• Journal of Intelligence and Information Systems
• /
• v.12 no.2
• /
• pp.167-183
• /
• 2006

Since data mining attempts to find unknown facts or rules by dealing with also vaguely-known data sets, it always suffers from high error rate. In order to reduce the error rate, many researchers have employed multiple models in solving a problem. In this research, we present a new type of multiple models, called DyMoS, whose unique feature is that it classifies the input data and applies the different model developed appropriately for each class of data. In order to evaluate the performance of DyMoS, we applied it to a real customer churn problem of an automobile insurance company, The result shows that the DyMoS outperformed any model which employed only one data mining technique such as artificial neural network, decision tree and case-based reasoning.

• English Language & Literature Teaching
• /
• v.8 no.1
• /
• pp.165-198
• /
• 2002

The purpose of this research is to improve the writing ability of students by an ideal test model of English writing based on strategies of procedural learning stages enhancing the level of students' writing ability. Assessment of writing in the field of English education has been limited so far to very restricted areas with no appropriate scientific scrutiny. Assessment is really meaningful only when it exactly estimates the ability of students. Since English writing competence has become indispensable in this era of global village, writing instruction should be most emphasized. The most forceful method of busting writing instruction is to utilize the so-called washback effect of testing. So, to develop a good test model of writing, the first thing that is required is to inspect writing strategy in steps and, then, testing itself. First of all, analyzed with a special reference to the 6th high school English curriculum were the goals and contents of the syllabus reflected in one kind of junior high textbook and eight different kinds of senior high textbooks. Then questionnaires on the whole area of writing and tendencies of English writing classes were given to 100 English teachers, 300 students. The results of questionnaires were statistically analyzed. Then, some suggestions and opinions about the questioning method were made: the procedural strategy in steps, English writing instruction and test model of assessment were applied to the syllabus referring to teaching plans. On the bases of the results of the questionnaires, three pretests and a final test of English writing were administered to verify the effect of enhanced English writing competence which had been gradually promoted and, through the promotion, produced the test criteria of English writing. In conclusion, guidance and evaluation of English writing through in steps are really indispensable to increase student's practical ability and, accordingly, we are in need of the development of a testing method of useful writing practiced in school class above anything else. So, it is necessary to further the study on methods to assess writing ability on the bases of participation and fluency of students with their keen interest in English. Also, to intensify the effect of the test model, more accommodating reorganization of syllabus is required in our education. For instance, we need a flexible operation in organizing time units from the current 50 minutes to 100-130 minutes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.4
• /
• pp.737-744
• /
• 2007

It need estimation model who is efficient and estimate correctly organization's information security level to achieve effectively organization's information security target. Also, estimate class information security level for this and need reformable estimation indicator or standard and estimation methodology of information security systems that application is possible should be studied in our country. Therefore many research centers including ISO are preparing the measuring and evaluating method for network duality. This study will represent an evaluating model for network security based on checklist. In addition, we propose ah measuring and evaluating method for network performance. The purpose of two studies is to present the evaluating procedure and method for measuring security of network on set workwill be identified and a measuring method and procedure will be proposed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.199-206
• /
• 2022

A malfunction or breakdown of a manufacturing facility leads to product defects and the suspension of production lines, resulting in huge financial losses for manufacturers. Due to the spread of smart factory services, a large amount of data is being collected in factories, and AI-based research is being conducted to predict and diagnose manufacturing facility breakdowns or manufacturing site efficiency. However, because of the characteristics of manufacturing data, such as a severe class imbalance about abnormalities and ambiguous label information that distinguishes abnormalities, developing classification or anomaly detection models is highly difficult. In this paper, we present an deep learning algorithm for anomaly detection of a manufacturing facility using reconstruction loss of CNN-based model and ananlyze its performance. The algorithm detects anomalies by relying solely on normal data from the facility's manufacturing data in the exclusion of abnormal data.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1224-1232
• /
• 2022

Whole body bone scan is the most frequently performed nuclear medicine imaging to evaluate bone metastasis in cancer patients. We evaluated the performance of a VGG16-based transfer learning classifier for bone scan images in which metastatic bone lesion was present. A total of 1,000 bone scans in 1,000 cancer patients (500 patients with bone metastasis, 500 patients without bone metastasis) were evaluated. Bone scans were labeled with abnormal/normal for bone metastasis using medical reports and image review. Subsequently, gradient-weighted class activation maps (Grad-CAMs) were generated for explainable AI. The proposed model showed AUROC 0.96 and F1-Score 0.90, indicating that it outperforms to VGG16, ResNet50, Xception, DenseNet121 and InceptionV3. Grad-CAM visualized that the proposed model focuses on hot uptakes, which are indicating active bone lesions, for classification of whole body bone scan images with bone metastases.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• Smart Media Journal
• /
• v.12 no.5
• /
• pp.73-80
• /
• 2023

