http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Robust Real-time Detection of Abandoned Objects using a Dual Background Model
( Hyeseung Park ),( Seungchul Park ),( Youngbok Joo ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.2
Detection of abandoned objects for smart video surveillance should be robust and accurate in various situations with low computational costs. This paper presents a new algorithm for abandoned object detection based on the dual background model. Through the template registration of a candidate stationary object and presence authentication methods presented in this paper, we can handle some complex cases such as occlusions, illumination changes, long-term abandonment, and owner’s re-attendance as well as general detection of abandoned objects. The proposed algorithm also analyzes video frames at specific intervals rather than consecutive video frames to reduce the computational overhead. For performance evaluation, we experimented with the algorithm using the well-known PETS2006, ABODA datasets, and our video dataset in a live streaming environment, which shows that the proposed algorithm works well in various situations.
다변량 입력이 딥러닝 기반 저수율 예측에 미치는 영향 분석과 중장기 예측 방안
박혜승 ( Hyeseung Park ),윤종욱 ( Jongwook Yoon ),이호준 ( Hojun Lee ),양현호 ( Hyunho Yang ) 한국정보처리학회 2024 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.13 No.4
지역 저수지들은 농업용수 공급의 중요한 수원공으로 가뭄과 같은 극단적 기후 조건을 대비하여 안정적인 저수율 관리가 필수적이다. 저수율 예측은 국지적 강우와 같은 지역적 기후 특성뿐만 아니라 작부시기를 포함하는 계절적 요인 등에 크게 영향을 받기 때문에 적절한 예측 모델을 선정하는 것만큼 입/출력 데이터 간 상관관계 파악이 무엇보다 중요하다. 이에 본 연구에서는 1991년부터 2022년까지의 전라북도 400여 개 저수지의 광범위한 다변량 데이터를 활용하여 각 저수지의 복잡한 수문학·기후학적 환경요인을 포괄적으로 반영한 저수율 예측 모델을 학습 및 검증하고, 각 입력 특성이 저수율 예측 성능에 미치는 영향력을 분석하고자 한다. 신경망 구조에 따른 저수율 예측 성능 개선이 아닌 다변량의 입력 데이터와 예측 성능 간의 상관관계에 초점을 맞추기 위하여 실험에 사용된 예측 모델로 합성곱신경망 또는 순환신경망과 같은 복잡한 형태가 아닌 완전연결계층, 배치정규화, 드롭아웃, 활성화 함수 등의 조합으로 구성된 기본적인 순방향 신경망을 채택하였다. 추가적으로 대부분의 기존 연구에서는 하루 단위의 단기 예측 성능만을 제시하고 있으며 이러한 단기 예측 방식은 10일, 한 달 단위 등 중장기적 예측이 필요한 실무환경에 적합하지 않기 때문에, 본 연구에서는 하루 단위 예측값을 다음 입력으로 사용하는 재귀적 방식을 통해 최대 한 달 뒤 저수율 예측 성능을 측정하였다. 실험을 통해 예측기간에 따른 성능 변화 양상을 파악하였으며, Ablation study를 바탕으로 예측 모델의 각 입력 특성이 전체 성능에 끼치는 영향을 분석하였다. Local reservoirs are crucial sources for agricultural water supply, necessitating stable water level management to prepare for extreme climate conditions such as droughts. Water level prediction is significantly influenced by local climate characteristics, such as localized rainfall, as well as seasonal factors including cropping times, making it essential to understand the correlation between input and output data as much as selecting an appropriate prediction model. In this study, extensive multivariate data from over 400 reservoirs in Jeollabuk-do from 1991 to 2022 was utilized to train and validate a water level prediction model that comprehensively reflects the complex hydrological and climatological environmental factors of each reservoir, and to analyze the impact of each input feature on the prediction performance of water levels. Instead of focusing on improvements in water level performance through neural network structures, the study adopts a basic Feedforward Neural Network composed of fully connected layers, batch normalization, dropout, and activation functions, focusing on the correlation between multivariate input data and prediction performance. Additionally, most existing studies only present short-term prediction performance on a daily basis, which is not suitable for practical environments that require medium to long-term predictions, such as 10 days or a month. Therefore, this study measured the water level prediction performance up to one month ahead through a recursive method that uses daily prediction values as the next input. The experiment identified performance changes according to the prediction period and analyzed the impact of each input feature on the overall performance based on an Ablation study.
