• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.7
• /
• pp.101-108
• /
• 1998

In this paper, after we got to realized FDNN (fuzzy decision neural network) applied the quantization triangularity fuzzy function to DBNN(decision based neural network) of a hierarchical structure for image process, we could esign hardware of the realized FDNN. Also it is normalized the standard image and the input image as the same size. We are applied DWW algorithm which selected the closest value with finding similarity of an interval image by this distance to FDNN. So we could calulated in terms of distance to weight of pixel which composed two image and eliminated the nise of image, minimized the lost of information, obtained the optimal information. It is designed hardware of high speed weighted FDNN using COMPASS tool. Aslo, the total circuit is realized as gates of 61,000 and could show to superiority of FDNN using the simulation.

• Journal of Applied Biological Chemistry
• /
• v.50 no.4
• /
• pp.221-226
• /
• 2007

The high molecular-weight mucilage extracted and purified from cactus fruit of Opuntia ficus-indica var. Saboten was degraded by the cell-free culture filtrate of a fungus isolated from soil. TLC analysis of the polymeric mucilage after incubation with the fungal culture filtrate confirmed its degradation. When the degradation products were tested for their qualitative reactions with ninhydrin and phenol-sulfuric acid, only phenol-sulfuric acid gave positive development, and ninhydrin did not show any observable color reaction. This coloring reaction suggested the presence of a carbohydrate without an amino group within the mucilage. Analyses by HPLC and liquid gel permeation chromatography on sephadex G-100 also provided additional information on degradation of the mucilage by the fungal culture filtrate. The sequences of ITS-5.8S rDNA from the fungal isolate that was cultivated for the preparation of mucilage-degrading enzyme showed 99% similarity to those of Pestalotiopsis aquatica.

• Journal of Life Science
• /
• v.6 no.1
• /
• pp.1-5
• /
• 1996

Using differential hybridization, a cDNA clone was isolated fortuitously from Amaranthus viridis and sequenced. This nucleotide sequence exhibited 55.1% identity with vma6 which encodes the 36-kD subunit of the vacuolar proton transporting ATPase in Saccharmoyces cerevisiae. The predicted open reading frame encodes a protein of 221 amino acid sequence with a calculated molecular weight of 25,452 and reveals high levels of similarity with subunit D polypeptide of vacuolar H -ATP(e.g., 48.5, 52.1 and 49.3% identity to the vacuolar 36-kD chain of yeast, vacuolar 32-kD polypeptide IV of human and vacuolar 28-kD protein of bovine chromaffin granules, respectively). The hydropathy index computation revealed that this predicted protein is a peripheral protein. These results indicated that the predicted protein may play a sturctural role in the vaculor H -ATPase as does gamma subunit in V-type ATPase.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.9
• /
• pp.8-16
• /
• 1992

This paper presents a method which can recognized the Handwritten Korean characters by using a Context-Free Grammar. The input characters are thinned in order to dwindle the mount of data, the thinned characters are converted into one-dimension strings according to six-forms. when the point of contact among phonemes is found, two phonemes are seperated respectively by marking the index mark (\) at the points. The Context-Free Grammar to input characters is classified into group grammars concerning the similarity of phonemes, input characters are parsed by making use of the Pushdown automata method. As the bent parts in the Handwritten characters are found frequently, We try to correct the bent parts by using the parsing distance measure, which recognize characters according to minium value caused by measuring the weight distance between two sentences. In this experiment, the recognition rate shows 93.8% to 275 Handwritten Korean characters.

• International Journal of Contents
• /
• v.9 no.2
• /
• pp.22-26
• /
• 2013

Comparing online and paper-based environment for report submission and correction, the former supersedes to the latter, since (1) the turn-around time becomes shorter, (2) teaching opportunity increases, and (3) as a consequence, the student's achievement level becomes higher in the online environment. In this paper, we propose an annotation tool GABA for PDF document in order to reduce correction time by the teachers and to facilitate instruction to students. In a usual class, the same or similar assignments are given to the students. Then it is often the case that many students make similar mistakes. A teacher can register and classify common correction comments to GABA. Report correction time becomes significantly shorter by reusing the registered comments. GABA also provides various support functions in order to assist efficient checking of numerous report files such as (1) sorting of frequently-used comments, (2) similarity-based file sorting, and (3) cross tabulation of comments using category and weight.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.285-288
• /
• 2006

Most previous studies on improving the effectiveness of CBR have focused on the similarity function aspect or optimization of case features and their weights. However, according to some of the prior research, finding the optimal k parameter for the k-nearest neighbor (k-NN) is also crucial for improving the performance of the CBR system. Nonetheless, there have been few attempts to optimize the number of neighbors, especially using artificial intelligence (AI) techniques. In this study, we introduce a genetic algorithm (GA) to optimize the number of neighbors that combine, as well as the weight of each feature. The new model is applied to the real-world case of a major telecommunication company in Korea in order to build the prediction model for the customer profitability level. Experimental results show that our GA-optimized CBR approach outperforms other AI techniques for this mulriclass classification problem.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.441-452
• /
• 2021

