• 한국정밀공학회지
• /
• 제19권9호
• /
• pp.27-33
• /
• 2002

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3855-3867
• /
• 2022

Name separation (splitting full names into surnames and given names) is not a tedious task in a multiethnic country because the procedure for splitting surnames and given names is ethnicity-specific. Malaysia has multiple main ethnic groups; therefore, separating Malaysian full names into surnames and given names proves a challenge. In this study, we develop a two-phase framework for Malaysian name separation using deep learning. In the initial phase, we predict the ethnicity of full names. We propose a recurrent neural network with long short-term memory network-based model with character embeddings for prediction. Based on the predicted ethnicity, we use a rule-based algorithm for splitting full names into surnames and given names in the second phase. We evaluate the performance of the proposed model against various machine learning models and demonstrate that it outperforms them by an average of 9%. Moreover, transfer learning and fine-tuning of the proposed model with an additional dataset results in an improvement of up to 7% on average.

• 지질공학
• /
• 제33권4호
• /
• pp.639-655
• /
• 2023

최근 지하공간에 대한 수요가 많아지면서 대심도 굴착으로 흙막이 벽체가 활용되고 있다. 흙막이 벽체는 변위에 취약한 구조물로써 국토교통부에서 제시한 관리기준으로 계측관리를 수행하고 있으나 계측관리를 통한 대비는 후처리에 가깝다고 할 수 있다. 따라서 본 연구에서는 머신러닝을 이용한 그라운드 앵커가 설치된 흙막이 벽체의 수평변위 예측뿐만 아니라 머신러닝으로 계측데이터를 학습하는 과정에서 데이터 스케일링과 분할 방법에 따른 예측모델의 영향을 분석하였다. 이 연구의 분석결과에 따르면 사용자 지정분할방법이 적합하지 않은 경우도 있었으나 일정 조건하에서 데이터 학습 및 출력에 가장 우수한 성능을 나타냈다. 데이터 스케일링은 앵커의 인장력, 수압을 표준화하였을 때 오차 1 이내, R-Squared 값이 0.77로 우수한 성능을 나타냈으며 스케일링을 적용하지 않은 모델 대비 음의 변위를 예측하는 결과를 보였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권11호
• /
• pp.826-836
• /
• 2010

본 논문은 RBMT, SMT, PBMT를 활용한 직렬 연결 방식의 하이브리드 번역 시스템을 제안한다. 번역 시스템은 입력된 문장에 대하여 구문 분석을 진행한 후, 이 정보를 바탕으로 구문 변환과 개체명 인식을 한다. 이 결과값을 의사 문장으로 변형, 문장 분리 규칙이 적용 가능할 경우, 분리된 문장에 대하여 다중 디코딩을 수행하고, 후처리기에서 접합 규칙에 따라 번역문을 생성하였다. 실험을 통하여 어순 배치의 경우 distortion 모델에 의존하지 않고 구문 변환(rule-based syntactic transfer)규칙을 사용하는 것이 더욱 효과적인 것으로 나타났다.

• 한국기계가공학회지
• /
• 제18권6호
• /
• pp.19-25
• /
• 2019

We have developed a tool that uses finite element analysis (FEA) to rapidly evaluate a shaft-bearing system of machine tools. We extracted commercial data on suitable clamping units and defined the inner profile of the shaft to avoid needing direct user input to define the profile. We use a splitting algorithm to convert the shaft into beam elements with two diameters and length. To validate the tool, we used it to design and evaluate a shaft-bearing system and found that our tool automated the construction of an FE system model in a commercial FEA package as well as the static stiffness evaluation; both tasks were completed in seconds, demonstrating a significant reduction from the minutes normally required to complete these tasks manually.

• 한국공작기계학회논문집
• /
• 제16권2호
• /
• pp.37-43
• /
• 2007

In this paper, laser vision sensor is used to detect some defects any $co_{2}$ welded specimen in hardware. But, as the best expression of defects of welded specimen, the concept of segment splitting method and mean distance are introduced in software. The developed GUI software is used for deriding whether any welded specimen makes as proper shape or detects in real time. The criteria are based upon ISO 5817 as limits of imperfections in metallic fusion welds.

