• Journal of Biomedical Engineering Research
• /
• v.27 no.5
• /
• pp.274-281
• /
• 2006

In this paper, we propose a ubiquitous $SaO_2$ monitoring system for patients using oxygen therapy. For these patients, the ability to monitor oxygen saturation ubiquitously is very important fur accurate adjustment of ventilator's flow rate to match the patient's time-varying requirements with the shortest lag time possible. We have developed a portable device to measure $SaO_2$ and transmit it to hospital in real-time or in store-and-forward mode through the integration of $Bluetooth^{TM}$ technology and the code division multiple access (CDMA) cellular network. We also developed software for doctors to receive and manage the patients' $SaO_2$ information. Performance of the developed system was evaluated as acceptable by assessing the accuracy of the measured oxygen saturation value and the stability of communication network. Test results in real clinical setting demonstrate that our system is feasible for immediate use in home oxygen therapy.

• The KIPS Transactions:PartC
• /
• v.12C no.2 s.98
• /
• pp.281-288
• /
• 2005

It is generally accepted that self-similar (or fractal) Processes may provide better models for teletraffic in modem computer networks than Poisson processes. f this is not taken into account, it can lead to inaccurate conclusions about performance of computer networks. Thus, an important requirement for conducting simulation studies of telecommunication networks is the ability to generate long synthetic stochastic self-similar sequences. A generator of pseudo-random self similar sequences, based on the SRA (successive random addition) method, is implemented and analysed in this paper. Properties of this generator were experimentally studied in the sense of its statistical accuracy and the time required to produce sequences of a given (long) length. This generator shows acceptable level of accuracy of the output data (in the sense of relative accuracy of the Hurst parameter) and is fast. The theoretical algorithmic complexity is O(n).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.809-812
• /
• 2006

This paper describes about the vision system, which was developed for the recognition of material management characters in the slab processing line. The material management characters, which are marked at the surface of a slab, are recognized by real time processing before slab moves to the next hot strip line. The vision system for the character recognition include that CCD camera system which acquire slab image, image transmission system which transmit captured image to the long distance, I/O devices for the interface with peripheral control system. We have installed vision system to the slab processing line and tested. Through the testing, we have checked durability, reliability and recognition rate of our system. In the results, we have confirmed that our system have good performance and higher recognition ability.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.11
• /
• pp.2629-2636
• /
• 2015

Recently Big Data management have a rapid increases interest in IT field, much research conducting to solve a problem of real-time processing to Big Data. Lots of resources are required for the ability to store data in real-time over the network but there is the problem of introducing an analyzing system due to aspect of high cost. Need of redesign of the system for low cost and high efficiency had been increasing to solve the problem. In this paper, the document type of database, MongoDB, is used for design a log management system based a document type of database, that is good at big data managing. The suggested log management system is more efficient than other method on log collection and processing, and it is strong on data forgery through the performance evaluation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.2843-2852
• /
• 2013

In the nested mobile network environment, the mobile node selects one of multiple mobile routers. The MR(Mobile Router) by existing top-down or bottom-up methods may not be the optimal MR if the numbers of mobile nodes and routers are substantially increased, and the scale of the network is increased drastically. Since an inappropriate MR decision causes handover or binding renewal to mobile nodes, determining of the optimal MR is important for efficiency. In this paper, we propose an algorithm that decides on the optimal MR using MR QoS(Quality of Service) information, and we describe how to understand the various structured MLP(Multi-Layered Perceptron) based on the algorithm. In conclusion, we prove the ability of the suggested neural network for a nesting mobile network through the performance analysis of each learned MLP.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.1-9
• /
• 2002

Evolutionary artificial neural networks (EANNs) are towards the near optimal ANN using the global search of evolutionary instead of trial-and-error process. However, many real-world problems are too hard to be solved by only one ANN. Recently there has been plenty of interest on combining ANNs in the last generation to improve the performance and reliability. This paper proposes a new approach of constructing multiple ANNs which complement each other by speciation. Also, we develop a multiple ANN to combine the results in abstract, rank, and measurement levels. The experimental results on Australian credit approval data from UCI benchmark data set have shown that combining of the speciated EANNs have better recognition ability than EANNs which are not speciated, and the average error rate of 0.105 proves the superiority of the proposed EANNs.

