• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.693-701
• /
• 2017

In this paper, we propose a new method for music genre classification using spikegram and deep neural network. The human auditory system encodes the input sound in the time and frequency domain in order to maximize the amount of sound information delivered to the brain using minimum energy and resource. Spikegram is a method of analyzing waveform based on the encoding function of auditory system. In the proposed method, we analyze the signal using spikegram and extract a feature vector composed of key information for the genre classification, which is to be used as the input to the neural network. We measure the performance of music genre classification using the GTZAN dataset consisting of 10 music genres, and confirm that the proposed method provides good performance using a low-dimensional feature vector, compared to the current state-of-the-art methods.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.3
• /
• pp.940-947
• /
• 2018

The purpose of this study was to obtain data to support applied motions of bench press and to provide basic data for the efficient execution of the exercise by analyzing muscular activation through measuring electromyogram of pectoralis major and erector spinae when flat bench pressing with feet on the ground versus feet on the bench. For this study, 4 amateur bodybuilders and 2 health trainers were chosen as subjects. Surface electrodes were attached on the measuring muscles; pectoralis major and erector spinae. Motion phases were defined for the flat bench press and each subject, with a 10RM load, performed a set with feet on the ground and another set with feet on the bench. Data was analyzed in SPSS 20.0 and the following results were obtained. The placement of the feet did not affect the muscular activation of the pectoralis major during the flat bench press. however, the muscular activation of the erector spinae was different between the two positions.

• The Journal of Korean Association of Computer Education
• /
• v.17 no.4
• /
• pp.45-57
• /
• 2014

Many studies on algorithm judging system which verifies the correctness and the time efficiency of your program have been underway recently, most of which are on an online judging system focused on programming contests. However this study is mainly about development and application of the judging system based on client-server. Especially, we designed to promote metacognition and motivation which are emphasized in CRESST model, and implemented the total system that consists of the problem, data set, validation program, and user service environments. We applied our system to elementary, middle, and high school students, and We noticed a significant difference of average score between the experimental and control group in posttest and concluded that the teaching method using our system gave the bigger positive effects on programming learning.

• Journal of IKEEE
• /
• v.14 no.1
• /
• pp.47-54
• /
• 2010

In this study, we analyzed the reduction of noise in a noise environment using 2, 3, 4 or 5 microphones in digital hearing aids. In order to be able to use this in actual digital hearing aids, we made the experiment microphone set similar to the behind-the-ear type (BTE) and then recorded the signal accordingly, with each situation. With the recorded signals, we reduced the noise in each signal by a noise reduction algorithm using multi-microphones. As a result, in the case of By comparing the SNR (Signal to Noise Ratio) and PESQ (Perceptual Evaluation of Speech) measurements, before and after the noise reduction, the results showed that the improvement in performance was highest when three or four microphones were used. Generally, when two or more microphones were used, we found that as the number of microphones increased there was an increase in performance.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.5
• /
• pp.537-543
• /
• 2012

In this study, we experimentally investigate a noise mechanism related to the machining accuracy of the reducer in the driving state. We fabricate a planetary reducer and four types of gears for use in the planetary reducer. We use signal analysis to determine the noise and vibration of the reducer at different motor speeds; the motor speed is increased from 0 rpm to the maximum speed in a stepwise manner. In addition, we obtain the sound level by using a sound level meter. The machining accuracy of gears is evaluated by public organizations, Korea Testing Laboratory (KTL), on the basis of the Japanese Industrial Standard (JIS). We analyze and compare the results with the noise and vibration of the reducer.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.5
• /
• pp.2009-2014
• /
• 2012

It is very important to minimize the die roll height of gear, in order to maximize the shear cutting surface(tooth surface) of fine blanking. In this paper, the fine blanking tool sets were manufactured in order to study the die roll height according to V-ring position and die chamfer shape. They were constituted of the various die inserts and guide plate inserts with different die chamfer shape and different V-ring distance. The fine blanking experiment was conducted with the fine blanking tool sets and the die roll height of the gear samples was measured. It should be noted that die roll height on the fine blanked gear increased with increasing the V-ring distance and die chamfer angle.

• Journal of Sensor Science and Technology
• /
• v.6 no.6
• /
• pp.466-475
• /
• 1997

In this paper, an implantable middle ear hearing aids using an electromagnetic transducer which consists of a tiny coil and a magnet is designed, and objective design method to implement a vibrator of the electromagnetic type transducer is proposed. Sound characteristic of the electromagnetic type vibrator is excellent but power transfer rate is lower than that of a ceramic type. To improve power transfer efficiency of system, external and inner part of a middle ear system is designed using FM transmission method. We implemented an experimental set of the designed transducer, inner part, and outer part. Then, we measured vibration characteristics of a metal strip and a temporal bone of a dead body. As the results, we confirmed the advantage of FM method and showed that designed transducer could effectively transmit vibration of amplified input sound pressure to ossicle.

• Journal of the Korean Applied Science and Technology
• /
• v.37 no.6
• /
• pp.1465-1474
• /
• 2020

The purpose of this study is the effects of 12 weeks complex training using swiss ball and elastic band on senior fitness and sarcopenia index in elderly women. The subject of this study was classified into exercise group (n=13) and control group (n=14). EG were carrier exercise program with swiss-ball and elastic band by 3 times a week, 3sets, RPE 11-13, and 60 minute. Test variables of among this study, senior fitness which is muscle strength, endurance, flexibility and dynamic balance and age-related sarcopenia index were muscle strength, muscle mass and short physical performance battery (SPPB). The results of this study were not significantly improvement at muscle strength, cardiopulmonary and flexibility but dynamic balance was significantly difference. And SPPB were significantly difference. In conclusion, the complex whole body training had positive effects on dynamic balance and SPPB of the elderly women.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.743-754
• /
• 2022

This paper contains the results of the development and performance evaluation of the environmental data monitoring system for the fish farm. For the hardware development, the analogue sensor is used to collect dissolved oxygen, pH, salinity, and temperature of the fish farm water, and the digital sensor is used for collecting ambient temperature, humidity, and location information via a GPS module to be sent to cloud-based Firebase DB. A set of LoRa transmitters and receivers is used as a communication module to upload the collected data. The data stored in Firebase is retrieved as a graph on a web and mobile application to monitor the environmental data changes in real-time. A notification will be delivered if the collected data is outside the determined optimal value. To evaluate the performance of the developed system, a response time from hardware modules to web and mobile applications is ranging from 6.2 to 6.85 seconds, which indicates satisfactory results.

• Journal of the Korean earth science society
• /
• v.44 no.2
• /
• pp.105-118
• /
• 2023

In this study, we predicted the presence of fog with a one-hour delay using the XGBoost DART machine learning algorithm for Andong, which had the highest occurrence of fog among inland stations from 2016 to 2020. We used six datasets: meteorological data, agricultural observation data, additional derived data, and their expanded data. The weather phenomenon numbers obtained through naked-eye observations and the visibility distances measured by visibility meters were classified as fog [1] or no-fog [0]. We set up twelve machine learning modeling experiments and used data from 2021 for model validation. We mainly evaluated model performance using recall and AUC-ROC, considering the harmful effects of fog on society and local communities. The combination of oversampled meteorological data features and the target induced by weather phenomenon numbers showed the best performance. This result highlights the importance of naked-eye observations in predicting fog using machine learning algorithms.