product categories hierarchically and describe them through sets of attributes, (ii) a product selection service able to deal with imprecise and vague search preferences which returns a set of results clustered in accordance with their potential relevance to the user, and (iii) a rule-based knowledge learning service to provide the users with knowledge about the existing relationships among the attributes that describe a given product category. The portal prototype is supported by a multi-agent infrastructure composed of a set of agents responsible for providing these and other services.

A multi-agent architecture for supporting distributed normality-based intelligent surveillance

Intelligent surveillance involves the use of AI techniques to monitor environments whose analysis is becoming more and more complex because of the large number of sensors used and the need of monitoring multiple events of interest simultaneously. Most of the current surveillance systems provide solutions for particular problems but still suffer from lack of flexibility and scalability when they are used on different or related surveillance problems. To overcome this limitation, two aspects should be addressed: a knowledge-based surveillance model flexible enough to deal with different events of interest and an architecture that gives support to this model when deploying the surveillance system within a particular scenario. This paper discusses the architecture devised to deploy intelligent surveillance systems by means of a set of autonomous agents that are responsible for the management of different surveillance tasks and for cooperating to monitor complex environments. This multi-agent architecture is inspired by a normality-based formal model used to define the knowledge needed to analyze general-purpose surveillance concepts. We use the architecture to deploy a surveillance system to monitor an urban traffic scenario.

INTELLIGENT SURVEILLANCE BASED ON NORMALITY ANALYSIS TO DETECT ABNORMAL BEHAVIORS

Intelligent surveillance refers to using Artificial Intelligence techniques in order to improve surveillance and deal with semantic information obtained from low-level security devices. In this con...

Monitoring Complex Environments Using a Knowledge-Driven Approach Based on Intelligent Agents

In this paper, the authors propose a method to develop intelligent surveillance systems based on surveillance components managed by software agents to deal with specific events of interest in complex environments.

A multi-agent approach to intelligent monitoring in smart grids

In this paper, we propose a scalable multi-agent architecture to give support to smart grids, paying special attention to the intelligent monitoring of distribution substations. The data gathered by multiple sensors are used by software agents that are responsible for monitoring different aspects or events of interest, such as normal voltage values or unbalanced intensity values that can end up blowing fuses and decreasing the quality of service of end consumers. The knowledge bases of these agents have been built by means of a formal model for normality analysis that has been successfully used in other surveillance domains. The architecture facilitates the integration of new agents and can be easily configured and deployed to monitor different environments. The experiments have been conducted over a power distribution network.

A modern approach to multiagent development

Multiagent systems (MAS) development frameworks aim at facilitating the development and administration of agent-based applications. Currently relevant tools, such as JADE, offer huge possibilities but they are generally linked to a specific technology (commonly Java). This fact may limit some application domains when deploying MAS, such as low efficiency or programming language restrictions. To contribute to the evolution of multiagent development tools and to overcome these constraints, we introduce a multiagent platform based on the FIPA standards and built on top of a modern object-oriented middleware. Experimental results prove the scalability and the short response-time of the proposal and justify the design and development of modern tools to contribute the multiagent technology.

A New Approach to Grid Computing for Distributed Rendering

Photo realistic Image Synthesis requires high computational power to generate virtual images from 3D models. In fact, the rendering of a single high-quality image may take days even on powerful computers. In this paper, we present a novel approach based on grid philosophy and the P2P model for distributed rendering. The grid allows us to face this challenge through a highly scalable decentralized architecture, which has been developed and evaluated to carry out rendering of single frames and full animations. An empirical comparison is established with a rendering cluster also developed for this work to generate images for monitoring applications. The main contribution of this paper is to reduce the gap between distributed rendering and the grid by empirically showing the advantages of this approach.

A Multi-agent Architecture for Multi-robot Surveillance

In this paper we propose a multi-agent architecture that gives support to a set of robots for surveillance tasks, such as environment exploration. We introduce two protocols to coordinate the robots: one of them to carry out role allocation depending on the mobility concept and the other one to gather information from the environment. The communication model is based on the use of communication channels and a publish-subscribe scheme that guarantees scalability when the number of robots increases. A case study in which the agents that control the robots are trained to recognise predefined patterns and to learn how far they are from the robots and their orientation is presented.

Dynamic weighted aggregation for normality analysis in intelligent surveillance systems

Intelligent surveillance systems should be able to carry out an exhaustive analysis from multi-sensor information according to multiple events of interest in order to classify situations as normal or abnormal. That is why the design of appropriate fusion methods is essential to combine the information from a number of monitored aspects and achieve a reliable interpretation of the environment state. Unfortunately, these systems operate under highly dynamic conditions. A static configuration of the weights that determine the importance of the monitored aspects or events of interest may lead to a high number of false alarms and the ignorance of critical situations. This paper performs a thorough study of different information fusion algorithms and proposes a method for the automatic reweighting of the values that establish the importance of the analyzed events of interest. This online method is flexible enough for adjusting such weights in each monitored situation to address the dynamic nature of real environments. The experiments, which have been conducted in a real urban traffic environment, demonstrate the feasibility of the proposed method.

OCULUS surveillance system: Fuzzy on-line speed analysis from 2D images

This paper presents an independent component integrated into a global surveillance system named as OCULUS. The aim of this component is to classify the speed of moving objects as normal or abnormal in order to detect anomalous events, taking into account the object class and spatio-temporal information such as locations and movements. The proposed component analyses the speed of the detected objects in real-time without needing several cameras, a 3D representation of the environment, or the estimation of precise values. Unlike other works, the proposed method does require knowing the camera parameters previously (e.g. height, angle, zoom level, etc.). The knowledge used by this component is automatically acquired by means of a learning algorithm that generates a set of highly interpretable fuzzy rules. The experimental results demonstrate that the proposed method is accurate, robust and provides a real-time analysis.