• 인터넷정보학회논문지
• /
• 제22권1호
• /
• pp.23-30
• /
• 2021

본 논문은 다수의 오토인코더 모델들을 이용한 잡음에 강인한 이미지 분류 시스템을 제안한다. 딥러닝 기술의 발달로 이미지 분류의 정확도는 점점 높아지고 있다. 하지만 입력 이미지가 잡음에 의해서 오염된 경우에는 이미지 분류 성능이 급격히 저하된다. 이미지에 첨가되는 잡음은 이미지의 생성 및 전송 과정에서 필연적으로 발생할 수밖에 없다. 따라서 실제 환경에서 이미지 분류기가 사용되기 위해서는 잡음에 대한 처리 및 대응이 반드시 필요하다. 한편 오토인코더는 입력값과 출력값이 유사하도록 학습되어지는 인공신경망 모델이다. 입력데이터가 학습데이터와 유사하다면 오토인코더의 출력데이터와 입력데이터 사이의 오차는 작을 것이다. 하지만 입력 데이터가 학습데이터와 유사성이 없다면 오토인코더의 출력데이터와 입력데이터 사이의 오차는 클 것이다. 제안하는 시스템은 오토인코더의 입력데이터와 출력데이터 사이의 관계를 이용한다. 제안하는 시스템의 이미지 분류 절차는 2단계로 구성된다. 1단계에서 분류 가능성이 가장 높은 클래스 2개를 선정하고 이들 클래스의 분류 가능성이 서로 유사하면 2단계에서 추가적인 분류 절차를 거친다. 제안하는 시스템의 성능 분석을 위해 가우시안 잡음으로 오염된 MNIST 데이터셋을 대상으로 분류 정확도를 실험하였다. 실험 결과 잡음 환경에서 제안하는 시스템이 CNN(Convolutional Neural Network) 기반의 분류 기법에 비해 높은 정확도를 나타냄을 확인하였다.

• 대한원격탐사학회지
• /
• 제37권5_3호
• /
• pp.1405-1423
• /
• 2021

강우 현상은 물 순환과 에너지 순환의 주요 요소 중 하나이며 강우량 추정은 수자원 확보와 수재해 예측 및 피해 감축에 매우 중요한 역할을 한다. 위성 기반 강우량 추정은 시공간적으로 고해상도인 자료를 통하여 넓은 지역을 연속적으로 감시할 수 있다는 장점이 있다. 본 연구에서는 Himawari-8 Advanced Himawari Imager(AHI) 수증기 채널(6.7 ㎛), 적외 채널(10.8 ㎛)과 기상 레이더 Column Max (CMAX) 합성장을 이용하여 기계학습 기반 정량적 강우량 추정 모델을 개발하였다. 기계학습 기법으로는 랜덤 포레스트(Random Forest, RF)를 사용하였으며 기상 레이더 반사도(dBZ)와 Z-R식으로 변환한 강우강도(mm/hr)를 타겟으로 하는 모델을 구축하여 비교하였다. 레이더 강우강도를 통해 검증하였을 때 임계성공지수(Critical Success Index, CSI)는 0.34, Mean-Absolute-Error (MAE) 4.82 mm/hr였다. GeoKompsat-2(GK-2A) 강우강도 산출물, Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)-Cloud Classification System (CCS) 산출물과 비교하였을 때 강우 유무 분류에서 CSI 21.73%, 10.81%, 강우강도 정량적 평가에서 MAE 31.33%, 23.49% 높은 성능을 보였다. 강우량 산출물을 지도화 한 결과, 실제 강우강도 분포와 유사한 분포를 모의하여 기존 산출물 대비 높은 정확도의 강우량을 추정했다.

• 한국컴퓨터정보학회논문지
• /
• 제23권8호
• /
• pp.9-16
• /
• 2018

In this paper, a kidnapping detection scheme in which human pose estimation is used to classify accurately between kidnapping cases and normal ones is proposed. To estimate human poses from input video, human's 10 joint information is extracted by OpenPose library. In addition to the features which are used in the previous study to represent the size change rates and the regularities of human activities, the human pose estimation features which are computed from the location of detected human's joints are used as the features to distinguish kidnapping situations from the normal accompanying ones. A frame-based kidnapping detection scheme is generated according to the selection of J48 decision tree model from the comparison of several representative classification models. When a video has more frames of kidnapping situation than the threshold ratio after two people meet in the video, the proposed scheme detects and notifies the occurrence of kidnapping event. To check the feasibility of the proposed scheme, the detection accuracy of our newly proposed scheme is compared with that of the previous scheme. According to the experiment results, the proposed scheme could detect kidnapping situations more 4.73% correctly than the previous scheme.

