• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.13-23
• /
• 2022

In this study we leveraged a probing method to evaluate how a pre-trained L2 LSTM language model represents sentences with relative and coordinate clauses. The probing experiment employed adapted models based on the pre-trained L2 language models to trace the syntactic properties of sentence embedding vector representations. The dataset for probing was automatically generated using several templates related to different sentence structures. To classify the syntactic properties of sentences for each probing task, we measured the adaptation effects of the language models using syntactic priming. We performed linear mixed-effects model analyses to analyze the relation between adaptation effects in a complex statistical manner and reveal how the L2 language models represent syntactic features for English sentences. When the L2 language models were compared with the baseline L1 Gulordava language models, the analogous results were found for each probing task. In addition, it was confirmed that the L2 language models contain syntactic features of relative and coordinate clauses hierarchically in the sentence embedding representations.

• Journal of the Korea Society for Simulation
• /
• v.29 no.4
• /
• pp.1-7
• /
• 2020

Early detection and classification of crop diseases play significant role to help farmers to reduce disease spread and to increase agricultural productivity. Recently, many researchers have used deep learning techniques like convolutional neural network (CNN) classifier for crop disease inspection with dataset of crop leaf images (e.g., PlantVillage dataset). These researches present over 90% of classification accuracy for crop diseases, but they have ability to detect only the pre-trained diseases. This paper proposes an efficient disease inspection CNN model for new crops not used in the pre-trained model. First, we present a benchmark crop disease classifier (CDC) for the crops in PlantVillage dataset using VGG16. Then we build a modified crop disease classifier (mCDC) to inspect diseases for untrained crops. The performance evaluation results show that the proposed model outperforms the benchmark classifier.

• International Journal of Contents
• /
• v.17 no.4
• /
• pp.1-15
• /
• 2021

Named entity recognition (NER) is a crucial task for NLP, which aims to extract information from texts. To build NER systems, deep learning (DL) models are learned with dictionary features by mapping each word in the dataset to dictionary features and generating a unique index. However, this technique might generate noisy labels, which pose significant challenges for the NER task. In this paper, we proposed DL-dictionary features, and evaluated them on two datasets, including the OntoNotes 5.0 dataset and our new infectious disease outbreak dataset named GFID. We used (1) a Bidirectional Long Short-Term Memory (BiLSTM) character and (2) pre-trained embedding to concatenate with (3) our proposed features, named the Convolutional Neural Network (CNN), BiLSTM, and self-attention dictionaries, respectively. The combined features (1-3) were fed through BiLSTM - Conditional Random Field (CRF) to predict named entity classes as outputs. We compared these outputs with other predictions of the BiLSTM character, pre-trained embedding, and dictionary features from previous research, which used the exact matching and partial matching dictionary technique. The findings showed that the model employing our dictionary features outperformed other models that used existing dictionary features. We also computed the F1 score with the GFID dataset to apply this technique to extract medical or healthcare information.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.9
• /
• pp.3885-3890
• /
• 2014

Background: This study aimed to determine nursing student knowledge, behavior and beliefs for breast cancer and breast self-examination receiving courses with a traditional lecturing method (TLM) and the Six Thinking Hats method (STHM). Materials and Methods: The population of the study included a total of 69 second year nursing students, 34 of whom received courses with traditional lecturing and 35 of whom received training with the STHM, an active learning approach. The data of the study were collected pre-training and 15 days and 3 months post-training. The data collection tools were a questionnaire form questioning socio-demographic features, and breast cancer and breast self-examination (BSE) knowledge and the Champion's Health Belief Model Scale. The tests used in data analysis were chi-square, independent samples t-test and paired t-test. Results: The mean knowledge score following traditional lecturing method increased from $9.32{\pm}1.82$ to $14.41{\pm}1.94$ (P<0.001) and it increased from $9.20{\pm}2.33$ to $14.73{\pm}2.91$ after training with the Six Thinking Hats Method (P<0.001). It was determined that there was a significant increase in pre and post-training perceptions of perceived confidence in both groups. There was a statistically significant difference between pre-training, and 15 days and 3 months post-training frequency of BSE in the students trained according to STHM (p<0.05). On the other hand, there was a statistically significant difference between pre-training and 3 months post-training frequency of BSE in the students trained according to TLM. Conclusions: In both training groups, the knowledge of breast cancer and BSE, and the perception of confidence increased similarly. In order to raise nursing student awareness in breast cancer, either of the traditional lecturing method or the Six Thinking Hats Method can be chosen according to the suitability of the teaching material and resources.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• Journal of Software Assessment and Valuation
• /
• v.16 no.1
• /
• pp.45-53
• /
• 2020

