Predicting Reports of Theft in Businesses via Machine Learning

JungIn Seo,JeongHyeon Chang 국제문화기술진흥원 2022 International Journal of Advanced Culture Technolo Vol.10 No.4

This study examines the reporting factors of crime against business in Korea and proposes a corresponding predictive model using machine learning. While many previous studies focused on the individual factors of theft victims, there is a lack of evidence on the reporting factors of crime against a business that serves the public good as opposed to those that protect private property. Therefore, we proposed a crime prevention model for the willingness factor of theft reporting in businesses. This study used data collected through the 2015 Commercial Crime Damage Survey conducted by the Korea Institute for Criminal Policy. It analyzed data from 834 businesses that had experienced theft during a 2016 crime investigation. The data showed a problem with unbalanced classes. To solve this problem, we jointly applied the Synthetic Minority Over Sampling Technique and the Tomek link techniques to the training data. Two prediction models were implemented. One was a statistical model using logistic regression and elastic net. The other involved a support vector machine model, tree-based machine learning models (e.g., random forest, extreme gradient boosting), and a stacking model. As a result, the features of theft price, invasion, and remedy, which are known to have significant effects on reporting theft offences, can be predicted as determinants of such offences in companies. Finally, we verified and compared the proposed predictive models using several popular metrics. Based on our evaluation of the importance of the features used in each model, we suggest a more accurate criterion for predicting var.

서울시립노인요양시설 경영수지 분석과 재정에 관한 종사자의 인식

서홍란(Seo, HongLan),배영미(Bae, YoungMi),김정인(Kim, JungIn) 강원대학교 사회과학연구원 2020 사회과학연구 Vol.59 No.2

본 연구는 서울시립노인요양시설의 재정상태를 파악하고 이에 대한 현장전문가의 인식을 밝히고자 수행되었다. 이를 위해 최근 3년간 (2016년∼2018년) 서울시립노인요양시설의 결산서를 분석하고, 해당 시설의 종사자를 세 집단으로 분류하여 각 1회씩 총 3회의 초점집단인터뷰를 수행하였다. 이외에도 경기지역에 위치한 서울시립노인요양시설을 총 2회 방문하였다. 모든 자료는 2019년 5월 3일부터 6월 21일까지 약 7주간 수집되었다. 연구결과 2016년부터 2018년까지 장기요양사업의 재정수지는 적자였다. 그러나 전체 수지는 흑자였는데 이는 장기요양사업 외 수지가 꾸준하게 흑자를 유지했기 때문이다. 한편, 초점집단인터뷰에 참여한 현장전문가들은 시설의 재정상황에 대해 ‘눈앞이 깜깜할 정도로 절망적이고 난감한 현실’임을 강조했다. 이들은 재정난의 주요인으로 수가로 감당하기 어려운 인건비를 지적했고, 이에 따른 영향으로 인적자원관리와 양질의 서비스를 제공하기 어려움을 주장했다. 본 연구에서는 돌봄의 공공성 강화, 시설의 자원동원 역량 강화, 4차 산업혁명 시대에 적합한 돌봄 환경 구축 등 서울시립노인요양시설의 재정 안정화 방안을 제시하였다. The purpose of this study is to figure out the financial status of the nursing homes contracted out by city of Seoul and to illuminate perceptions of the field experts on financial conditions. For this purpose, balance sheets of the municipal nursing homes for the last three years(2016–2018) were analyzed. Also, focus group interviews with the field experts were conducted three times. In addition, visitations to two nursing homes located in Gyeonggi province were conducted. All of the data were collected from May 3 to June 21 in 2019, for approximately 7 weeks. The result are as follows. The fiscal balance of the long-term care from 2016 to 2018 was deficit. On the other hand, overall finance of the nursing homes has shown a surplus as finances for areas other than the long-term care business have maintained consistent surpluses. Meanwhile, the field experts who participated in the focus group interview emphasized that the current financial situation of the facility is ‘hopeless.’ Also, they perceived that financial difficulty is related to ‘labor costs’which is too high to handle with the fee for services. In the aftermath of the increase in labor costs, it was difficult to manage human resources and provide quality services. Based on the results, this study proposed several strategies to stabilize the finance of the Seoul municipal nursing homes. The financial stability strategies include strengthening publicity of care, strengthening the facility’s resource mobilization capacity, and establishing a caring environment suitable for the era of the 4th industrial revolution.

