• 음성과학
• /
• 제10권1호
• /
• pp.71-84
• /
• 2003

In the acoustic modeling for large vocabulary speech recognition, a sparse data problem caused by a huge number of context-dependent (CD) models usually leads the estimated models to being unreliable. In this paper, we develop a new clustering method based on the C45 decision-tree learning algorithm that effectively encapsulates the CD modeling. The proposed scheme essentially constructs a supervised decision rule and applies over the pre-clustered triphones using the C45 algorithm, which is known to effectively search through the attributes of the training instances and extract the attribute that best separates the given examples. In particular, the data driven method is used as a clustering algorithm while its result is used as the learning target of the C45 algorithm. This scheme has been shown to be effective particularly over the database of low unknown-context ratio in terms of recognition performance. For speaker-independent, task-independent continuous speech recognition task, the proposed method reduced the percent accuracy WER by 3.93% compared to the existing rule-based methods.

• Nuclear Engineering and Technology
• /
• 제30권6호
• /
• pp.496-506
• /
• 1998

This paper deals with the computational modeling of buoyancy-driven turbulent heat transfer involving spatially uniform volumetric heat sources in semicircular geometry. The Launder & Sharma low-Reynolds number k-$\varepsilon$ turbulence model without any modifications and the SIMPLER computational algorithm were used for the numerical modeling, which was incorporated into the new computer code CORE-TNC. This computer code was subsequently benchmarked with the Mini-ACOPO experimental data in the modified Rayleigh number range of 2$\times$10$^{13}$ $\times$10$^{14}$ . The general trends of the velocity and temperature fields were well predicted by the model used, and the calculated isotherm patterns were found to be very similiar to those observed in previous experimental investigations. The deviation between the Mini-ACOPO experimental data and the corresponding numerical results obtained with CORE-TNC for the average Nusselt number was less than 30% using fine grid in the near-wall region and the three-point difference formula for the wall temperature gradient. With isothermal pool boundaries, heat was convected predominantly to the upper and adjacent lateral surfaces, and the bottom surface received smaller heat fluxes.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.294-298
• /
• 2015

In the United States, the completion of Construction Work Zone (CWZ) impact assessments for all federally-funded highway infrastructure improvement projects is mandated, yet it is regarded as a daunting task for state transportation agencies, due to a lack of standardized analytical methods for developing sounder Transportation Management Plans (TMPs). To circumvent these issues, this study aims to create a spatiotemporal modeling framework, dubbed "SWAT" (Spatiotemporal Work zone Assessment for TMPs). This study drew a total of 43,795 traffic sensor reading data collected from heavily trafficked highways in U.S. metropolitan areas. A multilevel-cluster-driven analysis characterized traffic patterns, while being verified using a measurement system analysis. An artificial neural networks model was created to predict potential 24/7 traffic demand automatically, and its predictive power was statistically validated. It is proposed that the predicted traffic patterns will be then incorporated into a what-if scenario analysis that evaluates the impact of numerous alternative construction plans. This study will yield a breakthrough in automating CWZ impact assessments with the first view of a systematic estimation method.

• Journal of Multimedia Information System
• /
• 제9권2호
• /
• pp.171-176
• /
• 2022

Today, it is imperative to educate students on how to best prepare themselves for the new data driven era of the future. Undergraduate education plays an important role in providing students with more Data Science opportunities and expanding the supply of Data Science talent. This paper surveys and analyzes the curricula of Data Science-related bachelor's degree programs in the United States. The 'required' and 'elective' courses in a curriculum for obtaining a B.S. degree were evaluated by course weight to indicate its necessity. As a result, it was possible to find out which courses were important in Data Science programs and which areas were emphasized for B.S. degrees in Data Science. We found that courses belong to the Data Science area, such as data management, data visualization, and data modeling, were more required for Data Science B.S. degrees in the United States.

• Journal of Computational Design and Engineering
• /
• 제1권4호
• /
• pp.233-242
• /
• 2014

A magnetically levitated vehicle (Maglev) system is under commercialization as a new transportation system in Korea. The Maglev is operated by an unmanned automatic control system. Therefore, the plan of train operation should be carefully established and validated in advance. In general, when making a train operation plan, statistically predicted traffic data is used. However, a traffic wave often occurs in real train service, and demand-driven simulation technology is required to review a train operation plan and service quality considering traffic waves. We propose a method and model to simulate Maglev operation considering continuous demand changes. For this purpose, we employed a discrete event model that is suitable for modeling the behavior of railway passenger transportation. We modeled the system hierarchically using discrete event system specification (DEVS) formalism. In addition, through implementation and an experiment using the DEVSim++ simulation environment, we tested the feasibility of the proposed model. Our experimental results also verified that our demand-driven simulation technology can be used for a priori review of train operation plans and strategies.

• Smart Structures and Systems
• /
• 제30권1호
• /
• pp.35-47
• /
• 2022

Data-driven engineering is crucial for information delivery between design, fabrication, assembly, and maintenance of prefabricated structures. Design for manufacturing and assembly (DfMA) is a critical methodology for prefabricated bridge structures. In this study, a novel concept of digital engineering model that combined existing knowledge of DfMA with object-oriented parametric modeling technologies was developed. Three-dimensional (3D) geometry models and their data models for each phase of a construction project were defined for information delivery. Digital design models were used for conceptual design, including aesthetic consideration and possible variation during fabrication and assembly. The seismic performance of a bridge pier was evaluated by linking the design parameters to the calculated moment-curvature curves. Control parameters were selected to consider the tolerance control and revision of the digital models. Digitalized fabrication of the prefabricated members was realized using the digital fabrication model with G-code for a concrete printer or a robot. The fabrication error was evaluated and the design digital models were updated. The revised fabrication models were used in the preassembly simulation to guarantee constructability. For the maintenance of the bridge, the as-built information was defined for the prefabricated bridge piers. The results of this process revealed that data-driven information delivery is crucial for lifecycle management of prefabricated bridge piers.

