• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.29-35
• /
• 2020

In this paper, we propose a new structured entity recognition DeNERT model. Recently, the field of natural language processing has been actively researched using pre-trained language representation models with a large amount of corpus. In particular, the named entity recognition, which is one of the fields of natural language processing, uses a supervised learning method, which requires a large amount of training dataset and computation. Reinforcement learning is a method that learns through trial and error experience without initial data and is closer to the process of human learning than other machine learning methodologies and is not much applied to the field of natural language processing yet. It is often used in simulation environments such as Atari games and AlphaGo. BERT is a general-purpose language model developed by Google that is pre-trained on large corpus and computational quantities. Recently, it is a language model that shows high performance in the field of natural language processing research and shows high accuracy in many downstream tasks of natural language processing. In this paper, we propose a new named entity recognition DeNERT model using two deep learning models, DQN and BERT. The proposed model is trained by creating a learning environment of reinforcement learning model based on language expression which is the advantage of the general language model. The DeNERT model trained in this way is a faster inference time and higher performance model with a small amount of training dataset. Also, we validate the performance of our model's named entity recognition performance through experiments.

• Journal of Korea Water Resources Association
• /
• v.54 no.12
• /
• pp.1265-1274
• /
• 2021

The analysis of hyperspectral characteristics of materials near the South Han River has been conducted using riverside area measurements by drone installed hyperspectral sensors. Each spectrum reflectance of the riverside materials were compared and analyzed which were consisted of grass, concrete, soil, etc. To verify the drone installed hyperspectral measurements, a ground spectrometer was deployed for field measurements and comparisons for the materials. The comparison results showed that the riverside materials had their unique hyperspectral band characteristics, and the field measurements were similar to the remote sensing data. For the classification of the riverside area, the K-means clustering method and SVM classification method were utilized. The supervised SVM method showed accurate classification of the riverside area than the unsupervised K-means method. Using classification and clustering methods, the inherent spectral characteristic for each material was found to classify the riverside materials of hyperspectral images from drones.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.11-19
• /
• 2021

A software system is required to change during its life cycle due to various requirements such as adding functionalities, fixing bugs, and adjusting to new computing environments. Such program code modification should be considered as carefully as a new system development becase unexpected software errors could be introduced. In addition, when reusing open source programs, we can expect higher quality software if code changes of the open source program are predicted in advance. This paper proposes a Convolutional Neural Network (CNN)-based deep learning model to predict source code changes. In this paper, the prediction of code changes is considered as a kind of a binary classification problem in deep learning and labeled datasets are used for supervised learning. Java projects and code change logs are collected from GitHub for training and testing datasets. Software metrics are computed from the collected Java source code and they are used as input data for the proposed model to detect code changes. The performance of the proposed model has been measured by using evaluation metrics such as precision, recall, F1-score, and accuracy. The experimental results show the proposed CNN model has achieved 95% in terms of F1-Score and outperformed the multilayer percept-based DNN model whose F1-Score is 92%.

• The Korean Journal of Archival Studies
• /
• no.42
• /
• pp.73-134
• /
• 2014

The ISO 30301 MSR Standards support successful management of organization while providing strategic plans to the issue of records management. In Korea, these standards are established as the national standard (KS) in May 2013, and also, there are actions being taken to adopt the certification of the ISO 30301 Standards. However, to adopt such certification, it is required that the certification operation system needs to be organized, as well as that the society in general should understand about records management. Accordingly, it is even more required an review on the adoption of the system. This study has the purpose in surveying a variety of stakeholders' perception for the adoption of ISO 30301 certification given the circumstance that the ISO 30301 certification is not yet adopted in Korea. For this purpose, the research is implemented through literature review and in-depth interviews. Firstly, the literature review looks at ISO 30301 standards and the concept of certification that is being carried out with the ISO 30301 Standards, and it discusses the necessity of the adoption of the relevant standards' certification. Secondly, there are in-depth interviews carried out to study for the adoption plan for the ISO 30301 certification. The participants to the interviews include five records and certification related experts and five records managers at public institutions whose records management is supervised by National Archives of Korea. Interview data was analyzed based on grounded theory methodology. This study will be able to provide significant implication to build a successful plan for the adoption of ISO 30301 certification by reviewing perception of professional and problem, strategy of this certification.

• Mycobiology
• /
• v.50 no.1
• /
• pp.66-78
• /
• 2022

The identification of oleaginous yeast species capable of simultaneously utilizing xylose and glucose as substrates to generate value-added biological products is an area of key economic interest. We have previously demonstrated that the Cutaneotrichosporon dermatis NICC30027 yeast strain is capable of simultaneously assimilating both xylose and glucose, resulting in considerable lipid accumulation. However, as no high-quality genome sequencing data or associated annotations for this strain are available at present, it remains challenging to study the metabolic mechanisms underlying this phenotype. Herein, we report a 39,305,439 bp draft genome assembly for C. dermatis NICC30027 comprised of 37 scaffolds, with 60.15% GC content. Within this genome, we identified 524 tRNAs, 142 sRNAs, 53 miRNAs, 28 snRNAs, and eight rRNA clusters. Moreover, repeat sequences totaling 1,032,129 bp in length were identified (2.63% of the genome), as were 14,238 unigenes that were 1,789.35 bp in length on average (64.82% of the genome). The NCBI non-redundant protein sequences (NR) database was employed to successfully annotate 11,795 of these unigenes, while 3,621 and 11,902 were annotated with the Swiss-Prot and TrEMBL databases, respectively. Unigenes were additionally subjected to pathway enrichment analyses using the Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), Cluster of Orthologous Groups of proteins (COG), Clusters of orthologous groups for eukaryotic complete genomes (KOG), and Non-supervised Orthologous Groups (eggNOG) databases. Together, these results provide a foundation for future studies aimed at clarifying the mechanistic basis for the ability of C. dermatis NICC30027 to simultaneously utilize glucose and xylose to synthesize lipids.

