With the recent surge in YouTube usage, there has been a proliferation of user-generated videos where individuals evaluate cosmetics. Consequently, many companies are increasingly utilizing evaluation videos for their product marketing and market research. However, a notable drawback is the manual classification of these product review videos incurring significant costs and time. Therefore, this paper proposes a deep learning-based cosmetics search algorithm to automate this task. The algorithm consists of two networks: One for detecting candidates in images using shape features such as circles, rectangles, etc and Another for filtering and categorizing these candidates. The reason for choosing a Two-Stage architecture over One-Stage is that, in videos containing background scenes, it is more robust to first detect cosmetic candidates before classifying them as specific objects. Although Two-Stage structures are generally known to outperform One-Stage structures in terms of model architecture, this study opts for Two-Stage to address issues related to the acquisition of training and validation data that arise when using One-Stage. Acquiring data for the algorithm that detects cosmetic candidates based on shape and the algorithm that classifies candidates into specific objects is cost-effective, ensuring the overall robustness of the algorithm.

This paper proposes an algorithm for the Unrelated Parallel Machine Scheduling Problem(UPMSP) without setup times, aiming to minimize total tardiness. As an NP-hard problem, the UPMSP is hard to get an optimal solution. Consequently, practical scenarios are solved by relying on operator's experiences or simple heuristic approaches. The proposed algorithm has adapted two methods: a policy network method, based on Transformer to compute the correlation between individual jobs and machines, and another method to train the network with a reinforcement learning algorithm based on the REINFORCE with Baseline algorithm. The proposed algorithm was evaluated on randomly generated problems and the results were compared with those obtained using CPLEX, as well as three scheduling algorithms. This paper confirms that the proposed algorithm outperforms the comparison algorithms, as evidenced by the test results.

목적 : 4차 산업혁명이 진행됨에 따라 타각적 굴절검사값, 수차 및 동공크기 등을 이용하여 최적의 안경처방값 을 도출해주는 머신러닝(machine learning)을 개발하고자 하였다. 방법: 시력에 영향을 줄 수 있는 안질환 및 전신질환이 없고 안구 수술 이력이 없는 근시안(1,000안)을 대상으로 진행하였다. I-Profilerplus(Zeiss, Berlin, Germany)를 사용하여 타각적 굴절이상도(objective-refraction) 및 안구수차(ocular wavefront-aberration), 동공 크기를 측정하였고, 자각적 굴절이상도(subjective-refraction)는 Visuphor500(Zeiss, Berlin, Germany)를 사용하여 구면 굴절력(S, Diopter), 원주 굴절력(C, Diopter), 난시 축(Ax, °)을 측정하였다. 측정 후, 파이썬(Python, version 3.10)을 이용하여 머신러닝 모델 생성 및 예측 성능을 확인하였다. 결과: 자각적 굴절이상도에서 구면 굴절력에 영향을 미치는 요인은 타각적 구면 굴절력, defocus aberration, spherical aberration, trefoil aberration 순으로 높았고, 원주 굴절력에 영향을 미치는 요인은 타각적 원주 굴 절력, defocus aberration, coma aberration, trefoil aberration 순으로 높았으며, 난시 축은 타각적 난시축만 영향을 미치는 것으로 나타났다. 구면 굴절력, 원주 굴절력, 난시 축의 자각적 굴절이상도와 머신러닝 예상값은 차이가 없는 것으로 나타났다(p=0.976, 0.948, and 0.349, respectively). 결론 : 자각적 굴절이상도를 예측하는 머신러닝 모델을 생성하였고, 해당 모델의 예측된 값과 자각적 굴절이상 도와 유의한 차이가 없는 것을 통해 예측 정확도를 확인하였으며 앞으로 개인 맞춤형 처방을 위한 정확한 안경처 방값을 도출하는데 기초자료가 될 수 있을 것으로 생각된다.

