A reliable prediction model of national occupational accident fatality rate can be used to evaluate level of safety and health protection for workers in a country. Moreover, the socio-economic aspects of occupational accidents can be identified through interpretation of a well-organized prediction model. In this paper, we propose a machine learning based relative comparison methods to predict and interpret a national occupational accident fatality rate based on socio-economic indicators. First, we collected 29 years of the relevant data from 11 developed countries. Second, we applied 4 types of machine learning regression models and evaluate their performance. Third, we interpret the contribution of each input variable using Shapley Additive Explanations(SHAP). As a result, Gradient Boosting Regressor showed the best predictive performance. We found that different patterns exist across countries in accordance with different socio-economic variables and occupational accident fatality rate.

The SLA 3d printer is the first of the commercial 3D printer. The 3D printed output is printed hanging on the bed that move to the upper position. Sandblasted bed is used to prevent layer shift. If sandblasting is wrong, the 3D printed output is layer shifted. For this reason, 3D printer manufacturing companies inspect the bed surface. However, the sandblasted surface has variety of irregular shapes and craters, so it is difficult to establish a quality control standard. To solve problems, this paper presents a standardized sandblasting histogram and threshold. We present a filter that can increase the classification rate.

For a plastic diffusion lens to uniformly diffuse light, it is important to minimize deformation that may occur during injection molding and to minimize deformation. It is essential to control the injection molding condition precisely. In addition, as the number of meshes increases, there is a limitation in that the time required for analysis increases. Therefore, We applied machine learning algorithms for faster and more precise control of molding conditions. This study attempts to predict the deformation of a plastic diffusion lens using the Decision Tree regression algorithm. As the variables of injection molding, melt temperature, packing pressure, packing time, and ram speed were set as variables, and the dependent variable was set as the deformation value. A total of 256 injection molding analyses were conducted. We evaluated the prediction model's performance after learning the Decision Tree regression model based on the result data of 256 injection molding analyses. In addition, We confirmed the prediction model's reliability by comparing the injection molding analysis results.

PURPOSES : In this study, the main factors affecting the severity of traffic accidents among elderly drivers were reviewed, and accident factors with a high accident risk were analyzed. This provided basic data for preparing a traffic safety system for elderly drivers and establishing policies. METHODS : Based on machine learning, the major factors influencing accident severity (from the analysis of traffic accident data for elderly drivers) were analyzed and compared with existing statistical analysis results. The machine learning algorithm used the Scikit-learn library and Python 3.8. A hyperparameter optimization process was performed to improve the safety and accuracy of the model. To establish the optimal state of the model, the hyperparameters were set (K = 5) using K-fold cross-validation. The hyperparameter search applied the most widely utilized grid search method, and the performance evaluation derived the optimal hyperparameter value using neutral squared error indicators. RESULTS : The traffic laws, road sections of traffic accidents, and time zones of accidents were analyzed for accidents involving elderly drivers in Daejeon Metropolitan City, and the importance of the variables was examined. For the analysis, a linear regression model, machine learning-based decision tree, and random forest model were used, and based on the root mean square error, the random forest accuracy performance was found to be the best. Ultimately, 18 variables were analyzed, including traffic violations, accident time zones, and road types. The variables influencing the accident severity were the speed, signal violation, intersection section, late-night driving, and pedestrian protection violation, with the relative importance of the variables in the order of speed (0.3490966), signal violation (0.285967), and late-night driving (0.173108). These can be seen as variables related to the expansion of life damage owing to physical aging and reduced judgment abilities arising from decreases in cognitive function. CONCLUSIONS : Restricting the driving of the elderly on the expressway and at night is reasonable, but specific standards for driving restrictions should be prepared based on individual driving capabilities.

