This study aims to develop a comprehensive predictive model for Digital Quality Management (DQM) and to analyze the impact of various quality activities on different levels of DQM. By employing the Classification And Regression Tree (CART) methodology, we are able to present predictive scenarios that elucidate how varying quantitative levels of quality activities influence the five major categories of DQM. The findings reveal that the operation level of quality circles and the promotion level of suggestion systems are pivotal in enhancing DQM levels. Furthermore, the study emphasizes that an effective reward system is crucial to maximizing the effectiveness of these quality activities. Through a quantitative approach, this study demonstrates that for ventures and small-medium enterprises, expanding suggestion systems and implementing robust reward mechanisms can significantly improve DQM levels, particularly when the operation of quality circles is challenging. The research provides valuable insights, indicating that even in the absence of fully operational quality circles, other mechanisms can still drive substantial improvements in DQM. These results are particularly relevant in the context of digital transformation, offering practical guidelines for enterprises to establish and refine their quality management strategies. By focusing on suggestion systems and rewards, businesses can effectively navigate the complexities of digital transformation and achieve higher levels of quality management.

이 연구는 1세대 스마트 온실의 재배환경 데이터와 장미 절 화의 품질 특성 데이터를 수집하고 그 요인들 간의 상관 관계 를 분석하여 절화수명 예측 및 최적 환경 조성의 기초 자료를 얻고자 수행되었다. 이를 위해, 토경재배(SC) 및 암면배지경 양액재배(RWH) 하우스 각 1개소를 선정하여 1년간 기온, 상 대습도(RH) 및 수증기압차(VPD), 일적산광량(DLI), 근권온도 등의 환경 데이터와 매월 말 수확된 장미 ‘Miss Holland’ 절 화의 품질 특성 데이터를 수집하였으며, 이 데이터와 절화수 명과의 상관관계를 분석하였다. 절화수명은 10월과 11월을 제외하고는 SC 하우스에서 RWH 하우스보다 더 길었다. 절 화수명과 환경 및 생육 특성 간의 상관관계 분석에서 SC 하우 스의 상관계수는 RWH 하우스보다 조금 더 높았으며, 절화수 명 예측을 위한 요소들도 두 하우스 간에 차이가 있었다. SC 하우스의 절화수명 Y=0.848X1+0.366X2-0.591X3+2.224X4- 0.171X5+0.47X6+0.321X7+9.836X8-110.219(X1-X8: 최고 RH, RH 일교차, DLI, pH, Hunter’s b value, EC, 절화 장, 잎 두께; R2=0.544)로 예측되었고, RWH 하우스의 절화수명 Y=-1.291X1+52.026X2-0.094X3+0.448X4-3.84X5+0.624X6 - 8.528X7+28.45(X1-X7: 경경, 야간 VPD, 최고 근권온도, 최 저 근권온도, 기온 일교차, RH 일교차, 최고 VPD; R2=0.5243) 로 예측되었다. 이 두 모델식으로부터 SC 하우스에서는 RH, EC 및 pH가, 그리고 RWH 하우스에서는 근권 온도가 절화수명에 더 큰 영향을 미친다는 것을 추론할 수 있다. 따라서 각 재배 방법에 따라 장미의 절화수명에 더 큰 영향을 미치는 환경적 요인을 효율적으로 관리할 필요가 있다.

Approximately 40,000 elevators are installed every year in Korea, and they are used as a convenient means of transportation in daily life. However, the continuous increase in elevators has a social problem of increased safety accidents behind the functional aspect of convenience. There is an emerging need to induce preemptive and active elevator safety management by elevator management entities by strengthening the management of poorly managed elevators. Therefore, this study examines domestic research cases related to the evaluation items of the elevator safety quality rating system conducted in previous studies, and develops a statistical model that can examine the effect of elevator maintenance quality as a result of the safety management of the elevator management entity. We review two types: odds ratio analysis and logistic regression analysis models.

