• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.17-24
• /
• 2019

The biggest problem in the AI field, which has become a hot topic in recent years, is how to deal with the lack of training data. Since manual data construction takes a lot of time and efforts, it is non-trivial for an individual to easily build the necessary data. On the other hand, automatic data construction needs to handle data quality issue. In this paper, we introduce a method to automatically extract the data required to develop Korean speech command recognizer from the web and to automatically select the data that can be used for training data. In particular, we propose a modified ResNet model that shows modest performance for the automatically constructed Korean speech command data. We conducted an experiment to show the applicability of the command set of the health and daily life domain. In a series of experiments using only automatically constructed data, the accuracy of the health domain was 89.5% in ResNet15 and 82% in ResNet8 in the daily lives domain, respectively.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.2
• /
• pp.87-93
• /
• 2018

This Study Propose A New Approach To Impliment A Intelligent Robot Control Based on Voice Recognition For Smart Factory Automation Since human usually communicate each other by voices, it is very convenient if voice is used to command humanoid robots or the other type robot system. A lot of researches has been performed about voice recognition systems for this purpose. Hidden Markov Model is a robust statistical methodology for efficient voice recognition in noise environments. It has being tested in a wide range of applications. A prediction approach traditionally applied for the text compression and coding, Prediction by Partial Matching which is a finite-context statistical modeling technique and can predict the next characters based on the context, has shown a great potential in developing novel solutions to several language modeling problems in speech recognition. It was illustrated the reliability of voice recognition by experiments for humanoid robot with 26 joints as the purpose of application to the manufacturing process.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.75-83
• /
• 2007

Multithreaded model is an effective parallel system in that it can reduce the long memory reference latency time and solve the synchronization problems. When compiling the non-strict functional programs for the multithreaded parallel machine, the most important thing is to find an set of sequentially executable instructions and to partitions them into threads. The existing partitioning algorithm partitions the condition of conditional expression, true expression and false expression into the basic blocks and apply local partitioning to these basic blocks. We can do the better partitioning if we modify the definition of the thread and allow the branching within the thread. The branching within the thread do not reduce the parallelism, do not increase the number of synchronization and do not violate the basic rule of the thread partitioning. On the contrary, it can lengthen the thread and reduce the number of synchronization. In the paper, we enhance the method of the partition of threads by combining the three basic blocks into one of two blocks.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.3
• /
• pp.209-217
• /
• 2013

This paper presents an optimal design of a magnetorheological(MR) fluid-based mount(MR mount) that can be used for to vibration control in diesel engines of ships. In this work, a mount that uses mixed-modes(squeeze mode, flow mode, and shear mode) is proposed and designed. To determine the actuating damping force of the MR mount required for efficient vibration control, the excitation force from a diesel engine is analyzed. In this analysis, a model of a V-type engine is considered. The relationship between the velocity and pressure of gas in terms of the torque acting on the piston is derived. Subsequently, by integrating the field-dependent rheological properties of commercially available MR fluid with the excitation force, the appropriate size of the MR mount is designed. In addition, to achieve the maximum actuating force under geometric constraints, design optimization is undertaken using the ANSYS parametric design language software. Through magnetic density analysis, optimal design parameters such as the bottom gap and radius of coil are determined.

• The Korean Journal of Applied Statistics
• /
• v.29 no.6
• /
• pp.1077-1094
• /
• 2016

Apache Spark is a fast and general-purpose cluster computing package. It provides a new abstraction named resilient distributed dataset, which is capable of support for fault tolerance while keeping data in memory. This type of abstraction results in a significant speedup compared to legacy large-scale data framework, MapReduce. In particular, Spark framework is suitable for iterative machine learning applications such as logistic regression and K-means clustering, and interactive data querying. Spark also supports high level libraries for various applications such as machine learning, streaming data processing, database querying and graph data mining thanks to its versatility. In this work, we introduce the concept and programming model of Spark as well as show some implementations of simple statistical computing applications. We also review the machine learning package MLlib, and the R language interface SparkR.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1279-1290
• /
• 2017

R's {shiny} package provides an environment for creating web applications with only R scripts. Shiny does not require knowledge of a separate web programming language and its development is very easy and straightforward. In addition, Shiny has a variety of extensibility, and its functions are expanding day by day. Therefore, the presentation of high-quality results is an excellent tool for R-based analysts. In this paper, we present actual cases of large data analysis using Shiny. First, geological anomaly zone is extracted by analyzing topographical data expressed in the form of contour lines by analysis related to spatial data. Next, we will construct a model to predict major diseases by 16 cities and provinces nationwide using weather, environment, and social media information. In this process, we want to show that Shiny is very effective for data visualization and analysis.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.37 no.1
• /
• pp.83-91
• /
• 2000

