Catálogo de publicaciones - libros

In this paper, we proposed a multi-agent based healthcare system (MAHS) which is the combination of medical sensor module and wireless communication technology. This MAHS provides wide services to mobile telemedicine, patient monitoring, emergency management, doctor’s diagnosis and prescription, patients and doctors, information exchange between hospital workers in a long distance. Also, MAHS is connected to Body Area Network (BAN) and a doctor and hospital workers. In addition, we designed and implemented extended JADE based MAHS that reduces hospital server’s burden. Agents gather, integrate, and deliver the collected patient’s information from sensor, and provide presentation in healthcare environment. Proposed MAHS has advantage that can handle urgent situation in the far away area from hospital like Islands through PDA and mobile device. In addition, by monitoring condition of patient (old man) in a real time base, it shortens time and expense and supports medical service efficiently.

Moving object segmentation in complex scene is the basis for video surveillance, event detection, tracking and development of vision agent in industrial robotics. However, due to presence of camera noise and illumination change, simple background subtraction based techniques are not able to detect moving objects properly. In this paper, we present a novel block based moving object detection method which dynamically quests for both local and global properties of difference image to achieve robustness. Noise model of the difference image is determined analyzing the histogram of difference image and block wise local properties are computed. These local properties are compared with the noise model to extract moving blocks. To remove the stair like artifacts of the segmented result, and to obtain smoothed and accurate boundary, a refinement procedure is employed on the boundary regions of detected moving objects. Experimental results show that the proposed method is robust and achieves better performance in dynamic environment.

The paper presents hierarchical and multi-agent control and information system with real-time update of self organising database as well as with negotiation capability for control events and decisions. A practical application is presented, that utilizes the OPC technology in the continuous-time part, and scripts using XML in the discrete-time part of the system for negotiation and cooperation in multi-agent environment. This feature is applied for the improvement of a non-conventional biotechnological process control in the pilot plant.

In this paper, we present a novel model of autonomous floating agents which can self-assemble on a water surface. We focus especially on the shape of the agent, which is essential as a factor of aggregation but difficult to deal with as finite states. After several experiments, a unique self-assembling behavior was observed by exploiting several physical-level forces; 6 agents gather into a cluster and form a specific pattern, which is unique to the configuration. This is considered crucial to achieve morphogenesis of a multi-agent system, of which we think as a hierarchical aggregation. The results shown here provide a good starting point for speculation about the level of autonomy of a agent in the complex environment when the system creates a self-assembling pattern.

This paper addresses the problem of building a failure detection service for large scale distributed systems, as well as multi-agent systems. It describes the failure detector mechanism and defines the roles it plays in the system. Afterwards, the key construction problems that are fundamental in the context of building the failure detection service are presented. Finally, a sketch of general framework for implementing such a service is described. The proposed failure detection service can be used by mobile agents as a crucial component for building fault-tolerant multi-agent systems.

Container terminals are essential intermodal interfaces in the global transportation network. Efficient container handling at terminals is important in reducing transportation costs and keeping shipping schedules. This paper discusses a multi-agent model to simulate, solve and optimize the amount of storage space for handling container departures within a fluvial or maritime port. The multi-agent model is developed to minimize the expected total number of rehandles while respecting spatio-temporal constraints. Experimental and numerical runs are given and illustrated. These runs carry out the proposed multi-agent model with comparison to the associated centralized version, basing on non-informed search algorithm and informed search algorithm. They show that the multi-agent model reduces rather the number of expected relocation movements especially when basing on informed search algorithm.

This paper proposes a distributed code and data propagation algorithm for Longest Common Subsequence problem solving and compares this algorithm performance against the algorithm based on J2EE technology. The new algorithm builds a graph devised to propagate classes and data between different nodes and the client, whereas the J2EE algorithm requires more complex communication and database processing. The proposed algorithm’s performance in terms of number of nodes and execution time is better than or comparable to that of the existing algorithms.

Developing sensor networks enable us to gather information about specified regions or tasks. Sensing nodes have several characteristics to have constrained energy and limited capacity. So, minimizing energy consumption and maximizing system lifetime have been a major issue for wireless sensor networks. What is unique about our proposed agent approach is that the agent has a learning capability using cluster configuration technique while the fitness criterion is based on energy consumption, election of cluster heads, and the number of clusters. This paper proposes an energy-efficient routing algorithm based on organizing clusters in sensing area by electing agents called cluster heads. This strategy allows an agent as cluster head to keep a routing table about intermediary nodes that can communicate between different clusters. The agent gathers routing information to establish routing paths by intermediary nodes and to decide an appropriate path by the routing table. When a sink node diffuses an interest, an agent finds neighbor clusters to reach to the sink node and transmits a response to intermediary nodes. The intermediary node then transmits the response to the agent. Thus, the agent decides to report to the sink node. This mechanism gives sensor nodes lower consumption of energy and prolonging system lifetime.

This paper is researched to design agent for the progress management. And this paper is intended to help the design agent and progress management based on the project management. Also, there are many defects that cause the domain problems during the project development. This paper remove the risk of the lifecycle and progress management that check the risk items in the process and also manage the progress and quality problems. Therefore, we are use of the incremental method for the remove of risk items. The analysis is made based on the types required for making use of the defect data. In this case, additional measures must be taken besides merely recording defects. And the theory is apply to the agent web security access control system for the security requirement. This paper provides an design of intelligence agent for the progress management. And the process can also be managed by using lifecycle and progress milestone, which can greatly improve the software process.

Standardized infrastructure for information or knowledge sharing is required to make autonomous agents interdependent on each other for effective collaboration in a multi-agent system. Folksonomy has become very popular as an enabling technology to provide a common conceptualization of the data that agent systems use. However, there are problems on free-form tagging in folksonomy. Folksonomy is only concerned with a group of instances which are labeled with tags without a formal definition. No available tool provides a way to contextualize folksonomies with respect to users, communities, goals, tasks, and so on. There is no formal approach to classifying and sharing tags that reflect a user’s mental model of information resources in terms of folksonomy. We present a novel approach to developing an agent environment for contextualizing folksonomies in a triadic context using Formal Concept Analysis. We conducted an experiment to build concept hieracrhies and contextualize folksonomies from tags of blogosphere.