• 한국산업정보학회논문지
• /
• 제18권6호
• /
• pp.1-8
• /
• 2013

스마트폰의 사용이 일상화되면서, 그 휴대성에 의해서 소셜 네트워크 서비스(SNS, Social Network Service) 어플리케이션의 사용이 매우 활발하다. 또한 위치 이동에 따른 정보의 활용이 가능한 위치 기반 서비스(Location based Service)의 수요가 확대되면서 SNS와 결합된 형태의 서비스가 스마트폰의 사용성을 향상시키고 있다. 본 논문에서는 사용자의 위치를 실시간으로 추적하여 이동하는 위치에 따라 작성되어진 SNS를 위한 정보를 자동으로 알려주는 LBSNS(Location Based Social Networking Service)가 가능한 어플리케이션을 구현한다.

• 산업공학
• /
• 제13권4호
• /
• pp.599-607
• /
• 2000

In recent days, Internet advertising effects are expanded by the steep increase of the Internet users and the extension of the advertising market will be accelerated through Internet. This paper indicates the importance of Internet advertising and suggests the solution of a network advertising service. The system is divided into an Advertise Server, an Advertiser and a Web Publisher. This study proposes both the collection and the analysis of traffic data in real time. Also, the banner advertising frames not for sale purpose are levelled for the impression using the solution for the banner exchange engine. In addition, with developing the advertising service system by using Active Server Pages, the newest language of server side script will be able to lead the additional supplement of more various profitable functions when it is considered the rapid increment of Active Server Pages.

• 한국멀티미디어학회논문지
• /
• 제25권7호
• /
• pp.903-911
• /
• 2022

A shrimp quality detection model using YOLOv4 deep learning algorithm is designed, which is superior in terms of network architecture, data processing and feature extraction. The shrimp images were taken and data expanded on their own, the LableImage platform was used for data annotation, and the network model was trained under the Darknet framework. Through comparison, the final performance of the model was all higher than other common target detection models, and its detection accuracy reached 93.7% with an average detection time of 47 ms, indicating that the method can effectively detect the quality of shrimp in the production process.

• 대한기계학회논문집
• /
• 제16권7호
• /
• pp.1322-1331
• /
• 1992

본 연구에서는 Fig.3과 같은 다층 퍼셉트론을 사용하기로 한다. 그리고 위 에서 언급한 세가지점에서 다층퍼셉트론을 다시 살펴보아 해결하고자 하는 문제에 맞 도록 다층퍼셉트론을 개선시켜 보기로 한다. 따라서 본 연구의 목적은 제한조건을 갖는 문제를 풀기위한 새로운 형태의 다층퍼셉트론 설계 및 이에 적합한 학습규칙을 적용하여 보다 간단한 구조와 빠른 학습시간을 갖는 신경망을 구성하는데 있다.

• 대한전기학회논문지
• /
• 제40권2호
• /
• pp.224-233
• /
• 1991

The multilayer expanson of single layer NN (Neural Network) was needed to solve the linear seperability problem as shown by the classic example using the XOR function. The EBP (Error Back Propagation ) learning rule is often used in multilayer Neural Networks, but it is not without its faults: 1)D.Rimmelhart expanded the Delta Rule but there is a problem in obtaining Ca from the linear combination of the Weight matrix N between the hidden layer and the output layer and H, wich is the result of another linear combination between the input pattern and the Weight matrix M between the input layer and the hidden layer. 2) Even if using the difference between Ca and Da to adjust the values of the Weight matrix N between the hidden layer and the output layer may be valid is correct, but using the same value to adjust the Weight matrixd M between the input layer and the hidden layer is wrong. Recognitron III was proposed to solve these faults. According to simulation results, since Recognitron III does not learn the three layer NN itself, but divides it into several single layer NNs and learns these with learning patterns, the learning time is 32.5 to 72.2 time faster than EBP NN one. The number of patterns learned in a EBP NN with n input and output cells and n+1 hidden cells are 2**n, but n in Recognitron III of the same size. [5] In the case of pattern generalization, however, EBP NN is less than Recognitron III.

• Animal cells and systems
• /
• 제14권1호
• /
• pp.45-51
• /
• 2010

Genetic variation was surveyed at the mitochondrial control region (766bp) to test for the presence of genetic stock structure in the small yellow croaker, Larimichthys polyactis from the Yellow and East China Seas. Individuals of the small yellow croaker could not be distinguished on the basis of its location, as demonstrated using the neighbor-joining (NJ) method, unweighted pair-group method, arithmetic average (UPGMA) and the minimum spanning network (MSN). Analysis of molecular variance revealed no significant differences among collections of the small yellow croaker taken from the four locations (two locations each in Korea and China). Neutrality tests and a mismatch distribution analysis indicated that this species has recently expanded. Our findings suggest either that the small yellow croaker has a high migration capability that enables it to overcome the effects of genetic drift, or that this species expanded relatively recently and has not yet had sufficient time to differentiate.

