• KIISE Transactions on Computing Practices
• /
• v.24 no.1
• /
• pp.53-57
• /
• 2018

A poisoning accident is often caused by a situation in which people eat poisonous mushrooms because they cannot distinguish between edible mushrooms and poisonous mushrooms. In this paper, we propose an automatic mushroom recognition system by using the convolutional neural network. We collected 1478 mushroom images of 38 species using image crawling, and used the dataset for learning the convolutional neural network. A comparison experiment using AlexNet, VGGNet, and GoogLeNet was performed using the collected datasets, and a comparison experiment using a class number expansion and a fine-tuning technique for transfer learning were performed. As a result of our experiment, we achieve 82.63% top-1 accuracy and 96.84% top-5 accuracy on test set of our dataset.

• Science of Emotion and Sensibility
• /
• v.6 no.3
• /
• pp.63-72
• /
• 2003

This study investigated how cognitive style and training context influenced visual discrimination skill acquisition and transfer under time pressure. This experiment consisted of a screening session, a training session, and a transfer session using random polygon comparison tasks. Screening session was designed to separate participants according to their cognitive style (analytic or holistic). Training session was divided into difficult and easy conditions. In transfer session, participants compared polygon pairs in a novel task. The stimuli were presented for 1.5 seconds to examine the influence of time pressure. Through the all sessions, this experiment measured accuracy and response time. According to the results of this study, analytic group responded as quickly as holistic group in the beginning of training session because time pressure induced them to the holistic strategy. However, as training session progressed, their slopes of reaction time increased, suggesting that their own analytic style emerged. Holistic group showed flatter slopes than did analytic group for training session. Of interest is the slopes increased at the beginning of transfer session, suggesting that they developed analytic strategies in difficult training context. It is suggested individuals differently develop strategic processing skills depending on cognitive styles even under time pressure.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.1-9
• /
• 2021

Traditionally, most malicious codes have been analyzed using feature information extracted by domain experts. However, this feature-based analysis method depends on the analyst's capabilities and has limitations in detecting variant malicious codes that have modified existing malicious codes. In this study, we propose a ResNet-Variational AutoEncder-based variant malware classification method that can classify a family of variant malware without domain expert intervention. The Variational AutoEncoder network has the characteristics of creating new data within a normal distribution and understanding the characteristics of the data well in the learning process of training data provided as input values. In this study, important features of malicious code could be extracted by extracting latent variables in the learning process of Variational AutoEncoder. In addition, transfer learning was performed to better learn the characteristics of the training data and increase the efficiency of learning. The learning parameters of the ResNet-152 model pre-trained with the ImageNet Dataset were transferred to the learning parameters of the Encoder Network. The ResNet-Variational AutoEncoder that performed transfer learning showed higher performance than the existing Variational AutoEncoder and provided learning efficiency. Meanwhile, an ensemble model, Stacking Classifier, was used as a method for classifying variant malicious codes. As a result of learning the Stacking Classifier based on the characteristic data of the variant malware extracted by the Encoder Network of the ResNet-VAE model, an accuracy of 98.66% and an F1-Score of 98.68 were obtained.

• Journal of the Korea Convergence Society
• /
• v.8 no.9
• /
• pp.117-125
• /
• 2017

This study is a descriptive survey on the studying science subjects before entrance to nursing department, the scores of basic nursing sciences and the academic adjustment. The data were analyzed using SPSS 19.0. There was a significant difference between studying certain science subjects before entrance and the scores of basic nursing sciences, studying Biology I, Chemistry I, Physics I and Earth science I increased mean score of basic nursing sciences(p<.05), there were positive correlations among them. And there was no correlation between studying science subjects before entrance and academic adjustment except Physics I, but, there was a positive correlation between score of basic nursing sciences and academic adjustment(r=0.296, p<.001). Also, studying science subjects before entrance affected partially to the scores of basic nursing sciences, and the scores of basic nursing sciences affected academic adjustment(p=.001). This result can be used in pre-school program for the freshmen after repeated study.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.197-202
• /
• 2019

토큰화는 입력 텍스트를 더 작은 단위의 텍스트로 분절하는 과정으로 주로 기계 학습 과정의 효율화를 위해 수행되는 전처리 작업이다. 현재까지 자연어 처리 분야 과업에 적용하기 위해 다양한 토큰화 방법이 제안되어 왔으나, 주로 텍스트를 효율적으로 분절하는데 초점을 맞춘 연구만이 이루어져 왔을 뿐, 한국어 데이터를 대상으로 최신 기계 학습 기법을 적용하고자 할 때 적합한 토큰화 방법이 무엇일지 탐구 해보기 위한 연구는 거의 이루어지지 않았다. 본 논문에서는 한국어 데이터를 대상으로 최신 기계 학습 기법인 전이 학습 기반의 자연어 처리 방법론을 적용하는데 있어 가장 적합한 토큰화 방법이 무엇인지 알아보기 위한 탐구 연구를 진행했다. 실험을 위해서는 대표적인 전이 학습 모형이면서 가장 좋은 성능을 보이고 있는 모형인 BERT를 이용했으며, 최종 성능 비교를 위해 토큰화 방법에 따라 성능이 크게 좌우되는 과업 중 하나인 기계 독해 과업을 채택했다. 비교 실험을 위한 토큰화 방법으로는 통상적으로 사용되는 음절, 어절, 형태소 단위뿐만 아니라 최근 각광을 받고 있는 토큰화 방식인 Byte Pair Encoding (BPE)를 채택했으며, 이와 더불어 새로운 토큰화 방법인 형태소 분절 단위 위에 BPE를 적용하는 혼합 토큰화 방법을 제안 한 뒤 성능 비교를 실시했다. 실험 결과, 어휘집 축소 효과 및 언어 모델의 퍼플렉시티 관점에서는 음절 단위 토큰화가 우수한 성능을 보였으나, 토큰 자체의 의미 내포 능력이 중요한 기계 독해 과업의 경우 형태소 단위의 토큰화가 우수한 성능을 보임을 확인할 수 있었다. 또한, BPE 토큰화가 종합적으로 우수한 성능을 보이는 가운데, 본 연구에서 새로이 제안한 형태소 분절과 BPE를 동시에 이용하는 혼합 토큰화 방법이 가장 우수한 성능을 보임을 확인할 수 있었다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.34-41
• /
• 2023

