• 대한원격탐사학회지
• /
• 제39권1호
• /
• pp.1-21
• /
• 2023

In this technically advanced era, we are surrounded by smartphones, computers, and cameras, which help us to store visual information in 2D image planes. However, such images lack 3D spatial information about the scene, which is very useful for scientists, surveyors, engineers, and even robots. To tackle such problems, depth maps are generated for respective image planes. Depth maps or depth images are single image metric which carries the information in three-dimensional axes, i.e., xyz coordinates, where z is the object's distance from camera axes. For many applications, including augmented reality, object tracking, segmentation, scene reconstruction, distance measurement, autonomous navigation, and autonomous driving, depth estimation is a fundamental task. Much of the work has been done to calculate depth maps. We reviewed the status of depth map estimation using different techniques from several papers, study areas, and models applied over the last 20 years. We surveyed different depth-mapping techniques based on traditional ways and newly developed deep-learning methods. The primary purpose of this study is to present a detailed review of the state-of-the-art traditional depth mapping techniques and recent deep learning methodologies. This study encompasses the critical points of each method from different perspectives, like datasets, procedures performed, types of algorithms, loss functions, and well-known evaluation metrics. Similarly, this paper also discusses the subdomains in each method, like supervised, unsupervised, and semi-supervised methods. We also elaborate on the challenges of different methods. At the conclusion of this study, we discussed new ideas for future research and studies in depth map research.

• 한국전자거래학회지
• /
• 제27권1호
• /
• pp.1-13
• /
• 2022

인터넷, 모바일 등 네트워크 기술이 발전함에 따라 내외부 침입 및 위협으로부터 조직의 자원을 보호하기 위한 보안의 중요성이 커지고 있다. 따라서 최근에는 다양한 보안 로그 이벤트에 대하여 보안 위협 여부를 사전에 파악하고, 예방하는 이상징후 식별 알고리즘의 개발이 강조되고 있다. 과거 규칙 기반 또는 통계 학습에 기반하여 개발되어 온 보안 이상징후 식별 알고리즘은 점차 기계 학습과 딥러닝에 기반한 모델링으로 진화하고 있다. 본 연구에서는 다양한 기계 학습 분석 방법론을 활용하여 악의적 내부자 위협을 사전에 식별하는 최적 알고리즘으로 LSTM-autoencoder를 변형한 Deep-autoencoder 모형을 제안한다. 본 연구는 비지도 학습에 기반한 이상탐지 알고리즘 개발을 통해 적응형 보안의 가능성을 향상시키고, 지도 학습에 기반한 정탐 레이블링을 통해 기존 알고리즘 대비 오탐율을 감소시켰다는 점에서 학문적 의의를 갖는다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.41-51
• /
• 2022

Cables are critical components of cable-stayed bridges. A structural health monitoring system provides real-time cable tension recording for cable health monitoring. However, the measurement data involve multiple sources of variability, i.e., varying environmental and operational factors, which increase the complexity of cable condition monitoring. In this study, a one-class classification method is developed for cable condition assessment using Bayesian factor analysis (FA). The single-peaked vehicle-induced cable tension is assumed to be relevant to vehicle positions and weights. The Bayesian FA is adopted to establish the correlation model between cable tensions and vehicles. Vehicle weights are assumed to be latent variables and the influences of different transverse positions are quantified by coefficient parameters. The Bayesian theorem is employed to estimate the parameters and variables automatically, and the damage index is defined on the basis of the well-trained model. The proposed method is applied to one cable-stayed bridge for cable damage detection. Significant deviations of the damage indices of Cable SJS11 were observed, indicating a damaged condition in 2011. This study develops a novel method to evaluate the health condition of individual cable using the FA in the Bayesian framework. Only vehicle-induced cable tensions are used and there is no need to monitor the vehicles. The entire process, including the data pre-processing, model training and damage index calculation of one cable, takes only 35 s, which is highly efficient.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권11호
• /
• pp.501-512
• /
• 2021

최근 Encoder-Decoder를 기반한 요약은 거의 인간 수준에 도달하였다. 하지만 이는 영어, 중국어 등 수백만 건의 데이터세트가 잘 갖추어진 주류 언어권에서만 활용 가능하며 데이터세트가 구축되지 않은 비주류 언어권에서는 활용하지 못하는 한계가 있다. 또한, 문서의 일부 영역에 초점 하여 요약하는 편향의 문제를 갖고 있어 동화나 소설과 같이 흐름이 있는 문서에는 적합하지 않다. 본 논문에서는 두 개의 Discriminator가 있는 GAN을 통해 비지도 학습 기반의 추상 요약을 하며, 가이드 토큰의 추출과 주입을 통해 편향 문제를 개선하는 추출 요약과 추상 요약을 혼합한 하이브리드 요약 방법을 제안한다. CNN/Daily Mail 데이터세트를 통해 모델을 평가하여 객관적인 타당성을 검증하고 비주류 언어 중 하나인 한국어에서도 유효한 성능을 보인다는 것을 입증한다.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.707-716
• /
• 2009

