• Korean Journal of Radiology
• /
• v.23 no.3
• /
• pp.343-354
• /
• 2022

Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.

• Steel and Composite Structures
• /
• v.52 no.1
• /
• pp.31-43
• /
• 2024

A very widely used analytical method (mathematical model), mentioned in Eurocode 3, to examine the connections' bending behavior is the component-based method that has certain weak points shown in the plastic behavior part of the moment-rotation curves. In the component method available in Eurocode 3, for simplicity, the effect of strain hardening is omitted, and the bending behavior of the connection is modeled with the help of a two-line diagram. To make the component method more efficient and reliable, this research proposed its advanced version, wherein the plastic part of the diagram was developed beyond the guidelines of the mentioned Regulation, implemented to connect the end plate, and verified with the moment-rotation curves found from the laboratory model and the finite element method in ABAQUS. The findings indicated that the advanced component method (the method developed in this research) could predict the plastic part of the moment-rotation curve as well as the conventional component-based method in Eurocode 3. The comparison between the laboratory model and the outputs of the conventional and advanced component methods, as well as the outputs of the finite elements approach using ABAQUS, revealed a different percentage in the ultimate moment for bolt-extended end-plate connections. Specifically, the difference percentages were -31.56%, 2.46%, and 9.84%, respectively. Another aim of this research was to determine the optimal dimensions of the end plate joint to reduce costs without letting the mechanical constraints related to the bending moment and the resulting initial stiffness, are not compromised as well as the safety and integrity of the connection. In this research, the thickness and dimensions of the end plate and the location and diameter of the bolts were the design variables, which were optimized using Particle Swarm Optimization (PSO), Snake Optimization (SO), and Teaching Learning-Based Optimization (TLBO) to minimization the connection cost of the end plate connection. According to the results, the TLBO method yielded better solutions than others, reducing the connection costs from 43.97 to 17.45€ (60.3%), which shows the method's proper efficiency.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.1-17
• /
• 2017

The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.1-23
• /
• 2014

Market forecasting aims to estimate the sales volume of a product or service that is sold to consumers for a specific selling period. From the perspective of the enterprise, accurate market forecasting assists in determining the timing of new product introduction, product design, and establishing production plans and marketing strategies that enable a more efficient decision-making process. Moreover, accurate market forecasting enables governments to efficiently establish a national budget organization. This study aims to generate a market growth curve for ICT (information and communication technology) goods using past time series data; categorize products showing similar growth patterns; understand markets in the industry; and forecast the future outlook of such products. This study suggests the useful and meaningful process (or methodology) to identify the market growth pattern with quantitative growth model and data mining algorithm. The study employs the following methodology. At the first stage, past time series data are collected based on the target products or services of categorized industry. The data, such as the volume of sales and domestic consumption for a specific product or service, are collected from the relevant government ministry, the National Statistical Office, and other relevant government organizations. For collected data that may not be analyzed due to the lack of past data and the alteration of code names, data pre-processing work should be performed. At the second stage of this process, an optimal model for market forecasting should be selected. This model can be varied on the basis of the characteristics of each categorized industry. As this study is focused on the ICT industry, which has more frequent new technology appearances resulting in changes of the market structure, Logistic model, Gompertz model, and Bass model are selected. A hybrid model that combines different models can also be considered. The hybrid model considered for use in this study analyzes the size of the market potential through the Logistic and Gompertz models, and then the figures are used for the Bass model. The third stage of this process is to evaluate which model most accurately explains the data. In order to do this, the parameter should be estimated on the basis of the collected past time series data to generate the models' predictive value and calculate the root-mean squared error (RMSE). The model that shows the lowest average RMSE value for every product type is considered as the best model. At the fourth stage of this process, based on the estimated parameter value generated by the best model, a market growth pattern map is constructed with self-organizing map algorithm. A self-organizing map is learning with market pattern parameters for all products or services as input data, and the products or services are organized into an $N{\times}N$ map. The number of clusters increase from 2 to M, depending on the characteristics of the nodes on the map. The clusters are divided into zones, and the clusters with the ability to provide the most meaningful explanation are selected. Based on the final selection of clusters, the boundaries between the nodes are selected and, ultimately, the market growth pattern map is completed. The last step is to determine the final characteristics of the clusters as well as the market growth curve. The average of the market growth pattern parameters in the clusters is taken to be a representative figure. Using this figure, a growth curve is drawn for each cluster, and their characteristics are analyzed. Also, taking into consideration the product types in each cluster, their characteristics can be qualitatively generated. We expect that the process and system that this paper suggests can be used as a tool for forecasting demand in the ICT and other industries.

