• 정보관리학회지
• /
• 제35권2호
• /
• pp.37-62
• /
• 2018

문헌정보학 분야의 국내 학술지 논문으로 구성된 문헌집합을 대상으로 기계학습에 기초한 자동분류의 성능에 영향을 미치는 요소들을 검토하였다. 특히, "정보관리학회지"에 수록된 논문에 주제 범주를 자동 할당하는 분류 성능 측면에서 용어 가중치부여 기법, 학습집합 크기, 분류 알고리즘, 범주 할당 방법 등 주요 요소들의 특성을 다각적인 실험을 통해 살펴보았다. 결과적으로 분류 환경 및 문헌집합의 특성에 따라 각 요소를 적절하게 적용하는 것이 효과적이며, 보다 단순한 모델의 사용으로 상당히 좋은 수준의 성능을 도출할 수 있었다. 또한, 국내 학술지 논문의 분류는 특정 논문에 하나 이상의 범주를 할당하는 복수-범주 분류(multi-label classification)가 실제 환경에 부합한다고 할 수 있다. 따라서 이러한 환경을 고려하여 단순하고 빠른 분류 알고리즘과 소규모의 학습집합을 사용하는 최적의 분류 모델을 제안하였다.

• 한국정보전자통신기술학회논문지
• /
• 제10권6호
• /
• pp.626-632
• /
• 2017

최근의 해마다 발생하는 자연재해를 살펴보면 사망, 실종과 같은 심각한 인명 피해와 더불어 수억 원에 달하는 재산피해가 동반된다. 이를 극복하기 위해 사회적, 경제적 손실을 최소화할 수 있는 ICT 기반의 자연재난 감시 및 대응 기술 개발에 대한 관심도가 높아지고 있다. 제안하는 플랫폼은 무인기에 탑재된 다중 센서 데이터의 실시간 처리 분석을 통해 국지적 산불 재난의 감지 및 상황대응을 지원하고, 통합경보 시스템과 연동하여 대국민 재난 정보 전달 서비스를 제공하는 서비스이다. 본 논문에서는 재난 영상의 획득, 분석, 대응을 수행하는 재난 감시 및 대응 플랫폼의 세부 기능들에 대해서 소개하고, 재난 인지에 핵심요소 기술인 Deep Learning 기반의 산불 영상 분석 기술을 제안한다. 제안하는 Deep Learning 기반 재난 영상 분석은 과거로부터 반복적으로 발생하는 재난이 촬영된 영상 정보를 사전에 미리 학습함으로써, 새롭게 획득한 재난 영상에 대한 재난 발생 여부를 판단한다. 제안하는 산불 영상 분석 알고리즘에 대한 실험 결과를 확인하여 제안하는 기법의 성능을 검증한다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.102-107
• /
• 2020

Recently, the number of people visiting the hospital is increasing due to diabetes. According to the Korean Diabetes Association, statistically, 1 in 7 adults over the age of 30 are suffering from diabetes. As such, diabetes is one of the most common diseases among modern people. In this paper, in addition to blood sugar, which is widely used for diabetes awareness, BMI, which is known to be related to diabetes, triglycerides and cholesterol that cause various complications in diabetics it was studied using random forest techniques and decision trees known to be effective for classification. The importance of each element was confirmed using the results and characteristic importance derived using two techniques. Through this, we studied the diabetes-related relationship between BMI, triglyceride, and cholesterol as well as blood sugar, a factor that diabetic patients should pay much attention to.

• International Journal of Contents
• /
• 제7권1호
• /
• pp.52-57
• /
• 2011

The organizational theory and design in future encourages us to bring a fluid perspective to the problems and challenges face. Organizational structure, strategy, management style, teamwork, organizational change, and even products and services can be vitalized and re-formed through creative images that allow us to act in new ways. Leaders and educators sat all levels must gain comfort in dealing with the insights and implications of diverse perspectives. In a leadership paradigm in action, leaders and educators who have more flexibility and willingness to create a learning organization are successful in improving productivity and student empowerment. The key element to organizational structure and changes for interior design education becomes communications. Finally, we need to recognize that despite its roots in mechanistic thinking, organization is a creative process of imagination. We organize as we imagine, and it is always possible to imagine in new ways.

