• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.962-977
• /
• 2019

The human voice is a convenient method of information transfer between different objects such as between men, men and machine, between machines. The development of information and communication technology, the voice has been able to transfer farther than before. The way to communicate, it is to convert the voice to another form, transmit it, and then reconvert it back to sound. In such a communication process, a vocoder is a method of converting and re-converting a voice and sound. The CELP (Code-Excited Linear Prediction) type vocoder, one of the voice codecs, is adapted as a standard codec since it provides high quality sound even though its transmission speed is relatively low. The EVRC (Enhanced Variable Rate CODEC) and QCELP (Qualcomm Code-Excited Linear Prediction), variable bit rate vocoders, are used for mobile phones in 3G environment. For the real-time implementation of a vocoder, the reduction of sound quality is a typical problem. To improve the sound quality, that is important to know the size and shape of noise. In the existing sound quality improvement method, the voice activated is detected or used, or statistical methods are used by the large mount of data. However, there is a disadvantage in that no noise can be detected, when there is a continuous signal or when a change in noise is large.This paper focused on finding a better way to decrease the reduction of sound quality in lower bit transmission environments. Based on simulation results, this study proposed a preprocessor application that estimates the SNR (Signal to Noise Ratio) using the spectral SNR estimation method. The SNR estimation method adopted the IMBE (Improved Multi-Band Excitation) instead of using the SNR, which is a continuous speech signal. Finally, this application improves the quality of the vocoder by enhancing sound quality adaptively.

• Journal of Fashion Business
• /
• v.23 no.1
• /
• pp.37-48
• /
• 2019

WKSF (Warp-knitted spacer fabrics) knitted using a double Raschel machine is the three-dimensional knit that has vertically connected separate layers in loop structures. Because of its unique structure, the fabric is light, compressible and breathable. Owing to the high production speed, the use of the fabric is increasing in various areas. The purpose of this study is to establish the design process in the utilization of WKSF program and analyze the difference between WKSF and Neoprene as garment materials.. The study on the design related to WKSF has rarely been carried out because of the complexity of WKSF structure and the difficulties encountered in analyzing the structure and thread. Therefore, checking beforehand the simulation results similar to a final knit using the CAD program for WKSF can only enhance the efficiency of the design for the light knits. The conclusion drawn after designing the light knits using the CAD program and analyzing the pros and cons of WKSF through the various property evaluation techniques is as follows. The tension characteristic analysis results indicated that Neoprene specimen has the elastic transformation and resilience, thus behaving like an elastic product such as rubber. By contrast, in the event that clothing and fashion accessories are designed with WKSF, these products are kept in a boxy style fit so that the fabric can be applied flexibly to a curvy body line. In addition, WKSF is good in forming noticeably around a curvy body, because its resistance shear deformation is lower than that of Neoprene.

• Journal of the Korea Society for Simulation
• /
• v.27 no.4
• /
• pp.1-8
• /
• 2018

The most common way to control a target point using artificial intelligence is through reinforcement learning. However, it had to process complicated calculations that were difficult to implement in order to process reinforcement learning. In this paper, the enhanced Proximal Policy Optimization (PPO) algorithm was used to simulate finding the planned flight trajectory to reach the target point in the virtual environment. In this paper, we simulated how this problem was used to find the planned flight trajectory to reach the target point in the virtual environment using the enhanced Proximal Policy Optimization(PPO) algorithm. In addition, variables such as changes in trajectory, effects of rewards, and external winds are added to determine the zero conditions of external environmental factors on flight trajectory learning, and the effects on trajectory learning performance and learning speed are compared. From this result, the simulation results have shown that the agent can find the optimal trajectory in spite of changes in the various external environments, which will be applicable to the actual vehicle.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.405-408
• /
• 2016