The prediction of algal bloom is an important field of study in algal bloom management, and chlorophyll-a concentration(Chl-a) is commonly used to represent the status of algal bloom. In, recent years advanced machine learning algorithms are increasingly used for the prediction of algal bloom. In this study, XGBoost(XGB), an ensemble machine learning algorithm, was used to develop a model to predict Chl-a in a reservoir. The daily observation of water quality data and climate data was used for the training and testing of the model. In the first step of the study, the input variables were clustered into two groups(low and high value groups) based on the observed value of water temperature(TEMP), total organic carbon concentration(TOC), total nitrogen concentration(TN) and total phosphorus concentration(TP). For each of the four water quality items, two XGB models were developed using only the data in each clustered group(Model 1). The results were compared to the prediction of an XGB model developed by using the entire data before clustering(Model 2). The model performance was evaluated using three indices including root mean squared error-observation standard deviation ratio(RSR). The model performance was improved using Model 1 for TEMP, TN, TP as the RSR of each model was 0.503, 0.477 and 0.493, respectively, while the RSR of Model 2 was 0.521. On the other hand, Model 2 shows better performance than Model 1 for TOC, where the RSR was 0.532. Explainable artificial intelligence(XAI) is an ongoing field of research in machine learning study. Shapley value analysis, a novel XAI algorithm, was also used for the quantitative interpretation of the XGB model performance developed in this study.

일반적으로 콘크리트는 골재, 모래, 시멘트, 담수, 혼합재 등 다양한 재료로 구성되어있으며 재령에 따라서 강도가 증 가한다. 콘크리트에 필요한 각 재료의 비율은 혼합 설계를 통해 결정되지만, 콘크리트의 강도는 실험적으로 측정되기 전까지는 알 수 없다. 이러한 한계를 극복하기 위해 실험을 통해 얻은 데이터를 이용하여 콘크리트의 압축 강도를 예측하기 위해 통계수 학과 기계학습 알고리즘을 이용한 많은 연구가 시도되었다. 이전의 연구는 콘크리트 압축 강도 예측에 신경망 기법이 가장 적 합하다고 제안하였다. 그러나 신경망 기법은 다른 기계학습과 비교하여 모델 학습에 계산 비용이 많이 들어 실제로 적용하기 어려운 문제점이 있다. 최근 몇 년 동안 다양한 회귀 분석 모델이 개발되었으므로 본 연구에서는 신경망 대신 최신 회귀 분석 모델을 이용하여 콘크리트 강도 예측모델을 제시하였다. 이를 위해 최근 개발된 회귀 분석 모델에 대한 교차검증을 시행하여 최적의 모델을 선정하였다. 그리드 검색을 통하여 선정된 각 모델의 하이퍼 파라미터를 최적화하고, 국내외 데이터를 활용하여 기계학습 모델을 훈련하고 검증하였다. 이들 중 CatBoost, LGBMR, RFR, XGBoost 회귀모델이 높은 성능을 보여주었다. 특히 그 중에서 XGBoost 회귀 분석 모델이 가장 작은 오차와 높은 정확도를 보여주었다. 이들 중 오류가 가장 큰 LGBMR 모델도 이전 연구에서 제안된 신경망 및 앙상블 모델보다 성능이 우수하였다. 현장 레미콘 콘크리트에 대한 압축 강도 예측을 시행하여 학 습된 모델의 현장 적용 가능성을 확인하였다.

밸브의 내부 누설 현상은 밸브의 내부 부품의 손상에 의해 발생하며 배관 시스템의 사고와 운전정지를 일으키는 주요 요인이 다. 본 연구는 버터플라이형 밸브의 내부 누설에 따라 배관계에서 발생하는 음향방출 신호를 이용하여 배관 가동 중 실시간 누설 진단의 가능성을 검토하였다. 이를 위해 밸브의 작동 모드별로 측정한 시간영역의 AE 원시신호를 취득하였으며 이로부터 구축한 데이터셋은 데 이터 기반의 인공지능 알고리즘에 적용하여 밸브의 내부 누설 유무를 진단하는 모델을 생성하였다. 누설 유무진단을 분류의 문제로 정의 하여 SVM 기반의 머신러닝과 CNN 기반의 딥러닝 분류 알고리즘을 적용하였다. 데이터의 특징 추출에 기반한 SVM 분류 모델의 경우, 이 진분류 모델에서 구축된 모델에 따라 83~90%의 정확도를 나타냈으며, 다중 클래스인 경우 분류 정확도가 66%로 감소하였다. 반면, CNN 기반의 다중 클래스 분류 모델의 경우 99.85%의 분류 정확도를 얻을 수 있었다. 결론적으로 밸브 내부 누설 진단을 위한 SVM 분류모델은 다중 클래스의 정확도 향상을 위해 적절한 특징 추출이 필요하며, CNN 기반의 분류모델은 프로세서의 성능 저하만 없다면 누설진단과 밸브 개도 분류에 효율적인 접근방법임을 확인하였다.

