특징적 단어 집합을 활용한 모바일 기기 내 성별 예측 프레임워크

김소이(Solee Kim),최예림(Yerim Choi),김윤정(Yoonjung Kim),박규연(Kyuyon Park),김길호(Kilho Kim),박종헌(Jonghun Park) 한국정보과학회 2015 한국정보과학회 학술발표논문집 Vol.2015 No.6

블록체인 기반의 화장품 성분 정보 검증 기법

박솔이(Solee Park),이기현(Gihyun Lee),박강산(Kangsan park),김현곤(Hyungon Kim) 한국통신학회 2018 한국통신학회 학술대회논문집 Vol.2018 No.11

특징적 단어 및 이모티콘 집합을 활용한 모바일 기기 내 성별 예측 프레임워크

김소이(Solee Kim),최예림(Yerim Choi),김윤정(Yoonjung Kim),박규연(Kyuyon Park),박종헌(Jonghun Park) 한국정보과학회 2015 정보과학회 컴퓨팅의 실제 논문지 Vol.21 No.11

사용자의 인구통계학적 정보는 추천 시스템과 같은 개인화 서비스 발달에 도움이 되며, 모바일 사용 데이터는 사용자의 인구통계학적 정보 예측에 활용될 수 있다. 특히 텍스트 데이터는 성별 예측에 효과적인 것으로 알려져 있지만, 모바일 텍스트 데이터는 프라이버시 이슈가 존재하여 그 활용이 제한되고 있다. 본 연구에서는 디바이스 내 예측 방법론을 제안하여 모바일 텍스트 데이터를 사용하면서 프라이버시 이슈를 최소화는 동시에 사용자의 성별을 효과적으로 예측하고자 한다. 우선, 성별에 따른 특징이 반영된 웹문서를 수집하여 각 성별에 따른 특징적 단어 집합과 특징적 이모티콘 집합을 구성한다. 단어 집합과 이모티콘 집합을 디바이스 내에서 사용자의 모바일 데이터와 비교하여 성별을 각각 예측하고, 두 예측 결과를 앙상블하여 최종적인 성별 예측 결과를 도출한다. 피실험자들의 모바일 텍스트 데이터를 사용하여 성별 예측 실험을 수행하였으며 제안 방법론의 우수한 성능을 확인하였다. User demographic information is necessary in order to improve the quality of personalized services such as recommendation systems. Mobile data, especially text data, is known to be effective for prediction of user demographic information. However, mobile text data has privacy issues so that its utilization is limited. In this regard, we introduce an on-device gender prediction framework utilizing mobile text data while minimizing the privacy issue. Discriminative word and emoticon sets of each gender are constructed from web documents written by authors of each gender. After gender prediction is performed by comparing discriminative word and emoticon sets with a user"s mobile text data, an ensemble method that combines two prediction results draws a final result. From experiments conducted on real-world mobile text data, the proposed on-device framework shows promising results for gender prediction.

Effects of Exercise Training on Body composition and Obesity-related Cytokines Expression in Elderly Subjects

( Kijin Kim ),( Nayoung Ahn ),( Jusik Park ),( Suryun Jung ),( Sungwook Kim ),( Kwangbae Park ),( Solee Park ),( Kyuho Lee ),( Kanghyun Sung ) 대한운동사협회 2016 대한운동사협회 워크숍자료집 Vol.45 No.-

Elemental Sulfur and Molybdenum Disulfide Composites for Li–S Batteries with Long Cycle Life and High-Rate Capability

Dirlam, Philip T.,Park, Jungjin,Simmonds, Adam G.,Domanik, Kenneth,Arrington, Clay B.,Schaefer, Jennifer L.,Oleshko, Vladimir P.,Kleine, Tristan S.,Char, Kookheon,Glass, Richard S.,Soles, Christopher American Chemical Society 2016 ACS APPLIED MATERIALS & INTERFACES Vol.8 No.21

<P>The practical implementation of Li-S technology has been hindered by short cycle life and poor rate capability owing to deleterious effects resulting from the varied solubilities of different Li polysulfide redox products. Here, we report the preparation and utilization of composites with a sulfur-rich matrix and molybdenum disulfide (MoS2) particulate inclusions as Li-S cathode materials with the capability to mitigate the dissolution of the Li polysulfide redox products via the MoS2 inclusions acting as 'polysulfide anchors'. In situ composite formation was completed via a facile, one-pot method with commercially available starting materials. The composites were afforded by first dispersing MoS2 directly in liquid elemental sulfur (S-8) with sequential polymerization of the sulfur phase via thermal ring opening polymerization or copolymerization via inverse vulcanization. For the practical utility of this system to be highlighted, it was demonstrated, that the composite formation methodology was amenable to larger scale processes with composites easily prepared in 100 g batches. Cathodes fabricated with the high sulfur content composites as the active material afforded Li-S cells that exhibited extended cycle lifetimes of up to 1000 cycles with low capacity decay (0.07% per cycle) and demonstrated exceptional rate capability with the delivery of reversible capacity up to 500 mAh/g at 5 C.</P>