The increasing use of drones in terrorist attacks highlights the need for effective strategies to prevent and respond to drone terrorism. This study uses machine learning approach to identify factors that predict the success of drone terrorism and suggests policy alternatives for preventing such acts. Drone terrorism is becoming increasingly accessible due to advancements in information and communication technology, and events such as North Korea’s drone infiltration and the Russia-Ukraine war demonstrate the potential threat of drone attacks on Important National Facilities, including nuclear power plants. Using the Global Terrorism Database (GTD), this study analyzed drone terrorism incidents that occurred worldwide from 2016 to 2020. The study employed the Random Forest algorithm, which can incorporate multiple factors and their interactions, making it particularly suitable for social science research. The study provides new insights by deriving predictors that were previously overlooked in empirical analyses of drone terrorism. The findings of this study can aid in the establishment of anti-terrorism policies aimed at addressing the growing threat of drone terrorism. This can include the organization and expansion of the crisis management governance terrorism response council, the creation of a working manual through the partial revision of laws concerning drone terrorism response, and the implementation of anti-drone equipment and systems. Ultimately, the insights gained from this study can provide development of effective strategies aimed at preventing and responding to drone attacks. The study highlights the importance of proactive measures to mitigate the risks posed by drone technology in the context of terrorism.

Recently, many studies are being conducted to extract emotion from text and verify its information power in the field of finance, along with the recent development of big data analysis technology. A number of prior studies use pre-defined sentiment dictionaries or machine learning methods to extract sentiment from the financial documents. However, both methods have the disadvantage of being labor-intensive and subjective because it requires a manual sentiment learning process. In this study, we developed a financial sentiment dictionary that automatically extracts sentiment from the body text of analyst reports by using modified Bayes rule and verified the performance of the model through a binary classification model which predicts actual stock price movements. As a result of the prediction, it was found that the proposed financial dictionary from this research has about 4% better predictive power for actual stock price movements than the representative Loughran and McDonald’s (2011) financial dictionary. The sentiment extraction method proposed in this study enables efficient and objective judgment because it automatically learns the sentiment of words using both the change in target price and the cumulative abnormal returns. In addition, the dictionary can be easily updated by re-calculating conditional probabilities. The results of this study are expected to be readily expandable and applicable not only to analyst reports, but also to financial field texts such as performance reports, IR reports, press articles, and social media.

Research and interest in sustainable printing are increasing in the packaging printing industry. Currently, predicting the amount of ink required for each work is based on the experience and intuition of field workers. Suppose the amount of ink produced is more than necessary. In this case, the rest of the ink cannot be reused and is discarded, adversely affecting the company's productivity and environment. Nowadays, machine learning models can be used to figure out this problem. This study compares the ink usage prediction machine learning models. A simple linear regression model, Multiple Regression Analysis, cannot reflect the nonlinear relationship between the variables required for packaging printing, so there is a limit to accurately predicting the amount of ink needed. This study has established various prediction models which are based on CART (Classification and Regression Tree), such as Decision Tree, Random Forest, Gradient Boosting Machine, and XGBoost. The accuracy of the models is determined by the K-fold cross-validation. Error metrics such as root mean squared error, mean absolute error, and R-squared are employed to evaluate estimation models' correctness. Among these models, XGBoost model has the highest prediction accuracy and can reduce 2134 (g) of wasted ink for each work. Thus, this study motivates machine learning's potential to help advance productivity and protect the environment.