With the current trend of the fourth industrial revolution, machine learning technique is increasingly adopted in various water industry fields. In this review paper, recent studies using machine learning to predict flood, water consumption, water quality, and water treatment processes are summarized. In the typical water purification processes such as flocculation, disinfection, and filtration, machine learning was able to present high-accuracy prediction results for complex non-linear mechanisms. Hybrid machine learning methods, combining multiple algorithms, generally outperformed machine learning results using only one algorithm. A more microscopic machine learning approach can provide valuable information to the operators in the water industry.

Strawberry is a stand-out cultivating fruit in Korea. The optimum production of strawberry is highly dependent on growing environment. Smart farm technology, and automatic monitoring and control system maintain a favorable environment for strawberry growth in greenhouses, as well as play an important role to improve production. Moreover, physiological parameters of strawberry plant and it is surrounding environment may allow to give an idea on production of strawberry. Therefore, this study intends to build a machine learning model to predict strawberry’s yield, cultivated in greenhouse. The environmental parameter like as temperature, humidity and CO2 and physiological parameters such as length of leaves, number of flowers and fruits and chlorophyll content of ‘Seolhyang’ (widely growing strawberry cultivar in Korea) were collected from three strawberry greenhouses located in Sacheon of Gyeongsangnam-do during the period of 2019-2020. A predictive model, Lasso regression was designed and validated through 5-fold cross-validation. The current study found that performance of the Lasso regression model is good to predict the number of flowers and fruits, when the MAPE value are 0.511 and 0.488, respectively during the model validation. Overall, the present study demonstrates that using AI based regression model may be convenient for farms and agricultural companies to predict yield of crops with fewer input attributes.

Odor is a type of sensory pollution that can stimulate the human sense of smell when it occurs, causing discomfort and making it difficult to create a pleasant environment. For this reason, there is a high possibility of complaints regarding odors if odors occur in pigsties near residential properties, and the number of such complaints is also increasing. In addition, odors emanating from pigsties around military installations can cause physical and psychological harm, not only to the soldiers living in these type of facilities but also to the families belonging to military personnel living there as well. Because the concentration of odors varies due to diverse factors such as temperature, humidity, wind direction, wind speed, and interaction between causative materials, predicting odors based on only one factor is not proper or appropriate. Therefore, in this work, we sought to construct models that are based on several regression techniques of machine learning using data collected in field. And we selected and utilized the model that has the highest-accuracy in order to notify and warn residents of odors in advance. In this work, 3672 data items were used to train and test the model. The several machine learning algorithms to build the models are polynomial regression, ridge regression, K-nearest neighbor regression (KNN Regression), and random forest. Comparing the performance of models based on each algorithm, the study found that KNN Regression was the most suitable model, and the result obtained from KNN regression was significant.

