• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2277-2298
• /
• 2019

Adaptive learning in e-learning has garnered researchers' interest. In it, learning resources could be recommended automatically to achieve a personalized learning experience. There are various ways to realize it. One of the realistic ways is adaptive learning path recommendation, in which learning resources are provided according to learners' requirements. This paper summarizes existing works and proposes an innovative approach. Firstly, a learner-centred concept map is created using graph theory based on the features of the learners and concepts. Then, the approach generates a linear concept sequence from the concept map using the proposed traversal algorithm. Finally, Learning Objects (LOs), which are the smallest concrete units that make up a learning path, are organized based on the concept sequences. In order to realize this step, we model it as a multi-objective combinatorial optimization problem, and an improved immune algorithm (IIA) is proposed to solve it. In the experimental stage, a series of simulated experiments are conducted on nine datasets with different levels of complexity. The results show that the proposed algorithm increases the computational efficiency and effectiveness. Moreover, an empirical study is carried out to validate the proposed approach from a pedagogical view. Compared with a self-selection based approach and the other evolutionary algorithm based approaches, the proposed approach produces better outcomes in terms of learners' homework, final exam grades and satisfaction.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.19-26
• /
• 2019

In this paper, the classification performance of learning algorithms is compared for TAB digit recognition. The TAB digits that are segmented from TAB musical notes contain TAB lines and musical symbols. The labeling method and non-linear filter are designed and applied to extract fret digits only. The shift operation of the 4 directions is applied to generate more data. The selected models are Bayesian classifier, support vector machine, prototype based learning, multi-layer perceptron, and convolutional neural network. The result shows that the mean accuracy of the Bayesian classifier is about 85.0% while that of the others reaches more than 99.0%. In addition, the convolutional neural network outperforms the others in terms of generalization and the step of the data preprocessing.

• Design & Manufacturing
• /
• v.13 no.1
• /
• pp.5-12
• /
• 2019

In this paper, we studied the micro tool deflection, micro cutting with low temperature, and deformation of micro ribs caused by cutting forces. First, we performed an integrated machining error compensation method based on captured images of tool deflection shapes in micro cutting process. In micro cutting process, micro tool deflection generates very serious problems in contrast to macro tool deflection. To get the real images of micro tool deflection, it is possible to estimate tool deflection in cutting conditions modeled and to compensate for machining errors using an iterative algorithm correcting tool path. Second, in macro cutting fields, the cryogenic cutting process has been applied to cut the refractory metal but, the serious problem may be generated in micro cutting fields by the cryogenic environment. However, if the proper low temperature is applied to micro cutting area, the cooling effect of cutting heat is expected. Such effect can make the reduction of tool wear and burr formation. For verifying this passibility, the micro cutting experiment at low temperature was performed and SEM images were analyzed. Third, the micro pattern was deformed by the cutting forces and the shape error occurred in the sidewall multi-step cutting process were minimized. As the results, the relationship between the cutting conditions and the deformation of micro-structure during micro cutting process was investigated.

• Smart Media Journal
• /
• v.10 no.3
• /
• pp.48-53
• /
• 2021

The authentication process is a key step that should be used to verify that a user is legitimate, and it should be used to verify that a user is a legitimate user and grant access only to that user. Recently, two-factor authentication and OTP schemes are used by most applications to add a layer of security to the login process and to address the vulnerability of using only one factor for authentication, but this method also allows access to user accounts without permission. This is a known security vulnerability. In this paper, we propose a Zero Knowledge Proofs (ZKP) personal information authentication scheme based on a Smart Contract of a block chain that authenticates users with minimal personal information exposure conditions. This has the advantage of providing many security technologies to the authentication process based on blockchain technology, and that personal information authentication can be performed more safely than the existing authentication method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.1
• /
• pp.133-143
• /
• 2021

In government procurement programs, cost estimation and analysis support funding decisions and are the basis for other major decisions, too. Such estimating and analyzing the cost of the weapon systems are crucial in execution of the defense budget. However, existing cost estimations and analyses have focused on domestic R&D projects, thus those are not valid in application to foreign weapon acquisitions. This study aims at foreign weapon systems that are acquired from Direct Commercial Sales. Because the data for price estimation of a foreign weapon is usually not available, we suggest a price estimation model based on performance factors of the weapon. In this study, the proper price of the weapon system is estimated using the parametric cost estimating model. Using the data of helicopter-launched anti-tank guided missiles worldwide, we analyze the effect of each performance factor on the weapon system price by regression analysis, and use step-wise and ridge regression analysis to remove multi-collinearity. This study hopefully contributes to more reasonable decision making on proper price of weapons.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4290-4309
• /
• 2020

