http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Detection of Moving Direction using PIR Sensors and Deep Learning Algorithm
Jiyoung Woo(우지영),Jaeseok Yun(윤재석) 한국컴퓨터정보학회 2019 韓國컴퓨터情報學會論文誌 Vol.24 No.3
In this paper, we propose a method to recognize the moving direction in the indoor environment by using the sensing system equipped with passive infrared (PIR) sensors and a deep learning algorithm. A PIR sensor generates a signal that can be distinguished according to the direction of movement of the user. A sensing system with four PIR sensors deployed by 45° increments is developed and installed in the ceiling of the room. The PIR sensor signals from 6 users with 10-time experiments for 8 directions were collected. We extracted the raw data sets and performed experiments varying the number of sensors fed into the deep learning algorithm. The proposed sensing system using deep learning algorithm can recognize the users’ moving direction by 99.2 %. In addition, with only one PIR senor, the recognition accuracy reaches 98.4%.
Profane or Not: Improving Korean Profane Detection using Deep Learning
( Jiyoung Woo ),( Sung Hee Park ),( Huy Kang Kim ) 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.1
Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.
우지영(Jiyoung Woo),김휘강(Huy Kang Kim) 한국정보보호학회 2017 情報保護學會誌 Vol.27 No.4
온라인 게임은 가상 재화를 현금화할 수 있게 되면서 여러 가지 부정 행위가 발생하고 있다. 그 중 대표적인 것이 사용자 대신에 게임 플레이를 해주는 게임 봇(game bot)이다. 이러한 게임 봇은 사용자는 물론 게임회사에 큰 해를 입히고 있다. 본 연구에서는 게임 봇을 탐지하는 기존의 연구 중 사용자의 행동 로그를 분석하는, 데이터 분석 기반의 연구를 조사하였다. 관련 연구를 사용자의 행위를 중심으로 구분하였고, 향후 연구가 나아갈 방향에 대해 첨언하였다.
온라인 게임 결제 데이터 분석 기반의 이상거래 탐지 모델
우지영(Jiyoung Woo),김하나(Hana Kim),곽병일(Byung Il Kwak),김휘강(Huy Kang Kim) 한국정보보호학회 2016 情報保護學會誌 Vol.26 No.3
소액결제에 대한 규제 완화로 이와 관련한 사기가 급증하고 있으며, 특히 소액결제가 대부분을 차지하는 온라인게임 산업은 관련 사기로 인한 피해가 증가하고 있다. 온라인 게임의 소액결제 사기는 단순히 금액에 대한 피해뿐만이 아니라 회사 브랜드에도 영향을 미치며, 나아가 고객 이탈로 이어질 수 있다. 소액결제 사기를 방지하기 위해 게임 산업에서도 이상거래탐지 시스템이 요구되고 있다. 본 연구는 게임 사용자의 결제 패턴을 분석하여 이상거래를 탐지할 수 있는 머신러닝 기반의 이상거래 탐지 모델을 제시하며, 제안하는 모델을 글로벌 온라인 게임에 적용한 사례를 소개한다.
의료 웹포럼에서의 텍스트 분석을 통한 정보적 지지 및 감성적 지지 유형의 글 분류 모델
우지영(Jiyoung Woo),이민정(Min-Jung Lee),Yungchang Ku 한국IT서비스학회 2012 한국IT서비스학회지 Vol.11 No.S
In the medical web forum, people share medical experience and information as patients and patents’ families. Some people search medical information written in non-expert language and some people offer words of comport to who are suffering from diseases. Medical web forums play a role of the informative support and the emotional support. We propose the automatic classification model of articles in the medical web forum into the information support and emotional support. We extract text features of articles in web forum using text mining techniques from the perspective of linguistics and then perform supervised learning to classify texts into the information support and the emotional support types. We adopt the Support Vector Machine (SVM), Naive-Bayesian, decision tree for automatic classification. We apply the proposed mode to the HealthBoards forum, which is also one of the largest and most dynamic medical web forum.
( Min Seok Woo ),( Jiyoung Park ),( Seong-ho Ok ),( Miyeong Park ),( Ju-tae Sohn ),( Man Seok Cho ),( Il-woo Shin ),( Yeon A Kim ) 대한통증학회 2021 The Korean Journal of Pain Vol.34 No.1
Background: Prolotherapy is a proliferation therapy as an alternative medicine. A combination of dextrose solution and lidocaine is usually used in prolotherapy. The concentrations of dextrose and lidocaine used in the clinical field are very high (dextrose 10%-25%, lidocaine 0.075%-1%). Several studies show about 1% dextrose and more than 0.2% lidocaine induced cell death in various cell types. We investigated the effects of low concentrations of dextrose and lidocaine in fibroblasts and suggest the optimal range of concentrations of dextrose and lidocaine in prolotherapy. Methods: Various concentrations of dextrose and lidocaine were treated in NIH- 3T3. Viability was examined with trypan blue exclusion assay and 3-(4,5-dimethylthiazol- 2-yl)-2,5-diphenyltetrazolium bromide assay. Migration assay was performed for measuring the motile activity. Extracellular signal-regulated kinase (Erk) activation and protein expression of collagen I and α-smooth muscle actin (α-SMA) were determined with western blot analysis. Results: The cell viability was decreased in concentrations of more than 5% dextrose and 0.1% lidocaine. However, in the concentrations 1% dextrose (D1) and 0.01% lidocaine (L0.01), fibroblasts proliferated mildly. The ability of migration in fibroblast was increased in the D1, L0.01, and D1 + L0.01 groups sequentially. D1 and L0.01 increased Erk activation and the expression of collagen I and α-SMA and D1 + L0.01 further increased. The inhibition of Erk activation suppressed fibroblast proliferation and the synthesis of collagen I. Conclusions: D1, L0.01, and the combination of D1 and L0.01 induced fibroblast proliferation and increased collagen I synthesis via Erk activation.