• Journal of Advanced Marine Engineering and Technology
• /
• 제39권3호
• /
• pp.274-279
• /
• 2015

본 연구는 스탠포드 감성 트리 말뭉치를 이용하여 감성 분류 시스템을 구현하였으며, 분류기로는 지지벡터기계(Support Vector Machines)를 이용하여 긍정, 중립, 부정 등의 3가지 감성으로 분류하였다. 먼저 감성 문장의 품사를 부착한 후 의존구조를 부착하였다. 트리 말뭉치의 모든 노드와 감성 태그를 자동으로 추출하여 문장 레벨의 지지벡터 분류 시스템과 노드 레벨의 지지벡터 분류 시스템을 각각 구현하였다. 자질로는 어휘, 품사, 감성어휘, 의존관계, 형제관계 등 다양한 자질의 조합을 이용하였다. 평가 말뭉치를 이용하여 3클래스로 분류한 결과, 노드 단위에서는 74.2%, 문장 단위에서는 67.0%의 정확도를 얻었으나 2클래스 분류에서는 현재 알려진 최고의 시스템에 어느 정도 필적하는 성능을 거두었다.

• 수산해양기술연구
• /
• 제49권3호
• /
• pp.208-217
• /
• 2013

Decoys for automatic jigging machines, the body part of a squid hook, have been developed in small and existing sizes in consideration of squid food, color blindness, and retinomotor responses and in utilization of pearl pigment, PP of high transparency, and combined mixture. In comparison of the developed silver-white decoy and existing decoys, the optical characteristics were examined, and the fishing performance of small size silver-white squid hooks was assessed in application of 4 fishing boats with the squid automatic jigging machine and metal halide fishing lamp in July, 2012. The luminances of the three squid hook colors-green, dark green and silver-white-increased as the intensity of illumination increased. Among these, the increase of silver-white was particularly distinguished. As to the average contrast of squid hooks, that of silver-white was 10.33, which was the highest, and then green 1.86 and dark green -0.10 in the order. As to the fishing performance of the silver-white hook, that of the 202 Geumyeong-ho and 101Yongjin-ho which caught squids were similar to that of the existing green hook and was relatively low in the case of the Dongbu-ho. However, that of the Haengbok-ho which caught relatively small squids whose average length was 19.9cm and installed silver-white hook in all automatic jigging machines was significantly excellent. In order to enhance the fishing performance of small size silver-white hooks, therefore, it would be effective to install in every automatic jigging machines of fishing boat and to start fishing before July by which small squids are caught.

• Journal of Biosystems Engineering
• /
• 제40권3호
• /
• pp.178-185
• /
• 2015

Purpose: This research suggests a method of establishing criteria for working area and operating cost for a long-term lease of agricultural machinery. Methods: Eight crops were selected-three food crops and five open-field vegetables-and agricultural machines used for sowing, transplanting, and cultivation in dry-field farming were analyzed. Results: The break-even acreage for agricultural machinery under a long-term lease was found to differ by agricultural machine, ranging from 1.0 to 5.8 ha. In terms of arable land area, the break-even acreages for harvesting machinery and transplanters were 15.6 to 26.1 ha and 6.1 to 8.6 ha, respectively. The working area lessees should secure was divided into two cases: (1) 2.0 to 11.6 ha when leasing individual agricultural machines (sowing and transplanting) for a long-term period, and (2) more than 10 ha when farmers who cultivate beans, potatoes, garlic, onions, and so on lease sowing and transplanting machines as a set. When agricultural machinery was leased for a long term, the operating cost and working time were reduced by 27.6 to 74.4% and 2.5 to 21.6%, respectively, indicating considerable effect. Conclusions: A long-term lease project needs to be promoted to overcome the limitation of short-term leases of agricultural machinery. The local government should lead this project and facilitate the mechanization of dry-field farming. The department in charge of agricultural machinery lease projects needs to set the working area to cover the rate and maintenance cost for farmers who lease agricultural machinery for the long term.

• 한국문헌정보학회지
• /
• 제50권2호
• /
• pp.309-336
• /
• 2016

본 논문에서는 지지벡터기계(Support Vector Machines, SVM) 기반의 기계 학습 모듈을 활용하여 특정 문장 내에서의 두 개체 간의 관계를 자동으로 식별하고 분류하는 바이오 분야 관계 추출 시스템을 제안한다. 제안된 시스템의 특징은 개체를 포함하고 있는 문장 내에서 풍부한 언어 자질을 추출하여 학습에 활용함으로써 그 성능을 극대화할 수 있는 다양한 기능들을 포함하고 있다는 점이다. 제안된 시스템의 성능 측정을 위해서 전 세계적으로 많이 활용되고 있는 바이오 분야 관계 추출 표준 컬렉션 3가지를 활용하여 심층적인 실험을 수행한 결과 모든 컬렉션에서 높은 성능을 획득하여 그 우수성을 입증하였다. 결론적으로, 본 논문에서 수행한 바이오 분야 관계 추출에 대한 광범위하고 심층적인 실험 연구가 향후 기계학습 기반의 바이오 분야 텍스트 분석 연구에 많은 시사점을 제공할 것으로 보인다.