인공지능은 4차 산업혁명의 프레임이 소개된 이후 점차 보편적인 기술로 자리를 잡아가고 있으며, 인공지능 관련 특허 출원도 크게 증가하고 있다. 최근에는 특허 생태계가 출원 건수 위주의 양적 경쟁에서 고품질의 특허 확보라는 질적 경쟁으로 패러다임이 변화되면서, 저품질 특허로 인한 비용 손실에 관심이 높아지고 있다. 이러한 배경으로 본 연구에서는 머신러닝과 Doc2Vec 알고리즘을 활용하여 특허 품질을 예측하는 방법을 제안하고자 한다. 본 연구를 위해 WIPO에서 정의한 CPC 코드를 활용하여 미국 특허청(USPTO)에 등록된 인공지능 관련 특허 데이터를 추출하였고, 이를 통해 정형 데이터 기반 19개 변수, 비정형 데이터 기반 7개 변수를 개발하였다. 특히, 새롭게 제안하는 Doc2Vec 알고리즘을 이용한 제목과 초록 텍스트 유사도 변수는 고품질 특허를 예측하는데 영향을 미칠 것으로 판단된다. 이에 유사도 변수의 효과를 확인하기 위해 유사도 변수를 포함한 앙상블 기반 머신러닝 모델과 포함하지 않은 모델을 개발하여 비교하였다. 실험 결과, 유사도 변수를 포함한 모델이 AUC 0.013, f1-score 0.025가 높게 나타나 더 우수한 성능을 보였다. 이는 유사도 변수가 고품질 특허 예측에 기여한다는 것을 시사한다. 또한, SHAP을 이용하여 블랙박스 형태의 머신러닝 변수 영향도를 설명하였다. 본 연구를 통해 핵심 기술 분야인 인공지능과 같은 영역에서 특허의 품질을 예측하고, 고품질 특허 개발을 장려함으로써 사회적 가치를 실현하는 데 기여할 수 있을 것으로 기대한다.

사출성형공정은 열가소성 수지를 가열하여 유동상태로 만들어 금형의 공동부에 가압 주입한 후에 금형 내에서 냉각시키는 공정으로, 금형의 공동모양과 동일한 제품을 만드는 방법이다. 대량생산이 가능하고, 복잡한 모양이 가능한 공정으로, 수지온도, 금형온도, 사출속도, 압력 등 다양한 요소들이 제품의 품질에 영향을 미친다. 제조현장에서 수집되는 데이터는 양품과 관련된 데이터는 많은 반면, 불량품과 관련된 데이터는 적어서 데이터불균형이 심각하다. 이러한 데이터불균형을 효율적으로 해결하기 위하여 언더샘플링, 오버샘플링, 복합샘플링 등이 적용되고 있다. 본 연구에서는 랜덤오버샘플링(ROS), 소수 클래스 오버 샘플링(SMOTE), ADASTN 등의 소수클래스의 데이터를 다수클래스만큼 증폭시키는 오버샘플링 기법을 활용하고, 데이터마이닝 기법을 활용하여 품질예측을 하고자 한다.

Ball stud parts are manufactured by a cold forging process, and fastening with other parts is secured through a head part cutting process. In order to improve process quality, stabilization of the forging quality of the head is given priority. To this end, in this study, a predictive model was developed for the purpose of improving forging quality. The prediction accuracy of the model based on 450 data sets acquired from the manufacturing site was low. As a result of gradually multiplying the data set based on FE simulation, it was expected that it would be possible to develop a predictive model with an accuracy of about 95%. It is essential to build automated labeling of forging load and dimensional data at manufacturing sites, and to apply a refinement algorithm for filtering data sets. Finally, in order to optimize the ball stud manufacturing process, it is necessary to develop a quality prediction model linked to the forging and cutting processes.

