• The Journal of the Acoustical Society of Korea
• /
• v.41 no.5
• /
• pp.518-524
• /
• 2022

In this paper, we propose a method for combining convolutional neural networks and attention mechanism to improve the recognition performance of emotional stress from Electroencephalogram (EGG) signals. In the proposed method, EEG signals are decomposed into five frequency domains, and spatial information of EEG features is obtained by applying a convolutional neural network layer to each frequency domain. As a next step, salient frequency information is learned in each frequency band using a gate transformer-based attention mechanism, and complementary frequency information is further learned through inter-frequency mapping to reflect it in the final attention representation. Through an EEG stress recognition experiment involving a DEAP dataset and six subjects, we show that the proposed method is effective in improving EEG-based stress recognition performance compared to the existing methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.589-591
• /
• 2002

본 연구에서는 영상안에서의 중요한 객체정보를 검출하기 위한 전처리 과정으로 효율적인 색상정보 정규화에 의한 영역분석 방법을 제안한다. 다중색상 정규화는 기존의 화소내 색상성분간의 정규화와 모든 화소에 대한 성분별 정규화를 복합적으로 사용함으로써, 객체의 영역들이 갖는 고유 색상성분의 분포를 좀더 특정 공간에 집중시키고 영상분할을 용이하게 한다. 이러한 방법의 효과를 입증하기 위해 가상의 입력영상을 제작하여 기존의 알고리즘과 본 논문에서의 방법을 함께 적용, 비교평가한다.

• Journal of Internet Computing and Services
• /
• v.19 no.1
• /
• pp.67-76
• /
• 2018

This paper addresses the problem of efficient processing of region monitoring queries. The centralized methods used for existing region monitoring query processing assumes that the mobile object periodically sends location-updates to the server and the server continues to update the query results. However, a large amount of location updates seriously degrade the system performance. Recently, some distributed methods have been proposed for region monitoring query processing. In the distributed methods, the server allocates to all objects i) a resident domain that is a subspace of the workspace, and ii) a number of nearby query regions. All moving objects send location updates to the server only when they leave the resident domain or cross the boundary of the query region. In order to allocate the resident domain to the moving object along with the nearby query region, we use a query index structure that is constructed by splitting the workspace recursively into equal halves. However, However, the above index structure causes unnecessary division, resulting in deterioration of system performance. In this paper, we propose an adaptive split method to reduce unnecessary splitting. The workspace splitting is dynamically allocated i) considering the spatial relationship between the query region and the resultant subspace, and ii) the distribution of the query region. We proposed an enhanced QR-tree with a new splitting method. Through a set of simulations, we verify the efficiency of the proposed split methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.141-144
• /
• 2018

비디오 압축에서, 변환은 데이터를 공간 영역에서 주파수 영역으로 변환 함으로써 에너지 압축에서 중요한 역할을 수행한다. HEVC(High Efficiency Video Coding)에서는 DCT-II(Discrete Cosine Transform type-II)를 사용하여 잔차신호 변환을 수행한다. DCT-II는 픽셀간 상관도가 높은 신호일수록 높은 에너지 집중도를 보이지만, 픽셀간 상관도가 비교적 낮은 블록일수록 낮은 에너지 집중도를 보인다. 본 논문에서는 DST-VII(Discrete Sine Transform type-VII) 및 잔차신호 플리핑을 사용하여 다양한 변환 방법으로 영상을 부호화 및 복호화 하는 알고리즘에 대해 제안한다. 다양한 변환 방법은 부호화기에서 블록단위로 1 가지를 선택하여 비트스트림으로 선택된 방법에 대한 정보를 전송한다. 제안된 방법은 HEVC 대비 약 2.47%의 BD-rate 감소를 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.29-32
• /
• 2011

최근 GPS를 탑재한 스마트 기기의 보급으로 인해 사용자의 위치 정보를 이용한 위치기반서비스(LBS)가 많은 관심 속에 급속도로 성장하고 있다. 대부분의 위치기반서비스는 사용자의 위치를 바탕으로 주변의 유용한 정보를 제공하고 있으며 이러한 사용자 주변의 유용한 정보를 효율적으로 검색하기 위해서는 공간 데이터에 대한 색인 기법이 필요하다. 그러나 기존 공간 색인은 대부분 중앙 집중식 환경에서 연구가 진행되었고 분산 스토리지 환경에 대한 연구는 미흡하다. 따라서 본 연구는 서비스 성장과 더불어 서비스 영역이 확대됨에 따른 대용량 공간 데이터 환경에서 효율적인 공간 데이터 검색을 지원하는 그리드 기반 분산 색인 기법을 제안한다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.1
• /
• pp.1-8
• /
• 2010

