• International Journal of Advanced Culture Technology
• /
• 제6권4호
• /
• pp.12-19
• /
• 2018

This article aims to discuss the transition of the Kazakh writing system from Cyrillic to Latin. First, the study investigates the relationship between the Kazakh Cyrillic alphabet and phonology, in order to linguistically evaluate the efficiency of the writing system. Second, the process of determining the Kazakh Latin alphabet is discussed in terms of the Kazakh phonological system. Third, the factors that determined the Latin alphabet of Kazakh language are analyzed. In Kazakh, the phonemic system is subject to controversy among linguists, but it can be said that the phonological system basically follows the one-to-one correspondence to the Russian and Kazakh phonemes. As for the depth of orthographies, Kazakh Cyrillic writing system is not based on the shallow orthographies, so it incorporates morphophonemic information to make skilled readers understand easier. The political and social aspects are considered as a cause of the alphabet change. Although there are studies suggesting the conversion of the writing system is caused by the extrinsic factors rather than the intrinsic factors, the five criteria of Smalley (1964), which compromise the intrinsic and extrinsic factors, are also persuasive. The five factors are 1) Maximum motivation for the learner, 2) Maximum representation of speech, 3) Maximum ease of learning, 4) Maximum transfer, 5) Maximum ease of reproduction.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.47-54
• /
• 2023

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. But previous researches had the flaws of low accuracy and overfitting problem. In this research, attention-based Conv1D and BiGRU model is designed for music emotion classification and comparative experimentation shows that the proposed model is classifying emotions more accurate. We have proposed a Conv1D and Bi-GRU with the attention-based model for emotion classification of our Bengali music dataset. The model integrates attention-based. Wav preprocessing makes use of MFCCs. To reduce the dimensionality of the feature space, contextual features were extracted from two Conv1D layers. In order to solve the overfitting problems, dropouts are utilized. Two bidirectional GRUs networks are used to update previous and future emotion representation of the output from the Conv1D layers. Two BiGRU layers are conntected to an attention mechanism to give various MFCC feature vectors more attention. Moreover, the attention mechanism has increased the accuracy of the proposed classification model. The vector is finally classified into four emotion classes: Angry, Happy, Relax, Sad; using a dense, fully connected layer with softmax activation. The proposed Conv1D+BiGRU+Attention model is efficient at classifying emotions in the Bengali music dataset than baseline methods. For our Bengali music dataset, the performance of our proposed model is 95%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권5호
• /
• pp.1141-1162
• /
• 2024

Humidity is an important parameter in meteorology and is closely related to weather, human health, and the environment. Due to the limitations of the number of observation stations and other factors, humidity data are often not as good as expected, so high-resolution humidity fields are of great interest and have been the object of desire in the research field and industry. This study presents a novel super-resolution algorithm for humidity fields based on the Wasserstein generative adversarial network(WGAN) framework, with the objective of enhancing the resolution of low-resolution humidity field information. WGAN is a more stable generative adversarial networks(GANs) with Wasserstein metric, and to make the training more stable and simple, the gradient cropping is replaced with gradient penalty, and the network feature representation is improved by sub-pixel convolution, residual block combined with convolutional block attention module(CBAM) and other techniques. We evaluate the proposed algorithm using ERA5 relative humidity data with an hourly resolution of 0.25°×0.25°. Experimental results demonstrate that our approach outperforms not only conventional interpolation techniques, but also the super-resolution generative adversarial network(SRGAN) algorithm.

• 대한원격탐사학회지
• /
• 제38권5_3호
• /
• pp.913-924
• /
• 2022

이 연구에서는 국내 연안어장을 대상으로 조식동물 및 서식지에 대한 수중영상 기반의 인공지능 학습자료를 구축하고, state-of-the-art (SOTA) 모델인 High Resolution Network-Object Contextual Representation(HRNet-OCR)과 Shifted Windows-L (Swin-L)을 이용하여, 조식동물 서식지 수중영상의 의미론적 분할을 수행함으로써 화소 또는 화소군 간의 공간적 맥락(상관성)을 반영하는 보다 실제적인 탐지 결과를 제시하였다. 조식동물 서식지인 감태, 모자반의 수중영상 레이블 중 1,390장을 셔플링(shuffling)하여 시험평가를 수행한 결과, 한국수산자원공단의 DeepLabV3+ 사례에 비해 약 29% 향상된 정확도를 도출하였다. 모든 클래스에 대해 Swin-L이 HRNet-OCR보다 판별율이 더 좋게 나타났으며, 특히 데이터가 적은 감태의 경우, Swin-L이 해당 클래스에 대한 특징을 더 풍부하게 반영할 수 있는 것으로 나타났다. 영상분할 결과 대상물과 배경이 정교하게 분리되는 것을 확인되었는데, 이는 Transformer 계열 백본을 활용하면서 특징 추출능력이 더욱 향상된 것으로 보인다. 향후 10,000장의 레이블 데이터베이스가 완성되면 추가적인 정확도 향상이 가능할 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.263-283
• /
• 2024