High-Pressure Phase Behavior of Heptadecafluoro-1-decene and Nonafluoro-1-hexene in Supercritical Carbon Dioxide

Cho, Dong Woo,Shin, Jungin,Bae, Won,Kim, Hwayong,Seo, Kyung Won American Chemical Society 2012 Journal of chemical and engineering data Vol.57 No.6

<P>High-pressure phase behavior measurements of (CO<SUB>2</SUB> + heptadecafluoro-1-decene) and (CO<SUB>2</SUB> + nonafluoro-1-hexene) binary mixture systems were carried out using a variable volume view cell. The experimental range of temperature and pressure are from 313.2 K to 343.2 K and up to 15 MPa, respectively. The correlation was performed using the Peng–Robinson equation of state and the van der Waals one-fluid mixing rule. The critical constants, <I>T</I><SUB>c</SUB> and <I>P</I><SUB>c</SUB>, were estimated by the several group contribution methods. The acentric factor was estimated by the Lee–Kesler method.</P><P><B>Graphic Abstract</B> <IMG SRC='http://pubs.acs.org/appl/literatum/publisher/achs/journals/content/jceaax/2012/jceaax.2012.57.issue-6/je300258z/production/images/medium/je-2012-00258z_0004.gif'></P>

Antioxidant and antimicrobial efficacy of a biflavonoid, amentoflavone from <i>Nandina domestica in vitro</i> and in minced chicken meat and apple juice food models

Bajpai, Vivek K.,Park, InWha,Lee, JungIn,Shukla, Shruti,Nile, Shivraj Hariram,Chun, Hyang Sook,Khan, Imran,Oh, Seo Yeong,Lee, Hoomin,Huh, Yun Suk,Na, MinKyun,Han, Young-Kyu Elsevier 2019 Food chemistry Vol.271 No.-

<P><B>Abstract</B></P> <P>A biflavonoid, amentoflavone isolated from <I>Nandina domestica</I> and characterized by NMR spectral-data analyses was assessed for its antioxidant, and antibacterial potential <I>in vitro</I> and in food-model systems. Amentoflavone exhibited potent antioxidant ability (19.21–75.52%) on scavenging DPPH, ABTS, superoxide, and hydroxyl radicals. Fluorescent images confirmed bacterial membrane depolarization of both the tested pathogens <I>Staphylococcus aureus</I> and <I>Escherichia coli</I>, with a significant reduction in cell viabilities at their respective MIC of 62.5 and 125 µg/mL. Increasing rates of membrane permeability observed in 260 nm-absorbing material, potassium ion, extracellular ATP, and relative electrical conductivity assays confirmed antibacterial mechanistic role of amentoflavone as also evidenced by microscopic studies of SEM and TEM. There was a marked inhibitory effect of amentoflavone with a significant reduction in cell counts of <I>S. aureus</I> and <I>E. coli</I> in minced chicken and apple juice at 4 °C, thus suggesting its nutritional enhancing efficacy as a natural antioxidant and antimicrobial agent.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A biflavonoid, amentoflavone was characterized based on the NMR analysis. </LI> <LI> Amentoflavone demonstrated significant antioxidant potential. </LI> <LI> Amentoflavone compromised membrane permeability of foodborne pathogens. </LI> <LI> Studies of SEM and TEM confirmed a mechanistic role of amentoflavone. </LI> <LI> Amentoflavone displayed microbial food safety in meat and apple juice. </LI> </UL> </P>

Integration of eye-tracking and object detection in a deep learning system for quality inspection analysis

Cho Seung-Wan,Lim Yeong-Hyun,Seo Kyung-Min,Kim Jungin 한국CDE학회 2024 Journal of computational design and engineering Vol.11 No.3

During quality inspection in manufacturing, the gaze of a worker provides pivotal information for identifying surface defects of a product. However, it is challenging to digitize the gaze information of workers in a dynamic environment where the positions and postures of the products and workers are not fixed. A robust, deep learning-based system, ISGOD (Integrated System with worker’s Gaze and Object Detection), is proposed, which analyzes data to determine which part of the object is observed by integrating object detection and eye-tracking information in dynamic environments. The ISGOD employs a six-dimensional pose estimation algorithm for object detection, considering the location, orientation, and rotation of the object. Eye-tracking data were obtained from Tobii Glasses, which enable real-time video transmission and eye-movement tracking. A latency reduction method is proposed to overcome the time delays between object detection and eye-tracking information. Three evaluation indices, namely, gaze score, accuracy score, and concentration index are suggested for comprehensive analysis. Two experiments were conducted: a robustness test to confirm the suitability for real-time object detection and eye-tracking, and a trend test to analyze the difference in gaze movement between experts and novices. In the future, the proposed method and system can transfer the expertise of experts to enhance defect detection efficiency significantly.

스파크 점화기관에서의 노킹판단 기준값의 자동수정 알고리즘 개발

강성현(Sunghyun Kang),장광수(Kwangsoo Chang),서정인(Jungin Seo),전광민(Kwangmin Chun) 한국자동차공학회 1999 한국 자동차공학회논문집 Vol.7 No.7