• Ecology and Resilient Infrastructure
• /
• v.9 no.4
• /
• pp.218-227
• /
• 2022

This study attempted classification through deep learning-based image training for land cover classification in river spaces which is one of the important data for efficient river management. For this purpose, land cover classification analysis with the RGB image of the target section based on the category classification index of major land cover map was conducted by using the learning outcomes from the result of labeling. In addition, land cover classification of the river spaces was performed by unsupervised and supervised classification from Sentinel-2 satellite images provided in an open format, and this was compared with the results of deep learning-based image classification. As a result of the analysis, it showed more accurate prediction results compared to unsupervised classification results, and it presented significantly improved classification results in the case of high-resolution images. The result of this study showed the possibility of classifying water areas and wetlands in the river spaces, and if additional research is performed in the future, the deep learning based image train method for the land cover classification could be used for river management.

• Journal of Gastric Cancer
• /
• v.22 no.2
• /
• pp.120-134
• /
• 2022

Purpose: This study aimed to identify prognostic factors for patients with distant lymph node-involved gastric cancer (GC) using a machine learning algorithm, a method that offers considerable advantages and new prospects for high-dimensional biomedical data exploration. Materials and Methods: This study employed 79 features of clinical pathology, laboratory tests, and therapeutic details from 289 GC patients whose distant lymphadenopathy was presented as the first episode of recurrence or metastasis. Outcomes were measured as any-cause death events and survival months after distant lymph node metastasis. A prediction model was built based on possible outcome predictors using a random survival forest algorithm and confirmed by 5×5 nested cross-validation. The effects of single variables were interpreted using partial dependence plots. A contour plot was used to visually represent survival prediction based on 2 predictive features. Results: The median survival time of patients with GC with distant nodal metastasis was 9.2 months. The optimal model incorporated the prealbumin level and the prothrombin time (PT), and yielded a prediction error of 0.353. The inclusion of other variables resulted in poorer model performance. Patients with higher serum prealbumin levels or shorter PTs had a significantly better prognosis. The predicted one-year survival rate was stratified and illustrated as a contour plot based on the combined effect the prealbumin level and the PT. Conclusions: Machine learning is useful for identifying the important determinants of cancer survival using high-dimensional datasets. The prealbumin level and the PT on distant lymph node metastasis are the 2 most crucial factors in predicting the subsequent survival time of advanced GC.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.75-82
• /
• 2023

Automatic speech recognition (ASR) has been revolutionized with deep learning-based approaches, among which self-supervised learning methods have proven to be particularly effective. In this study, we aim to enhance the performance of OpenAI's Whisper model, a multilingual ASR system on the Korean language. Whisper was pretrained on a large corpus (around 680,000 hours) of web speech data and has demonstrated strong recognition performance for major languages. However, it faces challenges in recognizing languages such as Korean, which is not major language while training. We address this issue by fine-tuning the Whisper model with an additional dataset comprising about 1,000 hours of Korean speech. We also compare its performance against a Transformer model that was trained from scratch using the same dataset. Our results indicate that fine-tuning the Whisper model significantly improved its Korean speech recognition capabilities in terms of character error rate (CER). Specifically, the performance improved with increasing model size. However, the Whisper model's performance on English deteriorated post fine-tuning, emphasizing the need for further research to develop robust multilingual models. Our study demonstrates the potential of utilizing a fine-tuned Whisper model for Korean ASR applications. Future work will focus on multilingual recognition and optimization for real-time inference.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.461-470
• /
• 2023

While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.3-38
• /
• 2024

Hallucination is a significant barrier to the utilization of large-scale language models or multimodal models. In this study, we collected 654 computer science papers with "hallucination" in the abstract from arXiv from December 2022 to January 2024 following the advent of Chat GPT and conducted frequency analysis, knowledge network analysis, and literature review to explore the latest trends in hallucination research. The results showed that research in the fields of "Computation and Language," "Artificial Intelligence," "Computer Vision and Pattern Recognition," and "Machine Learning" were active. We then analyzed the research trends in the four major fields by focusing on the main authors and dividing them into data, hallucination detection, and hallucination mitigation. The main research trends included hallucination mitigation through supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), inference enhancement via "chain of thought" (CoT), and growing interest in hallucination mitigation within the domain of multimodal AI. This study provides insights into the latest developments in hallucination research through a technology-oriented literature review. This study is expected to help subsequent research in both engineering and humanities and social sciences fields by understanding the latest trends in hallucination research.