• Journal of Korean Institute of Industrial Engineers
• /
• v.36 no.3
• /
• pp.193-202
• /
• 2010

The recommender system is a typical software solution for personalized services which are now popular in e-commerce sites. Most of the existing recommender systems are based on customers' explicit rating data on items (e.g., ratings on movies), and it is only recently that recommender systems based on implicit ratings have been proposed as a better alternative. Implicit ratings of a customer on those items that are clicked but not purchased can be inferred from the customer's navigational and behavioral patterns. In this article, a dimensionality reduction (DR) technique is newly applied to the implicit rating-based recommender system, and its effectiveness is assessed using an experimental e-commerce site. The experimental results indicate that the performance of the proposed approach is superior or at least similar to the conventional collaborative filtering (CF)-based approach unless the number of recommended products is 'large.' In addition, the proposed approach requires less memory space and is computationally more efficient.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• Journal of Korean Society for Quality Management
• /
• v.51 no.2
• /
• pp.223-245
• /
• 2023

Purpose: This study aim to identify the trends in AI-based PHM technology that can enhance reliability and minimize costs. Furthermore, this research provides valuable guidelines for future studies in various industries Methods: In this study, I collected and selected AI-based PHM studies, established classification criteria, and analyzed research trends based on classified fields and techniques. Results: Analysis of 125 domestic studies revealed a greater emphasis on machinery in both diagnosis and prognosis, with more papers dedicated to diagnosis. various algorithms were employed, including CNN for image diagnosis and frequency analysis for signal data. LSTM was commonly used in prognosis for predicting failures and remaining life. Different industries, data types, and objectives required diverse AI techniques, with GAN used for data augmentation and GA for feature extraction. Conclusion: As studies on AI-based PHM continue to grow, selecting appropriate algorithms for data types and analysis purposes is essential. Thus, analyzing research trends in AI-based PHM is crucial for its rapid development.

• Korean Journal of Soil Science and Fertilizer
• /
• v.32 no.3
• /
• pp.223-231
• /
• 1999

This study was carried out to investigate the factors influencing water quality of the river (Mankyeong River) and groundwater in controlled horticulture region from 1994 to 1998. Water quality of Mankyeong River was monitored at 13 sites along main stream for 6 months from April to September from 1994 to 1997. Monthly average concentrations of $NH_4-N$, $SO{_4}^{2-}$ and $Cl^-$ were highest in April, while that of $NO_3-N$ was highest in August. Monthly average concentrations of COD was highest in September Concentrations of $NH_4-N$ and $SO{_4}^{2-}$ in many sites of Mankyeong River exceeded the water quality criteria of agricultural water for irrigation. Water quality of Mankyeong River was not suitable for the irrigation source excepted the sites such as Hari, Gosan and Soyang stream. The floodgates of Mokcheon, Yocheon, Jeonju and Samcheon streams were rapidly polluted by the municipal sewage, otherwise the Iksan stream was rapidly polluted by the sewage of swine. The sum of inorganic ion concentrations in Mankyeong River was highest at floodgate of Yocheon due to the sewages municipal and industrial. The order of the major anions and canons concentration in Mankyeong River- stream were $SO{_4}^{2-}$ > $Cl^-$ > $NO{_3}^-$ > $PO{_4}^{3-}$ and $Na^+$ > $Ca^{2+}$ > $NH{_4}^+$ > $Mg^{2+}$ > $K^+$, respectively. The geoundwater quality at controlled horticulture region was surveyed 4 sites from 1994 to 1998. Concentrations of $NH_4-N$ and $NO_3-N$ were lower at the deeper groundwater. However there was no difference between the concentrations of $SO{_4}^{2-}$ and $Na^+$, and the groundwater depth below 15m. Contents of $NH_4-N$, $NO_3-N$, $PO{_4}^{3-}$, $SO{_4}^{2-}$, $Na^+$ and $Cl^-$ in groundwater were the highest at dry season. Nitrate-N level, exceeded $20mg\;l^{-1}$, the critical level for agricultural usage, at Yongjinmyeon Wanju and $PO{_4}^{3-}$ concentration were higher at Seogtandong Iksan than the other places.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.4
• /
• pp.1391-1398
• /
• 2010

Reuse feasibility of MBR effluent of S Electronic Company's organic wastewater as a LCD process water was investigated by a $32m^3/d$ pilot-scale RO membrane process. The effects of operating pressure and permeate flux at constant 85% recovery of RO membrane process using MBR effluent were analyzed for transmembrane pressure and period for CIP by membrane fouling as well as rejection of TOC and conductivity. MBR effluent requires additional treatment to meet the LCD process water quality criteria of TOC<1 mg/L and conductivity<$100{\mu}S/cm$ which is stringent as compared with those of conventional reuse water quality criteria. The RO process operated at 85% recovery with stepwise increasing of permeate fluxes from 12.5 LMH to 22.0 LMH was able to meet LCD process water quality criteria. However, the transmembrane pressure increased and the period of CIP decreased as increasing permeability fluxes due to fouling of RO membrane. The optimum operational conditions of RO membrane process were permeate fluxes of 16.5~18.5 LMH with operating pressure of $6.7{\sim}12.4kgf/cm^2$ and CIP period of 20~25 days at constant 85% recovery.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2009.04a
• /
• pp.59-62
• /
• 2009