• KEPCO Journal on Electric Power and Energy
• /
• 제4권2호
• /
• pp.89-99
• /
• 2018

Downtime and malfunction of industrial rotor machines represents a crucial cost burden and productivity loss. Fault diagnosis of this equipment has recently been carried out to detect their fault(s) and cause(s) by using fault classification methods. However, these methods are of limited use in detecting rotor faults because of their hypersensitivity to unexpected and different equipment conditions individually. These limitations tend to affect the accuracy of fault classification since fault-related features calculated from vibration signal are moved to other regions or changed. To improve the limited diagnosis accuracy of existing methods, we propose a new approach for fault diagnosis of rotor machines based on the model generated by supervised learning. Our work is based on feature residual values from vibration signals as fault indices. Our diagnostic model is a robust and flexible process that, once learned from historical data only one time, allows it to apply to different target systems without optimization of algorithms. The performance of the proposed method was evaluated by comparing its results with conventional methods for fault diagnosis of rotor machines. The experimental results show that the proposed method can be used to achieve better fault diagnosis, even when applied to systems with different normal-state signals, scales, and structures, without tuning or the use of a complementary algorithm. The effectiveness of the method was assessed by simulation using various rotor machine models.

• 대한원격탐사학회지
• /
• 제34권1호
• /
• pp.45-74
• /
• 2018

Landslide is a natural hazard that threats lives and properties in many areas around the world. Landslides are difficult to recognize, particularly in rainforest regions. Thus, an accurate, detailed, and updated inventory map is required for landslide susceptibility, hazard, and risk analyses. The inconsistency in the results obtained using different features selection techniques in the literature has highlighted the importance of evaluating these techniques. Thus, in this study, six techniques of features selection were evaluated. Very-high-resolution LiDAR point clouds and orthophotos were acquired simultaneously in a rainforest area of Cameron Highlands, Malaysia by airborne laser scanning (LiDAR). A fuzzy-based segmentation parameter (FbSP optimizer) was used to optimize the segmentation parameters. Training samples were evaluated using a stratified random sampling method and set to 70% training samples. Two machine-learning algorithms, namely, Support Vector Machine (SVM) and Random Forest (RF), were used to evaluate the performance of each features selection algorithm. The overall accuracies of the SVM and RF models revealed that three of the six algorithms exhibited higher ranks in landslide detection. Results indicated that the classification accuracies of the RF classifier were higher than the SVM classifier using either all features or only the optimal features. The proposed techniques performed well in detecting the landslides in a rainforest area of Malaysia, and these techniques can be easily extended to similar regions.

• 응용통계연구
• /
• 제35권1호
• /
• pp.19-33
• /
• 2022

SNS의 등장으로 인터넷 이용자들이 온라인에 남기는 텍스트의 양이 방대해지고 그 중요성이 강조되고있다. 특히 네이버의 영화 탭에서 볼 수 있는 영화 평점이나 리뷰는 실제로 관객들이 영화를 보기 전 해당 영화를 볼 것인지 결정하는 데 주요 요인이 되기도 한다. 본 연구는 실제 네이버 영화 리뷰 데이터를 가지고 평점을 예측하는 분석을 수행했다. 영화 리뷰 데이터를 분석하기 위해 평점의 분포를 통해 데이터 특성을 살펴보았고, 텍스트의 의미를 분석하기 위해 형태소 분석을 통한 한국어 자연어처리를 수행했다. 또한 평점 예측에 활용할 모델 선택을 위해 2-Class와 multi-Class 문제들에 대해 머신러닝과 딥러닝, 회귀와 분류 분석을 비교했으며, 오분류의 원인을 영화 리뷰 데이터 특성과 연관시켜 서술했다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.792-799
• /
• 2022

Building Information Modeling (BIM) technology is a key component of modern construction engineering and project management workflows. As-is BIM models that represent the spatial reality of a project site can offer crucial information to stakeholders for construction progress monitoring, error checking, and building maintenance purposes. Geometric methods for automatically converting raw scan data into BIM models (Scan-to-BIM) often fail to make use of higher-level semantic information in the data. Whereas, semantic segmentation methods only output labels at the point level without creating object level models that is necessary for BIM. To address these issues, this research proposes a hybrid semantic-geometric approach for clutter-resistant floorplan generation from laser-scanned building point clouds. The input point clouds are first pre-processed by normalizing the coordinate system and removing outliers. Then, a semantic segmentation network based on PointNet++ is used to label each point as ceiling, floor, wall, door, stair, and clutter. The clutter points are removed whereas the wall, door, and stair points are used for 2D floorplan generation. A region-growing segmentation algorithm paired with geometric reasoning rules is applied to group the points together into individual building elements. Finally, a 2-fold Random Sample Consensus (RANSAC) algorithm is applied to parameterize the building elements into 2D lines which are used to create the output floorplan. The proposed method is evaluated using the metrics of precision, recall, Intersection-over-Union (IOU), Betti error, and warping error.