The role of cost modeller is to facilitate the design process by systematic application of cost factors so as to maintain a sensible and economic relationship between cost, quantity, utility and appearance which thus helps in achieving the client's requirements within an agreed budget. There are a number of research on cost estimates in the early design stage based on the improvement of accuracy or impact factors. It is common knowledge that cost estimates are undertaken progressively throughout the design stage and make use of the information that is available at each phase, through the related research up to now. In addition, Cost estimates in the early design stage shall analyze the information under the various kinds of precondition before reaching the more developed design because a design can be modified and changed in all process depending on clients' requirements. Parametric cost estimating models have been adopted to support decision making in a changeable environment, in the early design stage. These models are using a similar instance or a pattern of historical case to be constituted in project information, geographic design features, relevant data to quantity or cost, etc. OLAP technique analyzes a subject data by multi-dimensional points of view; it supports query, analysis, comparison of required information by diverse queries. OLAP's data structure matches well with multiview-analysis framework. Accordingly, this study implements multi-dimensional information system for case based quantity data related to design information that is utilizing OLAP's technology, and then analyzes impact factors of quantity by the design criteria or parameter of the same meaning. On the basis of given factors examined above, this study will generate the rules on quantity measure and produce resemblance class using clustering of data mining. These sorts of knowledge-base consist of a set of classified data as group patterns, of which will be appropriate stand on the parametric cost estimating method.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.177-189
• /
• 2023

Malware detection is an increasingly important operational focus in cyber security, particularly given the fast pace of such threats (e.g., new malware variants introduced every day). There has been great interest in exploring the use of machine learning techniques in automating and enhancing the effectiveness of malware detection and analysis. In this paper, we present a deep recurrent neural network solution as a stacked Long Short-Term Memory (LSTM) with a pre-training as a regularization method to avoid random network initialization. In our proposal, we use global and short dependencies of the inputs. With pre-training, we avoid random initialization and are able to improve the accuracy and robustness of malware threat hunting. The proposed method speeds up the convergence (in comparison to stacked LSTM) by reducing the length of malware OpCode or bytecode sequences. Hence, the complexity of our final method is reduced. This leads to better accuracy, higher Mattews Correlation Coefficients (MCC), and Area Under the Curve (AUC) in comparison to a standard LSTM with similar detection time. Our proposed method can be applied in real-time malware threat hunting, particularly for safety critical systems such as eHealth or Internet of Military of Things where poor convergence of the model could lead to catastrophic consequences. We evaluate the effectiveness of our proposed method on Windows, Ransomware, Internet of Things (IoT), and Android malware datasets using both static and dynamic analysis. For the IoT malware detection, we also present a comparative summary of the performance on an IoT-specific dataset of our proposed method and the standard stacked LSTM method. More specifically, of our proposed method achieves an accuracy of 99.1% in detecting IoT malware samples, with AUC of 0.985, and MCC of 0.95; thus, outperforming standard LSTM based methods in these key metrics.

• 대한원격탐사학회지
• /
• 제39권4호
• /
• pp.409-423
• /
• 2023

North Korea is carrying out reclamation activities in tidal flat areas distributed throughout the west coast. Previousremote sensing research on North Korean tidal flats either failsto reflect recent trends or focuses on identifying and analyzing tidal flats. Thisstudy aimsto quantify the impact of recent reclamation activitiesin North Korea's coastal areas and contribute knowledge useful for determining the best remote sensing methods for coastal areas with limited accessibility, such as those in North Korea. Using Landsat-8 OLI images from 2014-2022, we analyzed land cover changesin an area on the west coast of Pyeonganbuk-do where reclamation activities are underway. Unsupervised classification using the normalized difference water index and the random forest classification technique were each used to divide the study area into classification groups, and changes in their areas over time were analyzed. The resultsshow a clear decrease in the water area and a tendency to increase cultivated area,supporting the evidence that North Korea'sreclamation isfor agricultural land expansion.Along coasts behind seawalls, the water area decreased by nearly half, and the cultivated area increased by over 2,300%, indicating significant changes and highlighting the anthropogenic nature of the cover changes due to reclamation. Both methods demonstrated high accuracy, making them suitable for detecting cover changes caused by reclamation. It is expected that further quality research will be conducted through the use of high-resolution satellite images and by combining data from multiple satellites in the future.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
• /
• pp.360-365
• /
• 2022