This paper presents a new technique to reduce a large interconnect circuit with tens of thousands of elements into the one that is small enough to be analyzed by circuit simulators such as SPICE. This technique takes a fundamentally different approach form the conventional methods based on the interconnect circuit structure analysis and several rules based on the Elmore time constant. The time moments are computed form the circuit consisting of the interconnect circuit and the CMOS gate driver model computed by the AWE technique. Then, the equivalent RC circuit is synthesized from those moments. The characteristics of the driving CMOS gate can be reflected with the high degree of accuracy and the size of the compressed circuit is determined by the number of output nodes regardless of the size of the original interconnect circuits. This technique has been implemented in C language, applied to several interconnect circuits driven by a 0.5${\mu}m$ CMOS gate and the equivalent RC circuits with more than 99% reduction ratio and accuracy with 1 ~ 10% error in therms of propagation delays were obtained.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.167-173
• /
• 2015

This paper presents a study on the Full-HD HEVC(High Efficiency Video Coding) encoder IP(Intellectual Property) design. The designed IP is for HEVC main profile 4.1, and performs encoding with a speed of 60 fps of full high definition. Before hardware and software design, overall reference model was developed with C language, and we proposed a parallel processing architecture for low-power consumption. And also we coded firmware and driver programs relating IP. The platform for verification of developed IP was developed, and we verified function and performance for various pictures under several encoding conditions by implementing designed IP to FPGA board. Compared to HM-13.0, about 35% decrease in bit-rate under same PSNR was achieved, and about 25% decrease in power consumption under low-power mode was performed.

• Structural Engineering and Mechanics
• /
• v.72 no.6
• /
• pp.713-722
• /
• 2019

Micromechanics is a technique for the analysis of composites or heterogeneous materials which focuses on the components of the intended structure. Each one of the components can exhibit isotropic behavior, but the microstructure characteristics of the heterogeneous material result in the anisotropic behavior of the structure. In this research, the general mechanical properties of a 3D anisotropic and heterogeneous Representative Volume Element (RVE), have been determined by applying periodic boundary conditions (PBCs), using the Asymptotic Homogenization Theory (AHT) and strain energy. In order to use the homogenization theory and apply the periodic boundary conditions, the ABAQUS scripting interface (ASI) has been used along with the Python programming language. The results have been compared with those of the Homogeneous Boundary Conditions method, which leads to an overestimation of the effective mechanical properties. According to the results, applying homogenous boundary conditions results in a 33% and 13% increase in the shear moduli G₂₃ and G₁₂, respectively. In polymeric composites, the fibers have linear and brittle behavior, while the resin exhibits a non-linear behavior. Therefore, the nonlinear effects of resin on the mechanical properties of the composite material is studied using a user-defined subroutine in Fortran (USDFLD). The non-linear shear stress-strain behavior of unidirectional composite laminates has been obtained. Results indicate that at arbitrary constant stress as 80 MPa in-plane shear modulus, G₁₂, experienced a 47%, 41% and 31% reduction at the fiber volume fraction of 30%, 50% and 70%, compared to the linear assumption. The results of this study are in good agreement with the analytical and experimental results available in the literature.

• The Journal of the Korea Contents Association
• /
• v.16 no.7
• /
• pp.256-263
• /
• 2016

Soo-Yeoun Kim & Ji-Eun Kim 2016. A Study on ESP Skating English Education Based on Job Analysis. This study aims to provide skating ESP(English for Specific Purposes) education model for skating instructors in Korea. For this purpose, a total of twenty-seven professional skating instructors were surveyed according to a questionnaire, which asked about their English skills and perspective of the importance of English study and English skating class. The main results are as follows: most skating instructors' confidence in their English is low; majority of them answered that English study is needed for skating instructors; a majority of them want English teaching that focused on speaking and teaching activities. After that, skating instructors' jobs were analyzed using the DACUM(Developing A Curriculum Method). A DACUM committee extracted the duties and tasks which require English education and conducted a survey that targeted skating instructors. When interpreting the study on ESP Skating English Education based on job analysis, it was evident that the English language would be essential for enabling effective communication with judges during national sports competitions, information exchange with foreign skaters, and for technical skating instructions. (Kookmin University, Catholic Kwandong University)