• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.271-280
• /
• 1999

인공신경망을 시계열예측에 적용하는 경우에 고려되어야 할 문제중, 특히 모형에 적합한 입력변수의 생성이 중요시되고 있는데, 이러한 분야는 인공신경망의 모형생성과정에서 입력변수에 대한 전처리기법으로써 다양하게 제시되어 왔다. 가장 최근의 입력변수 전처리기법으로써 제시되고 있는 신호처리기법은 전통적 주기분할처리방법인 푸리에변환기법(Fourier transforms)을 비롯하여 이를 확장시킨 개념인 웨이블릿변환기법(wavelet transforms) 등으로 대별될 수 있다. 이는 기본적으로 시계열이 다수의 주기(cycle)들로 구성된 상이한 시계열들의 집합이라는 가정에서 출발하고 있다. 전통적으로 이러한 시계열은 전기 또는 전자공학에서 주파수영역분할, 즉 고주파 및 저주파수를 분할하기 위한 기법에 적용되어 왔다. 그러나, 최근에는 이러한 연구가 다양한 분야에 활발하게 응용되기 시작하였으며, 그 중의 대표적인 예가 바로 경영분야의 재무시계열에 대한 분석이다. 전통적으로 재무시계열은 장, 단기의사결정을 가진 시장참여자들간의 거래특성이 시계열에 각기 달리 가격으로 반영되기 때문에 이러한 상이한 집단들의 고요한 거래움직임으로 말미암아 예를 들어, 주식시장이 프랙탈구조를 가지고 있다고 보기도 한다. 이처럼 재무시계열은 다양한 사회현상의 집합체라고 볼 수 있으며, 그만큼 예측모형을 구축하는데 어려움이 따른다. 본 연구는 이러한 시계열의 주기적 특성에 기반을 둔 신호처리분석으로서 기존의 시계열로부터 노이즈를 줄여 주면서 보다 의미있는 정보로 변환시켜줄 수 있는 웨이블릿분석 방법론을 새로운 필터링기법으로 사용하여 현재 많은 연구가 진행되고 있는 인공신경망의 모형결합을 통해 기존연구과는 다른 새로운 통합예측방법론을 제시하고자 한다. 본 연구에서는 제시하는 통합방법론은 크게 2단계 과정을 거쳐 예측모형으로 완성이 된다. 즉, 1차 모형단계에서 원시 재무시계열은 먼저 웨이브릿분석을 통해서 노이즈가 필터링 되는 동시에, 과거 재무시계열의 프랙탈 구조, 즉 비선형적인 움직임을 보다 잘 반영시켜 주는 다차원 주기요소를 가지는 시계열로 분해, 생성되며, 이렇게 주기에 따라 장단기로 분할된 시계열들은 2차 모형단계에서 신경망의 새로운 입력변수로서 사용되어 최종적인 인공 신경망모델을 구축하는 데 반영된다. 기존의 주기분할방법론은 모형개발자입장에서 여러 가지 통계기준치중에서 최적의 기준치를 합리적으로 선택해야 하는 문제가 추가적으로 발생하며, 본 연구에서는 이상의 제반 문제들을 개선시키기 위해 통합방법론으로서 기존의 인공신경망모형을 구조적으로 확장시켰다. 이 모형에서 기존의 입력층 이전단계에 새로운 층이 정의된다. 이렇게 해서 생성된 새로운 통합모형은 기존모형에서 생성되는 기본적인 학습파라미터와 더불어, 본 연구에서 새롭게 제시된 주기분할층의 파라미터들이 모형의 학습성과를 높이기 위해 함께 고려된다. 한편, 이러한 학습과정에서 추가적으로 고려해야 할 파라미터 갯수가 증가함에 따라서, 본 모델의 학습성과가 local minimum에 빠지는 문제점이 발생될 수 있다. 즉, 웨이블릿분석과 인공신경망모형을 모두 전역적으로 최적화시켜야 하는 문제가 발생한다. 본 연구에서는 이 문제를 해결하기 위해서, 최근 local minimum의 가능성을 최소화하여 전역적인 학습성과를 높여 주는 인공지능기법으로서 유전자알고리즘기법을 본 연구이 통합모델에 반영하였다. 이에 대한 실증사례 분석결과는 일일 환율예측문제를 적용하였을 경우, 기존의 방법론보다 더 나운 예측성과를 타나내었다.