Federated learning provides an efficient integrated model for distributed data, allowing the local training of different data. Meanwhile, the goal of multi-task learning is to simultaneously establish models for multiple related tasks, and to obtain the underlying main structure. However, traditional federated multi-task learning models not only have strict requirements for the data distribution, but also demand large amounts of calculation and have slow convergence, which hindered their promotion in many fields. In our work, we apply the rank constraint on weight vectors of the multi-task learning model to adaptively adjust the task's similarity learning, according to the distribution of federal node data. The proposed model has a general framework for solving optimal solutions, which can be used to deal with various data types. Experiments show that our model has achieved the best results in different dataset. Notably, our model can still obtain stable results in datasets with large distribution differences. In addition, compared with traditional federated multi-task learning models, our algorithm is able to converge on a local optimal solution within limited training iterations.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.265-271
• /
• 2019

본 논문은 어휘가 비슷한 문장들을 효과적으로 분류하는 BERT 기반 유사 문장 분류기의 학습 자료 구성 방법을 제안한다. 기존의 유사 문장 분류기는 문장의 의미와 상관 없이 각 문장에서 출현한 어휘의 유사도를 기준으로 분류하였다. 이는 학습 자료 내의 유사 문장 쌍들이 유사하지 않은 문장 쌍들보다 어휘 유사도가 높기 때문이다. 따라서, 본 논문은 어휘 유사도가 높은 유사 의미 문장 쌍들과 어휘 유사도가 높지 않은 의미 문장 쌍들을 학습 자료에 추가하여 BERT 유사 문장 분류기를 학습하여 전체 분류 성능을 크게 향상시켰다. 이는 문장의 의미를 결정짓는 단어들과 그렇지 않은 단어들을 유사 문장 분류기가 학습하였기 때문이다. 제안하는 학습 데이터 구축 방법을 기반으로 학습된 BERT 유사 문장 분류기들의 학습된 self-attention weight들을 비교 분석하여 BERT 내부에서 어떤 변화가 발생하였는지 확인하였다.

• Asian-Australasian Journal of Animal Sciences
• /
• v.28 no.7
• /
• pp.926-935
• /
• 2015

The efficiency of genome-wide association analysis (GWAS) depends on power of detection for quantitative trait loci (QTL) and precision for QTL mapping. In this study, three different strategies for GWAS were applied to detect QTL for carcass quality traits in the Korean cattle, Hanwoo; a linkage disequilibrium single locus regression method (LDRM), a combined linkage and linkage disequilibrium analysis (LDLA) and a $BayesC{\pi}$ approach. The phenotypes of 486 steers were collected for weaning weight (WWT), yearling weight (YWT), carcass weight (CWT), backfat thickness (BFT), longissimus dorsi muscle area, and marbling score (Marb). Also the genotype data for the steers and their sires were scored with the Illumina bovine 50K single nucleotide polymorphism (SNP) chips. For the two former GWAS methods, threshold values were set at false discovery rate <0.01 on a chromosome-wide level, while a cut-off threshold value was set in the latter model, such that the top five windows, each of which comprised 10 adjacent SNPs, were chosen with significant variation for the phenotype. Four major additive QTL from these three methods had high concordance found in 64.1 to 64.9Mb for Bos taurus autosome (BTA) 7 for WWT, 24.3 to 25.4Mb for BTA14 for CWT, 0.5 to 1.5Mb for BTA6 for BFT and 26.3 to 33.4Mb for BTA29 for BFT. Several candidate genes (i.e. glutamate receptor, ionotropic, ampa 1 [GRIA1], family with sequence similarity 110, member B [FAM110B], and thymocyte selection-associated high mobility group box [TOX]) may be identified close to these QTL. Our result suggests that the use of different linkage disequilibrium mapping approaches can provide more reliable chromosome regions to further pinpoint DNA makers or causative genes in these regions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.4
• /
• pp.102-115
• /
• 2019

This study aims to establish and apply a drought vulnerability assessment plan including various factors related to drought. The evaluation technique consisted of three stages: evaluation factor and weight selection, evaluation data database construction, evaluation data and weight combination, and Delphi investigation method was applied to evaluation factor and weight selection. As the evaluation method, the TOPSIS method, which is a widely used MCDM method, was used. The results of the drought vulnerability assessment were applied to the administrative districts of Sigun-gu, Korea from March 2016 to September 2019. As a result of the evaluation, drought vulnerable areas were identified in Chungcheongbuk-do, Gyeongsangnam-do, and Jeollanam-do, and it was analyzed that it is necessary to establish drought response plans for these areas.