• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.177-187
• /
• 2023

Semi-supervised learning (SSL) is an effective approach to training models using a small amount of labeled data and a larger amount of unlabeled data. However, many papers in the field use a fixed threshold when applying pseudo-labels without considering the feature-wise differences among images of different classes. In this paper, we propose a SSL method for synthetic aperture radar (SAR) image classification that applies different thresholds for each class instead of using a single fixed threshold for all classes. We propose a threshold learning module into the model, considering the differences in feature distributions among classes, to dynamically learn thresholds for each class. We compare the application of a SSL SAR image classification method using different thresholds and examined the advantages of employing class-specific thresholds.

• Journal of Microbiology and Biotechnology
• /
• v.26 no.5
• /
• pp.837-845
• /
• 2016

A novel endodextranase isolated from Paenibacillus sp. was found to produce isomaltotetraose and small amounts of cycloisomaltooligosaccharides with a degree of polymerization of 7-14 from dextran. To determine the active site, the enzyme was modified with 1-ethyl-3-[3-(dimethylamino)-propyl]-carbodiimide (EDC) and α-epoxyalkyl α-glucosides (EAGs), an affinity labeling reagent. The inactivation followed pseudo first-order kinetics. Kinetic analysis and chemical modification using EDC and EAGs indicated that carboxyl groups are essential for the enzymatic activity. Three Asp and one Glu residues were identified as candidate catalytic amino acids, since these residues are completely conserved across the GH family of 66 enzymes. Replacement of Asp189, Asp340, or Glu412 completely abolished the enzyme activity, indicating that these residues are essential for catalytic activity.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.70-75
• /
• 2001

This paper proposes a syllabic segmentation method for the korean continuous speech. This method are formed three major steps as follows. (1) labeling the vowel, consonants, silence units and forming the Token the sequence of speech data using the segmental parameter in the time domain, pitch, energy, ZCR and PVR. (2) scanning the Token in the structure of korean syllable using the parser designed by the finite state automata, and (3) re-segmenting the syllable parts witch have two or more syllables using the pseudo-syllable nucleus information. Experimental results for the capability evaluation toward the proposed method regarding to the continuous words and sentence units are 73.5％, 85.9％, respectively.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.129-138
• /
• 2022

Collecting and labeling sufficient training data, which is essential to deep learning-based visual inspection, is difficult for manufacturers to perform because it is very expensive. This paper presents a steel plate surface defect detection system with industrial-grade detection performance by training a small amount of steel plate surface images consisting of labeled and non-labeled data. To overcome the problem of lack of training data, we propose two data augmentation techniques: program-based augmentation, which generates defect images in a geometric way, and generative model-based augmentation, which learns the distribution of labeled data. We also propose a 4-step semi-supervised learning using pseudo labels and consistency training with fixed-size augmentation in order to utilize unlabeled data for training. The proposed technique obtained about 99% defect detection performance for four defect types by using 100 real images including labeled and unlabeled data.

• Proceedings of the Korean Society of Applied Pharmacology
• /
• 1995.04a
• /
• pp.74-74
• /
• 1995

GABA transaminase is inactivated by preincubation with p$^1$, p$^2$-bis(5'-pyridoxal) diphosphate at pH 7.0. The inactivation under pseudo-first order conditions proceeds at a slow rate (K$\_$obs/=0.035 min$\^$-1/). The degree of labeling of the enzyme by p$^1$, p$^2$-bis(5'-pyridoxal) diphosphate was determined by absorption spectroscopy, The blocking of 2 lysyl residues/dimer is needed for inactivation of the transaminase. The time course of the reaction is significantly affected by the substrate ${\alpha}$-ketoglutarate, which afforded complete protection against the loss of the catalytic activity. Whereas cofator pyridoxal phosphate failed to prevent the inactivation of the enzyme. Therefore, it is postulated that binding of ${\alpha}$-ketoglutarate tn lysyl residues is the major factor contributing to stabilization of the catalytic site and bifuctional reagent p$^1$, p$^2$bis(5'-pyridoxal) diphosphate blocks lysyl residues other than those involved in the binding of the cofactor.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.472-484
• /
• 2019

This paper proposes a time-domain sound event detection algorithm using DNN (Deep Neural Network). In this system, time domain sound waveform data which is not converted into the frequency domain is used as input to the DNN. The overall structure uses CRNN structure, and GLU, ResNet, and Squeeze-and-excitation blocks are applied. And proposed structure uses structure that considers features extracted from several layers together. In addition, under the assumption that it is practically difficult to obtain training data with strong labels, this study conducted training using a small number of weakly labeled training data and a large number of unlabeled training data. To efficiently use a small number of training data, the training data applied data augmentation methods such as time stretching, pitch change, DRC (dynamic range compression), and block mixing. Unlabeled data was supplemented with insufficient training data by attaching a pseudo-label. In the case of using the neural network and the data augmentation method proposed in this paper, the sound event detection performance is improved by about 6 %(based on the f-score), compared with the case where the neural network of the CRNN structure is used by training in the conventional method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.607-610
• /
• 2021

When learning a model in supervised learning, input data and the label of the data are required. However, labeling is high cost task and if automated, there is no guarantee that the label will always be correct. In the case of supervised learning in such a noisy labels environment, the accuracy of the model increases at the initial stage of learning, but decrease significantly after a certain period of time. There are various methods to solve the noisy label problem. But in most cases, the probability predicted by the model is used as the pseudo label. So, we proposed a method to predict the true label more quickly by refining the probabilities predicted by the model. Result of experiments on the same environment and dataset, it was confirmed that the performance improved and converged faster. Through this, it can be applied to methods that use the probability distribution predicted by the model among existing studies. And it is possible to reduce the time required for learning because it can converge faster in the same environment.