• Structural Engineering and Mechanics
• /
• 제83권3호
• /
• pp.293-304
• /
• 2022

In this work, a novel reliability approach for combined high and low cycle fatigue (CCF) estimation is developed by combining active learning strategy with least squares support vector machines (LS-SVM) (named as ALS-SVM) surrogate model to address the multi-resources uncertainties, including working loads, material properties and model itself. Initially, a new active learner function combining LS-SVM approach with Monte Carlo simulation (MCS) is presented to improve computational efficiency with fewer calls to the performance function. To consider the uncertainty of surrogate model at candidate sample points, the learning function employs k-fold cross validation method and introduces the predicted variance to sequentially select sampling. Following that, low cycle fatigue (LCF) loads and high cycle fatigue (HCF) loads are firstly estimated based on the training samples extracted from finite element (FE) simulations, and their simulated responses together with the sample points of model parameters in Coffin-Manson formula are selected as the MC samples to establish ALS-SVM model. In this analysis, the MC samples are substituted to predict the CCF reliability of turbine blades by using the built ALS-SVM model. Through the comparison of the two approaches, it is indicated that the reliability model by linear cumulative damage rule provides a non-conservative result compared with that by the proposed one. In addition, the results demonstrate that ALS-SVM is an effective analysis method holding high computational efficiency with small training samples to gain accurate fatigue reliability.

• 시스템엔지니어링학술지
• /
• 제18권2호
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.823-830
• /
• 2022

The risk of project execution increases due to the enlargement and complexity of Engineering, Procurement, and Construction (EPC) plant projects. In the fourth industrial revolution era, there is an increasing need to utilize a large amount of data generated during project execution. The design is a key element for the success of the EPC plant project. Although the design cost is about 5% of the total EPC project cost, it is a critical process that affects the entire subsequent process, such as construction, installation, and operation & maintenance (O&M). This study aims to develop a system using machine-learning (ML) techniques to predict risks and support decision-making based on big data generated in an EPC project's design and construction stages. As a result, three main modules were developed: (M1) the design cost estimation module, (M2) the design error check module, and (M3) the change order forecasting module. M1 estimated design cost based on project data such as contract amount, construction period, total design cost, and man-hour (M/H). M2 and M3 are applications for predicting the severity of schedule delay and cost over-run due to design errors and change orders through unstructured text data extracted from engineering documents. A validation test was performed through a case study to verify the model applied to each module. It is expected to improve the risk response capability of EPC contractors in the design and construction stage through this study.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• 정보보호학회논문지
• /
• 제30권1호
• /
• pp.39-49
• /
• 2020

본 논문에서는 중국 표준 블록 암호 알고리즘인 SM4가 부채널 공격에 취약함을 보이고 그에 대한 대응책을 제안하고자 한다. 먼저, SM4는 차분 전력 분석(DPA)과 상관 전력 분석(CPA)에 기반한 공격에 의해 쉽게 비밀 키가 노출됨을 확인하였다. 논문에서는 공격 취약 요소를 분석하고 데이터 마스킹에 기반한 전력 분석 공격 대응 기법을 설계하였다. 제안한 SM4에 대한 1차 마스킹 기법은 딥 러닝 기반의 다층 퍼셉트론(MLP) 모델을 이용한 공격 프로파일링(profiling) 기반 공격에는 여전히 취약하지만, 차분 전력 분석이나 상관 전력 분석과 같은 비프로파일링(non-profiling) 공격에는 충분히 대응할 수 있음을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• 제23권2호
• /
• pp.47-54
• /
• 2023

This article reviews recent advances and perspectives in neuroscience related to consciousness, cognition, and neural networks in the brain. The neural mechanisms underlying cognitive processes, such as perception, attention, memory, and decision-making, are explored. The article also examines how these processes give rise to our experience of consciousness. The implications of these findings for our understanding of the brain and its functions are presented, as well as potential applications of this knowledge in fields such as medicine, psychology, and artificial intelligence. Additionally, the article explores the concept of a quantum viewpoint concerning consciousness, cognition, and creativity and how incorporating DNA as a key element could reconcile classical and quantum perspectives on human behaviour, consciousness, and cognition, as explained by genomic psychological theory. Furthermore, the article explains how the human brain processes external stimuli through the sensory nervous system and how it can be simulated using an artificial neural network (ANN) consisting of one input layer, multiple hidden layers, and an output layer. The law of learning is also discussed, explaining how ANNs work and how the modification of weight values affects the output and input values. The article concludes with a discussion of future research directions in this field, highlighting the potential for further discoveries and advancements in our understanding of the brain and its functions.