• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.23-31
• /
• 2023

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.

• Computers and Concrete
• /
• 제31권2호
• /
• pp.85-95
• /
• 2023

Natural pozzolans are used as additives in cement to develop more durable and high-performance concrete. Pozzolanic activity index (PAI) is important for assessing the performance of a pozzolan as a binding material and has an important effect on the compressive strength, permeability, and chemical durability of concrete mixtures. However, the determining of the 28 days (short term) and 90 days (long term) PAI of concrete mixtures is a time-consuming process. In this study, to reduce extensive experimental work, it is aimed to predict the short term and long term PAIs as a function of the chemical compositions of various natural pozzolans. For this purpose, the chemical compositions of various natural pozzolans from Central Anatolia were determined with X-ray fluorescence spectroscopy. The mortar samples were prepared with the natural pozzolans and then, the short term and the long term PAIs were calculated based on compressive strength method. The effect of the natural pozzolans' chemical compositions on the short term and the long term PAIs were evaluated and the PAIs were predicted by using multiple linear regression (MLR) and adaptive neuro-fuzzy inference system (ANFIS) model. The prediction model results show that both reactive SiO₂ and SiO₂+Al₂O₃+Fe₂O₃ contents are the most effective parameters on PAI. According to the performance of prediction models determined with metrics such as root mean squared error (RMSE) and coefficient of correlation (R²), ANFIS models are more feasible than the multiple regression model in predicting the 28 days and 90 days pozzolanic activity. Estimation of PAIs based on the chemical component of natural pozzolana with high-performance prediction models is going to make an important contribution to material engineering applications in terms of selection of favorable natural pozzolana and saving time from tedious test processes.

• International Journal of Computer Science & Network Security
• /
• 제23권7호
• /
• pp.219-230
• /
• 2023

Wireless Body Area Networks (WBANs) have made it easier for healthcare workers and patients to monitor patients' status continuously in real time. WBANs have complex and diverse network structures; thus, management and control can be challenging. Therefore, considering emerging Software-defined networks (SDN) with WBANs is a promising technology since SDN implements a new network management and design approach. The SDN concept is used in this study to create more adaptable and dynamic network architectures for WBANs. The study focuses on comparing the performance of two SDN controllers, POX and Ryu, using Mininet, an open-source simulation tool, to construct network topologies. The performance of the controllers is evaluated based on bandwidth, throughput, and round-trip time metrics for networks using an OpenFlow switch with sixteen nodes and a controller for each topology. The study finds that the choice of network controller can significantly impact network performance and suggests that monitoring network performance indicators is crucial for optimizing network performance. The project provides valuable insights into the performance of SDN-based WBANs using POX and Ryu controllers and highlights the importance of selecting the appropriate network controller for a given network architecture.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.792-799
• /
• 2022

Building Information Modeling (BIM) technology is a key component of modern construction engineering and project management workflows. As-is BIM models that represent the spatial reality of a project site can offer crucial information to stakeholders for construction progress monitoring, error checking, and building maintenance purposes. Geometric methods for automatically converting raw scan data into BIM models (Scan-to-BIM) often fail to make use of higher-level semantic information in the data. Whereas, semantic segmentation methods only output labels at the point level without creating object level models that is necessary for BIM. To address these issues, this research proposes a hybrid semantic-geometric approach for clutter-resistant floorplan generation from laser-scanned building point clouds. The input point clouds are first pre-processed by normalizing the coordinate system and removing outliers. Then, a semantic segmentation network based on PointNet++ is used to label each point as ceiling, floor, wall, door, stair, and clutter. The clutter points are removed whereas the wall, door, and stair points are used for 2D floorplan generation. A region-growing segmentation algorithm paired with geometric reasoning rules is applied to group the points together into individual building elements. Finally, a 2-fold Random Sample Consensus (RANSAC) algorithm is applied to parameterize the building elements into 2D lines which are used to create the output floorplan. The proposed method is evaluated using the metrics of precision, recall, Intersection-over-Union (IOU), Betti error, and warping error.