Games like Go, Chess, Janggi have helped to brain development of the people. These games are developed by computer program. And many algorithms have been developed to allow myself to play. The person winning chess program was developed in the 1990s. But game of go is too large number of cases. So it was considered impossible to win professional go player. However, with the use of MCTS(Monte Carlo Tree Search) and CNN(Convolutional Neural Network), the performance of the go algorithm is greatly improved. In this paper, using CNN and MCTS were proceeding development of go algorithm. Using the manual of go learning CNN look for the best position, MCTS calculates the win probability in the game to proceed with simulation. In addition, extract pattern information of go using existing manual of go, plans to improve speed and performance by using it. This method is showed a better performance than general go algorithm. Also if it is receiving sufficient computing power, it seems to be even more improved performance.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.1
• /
• pp.111-116
• /
• 2019

The fire detectors used in the engine rooms of ships offer only a slow response to emergencies because smoke or heat must reach detectors installed on ceilings, but the air flow in engine rooms can be very fluid depending on the use of equipment. In order to overcome these disadvantages, much research on video-based fire detection has been conducted in recent years. Video-based fire detection is effective for initial detection of fire because it is not affected by air flow and transmission speed is fast. In this paper, experiments were performed using images of smoke from a smoke generator in an engine room. Data generated using LBP and GLCM operators that extract the textural features of smoke was classified using SVM, which is a machine learning classifier. Even if smoke did not rise to the ceiling, where detectors were installed, smoke detection was confirmed using the image-based technique.

• Restorative Dentistry and Endodontics
• /
• v.44 no.1
• /
• pp.5.1-5.9
• /
• 2019

Objectives: The aim of this in vitro study was to evaluate the push-out bond strength of a novel calcium silicate-based root repair material-BIOfactor MTA to root canal dentin in comparison with white MTA-Angelus (Angelus) and Biodentine (Septodont). Materials and Methods: The coronal parts of 12 central incisors were removed and the roots were embedded in acrylic resin blocks. Midroot dentin of each sample was horizontally sectioned into 1.1 mm slices and 3 slices were obtained from each root. Three canal-like standardized holes having 1 mm in diameter were created parallel to the root canal on each dentin slice with a diamond bur. The holes were filled with MTA-Angelus, Biodentine, or BIOfactor MTA. Wet gauze was placed over the specimens and samples were stored in an incubator at $37^{\circ}C$ for 7 days to allow complete setting. Then samples were subjected to the push-out test method using a universal test machine with the loading speed of 1 mm/min. Data was statistically analyzed using Friedman test and post hoc Wilcoxon signed rank test with Bonferroni correction. Results: There were no significant differences among the push-out bond strength values of MTA-Angelus, Biodentine, and BIOfactor MTA (p > 0.017). Most of the specimens exhibited cohesive failure in all groups, with the highest rate found in Biodentine group. Conclusions: Based on the results of this study, MTA-Angelus, Biodentine, and BIOfactor MTA showed similar resistances to the push-out testing.

• Journal of Technologic Dentistry
• /
• v.41 no.3
• /
• pp.177-185
• /
• 2019

Purpose: This study was to investigate the effect of three different surface treatments on the shear bond strength of lithium disilicate ceramics to enamel. Methods: Totally 60 lithium disilicate ceramic disc specimens were fabricated with IPS e.max press (Ivoclar Vivadent, Schaan, Liechtenstein) and Mazic Claro (Vericom, Korea). 30 specimens in each lithium disilicate ceramic were assigned to 3 groups of the each following surface treatment: 1) $50{\mu}m$ airborne particle abrasion+silane, 2) 9.5% hydroflouric acid etching (HF)+silane, 3) $50{\mu}m$ airborne particle abrasion+9.5% HF+silane. Lithium disilicate ceramic surfaces after surface treatments were AFM examined. The shear bond strength was measured in a universal testing machine at 0.5mm/min crosshead speed. All data were analyzed using a two-way ANOVA and Tukey's test(${\alpha}=0.05$). Results: The mean surface roughness of lithium disilicate ceramics ranged from $0.178{\mu}m$ to $0.441{\mu}m$. The mean shear bond strengths ranged from $23.81{\pm}2.78MPa$ to $33.99{\pm}4.85MPa$. Conclusion: 1. Mazic Claro showed higher shear bond strength than IPS e.max press at 3 different surface treatments, and no statistically significant was observed. 2. The shear bond strength of IPS e.max press was strongly enhanced as surface treated with $50{\mu}m$ airborne particle abrasion and 9.5% hydroflouric acid etching. And there was no statistical significance at the shear bond strength of Mazic Claro with surface treatments.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.1
• /
• pp.1-9
• /
• 2019

