• The Transactions of the Korea Information Processing Society
• /
• v.7 no.12
• /
• pp.3821-3828
• /
• 2000

Many software projects collect grouped failure data (failures in some failure interval or in variable time interval) rather than individual failure times or failure count data during the testing or operational phase. This paper presents the neural network (NN) modeling that is dble to predict cumulative failures in the variable future time for grouped failure data. ANN's predictive ability can be affected by what it learns and in its ledming sequence. Eleven training regimes that represents the input-output of NN are considered. The best training regimes dre selected rJdsed on the next' step dvemge reldtive prediction error (AE) and normalized AE (NAE). The suggested NN models are compared with other well-known KN models and statistical software reliability growth models (SHGlvls) in order to evaluate performance, Experimental results show that the NN model with variable time interval information is necessary in order to predict cumulative failures in the variable future time interval.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.40 no.3
• /
• pp.182-188
• /
• 2004

It has been, in general, known that the catching efficiency of a trammel net is better than that of a gill net because of the variability of catch species and size. In this stidy, A fishing gear test was carried out to analyze the catching efficiency of the gill net and the trammel net on the coast of Geomun-do of southern Korean waters and fish school aggregation was also investigated using a underwater video camera. CPUE of the gill net was 49.2% higher than the trammel net but fish species was 34.5% lower where there was no difference on the significance level of 5% by ANOVA test. Main catch species caught by the gill net were red seabream(Pagrus major) and triggerfish(Aluterus monoceros), skate ray(Raja Kenojei) and red seabream for the trammel net, and the average body length of red seabream was shorter than the trammel net. It was thought that the reason of higher catch in the gill net than the trammel net was a fish school which can be caught easily by gill net and the size of population was suitable for the gill net.

• The KIPS Transactions:PartC
• /
• v.9C no.4
• /
• pp.551-562
• /
• 2002

We usually applied PPP CHAP when the visited ISP subscriber accesses to authentication server in own home ISP network and IP Assignment for remote Internet service. But PPP CHAP doesn't support in case of visited ISP subscriber in GPRS network accesses to authentication sorrel in own home ISP network for wireless Internet service. We suggest solution for this problem with PPP CHAP improvement. For this we propose the modified PPP CHAP message format, PCO Message format at MT, and interworking message and format between GGSN and RADIUS in home ISP network for wireless internet service of mobile ISP subscriber at GPRS network in this paper. We also show authentication results when visited mobile ISP subscriber via PPP CHAP at GPRS network accesses the RADIUS server in home ISP network.

• Journal of the Korean GEO-environmental Society
• /
• v.13 no.8
• /
• pp.25-33
• /
• 2012

Although it is important to reflect the accurate information of the ground condition in the tunnel design, the analysis and design are conducted by limited information because it is very difficult to consider various geographies and geotechnical conditions. When the tunnel is under construction, examination of accurate safety and prediction of behavior are overcome the limits of predicting behavior by Artificial Neural Network in this study. First, construct the suitable structure after the data of field was made sure by the multi-layer back propagation, then apply with algorithm. Employ the result of measured data from database, and consider the influence factor of tunnel, like supporting pattern, RMR, Q, the types of rock, excavation length, excavation shape, excavation over, to carry out the reliable analysis through field applicability of Artificial Neural Network. After studying, using the ANN model to predict the shearing displacement, convergence displacement, underground displacement, Rock bolt output follow the excavation over of tunnel construction field, then determine the field applicability with ANN through field measured value and comparison analysis when tunnel is being constructed.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.1
• /
• pp.54-61
• /
• 2001

A software package to classify acoustic emission (AE) signals using the wavelet transform and the neural network was developed Both of the continuous and the discrete wavelet transforms are considered, and the error back-propagation neural network is adopted as m artificial neural network algorithm. The signals acquired during the 3-point bending test of specimens which have artificial defects on weld zone are used for the classification of the defects. Features are extracted from the time-frequency plane which is the result of the wavelet transform of signals, and the neural network classifier is tamed using the extracted features to classify the signals. It has been shown that the developed software package is useful to classify AE signals. The difference between the classification results by the continuous and the discrete wavelet transforms is also discussed.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.11a
• /
• pp.143-144
• /
• 2023

해양수산부가 구축한 초고속 해상무선통신망(LTE-Maritime)은 연안으로부터 최대 100km 해역을 항해하는 선박들에게 지능형 해상교통정보서비스(e-Nav)를 제공하기 위한 기반 통신 인프라다. 선박에서 e-Nav 서비스를 제공받기 위해 LTE-M. 무선설비는 선내 고정 설치되어 유선으로 연결된 표시장치와 연동이 필요하다. 이는 공간이 협소하고 밀폐된 소형선박에 설치의 어려움뿐 아니라 선내 센서를 비롯한 다양한 IoT 기기 등과의 연결성에 제약을 줄 수 있다. 또한 선박이 육상의 LTE-M. 기지국과 멀리 떨어질 경우, 다운링크에 비해 업링크 통신품질이 상대적으로 취약해져 긴급 조난 신호를 비롯한 위험상황의 전달에 문제가 발생될 수 있다. 본 연구에서는 LTE-M. 망의 무선설비 다각화 사업으로 추진·개발된 소형선용 WiFi 및 업링크 향상용 무선설비의 실해역 성능 시험 방안을 고찰하여, 선내 WiFi 무선 품질을 평가하기 위한 성능 지표를 비롯해 업링크 통신속도 개선 등을 확인하기 위한 상호운용성 성능 시험 방안을 제시하고자 한다.

• Proceedings of the Korean Aquaculture Society Conference
• /
• 2006.05a
• /
• pp.65-66
• /
• 2006

• Proceedings of the Korean Society of Fisheries Technology Conference
• /
• 2005.05a
• /
• pp.125-129
• /
• 2005

• Proceedings of the Korean Society of Fisheries Technology Conference
• /
• 2005.11a
• /
• pp.75-78
• /
• 2005

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.4
• /
• pp.43-51
• /
• 2016

Preventing the forgery and alteration of test reports is important, in order to maintain the reliability of military supplies. Based on a survey of reports on testing institutions and a case study of established electronic document systems in the public sector, we propose a system architecture, which helps prevent the forgery and alteration of test reports with legal force. The proposed architecture takes advantage of both the time stamp that records the time a document is received and a server synchronized with the testing institution. Using the proposed system architecture, the user is able to request a test and receive reports from the testing institution without delay. Also, a defense agency is able to conveniently prove the authenticity of the test reports and utilize the statistical data collected by the architecture. Therefore, we expect that the proposed system architecture will help defense agencies to prevent the forgery and alteration of test reports and ensure their reliability and quality.