• 보건의료기술평가
• /
• 제1권1호
• /
• pp.22-26
• /
• 2013

Objectives: Balancing benefits and risks through the drug life cycle has been discussed for many decades. The objective of this study was to review the processes and tools currently proposed for benefit-risk assessment of medicinal drugs. It aimed to establish scientific and efficient drug safety management system based on the synthetic analysis of benefit-risk evidence. Methods: We conducted a review of exiting literatures published by regulatory agencies or initiatives. Not only quantitative methodologies but also qualitative method were compared to understand their key characteristics for the benefit and risk assessment of drugs. Results: Recently, benefit-risk assessments have more structured approaches to decision making as part of regulatory science. Regulatory agencies such as European Medicines Agency, FDA have prepared plans to apply benefit-risk assessment to regulatory decision making. Also many initiatives such as IMI (Innovative Medicine Initiative) have conducted research and published reports about benefit-risk assessment. For benefit-risk assessment, four kinds of methods are necessary. Frameworks such as BRAT (Benefit Risk Action Team) framework, PrOACT-URL provide guidance for the whole process of decision-making. Metrics are measurements of risk benefit. The estimation techniques are methods to synthesis and combine evidences from various sources. The utility survey techniques are necessary to explicit preferences of various outcome from stakeholders. Conclusion: There is the lack of widely accepted, validated model for benefit-risk assessment. Nor there is an agreement among academia, industry, and government on methods for the quantitative valuation. It is also limited by available evidence and underlying assumptions. Nevertheless, benefit-risk assessment is fundamental to improve transparency, consistency and predictability for decision making through the structured systematic approaches.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.80-80
• /
• 2022

Estimation of heading date of paddy rice is laborious and time consuming. Therefore, automatic estimation of heading date of paddy rice is highly essential. In this experiment, deep learning classification models were used to classify two difference categories of rice (vegetative and reproductive stage) based on the panicle initiation of paddy field. Specifically, the dataset includes 444 slanted view images belonging to two categories and was then expanded to include 1,497 images via IMGAUG data augmentation technique. We adopt two transfer learning strategies: (First, used transferring model weights already trained on ImageNet to six classification network models: VGGNet, ResNet, DenseNet, InceptionV3, Xception and MobileNet, Second, fine-tuned some layers of the network according to our dataset). After training the CNN model, we used several evaluation metrics commonly used for classification tasks, including Accuracy, Precision, Recall, and F1-score. In addition, GradCAM was used to generate visual explanations for each image patch. Experimental results showed that the InceptionV3 is the best performing model in terms of the accuracy, average recall, precision, and F1-score. The fine-tuned InceptionV3 model achieved an overall classification accuracy of 0.95 with a high F1-score of 0.95. Our CNN model also represented the change of rice heading date under different date of transplanting. This study demonstrated that image based deep learning model can reliably be used as an automatic monitoring system to detect the heading date of rice crops using CCTV camera.

• 치위생과학회지
• /
• 제23권3호
• /
• pp.193-198
• /
• 2023

Background: The nose is located at the center of the face, and it is possible to determine race, sex, and the like. Research using the nasal index (NI) classification method to classify the shape of the nose is currently in progress. However, domestic research is required as most research is being conducted abroad. In this study, we used a 3D program to confirm the ratio of the nose shape of Koreans. Methods: One hundred patients (50 males and 50 females) in their 20s were evaluated (IRB approval no. DKUDH IRB 2020-01-007). Cone beam computed tomography was performed using the Mimics ver.22 (Materialise Co., Leuven, Belgium) 3D program to model the patient's skull and soft tissues into three views: coronal, sagittal, and frontal. To confirm the ratio of measurement metrics, analysis was performed using the SPSS ver. 23.0 (IBM Co., Armonk, NY, USA) program. Results: Ten leptorrhine (long and narrow) type, 76 mesorrhine (moderate shape) type, and 14 platyrrhine (broad and short) type noses were observed. In addition, as a result of sex comparison, five males had the leptorrhine (long and narrow) type, 40 mesorrhine (moderate shape), and five platyrrhine (broad and short) types. For females, five patients had the leptorrhine (long and narrow) type, 36 patients had the mesorrhine (moderate shape) type, and nine patients had the platyrrhine (broad and short) type. Conclusion: This study will be helpful when performing nose-related surgeries and procedures in clinical practice and for similar studies in the future.