• Journal of the Korean Geotechnical Society
• /
• v.21 no.8
• /
• pp.73-84
• /
• 2005

A three layered neural network model was developed using back propagation algorithm to estimate the UU undrained shear strength of Korean soft soil based on the database of actual undrained shear strengths and piezocone measurements compiled from 8 sites over the Korea. The developed model was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was also compared with conventional empirical methods. It was found that the number of neuron in hidden layer is different for the different combination of transfer functions of neural network models. However, all piezocone neural network models are successful in inferring a complex relationship between piezocone measurements and the undrained shear strength of Korean soft soils, which give relatively high coefficients of determination ranging from 0.69 to 0.72. Since neural network model has been generalized by self-learning from database of piezocone measurements and undrained shear strength over the various sites, the developed neural network models give more precise and generally reliable undrained shear strengths than empirical approaches which still need site specific calibration.

• The KIPS Transactions:PartC
• /
• v.12C no.3 s.99
• /
• pp.457-464
• /
• 2005

This paper describes an Adaptive Context-aware Service (ACS) using Model Driven Architecture (MDA)-based Service Creation Environment (SCE) on PARLAY X based service delivery platform in ubiquitous computing environments. It can be expected that both the context-awareness and adaptation in ubiquitous computing environments will be deployed. But the existing context-aware middleware lacks in considering adaptation. Therefore, the object of this paper is to support the architecture and the Application Programming Interface (API) of the network service for both the context-awareness and adaptation in ubiquitous computing environment. ACS is to provide users with the adaptive network service to the changing context constraints as well as detecting the changing context. For instance, ACS can provide users with QoS in network according to the detected context, after detecting the context such as location and speed. The architecture of ACS is comprised of a Service Creation Environment (SCE), Adaptive Context Broker and PARLAY gateway. SCE is to use Context-based Constraint Language (CCL) for an expression of context-awareness and adaptation. Adaptive Context Broker is to make a role of the broker between SCE and PARLAY G/W. PARLAY G/W is to support API for PARLAY X-based service delivery platform.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.34 no.1
• /
• pp.13-20
• /
• 1998

The moving behaviour of Yellowtail Seriola quinqueradiata schools in the main-net of a large scale set-net was investigated in relation to the catching function of the funnel-net by a scanning sonar. The investigation was took place in the Kishihata set-net fishing ground located in Nanao city Ishigawa prefecture, Japan from Nov. 9 to Nov. 13, 1992. The obtained results are summarized as follows; 1. Fish schools showed the greatest number at the playground in the morning and at the bag-net in the afternoon. The fish schools remained long time in the main-net. 2. The rate of fish school through the funnel-net was smaller than that of fish school which is though the playground and bag-net. Because the Yellowtail school changed the shape of school in passing the funnel-net. 3. The rate of entering the bag-net was 24%, among the fish school heading to the outer funnel-net. But, the rate of escaping to the playground was 27%, among the fish school heading to the inner funnel-net. It seems that the structure of the outer funnel-net was not enough to lead the fish to the bag-net. However, the structure of the inner funnel-net was very effective at preventing escape. 4. It is appropriate to haul the net in the morning in considering the number of accumulated fish in the bag-net during the survey.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.93-103
• /
• 2021

S&OP(Sales and Operations Planning) is an ongoing process of periodic planning, reviewing, and evaluation through the involvement of all key stakeholders. Within this process, performance is regularly reviewed and early warning signals are generated, so that the company can react quickly to changing market and operational environment. This paper presents a framework for effective S&OP for fair alignment, accountability, teamwork, visibility, and risk management. This framework focuses on supply chain information governance, level of information sharing through S&OP, role of S&OP as coordination mechanism, APS effectivesness as a planning tool and SCM performance. In addition, a brief case study on the operating characteristics of S&OP at three Korean firms is presented. Implications of the study finding are also provided. It will also make companies that are considering the introduction of S&OP aware of the importance of S&OP, which will provide practical guidelines for the introduction of S&OP.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.4
• /
• pp.283-289
• /
• 2018

