• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.1
• /
• pp.1-10
• /
• 2021

This study proposed a Long-Short Term Memory network to consider changes in emotion over time, and applied an attention mechanism to give weights to the emotion states that appear at specific moments. We used 32 channel EEG data from DEAP database. A 2-level classification (Low and High) experiment and a 3-level classification experiment (Low, Middle, and High) were performed on Valence and Arousal emotion model. As a result, accuracy of the 2-level classification experiment was 90.1% for Valence and 88.1% for Arousal. The accuracy of 3-level classification was 83.5% for Valence and 82.5% for Arousal.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• The Journal of Information Systems
• /
• v.31 no.3
• /
• pp.1-18
• /
• 2022

Purpose The purpose of this study is to analize a psychological and behavioral mechanism for using profile picture management in digital service such as social network service. Profile picture management falls under metadata management and is performed only by those who want it. This means that it, is one of the typical makeup-type digital shadow works (DSWs) which have not been studied yet. Design/methodology/approach This study adopts ground theory method(GTM) as research methodology. GTM, which is one of qualitative methodologies, is for developing theories while most survey based methodologies, which are well adopted in much research for information systems, are for validation of theories. By interviewing ten users, the data are collected and analyzed by open coding, axis coding with paradigm model, and selective coding. Findings In result, 39 codes are found and classified into 29 sub classes and 15 classes. These 15 classes are organized by paradigm model which derives core code of profile picture management as 'voluntary management tasks to experience small pleasures with intermittent attention'. Finally, based on the paradigm model and the core code, the story line, which can explain profile picture management, is suggested.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4326-4344
• /
• 2021

The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.840-860
• /
• 2023

Aiming at the serious occlusion and slow tracking speed in pedestrian target tracking and recognition in complex scenes, a target tracking method based on improved YOLO v5 combined with Deep SORT is proposed. By merging the attention mechanism ECA-Net with the Neck part of the YOLO v5 network, using the CIoU loss function and the method of CIoU non-maximum value suppression, connecting the Deep SORT model using Shuffle Net V2 as the appearance feature extraction network to achieve lightweight and fast speed tracking and the purpose of improving tracking under occlusion. A large number of experiments show that the improved YOLO v5 increases the average precision by 1.3% compared with other algorithms. The improved tracking model, MOTA reaches 54.3% on the MOT17 pedestrian tracking data, and the tracking accuracy is 3.7% higher than the related algorithms and The model presented in this paper improves the FPS by nearly 5 on the fps indicator.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.19-21
• /
• 2021

In this paper, we introduce the model so-called Explainable Fact-Checking model based on attention mechanism which shows both the result of fact check of the news and the evidence of verdict. Recently, several news surge on media, so fact check attracts much attentions. However, in present fact check relies on the search made by journalists and members of fact check orgainzation, so there is some researchs about automated fact checking. Therefore in this paper we propose explainable automated fact checking model.

• Nuclear Engineering and Technology
• /
• v.55 no.5
• /
• pp.1630-1643
• /
• 2023

The correct situation awareness (SA) of operators is important for managing nuclear power plants (NPPs), particularly in accident-related situations. Among the three levels of SA suggested by Ensley, Level 3 SA (i.e., projection of the future status of the situation) is challenging because of the complexity of NPPs as well as the uncertainty of accidents. Hence, several prediction methods using artificial intelligence techniques have been proposed to assist operators in accident prediction. However, these methods only predict short-term plant status (e.g., the status after a few minutes) and do not provide information regarding the uncertainty associated with the prediction. This paper proposes an algorithm that can predict the multivariate and long-term behavior of plant parameters for 2 h with 120 steps and provide the uncertainty of the prediction. The algorithm applies bidirectional long short-term memory and an attention mechanism, which enable the algorithm to predict the precise long-term trends of the parameters with high prediction accuracy. A conditional variational autoencoder was used to provide uncertainty information about the network prediction. The algorithm was trained, optimized, and validated using a compact nuclear simulator for a Westinghouse 900 MWe NPP.

• Korean Journal of Psychosomatic Medicine
• /
• v.4 no.2
• /
• pp.262-268
• /
• 1996

It is important not only understanding the underlying psychodynamic mechanism of the somatization but also understanding the somatization as a process where biological and sociocultural factors are acting as maintaining and exaggerating the primary vague somatic symptoms. Recently, among mechanisms of the somatization biological and cognitive aspect became more important than psychodynamics. When the doctors see patients complain physical discomforts without organic foundation, they should give attention to the mechanism of symptom amplification, misinterpretation, individual cognitive characteristics and learned behavior. Psychiatric disorders which show somatic symptoms should be also evaluated. Autonomic dysfunctions linked with stress would give some clues of the mystery of the mind-body relationship.

• International Journal of Contents
• /
• v.8 no.1
• /
• pp.10-15
• /
• 2012

Since MegaStudy started e-learning business for Korean high school students, the Korean e-learning industry began to expand and steadily gain attention. This paper focused on the analysis of the development of the Korean e-learning business for teens and the growth of MegaStudy. The three institutional mechanisms were used to examine the factors that aided the development of the business. The regulatory mechanism was the government policy to prevent the expansion of the offline private education sector, which greatly aided the growth of the e-learning business. The mimetic mechanism was the notion to mimic the characteristics of the Korean e-business initiatives. The normative mechanism involved the widespread social norm suggesting that every student should be given an equal opportunity of private education. This paper also examined the case of MegaStudy as a successful case of the e-learning companies. It analyzed the business model of MegaStudy, which is based on its advantage as the front-runner and its high-quality contents and services.