• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.238-244
• /
• 2013

For musical genre classification, various types of feature vectors are utilized. Mel-frequency cepstral coefficient (MFCC), decorrelated filter bank (DFB), and octave-based spectral contrast (OSC) are widely used as short-term features, and their long-term variations are also utilized. In this paper, OSC features are extracted not only in the single-octave band domain, but also in the multiple-octave band one to capture the correlation between octave bands. As a baseline system, we select the genre classification system that won the fourth place in the 2012 music information retrieval evaluation exchange (MIREX) contest. By applying the OSC features based on multiple-octave bands, we obtain the better classification accuracy by 0.40% and 3.15% for the GTZAN and Ballroom databases, respectively.

• Journal of Astronomy and Space Sciences
• /
• v.25 no.2
• /
• pp.71-76
• /
• 2008

Study of terrestrial impact craters is important not only in the field of the solar system formation and evolution but also of the Galactic astronomy. The terrestrial impact cratering record recently has been examined, providing short- and intermediate-term periodicities, such as, ${\sim}26$ Myrs, ${\sim}37$ Myrs. The existence of such a periodicity has an implication in the Galactic dynamics, since the terrestrial impact cratering is usually interpreted as a result of the environmental variation during solar orbiting in the Galactic plane. The aim of this paper is to search for a long-term periodicity with a novel method since no attempt has been made so far in searching a long-term periodicity in this research field in spite of its great importance. We apply the cepstrum analysis method to the terrestrial impact cratering record for the first time. As a result of the analysis we have found noticeable peaks in the Fourier power spectrum appear ing at periods of ${\sim}300$ Myrs and ${\sim}100$ Myrs, which seem in a simple resonance with the revolution period of the Sun around the Galactic center. Finally we briefly discuss its implications and suggest theoretical study be pursued to explain such a long-term periodicity.

• Ocean and Polar Research
• /
• v.31 no.1
• /
• pp.71-76
• /
• 2009

Drastic changes in the water quality and phytoplankton community of the new Saemankeum Lakeduring the first decade following the construction of the Saemankeum Sea Wall has been considered to be unavoidable. Input of eutrophicated water through the Mankyeong River and Dongjin River might produce more direct effects on the water quality and phytoplankton community, which lead us to launch a long-term semi-weekly investigation at the "Mankyeong Bridge" monitoring point to resolve its short-term effect as well as long-term stabilization of the ecosystem in the new Saemankeum Lake. During 15 months starting from June 2006, the water temperature varied in accordance with the typical seasonal variations in temperate on the coasts, and no significant daily variations evoked by tidal cycle could be detected. However, there was an inverse relationship between seasonal precipitation and salinity even though the range in annual variation was drastically reduced right after the construction of the Saemankeum Sea Wall. Species richness in the phytoplankton community was also reduced due to the narrowed annual range of salinity, which would eliminate the mid-high salinity species from the Mankyeong Bridge monitoring point. Similarly, species diversity was decreased with increased dominance of the phytoplankton community after the construction. Between the two summer seasons during the present study, species diversity was higher in 2007 than in 2006, which might indicate the early stage of a gradual stabilization in the ecosystem including the phytoplankton community at the monitoring station. The phytoplankton community thus needs to be monitored on a long-term basis to identify indirect signals that can be used to assess the stability of the ecosystem in the young Saemankeum Lake.

• Proceedings of the KIEE Conference
• /
• 2001.07c
• /
• pp.1667-1669
• /
• 2001

The clack of Insulator, which results from internal or external surges such as electrical, mechanical, and thermal stress, might cause ground fault and a power failure without proper repairs. In order to minimize losses caused by a short-term or long-term power failure, it is necessary to detect the deteriorated insulator as early as possible. To do so, we will develop a new device, which can detect and trace an deteriorated insulator by monitoring its physical change the variation of frequency spectrum. This device will do so by finding a Periodic wave sharp (120 Hz), a peculiar wave generated by defused electricity.

• ETRI Journal
• /
• v.26 no.5
• /
• pp.391-396
• /
• 2004

In this paper, we propose a packet scheduling discipline called packet loss fair scheduling, in which the packet loss of each user from different real-time traffic is fairly distributed according to the quality of service requirements. We consider an orthogonal frequency division multiple access (OFDMA) system. The basic frame structure of the system is for the downlink in a cellular packet network, where the time axis is divided into a finite number of slots within a frame, and the frequency axis is segmented into subchannels that consist of multiple subcarriers. In addition, to compensate for fast and slow channel variation, we employ a link adaptation technique such as adaptive modulation and coding. From the simulation results, our proposed packet scheduling scheme can support QoS differentiations while guaranteeing short-term fairness as well as long-term fairness for various real-time traffic.

