• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.3
• /
• pp.128-133
• /
• 2021

Recently Recently, the incidence of spinal diseases due to poor posture among students and office workers is increasing, and various studies have been conducted to help maintain correct posture. In previous studies, a membrane sensor or a pressure sensor was placed on the seat cushion to see the weight bias, or a sensor that restrained the user was attached to measure the position change. In our previous study, we developed a sensor device which can be easily attached to the body with an adhesive gel sheet and that measures and outputs the user's posture and body position in real time, but it has a limitation in the accuracy of the sensor value. In this study, a study was conducted to improve the performance of the position conversion sensor device and quantitatively evaluate the accuracy of the angle conversion measurement value, and a high accuracy with 2.53% of error rate was confirmed. In future research, it is considered that additional research targeting actual users is needed by diversifying posture correction training contents with multimedia elements added.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.3
• /
• pp.110-115
• /
• 2021

With the era of the 4th Industrial Revolution, education on artificial intelligence is one of the important topics. However, since existing education is aimed at knowledge, it is not suitable for developing the active problem-solving ability and AI utilization ability required by artificial intelligence education. To solve this problem, we proposes PBL-based education method in which learners learn in the process of solving the presented problem. The problem presented to the learner is a completed project. This project consists of three types: a classification model, the training data of the classification model, and the block code to be executed according to the classified result. The project works, but each component is designed to perform a low level of operation. In order to solve this problem, the learners can expect to improve their computational thinking skills by finding problems in the project through testing, finding solutions through discussion, and improving to a higher level of operation.

• Journal of Audiology & Otology
• /
• v.25 no.2
• /
• pp.65-71
• /
• 2021

Background and Objectives: In masking level difference (MLD), the masked detection threshold for a signal is determined as a function of the relative interaural differences between the signal and the masker. Study 1 analyzed the results of school-aged children with good school performance in the MLD test, and study 2 compared their results with those of a group of children with poor academic performance. Subjects and Methods: Study 1 was conducted with 47 school-aged children with good academic performance (GI) and study 2 was carried out with 32 school-aged children with poor academic performance (GII). The inclusion criteria adopted for both studies were hearing thresholds within normal limits in basic audiological evaluation. Study 1 also considered normal performance in the central auditory processing test battery and absence of auditory complaints and/or of attention, language or speech issues. The MLD test was administered with a pure pulsatile tone of 500 Hz, in a binaural mode and intensity of 50 dBSL, using a CD player and audiometer. Results: In study 1, no significant correlation was observed, considering the influence of the variables age and sex in relation to the results obtained in homophase (SoNo), antiphase (SπNo) and MLD threshold conditions. The final mean MLD threshold was 13.66 dB. In study 2, the variables did not influence the test performance either. There was a significant difference between test results in SπNo conditions of the two groups, while no differences were found both in SoNo conditions and the final result of MLD. Conclusions: In study 1, the cut-off criterion of school-aged children in the MLD test was 9.3 dB. The variables (sex and age) did not interfere with the MLD results. In study 2, school performance did not differ in the MLD results. GII group showed inferior results than GI group, only in SπNo condition.

• Korean Journal of Audiology
• /
• v.25 no.2
• /
• pp.65-71
• /
• 2021

Background and Objectives: In masking level difference (MLD), the masked detection threshold for a signal is determined as a function of the relative interaural differences between the signal and the masker. Study 1 analyzed the results of school-aged children with good school performance in the MLD test, and study 2 compared their results with those of a group of children with poor academic performance. Subjects and Methods: Study 1 was conducted with 47 school-aged children with good academic performance (GI) and study 2 was carried out with 32 school-aged children with poor academic performance (GII). The inclusion criteria adopted for both studies were hearing thresholds within normal limits in basic audiological evaluation. Study 1 also considered normal performance in the central auditory processing test battery and absence of auditory complaints and/or of attention, language or speech issues. The MLD test was administered with a pure pulsatile tone of 500 Hz, in a binaural mode and intensity of 50 dBSL, using a CD player and audiometer. Results: In study 1, no significant correlation was observed, considering the influence of the variables age and sex in relation to the results obtained in homophase (SoNo), antiphase (SπNo) and MLD threshold conditions. The final mean MLD threshold was 13.66 dB. In study 2, the variables did not influence the test performance either. There was a significant difference between test results in SπNo conditions of the two groups, while no differences were found both in SoNo conditions and the final result of MLD. Conclusions: In study 1, the cut-off criterion of school-aged children in the MLD test was 9.3 dB. The variables (sex and age) did not interfere with the MLD results. In study 2, school performance did not differ in the MLD results. GII group showed inferior results than GI group, only in SπNo condition.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.222-227
• /
• 2022