Users' comments after online shopping are critical to product reputation and business improvement. These comments, sometimes known as e-commerce reviews, influence other customers' purchasing decisions. To confront large amounts of e-commerce reviews, automatic analysis based on machine learning and deep learning draws more and more attention. A core task therein is sentiment analysis. However, the e-commerce reviews exhibit the following characteristics: (1) inconsistency between comment content and the star rating; (2) a large number of unlabeled data, i.e., comments without a star rating, and (3) the data imbalance caused by the sparse negative comments. This paper employs Bidirectional Encoder Representation from Transformers (BERT), one of the best natural language processing models, as the base model. According to the above data characteristics, we propose the F_MixBERT framework, to more effectively use inconsistently low-quality and unlabeled data and resolve the problem of data imbalance. In the framework, the proposed MixBERT incorporates the MixMatch approach into BERT's high-dimensional vectors to train the unlabeled and low-quality data with generated pseudo labels. Meanwhile, data imbalance is resolved by Focal loss, which penalizes the contribution of large-scale data and easily-identifiable data to total loss. Comparative experiments demonstrate that the proposed framework outperforms BERT and MixBERT for sentiment analysis of e-commerce comments.

• 한국컴퓨터정보학회논문지
• /
• 제28권9호
• /
• pp.17-25
• /
• 2023

본 논문에서는 매개변수가 더 적고, 빠르게 추정 가능한 MobileViT 기반 모델을 통해 사람 자세 추정 과업을 수행할 수 있는 모델을 제안한다. 기반 모델은 합성곱 신경망의 특징과 Vision Transformer의 특징이 결합한 구조를 통해 경량화된 성능을 입증한다. 본 연구에서 주요 매커니즘이 되는 Transformer는 그 기반의 모델들이 컴퓨터 비전 분야에서도 합성곱 신경망 기반의 모델들 대비 더 나은 성능을 보이며, 영향력이 커지게 되었다. 이는 사람 자세 추정 과업에서도 동일한 상황이며, Vision Transformer기반의 ViTPose가 COCO, OCHuman, MPII 등 사람 자세 추정 벤치마크에서 모두 최고 성능을 지키고 있는 것이 그 적절한 예시이다. 하지만 Vision Transformer는 매개변수의 수가 많고 상대적으로 많은 연산량을 요구하는 무거운 모델 구조를 가지고 있기 때문에, 학습에 있어 사용자에게 많은 비용을 야기시킨다. 이에 기반 모델은 Vision Transformer가 많은 계산량을 요구하는 부족한 Inductive Bias 계산 문제를 합성곱 신경망 구조를 통한 Local Representation으로 극복하였다. 최종적으로, 제안 모델은 MS COCO 사람 자세 추정 벤치마크에서 제공하는 Validation Set으로 ViTPose 대비 각각 5분의 1과 9분의 1만큼의 3.28GFLOPs, 972만 매개변수를 나타내었고, 69.4 Mean Average Precision을 달성하여 상대적으로 우수한 성능을 보였다.