In recent years, advancements in machine learning capabilities have allowed it to see widespread adoption for tasks such as object detection, image classification, and anomaly detection. However, despite their promise, a limitation lies in the fact that a network's performance quality is based on the data which it receives. A well-trained network will still have poor performance if the subsequent data supplied to it contains artifacts, out of focus regions, or other visual distortions. Under normal circumstances, images of the same scene captured from differing points of focus, angles, or modalities must be separately analysed by the network, despite possibly containing overlapping information such as in the case of images of the same scene captured from different angles, or irrelevant information such as images captured from infrared sensors which can capture thermal information well but not topographical details. This factor can potentially add significantly to the computational time and resources required to utilize the network without providing any additional benefit. In this study, we plan to explore using image fusion techniques to assemble multiple images of the same scene into a single image that retains the most salient key features of the individual source images while discarding overlapping or irrelevant data that does not provide any benefit to the network. Utilizing this image fusion step before inputting a dataset into the network, the number of images would be significantly reduced with the potential to improve the classification performance accuracy by enhancing images while discarding irrelevant and overlapping regions.

• Journal of Korean Neurosurgical Society
• /
• v.64 no.4
• /
• pp.619-630
• /
• 2021

Objective : The skull base reconstruction step, which prevents cerebrospinal fluid (CSF) leakage, is one of the most challenging steps in endoscopic skull base surgery (ESS). The purpose of this study was to assess the outcomes and complications of a reconstruction technique for immediate CSF leakage repair using multiple onlay grafts following ESS. Methods : A total of 230 consecutive patients who underwent skull base reconstruction using multiple onlay grafts with fibrin sealant patch (FSP), hydroxyapatite cement (HAC), and pedicled nasoseptal flap (PNF) for high-flow CSF leakage following ESS at three institutions were enrolled. We retrospectively reviewed the medical and radiological records to analyze the preoperative features and postoperative results. Results : The diagnoses included craniopharyngioma (46.8%), meningioma (34.0%), pituitary adenoma (5.3%), chordoma (1.6%), Rathke's cleft cyst (1.1%) and others (n=21, 11.2%). The trans-planum/tuberculum approach (94.3%) was the most commonly adapted surgical method, followed by the trans-sellar and transclival approaches. The third ventricle was opened in 78 patients (41.5%). Lumbar CSF drainage was not performed postoperatively in any of the patients. Postoperative CSF leakage occurred in four patients (1.7%) due to technical mistakes and were repaired with the same technique. However, postoperative meningitis occurred in 13.5% (n=31) of the patients, but no microorganisms were identified. The median latency to the diagnosis of meningitis was 8 days (range, 2-38). CSF leakage was the unique risk factor for postoperative meningitis (p<0.001). Conclusion : The use of multiple onlay grafts with FSP, HAC, and PNF is a reliable reconstruction technique that provides immediate and complete CSF leakage repair and mucosal grafting on the skull base without the need to harvest autologous tissue or perform postoperative CSF diversion. However, postoperative meningitis should be monitored carefully.

• Applied Chemistry for Engineering
• /
• v.32 no.3
• /
• pp.229-236
• /
• 2021

During the last two decades, metal-organic frameworks (MOFs) have been drawn attention due to their high specific surface area, porosity, and catalytic activities that allow to use in many applications such as sensor, catalysis, energy storage, etc. To synthesize MOFs hydrothermal or solvothermal method were generally used. However, these methods require high-cost equipment and long time-spend for the synthesis with multi-step process. In contrast, electrochemical synthesis has been considered as a simple and easy process under the ambient conditions. In this review, we described the mechanism of electrochemical MOFs synthesis by the number of configured electrodes system, with the recent reports of various applications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.219-224
• /
• 2020

Binary classification has been broadly investigated in machine learning. In addition, binary classification can be easily extended to multi class problems. To successfully utilize machine learning methods for classification tasks, preprocessing and feature extraction steps are essential. These are important steps to improve their classification performances. In this paper, we propose a new learning method based on weighted least squares. In the weighted least squares, designing weights has a significant role. Due to this necessity, we also propose a new technique to obtain weights that can achieve feature transformation. Based on this weighting technique, we also propose a method to combine the learning and feature extraction processes together to perform both processes simultaneously in one step. The proposed method shows the promising performance on five UCI machine learning data sets.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.303-310
• /
• 2021

A method for developing a visual information concept that analogously compares and analyzes macroscopic data changes in a simple form is needed. The development of the visual information concept requires the selection of visualization form, selection of rhetorical effects, and selection of digital expression elements. Among them, an example of a rhetorical effect selection method for effectively delivering visual information to a user is presented. In this study, metaphorical rhetoric, which allows data comparison and analysis from a macroscopic point of view, was selected for stock price analysis by period and industry. We present a two-dimensional three-stage shape change using a dandelion with spreading cockle hair as a metaphor and a three-dimensional three-stage shape change information expression method using a coral peony flower that changes shape and color according to time as a metaphor. Using this rhetorical metaphor, it is possible to compare macroscopic trading changes and stock prices by industry.