• 화약ㆍ발파
• /
• 제20권2호
• /
• pp.7-19
• /
• 2002

The cut is placed high up in the section, the 1st sloping holes below the cut, and divided all the holes located below the 1st sloping holes into a certain area with longitudinal section, to lower pollution made from tunnel blasting. With the sequential blasting machine, after I first blasted holes around the cut holes by a pre-splitting method, blasted the cut area and the 1st sloping holes. The 1st and 2nd sloping holes divided areas are initiated gradually to free face upwards made by the cut. Especially, I pre-splinted contour holes previous blast the before sloping holes from the contours. The ground vibration from the earth surface just over the advance face decreased about 42.0% compare with the down blasting method under the condition of equal charge weight per delay. I controlled the crack and over break of the mother rock by pre-splitting contour holes before blast the first sloping holes from the contours. The peak values of noise and air blast by blasting decreased about 10dB more than the down blasting method. the noise and air blast diminished gradually as a round. The throw distance of the fly rock was decreased about 55%.

• Advances in nano research
• /
• 제16권4호
• /
• pp.375-394
• /
• 2024

The extensive utilization of concrete has given rise to environmental concerns, specifically concerning the depletion of river sand. To address this issue, waste deposits can provide manufactured-sand (MS) as a substitute for river sand. The objective of this study is to explore the application of machine learning techniques to facilitate the production of manufactured-sand concrete (MSC) containing stone nano-powder through estimating the splitting tensile strength (STS) containing compressive strength of cement (CSC), tensile strength of cement (TSC), curing age (CA), maximum size of the crushed stone (Dmax), stone nano-powder content (SNC), fineness modulus of sand (FMS), water to cement ratio (W/C), sand ratio (SR), and slump (S). To achieve this goal, a total of 310 data points, encompassing nine influential factors affecting the mechanical properties of MSC, are collected through laboratory tests. Subsequently, the gathered dataset is divided into two subsets, one for training and the other for testing; comprising 90% (280 samples) and 10% (30 samples) of the total data, respectively. By employing the generated dataset, novel models were developed for evaluating the STS of MSC in relation to the nine input features. The analysis results revealed significant correlations between the CSC and the curing age CA with STS. Moreover, when delving into sensitivity analysis using an empirical model, it becomes apparent that parameters such as the FMS and the W/C exert minimal influence on the STS. We employed various loss functions to gauge the effectiveness and precision of our methodologies. Impressively, the outcomes of our devised models exhibited commendable accuracy and reliability, with all models displaying an R-squared value surpassing 0.75 and loss function values approaching insignificance. To further refine the estimation of STS for engineering endeavors, we also developed a user-friendly graphical interface for our machine learning models. These proposed models present a practical alternative to laborious, expensive, and complex laboratory techniques, thereby simplifying the production of mortar specimens.

• 한국공작기계학회논문집
• /
• 제16권1호
• /
• pp.9-18
• /
• 2007

There have been continuous efforts for automation of joint tracking system. This automation process is mainly used to do in root pass of gas metal arc welding in the field of heavy industry and shipbuilding etc. For automation, it is important using of vision sensor. Welding robot with vision sensor is used for weld seam tracking on welding fabrication. Recently, it is used to on post-weld inspection for weld quality evaluation. For real time seam tracking, it is very important role in vision process technique. Vision process is included in filtering and thinning, segmentation processing, feature extraction and recognition. In this paper, it has shown performance comparison results of seam tracking for real time root pass on gas metal arc welding. It can be concluded better segment splitting method than iterative averaging technique in the performance results of seam tracking.

• 한국정밀공학회지
• /
• 제16권11호
• /
• pp.213-223
• /
• 1999

In this paper, input-output transmission characteristics of the Eclipse, which is a parallel machine tool capable of 5 face rapid machining, are investigated. By splitting the weighted Jacobian matrix into two parts, the force and moment transmission characteristics together with the velocity and angular velocity transmission characteristics are analyzed. A new manipulability measure, which combines the volume of the manipulability ellipsoid and the condition number of the splitted Jcobian matrix, is proposed. Two link parameters, the ratio of upper and lower platforms' radii and the length of a supporting link of the Eclipse, are designed by applying the new manipulability measure derived. Computer simulations are provided.