PURPOSES : Roller-compacted concrete pavement (RCCP) is a superstiff-consistency concrete pavement that exhibits excellent strength development owing to a hydration reaction and interlocking aggregates owing to the roller compaction. A zero-slump concrete mixture is generally used. Hence, it is important to control the consistency of the RCCP mixture to prevent the deterioration of the construction quality (such as material separation during paving). The workability of the RCCP is characterized by its consistency and controlled by the Vebe time, whereas a conventional concrete pavement is controlled based on the slump test. The consistency of the RCCP changes over time after concrete mixing owing to delivery, construction time delays, etc. Thus, it is necessary to use the optimum Vebe time to achieve the best construction quality. Therefore, this study aims to develop a Vebe time prediction model for efficiently controlling the consistency of RCCPs according to random time variations. METHODS : A Vebe time prediction model was developed using a multiple linear regression analysis. A dataset of 131 samples was used to develop the model. The collected data consisted of variables with large potential effects on the consistency of the RCCP, such as the water-cement ratio (W/C), sand/aggregate ratio (S/a), water content (ω), water content per unit volume (W), cement (C), fine aggregate (S), coarse aggregate (G), water reducing admixtrue (PNS), air-entraining admixture (AE), delay time (T), air temperature (TEM), and humidity (HUM). In the multiple linear regression analysis, the mentioned parameters were used as the independent variables, and the Vebe time was the dependent variable. The Vebe time prediction models were evaluated by considering the adjusted R2 and p-values. The selection of the model was based on the largest R2 value and an acceptable p-value (p<0.05). RESULTS : The Vebe time prediction model achieved an adjusted R2 value of 64.14% with a significance level (p-value) of less than 0.05. This shows that the predictive model is adequately described for the dependent variable, and that the model is suitable for Vebe time predictions. Moreover, the significance level of the independent variables is less than 0.05, indicating significant effects on the Vebe time (i.e., the dependent variable). CONCLUSIONS : The Vebe time prediction model developed in this study can be used to estimate Vebe times with an R2 of 63.33% between the measured and predicted values. The proposed Vebe time prediction model is expected to be effectively utilized for the quality control of RCCP mixtures. Moreover, it is expected to contribute to achieving good RCCP construction quality.

There are a number of methods to evaluate the quality of squid. However, when purchasing the fish, consumers and retails rely only on the sensory test and flavor in the field. Therefore, this study was aimed to prove relationship between scientific indicator and sensory test. Total viable cell count (TVC), viable cell count of Pseudomonas spp., pH and volatile basic nitrogen (VBN) were selected as scientific indicators and mesured during the storage of squid at different temperature. The squid was storaged at 3 different temperature (5oC, 15oC, 20oC). Off flavor determination time was measured by R-index, and kinetic modeling was conducted. Activation energies of offflavor determination time, TVC, Pseudomonas spp, VBN, and pH were 51.210 kJ/mol, 42.88 kJ/mol, 50.283 kJ/mol, 72.594 kJ/mol and 41.99 kJ/mol respectively. Activation energy of off-flavor determination time was approximated to viable cell count of Pseudomonas spp., TVC, pH and VBN as an order. Especially, viable cell count of Pseudomonas spp. had best match of the activation energy. Therefore, it was judged that indicator of off-flavor determine time was viable cell count of Pseudomonas spp..

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F1-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

In this study, as part of the paradigm shift for manufacturing innovation, data from the multi-stage cold forging process was collected and based on this, a big data analysis technique was introduced to examine the possibility of quality prediction. In order for the analysis algorithm to be applied, the data collection infrastructure corresponding to the independent variable affecting the quality was built first. Similarly, an infrastructure for collecting data corresponding to the dependent variable was also built. In addition, a data set was created in the form of an independent variable-dependent variable, and the prediction accuracy of the quality prediction model according to the traditional statistical analysis and the tree-based regression model corresponding to the big data analysis technique was compared and analyzed. Lastly, the necessity of changing the manufacturing environment for the use of big data analysis in the manufacturing process was added.

This study suggests a machine learning model for predicting the production quality of free-machining 303-series stainless steel small rolling wire rods according to the manufacturing process's operation condition. The operation condition involves 37 features such as sulfur, manganese, carbon content, rolling time, and rolling temperature. The study procedure includes data preprocessing (integration and refinement), exploratory data analysis, feature selection, machine learning modeling. In the preprocessing stage, missing values and outlier are removed, and variables for the interaction between processes and quality influencing factors identified in existing studies are added. Features are selected by variable importance index of lasso regression, extreme gradient boosting (XGBoost), and random forest models. Finally, logistic regression, support vector machine, random forest, and XGBoost is developed as a classifier to predict good or defective products with new operating condition. The hyper-parameters for each model are optimized using k-fold cross validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with accuracy of 0.9929, specificity of 0.9372, F1-score of 0.9963 and logarithmic loss of 0.0209. In this study, the quality prediction model is expected to be able to efficiently perform quality management by predicting the production quality of small rolling wire rods in advance.

