• Journal of The Korean Association of Information Education
• /
• v.26 no.3
• /
• pp.197-207
• /
• 2022

In this paper, we develop a machine learning based block code generation and recommendation model for the purpose of reducing cognitive load of learners during coding education that learns the learner's block that has been made in the block programming environment using natural processing model and fine-tuning and then generates and recommends the selectable blocks for the next step. To develop the model, the training dataset was produced by pre-processing 50 block codes that were on the popular block programming language web site 'Entry'. Also, after dividing the pre-processed blocks into training dataset, verification dataset and test dataset, we developed a model that generates block codes based on LSTM, Seq2Seq, and GPT-2 model. In the results of the performance evaluation of the developed model, GPT-2 showed a higher performance than the LSTM and Seq2Seq model in the BLEU and ROUGE scores which measure sentence similarity. The data results generated through the GPT-2 model, show that the performance was relatively similar in the BLEU and ROUGE scores except for the case where the number of blocks was 1 or 17.

• Korean Journal of Computational Design and Engineering
• /
• v.5 no.2
• /
• pp.144-154
• /
• 2000

We propose an algorithm for obtaining a triangular approximation of a trimmed NLRBS surface. Triangular approximation is used in the pre-processing step of many applications such as RP(Rapid Prototyping), NC(Numerical Control) and FEA(Finite Element Analysis), etc. The algorithm minimizes the number of triangular elements within tolerance and generates a valid triangular mesh for STL file and NC tool path generation. In the algorithm, a subdivision method is used. Since a patch is a basic element of triangular mesh creation, boundary curves of a patch are divided into line segments and the division of curves is applied for the interior of the surface. That is, boundary curves are subdivided into line segments and two end points of each line segment are propagated to the interior of the surface. For the case of a trimmed surface, triangulation is carried out using a model space information. The algorithm is superior because the number of elements can be controlled as the curvature of the surface varies and it generates the triangular mesh in a trimmed region efficiently. To verify the efficiency, the algorithm was implemented and tested for several 3D objects bounded by NURBS surfaces.

• Textile Coloration and Finishing
• /
• v.26 no.4
• /
• pp.283-289
• /
• 2014

This study describes the feasibility and optimization of reactive dyeing on bio treated cotton knitted fabrics. For this, cotton knitted fabrics distinctly with two different enzymes, alkaline Pectinases(Scourzyme $L^{(R)}$) and Pectate lyases(Bactosol Co. ip $liquor^{(R)}$). In this way by increasing the concentration and processing temperature, the access of enzymes towards the fatty and waxy substrate was found to be accelerated. To achieve higher absorbency and whiteness index, a series of experiments was carried out to assure that Pectate lyases enzymes possesses high access towards the fats and waxes at high temperature. To this end, cotton knitted fabrics was dyed without oxidative bleaching step. The Pectate lyases scoured and dyed fabrics showed less color difference when 2% dye shade is used. The fabrics pre-scoured with Pectate lyases showed good the light and washing fastness properties, compared to the conventional and Pectinases dyed fabrics. However pectinases enzymes showed lower activity at high temperature, caused poor wettability and whiteness index of fabrics. The improvement of the accessibility of enzyme to the pectin at higher temperature Pectate lyases treatment before dyeing was found to be useful for subsequent pectin degradation in cotton knitted fabrics.

• Transactions of Materials Processing
• /
• v.19 no.6
• /
• pp.329-336
• /
• 2010

Ring forging process is more appropriate for high-length and thin walled ring, because it utilizes the forging press and hence does not require heavy-duty ring rolling mill. Although ring forging process is very simple and economic for facilities, the process is not efficient because of multi-forging-step and low material utilization. An effective ring forging process is developed using a hollow ingot. When a hollow ingot is used with a workpiece, the ingot can be forged into a final ring without multi-stage pre-forging process, such as, cogging, upsetting, and piercing, etc.. Finally it has advantages of the material utilization and process improvement because a few reheating and forging process are not necessary to make workpiece for ring forging. The important design variables are the applied plastic deformation energy to eliminate cast structure and make uniform properties. In this study, the mechanical properties after forging of hollow cast ingot were investigated from the experiment using circumferential sectional model. Also, the effects of process variables were studied by FEM simulation on the basis of thermo-visco-plastic constitutive equation. Applied strain is different at each position in length direction because diameter of hollow ingot is different in length direction. The different strain distribution become into a narrow gap by additional plastic deformation during diameter extension process.

