• 대한전자공학회논문지
• /
• 제26권3호
• /
• pp.160-166
• /
• 1989

공간영역 예측기의 계수를 계산하기 위한 적응 알고리듬이 제안되었다. 제안된 방법은 LMS 알고리듬을 사용하여 TDL(tapped-delay-line)과 ESC(escalator) 구조를 갖는 공간영역 예측기의 계수를 계산한다. 기종존의 일반적인 예측기와 다른점은 순방향과 역방향 예측 오차의 평균 자승값의 합을 최소화하며 예측기의 계수를 계산함으로 향상된 선형예측 공간 스펙트럼을 얻을 수 있다. 제안된 방법을 선형으로 배열된 센서에 의하여 얻어진 협대역신호의 입사각 추정문제에 적용시켜 기존의 적응예측 알고리듬과 컴퓨터 시뮬레이션을 통하여 성능을 비교하였다.

• 한국국방경영분석학회지
• /
• 제25권1호
• /
• pp.142-159
• /
• 1999

To assign the soldiers in the adequate positions I military is almost as important as managing officers because they compose the main part of military structure and equipment operators. The current Military Occupational Specialty(MOS) assignment system lacks the capability to optimize the use of recruit's potential. We suggest an MOS assignment method for enlisted recruits using the Analytic Hierarchy Process(AHP) method, this method systematically provides a method of calculation of composite relative weights of decision elements to be considered during MOS assignment and a method of quantification for personal quality of new recruits. The quantified value of personal quality, Mission Performance Capability(MPC), in this study means the mission performance capability when a personnel is assigned to a certain MOS. This paper develops a multiple objectives MOS assignment model for enlisted recruits. It uses MPC of personnels, calculated with AHP method and consensus method, as parameters. The goal constraints are assurance of filling requirement, minimization of the number of unassigned personnel to MOS, capability satisfaction of education facility and support facility, assurance of desired MPC value level for MOS assignment, and maximization of total MPC. The objective function is to terminalization of the negative or positive deviation for the above goal constraints.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 공동추계학술대회
• /
• pp.516-525
• /
• 2005

Case-based reasoning (CBR) has been widely used in various areas due to its convenience and strength in complex problem solving. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However, designing a good matching and retrieval mechanism for CBR systems is still a controversial research issue. Most prior studies have tried to optimize the weights of the features or selection process of appropriate instances. But, these approaches have been performed independently until now. Simultaneous optimization of these components may lead to better performance than in naive models. In particular, there have been few attempts to simultaneously optimize the weight of the features and selection of the instances for CBR. Here we suggest a simultaneous optimization model of these components using a genetic algorithm (GA). We apply it to a customer classification model which utilizes demographic characteristics of customers as inputs to predict their buying behavior for a specific product. Experimental results show that simultaneously optimized CBR may improve the classification accuracy and outperform various optimized models of CBR as well as other classification models including logistic regression, multiple discriminant analysis, artificial neural networks and support vector machines.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권11호
• /
• pp.563-568
• /
• 2016

단어 의미 분별 문제는 문장에서 어떤 단어가 사전에 가지고 있는 여러 가지 의미 중 정확한 의미를 파악하는 문제이다. 우리는 이 문제를 다중 클래스 분류 문제로 간주하고 지지벡터기계를 이용하여 분류한다. 세종 의미 부착 말뭉치에서 추출한 의미 중의성 단어의 문맥 단어를 두 가지 벡터 공간에 표현한다. 첫 번째는 문맥 단어들로 이뤄진 벡터 공간이고 이진 가중치를 사용한다. 두 번째는 문맥 단어의 윈도우 크기에 따라 문맥 단어를 단어 임베딩 모델로 사상한 벡터 공간이다. 실험결과, 문맥 단어 벡터를 사용하였을 때 약 87.0%, 단어 임베딩을 사용하였을 때 약 86.0%의 정확도를 얻었다.

• Journal of Chest Surgery
• /
• 제25권5호
• /
• pp.458-468
• /
• 1992

With the aid of extracorporeal circulation, nine dogs underwent orthotopic cardiopulmonary transplantation after preservation of the donor heart in a hypothermic amino acid[glutamate, aspartate] enriched high potassium extracellular solution, and preservation of the donor lung with hypothermic low potassium dextran solution from June 1990 to May 1991. The mean body weights of dogs were 20kg and the recipients` preoperative hematologic and hemodynamic pictures were within normal range except slightly decreased level of albumin and total protein, which was supposed to be due to malnutrition. The following modifications of the original Stanford technique were emphasized: [1] the posterior mediastinum is dissected as little as possible with meticulous hemostasis; [2] the surgical procedure is kept away from the phrenic and vagus nerves; [3] the tracheal anastomosis may be wrapped with recipient`s pulmonary artery flap or surrouding soft tissues. A combination of Cyclosporine, Azathioprine, corticosteroid was used as perioperative immunosuppressive therapy. Postoperatively all recipients could be weaned from extracorporeal circulation, showing favorable vital signs, but within 24 hours, irreversible congetive heart failure, ascites, arrhythmias developed with a mean survival time 13.6$\pm$6.6[n=9, range=6~26] hours. Hemoglobin and platelet counts were significantly[p<0.05] decreased postoperatively, which is thought to be attributed to blood damage by cardiopulmonary bypass and hemodilution. Postmortem finding included multiple subendocardial patch hemorrhage in both atrial and ventricular cavities, pulmonary and liver congestion, and all tracheal anastomoses were intact. Further consideration about quality control of the animal, infection, rejection, the effect of cardiopulmonary bypass on the experimental animal is required to improve the results.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2013년도 추계학술대회 논문집
• /
• pp.320-324
• /
• 2013

