• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.670-675
• /
• 1994

Yhis paper describes a fault diagnosis simulation of the Real-Time Multiple Fault Dignosis System (RTMFDS) for forcasting faults in a system and deciding current machine state from signal information. Comparing with other diagnosis system for single fault,the system developed deals with multiple fault diagnosis,comprising two main parts. One is a remotesignal generating and transimission terminal and the other is a host system for fault diagnosis. Signal generator generate the random fault signal and the image information, and send this information to host. Host consists of various modules and agents such as Signal Processing Module(SPM) for sinal preprocessing, Performence Monotoring Module(PMM) for subsystem performance monitoring, Trigger Module(TM) for multi-triggering subsystem fault diagnosis, Subsystem Fault Diagnosis Agent(SFDA) for receiving trigger signal, formulating subsystem fault D\ulcornerB and initiating diagnosis, Fault Diagnosis Module(FDM) for simulating component fault with Hierarchical Artificial Neural Network (HANN), numerical models and Hofield network,Result Agent(RA) for receiving simulation result and sending to Treatment solver and Graphic Agent(GA). Each agent represents a separate process in UNIX operating system, information exchange and cooperation between agents was doen by IPC(Inter Process Communication : message queue, semaphore, signal, pipe). Numerical models are used to deseribe structure, function and behavior of total system, subsystems and their components. Hierarchical data structure for diagnosing the fault system is implemented by HANN. Signal generation and transmittion was performed on PC. As a host, SUN workstation with X-Windows(Motif)is used for graphic representation.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.9-17
• /
• 2021

In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.8
• /
• pp.1109-1116
• /
• 2001

This paper describes a mechanism and its aspects for monitoring user actions and behaviors on the web operated under the layered architecture that utilizes intelligent agents, and by which personalized information services, for instance one-to-one marketing, is easily facilitated and developed. Intelligent agent is one of techniques which enables to automate the whole process for providing personalized services that includes monitoring, logging a user actions and analyzing behaviors based on his or her profiles, and then selecting, organizing customizable contents which are at last delivered to the users browser or mail box also by intelligent agents. Monitoring technologies can utilize to help better construct the process in providing personalized services in that those services require intelligence in operating. As a result, implementing effective personalized services, however, depends on how well to define various users interests and needs, and how correctly to detect and log the actions when hey are done by users.

• The KIPS Transactions:PartD
• /
• v.11D no.1
• /
• pp.105-114
• /
• 2004

In this paper, we propose a collaboration method of diverse agents each others in multi-agent model and describe a node migration algorithm of Mobile-Agent (MA) using by the metadata of Naming-Agent (NA). Collaboration work of multi-agent assures stability of agent system and provides reliability of information retrieval on the distributed environment. NA, an important part of multi-agent, identifies each agents and series the unique name of each agents, and each agent references the specified object using by its name. Also, NA integrates and manages naming service by agents classification such as Client-Push-Agent (CPA), Server-Push-Agent (SPA), and System-Monitoring-Agent (SMA) based on its characteristic. And, NA provides the location list of mobile nodes to specified MA. Therefore, when MA does move through the nodes, it is needed to improve the efficiency of node migration by specified priority according to hit_count, hit_ratio, node processing and network traffic time. Therefore, in this paper, for the integrated naming service, we design Naming Agent and show the structure of metadata which constructed with fields such as hit_count, hit_ratio, total_count of documents, and so on. And, this paper presents the flow of creation and updating of metadata and the method of node migration with hit_count through the collaboration of multi-agent.

• Smart Structures and Systems
• /
• v.4 no.4
• /
• pp.439-448
• /
• 2008

Optical fiber sensors are by now broadly accepted as an innovative and reliable device for structural health monitoring, to be used either embedded into or bonded on structures. The accuracy of the strain measurement achievable by optical fiber sensors is critically dependent on the characteristics of the bonding of the various interface layers involved in the sensor bonding/embedding (structure material and gluing agent, fiber coating and gluing agent, fiber coating and fiber core). In fact, the signal of the bonded/embedded optical fiber sensor must correspond to the strain experienced by the monitored structure, but the quality of each involved interface can affect the strain transfer. This paper faces the characterization, carried on by both mechanical tests and morphological analysis, of the strain transfer function resulting with epoxidic and vinylester gluing agent on polyimide and acrylate coated optical fibers.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.85-90
• /
• 2001

Recently there are lots of concerning on robot agent system working for itself with the trends of the research of bio-mimetic system and intelligent Therefore it is necessary to develop more humanized interface system from communicating with the robot agent. In this paper a virtual 3D interface system is proposed based on Internet for remote controlling and monitoring of robot agent. The proposed system is constructed as manager-agent model and a man can order a job at the 3D virtual interface environment of the manager located remotely Then the robot agent detects a 3D profile data from a range finder automatically and the robot moves the object to the new position in real space. The proposed system supports a advanced interface displaying virtual 3D graphics and real moving images and which makes it possible one to manage the robot agent more conveniently.

• Journal of Advanced Navigation Technology
• /
• v.18 no.6
• /
• pp.625-632
• /
• 2014

The u-health service is using portable device such as smart device and it consists of small computing device. The u-health service carry out same performance with desktop computer. We designed message structure based on Bluetooth HDP. This message structure is used to transmit patient's biometric data on the smart device of medical team, patient and family over the mobile network environment. ISO/IEEE 11073 PHD standard was defined based on the method of communication between the agent and the manager. And We are confirmed the reliable transmission of biometric data at the smart device by implementing the android OS based patient information monitoring application to check the status of patient for medical team, patient and family.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.98-105
• /
• 2010

Health of the people involved in blood sugar, blood pressure, activity, and using bio-sensors to obtain biometric information, the system for monitoring health research for development is a lot. This paper analyzes the bio information by monitoring the u-health care agent system was developed. Activity measurement technology that uses 3-axis accelerometer sensor. 3-axis acceleration sensors, using information obtained from activity to activity analysis to calculate the exact algorithm was developed. More accurate than the existing system to calculate the calorie consumption, it is stored in the database management. and you can check your health status using of activity and bio-information.

• Journal of Internet Computing and Services
• /
• v.2 no.2
• /
• pp.1-9
• /
• 2001

To access massive and various HTML documents that are in the web using wireless Internet equipments, another WML document that is equal to the HTML document must be written. In the case Web documents written by HTML are massive, the construction of a WML site with the same information needs much cost of space and time. This paper designs and implements the HTML-XML converter that alleviates such a problem. The HTML-XML converter translates the Web document written by HTML to the WML document for portable wireless equipments. The HTML-XML converter has advantages that it reconstructs WML document dynamically according to portable wireless equipments and processes various image formats such as GIF, JPG, BMP, and so on. The HTML-WML converter can be used as not only a utility of the WML editor but also a real time converter on wireless internet.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.2
• /
• pp.63-70
• /
• 2018

Safety management agent manages the risk behavior of the worker with the naked eye, but there is a real difficulty for one the agent to manage all the workers. In this paper, IoT device is attached to a harness safety belt that a worker wears to solve this problem, and behavior data is upload to the cloud in real time. We analyze the upload data through the deep learning and analyze the risk behavior of the worker. When the analysis result is judged to be dangerous behavior, we designed and implemented a system that informs the manager through monitoring application. In order to confirm that the risk behavior analysis through the deep learning is normally performed, the data values of 4 behaviors (walking, running, standing and sitting) were collected from IMU sensor for 60 minutes and learned through Tensorflow, Inception model. In order to verify the accuracy of the proposed system, we conducted inference experiments five times for each of the four behaviors, and confirmed the accuracy of the inference result to be 96.0%.