• 한국염색가공학회지
• /
• 제8권5호
• /
• pp.7-16
• /
• 1996

The air-flow dyeing machine is a new type of dyeing machine. Which is an energy saving type to be able to dye the fabrics with the lowest liquor ratio and in shorter time. This machine is operated with an aerodynamic system rather than a hyd raulic system for traditional jet or overflow dyeing. An air-flow dyeing machine(Green-flow) by the use of aerodynamic technology was developed and compared with the Luft-roto machine made by Thies Company, Germany, in this study. Three samples were dyed with both machines under the same dyeing conditions and color fastness, dyeing levelness, drapability, and mechanical properties of these samples were compared. The results were as follows; Both machines have almost the same dyeability. The dyeability was good at liquor ratio of 1: 3.5 and the speed of 450yds/min. The order for drapability was Crepe de Chine > Cool Peach > Charmeuse. Except for the color fastness of sublimation being below class 4, most color fastness of samples dyed with Green-flow m/c were above class 4. The maximum speed was 510yds/min. for Crepe de Chine and the standard deviation of K/S value was lower for Charmeuse and Cool Peach when employed on the "Green-flow" machine and lower for Crepe de Chine when employed on the Luft-roto machine. Comparing with dyeing of the Green-flow machine and that of the Luft-roto machine, the RT of the Charmeuse was found to be higher with the Green-flow machine and thus the sample had an improved wrinkle recovery. LT and WT of Cool Peach were higher, and shear properties(G, 2HG, 2HGS) of Crepe de Chine were higher, both turning out as suitable for clothing. clothing.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 공동추계학술대회
• /
• pp.241-250
• /
• 2005

New product development (NPD) is defined as the transformation of a market opportunity and a set of assumptions about product technology into a product available for sale. Managers charged with project selection decisions in the NPD process, such as go/no-go choices and specific resource allocation decisions, are faced with a complicated problem. Therefore, the ability to develop new successful products has identifies as a major determinant in sustaining a firm's competitive advantage. The purpose of this study is to develop a new evaluation model for NPD project selection in the high -tech industry using support vector machines (SYM). The evaluation model is developed through two phases. In the first phase, binary (go/no-go) classification prediction model, i.e. SVM for high-tech NPD project selection is developed. In the second phase. using the predicted output value of SVM, feasibility grade is calculated for the final NPD project decision making. In this study, the feasibility grades are also divided as three level grades. We assume that the frequency of NPD project cases is symmetrically determined according to the feasibility grades and misclassification errors are partially minimized by the multiple grades. However, the horizon of grade level can be changed by firms' NPD strategy. Our proposed feasibility grade method is more reasonable in NPD decision problems by considering particularly risk factor of NPD in viewpoints of future NPD success probability. In our empirical study using Korean NPD cases, the SVM significantly outperformed ANN and logistic regression as benchmark models in hit ratio. And the feasibility grades generated from the predicted output value of SVM showed that they can offer a useful guideline for NPD project selection.

• 한국전자통신학회논문지
• /
• 제16권3호
• /
• pp.471-476
• /
• 2021

분말 야금 기술에 의한 복합 연자성 재료는 전기기기에 일반적으로 사용되는 종래의 전기강판보다 많은 장점을 가지고 있으며, 그 관련 기술은 최근에 상당한 발전을 거듭하고 있다. 복합 연자성 재료는 일반적으로 분말의 형태로 인해 자기적 등방성 가지므로 3차원 자속 및 복잡한 구조의 전기기기 구성에 적합하다. 하지만 SMC와 같이 등방성 자기 특성을 가지는 재료는 복잡한 벡터 히스테리시스를 가지므로 정확한 손실 특성을 예측하는 것이 매우 어렵다. 따라서 본 논문에서는 전기강판 및 SMC의 링 타입 시편을 제작하고 시편 크기에 따라 자기적 특성을 측정한 후, 측정된 자기적 정보를 이용하여 800Hz 이상에서 구동하는 고속 영구자석 전동기의 전자계 해석을 수행하였다. 또한, 해당 모델의 시작품을 제작하고 효율 측정 및 비교를 통해 본 논문의 신뢰성을 입증하였다.

• 한국CDE학회논문집
• /
• 제2권4호
• /
• pp.244-252
• /
• 1997

In this paper, arm-type lifting mechanism which is attached under the frame of truck is analyzed. The three types of motions which are divided into rotation, pure lifting and automatic tilting motions are analyzed kinematically. These motions are visualized by computer graphics using Visual Basic. This program will be used for designer to demonstrate the arm-type lifting mechanism before making real machines. Also this program can change design parameter interactively.

• 한국생산제조학회지
• /
• 제5권3호
• /
• pp.66-72
• /
• 1996

The applicability of a new method, termed the whirling motion concept, for the improvement of the surface finish in milling three-dimensional sculptured surfaces has been investigated. A method for implementing this concept o conventional NC machines that utilize a suitably configured attachment has been proposed. The tool path equation for the ball-end milling process, based on the surface-shaping system, has been obtained. Both results of the computer simulation and the experiment verified the proposed approach.

• 산업경영시스템학회지
• /
• 제17권31호
• /
• pp.91-98
• /
• 1994

Most of machines are physically or chemically degenerated by continuous usage. There- fore, a preventive maintenance is necessary. Producing defects are caused by process shift in mean and variance which are due to three types of degeneration. We develope the function of process variance from the experimental data and determine the optimal tool wear limit and the initial setting position of tool by considering the percent defective cost and the preventive maintenance cost.