Launch Acceptability Region(LAR) means an area for successfully hitting the target. And LAR should be calculated in real time on aircraft so that LAR can be seen by pilot. LAR can be changed by the launch condition of the bomb, the impact condition of the target, and the atmospheric condition at the time of flight of the bomb. In this paper, we propose the calculation method of LAR using Artificial Neural Network(ANN). The learning data was generated by changing each condition from existing LAR model, and LAR model was derived through ANN learning. We confirmed the accuracy of the new LAR model by comparing the difference between the result data of existing LAR model and the new LAR model. And we confirmed the possibility of real time calculation of the LAR model on the aircraft by comparing the calculation time.

• KIISE Transactions on Computing Practices
• /
• v.23 no.12
• /
• pp.698-702
• /
• 2017

Since the introduction of Deep Neural Networks to the Natural Language Processing field, two major approaches have been considered for modeling text. One method involved learning embeddings, i.e. the distributed representations containing abstract semantics of words or sentences, with the textual context. The other strategy consisted of composing the embeddings trained by the above to get embeddings of longer texts. However, most studies of the composition methods just adopt word embeddings without consideration of the optimal embedding unit and the optimal method of composition. In this paper, we conducted experiments to analyze the optimal embedding unit and the optimal composition method for modeling longer texts, such as documents. In addition, we suggest a new discourse-based composition to overcome the limitation of the sequential composition method on composing sentence embeddings.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.2
• /
• pp.141-149
• /
• 2018

This paper presents a neural network controller design for complex damage to a blended wing Unmanned Aerial Vehicle(UAV): partial loss of main wing and vertical tail. Longitudinal/lateral axis instability and the change of flight dynamics is investigated via numerical simulation. Based on this, neural network based adaptive controller combined with two types of feedback linearization are designed in order to compensate for the complex damage. Performance of two kinds of dynamic inversion controllers is analyzed against complex damage. According to the structure of the dynamic inversion controller, the performance difference is confirmed in normal situation and under damaged situation. Numerical simulation verifies that the instability from the complex damage of the UAV can be stabilized via the proposed adaptive controller.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.11 no.2
• /
• pp.35-41
• /
• 1993

The height differences in Mean Sea Level is an important factor in geodetic leveling net, because MSL is the reference datum for height. Geodesists and Oceanographers agree on the height differences in MSL in the east-west direction, but they disagree almost always on the north-south slope, each suspecting systematic errors in the leveling methods of the others. A promising method for determining this slope is comparison of MSL at the tidal station connected by geodetic leveling. The slopes of the sea surface along the coast of Korean Peninsular is estimated from conventional local MSL at the tidal station and bench mark height of first order leveling net in Korea. As a reference level surface, MSL at Inchon is chosen. The results indicate that sea level rises along coast of Korean Peninsular from south to north about 5.5 cm/latitude. In the east-west direction, sea level along East Sea coast stands about 5 cm higher than that along Yellow Sea coast. These are not invariable but provisional phenomena. It may become certain provided that the exact MSL is estimated.

• Journal of The Korean Association of Information Education
• /
• v.21 no.2
• /
• pp.161-169
• /
• 2017

We often use spellcheckers in order to correct the syntactic errors in our documents. However, these computer programs are not enough for elementary school students, because their sentences are not smooth even after correcting the syntactic errors in many cases. In this paper, we introduce an automated method for evaluating the smoothness of two synonymous sentences. This method uses a recurrent neural network to solve the problem of long-term dependencies and exploits subwords to cope with the rare word problem. We trained the recurrent neural network language model based on a monolingual corpus of about two million English sentences. In our experiments, the trained model successfully selected the more smooth sentences for all of nine types of test set. We expect that our approach will help in elementary school writing after being implemented as an application for smart devices.