This study was conducted to investigate the quality of kimchi cabbages stored under a pallet unit-controlled atmosphere (PUCA), containing 2% O2 and 5% CO2, and to develop quality prediction models for cabbages stored under such conditions. Summer and winter cabbage samples were divided into PUCA-exposed groups and atmospheric airexposed control groups (in a cold storage). The control summer cabbages lost up to 8.31% of their weight, whereas the PUCA-exposed summer cabbages lost only 1.23% of their weight. Additionally, PUCA storage effectively delayed the reduction in cabbage moisture content compared with the control storage. After storage for 60 and 120 days of the summer and winter samples, respectively, the reducing sugar contents were higher in the PUCA groups than in the control groups. The linear regression analysis-derived equations for predicting the storage period, weight loss, and moisture content in the control groups, as well as those for predicting the storage period and weight loss in the PUCA groups, were appropriate according to the adjusted coefficient of determination, root mean square error, accuracy factor, and bias factor values. Therefore, this PUCA system would be useful for improving the shelf life of the postharvest summer and winter cabbages used in the commercial kimchi industry.

우리 사회에 출생률 감소와 급속한 고령화, 일자리 감소와 소득 양극화 등 사회·경제적으로 부정적인 여건이 대두되고 지속되면서 앞으로의 경제전망은 더욱 어두워지고 있다. 이러한 상황에서 정부는 경제 활성화를 위하여 미래 혁신성장동력 확보, 규제혁신 등 여러 경제정책을 종합하여 추진하고 있다. 본 연구는 일반적으로 미래 성장동력으로 쉽게 여겨지지 않는 농식품분야에서 유망한 대표적인 신산업을 대상으로 분석을 실시하였다. 고령친화식품산업과 펫푸드(Pet Food)산업에 대하여 산업 활성화를 위한 규제개선의 과제로 품질인증제 도입을 제시하고 이로 인한 경제적 효과도 예시적으로 계측하였으며, 마지막으로 이것이 갖는 경제학적 의미를 논의하였다. 두 농식품분야 신산업에서의 품질인증제 시행은 식품의 안전성을 강화하는 동시에 사회 전체 후생도 향상시킬 수 있는 방안으로 기대된다.

This study was carried out to indirectly predict the storage time limit, hardness, and acidity of Fuji apples in controlled atmosphere (CA) storage. A sensor installed inside the CA storage measured temperature, relative humidity, and gas composition data in real time. The respiration rate from five tons of apples in CA storage was calculated to predict the weight loss rate. As a result, the predicted and actual weight loss rate induced a predictable residual storage time equation that showed a significantly high correlation. The apple storage period showed a high reliability (R2=0.9322) because the predicted equation using respiration rate and number of days stored was about nine months for five tons of apples. Furthermore, the hardness and acidity prediction equation were derived from the quality analysis. However, there was not enough analysis sample correlation (the coefficient was as low as 0.3506 and 0.3144, respectively), but the tendency could be confirmed by reduced hardness and acidity. As a result, these quality prediction equations could encourage CA container distribution, effective for agricultural shipment regulation and increasing the ease of operations.

This study was conducted to determine the effect of mathematical transformation on near infrared spectroscopy (NIRS) calibrations for the prediction of chemical composition and fermentation parameters in corn silage. Corn silage samples (n=407) were collected from cattle farms and feed companies in Korea between 2014 and 2015. Samples of silage were scanned at 1 nm intervals over the wavelength range of 680~2,500 nm. The optical data were recorded as log 1/Reflectance (log 1/R) and scanned in intact fresh condition. The spectral data were regressed against a range of chemical parameters using partial least squares (PLS) multivariate analysis in conjunction with several spectral math treatments to reduce the effect of extraneous noise. The optimum calibrations were selected based on the highest coefficients of determination in cross validation (R2 cv) and the lowest standard error of cross validation (SECV). Results of this study revealed that the NIRS method could be used to predict chemical constituents accurately (correlation coefficient of cross validation, R2 cv, ranging from 0.77 to 0.91). The best mathematical treatment for moisture and crude protein (CP) was first-order derivatives (1, 16, 16, and 1, 4, 4), whereas the best mathematical treatment for neutral detergent fiber (NDF) and acid detergent fiber (ADF) was 2, 16, 16. The calibration models for fermentation parameters had lower predictive accuracy than chemical constituents. However, pH and lactic acids were predicted with considerable accuracy (R2 cv 0.74 to 0.77). The best mathematical treatment for them was 1, 8, 8 and 2, 16, 16, respectively. Results of this experiment demonstrate that it is possible to use NIRS method to predict the chemical composition and fermentation quality of fresh corn silages as a routine analysis method for feeding value evaluation to give advice to farmers.

