• Journal of the Optical Society of Korea
• /
• v.12 no.4
• /
• pp.281-287
• /
• 2008

An acousto-optic tunable filter based 3-D micro surface profile measurement using an equally spaced 5 spectral phase shifting is described. The 5-bucket spectral phase shifting method is compared with a Fourier-transform method in the spectral domain. It can provide a fast measurement capability while maintaining high accuracy since it needs only 5 pieces of spectrally phase shifted imaging data and a simple calculation in comparison with the Fourier transform method that requires full wavelength scanning data and relatively complicated computation. The 3-D profile data of micro objects can be obtained in a few seconds with an accuracy of ${\sim}10nm$. The 3-D profile method also has an inherent benefit in terms of being speckle-free in measuring diffuse micro objects by employing an incoherent light source. Those simplicity and practical applicability is expected to have diverse applications in 3-D micro profilometry such as semiconductors and micro-biology.

• Design & Manufacturing
• /
• v.13 no.2
• /
• pp.6-11
• /
• 2019

In this study, we constructed the mathematical model to evaluate the roundness for plastic injection mold parts with complicated 3D curvatures. Mathematically we started off from the equation of circle and successfully derived an analytical solution so as to minimize the area of the residuals. On the other hand, we employed the numerical method the similar optimization process for the comparison. To verify the mathematical models, we manufactured and used a ball valve type plastic parts to apply the derived model. The plastic parts was fabricated under the process conditions of 220-ton injection mold machine with a raw material of polyester. we experimentally measured (x, y) position using 3D contact automated system and applied two mathematical methods to evaluated the accuracy of the mathematical models. We found that the analytical solution gives better accuracy of 0.4036 compared to 0.4872 of the numerical solution. The numerical method however may give adaptiveness and versatility for optional simulations such as a fixed center.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1467-1472
• /
• 2018

For the problem that the face image of surveillance video cannot be accurately identified due to the low resolution, this paper proposes a low resolution face recognition solution based on convolutional neural network model. Convolutional Neural Networks (CNN) model for multi-scale input The CNN model for multi-scale input is an improvement over the existing "two-step method" in which low-resolution images are up-sampled using a simple bi-cubic interpolation method. Then, the up sampled image and the high-resolution image are mixed as a model training sample. The CNN model learns the common feature space of the high- and low-resolution images, and then measures the feature similarity through the cosine distance. Finally, the recognition result is given. The experiments on the CMU PIE and Extended Yale B datasets show that the accuracy of the model is better than other comparison methods. Compared with the CMDA_BGE algorithm with the highest recognition rate, the accuracy rate is 2.5%~9.9%.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.967-985
• /
• 2019

Bug report processing is a key element of bug fixing in modern software maintenance. Bug reports are not processed immediately after submission and involve several processes such as bug report deduplication and bug report triage before bug fixing is initiated; however, this method of bug fixing is very inefficient because all these processes are performed manually. Software engineers have persistently highlighted the need to automate these processes, and as a result, many automation techniques have been proposed for bug report processing; however, the accuracy of the existing methods is not satisfactory. Therefore, this study focuses on surveying to improve the accuracy of existing techniques for bug report processing. Reviews of each method proposed in this study consist of a description, used techniques, experiments, and comparison results. The results of this study indicate that research in the field of bug deduplication still lacks and therefore requires numerous studies that integrate clustering and natural language processing. This study further indicates that although all studies in the field of triage are based on machine learning, results of studies on deep learning are still insufficient.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.8
• /
• pp.52-59
• /
• 2021

In this study, we experimentally evaluated the mechanical properties and geometric form accuracy in FDM 3D printing processes based on the printing direction, building direction, and layer thickness. The specimen test results showed that the tensile strength increased by over 33% in the printing direction compared to the direction perpendicular to printing and the tensile strength becomes larger as the layer thickness decreased. Furthermore, the tensile and impact strengths in the building direction were significantly reduced due to the difference in the interlayer joining and bonding strengths of the fused material. Additionally, shrinkage of the material due to phase change induced curl distortion especially in thin and long 3D-printed products, which increased as the layer thickness increased.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.3
• /
• pp.341-347
• /
• 2022