Noise removal methods for noisy images have been studied a lot in the domain of spatial and transform filtering. Low pass filtering was initially applied in the spatial domain. Recently, discrete wavelet transform has widely used for image denoising as well as image compression due to an excellent energy compaction and a property of multiresolution. In this paper, Gabor cosine and sine transform which is considered as human visual filter is applied to image denoising areas using soft thresholding technique. GCST is compared with excellent wavelet transform which uses existing soft thresholding methods from PSNR point of view. Resultant images removed noises are also visually compared. Experimental results with adding four different standard deviation levels of Gaussian distributed noises to real images show that the proposed transform has better PSNR performance of a maximum of 1.18 dB and visible perception than wavelet transform.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.420-424
• /
• 2016

Recently, with the development of Internet technology and multi-media technology, the Internet is going to develop in many areas, a new application areas. In particular, in the area of education, has made a Epoch-making development in the Internet applications, it has presented the instructional methods of the new paradigm. Study using the online learning, instructional method of a conventional traditional new proposal that deviates from the off-line teaching, Unlike the existing off-line learning, without being bound by time and space, in terms of anytime, anywhere it is possible to attend the lecture, is a very efficient learning. Online lectures Despite many advantages, and containing a number of problems. In terms of space of the learning is performed on-line, there is a disadvantage that the student management and learning, the reliability of evaluation missing number. In this study, out of such a variety of problems, concentration to induce an active learning attitude of learners, learners of learning who attempt to increase the reliability and using the face detection system of attendance learning It proposed a degree system.

• Therapeutic Science for Rehabilitation
• /
• v.6 no.1
• /
• pp.11-23
• /
• 2017

Spatial neglect is a neurological disorder following stroke, a lesion that usually affects the right hemisphere, fail to process or attention on the contralateral side of body and space. Functional neuroimaging studies report that spatial neglect is associated with lesions of large middle cerebral artery, perisylvian network and attention network. Spatial neglect is associated with a poor outcome. For optimal diagnosis and intervention, Types and theories of spatial neglect should be considered, in addition to clinical assessment with the conventional test and functional test. The treatment for spatial neglect could be consist of top-down approaches and bottom-up approaches. Recent trends in rehabilitation intervention for spatial neglect have reported prism adaptation.

• The Journal of the Korea Contents Association
• /
• v.18 no.1
• /
• pp.587-595
• /
• 2018

This research aims to analyze the importance-performance among multiplex cinema selection attributes. Therefore, we collected data for visitors who visited the multiplex cinema and want to watch movies. Of the various multiplex cinema selection attributes, four factors were deduced that includes: major services, human services, physical environment, auxiliary services using exploratory factor analysis. In the quadrant I, the area of 'Concentrate Here' was 'diversity of screening time', 'diversity of movie genre', 'convenience of mobile app use', 'size and convenience of parking facility'. In the quadrant II, 'Keep up the Good Work' area was 'convenience of website booking', 'discounts through card partnerships', 'employee friendliness', 'accurate employee information delivery', 'comfortable seating', 'screen size', 'cinematic sound quality', and 'convenience of traffic' etc. The quadrant III, 'Low Priority' appeared to be 'membership system', 'tidiness of staff attire', 'resting space for waiting time', 'accessibility to the neighboring area', 'diversity of the snack corner', and 'overall cleanliness' etc. The quadrant IV, 'Possible Overkill' was 'appropriateness of the auditorium temperature' and 'service proficiency'.

• Journal of the Economic Geographical Society of Korea
• /
• v.18 no.3
• /
• pp.335-347
• /
• 2015

Music industry is considered as a creative industry, which tends to locate within a city. However, there is very few paper analysing spatial patterns of music industry in Korea. This study aims to understand music industry's value chain and its location pattern; whether it is clustered or dispersed. In detail, music industry contains five sub-industry: planning, manufacturing, distribution, sales and performance. Locational pattern of each sub-industry is tested by GIS and hot spot analysis. There are several findings from this research. First, value chain of music industry make clusters and have a spatial autocorrelation. Second, the result shows that music industry makes a hotspot area at Gangnam, Guro, Mapo and Jongro-Junggu.