• Journal of Information Technology Services
• /
• v.11 no.4
• /
• pp.233-250
• /
• 2012

In this paper, credit card delinquency means the possibility of occurring bad debt within the certain near future from the normal accounts that have no debt and the problem is to predict, on the monthly basis, the occurrence of delinquency 3 months in advance. This prediction is typical binary classification problem but suffers from the issue of data imbalance that means the instances of target class is very few. For the effective prediction of bad debt occurrence, Support Vector Machine (SVM) with kernel trick is adopted using credit card usage and payment patterns as its inputs. SVM is widely accepted in the data mining society because of its prediction accuracy and no fear of overfitting. However, it is known that SVM has the limitation in its ability to processing the large-scale data. To resolve the difficulties in applying SVM to bad debt occurrence prediction, two stage clustering is suggested as an effective data reduction method and ensembles of SVM models are also adopted to mitigate the difficulty due to data imbalance intrinsic to the target problem of this paper. In the experiments with the real world data from one of the major domestic credit card companies, the suggested approach reveals the superior prediction accuracy to the traditional data mining approaches that use neural networks, decision trees or logistics regressions. SVM ensemble model learned from T2 training set shows the best prediction results among the alternatives considered and it is noteworthy that the performance of neural networks with T2 is better than that of SVM with T1. These results prove that the suggested approach is very effective for both SVM training and the classification problem of data imbalance.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.23 no.7
• /
• pp.575-579
• /
• 2010

The technologies of Ni/Cu plating contact is attributed to the reduced series resistance caused by a better contact conductivity of Ni with Si and the subsequent electroplating of Cu on Ni. The ability to pattern narrower grid lines for reduced light shading was combined with the lower resistance of a metal silicide contact and an improved conductivity of the plated deposit. This improves the FF (fill factor) as the series resistance is reduced. This is very much requried in the case of low concentrator solar cells in which the series resistance is one of the important and dominant parameter that affect the cell performance. A Selective emitter structure with highly dopeds regions underneath the metal contacts, is widely known to be one of the most promising high-efficiency solution in solar cell processing In this paper the formation of a selective emitter, and the nickel silicide seed layer at the front side metallization of silicon cells is considered. After generating the nickel seed layer the contacts were thickened by Cu LIP (light induced plating) and by the formation of a plated Ni/Cu two step metallization on front contacts. In fabricating a Ni/Cu plating metallization cell with a selective emitter structure it has been shown that the cell efficiency can be increased by at least 0.2%.

• The Journal of Korean Physical Therapy
• /
• v.28 no.1
• /
• pp.8-13
• /
• 2016

Purpose: The purpose of the present current study was to examine control of upper limb multi-joint movements with differential coordination stability. To achieve the goals of the study, torque analyses were utilized to answer questions about how torque components were differed among various elbow-wrist coordination patterns. Methods: Eight self-reported right-handed college students (3 males and 5 females, mean age=20.6 yr) were volunteered. The task required participants to rhythmically coordinate the flexion-extension motions of their elbow and wrist with coordination relationship of $0^{\circ}$, $90^{\circ}$, and $180^{\circ}$relative phases between the two joints. Mean relative phase and phase stability (standard deviation of relative phase) were computed to for analysisze of overall coordination performance. To determine the figure out characteristics of torque components in elbow and wrist joints, impulse values of muscle torque (MT) and interactive torque (IT) and MT as a percentage of cycle duration (MT-PCD) were analyzed. Results: Torque results showed that the proximal elbow joint generated motions with mainly muscle efforts regardless of coordination patterns, while the distal wrist joint adjusted the coordination patterns by changing amount of MT. Impulse analyses showed that the least stable $90^{\circ}$ pattern was performed by utilizing a similar coordination strategy of the most stable $0^{\circ}$ pattern. Conclusion: The present current study suggests that the roles of distal and proximal joints differ in order to achieve various multi-joint coordination movements. This study provides information for use in gives an idea to development of rehabilitation or training programs for to persons with an impaired upper limb motor ability.

• Journal of Internet Computing and Services
• /
• v.10 no.6
• /
• pp.1-6
• /
• 2009

In this paper, we propose an energy efficient index scheme for Nearest Neighbor queries, specially designed for mobile P2P environments. we propose a PMBR (P2P Minimum Boundary Rectangle) index that provides the client with the ability of selective contacting and tuning from other nodes. The mobile client is able to identify whether or not the neighbor nodes have the desired information by accessing PMBR. Thus, the client immediately switches to change to another node's broadcast channel if the index does not contain the desired information. Furthermore, the client is able to predict the arrival time of the desired data items and only needs to tune into the broadcast channel when the requested data items arrives, by first accessing PMBR. Thus, the mobile client can stay in power save mode most of time, and tune into the broadcast channel only when the requested data items arrive. Experiments are conducted to evaluate the performance of the proposed scheme. Comprehensive experiments illustrate that the proposed scheme is more efficient than the previous techniques in terms of energy consumption.