• Environmental Engineering Research
• /
• 제14권4호
• /
• pp.200-210
• /
• 2009

The modern era of water quality modeling in the United States began in the 1960s. Pushed by advances in computer technology as well as environmental sciences, water quality modeling evolved through five broad periods: (1) initial model development with mainframe computers (1960s - mid 1970s), (2) model refinement and generalization with minicomputers (mid 1970s - mid 1980s), (3) model standardization and support with microcomputers (mid 1980s - mid 1990s), (4) better model access and performance with faster desktop computers running Windows and local area networks linked to the Internet (mid 1990s - early 2000s), and (5) model integration and widespread use of the Internet (early 2000s - present). Improved computer technology continues to drive improvements in water quality models, including more detailed environmental analysis (spatially and temporally), better user interfaces and GIS software, more accessibility to environmental data from on-line repositories, and more robust modeling frameworks linking hydrodynamics, water quality, watershed and atmospheric models. Driven by regulatory needs and advancing technology, water quality modeling will continue to improve to better address more complicated water bodies and pollutant types, and more complicated management questions. This manuscript describes historical trends in water quality model development in the United States, reviews current efforts, and projects promising future directions.

• 서비스연구
• /
• 제14권3호
• /
• pp.188-205
• /
• 2024

푸드트럭 비즈니스는 이동식 차량을 이용하여 다양한 음식을 판매하는 소규모 외식업 형태로, 최근 도시 중심지나 행사장에서 큰 인기를 끌고 있다. 그러나 경쟁이 치열해짐에 따라 고객 만족도를 높이고, 재방문을 유도하기 위한 서비스 품질 관리의 중요성이 더욱 주목받고 있음에도 불구하고 이에 관한 실증적 연구는 다소 부족한 상태이다. 이에 본 연구에서는 이러한 푸드트럭 서비스에 대한 고객 경험을 분석하여 서비스품질 개선을 위한 전략적 인사이트를 도출하는 것을 목표로 한다. 이를 위해 구조적 토픽모델링을 활용해 푸드트럭 관련 고객 리뷰 데이터를 분석하여 50개의 주요 토픽을 도출하였으며, 최적의 토픽 개수를 설정하기 위한 다양한 모형 진단과 해석 가능성을 종합적으로 검토하는 과정을 통해 서비스 경험과 관련된 주요 토픽을 확정하였다, 도출된 토픽이 전반적인 고객 만족도에 미치는 영향을 회귀분석을 통해 실증적으로 검증한 결과, "음식 맛", "직원 친절도", "긍정적 감정" 등이 고객 만족도에 긍정적인 영향을 미치는 반면, "지연된 서비스", "부정적 감정", "음료 서비스" 등이 부정적인 영향을 미치는 것으로 나타났다. 이러한 분석을 바탕으로, 푸드트럭 운영자들이 고객 피드백을 체계적으로 분석하고 이를 기반으로 서비스 개선과 혁신을 추진할 수 있는 구체적인 방법을 제시하였다. 본 연구는 푸드트럭과 같은 소규모 비즈니스 환경에서도 데이터 기반 의사결정의 중요성을 강조하였으며 이를 통해, 서비스 산업에서의 토픽모델링 활용 가능성을 확장하는 데 기여한다.

• 전기학회논문지P
• /
• 제65권2호
• /
• pp.108-113
• /
• 2016

The real-world problems usually show nonlinear and multi-variate characteristics, so it is difficult to establish concrete mathematical models for them. Thus, it is common to practice data-driven modeling techniques in these cases. Among them, most widely adopted techniques are regression model and intelligent model such as neural networks. Regression model has drawback showing lower performance when much non-linearity exists between input and output data. Intelligent model has been shown its superiority to the linear model due to ability capable of effectively estimate desired output in cases of both linear and nonlinear problem. This paper proposes modeling method of daily photovoltaic power systems using ELM(Extreme Learning Machine) based modular networks. The proposed method uses sub-model by fuzzy clustering rather than using a single model. Each sub-model is implemented by ELM. To show the effectiveness of the proposed method, we performed various experiments by dataset acquired during 2014 in real-plant.

• 한국해안해양공학회지
• /
• 제10권1호
• /
• pp.27-36
• /
• 1998

물의 유동을 해석하기 위한 3차원 수치모형이 개발되었다 모형은 균질류에 대한 $\sigma$-좌표에서 방정식들 을 유한요소법을 사용하여 해석한다. 모형의 정확성을 정토하기 위하여 1차원 수로에서 취송류 분포, 정사각형 호수에서 취송류 분포를 해석하고 해석해와 비교 검증하였으며, 마산-진해만에서 조류분포를 계산하고 현장 관측자료와 비교 검증하였다. 계산결과가 비교된 해석해 및 관측치와 대체로 일치하는 양호한 결과를 보였다. 따라서, 개발된 모형은 복잡한 육지경계를 갖는 자연 수괴의 3차원적 순환현상을 해석하는 데 널리 활용될 수 있을 것이다