• 대한음성학회지:말소리
• /
• 제59호
• /
• pp.53-68
• /
• 2006

We report the evaluation results of the Korean speech recognition platform called ECHOS. The platform has an object-oriented and reusable architecture so that researchers can easily evaluate their own algorithms. The platform has all intrinsic modules to build a large vocabulary speech recognizer: Noise reduction, end-point detection, feature extraction, hidden Markov model (HMM)-based acoustic modeling, cross-word modeling, n-gram language modeling, n-best search, word graph generation, and Korean-specific language processing. The platform supports both lexical search trees and finite-state networks. It performs word-dependent n-best search with bigram in the forward search stage, and rescores the lattice with trigram in the backward stage. In an 8000-word continuous speech recognition task, the platform with a lexical tree increases 40% of word errors but decreases 50% of recognition time compared to the HTK platform with flat lexicon. ECHOS reduces 40% of recognition errors through incorporation of cross-word modeling. With the number of Gaussian mixtures increasing to 16, it yields word accuracy comparable to the previous lexical tree-based platform, Julius.

• 한국IT서비스학회지
• /
• 제18권4호
• /
• pp.135-149
• /
• 2019

Recently, there are many researches for extracting meaningful information from large amount of text data. Among various applications to extract information from text, topic modeling which express latent topics as a group of keywords is mainly used. Topic modeling presents several topic keywords by term/topic weight and the quality of those keywords are usually evaluated through coherence which implies the similarity of those keywords. However, the topic quality evaluation method based only on the similarity of keywords has its limitations because it is difficult to describe the content of a topic accurately enough with just a set of similar words. In this research, therefore, we propose topic keywords reorganizing method to improve the identifiability of topics. To reorganize topic keywords, each document first needs to be labeled with one representative topic which can be extracted from traditional topic modeling. After that, classification rules for classifying each document into a corresponding label are generated, and new topic keywords are extracted based on the classification rules. To evaluated the performance our method, we performed an experiment on 1,000 news articles. From the experiment, we confirmed that the keywords extracted from our proposed method have better identifiability than traditional topic keywords.

• Advances in Computational Design
• /
• 제8권3호
• /
• pp.219-236
• /
• 2023

In this paper, finite element modeling of the laser ultrasonics (LU) process in ablation regime is of interest. The momentum resulting from the removal of material from the specimen surface by the laser beam radiation in ablation regime is modeled as a pressure pulse. To model this pressure pulse, two equations are required: one for the spatial distribution and one for the temporal distribution of the pulse. Previous researchers have proposed various equations for the spatial and temporal distributions of the pressure pulse in different laser applications. All available equations are examined and the best combination of the temporal and spatial distributions of the pressure pulse that provides the most accurate results is identified. This combination of temporal and spatial distributions has never been used for modeling laser ultrasonics before. Then by using this new model, the effects of variations in pulse duration and laser spot radius on the shape, amplitude, and frequency spectrum of ultrasonic waves are studied. Furthermore, the LU in thermoelastic regime is simulated by this model and compared with LU in ablation regime. The interaction of ultrasonic waves with a defect is also investigated in the LU process in ablation regime. Good agreement of the results obtained from the new finite element model and available experimental data confirms the accuracy of the proposed model.

• Geomechanics and Engineering
• /
• 제31권3호
• /
• pp.319-328
• /
• 2022

Ensuring the integrity of a country's infrastructure is necessary to protect surrounding communities in case of disaster. Embankment dam systems across the US are an essential component of infrastructure, referred to as lifeline structures. Embankment dams are crucial to the survival of life and if these structures were to fail, it is imperative that states be prepared. Southern California is particularly concerned with the stability of embankment dams due to the frequent seismic activity that occurs in the state. The purpose of this study was to create a numerical model of an existing embankment dam simulated under seismic loads using previously recorded data. The embankment dam that was studied in Los Angeles, California was outfitted with accelerometers provided by the California Strong Motion Instrumentation Program that have recorded strong motion data for decades and was processed by the Center for Engineering Strong Motion Data to be used in future engineering applications. The accelerometer data was then used to verify the numerical model that was created using finite element modeling software RS2. The results from this study showed Puddingstone Dam's simulated response was consistent with that experienced during previous earthquakes and therefore validated the predicted behavior from the numerical model. The study also identified areas of weakness and instability on the dam that posed the greatest risk for its failure. Following this study, the numerical model can now be used to predict the dam's response to future earthquakes, develop plans for its remediation, and for emergency response in case of disaster.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.439-443
• /
• 2004

