• 한국지능시스템학회논문지
• /
• 제21권5호
• /
• pp.609-617
• /
• 2011

본 논문에서는 트위터로부터 자동 생성한 사용자 프로파일을 이용하는 개인 맞춤형 음식 추천 시스템을 제안한다. 사용자 개인의 트위터 문장에서 명사를 추출하고, 감정단어와의 공기 여부에 따라 감정점수를 계산한 후. 사용자 프로파일을 생성한다. 각 음식에 관한 정보는 웹에서 검색한 웹 페이지를 분석, 가공하여 음식별 대표 명사 목록을 만들어 사용한다. 이렇게 구축된 사용자 프로파일과 각 음식별 특징 정보 간 유사도를 계산하여 사용자에 맞는 음식을 추천 해준다. 제안하는 방법은 추천 시스템을 처음 사용하는 사용자라 할지라도 사용자 프로파일이 자동으로 구축되어 추천에 사용되기 때문에 항상 추천 결과를 얻을 수 있는 장점이 있다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.844-847
• /
• 2005

A seamless analysis of complex geometry is one of greatly interesting topic. However, there are still gaps between the industrial applications and fundamental academic studies owing to time consuming modeling process. To resolve this problem, an auto mesh generation program based on grid-based approach has been developed for IT-product in the present study. At first, base mesh and skin mesh are generated using the information of entities which extracted from IGES file. Secondly the provisional core mesh with rugged boundary geometry is constructed by superimposing the skin mesh as well as the base mesh generated from the CAD model. Finally, the positions of boundary nodes are adjusted to make a qualified mesh by adapting node modification and smoothing techniques. Also, for the sake of verification of mesh quality, the hexahedral auto mesh constructed by the program is compared with the corresponding tetrahedral free mesh and hexahedral mapped mesh through static finite element analyses. Thereby, it is anticipated that the grid-based approach can be used as a promising pre-processor for integrity evaluation of various IT-products.

• Journal of Biosystems Engineering
• /
• 제38권1호
• /
• pp.1-8
• /
• 2013

Purpose: Path planning and tracking algorithms applicable to various agricultural operations, such as tillage, planting, and spraying, are needed to generate steering angles for auto-guidance tractors to track a point ahead on the path. An optimal coverage path algorithm can enable a vehicle to effectively travel across a field by following a sequence of parallel paths with fixed spacing. This study proposes a path generation and tracking algorithm for an auto-guided Korean tractor with a tillage implement that generates a path with C-type turns and follows the generated path in a paddy field. A mathematical model was developed to generate a waypoint path for a tractor in a field. This waypoint path generation model was based on minimum tractor turning radius, waypoint intervals and LBOs (Limit of Boundary Offsets). At each location, the steering angle was calculated by comparing the waypoint angle and heading angle of the tractor. A path following program was developed with Labview-CVI to automatically read the waypoints and generate steering angles for the tractor to proceed to the next waypoint. A feasibility test of the developed program for real-time path tracking was performed with a mobile platform traveling on flat ground. The test results showed that the developed algorithm generated the desired path and steering angles with acceptable accuracy.

• 전기학회논문지
• /
• 제61권7호
• /
• pp.937-943
• /
• 2012

Most of faults occurred in transmission lines are single-phase to ground faults and transient faults. Single-phase auto reclosing is an appropriate scheme to maintain the system stability and restore the system effectively when those faults are occurred. In single-phase auto reclosing scheme, the secondary arc is generated after faulted phase is tripped to eliminate the fault and it is sustained by the capacitive and inductive coupling to the healthy phases. It is important to reclose the faulted phase after fully extinction of secondary arc because of the damage applied to system. Therefore, it is necessary to research on the detection of secondary arc extinction to ensure high success rate of reclosing. In this step, firstly, the accurate modelling of secondary arc should be performed. In this paper, the modelling of secondary arc is performed by using EMTP-RV and the simulation results show that the implemented model is correct and effective.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• 한국산업융합학회 논문집
• /
• 제16권2호
• /
• pp.41-46
• /
• 2013

On the purpose of helping the inhabitants living in farming, fishing villages, and islands for more safe and hygienic water from simple waterworks, experimental investigations were performed concerning the development of a water purifier with silver nanomaterial packed, having a function of the auto-disinfection. The results show as follows through such filteration and auto-disinfection processes. It is possible to get hygienic and safe water, for example, more than 95% of general bacteria, total coliforms, and fecal coliforms were removed. It is also possible to get good-quality water, for 49.4% of spent potassium permanganate and 85% and 63% of turbidity and conductivity were removed respectively. It is a very effective equipment, for 100% cost reduction of used chemicals was achieved by no-chemical disinfection process and THM was not generated.

