• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.727-730
• /
• 2024

최근 딥러닝 기술이 급속히 발전하며 현대 사회의 다양한 응용분야에서 빠르게 적용되고 있다. 특히 영상 기반의 딥러닝 기술은 자연어 처리와 함께 인공지능 기술의 핵심 연구 분야로 많은 연구가 진행되고 있다. 논문에서는 최근 많은 연구가 진행되고 있는 영상의 의미적 분할 (Semantic Segmentation) 성능을 향상하기 위한 연구를 진행한다. 특히 모델에서 고정밀의 의미적 분할을 수행할 수 있도록 추가적인 정보로써 의사 깊이맵 (Pseudo Depth-Map)을 활용하는 방법을 제안하였다. 더불어, 의사 깊이맵을 모델 상에서 효과적으로 학습시키기 위하여 다중 디코더 모델과 학습 효율을 높이는 학습 스케줄링 전략을 제안한다. 의사 깊이맵과 다중 디코더 모델 기반의 제안 모델은 기존 의미적 분할 모델과 비교하여 iIoU 기준 2%의 성능 향상을 보였다.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.192-195
• /
• 2024

최근 빠른 속도로 개발되고 있는 인공지능 기술은 여러 산업 분야에서 활용 되고 있다. 그러나 최근 딥러닝 네트워크에 대한 부채널 공격 기법들이 등장하고 있으며, 이는 해당 모델을 재구현하여 자율 주행 자동차에 대한 해킹 등과 같이 치명적인 보안 위협이 될 수 있으므로 이에 대한 이해와 대응책이 필요하다. 본 논문에서는 딥러닝 네트워크에 대한 부채널 공격 기법 동향에 대해 살펴보고, 이에 대한 대응 기술 또한 함께 알아본다.

• Journal of The Korean Association of Information Education
• /
• v.21 no.4
• /
• pp.393-401
• /
• 2017

The purpose of this study is to develop a deep learning based learning system for improving learner's data analytical thinking ability. The contents of the study are as follows. First, deep learning was applied to the discovery learning model to improve data analytical thinking ability. This is a learning method that can generate a model showing the relationship of given data by using the deep learning method, then apply the model to new data to obtain the result. Second, we developed a deep learning based system for DBD learning model. Specifically, we developed a system to generate a model of data using the deep learning method and to apply this model. The research of deep learning based learning system will be a new approach to improve learner's data analytical thinking ability in future society where data becomes more important.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.19-24
• /
• 2020

Artificial intelligence technology, which is the core of the 4th industrial revolution, is making intelligent judgments through deep learning techniques and machine learning that it is impossible to predict if it is applied to stock prediction beyond human capabilities. In US fund management companies, artificial intelligence is replacing the role of stock market analyst, and research in this field is actively underway. In this study, we use BLSTM to reduce errors that occur in unidirectional prediction of the existing LSTM method, reduce errors in predictions by predicting in both directions, and macroscopic indicators that affect stock prices, namely, economic growth rate, economic indicators, interest rate, analyze the trade balance, exchange rate, and volume of currency. To help stock investment by accurately predicting the target price of stocks by analyzing the PBR, BPS, and ROE of individual stocks after analyzing macro-indicators, and by analyzing the purchase and sale quantities of foreigners, institutions, pension funds, etc., which have the most influence on stock prices.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.301-302
• /
• 2022

본 논문에서는 사용자 정보를 바탕으로, 사용자에게 적합한 다이빙 플랜을 자동으로 매칭하고, 해양생태정보를 수집하는 시스템을 제안한다. 이 시스템은 사용자의 정보를 바탕으로 사용자에게 적합한 다이빙 플랜이 자동으로 매칭되므로, 최적 조건의 다이빙 플랜이 사용자에게 제공될 수 있다. 또한, 해양 생태 정보를 수집하여 데이터화함으로써 해양 생태 변화에 대한 자료가 사용자에게 제공될 수 있다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.39-43
• /
• 2023