본 연구는 메꽃과 6종의 식물에 대해 신속하고 비파괴적으로 분류하기 위해 근적외선 (Vis-NIR) 스펙트럼을 이용하였고 데이터의 전처리와 머신러닝 기술을 적용하였다. 전국적으로 분포하는 메꽃과 6종에 대해 야외에서 휴대용 분광기를 이용하여 판별하였다. 식물의 잎의 표면에서 400~1,075 nm의 근적외선 스펙트럼 (1.5 nm)을 수집하였 다. 수집된 스펙트럼 데이터는 3가지의 전처리와 raw데이터를 이용하였고 4종류의 머신러닝 모델을 적용하여 높은 판별 정확도를 확인하였다. 전처리와 머신러닝 모델의 조합을 통해 분석된 판별의 정확도는 43~99%의 범위로 분석되었고, standard normal variate 전처리와 support vector machine 머신러닝 모델의 조합에서 판별 정확도가 98.6% 로 가장 높게 나타났다. 본 연구에서 수집된 스펙트럼은 식물의 성장단계, 다양한 측정 지역 및 잎에서의 측정 위치 등과 같은 요인과 더불어 데이터 분석을 위한 조건으로 최 적의 전처리와 머신러닝 기술을 적용한다면 메꽃과 식물의 야외에서의 정확한 분류가 가능하고 이들 식물의 효과적인 관리와 모니터링에 활용할 수 있을 것으로 판단되었다.

Algal bloom is an ongoing issue in the management of freshwater systems for drinking water supply, and the chlorophyll-a concentration is commonly used to represent the status of algal bloom. Thus, the prediction of chlorophyll-a concentration is essential for the proper management of water quality. However, the chlorophyll-a concentration is affected by various water quality and environmental factors, so the prediction of its concentration is not an easy task. In recent years, many advanced machine learning algorithms have increasingly been used for the development of surrogate models to prediction the chlorophyll-a concentration in freshwater systems such as rivers or reservoirs. This study used a light gradient boosting machine(LightGBM), a gradient boosting decision tree algorithm, to develop an ensemble machine learning model to predict chlorophyll-a concentration. The field water quality data observed at Daecheong Lake, obtained from the real-time water information system in Korea, were used for the development of the model. The data include temperature, pH, electric conductivity, dissolved oxygen, total organic carbon, total nitrogen, total phosphorus, and chlorophyll-a. First, a LightGBM model was developed to predict the chlorophyll-a concentration by using the other seven items as independent input variables. Second, the time-lagged values of all the input variables were added as input variables to understand the effect of time lag of input variables on model performance. The time lag (i) ranges from 1 to 50 days. The model performance was evaluated using three indices, root mean squared error-observation standard deviation ration (RSR), Nash-Sutcliffe coefficient of efficiency (NSE) and mean absolute error (MAE). The model showed the best performance by adding a dataset with a one-day time lag (i=1) where RSR, NSE, and MAE were 0.359, 0.871 and 1.510, respectively. The improvement of model performance was observed when a dataset with a time lag up of about 15 days (i=15) was added.

In this paper, we propose a method for diagnosing overload and working load of collaborative robots through performance analysis of machine learning algorithms. To this end, an experiment was conducted to perform pick & place operation while changing the payload weight of a cooperative robot with a payload capacity of 10 kg. In this experiment, motor torque, position, and speed data generated from the robot controller were collected, and as a result of t-test and f-test, different characteristics were found for each weight based on a payload of 10 kg. In addition, to predict overload and working load from the collected data, machine learning algorithms such as Neural Network, Decision Tree, Random Forest, and Gradient Boosting models were used for experiments. As a result of the experiment, the neural network with more than 99.6% of explanatory power showed the best performance in prediction and classification. The practical contribution of the proposed study is that it suggests a method to collect data required for analysis from the robot without attaching additional sensors to the collaborative robot and the usefulness of a machine learning algorithm for diagnosing robot overload and working load.

PURPOSES : This study aims to develop and evaluate computer vision-based algorithms that classify the road roughness index (IRI) of road specimens with known IRIs. The presented study develops and compares classifier-based and deep learning-based models that can effectively determine pavement roughness grades. METHODS : A set road specimen was developed for various IRIs by generating road profiles with matching standard deviations. In addition, five distinct features from road images, including mean, peak-to-peak, standard variation, and mean absolute deviation, were extracted to develop a classifier-based model. From parametric studies, a support vector machine (SVM) was selected. To further demonstrate that the model is more applicable to real-world problems, with a non-integer road grade, a deep-learning model was developed. The algorithm was proposed by modifying the MNIST database, and the model input parameters were determined to achieve higher precision. RESULTS : The results of the proposed algorithms indicated the potential of using computer vision-based models for classifying road surface roughness. When SVM was adopted, near 100% precision was achieved for the training data, and 98% for the test data. Although the model indicated accurate results, the model was classified based on integer IRIs, which is less practical. Alternatively, a deep-learning model, which can be applied to a non-integer road grade, indicated an accuracy of over 85%. CONCLUSIONS : In this study, both the classifier-based, and deep-learning-based models indicated high precision for estimating road surface roughness grades. However, because the proposed algorithm has only been verified against the road model with fixed integers, optimization and verification of the proposed algorithm need to be performed for a real road condition.