• 대한조선학회논문집
• /
• 제35권4호
• /
• pp.98-108
• /
• 1998

중앙 단면도 등의 선박의 초기 구조설계는 여러 가지 이유로 2차원으로 설계되어 다른 설계부서에 도면으로 전달되고 있다. 본 연구에서는 기능이 서로 다른 여러 가지 컴퓨터 시스템사이의 데이터 교환을 위한 예제로, AutoCAD로 작성된 2차원의 초기 구조 설계 데이터를 구조해석(FEM) 시스템이나 상세설계 시스템(AutoDef)등의 다른 시스템에서 사용할 수 있는 데이터를 생성해 보았다. 이를 위해 STEP 제품모델의 방법에 따라 데이터가 정의 되었으며 2D 형상이나 3D 와이어프레임, 솔리드 모델등 다양한 형상을 다룰 수 있는 복합다양체 모델링 형상 도구인 ACIS가 사용되었다.

• 한국빅데이터학회지
• /
• 제8권2호
• /
• pp.83-95
• /
• 2023

스마트 플랜트 발전에 있어서 빅데이터 분석과 인공지능은 중요한 역할을 한다. 본 연구에서는 플랜트 데이터를 위한 빅데이터 플랫폼과 인공지능 기반 플랜트 유지 관리를 위한 'AutoML 플랫폼'을 개발하였다. 빅데이터 플랫폼은 하둡, 스파크, 카프카를 활용하여 플랜트에서 발생하는 대용량의 데이터를 수집, 처리, 적재하는 플랫폼이다. AutoML 플랫폼은 설비의 예지보전 및 공정 최적화를 위한 예측 모델을 구축하는 머신러닝 자동화 시스템이다. 위 플랫폼은 기존 플랜트 운영 정보 시스템과의 호환성을 고려하여 데이터 파이프라인을 구성하고, 웹 기반 GUI를 통해 작업자의 접근성과 편의성을 향상하였으며, 데이터 처리와 학습 알고리즘에 사용자 정의 모듈을 탑재하는 기능을 통해 유연성을 증대시켰다. 본 논문은 국내 정유회사의 특정 공정을 대상으로 플랫폼을 실제 운영해보았고, 이를 통해 스마트 플랜트를 위한 효과적인 데이터 활용 플랫폼 사례를 제시한다.

• Nuclear Engineering and Technology
• /
• 제54권12호
• /
• pp.4514-4521
• /
• 2022

In this study, the effects of heat and radiation on the degradation behaviour of fluoroelastomer under simulated normal operation and a severe accident environment were investigated using sequential testing of gamma irradiation and thermal degradation. Tensile properties and Shore A hardness were measured, and thermogravimetric analysis was used to evaluate the degradation behaviour of fluoroelastomer. Fourier transform infrared spectroscopy and X-ray photoelectron spectroscopy were used to characterize the structural changes of the fluoroelastomer. Heat and radiation generated in nuclear power plant break and deform the chemical bonds, and fluoroelastomer exposed to these environments have decreased C-H and functional groups that contain oxygen and double bonds such as C-O, C=O and C=C were generated. These functional groups were formed by auto oxidation by reacting free radicals generated from the cleaved bond with oxygen in the atmosphere. In this auto oxidation reaction, crosslinks were generated where bonded to each other, and the mobility of molecules was decreased, and as a result, the fluoroelastomer was hardened. This hardening behaviour occurred more significantly in the severe accident environment than in the normal operation condition, and it was found that thermal stability decreased with the generation of unstable structures by crosslinking.

• 소성∙가공
• /
• 제4권1호
• /
• pp.28-38
• /
• 1995

An integrated process planning system can determine desirable operation sequences even if they have little experience in the design of multistage cold forging process. This system is composed of seven major modules such as input module, pre-design module, formability check module, forming sequence design module, forming analysis module, FEM verification module, and output module which are used independently or in all. The forming sequence for the part can be determined by means of primitive geometries such as cylinder, cone, convex, and concave. By utilizing this geometrical characteristics(diameter, height, and radius), the part geometry is expressed by a list of the primitive geometries. Accordingly, the forming sequence design is formulated as the search problem which starts with a billet geometry and finishes with a given product one. Using the developed system, the sequence drawing with all dimensions, which includes the dimensional tolerances and the proper sequence of operations for parts, is generated under the environment of AutoCAD. Several forming sequences generated by the planning system can be checked by the forming analysis module. The acceptable forming sequences can be verified further, using FE simulation.