Cost-Effective Algae Control in the Coastal Waters of the Korean Peninsula

Sujin Choi(최수진) 한국환경정책학회 2017 環境政策 Vol.25 No.2

코어 다중가공에서 공구마모 예측을 위한 기계학습 데이터 분석

최수진(Sujin Choi),이동주(Dongju Lee),황승국(Seungkuk Hwang) 한국기계가공학회 2021 한국기계가공학회지 Vol.20 No.9

As real-time data of factories can be collected using various sensors, the adaptation of intelligent unmanned processing systems is spreading via the establishment of smart factories. In intelligent unmanned processing systems, data are collected in real time using sensors. The equipment is controlled by predicting future situations using the collected data. Particularly, a technology for the prediction of tool wear and for determining the exact timing of tool replacement is needed to prevent defected or unprocessed products due to tool breakage or tool wear. Directly measuring the tool wear in real time is difficult during the cutting process in milling. Therefore, tool wear should be predicted indirectly by analyzing the cutting load of the main spindle, current, vibration, noise, etc. In this study, data from the current and acceleration sensors; displacement data along the X, Y, and Z axes; tool wear value, and shape change data observed using Newroview were collected from the high-speed, two-edge, flat-end mill machining process of SKD11 steel. The support vector machine technique (machine learning technique) was applied to predict the amount of tool wear using the aforementioned data. Additionally, the prediction accuracies of all kernels were compared.

Differential Deficits of Nouns and Verbs in a Generative Naming Task for Individuals with Mild Cognitive Impairment

최수진(Sujin Choi),성지은(Jee Eun Sung),정지향(Jee Hyang Jeong) 한국언어청각임상학회 2020 Communication Sciences and Disorders Vol.25 No.1

배경 및 목적: 경도인지장애군은 기억력 저하와 함께 단어 산출에 어려움을 보이는데, 명사 뿐만 아니라 동사 산출에도 결함을 보인다. 본 연구는 경도인지장애 집단을 대상으로 품사에 따른 생성이름대기 과제를 실시하고 수행력 차이를 비교하였다. 방법: 본 연구는 경도인지장애 집단 15명과 정상 노년층 집단 15명을 대상으로 품사(명사 vs. 동사)에 따른 생성이름대기 과제를 실시하였다. 명사 생성이름대기 과제는 생물성 유무에 따라 두 개의 범주로 분류하였고, 동사 생성이름대기 과제는 산출된 동사를 세 가지 유형에 따라 분류하여 수행력 차이를 비교하였다. 결과: 경도인지장애 집단이 정상 노년층 집단에 비해 품사에 따른 생생이름대기 과제에서 유의하게 낮은 수행력을 보였다. 또한 두 집단 모두 동사 생성이름대기 과제에서 어려움을 보이는 것으로 나타났다. 명사 생성이름대기 과제에서는 범주의 생물성 유무에 따른 수행력이 차이가 나타나지 않았다. 그러나 동사 생성이름대기 과제에서는 경도인지장애 집단이 정상 노년층에 비해 타동사의 산출에서 유의한 결함을 보이는 것으로 나타났다. 논의 및 결론: 동사 생성이름대기 과제는 정상 노화 과정으로부터 경도인지장애군을 감별 진단하는 민감한 도구일 수 있다. 또한 동사를 유형에 따라 세부적으로 분석하는 것은 경도인지장애 집단의 선택적 결함을 확인할 수 있는 매우 의미 있는 방법임을 제언한다. Objectives: Individuals with Mild Cognitive Impairment (MCI) have demonstrated word retrieval difficulties. The current study investigated differential deficits in the word retrieval process as a type of the word class (nouns vs. verbs) using generative naming tasks between the MCI and their control groups. Methods: Fifteen individual with MCI and 15 normal controls participated in this study. We administered generative naming tasks of nouns and verbs in both groups. The noun generative naming task consisted of two categories (animate vs. inanimate). Performance on the verb generative naming task was analyzed by the types of verbs. Results: The MCI group produced fewer numbers of nouns and verbs on the generation tasks than their controls. Both groups presented significantly lower performance on verbs than nouns. There was no significant difference depending on the animacy in the noun generative naming task. In contrast, there were significant differences in the subtype analyses of verb between the groups, indicating that individuals with MCI demonstrated significantly lower performance on transitive verbs than their controls, but there was no group difference in intransitive and do-verbs. Conclusion: The verb generative naming task may serve as a sensitive tool to differentiate the MCI group from normal aging populations. Furthermore, the more finite analyses of verbs’ subtypes can additionally contribute to identifying differential deficits of word retrieval process for individuals with MCI.

서포트벡터 회귀를 이용한 실시간 제품표면거칠기 예측

최수진(Sujin Choi),이동주(Dongju Lee) 한국산업경영시스템학회 2021 한국산업경영시스템학회지 Vol.44 No.3

The development of IOT technology and artificial intelligence technology is promoting the smartization of manufacturing system. In this study, data extracted from acceleration sensor and current sensor were obtained through experiments in the cutting process of SKD11, which is widely used as a material for special mold steel, and the amount of tool wear and product surface roughness were measured. SVR (Support Vector Regression) is applied to predict the roughness of the product surface in real time using the obtained data. SVR, a machine learning technique, is widely used for linear and non-linear prediction using the concept of kernel. In particular, by applying GSVQR (Generalized Support Vector Quantile Regression), overestimation, underestimation, and neutral estimation of product surface roughness are performed and compared. Furthermore, surface roughness is predicted using the linear kernel and the RBF kernel. In terms of accuracy, the results of the RBF kernel are better than those of the linear kernel. Since it is difficult to predict the amount of tool wear in real time, the product surface roughness is predicted with acceleration and current data excluding the amount of tool wear. In terms of accuracy, the results of excluding the amount of tool wear were not significantly different from those including the amount of tool wear.