문장 표현(sentence representation)은 자연어처리 분야 내의 다양한 문제 해결 및 응용 개발에 있어 유용하게 활용될 수 있는 주요한 도구 중 하나이다. 하지만 최근 널리 도입되고 있는 사전 학습 언어 모델(pre-trained language model)로부터 도출한 문장 표현은 이방성(anisotropy)이 뚜렷한 등 그 고유의 특성으로 인해 문장 유사도(Semantic Textual Similarity; STS) 측정과 같은 태스크에서 기대 이하의 성능을 보이는 것으로 알려져 있다. 이러한 문제를 해결하기 위해 대조 학습(contrastive learning)을 사전 학습 언어 모델에 적용하는 연구가 문헌에서 활발히 진행되어 왔으며, 그중에서도 레이블이 없는 데이터를 활용하는 비지도 대조 학습 방법이 주목을 받고 있다. 하지만 대다수의 기존 연구들은 주로 영어 문장 표현 개선에 집중하였으며, 이에 대응되는 한국어 문장 표현에 관한 연구는 상대적으로 부족한 실정이다. 이에 본 논문에서는 대표적인 비지도 대조 학습 방법(ConSERT, SimCSE)을 다양한 한국어 사전 학습 언어 모델(KoBERT, KR-BERT, KLUE-BERT)에 적용하여 문장 유사도 태스크(KorSTS, KLUE-STS)에 대해 평가하였다. 그 결과, 한국어의 경우에도 일반적으로 영어의 경우와 유사한 경향성을 보이는 것을 확인하였으며, 이에 더하여 다음과 같은 새로운 사실을 관측하였다. 첫째, 사용한 비지도 대조 학습 방법 모두에서 KLUE-BERT가 KoBERT, KR-BERT보다 더 안정적이고 나은 성능을 보였다. 둘째, ConSERT에서 소개하는 여러 데이터 증강 방법 중 token shuffling 방법이 전반적으로 높은 성능을 보였다. 셋째, 두 가지 비지도 대조 학습 방법 모두 검증 데이터로 활용한 KLUE-STS 학습 데이터에 대해 성능이 과적합되는 현상을 발견하였다. 결론적으로, 본 연구에서는 한국어 문장 표현 또한 영어의 경우와 마찬가지로 비지도 대조 학습의 적용을 통해 그 성능을 개선할 수 있음을 검증하였으며, 이와 같은 결과가 향후 한국어 문장 표현 연구 발전에 초석이 되기를 기대한다.

• 산업융합연구
• /
• 제21권1호
• /
• pp.167-173
• /
• 2023

경제지표를 분석하는 방법으로 회귀 분석이나, 인공지능을 활용하여 미래의 데이터를 예측하는 연구가 발표되었다. 본 연구에서는 토픽모델링을 사용하여 과거 뉴스 기사로부터 얻은 주제 확률 데이터를 이용한 인공지능으로 미래 선물 가격을 예측하는 시스템을 구상하였다. 과거 뉴스 기사로부터 비지도학습을 통한 문서의 주제를 추출할 수 있는 LDA 방법으로 각 뉴스 기사 주제 확률 분포 데이터를 얻을 수 있고, 해당 데이터를 인공지능의 RNN의 파생 구조인 LSTM의 입력 데이터로 활용함으로써 미래 선물 가격을 예측하였다. 본 연구에서 제안한 방법에서는 선물 가격의 추세를 예측할 수 있었고, 이를 활용하여 추후 옵션 상품 등의 파생 상품에 대한 가격 추세도 예측할 수 있을 것으로 보인다. 다만, 일부 데이터에 대해 오차가 발생하는 것이 확인되어 정확도 향상을 위한 추가적인 연구가 필요하다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권4호
• /
• pp.1123-1146
• /
• 2023

In South Korea, there have been many studies on efficient building-energy management using renewable energy facilities in single zero-energy houses or buildings. However, such management was limited due to spatial and economic problems. To realize a smart zero-energy city, studying efficient energy integration for the entire city, not just for a single house or building, is necessary. Therefore, this study was conducted in the eco-friendly energy town of Chungbuk Innovation City. Chungbuk successfully realized energy independence by converging new and renewable energy facilities for the first time in South Korea. This study analyzes energy data collected from public buildings in that town every minute for a year. We propose a smart city building-energy management model based on the results that combine various renewable energy sources with grid power. Supervised learning can determine when it is best to sell surplus electricity, or unsupervised learning can be used if there is a particular pattern or rule for energy use. However, it is more appropriate to use reinforcement learning to maximize rewards in an environment with numerous variables that change every moment. Therefore, we propose a power distribution algorithm based on reinforcement learning that considers the sales of Energy Storage System power from surplus renewable energy. Finally, we confirm through economic analysis that a 10% saving is possible from this efficiency.