A crack identification method using an equivalent bending stiffness for cracked beam and committee of neural networks is presented. The equivalent bending stiffness is constructed based on an energy method for a straight thin-walled pipe, which has a through-the-thickness crack, subjected to bending. Several numerical analysis for a steel cantilever pipe using the equivalent bending stiffness are carried out to extract the natural frequencies and mode shapes of the cracked beam. The extracted modal properties are used in constructing a training patterns of a neural network. The input to the neural network consists of the modal properties and the output is composed of the crack location and size. Multiple neural networks are constructed and each individual network is trained independently with different initial synaptic weights. Then, the estimated crack locations and sizes from different neural networks are averaged. Experimental crack detection is carried out for 3 damage cases using the proposed method, and the identified crack locations and sizes agree reasonably well with the exact values.

• 한국산림과학회지
• /
• 제95권5호
• /
• pp.569-579
• /
• 2006

This study focuses on the application of multi-criteria performance measures based on the concept of equifinality to the calibration of the rainfall-runoff model TOPMODEL in a small deciduous forest catchment. The performance of each parameter set was evaluated by six performance measures, individually, and each set was identified as a behavioral or non-behavioral parameter set by a given behavioral acceptance threshold. Many behavioral parameter sets were scattered throughout the parameter space, and the range of model behavior and the sensitivity for each parameter varied considerably between the different performance measures. Sensitivity was very high in some parameters, and varied depending on the kind of performance measure as well. Compatibilities of behavioral parameter sets between different performance measures also varied, and very few parameter sets were selected to be used in making god predictions for all performance measures. Since different behavioral parameter sets with different likelihood weights were obtained for each performance measure, the decision on which performance measure to be used may be very important to achieve the goal of study. Therefore, one or more suitable performance measures should be selected depending on the environment and the goal of a study, and this may lead to decrease model uncertainty.

• Smart Structures and Systems
• /
• 제24권5호
• /
• pp.617-630
• /
• 2019

Currently most of the vision-based structural identification research focus either on structural input (vehicle location) estimation or on structural output (structural displacement and strain responses) estimation. The structural condition assessment at global level just with the vision-based structural output cannot give a normalized response irrespective of the type and/or load configurations of the vehicles. Combining the vision-based structural input and the structural output from non-contact sensors overcomes the disadvantage given above, while reducing cost, time, labor force including cable wiring work. In conventional traffic monitoring, sometimes traffic closure is essential for bridge structures, which may cause other severe problems such as traffic jams and accidents. In this study, a completely non-contact structural identification system is proposed, and the system mainly targets the identification of bridge unit influence line (UIL) under operational traffic. Both the structural input (vehicle location information) and output (displacement responses) are obtained by only using cameras and computer vision techniques. Multiple cameras are synchronized by audio signal pattern recognition. The proposed system is verified with a laboratory experiment on a scaled bridge model under a small moving truck load and a field application on a footbridge on campus under a moving golf cart load. The UILs are successfully identified in both bridge cases. The pedestrian loads are also estimated with the extracted UIL and the predicted weights of pedestrians are observed to be in acceptable ranges.

• 대한수의학회지
• /
• 제61권2호
• /
• pp.12.1-12.9
• /
• 2021

The mosquito-borne pathogen Zika virus may result in neurological disorders such as Guillain-Barré syndrome and microcephaly. The virus is classified as a member of the Flaviviridae family and its wide spread in multiple continents is a significant threat to public health. So, there is a need to develop animal models to examine the pathogenesis of the disease and to develop vaccines. To examine the clinical profile during Zika virus infection, we infected neonatal and adult wild-type mice (C57BL/6 and Balb/c) and compared the clinical signs of African-lineage strain (MR766) and Asian-lineage strain (PRVABC59, MEX2-81) of Zika virus. Consistent with previous reports, eight-week-old female Balb/c mice infected with these viral strains showed no changes in body weight, survival rate, and neurologic signs, but demonstrated increases in the weights of spleens and hearts. However, one-day-old neonates showed significantly lower survival rate and body weight with the African-lineage strain than the Asian-lineage strain. These results confirmed the pathogenic differences between Zika virus strains. We also evaluated the clinical responses in neonatal and adult mice of different strains. Our findings suggest that these are useful mouse models for characterization of Zika virus for vaccine development.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.237-245
• /
• 2022

The prominence of IoTs (Internet of Things) and exponential advancement of computer networks has resulted in massive essential applications. Recognizing various cyber-attacks or anomalies in networks and establishing effective intrusion recognition systems are becoming increasingly vital to current security. MLTs (Machine Learning Techniques) can be developed for such data-driven intelligent recognition systems. Researchers have employed a TFDNNs (Tensor Flow Deep Neural Networks) and DCNNs (Deep Convolution Neural Networks) to recognize pirated software and malwares efficiently. However, tuning the amount of neurons in multiple layers with activation functions leads to learning error rates, degrading classifier's reliability. HTFDNNs ( Hybrid tensor flow DNNs) and MRNs (Modified Residual Networks) or Resnet CNNs were presented to recognize software piracy and malwares. This study proposes HTFDNNs to identify stolen software starting with plagiarized source codes. This work uses Tokens and weights for filtering noises while focusing on token's for identifying source code thefts. DLTs (Deep learning techniques) are then used to detect plagiarized sources. Data from Google Code Jam is used for finding software piracy. MRNs visualize colour images for identifying harms in networks using IoTs. Malware samples of Maling dataset is used for tests in this work.