• 한국정보통신학회논문지
• /
• 제4권3호
• /
• pp.619-625
• /
• 2000

많은 제어기법들이 이산시간영역제어계의 제어성능을 개선시키기 위해서 제안되고 있다. 위치제어계에서 일반적으로 제어기의 출력이 제어대상의 입력으로 사용된다. 그러나 불필요한 잡음이 제어기의 출력에 포함된다. 그러므로 이러한 잡음을 제거하기 위해서 전치보상기를 사용할 필요가 있다. 본 논문에서 전치보상기를 갖는 확대 I-PD 제어계를 구성하였고 이 전치보상기와 I-PD 제어기를 신경망으로 설계하였다. 그리고 전치보상기와 I-PD제어기의 계수들이 계의 응답특성들이 어떤 조건 하에서 변할 때 계의 희망하는 응답이 되도록 자동적으로 조정되도록 하였다.

• International Journal of Advanced Culture Technology
• /
• 제8권3호
• /
• pp.325-333
• /
• 2020

In the past, eating outside was usually the purpose of eating. However, it has recently expanded into a restaurant culture market. In particular, a dessert culture is being established where people can talk and enjoy. Each consumer has a different tendency to buy chocolate such as health, taste, and atmosphere. Therefore, it is time to recommend chocolate according to consumers' tendency to eat out. In this paper, we propose a chocolate recommendation application based on the tendency to eat out using data on social networks. To collect keyword-based chocolate information, Textom is used as a text mining big data analysis solution.Text mining analysis and related topics are extracted and modeled. Because to shorten the time to recommend chocolate to users. In addition, research on the propensity of eating out is based on prior research. Finally, it implements hybrid app base.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 춘계학술발표회논문집
• /
• pp.485-490
• /
• 2004

Recently, distribution transfer velocity was extremely lowered by high supply rate of vehicle and low road rate. Therefore expansions of transfer network these were subway, road and railway to recover competitive power as a reform measure of physical distribution traffic were become preference previous subject. For reason of that, an expansion of transfer network is meeting competitive power as selected an elevated road in the ground road network that condition of location calm and get out of the existing urban than the underground road to connect oversensitive a large city and expanded small and medium satellite town. In the meantime, while elevated structures construct, they go through the civilian residential section, agriculture land, etc. The consequence is that it raises a vibration, noise, dust, an infringement of the right to a view and an infringement of the right to a sunshine. In this study, we analyzed Quantitatively sunshine quantity with building 3D simulation model of civil structure. Therefore, we present as planning data to reduce a civilian appeal for dispute of the right to sunshine and an economic and time loss between the government and construction company In addition to that, for the standard of the standard plan of usable sunshine quantity program in the practical business, the building of convenient user interface will be the project to be done.

• 대한교통학회지
• /
• 제27권6호
• /
• pp.129-137
• /
• 2009

첨단교통체계의 기술발전과 교통 분석의 수준이 상세해짐에 따라 동적 교통 분석에 대한 필요성이 증가하고 있다. 기존의 정적인 분석이 하루 평균 개념의 통행특성과 네트워크 상태를 묘사한 반면, 동적 분석에서는 시간흐름에 따른 네트워크의 상태를 분석한다. 본 논문에서는 교통시스템 동적 분석의 필요성을 인식하여, 고속도로망을 대상으로 FTMS 자료를 활용한 분석 방법론을 개발하였다. 개별 차량의 실제 통행기록 자료인 TCS 자료를 이용하여 전국 고속도로망을 대상으로 동적 기종점 통행량을 구축하였으며, 시뮬레이션 연산시간 문제 해결을 위해 분석범위를 설정한 Subarea 분석을 활용하였다. 이를 위해 전국 고속도로망을 대상으로 구축된 시간대별 기종점 통행량을 Subarea 기종점 통행량으로 전환하기 위한 방법론을 개발하였다. 구축된 모형의 적용을 위해 시나리오 분석을 실시하였으며, 이를 통해 각각의 시나리오에 대하여 기존의 단편적인 효과분석과 달리 하루 중 시간대별 교통여건에 따른 네트워크 상태분석을 수행하였다. 본 연구는 동적 교통 분석의 초기 시도라는 점과 실제 기종점 자료인 FTMS 자료를 활용한 분석이라는 점에서 의미를 가지며, 현재 교통 분석의 큰 흐름인 동적 교통 분석의 필요성을 부각시키고자 한다. 향후 고속도로뿐만이 아닌 기타 도로를 포함한 모형 구축이 필요하며, Hybrid 모형 및 프로그램 개발을 통해 궁극적인 목표인 실시간동적 분석 모형 개발을 위한 연산시간 문제 해결이 필요할 것이다.