In electric agricultural machine the gearbox is used to increase torque and lower the output speed of the motor shaft. The gearbox consists of several shafts, helical gears and spur gears works in series. Optimization plays an important role in gear design as reducing the weight or volume of a gear set will increase its service life and improve the bearing capacity. In this paper the basic design parameters for gear like shaft diameter and face width are considered as the input variables. The bending stress and material volume is considered as the objective function. ANSYS was used to investigate the bending stress when the variable was changed. Artificial Neural Network (ANN) was used to obtain the mathematical model of the system based on the bending stress behaviour. The ANN was used since the output system is nonlinear. The Genetic Algorithm (GA)　technique of optimization is used to obtain the optimized values of shaft diameter and face width on the pinion based on the ANN mathematical model and the results are compared as that obtained using the traditional method. The ANN and GA were performed using MATLAB. The simulation results were shown that the proposed algorithm was successfully calculated the value of shaft diameter and face width to obtain the minimal bending stress and material volume of the gearbox.

• Journal of Technologic Dentistry
• /
• v.41 no.2
• /
• pp.71-80
• /
• 2019

Purpose: In this study, to evaluate the effect of oxide changes on the shear bond strength according to the composition of Ni-Cr alloys for porcelain fused matal crown, T-4 alloys, Zeroy alloys and Zeroy-X alloys were selected. Methods: 20 specimens were fabricated using selected Ni-Cr alloys and porcelain powders. A Ni-Cr alloy having a diameter of 5 mm and a height of 25 mm was produced and the metal surface was polished. Porcelain powder was fired on the polished metal surface to a diameter of 5 mm and a height of 3 mm. The experiment group consisted of three groups, T-4(TNA), Zeroy(ZNA) and Zeroy-X(ZXA). The fabricated specimens were mounted on a jig of a universal testing machine(UTM) and fracture strength was measured by applying a shear force at a UTM crosshead speed of 0.5 mm/min. The fracture strength was calculated as the bond strength between the porcelain and the alloy. The surface of the fractured alloy was analyzed by X-ray diffraction(XRD) and scanning electron microscopy(SEM), and the components of the oxide were measured by energy dispersive X-ray spectroscopy(EDX) line profile method. Results: In SEM, XRD and EDX analysis, yttrium tended to increase the mechanical and chemical bonding forces. The shear bond strength of ZXA group containing yttrium showed the highest value at 27.53 MPa. Conclusion: Based on the results of this study, it is considered that the yttrium-added Ni-Cr alloy is clinically acceptable in porcelain shear bond strength.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.67-75
• /
• 2020

This paper proposes a methodology for gantry route optimization in order to maximize the productivity of a odd-type surface mount device (SMD). A odd-type SMD is a machine that uses a gantry to mount electronic components on the placement point of a printed circuit board (PCB). The gantry needs a nozzle to move its electronic components. There is a suitability between the nozzle and the electronic component, and the mounting speed varies depending on the suitability. When it is difficult for the nozzle to adsorb electronic components, nozzle exchange is performed, and nozzle exchange takes a certain amount of time. The gantry route optimization problem is divided into the mounting order on PCB and the allocation of nozzles and electronic components to the gantry. Nozzle and electronic component allocation minimized the time incurred by nozzle exchange and nozzle-to-electronic component compatibility by using an mixed integer programming method. Sequence of mounting points on PCB minimizes travel time by using the branch-and-price method. Experimental data was made by randomly picking the location of the mounting point on a PCB of 800mm in width and 800mm in length. The number of mounting points is divided into 25, 50, 75, and 100, and experiments are conducted according to the number of types of electronic components, number of nozzle types, and suitability between nozzles and electronic components, respectively. Because the experimental data are random, the calculation time is not constant, but it is confirmed that the gantry route is found within a reasonable time.