• 인터넷정보학회논문지
• /
• 제21권3호
• /
• pp.103-111
• /
• 2020

Liver cancer is the most fatal cancer that occurs worldwide. In order to diagnose liver cancer, the patient's physical condition was checked by using a CT technique using radiation. Segmentation was needed to diagnose the liver on the patient's abdominal CT scan, which the radiologists had to do manually, which caused tremendous time and human mistakes. In order to automate, researchers attempted segmentation using image segmentation algorithms in computer vision field, but it was still time-consuming because of the interactive based and the setting value. To reduce time and to get more accurate segmentation, researchers have begun to attempt to segment the liver in CT images using CNNs, which show significant performance in various computer vision fields. The pixel value, or numerical value, of the CT image is called the Hounsfield Unit (HU) value, which is a relative representation of the transmittance of radiation, and usually ranges from about -2000 to 2000. In general, deep learning researchers reduce or limit this range and use it for training to remove noise and focus on the target organ. Here, we observed that the range of HU values was limited in many studies but different in various liver segmentation studies, and assumed that performance could vary depending on the HU range. In this paper, we propose the possibility of considering HU value range as a hyper parameter. U-Net and ResUNet were used to compare and experiment with different HU range limit preprocessing of CHAOS dataset under limited conditions. As a result, it was confirmed that the results are different depending on the HU range. This proves that the range limiting the HU value itself can be a hyper parameter, which means that there are HU ranges that can provide optimal performance for various models.

• Nuclear Engineering and Technology
• /
• 제52권7호
• /
• pp.1429-1435
• /
• 2020

Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy prediction. However, the effectiveness of models still suffers from two issues in PWL prediction: the correlations shifting over time between PWL and other feature parameters, and the example imbalance between fluctuation examples (minority) and stable examples (majority). To address these problems, we propose a cost-sensitive mechanism to facilitate the model to learn the feature representation of later examples and fluctuation examples. By weighting the standard mean square error loss with a cost-sensitive factor, we develop a Cost-Sensitive Long Short-Term Memory (CSLSTM) model to predict the PWL of PWRs. The overall performance of the CSLSTM is assessed by a variety of evaluation metrics with the experimental data collected from a marine PWR simulator. The comparisons with the Long Short-Term Memory (LSTM) model and the Support Vector Regression (SVR) model demonstrate the effectiveness of the CSLSTM.

• 인터넷정보학회논문지
• /
• 제18권6호
• /
• pp.55-63
• /
• 2017

One of the purposes of Information Technology (IT) is to support human response to natural and social problems such as natural disasters and spread of disease, and to improve the quality of human life. Recent climate change has happened worldwide, natural disasters threaten the quality of life, and human safety is no longer guaranteed. IT must be able to support tasks related to disaster response, and more importantly, it should be used to predict and minimize future damage. In South Korea, the data related to the damage is checked out by each local government and then federal government aggregates it. This data is included in disaster reports that the federal government discloses by disaster case, but it is difficult to obtain raw data of the damage even for research purposes. In order to obtain data, information extraction may be applied to disaster reports. In the field of information extraction, most of the extraction targets are web documents, commercial reports, SNS text, and so on. There is little research on information extraction for government disaster reports. They are mostly text, but the structure of each sentence is very different from that of news articles and commercial reports. The features of the government disaster report should be carefully considered. In this paper, information extraction method for South Korea government reports in the word format is presented. This method is based on patterns and dictionaries and provides some additional ideas for tokenizing the damage representation of the text. The experiment result is F1 score of 80.2 on the test set. This is close to cutting-edge information extraction performance before applying the recent deep learning algorithms.

• 한국정보기술학회논문지
• /
• 제17권7호
• /
• pp.31-45
• /
• 2019

현재 지능적 서비스의 핵심 기술은 딥러닝 즉 신경망, 그리고 GPU 병렬 컴퓨팅 및 빅 데이터와 같은 병렬 분산 처리 기술이다. 하지만 미래의 전 세계적으로 공유된 온톨로지를 통한 지능적 서비스 및 지식 공유 서비스에서는 지식의 표현 및 추론을 위하여 신경망보다 더 나은 방법이 있다. 그것은 시맨틱 웹의 표준 규칙 언어인 RIF 혹은 SWRL의 IF-THEN의 지식 표현이며, 이러한 규칙을 rete 알고리즘을 이용하여 효율적으로 추론할 수 있다. 하지만 단일 컴퓨터에서 동작하는 rete 알고리즘의 처리 규칙 수가 100,000개가 될 경우 그 성능이 수 십 분으로 매우 안 좋아지며, 분명한 한계가 존재한다. 따라서 본 논문에서는 rete 알고리즘의 병렬 및 분산 처리에 대한 과거로부터 현재까지의 연구 내용을 정리 분석하며, 이를 통해 효율적인 rete 알고리즘의 구현을 위해 어떤 측면들이 고려되어야 하는지를 살펴본다.