In this research, we describe the sorting conditions modeling by friction force. As in any mechanism which is required to provide good dynamic performance and high accuracy, performance evaluation of optimal control. To understand friction it is necessary to investigate the topography of the sliding surfaces in contact. Any surfaces, even apparently smooth surfaces, are microscopically rough. When two surfaces come into contact, the true contact takes place only at point where asperities come together. The sorting conditions of sorting mechanism with friction force is sorting force must be equal with force can sorting one highest veneer among loaded veneer. This is just a thing being sorted veneer have friction with under veneer and this friction disturb sorting at the same time. Hence, the sorting conditions evaluation is important to sorting one veneer must get under control friction with veneer.

• 한국CDE학회논문집
• /
• 제15권4호
• /
• pp.289-296
• /
• 2010

Energy consumption by buildings accounts for a large part of the world‘s energy consumption. Methods to analyze building energy consumption before construction have been studied for decades. With BIM (Building Information Modeling) technology, architects can easily export building information to data models in order to analyze the design‘s effect on building energy efficiency. Although several BIM-based energy simulation applications are currently available, utilizing these applications for energy efficiency simulation is difficult. In this paper, by comparing existing BIM-based energy applications, the authors test the building energy efficiencies estimated by some BIM models, offer ideas and solutions to problems that appeared during the test process and propose new methods for BIM-based energy evaluation based on quantitative factors.

• Industrial Engineering and Management Systems
• /
• 제13권1호
• /
• pp.15-28
• /
• 2014

Evaluation of the implementation and performance of a firm's green supply chain management (GSCM) is an ongoing process. Balanced scorecard is a multi-criteria evaluation concept that highlights implementation and performance measures. The literature on the framework is abundant literature but scarce on how to build a hierarchical framework under uncertainty with dependence relations. Hence, this study proposes a hybrid approach, which includes applied interpretive structural modeling to build a hierarchical structure and uses the analytic network process to analyze the dependence relations. Additionally, this study applies the fuzzy set theory to determine linguistic preferences. Twenty dependence criteria are evaluated for a GSCM implemented firm in Taiwan. The result shows that the financial aspect and life cycle assessment are the most important performance and weighted criteria.

• 한국CDE학회논문집
• /
• 제6권2호
• /
• pp.140-146
• /
• 2001

A nuclear Power Plant is composed of a number of mechanical components. Maintaining the integrity of these components is one of the most critical issues in nuclear industry. In order to evaluate the integrity of these mechanical components, a lot of data are required including inspection data, geometrical data, material properties, etc. Therefore, an effective database system is essential to manage the integrity of nuclear power plant. For this purpose, an internet based virtual reality environment and web database system was proposed. The developed virtual reality environment provides realistic geometrical configurations of mechanical components using VRML (Virtual Reality Modeling Language). The virtual reality environment was linked with the web database, which can manage the required data for the integrity evaluation. The proposed system is able to share the information regarding the integrity evaluation through internet, and thus, will be suitable for an integrated system for the maintenance of mechanical components.

• Architectural research
• /
• 제17권2호
• /
• pp.75-81
• /
• 2015

Insulation and condensation performance evaluation (I&CPE) is an important energy analysis. While considerable amount of data are already represented in a Building Information Model (BIM), the lack of interoperability between BIM modeling and I&CPE programs prevents the simulation process from being efficient and accurate. This study proposes a prototype of a BIM-based I&CPE simulation program, in order to enhance the interoperability between BIM modeling and I&CPE programs. This study discusses the information flow process, defines the required information and its level of detail, develops standardized libraries, and finally proposes a prototype that consists of a data extraction module, conversion module, and performance module. The assurance of interoperability between systems might greatly benefit architects and energy professionals.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2005년도 동계학술발표대회 논문집
• /
• pp.51-56
• /
• 2005

The objective of this study is to develop Home Indoor Air Quality evaluation prorgram considering planning and construction stage for architects, engineers and occupants to estimate and improve the IAQ of a home. In this study, the IAQ modeling technique was discussed to determine the appropriate modeling of housing unit in Korea. The program algorithm was developed based on the selected model reflecting planning and construction stage. This program can be applied to estimate the IAQ of a home and encourage appropriate action in advance.