Recently, intelligent control systems are developing rapidly in various application fields, and methods for utilizing technologies such as deep learning, IoT, and cloud computing for intelligent control systems are being studied. An important technology in an intelligent control system is recognizing and tracking objects in images. However, existing multi-object tracking technology has problems in accuracy and speed. In this paper, a real-time intelligent control system was implemented using YOLO v5 and YOLO v6 based on a one-shot architecture that increases the accuracy of object tracking and enables fast and accurate tracking even when objects overlap each other or when there are many objects belonging to the same class. The experiment was evaluated by comparing YOLO v5 and YOLO v6. As a result of the experiment, the YOLO v6 model shows performance suitable for the intelligent control system.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.35 no.12
• /
• pp.1367-1373
• /
• 2011

This research concerns the development of a compression/absorption high-temperature hybrid heat pump that uses a natural refrigerant mixture. Heat pumps based on the compression/absorption cycle offer various advantages over conventional heat pumps based on the vapor compression cycle, such as large temperature glide, temperature lift, flexible operating range, and capacity control. In this study, a lab-scale prototype hybrid heat pump was constructed with a two-stage compressor, absorber, desorber, desuperheater, solution heat exchanger, solution pump, liquid/vapor separator, and rectifier as the main components. The hybrid heat pump system operated at 10-kW-class heating capacity producing hot water whose temperature was more than $90^{\circ}C$ when the heat source and sink temperatures were $50^{\circ}C$. Experiments with various $NH_3/H_2O$ mass fractions and compressor/pump circulation ratios were performed on the system. From the study, the system performance was optimized at a specific $NH_3$ concentration.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.56-63
• /
• 2016

We consider a satellite mission scheduling problem, which is a promising problem in recent satellite industry. This problem has various considerations such as customer importance, due date, limited capacity of energy and memory, distance of the location of each mission, etc. Also we consider the objective of each satellite such as general purpose satellite, strategic mission and commercial satellite. And this problem can be modelled as a general knapsack problem, which is famous NP-hard problem, if the objective is defined as to maximize the total mission score performed. To solve this kind of problem, heuristic algorithm such as taboo and genetic algorithm are applied and their performance are acceptable in some extent. To propose more efficient algorithm than previous research, we applied a particle swarm optimization algorithm, which is the most promising method in optimization problem recently in this research. Owing to limitation of current study in obtaining real information and several assumptions, we generated 200 satellite missions with required information for each mission. Based on generated information, we compared the results by our approach algorithm with those of CPLEX. This comparison shows that our proposed approach give us almost accurate results as just less than 3% error rate, and computation time is just a little to be applied to real problem. Also this algorithm has enough scalability by innate characteristic of PSO. We also applied it to mission scheduling problem of various class of satellite. The results are quite reasonable enough to conclude that our proposed algorithm may work in satellite mission scheduling problem.

• Journal of Korean Elementary Science Education
• /
• v.29 no.2
• /
• pp.207-218
• /
• 2010

The revised curriculum in 2007 adds an open inquiry approach to increase students' creativity and interest in science. Because it is the first time for elementary students to perform the open inquiry due to the national curriculum, it is essential that teachers give students' successful experiences in order to build a positive impression about inquiry activity. The purpose of this research is to develop and apply the open inquiry program. The research findings are as follows: First, we analyzed the students' traits of open inquiry ability during the program. The third and fourth grade students showed weakness in operating and inquiring abilities. They also feared failure and were unable to concentrate in classes which were based on explanation or discussion. When students had unexpected results, however, their inquiring abilities and creativeness increased considerably. Additionally there were some students who were stressed during the science-inquiry activity, due to no interest in science and an inability to think scientifically. Second, we developed an open inquiry program for elementary students. The program was modified, reflected upon the students' traits during open inquiry in class. Through repeated feedback like this, we completed the program. Third, for those who studied in the lessons there was a meaningful change in students' science inquiry abilities and abilities to perform 'formulating a hypothesis' and 'the control of variables'. These students' level of self-inquiry performance improved steadily. Moreover, they obtained a strong attachment to their inquiry and understood the method of quantitative experiments.