In recent years, as the range of human activities has increased, the introduction of alien species has become frequent. Among them, raccoons have been designated as harmful animals since 2020. Raccoons are similar in size and shape to raccoon dogs, so they generally need to be distinguished in capturing them. To solve this problem, we use VGG19, ResNet152V2, InceptionV3, InceptionResNet and NASNet, which are CNN deep learning models specialized for image classification. The parameters to be used for learning are pre-trained with a large amount of data, ImageNet. In order to classify the raccoon and raccoon dog datasets as outward features of animals, the image was converted to grayscale and brightness was normalized. Augmentation methods were applied using left and right inversion, rotation, scaling, and shift to create sufficient data for transfer learning. The FCL consists of 1 layer for the non-augmented dataset while 4 layers for the augmented dataset. Comparing the accuracy of various augmented datasets, the performance increased as more augmentation methods were applied.

• The Journal of the Korea Contents Association
• /
• v.20 no.1
• /
• pp.581-592
• /
• 2020

This research aims to explore the effect of participation in 'peer tutoring(learning tutoring)' program designed for low achiever students, and to provide an explanation for the improvement of related extracurricular activity. For this, firstly, the study analyzed differences between goal attainment group and non-attainment group in self-directed learning readiness, learning presence and learning transfer. Secondly, the relationships between three variables were analyzed. Based on an online survey of 154 low achievers participating in learning tutoring, two research questions were examined using t-test, correlation and hierarchical multiple regression analyses. Our findings show that firstly, the academic achievement after participating in tutoring improved more than before. Secondly, there were differences in three variables by gender and grades. Also, there were differences in three variables between two groups. Finally, there was a high positive correlation between three variables, and 71% of learning transfer was explained by self-directed learning readiness and learning presence. Based on these findings, the practical implications are discussed regarding the improvement of tutoring program.

• Journal of Digital Convergence
• /
• v.16 no.1
• /
• pp.63-72
• /
• 2018

This paper examined the learning transfer of job training participants and its influencing factors. A survey of 279 care workers in the city of Seoul and Kyeong Gi province who recently participated dementia job training was conducted. The results of multiple regression analysis indicated that the self-efficacy of the care workers, the capability of instructor, the training methods and the transfer opportunity positively influenced the level of learning transfer. The findings suggested increasing care workers' self-efficacy, enhancing practical skill-based training program, hiring instructors with high workplace experiences, fostering work environment with higher transfer opportunity are required.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.115-127
• /
• 2023

Video stabilization is one of the camera technologies that the importance is gradually increasing as the personal media market has recently become huge. For deep learning-based video stabilization, existing methods collect pairs of video datas before and after stabilization, but it takes a lot of time and effort to create synchronized datas. Recently, to solve this problem, unsupervised learning method using only unstable video data has been proposed. In this paper, we propose a network structure that learns the stabilized trajectory only with the unstable video image without the pair of unstable and stable video pair using the Convolutional Auto Encoder structure, one of the unsupervised learning methods. Optical flow data is used as network input and output, and optical flow data was mapped into grid units to simplify the network and minimize noise. In addition, to generate a stabilized trajectory with an unsupervised learning method, we define the loss function that smoothing the input optical flow data. And through comparison of the results, we confirmed that the network is learned as intended by the loss function.

• Journal of the Korea Society for Simulation
• /
• v.31 no.1
• /
• pp.11-18
• /
• 2022

Recently, research to classify human activity using imagery has been actively conducted for the purpose of crime prevention and facility safety in public places and facilities. In order to improve the performance of human activity classification, most studies have applied deep learning based-transfer learning. However, despite the increase in the number of backbone network models that are the basis of deep learning as well as the diversification of architectures, research on finding a backbone network model suitable for the purpose of operation is insufficient due to the atmosphere of using a certain model. Thus, this study applies the transfer learning into recently developed deep learning backborn network models to build an intelligent system that classifies human activity using imagery. For this, 12 types of active and high-contact human activities based on sports, not basic human behaviors, were determined and 7,200 images were collected. After 20 epochs of transfer learning were equally applied to five backbone network models, we quantitatively analyzed them to find the best backbone network model for human activity classification in terms of learning process and resultant performance. As a result, XceptionNet model demonstrated 0.99 and 0.91 in training and validation accuracy, 0.96 and 0.91 in Top 2 accuracy and average precision, 1,566 sec in train process time and 260.4MB in model memory size. It was confirmed that the performance of XceptionNet was higher than that of other models.