• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.23-29
• /
• 2019

In this paper, a deep learning-based detection and classification using multi-band frequency signals is presented for detecting earthquakes prevalent in Korea. Based on an analysis of the previous earthquakes in Korea, it is observed that multi-band signals are appropriate for classifying earthquake signals. Therefore, in this paper, we propose a deep CNN (Convolutional Neural Network) using multi-band signals as training data. The proposed algorithm extracts the multi-band signals (Low/Medium/High frequency) by applying band pass filters to mel-spectrum of earthquake signals. Then, we construct three CNN architecture pipelines for extracting features and classifying the earthquake signals by a late fusion of the three CNNs. We validate effectiveness of the proposed method by performing various experiments for classifying the domestic earthquake signals detected in 2018.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.63.2-63.2
• /
• 2011

We describe the Infrared Medium-deep Survey (IMS), a survey of quasars in the early universe beyond z=5. IMS uses multi-wavelength archival data such as SDSS, CFHT-LS, UKIDSS, and SWIRE, which provide deep images over wide area enough for searching of high redshift bright quasars. In addition, we are carrying out J-band imaging survey with the depth of 23AB at UKIRT for up to 200 $deg^2$, of which 50 $deg^2$ is covered so far. For the quasar candidates at z~5.5, we are making observations with custom-made filters, which are more efficient to make robust quasar candidate samples in this redshift range. Because of the deeper survey depth and the unique methods, our IMS can provide a large number of high redshift quasars comparing with ongoing high redshift bright quasar survey. The high redshift quasars we confirm will give us with clues of the growth of super massive black holes and the metal enrichment history in the early universe.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.74.2-74.2
• /
• 2017

Faint quasars are important to test the possibility that quasars are the main contributor to the cosmic reionization. However, it has been difficult to find faint quasars due to the lack of deep, wide-field imaging data. In this poster, we present our efforts to find faint quasars in the ELAIS-N1 field through the deep data (iAB ~ 25) obtained by the Subaru Hyper Suprime-Cam (HSC) Strategic Program survey. To select reliable quasar candidate, we also use the near-infrared (NIR) data of the Infrared Medium-deep Survey (IMS) and the UKIRT Infrared Deep Sky Survey (UKIDSS) - Deep Extragalactic Survey (DXS). Using multiple-band color cuts, we select high redshift quasar candidates. To confirm them as high redshift quasars, candidates are observed by the SED camera for QUasars in EArly uNiverse (SQUEAN) instrument in several medium band filters that can sample the redshifted Lyman break efficiency. The quasar sample will be used to study the growth of BH and stellar mass, the relation between the quasar activity and the host galaxy, and their contribution to the cosmic re-ionization.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.1
• /
• pp.64.1-64.1
• /
• 2011

MIRIS (Multipurpose Infra-Red Imaging System), is a small infrared space telescope which is being developed by KASI, as the main payload of Science and Technology Satellite 3 (STSAT-3). Two wideband filters (I and H) of the MIRIS enables us to study the cosmic infrared background by detecting the absolute background brightness. The narrow band filter for Paschen ${\alpha}$ emission line observation will be employed to survey the Galactic plane for the study of warm ionized medium and interstellar turbulence. The opto-mechanical design of the MIRIS is optimized to operate around 200K for the telescope, and the cryogenic temperature around 90K for the sensor in the orbit, by using passive and active cooling technique, respectively. The engineering and qualification model of the MIRIS has been fabricated and successfully passed various environmental tests, including thermal, vacuum, vibration and shock tests. The flight model was also assembled and is in the process of system optimization to be launched in 2012 by a Russian rocket. The mission operation scenario and the data reduction software is now being developed. After the successful mission of FIMS (the main payload of STSAT-1), MIRIS is the second Korean space telescope, and will be an important step towards the future of Korean space astronomy.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.