자동 음성 인식(Automatic Speech Recognition, ASR)은 컴퓨터가 인간의 음성을 텍스트로 변환하는 기술이다. 자동 음성 인식 시스템은 다양한 응용 분야에서 사용되며, 음성 명령 및 제어, 음성 검색, 텍스트 트랜스크립션, 자동 음성 번역 등 다양한 작업을 목적으로 한다. 자동 음성 인식의 노력에도 불구하고 노인 음성 인식(Elderly Speech Recognition, ESR)에 대한 어려움은 줄어들지 않고 있다. 본 연구는 노인 음성 인식에 콘포머(Conformer)와 피쳐 퓨전 모듈(Features Fusion Module, FFM)기반 노인 음성 인식 모델을 제안한다. 학습, 평가는 VOTE400(Voide Of The Elderly 400 Hours) 데이터셋으로 한다. 본 연구는 그동안 잘 이뤄지지 않았던 콘포머와 퓨전피쳐를 사용해 노인 음성 인식을 위한 딥러닝 모델을 제시하였다는데 큰 의미가 있다. 또한 콘포머 모델보다 높은 수준의 정확도를 보임으로써 노인 음성 인식을 위한 딥러닝 모델 연구에 기여했다.

• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.

• Korean Journal of Ecology and Environment
• /
• v.56 no.3
• /
• pp.268-279
• /
• 2023

Nowadays, artificial intelligence model approaches such as machine and deep learning have been widely used to predict variations of water quality in various freshwater bodies. In particular, many researchers have tried to predict the occurrence of cyanobacterial blooms in inland water, which pose a threat to human health and aquatic ecosystems. Therefore, the objective of this study were to: 1) review studies on the application of machine learning models for predicting the occurrence of cyanobacterial blooms and its metabolites and 2) prospect for future study on the prediction of cyanobacteria by machine learning models including deep learning. In this study, a systematic literature search and review were conducted using SCOPUS, which is Elsevier's abstract and citation database. The key results showed that deep learning models were usually used to predict cyanobacterial cells, while machine learning models focused on predicting cyanobacterial metabolites such as concentrations of microcystin, geosmin, and 2-methylisoborneol (2-MIB) in reservoirs. There was a distinct difference in the use of input variables to predict cyanobacterial cells and metabolites. The application of deep learning models through the construction of big data may be encouraged to build accurate models to predict cyanobacterial metabolites.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.5
• /
• pp.221-226
• /
• 2024

In information retrieval, queries come in various types, ranging from abstract queries to those containing specific keywords, making it a challenging task to accurately produce results according to user demands. Additionally, search systems must handle queries encompassing various elements such as typos, multilingualism, and codes. Reranking is performed through training suitable documents for queries using DeBERTa, a deep learning model that has shown high performance in recent research. To evaluate the effectiveness of the proposed method, experiments were conducted using the test collection of the Product Search Track at the TREC 2023 international information retrieval evaluation competition. In the comparison of NDCG performance measurements regarding the experimental results, the proposed method showed a 10.48% improvement over BM25, a basic information retrieval model, in terms of search through query error handling, provisional relevance feedback-based product title-based query expansion, and reranking according to query types, achieving a score of 0.7810.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.317-318
• /
• 2022

최근 인공지능 기술이 발전함에 따라 자율주행, 첨단 운전자 지원 시스템과 같은 기술들이 개발되고 있다. 이런 기술들은 교통사고를 예방하여 사망률 등을 감소시키고, 운전자의 편의성을 향상시킨다. 본 논문에서는 자율주행과 첨단 운전자 지원 시스템에서 사용할 수 있는 기술들을 개발하고, 이를 RC카에 적용하여 구현하였고, 인공트랙에서 실험하여 평가하였다. 딥러닝 기반 실시간 객체 인식 및 Opencv 를 이용한 차선 인식기술을 통해 차선을 인식하여 이탈하지 않고 주행하며 표지판 등 객체를 인식하여 상황에 따른 대응으로 모터를 제어하는 기술을 개발하고 인공트랙을 자율주행하는 RC카를 구현하고 실험하였다.