• Journal of Environmental Science International
• /
• v.9 no.4
• /
• pp.303-309
• /
• 2000

The relationship between air temperature and sea surface temperature and studied using the daily air temperature and sea surface temperature data for 25 years (1970~1994) at 9 coastal stations in Korea. Seasonal variations of air temperature have larger amplitudes than those of sea surface temperature. The seasonal variations of air temperature leads those of sea surface temperature by 2 to 3 weeks. The anomalies of sea surface temperature and air temperature with time scales more than 1 month are more ghighly correlated than those of short term, with time scales less than 1 month. Accumulated monthly anomalies of sea surface temperature and air temperature for 6 months shwoed higher correlation than the anomailes of each month. The magnitudes of sea surface temperature and air temperature anomalies are related with the duration of anomalies. Their magnitudes are large when the durations of anomalies are long.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.8
• /
• pp.917-923
• /
• 1999

This paper proposes an efficient method of hydro-thermal scheduling in coordination with head variation and hydraulically coupled plants using Evolutionary Programing(EP). Based on the EP technique, the proposed algorithm is capable of determining the global optimal solutions. The constraints such a power balance condition, water available condition and transmission losses are embedded and satisfied throughout the proposed EP approach. The effectiveness of the proposed approach is demonstrated on the test systems and compared to those of other method. The results show that the new approach obtains a more highly optimal solutions than the conventional other methods such as newton-raphson method, Dynamic Programming(DP), LU factorization.

• Journal of Korea Water Resources Association
• /
• v.53 no.4
• /
• pp.273-283
• /
• 2020

Quantitative forecasting of groundwater levels for the assessment of groundwater variation and vulnerability is very important. To achieve this purpose, various time series analysis and machine learning techniques have been used. In this study, we developed a prediction model based on LSTM (Long short term memory), one of the artificial neural network (ANN) algorithms, for predicting the daily groundwater level of 11 groundwater wells in Hankyung-myeon, Jeju Island. In general, the groundwater level in Jeju Island is highly autocorrelated with tides and reflected the effects of precipitation. In order to construct an input and output variables based on the characteristics of addressing data, the precipitation data of the corresponding period was added to the groundwater level data. The LSTM neural network was trained using the initial 365-day data showing the four seasons and the remaining data were used for verification to evaluate the fitness of the predictive model. The model was developed using Keras, a Python-based deep learning framework, and the NVIDIA CUDA architecture was implemented to enhance the learning speed. As a result of learning and verifying the groundwater level variation using the LSTM neural network, the coefficient of determination (R²) was 0.98 on average, indicating that the predictive model developed was very accurate.

• Ocean Science Journal
• /
• v.43 no.1
• /
• pp.1-7
• /
• 2008

Physical and biological environmental variations in the East Sea were investigated by analysing time-series of oceanographic data and meteorological indices. From 1971 to 2000, dominant periodicity in water temperature variations had two apparent periods of 3 to 4 years and of decades, especially in the southwestern part of the East Sea affected by the influence of inflowing Tsushima warm current. Fluctuating water temperature within a certain period appears to respond to El $Ni{\tilde{n}}o$ events with a time lag. It was found that there was a strong correlation between water temperature and El $Ni{\tilde{n}}o$ events with a time lag of 1.5 and 5.5 years for periods of 3 to 6 years and of decades, respectively. Corresponding with El $Ni{\tilde{n}}o$ events, water temperature variability also showed strong correlation with shift and/or changes in biological and chemical environments of nutrient concentrations, zooplankton biomass, and fisheries. However, there also occurred a short-term periodicity of water temperature variations. Within a period of 1 to 4 years, a relatively short-term cycle of water temperature variation had strong correlation with other climate indices such as Pacific Decadal Oscillation and monsoon index. After comparing coherence and phase spectrum between water temperature and different climate indices, we found that there was a shift of coherent periods to another climate index during the years when climate regime shift was reported.

• Journal of Korean Society for Atmospheric Environment
• /
• v.27 no.6
• /
• pp.692-702
• /
• 2011

For more effective indoor radon reduction policy and technique, we researched radon data analysis for some buildings in Seoul. Those buildings were categorized as dwelling, underground and office space and the variations of radon concentration and its sources were evaluated. The variations of radon concentrations of indoor space of buildings for a day were patterned specifically by dwelling habits and different environment. As for the new built apartments which were not yet moved in, their indoor radon concentrations were showed more than 3 times after applying interior assembly, and were 5 times higher than ones of rather old residences. As for the subway stations, the radon concentrations during off-run times were about 15% higher than run-times. 10% of radon seemed to be reduced by installation of platform screen doors. As for office space, radon concentrations during working hours were about 2.5 times higher than non-working hours. Plaster board are expected as a main source of radon for them. By radon measurement method for long-term, its data can be over estimated because it covers non-active time in office or public space. Therefore combination of short and long-term measurement method is required for effective and economic reduction. Furthermore importance of ventilation is requested as public information service for all dwelling space. And also standardization for radium content or radiation of radon is necessary.