• Journal of Trauma and Injury
• /
• 제36권3호
• /
• pp.231-241
• /
• 2023

Purpose: Overtriage and undertriage rates are critical metrics in trauma, influenced by both trauma team activation (TTA) criteria and compliance with these criteria. Analysis of undertriaged patients at a level I trauma center revealed suboptimal compliance with existing criteria. This study assessed triage patterns after implementing compliance-focused process interventions. Methods: A physician-driven, free-text alert system was modified to a nonphysician, hospital dispatcher-guided system. The latter employed dropdown menus to maximize compliance with criteria. The preintervention period included patients who presented between May 12, 2020, and December 31, 2020. The postintervention period incorporated patients who presented from May 12, 2021, through December 31, 2021. We evaluated appropriate triage, overtriage, and undertriage using the Standardized Trauma Assessment Tool. Statistical analyses were conducted with an α level of 0.05. Results: The new system was associated with improved compliance with existing TTA criteria (from 70.3% to 79.3%, P=0.023) and decreased undertriage (from 6.0% to 3.2%, P=0.002) at the expense of increasing overtriage (from 46.6% to 57.4%, P<0.001), ultimately decreasing the appropriate triage rate (from 78.4% to 74.6%, P=0.007). Conclusions: This study assessed a workflow change designed to improve compliance with TTA criteria. Improved compliance decreased undertriage to below the target threshold of 5%, albeit at the expense of increased overtriage. The decrease in appropriate triage despite compliance improvements suggests that the current criteria at this institution are not adequately tailored to optimally balance the minimization of undertriage and overtriage. This finding underscores the importance of improved compliance in evaluating the efficacy of TTA criteria.

• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.57-69
• /
• 2024

Crop classification plays a vitalrole in monitoring agricultural landscapes and enhancing food production. In this study, we explore the effectiveness of Long Short-Term Memory (LSTM) models for crop classification, focusing on distinguishing between apple and rice crops. The aim wasto overcome the challenges associatedwith finding phenology-based classification thresholds by utilizing LSTM to capture the entire Normalized Difference Vegetation Index (NDVI)trend. Our methodology involvestraining the LSTM model using a reference site and applying it to three separate three test sites. Firstly, we generated 25 NDVI imagesfrom the Sentinel-2A data. Aftersegmenting study areas, we calculated the mean NDVI values for each segment. For the reference area, employed a training approach utilizing the NDVI trend line. This trend line served as the basis for training our crop classification model. Following the training phase, we applied the trained model to three separate test sites. The results demonstrated a high overall accuracy of 0.92 and a kappa coefficient of 0.85 for the reference site. The overall accuracies for the test sites were also favorable, ranging from 0.88 to 0.92, indicating successful classification outcomes. We also found that certain phenological metrics can be less effective in crop classification therefore limitations of relying solely on phenological map thresholds and emphasizes the challenges in detecting phenology in real-time, particularly in the early stages of crops. Our study demonstrates the potential of LSTM models in crop classification tasks, showcasing their ability to capture temporal dependencies and analyze timeseriesremote sensing data.While limitations exist in capturing specific phenological events, the integration of alternative approaches holds promise for enhancing classification accuracy. By leveraging advanced techniques and considering the specific challenges of agricultural landscapes, we can continue to refine crop classification models and support agricultural management practices.

• 정보보호학회논문지
• /
• 제33권5호
• /
• pp.847-859
• /
• 2023

최근 국내에서 소프트웨어의 취약점을 이용한 악성코드로 피해가 증가하는 가운데 악성코드를 막기 위한 안티바이러스 설치는 필수사항이라 할 수 있다. 하지만 일반 사용자는 어떠한 안티바이러스 제품의 성능이 좋은지 자신의 환경에 적합한지를 알기란 쉽지 않다. 국외에 안티바이러스 성능에 대한 정보를 제공해주는 기관이 다수 존재하고 이런 기관들은 자체 테스트 환경과 시험평가 항목을 수립하여 테스트를 진행하고 있으나, 자세한 테스트 환경 정보, 세부적인 시험평가 항목 및 결과는 공개하지 않는다. 또한 기존 품질평가 연구들은 안티바이러스 제품 평가에는 부합되지 않는 평가 기준이 다수 존재하는 등의 이유로 최신 안티바이러스 평가에는 적절하지 않다. 그래서 본 논문에서는 최신 안티바이러스 평가에 적합한 세부적인 안티바이러스 평가지표를 수립하고 이를 국내외 9종의 안티바이러스 제품에 적용하여 안티바이러스의 기능 및 성능을 검증하였다.