Effects of intermittent ladder-climbing exercise training on mitochondrial biogenesis and endoplasmic reticulum stress of the cardiac muscle in obese middle-aged rats

Kijin Kim,Nayoung Ahn,Suryun Jung,Solee Park 대한생리학회-대한약리학회 2017 The Korean Journal of Physiology & Pharmacology Vol.13 No.3

The aim of this study is to investigate the effects of intermittent ladder-climbing exercise training on mitochondrial biogenesis and ER stress of the cardiac muscle in high fat diet-induced obese middle-aged rats. We induced obesity over 6 weeks of period in 40 male Sprague-Dawley rats around 50 weeks old, and were randomly divided into four experimental groups: chow, HFD, exercise+HFD, and exercise+chow. The exercising groups underwent high-intensity intermittent training using a ladder-climbing and weight exercise 3 days/week for a total of 8 weeks. Highfat diet and concurrent exercise resulted in no significant reduction in body weight but caused a significant reduction in visceral fat weight (p<0.05). Expression of PPARδ increased in the exercise groups and was significantly increased in the high-fat diet+exercise group (p<0.05). Among the ER stress-related proteins, the expression levels of p-PERK and CHOP, related to cardiac muscle damage, were significantly higher in the cardiac muscle of the high-fat diet group (p<0.05), and were significantly reduced by intermittent ladder-climbing exercise training (p<0.05). Specifically, this reduction was greater when the rats underwent exercise after switching back to the chow diet with a reduced caloric intake. Collectively, these results suggest that the combination of intermittent ladder-climbing exercise training and a reduced caloric intake can decrease the levels of ER stress-related proteins that contribute to cardiac muscle damage in obesity and aging. However, additional validation is required to understand the effects of these changes on mitochondrial biogenesis during exercise.

모바일 사용자의 성별 예측을 위한 식별 및 인기 단어 집합 기반 2단계 기기 내 분석

최예림(Yerim Choi),박규연(Kyuyon Park),김소이(Solee Kim),박종헌(Jonghun Park) 한국전자거래학회 2016 한국전자거래학회지 Vol.21 No.1

모바일 기기 데이터를 활용한 분석에서 사용자의 프라이버시를 보호하는 것이 주요한 이슈로 대두됨에 따라 데이터를 외부로 전송하지 않고 모바일 기기 안에서 분석을 수행하는 기기내 분석이 주목 받고 있다. 기기 내 분석을 활용하면 문자 메시지, 검색 단어, 북마크, 연락처등 매우 개인적이지만 성별 구분에 효과적이라고 알려진 모바일 텍스트를 이용한 성별 예측이 가능하며, 사전에 선정된 단어들의 집합을 모바일 기기로 전송하여 이 단어들과 모바일 텍스트를 비교를 통해 성별을 예측하는 단어 비교 방식을 이용하면 모바일 기기의 제한된 자원 문제를 극복할 수 있다. 특히, 확실한 근거를 이용하여 필터링 한 후 예측을 수행하면 정확도를 극대화하고 복잡도를 낮출 수 있다. 따라서 본 논문에서는 단어의 식별력과 인기도를 순차적으로 고려하는 2단계의 기기 내 성별 예측 방법을 제안한다. 구체적으로, 제안하는 방법론은 소수의 높은 식별력을 가지는 단어를 이용하여 전체 사용자의 성별을 예측하고 이어서 인기도가 높은 단어를 활용하여 앞서 예측이 되지 않은 사용자의 성별을 예측한다. 실제 데이터를 이용한 실험에서 제안하는 방법론은 비교 방법론보다 우수한 성능을 나타내었다. As respecting one’s privacy becomes an important issue in mobile device data analysis, on-device analysis is getting attention, in which the data analysis is conducted inside a mobile device without sending data from the device to outside. One possible application of the on-device analysis is gender prediction using text data in mobile devices, such as text messages, search keyword, website bookmarks, and contact, which are highly private, and the limited computing power of mobile devices can be addressed by utilizing the word comparison method, where words are selected beforehand and delivered to a mobile device of a user to determine the user’s gender by matching mobile text data and the selected words. Moreover, it is known that performing prediction after filtering instances using definite evidences increases accuracy and reduces computational complexity. In this regard, we propose a two-phase approach to on-device gender prediction, where both discriminability and popularity of a word are sequentially considered. The proposed method performs predictions using a few highly discriminative words for all instances and popular words for unclassified instances from the previous prediction. From the experiments conducted on real-world dataset, the proposed method outperformed the compared methods.