• Parasites, Hosts and Diseases
• /
• 제47권3호
• /
• pp.235-241
• /
• 2009

The aim of this study was to estimate the benefit from repeated examinations in the diagnosis of enterobiasis in nursery school groups, and to test the effectiveness of individual-based risk predictions using different methods. A total of 604 children were examined using double, and 96 using triple, anal swab examinations. The questionnaires for parents, structured observations, and interviews with supervisors were used to identify factors of possible infection risk. In order to model the risk of enterobiasis at individual level, a similarity-based machine learning and prediction software Constud was compared with data mining methods in the Statistica 8 Data Miner software package. Prevalence according to a single examination was 22.5%; the increase as a result of double examinations was 8.2%. Single swabs resulted in an estimated prevalence of 20.1% among children examined 3 times; double swabs increased this by 10.1%, and triple swabs by 7.3%. Random forest classification, boosting classification trees, and Constud correctly predicted about 2/3 of the results of the second examination. Constud estimated a mean prevalence of 31.5% in groups. Constud was able to yield the highest overall fit of individual-based predictions while boosting classification tree and random forest models were more effective in recognizing Enterobius positive persons. As a rule, the actual prevalence of enterobiasis is higher than indicated by a single examination. We suggest using either the values of the mean increase in prevalence after double examinations compared to single examinations or group estimations deduced from individual-level modelled risk predictions.

• 융합정보논문지
• /
• 제11권7호
• /
• pp.14-20
• /
• 2021

겨울철 도로 결빙으로 인한 사고는 대부분 큰 사고로 이어진다. 이는 운전자가 도로의 결빙을 사전에 자각하기 어렵기 때문이다. 본 연구에서는 AutoML과 CNN의 앙상블 모델을 이용하여 도로교통 이머징 리스크를 정확하게 탐지하는 방법을 연구한다. 비정형 데이터인 이미지를 이용한 CNN 이미지 특징 추출 기반 도로교통 이머징 리스크 분류 모델과 정형 데이터인 기상 데이터를 이용한 AutoML 기반 도로교통 이머징 리스크 분류 모델을 각각 학습시킨다. 그 후 모델들에서 도출된 확률값을 입력하여 CNN 기반 분류 모델을 보완하도록 앙상블 모델을 설계한다. 이를 통해 도로교통 이머징 리스크 분류 성능을 향상하고 더 정확하고 빠르게 운전자에게 경고하여 안전한 주행이 가능하도록 한다.

• 대한안전경영과학회지
• /
• 제26권2호
• /
• pp.23-31
• /
• 2024

In the military, ammunition and explosives stored and managed can cause serious damage if mishandled, thus securing safety through the utilization of ammunition reliability data is necessary. In this study, exploratory data analysis of ammunition inspection records data is conducted to extract reliability information of stored ammunition and to predict the ammunition condition code, which represents the lifespan information of the ammunition. This study consists of three stages: ammunition inspection record data collection and preprocessing, exploratory data analysis, and classification of ammunition condition codes. For the classification of ammunition condition codes, five models based on boosting algorithms are employed (AdaBoost, GBM, XGBoost, LightGBM, CatBoost). The most superior model is selected based on the performance metrics of the model, including Accuracy, Precision, Recall, and F1-score. The ammunition in this study was primarily produced from the 1980s to the 1990s, with a trend of increased inspection volume in the early stages of production and around 30 years after production. Pre-issue inspections (PII) were predominantly conducted, and there was a tendency for the grade of ammunition condition codes to decrease as the storage period increased. The classification of ammunition condition codes showed that the CatBoost model exhibited the most superior performance, with an Accuracy of 93% and an F1-score of 93%. This study emphasizes the safety and reliability of ammunition and proposes a model for classifying ammunition condition codes by analyzing ammunition inspection record data. This model can serve as a tool to assist ammunition inspectors and is expected to enhance not only the safety of ammunition but also the efficiency of ammunition storage management.