• KIISE Transactions on Computing Practices
• /
• v.22 no.9
• /
• pp.461-466
• /
• 2016

Topic expansion is an expansion method that reflects external data for improving quality of learned topic. The online learning topic model is not appropriate for topic expansion using external data, because it does not reflect unseen words to learned topic model. In this study, we proposed topic expansion method using infinite vocabulary online LDA. When unseen words appear in learning process, the proposed method allocates unseen word to topic after calculating semantic correlation between unseen word and each topic. To evaluate the proposed method, we compared with existing topic expansion method. The results indicated that the proposed method includes additional information that is not contained in broadcasting script by reflecting external documents. Also, the proposed method outperformed on coherence evaluation.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.849-858
• /
• 2004

Most of supervised teaming algorithms could be applied after that continuous variables are transformed to categorical ones at the preprocessing stage in order to avoid the difficulty of processing continuous variables. This preprocessing stage is called global discretization, uses the class distribution list called bins. But, when data are large and the range of the variable to be discretized is very large, many sorting and merging should be performed to produce a single bin because most of global discretization methods need a single bin. Also, if new data are added, they have to perform discretization from scratch to construct categories influenced by the data because the existing methods perform discretization in batch mode. This paper proposes a method that extracts sample points and performs discretization from these sample points in order to solve these problems. Because the approach in this paper does not require merging for producing a single bin, it is efficient when large data are needed to be discretized. In this study, an experiment using real and synthetic datasets was made to compare the proposed method with an existing one.

• Journal of the Korea Convergence Society
• /
• v.9 no.3
• /
• pp.249-256
• /
• 2018

This study aims to explore efficient foreign language learning paradigm with a focus on reading fluency and accuracy. From a perspective of language acquisition in the foreign language context, the priority in the L2 learning between accuracy and fluency has been a very important issue. Fluency becomes an important issue due to many researchers' interests in the L1 and L2 classroom. Although both accuracy and fluency are crucial, the paradigm shift from fluency to accuracy is necessary in the foreign language teaching. In this context, as an alternative methodology for L2 learners' fluency, the extensive reading approach is provided. A number of studies have suggested that extensive reading program could lead to improvement of L2 learners' reading rate and is an effective approach to improving general language proficiency.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.61-73
• /
• 2024

Class imbalance is one of the significant challenges in deep learning tasks, particularly pronounced in areas with limited data. This study proposes a new approach that utilizes minimal labeled data for effectively classifying tomato leaf diseases. We introduced a recursive learning method using the YOLOv8 model. By utilizing the detection predictions of images on the training data as additional training data, the number of labeled data is progressively increased. Unlike conventional data augmentation and up-down sampling techniques, this method seeks to fundamentally solve the class imbalance problem by maximizing the utility of actual data. Based on the secured labeled data, tomato leaves were extracted, and diseases were classified using the EfficientNet model. This process achieved a high accuracy of 98.92%. Notably, a 12.9% improvement compared to the baseline was observed in the detection of Late blight diseases, which has the least amount of data. This research presents a methodology that addresses data imbalance issues while offering high-precision disease classification, with the expectation of application to other crops.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.9
• /
• pp.1979-1986
• /
• 2010

Biological early warning system detects toxicity by looking at behavior of organisms in water. The system uses classifier for judgement about existence and amount of toxicity in water. Boosting algorithm is one of possible application method for improving performance in a classifier. Boosting repetitively change training example set by focusing on difficult examples in basic classifier. As a result, prediction performance is improved for the events which are difficult to classify, but the information contained in the events which can be easily classified are discarded. In this paper, an incremental learning method to overcome this shortcoming is proposed by using the extended data expression. In this algorithm, decision tree classifier define class distribution information using the weight parameter in the extended data expression by exploiting the necessary information not only from the well classified, but also from the weakly classified events. Experimental results show that the new algorithm outperforms the former Learn++ method without using the weight parameter.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.319-327
• /
• 2012

In this paper, we present a sign language recognition model which does not use any wearable devices for object tracking. The system design issues and implementation issues such as data representation, feature extraction and pattern classification methods are discussed. The proposed data representation method for sign language patterns is robust for spatio-temporal variances of feature points. We present a feature extraction technique which can improve the computation speed by reducing the amount of feature data. A neural network model which is capable of incremental learning is described and the behaviors and learning algorithm of the model are introduced. We have defined a measure which reflects the relevance between the feature values and the pattern classes. The measure makes it possible to select more effective features without any degradation of performance. Through the experiments using six types of sign language patterns, the proposed model is evaluated empirically.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.1
• /
• pp.113-117
• /
• 2018

Human emotions are revealed by various factors. Words, actions, facial expressions, attire and so on. But people know how to hide their feelings. So we can not easily guess its sensitivity using one factor. We decided to pay attention to behaviors and facial expressions in order to solve these problems. Behavior and facial expression can not be easily concealed without constant effort and training. In this paper, we propose an algorithm to estimate human emotion through combination of two results by gradually learning human behavior and facial expression with little data through the deep learning method. Through this algorithm, we can more comprehensively grasp human emotions.

• School Mathematics
• /
• v.5 no.1
• /
• pp.43-58
• /
• 2003

This study intends to compare the structure of contents and the way of developing concepts in mathematics textbooks of south and those of north Korea. After thorough investigations of the textbooks from south and north Korea, the following three characteristics were identified. First, the mathematics textbooks of south Korea tends to spread out contents across several grades, while those of north Korea have a tendency of centralization in terms of locating contents Second, in the textbooks of South Korea, mathematics concepts are permeated through real world situations, and students gradually acquire those concepts mostly through activities. This is different from the approach of the north Korean textbooks in which various problems play a key role in explaining concepts. Third, the main strategy of introducing contents in the textbooks of south and that of north Korea corresponds to 'guidance' and 'explanation' respectively. Exploratory questions leading to the concepts are more emphasized in the textbooks of south Korea, on the other hand, meaningful explanations play an important role in the textbooks of north Korea.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.247-251
• /
• 2014

As smart education increases the demand for new teaching-learning methods, teacher training colleges need to systematize smart education teaching-learning methods for pre-service teachers. This study designed a smart education teaching-learning model, which is applicable to pre-service teachers, by analyzing the smart education teaching-learning types for primary and secondary schools at national and international levels and by analyzing the Creation Teaching Learning Assessment (CTLA) model. The goal of smart education is to reinforce capability of learners. The smart education teaching-learning model designed to help pre-service teachers reinforce their smart literacy is suitable for reinforcing capability of future learners to receive smart education. The smart education teaching-learning model in this study was designed as a 15-week teaching plan applicable to pre-service teachers at teacher training colleges. In the teaching-learning model, problem-based learning (PBL), a situated learning model, and cooperative learning model were applied to weekly instructions. Further research should be conducted to prove its effectiveness in allowing pre-service teachers to reinforce their smart literacy by making gradual improvement in this model and to develop and test smart education teaching-learning models constantly.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.419-428
• /
• 2021

Shadow removal plays a key role for the pre-processing of image processing techniques such as object tracking and detection. With the advances of image recognition based on deep convolution neural networks, researches for shadow removal have been actively conducted. In this paper, we propose a novel method for shadow removal, which utilizes self attention distillation to extract semantic features. The proposed method gradually refines results of shadow detection, which are extracted from each layer of the proposed network, via top-down distillation. Specifically, the training procedure can be efficiently performed by learning the contextual information for shadow removal without shadow masks. Experimental results on various datasets show the effectiveness of the proposed method for shadow removal under real world environments.