This paper presents a comparison result of two simultaneous localization and mapping (SLAM) algorithms for navigation that have been proposed in literature. The performances of Extended Kalman Filter (EKF) SLAM under Gaussian condition, FastSLAM algorithms using Rao-Blackwellised method for particle filtering are compared in terms of accuracy of state estimations for localization of a robot and mapping of its environment. The algorithms were run using the same type of robot on indoor environment. The results show that the Particle filter based FastSLAM has the better performance in terms of accuracy of localization and mapping. The experimental results are discussed and compared.

• Journal of information and communication convergence engineering
• /
• v.19 no.4
• /
• pp.241-247
• /
• 2021

Particulate matter has emerged as a serious global problem, necessitating highly reliable information on the matter. Therefore, various algorithms have been used in studies to predict particulate matter. In this study, we compared the prediction performance of neural network models that have been actively studied for particulate matter prediction. Among the neural network algorithms, a deep neural network (DNN), a recurrent neural network, and long short-term memory were used to design the optimal prediction model using a hyper-parameter search. In the comparative analysis of the prediction performance of each model, the DNN model showed a lower root mean square error (RMSE) than the other algorithms in the performance comparison using the RMSE and the level of accuracy as metrics for evaluation. The stability of the recurrent neural network was slightly lower than that of the other algorithms, although the accuracy was higher.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1606-1613
• /
• 2021

Recently various attempts to control hardware through integration of sensors and artificial intelligence have been made. This paper proposes a smart hazardous sound detection at home. Previous sound recognition methods have problems due to the processing of background sounds and the low recognition accuracy of high-frequency sounds. To get around these problems, a new MFCC(Mel-Frequency Cepstral Coefficient) algorithm using Wiener filter, modified filterbank is proposed. Experiments for comparing the performance of the proposed method and the original MFCC were conducted. For the classification of feature vectors extracted using the proposed MFCC, DNN(Deep Neural Network) was used. Experimental results showed the superiority of the modified MFCC in comparison to the conventional MFCC in terms of 1% higher training accuracy and 6.6% higher recognition rate.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_2
• /
• pp.969-977
• /
• 2022

Currently, in Korea, aerial photogrammetry is being studied for cadastral boundaries and numerical maps. Since the announced value of cadastral survey is closely related to ownership, the accuracy and reliability of the published value should be emphasized above all else. However, although aerial photogrammetry has great advantages in economic feasibility and surveying efficiency, it has many limitations when extracting the boundary of cadastral survey based on the acquired image. In order to improve these limitations, in this study, an aerial target was applied to obtain reliability improvement. Therefore, in order to examine the usefulness of aerial photogrammetry for cadastral survey application, cadastral boundary extraction and accuracy comparison analysis were conducted.

• Structural Engineering and Mechanics
• /
• v.85 no.1
• /
• pp.15-27
• /
• 2023

Using artificial intelligence and internet of things methods in engineering and industrial problems has become a widespread method in recent years. The low computational costs and high accuracy without the need to engage human resources in comparison to engineering demands are the main advantages of artificial intelligence. In the present paper, a deep neural network (DNN) with a specific method of optimization is utilize to predict fundamental natural frequency of a cylindrical structure. To provide data for training the DNN, a detailed numerical analysis is presented with the aid of functionally modified couple stress theory (FMCS) and first-order shear deformation theory (FSDT). The governing equations obtained using Hamilton's principle, are further solved engaging generalized differential quadrature method. The results of the numerical solution are utilized to train and test the DNN model. The results are validated at the first step and a comprehensive parametric results are presented thereafter. The results show the high accuracy of the DNN results and effects of different geometrical, modeling and material parameters in the natural frequencies of the structure.