디지털 측색 방법을 활용한 제조업체별 전투복 원단 색차 해소방안 연구

최수진 ( Choi Sujin ),염슬기 ( Yeom Seulki ),이민희 ( Lee Minhee ),홍성돈 ( Hong Seongdon ) 한국품질경영학회 2020 품질경영학회지 Vol.48 No.3

Purpose: The purpose of this study was to minimize the difference between color of fibers of combat uniforms occurring depending on the type of dye or process of each manufacturer. Methods: Color difference between combat uniforms made from different manufacturers in mass production by lot was analyzed using spectrophotometer and calculated by color difference formula. Results: By the results of analyzing the color difference between combat uniforms made from different manufacturers with moving average and time series analysis, the feedback to each manufacturer was given. Conclusion: By this study, the color deviation of combat uniforms from different manufacturers was improved to be reduced.

성수동의 지역성을 구현하는 건축사례 연구 -리모델링 및 신축 문화공간 사례를 중심으로-

최수진(Choi Sujin),김수미(Kim Soomi) 대한건축학회 2023 대한건축학회 학술발표대회 논문집 Vol.43 No.1

As peoples quality of life increases, cultural spaces are attracting more and more attention. In particular, the complex cultural space, which combines various cultural spaces, is becoming more active and diverse. Based on this background, the purpose of this study is to investigate the characteristics of the cultural space that shows the regional characteristics of Seongsu-dong through a case study of Seongsu-dongs cultural space. In this study, we will grasp the importance of the regional characteristics of Seongsu-dong and propose how the cultural space of Seongsu-dong can continue to develop in the future.

동적 메모리 할당을 이용한 메모리 효율적인 다중 태스크 학습

최수진(Sujin Choi),김은우(Eunwoo Kim) 대한전자공학회 2023 대한전자공학회 학술대회 Vol.2023 No.6

음식물쓰레기와 하수 슬러지 통합 소화조의 성능 시계열 예측

최수진(Sujin Choi),Abu Hanifa Jannat,이원섭(Wonseob Lee),황석환(Seok Hwan Hwang) 대한환경공학회 2022 대한환경공학회 학술발표논문집 Vol.2022 No.11

취학 전 표현언어부진 아동과 일반 아동이 사용하는 제스처와 발화의 관계 특성 비교

최수진(Sujin Choi),정상임(Sang-Im Jung),김영태(Young Tae Kim) 한국아동학회 2020 아동학회지 Vol.41 No.4

Objectives: The purpose of this study was to investigate the relationship between gesture and speech in the preschool children with expressive language impairment (E-SLI). Methods: Thirty-six preschool children-12 E-SLI, 12 typically developing children matched for chronological age (CA-TD), and 12 typically developing children matched for language age (LA-TD)-completed a picture naming task and a description task. Three-way mixed analysis of variance was used to analyze the modality of expression, the types of gestures, and the semantic relationship between gestures and co-occurring speech. Results: The frequency of ‘speech + gesture’ in children with E-SLI was significantly higher than in CA-TD children. In addition, the frequency of ‘only speech’ and ‘speech + gesture’ in children with E-SLI was similar to that in LA-TD children. In terms of the gesture types, children with E-SLI used significantly more deictic gestures than CA-TD children did. Further, the frequency of representational gestures in children with E-SLI was similar to that of LA-TD children. Conclusion: In educational and clinical settings, it is important to acknowledge that the gestures accompanying with limited verbal expression in children with E-SLI deliver additional semantic information. Therefore, it is essential for educators and clinicians to carefully examine the use of gestures when treating children with E-SLI.

한류에 대한 미ㆍ중 언론보도 프레임 및 정서적 톤 분석

최수진(Sujin Choi) 한국언론학회 2014 한국언론학보 Vol.58 No.2

This study examines the frame and affective tone of Hallyu news reports by the U.S. and China after the worldwide hit of the South Korean singer Psy’s ‘Gangnam Style’. The U.S. and China were selected because the two countries have a close relationship with South Korea from the perspective of cultural imperialism and cultural proximity theory. Based on both deductive and inductive approaches, we drew frames from news reports and constructed semantic networks. In addition, we conducted a computer-assisted content analysis to reveal affective tones embedded in the news reports. The results suggest that the U.S. news reports contained cultural interaction frame, conflict frame, interest/ curiosity frame, neighbor response frame, and cause/effect frame; whereas the Chinese news reports contained cost/benefit frame, comparison frame, episodic frame, heroic frame, others frame, and simple information frame. In terms of affective tones, the U.S. news reports used relatively more words that reflect anxiety and concern, and the Chinese news reports used relatively more words that reflect anger. These findings provide not only theoretical and methodological implications but also practical implications for cultural industry policies.