The management of algal bloom is essential for the proper management of water supply systems and to maintain the safety of drinking water. Chlorophyll-a(Chl-a) is a commonly used indicator to represent the algal concentration. In recent years, advanced machine learning models have been increasingly used to predict Chl-a in freshwater systems. Machine learning models show good performance in various fields, while the process of model development requires considerable labor and time by experts. Automated machine learning(auto ML) is an emerging field of machine learning study. Auto ML is used to develop machine learning models while minimizing the time and labor required in the model development process. This study developed an auto ML to predict Chl-a using auto sklearn, one of most widely used open source auto ML algorithms. The model performance was compared with other two popular ensemble machine learning models, random forest(RF) and XGBoost(XGB). The model performance was evaluated using three indices, root mean squared error, root mean squared error-observation standard deviation ratio(RSR) and Nash-Sutcliffe coefficient of efficiency. The RSR of auto ML, RF, and XGB were 0.659, 0.684 and 0.638, respectively. The results shows that auto ML outperforms RF, and XGB shows better prediction performance than auto ML, while the differences between model performances were not significant. Shapley value analysis, an explainable machine learning algorithm, was used to provide quantitative interpretation about the model prediction of auto ML developed in this study. The results of this study present the possible applicability of auto ML for the prediction of water quality.

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.

The color image of the brand comes first and is an important visual element that leads consumers to the consumption of the product. To express more effectively what the brand wants to convey through design, the printing market is striving to print accurate colors that match the intention. In ‘offset printing’ mainly used in printing, colors are often printed in CMYK (Cyan, Magenta, Yellow, Key) colors. However, it is possible to print more accurate colors by making ink of the desired color instead of dotting CMYK colors. The resulting ink is called ‘spot color’ ink. Spot color ink is manufactured by repeating the process of mixing the existing inks. In this repetition of trial and error, the manufacturing cost of ink increases, resulting in economic loss, and environmental pollution is caused by wasted inks. In this study, a deep learning algorithm to predict printed spot colors was designed to solve this problem. The algorithm uses a single DNN (Deep Neural Network) model to predict printed spot colors based on the information of the paper and the proportions of inks to mix. More than 8,000 spot color ink data were used for learning, and all color was quantified by dividing the visible light wavelength range into 31 sections and the reflectance for each section. The proposed algorithm predicted more than 80% of spot color inks as very similar colors. The average value of the calculated difference between the actual color and the predicted color through ‘Delta E’ provided by CIE is 5.29. It is known that when Delta E is less than 10, it is difficult to distinguish the difference in printed color with the naked eye. The algorithm of this study has a more accurate prediction ability than previous studies, and it can be added flexibly even when new inks are added. This can be usefully used in real industrial sites, and it will reduce the attempts of the operator by checking the color of ink in a virtual environment. This will reduce the manufacturing cost of spot color inks and lead to improved working conditions for workers. In addition, it is expected to contribute to solving the environmental pollution problem by reducing unnecessarily wasted ink.

본 논문은 딥러닝 알고리즘을 이용하여 딸기 영상 데이터의 병충해 존재 여부를 자동으로 검출할 수 있는 서비스 모델을 제안한다. 또한 병징에 특화된 분할 이미지 데이터 세트를 제 안하여 딥러닝 모델의 병충해 검출 성능을 향상한다. 딥러닝모델은 CNN 기반 YOLO를 선정하여 기존의 R-CNN 기반 모델의 느린 학습속도와 추론속도를 개선하였다. 병충해 검 출 모델을 학습하기 위해 일반적인 데이터 세트와 제안하는 분할 이미지 데이터 세트를 구축하였다. 딥러닝 모델이 일반 적인 학습 데이터 세트를 학습했을 때 병충해 검출률은 81.35%이며 병충해 검출 신뢰도는 73.35%이다. 반면 딥러닝 모델이 분할 이미지 학습 데이터 세트를 학습했을 때 병충해 검출률은 91.93%이며 병충해 검출 신뢰도는 83.41%이다. 따 라서 분할 이미지 데이터를 학습한 딥러닝 모델의 성능이 우 수하다는 것을 증명할 수 있었다.