초분광영상을 이용하여 방울토마토의 전체 면에서 반사스펙트럼을 획득하였으며 숙도 등급(GN-RD)에 따른 스펙트럼의 차이를 관찰하였다. 방울토마토의 반사스펙트럼에서 클로로필에 의한 675 nm 영역의 흡수가 관찰되었고, 당과 수분의 영향으로 알려진 840 nm, 970 nm 영역에서 흡수가 관찰되었다. 특히 GN에서 RD 등급으로 숙도가 진행될수록 평균 스펙트럼의 경우 반사율이 낮아지는 경향이 관찰되었다. 총 8개의 전처리를 이용하여 전 숙도 등급의 시료에 적용한 PLS 회귀 분석에서 내부품질들 중 경도 예측모델이 가장 우수한 것으로 확인되었다. 이때 전처리는 평균값을 이용한 정규화이었으며 결정계수는 0.876, 그리고 SEP은 1.875 kgf 이었다. 당도의 경우는 최대값을 이용한 정규화에서 결정계수가 0.823과 SEP 0.388oBx로 나타났으며, 산 함량의 경우 최대값을 이용한 정규화에서 0.620의 결정계수와 0.208%의 SEP이 확인되었다. 상품성을 고려한 PK, LR, RD 등급의 시료에서 PLS 회귀 분석을 실시한 결과 내부품질 중 전체의 숙도 등급의 시료를 사용하여 예측한 결과보다는 전체적으로 다소 낮은 예측결과를 확인할 수 있었다. 내부 품질 중 경도에서 가장 높은 예측모델이 확인되었으며, 전처리는 일정 범위를 이용한 정규화이고 0.679의 결정계수와 0.976oBx의 SEP이 확인되었다. 당도는 최대값을 이용한 정규화에서 0.586의 결정계수와 0.546 kgf의 SEP의 결과를 보였으며 산 함량은 Savitzky Golay의 2차 미분에서 0.547의 결정계수와 0.188%의 SEP을 보였다. 본 연구에서는 최근 연구 활용이 시작되고 있는 최신기술인 초분광 반사영상을 이용하여 방울토마토 내부품질인 경도, 당도, 산 함량 예측의 가능성을 확인하였다. 초분광영상은 영상처리를 이용하여 외부의 결함 및 외부 착색도 등도 측정할 수 있으므로 본 연구에서 수행한 내부품질 측정과 융합하여 복합적인 농산물 품질 선별기 개발에 활용할 수 있을 것으로 판단된다.

The purpose of this study was to measure respondent's demographic characteristics, respondent's attitudes toward chicken, and factor influencing on the level of perceived helpfulness of country of origin in predicting the quality of chicken. The data was collected through a consumer survey during the March 2006. A total number of 250 meat consumers living in Suncheon, the eastern part of Chonnam, were randomly selected as respondents. Eleven respondents did not complete the survey instrument, resulting in a final sample size of 239. All estimations were carried out using chi-square, correlation, and logistic procedure of SAS package. The results are as follows. The level of perceived helpfulness of country of origin in predicting the quality of chicken was significantly different by age and occupation of demographic variables, and was significantly correlated with respondent informed of attitude variables. The proportional odds assumption of model was not violated at p<0.05. The effects of income, occupation and respondent informed on the level of perceived helpfulness of country of origin in predicting the quality of chicken. The results from this study could be useful in developing marketing and health promotion strategies, as well as government trade policy.