• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.4
• /
• pp.508-516
• /
• 2016

When GPS signals are not available, a relative localization can be alternatively used to represent the topological relationship between mobile nodes. A relative location map of a network can be constructed by using the distance information between all the pairs of nodes in the network. If a network is large, a number of small local maps are individually constructed and are merged to obtain the whole map. However, this approach may result in a high computation and communication overhead. In this paper, we propose a reference-node selection scheme for relative localization map construction, which chooses a subset of nodes as a reference node that is supposed to construct local maps. The scheme is a greedy algorithm that iteratively chooses nodes with high degree as a reference node until the chosen local maps are successfully merged with a sufficient number of common nodes between nearby local maps. The simulation results indicate that the proposed scheme achieves higher localization accuracy with a reduced computational overhead.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.5
• /
• pp.426-432
• /
• 2012

The positions of vessels in JTIDS where each vessel broadcasts its position, can be found using the relative navigation method. Besides positioning, the relative navigation could be adopted for identification friend or foe, tracking targets, monitoring battle field and etc. In this paper, we have explained the fundamental operation and technical structure for the relative navigation and implemented the simulation platform to evaluate the basic function and performance of the system in arbitrary environment. Using platform, the availability of relative navigation within the group network and the characteristic of the algorithm for position prediction was verified. Based on the simulation result, it was verified that EKF based navigation algorithm could produce great initial error and need quite convergence time. To improve the performance, we proposed a new navigation algorithm which uses the minimum norm estimation algorithm until the EKF converges. The simulation results reveal the relative navigation can be effectively used in the formation flight and collision avoidance system.

• Journal of Computing Science and Engineering
• /
• v.4 no.1
• /
• pp.53-79
• /
• 2010

This study proposes a framework to investigate the factors of mobile web success in the context of e-commerce, and the relative importance of these success factors in selecting the most preferred mobile web. First, the Updated Delone and Mclean IS success model (2003) is chosen to extract significant mobile web success factors in the context of e-commerce. Second, it is extended through applying an Analytic Network Process (ANP) approach for investigating the relative importance of each factor and ranking alternative mobile webs in the context of e-commerce. The choice of success measure is a function of the context, which is the objective of this study. Thus, the present study is aimed at evaluating the success of an e-commerce mobile web by customizing measures of the Updated Delone and McLean IS Success model according to the context.

• Proceedings of the KOSOMBE Conference
• /
• v.1995 no.11
• /
• pp.197-200
• /
• 1995

In this paper, we proposed the multi-step multi-layer artificial neural network(MMANN) to classify the chromosome, Which is used as a chromosome pattern classifier after learning. We extracted three chromosome morphological feature parameters such as centromeric index, relative length ratio, and relative area ratio by means of preprocessing method from ten chromosome images. The feature parameters of five chromosome images were used to learn neural network and the rest of them were used to classify the chromosome images. The experiment results show that the chromosome classification error is reduced much more, comparing with less feature parameters than that of the other researchers.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.71-76
• /
• 2003

The purpose of this study is the development, application and assessment of probability and artificial neural network methods for assessing landslide susceptibility in a chosen study area. As the basic analysis tool, a Geographic Information System (GIS) was used for spatial data management. A probability method was used for calculating the rating of the relative importance of each factor class to landslide occurrence, For calculating the weight of the relative importance of each factor to landslide occurrence, an artificial neural network method was developed. Using these methods, the landslide susceptibility index was calculated using the rating and weight, and a landslide susceptibility map was produced using the index. The results of the landslide susceptibility analysis, with and without weights, were confirmed from comparison with the landslide location data. The comparison result with weighting was better than the results without weighting. The calculated weight and rating can be used to landslide susceptibility mapping.

• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.555-559
• /
• 1998

The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis have been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, We proposed an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of two-step multi-layer neural network(TMANN). We reconstructed chromosome image to improve the chromosome classification accuracy and extracted four morphological features parameters such as centromeric index (C.I.), relative length ratio(R.L.), relative area ratio(R.A.) and chromosome length(C.L.). These Parameters employed as input in neural network by preprocessing twenty human chromosome images. The experiment results shown that the chromosome classification error was reduced much more than that of the other classification methods.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2007.11a
• /
• pp.457-458
• /
• 2007

We investigated a resistor network model for the horizontal AlInGaN LED. Adding the proposed current density dependent relative quantum efficiency, the power simulation can be also obtained. Comparing the simulation and the measurement results for the LED with the size of $350{\mu}m$, the model is reasonable to simulate the forward voltage and the light output power. Using this model we investigated the optimization of the position and the number of the finger electrodes in a given chip area. It shows that the center disposition of the p-finger electrode in p-area is optimal for the voltage and best for the power. And the minimum number of the n-finger electrodes is best for the power.

• ETRI Journal
• /
• v.45 no.2
• /
• pp.329-337
• /
• 2023

For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

• The KIPS Transactions:PartC
• /
• v.12C no.7 s.103
• /
• pp.1007-1014
• /
• 2005

A generation of rules or patterns for detecting attacks from network is very difficult. Detection rules and patterns are usually generated by Expert's experiences that consume many man-power, management expense, time and so on. This paper proposes statistical methods that effectively detect intrusion and attacks without expert's experiences. The methods are to select useful measures in measures of network connection(session) and to detect attacks. We extracted the network session data of normal and each attack, and selected useful measures for detecting attacks using relative entropy. And we made probability patterns, and detected attacks using likelihood ratio testing. The detecting method controled detection rate and false positive rate using threshold. We evaluated the performance of the proposed method using KDD CUP 99 Data set. This paper shows the results that are to compare the proposed method and detection rules of decision tree algorithm. So we can know that the proposed methods are useful for detecting Intrusion and attacks.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.6
• /
• pp.144-151
• /
• 2023

In this study, a database was established by collecting experimental results on various concrete mixtures subjected to freeze-thaw cycles, based on which an artificial neural network-based prediction model was developed to estimate durability resistance of concrete. A regression analysis was also conducted to derive an equation for estimating relative dynamic modulus of elasticity subjected to freeze-thaw loads. The error rate and coefficient of determination of the proposed artificial neural network model were approximately 11% and 0.72, respectively, and the regression equation also provided very similar accuracy. Thus, it is considered that the proposed artificial neural network model and regression equation can be used for estimating relative dynamic modulus of elasticity for various concrete mixtures subjected to freeze-thaw loads.