Effects of intermittent ladder-climbing exercise training on mitochondrial biogenesis and endoplasmic reticulum stress of the cardiac muscle in obese middle-aged rats

Kim, Kijin,Ahn, Nayoung,Jung, Suryun,Park, Solee The Korean Society of Pharmacology 2017 The Korean Journal of Physiology & Pharmacology Vol.21 No.6

The aim of this study is to investigate the effects of intermittent ladder-climbing exercise training on mitochondrial biogenesis and ER stress of the cardiac muscle in high fat diet-induced obese middle-aged rats. We induced obesity over 6 weeks of period in 40 male Sprague-Dawley rats around 50 weeks old, and were randomly divided into four experimental groups: chow, HFD, exercise+HFD, and exercise+chow. The exercising groups underwent high-intensity intermittent training using a ladder-climbing and weight exercise 3 days/week for a total of 8 weeks. High-fat diet and concurrent exercise resulted in no significant reduction in body weight but caused a significant reduction in visceral fat weight (p<0.05). Expression of $PPAR{\delta}$ increased in the exercise groups and was significantly increased in the high-fat diet+exercise group (p<0.05). Among the ER stress-related proteins, the expression levels of p-PERK and CHOP, related to cardiac muscle damage, were significantly higher in the cardiac muscle of the high-fat diet group (p<0.05), and were significantly reduced by intermittent ladder-climbing exercise training (p<0.05). Specifically, this reduction was greater when the rats underwent exercise after switching back to the chow diet with a reduced caloric intake. Collectively, these results suggest that the combination of intermittent ladder-climbing exercise training and a reduced caloric intake can decrease the levels of ER stress-related proteins that contribute to cardiac muscle damage in obesity and aging. However, additional validation is required to understand the effects of these changes on mitochondrial biogenesis during exercise.

스마트 기기의 멀티 모달 로그 데이터를 이용한 사용자 성별 예측 기법 연구

김윤정(Yoonjung Kim),최예림(Yerim Choi),김소이(Solee Kim),박규연(Kyuyon Park),박종헌(Jonghun Park) 한국전자거래학회 2016 한국전자거래학회지 Vol.21 No.1

스마트 기기 사용자의 성별 정보는 성공적인 개인화 서비스를 위해 중요하며, 스마트기기로부터 수집된 멀티 모달 로그 데이터는 사용자의 성별 예측에 중요한 근거가 된다. 하지만 각 멀티 모달 데이터의 특성에 따라 다른 방식으로 성별 예측을 수행해야 한다. 따라서 본 연구에서는 스마트 기기로부터 발생한 로그 데이터 중 텍스트, 어플리케이션, 가속도 데이터에 기반한 각기 다른 분류기의 예측 결과를 다수결 방식으로 앙상블하여 최종 성별을 예측하는 기법을 제안한다. 텍스트 데이터를 이용한 분류기는 데이터 유출에 의한 사생활 침해 문제를 최소화하기 위해 웹 문서로부터 각 성별의 특징적 단어 집합을 도출하고 이를 기기로 전송하여 사용자의 기기 내에서 성별 분류를 수행한다. 어플리케이션 데이터에 기반한 분류기는 사용자가 실행한 어플리케이션들에 성별을 부여하고 높은 비율을 차지하는 성별로 사용자의 성별을 예측한다. 가속도 기반 분류기는 성별에 따른 사용자의 가속도 데이터 인스턴스를 학습한 SVM 모델을 사용하여 주어진 성별을 분류한다. 자체 제작한 안드로이드 어플리케이션을 통해 수집된 실제 스마트 기기 로그 데이터를 사용하여 제안하는 기법을 평가하였으며 그 결과 높은 예측 성능을 보였다. Gender information of a smart device user is essential to provide personalized services, and multi-modal data obtained from the device is useful for predicting the gender of the user. However, the method for utilizing each of the multi-modal data for gender prediction differs according to the characteristics of the data. Therefore, in this study, an ensemble method for predicting the gender of a smart device user by using three classifiers that have text, application, and acceleration data as inputs, respectively, is proposed. To alleviate privacy issues that occur when text data generated in a smart device are sent outside, a classification method which scans smart device text data only on the device and classifies the gender of the user by matching text data with predefined sets of word. An application based classifier assigns gender labels to executed applications and predicts gender of the user by comparing the label ratio. Acceleration data is used with Support Vector Machine to classify user gender. The proposed method was evaluated by using the actual smart device log data collected from an Android application. The experimental results showed that the proposed method outperformed the compared methods.