한국어 ‘셀프(self)’ 합성명사의 유형과 ‘자기(自己)’, ‘자가(自家)’와의 의미 관계
박혜승(Hyeseung Park) 사단법인 한국언어학회 2021 언어학 Vol.- No.90
This paper discusses how to classify compound nouns composed of Korean ‘self’ and noun combinations according to the meaning of ‘self’, and examines the difference in meaning between compound nouns combined with ‘jagi’ and ‘jaga’. Discussions related to ‘self’ in Korean have focused on revealing the attributes of the noun that follows rather than the meaning of ‘self’. On the other hands, it was not possible to clearly explain the meaning of ‘self’ in sentences such as “water is self.” To complement this, two types of ‘self’ compound nouns were presented as type ‘self’ and type ‘self(-service)’. In order to examine which nouns are frequently combined with ‘self’ and ‘self(-service)’, the distribution patterns of ‘jagi’ and ‘jaga’ compound nouns are analyzed together, and areas overlapping each independent semantic domain was separated. As a result, the compound nouns ‘jagi’ was mainly responsible for the domains of ‘emotions’ or ‘attitude’ of the agent, and the compound noun ‘jaga’ formed a semantic category related to the ‘scientific operation’ or the ‘rational judgment’ of it. On the other hands, ‘self’ revealed that it occupies the most extensive area including two compound nouns.
The first co-infection of scrub typhus and SFTS
( Hyeseung Yoo ),( Yoon Soo Park ),( Yong Kyun Cho ),( Song Mi Moon ) 대한내과학회 2015 대한내과학회 추계학술대회 Vol.2015 No.1
As ticks are excellent vectors for disease transmission, tick-borne diseases are common. And, a single tick bite can transmit multiple pathogens. Accordingly, it leads to atypical presentations of some classic tick-borne diseases, such as high fever, myalgia, arthralgia, and gastrointestinal symptoms. When tick-bite history is evident, scrub typhus is the first disease for differential diagnosis in Korea due to its high prevalence rate. Beside the scrub typhus, Severe fever with Thrombocytopenia Syndrome (SFTS) is also needed to be considered in Korea. SFTS is an emerging infectious disease caused by a novel tick-borne Phlebovirus of Bunyaviridae, first identified in China in 2010. In South Korea, the first patient was identified in May, 2013 and after then, 36 patients with SFTS were found and 17 of them were fatal cases. The clinical symptoms of SFTS are high fever, vomiting, diarrhea, thrombocytopenia, leukopenia and multiple organ failure and disseminated intravascular coagulation, resulting in death 7 14 days after the onset of the illness. We report the case of a 78-year-old woman who had sudden onset fever 5 days before her admission. Her condition did not improve after antibiotic treatment and she was transferred to Gil hospital. She had 2 scab formed wounds on the anterior neck area and on the abdomen. Tick-borne disease was suspected and her sera were tested for SFTSV and O. tsutsugmushi Ab. Co-infection of scrub typhus (positive 1: 5120) and SFTS was diagnosed. Her condition improved with doxycycline treatment with supportive care. This is the first case report of co infection of scrub typhus and SFTS. As some of the tick-borne diseases have affirmative treatment choice such as doxycycline for scrub typhus, anaplasmosis and Ehrlichiosis, in patient with tick bite, co-infection of tick-borne diseases should be considered and all treatment options should be taken into account without delay.
박선우(Sunwoo Park),조성문(Sungmoon Cho),한혜승(Hyeseung Hahn) 한국음운론학회 2016 음성·음운·형태론 연구 Vol.22 No.1
The purpose of this paper is to investigate variations of monophthongization and acoustical characteristics of /ɨi/ found in Seoul Corpus. Monophthongization occurs in 93.04% of a total of 2,370 tokens and in higher than 99% of the cases with onsets and also of non-initial position in a word. However, only 31.82% of word initial tokens are monophthongized, which supports the findings that Seoul Korean still retains /ɨi/ as a diphthong, though only in some restricted contexts. 94.40% of monophthongized /ɨi/ tokens are realized as [i] except for the cases of genitive case marking which mostly show [e]. In word initial position, though, 61.74% of the monophthongized diphthong tokens are realized as [ɨ] and in the other cases as [i]. This result assumes that the phonological characteristics of /ɨi/ are totally different in terms of its position (word initial or non-initial) or its grammatical role as a genitive case marker.