In this paper, we implemented a Korean text generation and classification model based on a deep learning algorithm that can be applied to various industries. It consists of two implemented GAN-based Korean handwriting generation models and CNN-based Korean handwriting classification models. The GAN model consists of a generator model for generating fake Korean handwriting data and a discriminator model for discriminating fake handwritten data. In the case of the CNN model, the model was trained using the 'PHD08' dataset, and the learning result was 92.45. It was confirmed that Korean handwriting was classified with % accuracy. As a result of evaluating the performance of the classification model by integrating the Korean cursive data generated through the implemented GAN model and the training dataset of the existing CNN model, it was confirmed that the classification performance was 96.86%, which was superior to the existing classification performance.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.271-271
• /
• 2019

Estimating ship motion is difficult because it take place in complex environments.. Estimating ship motion is an important factor in ensuring the safety of ship, so accurate estimates are needed. Existing motion-related studies compare the apparent motion of the model acquired and the reference model by experimenting with the ship motion on a particular alignment, making it difficult to intuitively estimate the hull motion. This study introduces the concept of estimating the characteristics of ship motion as a transfer function through pole-zero interpretation and frequency response analysis by applying the method of transfer function of Linear-Time Invariant system. Ship motion analysis model using Linear-Time Invariant system is consist with 1) wave as input signal 2) ship motion as output signal 3) hull defined as black box. This model can be defined by numericalizing the ship motion as a transfer function and is expected to facilitate the characterization of the ship motion through pole-zero analysis and frequency response analysis.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.15-20
• /
• 2023

In general, maintaining an incorrect sitting posture for a long time is widely known to adversely affect the spine. Recently, several researchers have been interested in the causal relationship between incorrect sitting posture and spinal diseases, and have been studying methods to precisely measure changes in sitting or standing posture to prevent spinal diseases. In previous studies, we have developed a sensor device capable of measuring real-time posture change, applied a momentum calculation algorithm to improve the accuracy of real-time posture change measurement, and verified the accuracy of the postural change measurement sensor. In this study, we developed a posture measurement and analysis device that considers changes in the center of body pressure through the developed sitting pressure measurement, and it confirmed the sensor as an auxiliary tool to increase the accuracy of posture correction training with improving the user's visual feedback.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.41-49
• /
• 2024

Speech recognition technology is continuously advancing and widely used in various fields. In this study, we aimed to investigate the impact of speech data quality on speech recognition models by dividing the dataset into the entire dataset and the top 70% based on Signal-to-Noise Ratio (SNR). Utilizing Seamless M4T and Google Cloud Speech-to-Text, we examined the text transformation results for each model and evaluated them using the Levenshtein Distance. Experimental results revealed that Seamless M4T scored 13.6 in models using data with high SNR, which is lower than the score of 16.6 for the entire dataset. However, Google Cloud Speech-to-Text scored 8.3 on the entire dataset, indicating lower performance than data with high SNR. This suggests that using data with high SNR during the training of a new speech recognition model can have an impact, and Levenshtein Distance can serve as a metric for evaluating speech recognition models.

• Geophysics and Geophysical Exploration
• /
• v.17 no.3
• /
• pp.137-146
• /
• 2014

This study presents a procedure for discrimination of artificial events from earthquakes occurred in and around the Korean Peninsula using data set in the Wonju KSRS seismograph network, Korea. Two training sets representing natural and artificial earthquakes were constructed with 150 and 56 events, respectively, with high signal to noise ratio. A frequency band, Pg(4-6 Hz)/Lg(5-7 Hz), which is optimal for the discrimination of seismic sources was derived from the two-dimensional grid of Pg/Lg spectral amplitude ratio. The corrections for the effects of earthquake magnitude and hypocentral distance were carried out for improvement of discrimination capability. For correcting the effect of magnitude dependence due to the inverse proportionality of corner frequency to seismic moment, the Brune's source spectrum was subtracted from the observation spectrum. The spectrum was corrected using the optimal damping coefficient to remove damping effect with the hypocentral distance. The effect of locally varying spectrum ratio was cancelled correcting variation of wave propagation along the ray path. The performance in discrimination between training sets of natural and artificial events was compared using the Mahalanobis distance in each step of correction. The procedure of magnitude, distance, and path corrections show clear improvements of the discrimination results with increasing Mahalanobis distance, from 1.98 to 3.01, between two training sets.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.4
• /
• pp.827-836
• /
• 2018

In this study, we developed a PC - based motorcycle simulator based on the development technology of a virtual patrol motorcycle training system. This simulator has been developed to be applied to a variety of fields such as driving training for beginners, driver factor research, and system development such as ABS, which can be seen in advanced models. The weight of the motorcycle operated by the patrol guards is more than 400Kg. There is a lot of risk due to the nature of work without prior practice. Therefore, we implemented a study on the untilization of physical stress and temporal pressure in emergency situations. In order to get a feeling that the motorcycle simulator is operating in real-life, it is important that the mutual reliable signal transmission and operation feel between the driver and the simulator. In order to achieve this, we developed a system that can apply the sub-systems of the actual vehicle to the motorcycle simulator in order to generate the same operation feeling as the actual vehicle. Based on these results, we have developed a method of generating a feedback queue.