• Journal of IKEEE
• /
• v.14 no.4
• /
• pp.332-338
• /
• 2010

Usually, mage feature extraction methods are performed as a pre-processing step in many applications including image retrieval, object recognition, and image indexing. Especially, in the image texture analysis, texture feature extraction methods attempt to increase texture contrast to make it easier to extract the texture features from the image. One of the distinct textures in microscopic skin image is the wrinkle, and its features could provide various useful information for the age-related applications. In this paper, we propose a scheme to extract age-related features from the skin images and improve its accuracy in the skin age estimation.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.6
• /
• pp.1055-1063
• /
• 2014

Recently, various methods have been proposed for improving the performance of the side channel analysis using the power consumption. Of those method, waveform compression method applies to reduce the noise component in pre-processing step. In this paper, we propose the new LDA(Linear Discriminant Analysis)-based signal compression method finding unique feature vector. Through experimentations, we are comparing the proposed method with the PCA(Principal Component Analysis)-based method which has known for the best performance among existing signal compression methods.

• Journal of KIISE
• /
• v.42 no.1
• /
• pp.33-43
• /
• 2015

Recently, patent images are growing importance and thus patent image retrieval is a growing area of research. However, most existing patent image retrieval systems use edges extracted in the images, whose performance is affected by the quality of edge detection in the image pre-processing step. To overcome this disadvantage, we propose a SURF-based patent image retrieval method which uses the morphological characteristics of the images. The proposed method detects SURF interest points with directions and computes regional histograms. We apply the proposed method to a patent image database with 2000 binary images and we show the proposed retrieval system achieves excellent results, even when the images have some loss or degradation.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.868-877
• /
• 2015

The barcode area extraction from images has been extensively studied, and existing methods exploit frequency characteristics or depend on the Hough transform (HT). However, the slantedness of the images and noise affects the performance of these approaches. Moreover, it is difficult to deal with the case where an image contains multiple barcodes. We therefore propose a barcode detection algorithm that is robust under such unfavorable conditions. The pre-processing step implements a probabilistic Hough transform to determine the areas that contain barcodes with a high probability, regardless of the slantedness, noise, and the number of instances. Then, a frequency component analysis extracts the barcodes. We successfully implemented the proposed system and performed a series of barcode extraction tests.

• International Journal of Oral Biology
• /
• v.46 no.3
• /
• pp.146-153
• /
• 2021

Accurate identification of microbes facilitates the prediction, prevention, and treatment of human diseases. To increase the accuracy of microbiome data analysis, a long region of the 16S rRNA is commonly sequenced via paired-end sequencing. In paired-end sequencing, a sufficient length of overlapping region is required for effective joining of the reads, and high-quality sequencing reads are needed at the overlapping region. Trimming sequences at the reads distal to a point where sequencing quality drops below a specific threshold enhance the joining process. In this study, we examined the effect of trimming conditions on the number of reads that remained after quality control and chimera removal in the Illumina paired-end reads of the V3-V4 hypervariable region. We also examined the alpha diversity and taxa assigned by each trimming condition. Optimum quality trimming increased the number of good reads and assigned more number of operational taxonomy units. The pre-analysis trimming step has a great influence on further microbiome analysis, and optimized trimming conditions should be applied for Divisive Amplicon Denoising Algorithm 2 analysis in QIIME2 platform.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.77-82
• /
• 2019

Diabetic retinopathy is a complicated form of diabetes due to circulatory disorder in the peripheral blood vessels of the retina. We segment the microvessel for diagnosing diabetic retinophathy. The conventional methods using filter and features can segment the thick blood vessels, but it has relatively weak for segmenting fine blood vessels. In pre-processing step, noise reduction filter and histogram equalization are applied to suppress the noise and enhance the image contrast. Then, deep learning technique is used for pixel-by-pixel segmentation. The accuracy of conventional methods is between 90% to 94%, while the proposed method has improved as 95% accuracy. There is a problem of segmentation error around the optic disc and exudate due to the network depth. However the accuracy can be improved by modifying the network architecture in the future.