본 연구는 효과적인 열전도를위한 거시적 구조 구성과 단위 구조 변화의 동시 설계를 위한 위상 최적화 방법을 제시한다. 거시적 규모의 구조 내에서 위치에 따른 단위 구조의 형태 변화는 거시적 규모뿐만 아니라 미시적 단위의 설계도 가능하며 등방성 단위 구조를 사용하는 것보다 더 나은 성능을 제공할 수 있다. 이 결과로 두 구성을 결합한 기능적으로 등급의 복합 구조가 생성된다. 대표 체적 요소 (RVE) 방법은 형태 변화에 따른 다중 재료 기반 단위 구조의 다양한 열전도 특성을 얻기 위해 적용된다. RVE 분석 결과를 바탕으 로 머신 러닝 기법을 이용하여 특정 형태의 단위 구조물의 물성치를 도출할 수 있다. 거시적 위상 최적화는 기존의 SIMP 방법을 사용하여 수행되며, 거시 구조를 구성하는 단위 구조는 동시 최적화 과정에 따라 열전도 성능을 향상시키기 위한 다양한 형태를 가질 수 있다. 제안된 방법의 효과를 확인하기 위해 열 컴플라이언스 최소화 문제의 수치예가 제공된다.

This study presents the estimation of crack depth by analyzing temperatures extracted from thermal images and environmental parameters such as air temperature, air humidity, illumination. The statistics of all acquired features and the correlation coefficient among thermal images and environmental parameters are presented. The concrete crack depths were predicted by four different machine learning models: Multi-Layer Perceptron (MLP), Random Forest (RF), Gradient Boosting (GB), and AdaBoost (AB). The machine learning algorithms are validated by the coefficient of determination, accuracy, and Mean Absolute Percentage Error (MAPE). The AB model had a great performance among the four models due to the non-linearity of features and weak learner aggregation with weights on misclassified data. The maximum depth 11 of the base estimator in the AB model is efficient with high performance with 97.6% of accuracy and 0.07% of MAPE. Feature importances, permutation importance, and partial dependence are analyzed in the AB model. The results show that the marginal effect of air humidity, crack depth, and crack temperature in order is higher than that of the others.

The increased turbidity in rivers during flood events has various effects on water environmental management, including drinking water supply systems. Thus, prediction of turbid water is essential for water environmental management. Recently, various advanced machine learning algorithms have been increasingly used in water environmental management. Ensemble machine learning algorithms such as random forest (RF) and gradient boosting decision tree (GBDT) are some of the most popular machine learning algorithms used for water environmental management, along with deep learning algorithms such as recurrent neural networks. In this study GBDT, an ensemble machine learning algorithm, and gated recurrent unit (GRU), a recurrent neural networks algorithm, are used for model development to predict turbidity in a river. The observation frequencies of input data used for the model were 2, 4, 8, 24, 48, 120 and 168 h. The root-mean-square error-observations standard deviation ratio (RSR) of GRU and GBDT ranges between 0.182~0.766 and 0.400~0.683, respectively. Both models show similar prediction accuracy with RSR of 0.682 for GRU and 0.683 for GBDT. The GRU shows better prediction accuracy when the observation frequency is relatively short (i.e., 2, 4, and 8 h) where GBDT shows better prediction accuracy when the observation frequency is relatively long (i.e. 48, 120, 160 h). The results suggest that the characteristics of input data should be considered to develop an appropriate model to predict turbidity.