• Journal of the Korea Society for Simulation
• /
• v.32 no.4
• /
• pp.19-26
• /
• 2023

The increase in the dropout rate of college students nationwide has a serious negative impact on universities and society as well as individual students. In order to proactive identify students at risk of dropout, this study built a decision tree, random forest, logistic regression, and deep learning-based dropout prediction model using academic data that can be easily obtained from each university's academic management system. Their performances were subsequently analyzed and compared. The analysis revealed that while the logistic regression-based prediction model exhibited the highest recall rate, its f-1 value and ROC-AUC (Receiver Operating Characteristic - Area Under the Curve) value were comparatively lower. On the other hand, the random forest-based prediction model demonstrated superior performance across all other metrics except recall value. In addition, in order to assess model performance over distinct prediction periods, we divided these periods into short-term (within one semester), medium-term (within two semesters), and long-term (within three semesters). The results underscored that the long-term prediction yielded the highest predictive efficacy. Through this study, each university is expected to be able to identify students who are expected to be dropped out early, reduce the dropout rate through intensive management, and further contribute to the stabilization of university finances.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.2236-2257
• /
• 2020

Ransomware is malicious software that encrypts the user-related files and data and holds them to ransom. Such attacks have become one of the serious threats to cyberspace. The avoidance techniques that ransomware employs such as obfuscation and/or packing makes it difficult to analyze such programs statically. Although many ransomware detection studies have been conducted, they are limited to a small portion of the attack's characteristics. To this end, this paper proposed a framework for the behavioral-based dynamic analysis of high survivable ransomware (HSR) with integrated valuable feature sets. Term Frequency-Inverse document frequency (TF-IDF) was employed to select the most useful features from the analyzed samples. Support Vector Machine (SVM) and Artificial Neural Network (ANN) were utilized to develop and implement a machine learning-based detection model able to recognize certain behavioral traits of high survivable ransomware attacks. Experimental evaluation indicates that the proposed framework achieved an area under the ROC curve of 0.987 and a few false positive rates 0.007. The experimental results indicate that the proposed framework can detect high survivable ransomware in the early stage accurately.

• The Journal of Korean Association of Computer Education
• /
• v.5 no.1
• /
• pp.99-108
• /
• 2002

As window programming and internet programming are more required, requirement of the training on the object-oriented programming and the object oriented software development are growing. But, it is not easy to learn new brand methodologies or techniques. In this paper, we tried to apply software reuse to object modeling education for effective learning of new programming and modeling method. In this paper, we present analogical matching techniques for the reuse of object models and patterns in object modeling education. Analogy-based matching is better than keyword-based retrieval for model reuse. Reuse can help to reduce the learning curve of object modeling. Also, by applying analogical reasoning, the performance of retrieval is better than keyword-based retrieval.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.175-175
• /
• 2023

Detection and monitoring of wildfires are essential for limiting their harmful effects on ecosystems, human lives, and property. In this research, we propose a novel method running in the Google Earth Engine platform for identifying and characterizing burnt regions using a hybrid of Sentinel-1 (C-band synthetic aperture radar) and Sentinel-2 (multispectral photography) images. The 2022 Uljin wildfire, the severest event in South Korean history, is the primary area of our investigation. Given its documented success in remote sensing and land cover categorization applications, we select the Random Forest (RF) method as our primary classifier. Next, we evaluate the performance of our model using multiple accuracy measures, including overall accuracy (OA), Kappa coefficient, and area under the curve (AUC). The proposed method shows the accuracy and resilience of wildfire identification compared to traditional methods that depend on survey data. These results have significant implications for the development of efficient and dependable wildfire monitoring systems and add to our knowledge of how machine learning and remote sensing-based approaches may be combined to improve environmental monitoring and management applications.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.159-166
• /
• 2020

The purpose of this research is to suggest some practical and policy implications for improving adolescent's self-esteem through analyzing longitudinally the effects of parental attitude, peer relationship, student-teacher relationship, school learning activity, life-goal on adolescent's self-esteem by using latent growth curve model. Analytical data was obtained from the KYCPS. The analytical results showed that the change model of adolescent's self_esteem turned out to be a leaner model in which the change rate and intercept were significant. Second, time dependent variables influence on adolescent's self_ esteem meaningfully. Third, time dependent variables influence on adolescent's self_ esteem changes significantly. This study proposed some policy implications basing on these findings.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.28 no.3
• /
• pp.129-139
• /
• 2024

In this study, the SBC system, a new mechanical joint method, was developed to improve the constructability of precast concrete (PC) beam-column connections. The reliability of the finite element analysis model was verified through the comparison of experimental results and FEM analysis results. Recently, the intermediate moment frame, a seismic force resistance system, has served as a ramen structure that resists seismic force through beams and columns and has few load-bearing walls, so it is increasingly being applied to PC warehouses and PC factories with high loads and long spans. However, looking at the existing PC beam-column anchorage details, the wire, strand, and lower main bar are overlapped with the anchorage rebar at the end, so they do not satisfy the joint and anchorage requirements for reinforcing bars (KDS 41 17 00 9.3). Therefore, a mechanical joint method (SBC) was developed to meet the relevant standards and improve constructability. Tensile and bending experiments were conducted to examine structural performance, and a finite element analysis model was created. The load-displacement curve and failure pattern confirmed that both the experimental and analysis results were similar, and it was verified that a reliable finite element analysis model was built. In addition, bending tests showed that the larger the thickness of the bolt joint surface of the SBC, the better its structural performance. It was also determined that the system could improve energy dissipation ability and ductility through buckling and yielding occurring in the SBC.