유체-고체 상호작용(FSI)은 산업전반에서 꼭 필요한 분야이면서도 쉽게 접근하기가 어려운 전산역학 분야의 난제 중 하나이다. 유체-고체 상호작용의 전산해석에서 유체와 고체 사이의 불일치 격자망을 어떻게 처리하는가는 매우 어렵고 민감한 부분이 된다. 운동학적 연속성과 계면을 따른 응력의 평형을 추적하기 위해 유체와 고체의 계면에서는 각각의 영역에서 해석된 물리량들을 다른 영역으로 정확히 전달해야 하는데 대부분의 유체-고체 상호작용의 문제들은 불일치 격자를 가지고 있기 때문에 불일치 격자망을 효과적으로 처리하는 수단이 필요하다. 그래서 넓은 분야에 걸쳐 적용 가능한 유체 고체 상호작용 문제에 대한 효과적인 해석방법의 제안이 큰 의미를 갖는다고 생각한다. 따라서 본 연구에서는 유체-고체 계면의 운동을 이동최소제곱 기반의 변절점 요소를 사용하여 모사함으로써 2차원 유체-고체의 상호작용(FSI)을 위한 새로운 접근방법을 제시하였다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.803-806
• /
• 2002

This paper estimated the stability of centrifuge as its rotating speed compared with the natural frequency of cylinder and screw by finite element analysis. It shows that the one of exciting causes is the tooth passing frequency of input and output parts by the periodic characteristics of transmission error due to an planetary gear having three stages. Also, it proposed the critical speed of cylinder and screw by the Campbell diagram.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1127-1128
• /
• 2011

실제 운용중인 수도사업장을 대상으로 펌프모터로 가장 많이 쓰이는 유도전동기의 유량제어를 위해 기존의 방법인 밸브개도에 의한 유량제어 방법과 최근기술인 인버터를 이용한 유량제어 방법을 비교분석하여 효율성을 평가 하였고, 최근 전력전자 기술의 발전에 따라 문제시되고 있는 인버터 사용에 따른 고조파를 분석하여 인버터 시스템 도입에 따른 안정성을 평가하였다. 본 연구에서 평가한 펌프모터의 속도 제어를 위한 기존의 방법인 밸브개도에 의한 유량제어 방법과 인버터를 이용한 유량제어 방법에 대한 효율성 및 안정성 평가결과를 바탕으로 인버터시스템을 산업현장에 적극 도입함으로서 에너지 절감에 따른 생산원가 절감 및 수용가의 용수공급 예측을 통한 관망운영의 안정성을 기대할 수 있다.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 2002.11a
• /
• pp.19-27
• /
• 2002

최근 경제구조가 고도화되고 생활수준이 향상됨에 따라 사회간접자본시설 및 각종 용도의 건축물에 대한 요구가 높으며, 특히 고층건물 건축시에 사용되는 리프트카의 수요 또한 증가되고 있다. 일반적으로 기계구조물은 사용기간동안 절대적 안전성을 확보하기 위하여 설계되고 있으나 실제 건설 현장에서 사용중인 피니언축에 균열이 발견되고 있으며 이로 인하여 피니언축 수리보수 기간동안의 공사중지로 공기지연 뿐만 아니라 리프트카 추락으로 인한 인명사고가 발생하는 등 그 위험성이 매우 높다. 이에 따라 각종 구조물, 설비 및 기기의 안전진단을 통한 유지보수가 중요시되고, 결함 검출의 정량화에 대한 연구, 기술 개발이 강력히 요구되고 있다.(중략)

• Water for future
• /
• v.47 no.1
• /
• pp.40-47
• /
• 2014

기후변화-수자원 적응과제들의 성공적인 수행과 결과물의 활용을 위해서는 안전행정부, 환경부, 농림축산식품부 등 물관련 정부부처간의 긴밀한 협조체계가 이루어져야 할 것이다. 이를 위해서는 (1)안전행정부의 재난관련 방재패러다임 전환 및 위기관리 체계강화를 위한 추진과제(자연재해 지자체 방재시스템), (2)환경부의 기후변화에 따른 물환경관리 대책 추진과제(비점오염, 수질, 수생태, 습지), (3)농림축산식품부의 농업수자원 및 산림자원 확보 추진과제(농업용수, 산림재해) 등의 진행상황 및 결과의 공유체계 및 공동활용을 위한 채널구축이 필요하다. 포럼에서의 의견으로서, 타분야 특히 산업일선에서는 이미 기후변화에 따른 적응정책과 더불어 관련기술의 개발이 진행되어 우리 수자원분야는 많이 늦은 감이 있다는 지적, 그리고 제시된 기획과제 중에서 제4세부과제인 수자원의 가치를 평가하는 기술개발이 매우 중요하다는 언급이 많았다. 이에 저자들은 수자원의 가치를 높이기 위해서는 농업 그리고 에너지 분야의 전문가들과의 협력연구(Water-Food-Energy Nexus)를 통하여 세 분야의 통계기반, 정보공유, 융합가치 등의 제반연구는 매우 중요한 미래과제라고 강조하였다.