본 연구는 데이터를 기반으로 한 인공지능 기계학습 기법을 활용하여 온실 내부온도 예측 시뮬레이션 모델을 개발을 수행 하였다. 온실 시스템의 내부온도 예측을 위해서 다양한 방법 이 연구됐지만, 가외 변인으로 인하여 기존 시뮬레이션 분석 방법은 낮은 정밀도의 문제점을 지니고 있다. 이러한 한계점 을 극복하기 위하여 최근 개발되고 있는 데이터 기반의 기계 학습을 활용하여 온실 내부온도 예측 모델 개발을 수행하였 다. 기계학습모델은 데이터 수집, 특성 분석, 학습을 통하여 개 발되며 매개변수와 학습방법에 따라 모델의 정확도가 크게 변 화된다. 따라서 데이터 특성에 따른 최적의 모델 도출방법이 필요하다. 모델 개발 결과 숨은층 증가에 따라 모델 정확도가 상승하였으며 최종적으로 GRU 알고리즘과 숨은층 6에서 r2 0.9848과 RMSE 0.5857℃로 최적 모델이 도출되었다. 본 연 구를 통하여 온실 외부 데이터를 활용하여 온실 내부온도 예 측 모델 개발이 가능함을 검증하였으며, 추후 다양한 온실데이 터에 적용 및 비교분석이 수행되어야 한다. 이후 한 단계 더 나아 가 기계학습모델 예측(predicted) 결과를 예보(forecasting)단 계로 개선하기 위해서 데이터 시간 길이(sequence length)에 따른 특성 분석 및 계절별 기후변화와 작물에 따른 사례별로 개발 모델을 관리하는 등의 다양한 추가 연구가 수행되어야 한다.

Recently, machine learning is widely used to solve optimization problems in various engineering fields. In this study, machine learning is applied to development of a control algorithm for a smart control device for reduction of seismic responses. For this purpose, Deep Q-network (DQN) out of reinforcement learning algorithms was employed to develop control algorithm. A single degree of freedom (SDOF) structure with a smart tuned mass damper (TMD) was used as an example structure. A smart TMD system was composed of MR (magnetorheological) damper instead of passive damper. Reward design of reinforcement learning mainly affects the control performance of the smart TMD. Various hyperparameters were investigated to optimize the control performance of DQN-based control algorithm. Usually, decrease of the time step for numerical simulation is desirable to increase the accuracy of simulation results. However, the numerical simulation results presented that decrease of the time step for reward calculation might decrease the control performance of DQN-based control algorithm. Therefore, a proper time step for reward calculation should be selected in a DQN training process.

It is important to ensure worker’s safety from radiation hazard in decommissioning site. Real-time tracking of worker’s location is one of the factors necessary to detect radiation hazard in advance. In this study, the integrated algorithm for worker tracking has been developed to ensure the safety of workers. There are three essential techniques needed to track worker’s location, which are object detection, object tracking, and estimating location (stereo vision). Above all, object detection performance is most important factor in this study because the performance of tracking and estimating location is depended on worker detection level. YOLO (You Only Look Once version 5) model capable of real-time object detection was applied for worker detection. Among the various YOLO models, a model specialized for person detection was considered to maximize performance. This model showed good performance for distinguishing and detecting workers in various occlusion situations that are difficult to detect correctly. Deep SORT (Simple Online and Realtime Tracking) algorithm which uses deep learning technique has been considered for object tracking. Deep SORT is an algorithm that supplements the existing SORT method by utilizing the appearance information based on deep learning. It showed good tracking performance in the various occlusion situations. The last step is to estimate worker’s location (x-y-z coordinates). The stereo vision technique has been considered to estimate location. It predicts xyz location using two images obtained from stereo camera like human eyes. Two images are obtained from stereo camera and these images are rectified based on camera calibration information in the integrated algorithm. And then workers are detected from the two rectified images and the Deep SORT tracks workers based on worker’s position and appearance between previous frames and current frames. Two points of workers having same ID in two rectified images give xzy information by calculating depth estimation of stereo vision. The integrated algorithm developed in this study showed sufficient possibility to track workers in real time. It also showed fast speed to enable real-time application, showing about 0.08 sec per two frames to detect workers on a laptop with high-performance GPU (RTX 3080 laptop version). Therefore, it is expected that this algorithm can be sufficiently used to track workers in real decommissioning site by performing additional parameter optimization.