• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.191-200
• /
• 1996

This paper presetns a new fuzzy neural network for fuzzy modeling.The fuzzy neural network is composed of 4 layers and then odes of each layer represent the each step of the if-then fuzzy inference. A heuristic based on the back-propagation algorithm is proposed to ajdust the parameters of the fuzzy nerual network. We prove the feasibility of the network using the experiments on modeling a nonlinear mathematical system and the comparison with previous research.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.138-144
• /
• 1994

An inference network is proposed as a tool for bidirectional approximate reasoning. The inference network can be designed directly from the given fuzzy data(knowledge). If a fuzzy input is given for the inference netwok, then the network renders a reasonable fuzzy output after performing approximate reasoning based on an equality measure. Conversely, due to the bidirectional structure, the network can yield its corresponding reasonable fuzzy input for a given fuzzy output. This property makes it possible to perform forward and backward reasoning in the knowledge base system.

• Journal of Korea Multimedia Society
• /
• v.1 no.2
• /
• pp.249-255
• /
• 1998

This paper analyzes the impact of Call Setup Time on UPT performance based on the AIN platform. Call Setup Time is used as the performance parameter. In implementing UPT based on the AIN platform, the geographical location of VLR affects network performance. In order to find an optimum location of VLR among three different types of structures, i.e. VLR is located close to Service Switching Point and Cell Site Controller and located at Service Control Point, each Call Setup Time on proposed time delay model is calculated and compared. Network performance is analyzed by changing the number of STP in No.7 signaling network in UPT and the utilization ratio, $\rho$, for SSP, STP and SCP.

• Journal of the Korea Convergence Society
• /
• v.2 no.4
• /
• pp.1-7
• /
• 2011

As the developing of the information technology, M2M market that is using communication between devices is growing rapidly and many companies are involved in M2M business. In this paper, the concept of telematics and vulnerabilities of vehicle network security are discussed. The convergence of vehicle and information technology, the development of mobile communication technology have improved quality of service that provided to user but as a result security threats has diverse. We proposed new business model that be occurred to the participation of mobile carriers in telematics business and we analyzed mobile radio communication network security vulnerabilities. We proposed smart phone and Vehicle authentication scheme with M2M device as a way to solve vulnerabilities.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.1
• /
• pp.69-76
• /
• 2006

Telematics, which is a compound word of a telecommunication and informatics, provides drivers with useful driving information such as driving path guidance, accident or robbery detection, traffic conditions and other valuable data at real time. This paper proposes and implements how to build a telematics terminal equipped with CDMA and GPS running embedded Linux, to check a vehicle's state through communication between telematics server and vehicle terminals using a cellular phone and to control a vehicle using SMS as shown in Figure 1. In order to do this, we use the SK-VM platform which is mobile terminal platform based on JAVA to design, implement and evaluate it.

• Korean Journal of Remote Sensing
• /
• v.23 no.5
• /
• pp.465-471
• /
• 2007

Many hospitals have been considering new technology such as wireless sensor network(WSN). The technology can be used to track the location of medical devices needed for inspections or repairs, and it can also be used to detect of a theft of an asset. In an asset-tracking system using WSN, acquiring the location of moving sensor nodes inherently introduces uncertainty in location determination. In fact, the sensor nodes attached to an asset are prone to failure from lack of energy or from physical destruction. Therefore, even if the asset is located within the predetermined area, the asset-tracking application could "misunderstand" that an asset has escaped from the area. This paper classifies the causes of such unexpected situations into the following five cases: 1) an asset has actually escaped from a predetermined area; 2) a sensor node was broken; 3) the battery for the sensor node was totally discharged; 4) an asset went into a shadow area; 5) a sensor node was stolen. We implemented and installed our asset-tracking system in a hospital and continuously monitored the status of assets such as ventilators, syringe pumps, wheel chairs and IV poles. Based on this real experience, we suggest how to differentiate each case of location uncertainty and propose possible solutions to prevent them.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.5
• /
• pp.149-157
• /
• 2008

In this paper, a POI(Point-of-Interest) telematics service platform, in which detailed POI telematics services are discovered automatically and provided, is developed. The platform discovers services with UPnP middleware and provides a location-based service using GIS information. It is implemented by a telematics server, terminals, and service gateways and tested by applying test scenario for validation. Also, the response time and throughput of UPnP messages in the platform is measured and analyzed. The result shows that it has little impact on the service network congestion.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.1
• /
• pp.88-98
• /
• 1994

A new neural network architecture called the Parallel. Self-Organizing Hierarchical Neural Network (PSHNN) is presented. The new architecture involves a number of stages in which each stage can be a particular neural network (SNN). The experiments performed in comparison to multi-layered network with backpropagation training and indicated the superiority of the new architecture in the sense of classification accuracy, training time,parallelism.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.3
• /
• pp.150-158
• /
• 1998

This paper describes the classification of remotely sensed image data using fuzzy neural network, whose algorithm was obtained by replacing real numbers used for inputs and outputs in the standard back propagation algorithm with fuzzy numbers. In the proposed method, fuzzy patterns, generated based on the histogram ofeach category for the training data, are put into the fuzzy neural network with real numbers. The results show that the generalization and appoximation are better than that ofthe conventional network in determining the complex boundary of patterns.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.4
• /
• pp.610-617
• /
• 1987

This thesis is concerned with fault-tolerance of a B-net (Beta-network) which is a kind of interconnection network in the multicomputer system. In this paper, a method for obtaining Maximal Tolerable Fault Set(MTFS) of link line connecting switching elements in the arbitrary B-net is presented. Using this method, it is seen that testing of DFA capability is possible when s-a-faults of link line occur, and criterion for determining degree of fault- tolerance of a B-net in terms of link line is introduced.