In this paper, we describe a new method for acquiring calibration data using a user interaction process, which occurs continuously during web browsing in gaze estimation, and for performing calibration naturally while estimating the user's gaze. The proposed non-intrusive calibration is a tuning process over the pre-trained gaze estimation model to adapt to a new user using the obtained data. To achieve this, a generalized CNN model for estimating gaze is trained, then the non-intrusive calibration is employed to adapt quickly to new users through online learning. In experiments, the gaze estimation model is calibrated with a combination of various user interactions to compare the performance, and improved accuracy is achieved compared to existing methods.

• Journal of Information Technology Applications and Management
• /
• v.30 no.2
• /
• pp.1-18
• /
• 2023

Recently, as technology development has accelerated and product life cycles have been shortened, it is necessary to derive key product features from customers in the R&D planning and evaluation stage. More companies want differentiated competitiveness by providing consumer-tailored products based on big data and artificial intelligence technology. To achieve this, the need to correctly grasp the required quality, which is a requirement of consumers, is increasing. However, the existing methods are centered on suppliers or domain experts, so there is a gap from the actual perspective of consumers. In other words, product attributes were defined by suppliers or field experts, but this may not consider consumers' actual perspective. Accordingly, the demand for deriving the product's main attributes through reviews containing consumers' perspectives has recently increased. Therefore, we propose a review data analysis-based required quality methodology containing customer requirements. Specifically, a pre-training language model with a good understanding of Korean reviews was established, consumer intent was correctly identified, and key contents were extracted from the review through a combination of KeyBERT and topic modeling to derive the required quality for each product. RevBERT, a Korean review domain-specific pre-training language model, was established through further pre-training. By comparing the existing pre-training language model KcBERT, we confirmed that RevBERT had a deeper understanding of customer reviews. In addition, all processes other than that of selecting the required quality were linked to the automation process, resulting in the automation of deriving the required quality based on data.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1375-1385
• /
• 2022

In this paper, we propose a semi-supervised domain adaptation solution to deal with practical face recognition (FR) scenarios where a single face image for each target identity (to be recognized) is only available in the training phase. Main goal of the proposed method is to reduce the discrepancy between the target and the source domain face images, which ultimately improves FR performances. The proposed method is based on the Domain Adatation network (DAN) using an MMD loss function to reduce the discrepancy between domains. In order to train more effectively, we develop a novel loss function learning strategy in which MMD loss and cross-entropy loss functions are adopted by using different weights according to the progress of each epoch during the learning. The proposed weight adoptation focuses on the training of the source domain in the initial learning phase to learn facial feature information such as eyes, nose, and mouth. After the initial learning is completed, the resulting feature information is used to training a deep network using the target domain images. To evaluate the effectiveness of the proposed method, FR performances were evaluated with pretrained model trained only with CASIA-webface (source images) and fine-tuned model trained only with FERET's gallery (target images) under the same FR scenarios. The experimental results showed that the proposed semi-supervised domain adaptation can be improved by 24.78% compared to the pre-trained model and 28.42% compared to the fine-tuned model. In addition, the proposed method outperformed other state-of-the-arts domain adaptation approaches by 9.41%.