• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2018년도 추계 학술논문 발표대회
• /
• pp.59-60
• /
• 2018

The purpose of this study is to predict and classify the accident types based on the KOSHA (Korea Occupational Safety & Health Agency) and weather data. We also have an effort to suggest an important management method according to accident types by deriving feature importance. We designed two models based on accident data and weather data (model(a)) and only weather data (model(b)). As a result of random forest method, the model(b) showed a lack of accuracy in prediction. However, the model(a) presented more accurate prediction results than the model(b). Thus we presented safety management plan based on the results. In the future, this study will continue to carry out real time prediction to occurrence types to prevent safety accidents by supplementing the real time accident data and weather data.

• Advances in Energy Research
• /
• 제6권2호
• /
• pp.91-101
• /
• 2019

This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.153-162
• /
• 2017

Today, weather radar is used as a key tool for modern high-tech weather observations and forecasts, along with a wide variety of ground gauges and weather satellites. In this paper, we propose a frequency transform based weather radar image processing technique to improve the weather radar image damaged by beam blocking and clutter removal in order to minimize the uncertainty of the weather radar observation. In the proposed method, DCT based mean energy correction is performed to improve damage caused by beam shielding, and DWT based morphological image processing and high frequency cancellation are performed to improve damage caused by clutter removal. Experimental results show that the application of the proposed method to the damaged original weather radar image improves the quality of weather radar image adaptively to the weather echo feature around the damaged area. In addition, radar QPE calculated from the improved weather radar image was also qualitatively confirmed to be improved by the damage. In the future, we will develop quantitative evaluation scales through continuous research and develop an improved algorithm of the proposed method through numerical comparison.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 추계학술대회
• /
• pp.514-517
• /
• 2017

태양광 발전 시스템에서 전력 생산은 기상 상태에 따라 크게 영향을 받으므로 안정적인 부하 운용을 위해 태양광 에너지에 대한 예측이 필수적이다. 따라서 태양광 에너지 예측을 위한 기계학습 알고리즘의 입력으로 기상 상태에 대한 데이터가 필요하다. 본 논문에서는 알고리즘에 대한 입력 데이터로 표면의 3시간 동안 누적된 강수량, 상 하향 장파 복사선 평균, 상 하향 단파 복사선 평균, 지상 2m에서의 3시간 동안 온도, 표면에서의 온도 등 15가지 종류의 기상 데이터를 사용한다. 기상 데이터의 통계적 특성을 파악하고 상관관계를 분석하여 태양광 에너지와 70% 이상의 높은 상관성을 갖는 하향 단파 복사선 평균과 상향 단파 복사선 평균을 특징벡터의 주요 원소로 추출하였다.

• 반도체디스플레이기술학회지
• /
• 제17권2호
• /
• pp.76-80
• /
• 2018

In recent years, with the development of automobile technology, smart system technology that assists safe driving has been developed. A camera is installed on the front and rear of the vehicle as well as on the left and right sides to detect and warn of collision risks and hazards. Beyond the technology of simple black-box recording via cameras, we are developing intelligent systems that combine various computer vision technologies. However, most related studies have been developed to optimize performance in laboratory-like environments that do not take environmental factors such as weather into account. In this paper, we propose a method to detect object by restoring visibility in image with degraded image due to weather factors such as fog. First, the image quality degradation such as fog is detected in a single image, and the image quality is improved by restoring using an intermediate value filter. Then, we used an adaptive feature extraction method that removes unnecessary elements such as noise from the improved image and uses it to recognize objects with only the necessary features. In the proposed method, it is shown that more feature points are extracted than the feature points of the region of interest in the improved image.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.794-797
• /
• 2024

Despite advancements in deep learning, existing semantic segmentation models exhibit suboptimal performance under adverse weather conditions, such as fog or rain, whereas they perform well in clear weather conditions. To address this issue, much of the research has focused on making image or feature-level representations weather-independent. However, disentangling the style and content of images remains a challenge. In this work, we propose a novel fine-tuning method, 'freeze-n-update.' We identify a subset of model parameters that are weather-independent and demonstrate that by freezing these parameters and fine-tuning others, segmentation performance can be significantly improved. Experiments on a test dataset confirm both the effectiveness and practicality of our approach.

• 한국산업융합학회 논문집
• /
• 제23권6_2호
• /
• pp.1025-1032
• /
• 2020

In this paper, we propose a method to classify road weather conditions into rain, fog, and sun using a SVM (Support Vector Machine) classifier after extracting weather features from images acquired in real time using an optical sensor installed on a roadside post. A multi-dimensional weather feature vector consisting of factors such as image sharpeness, image entropy, Michelson contrast, MSCN (Mean Subtraction and Contrast Normalization), dark channel prior, image colorfulness, and local binary pattern as global features of weather-related images was extracted from road images, and then a road weather classifier was created by performing machine learning on 700 sun images, 2,000 rain images, and 1,000 fog images. Finally, the classification performance was tested for 140 sun images, 510 rain images, and 240 fog images. Overall classification performance is assessed to be applicable in real road services and can be enhanced further with optimization along with year-round data collection and training.

• 정보처리학회논문지B
• /
• 제18B권4호
• /
• pp.201-212
• /
• 2011

본 논문에서는 특징점 추적을 이용한 끼어들기 위반차량 검지 시스템을 제안한다. 제안된 끼어들기 위반차량 검지 시스템의 전체적인 알고리즘은 영상 변환 및 전처리, 특징 추출, 추적대상 차량의 특징점 등록 및 추적, 끼어들기 위반차량 검지 등의 단계로 구성된다. 특히 형태학적 기울기 영상을 이용하여 특징점을 추출하므로 써 주간 및 야간 영상에 대해 동일한 알고리즘을 적용하여 그림자, 기상 조건, 차량 전조등 및 조명 등에 강인한 영상 검지 시스템을 구성 한다. 제안한 시스템을 끼어들기 금지구간에서 주간, 야간, 비 오는 날 야간에 취득한 영상을 사용하여 실험한 결과 정인식률 99.49%와 오류율 0.51%를 보였다. 또한 실시간처리에 문제가 없는 평균 91.34frame/s의 빠른 처리속도를 나타냈다.

• 전기학회논문지
• /
• 제64권3호
• /
• pp.393-398
• /
• 2015

City or Community-scale Energy Management System(CEMS) is used to reduce the total energy consumed in the city by arranging the energy resources efficiently at the planning stage and controlling them economically at the operating stage. Of the operational functions of the CEMS, generation forecasting of renewable energy resources is an essential feature for the effective supply scheduling. This is because it can develop daily operating schedules of controllable generators in the city (e.g. diesel turbine, micro-gas turbine, ESS, CHP and so on) in order to minimize the inflow of the external power supply system, considering the amount of power generated by the uncontrollable renewable energy resources. This paper is written to introduce numerical models for photo-voltaic power generation prediction based on the weather forecasting information. Unlike the conventional methods using the average radiation or average utilization rate, the proposed models are developed for CEMS applications using the realtime weather forecast information provided by the National Weather Service.

• 한국컴퓨터정보학회논문지
• /
• 제27권7호
• /
• pp.49-55
• /
• 2022

본 논문에서는 날씨와 같은 외부 환경요인에도 강건하게 동작할 수 있는 장애물 감지 기법을 제안한다. 특히, DB 기반의 특징 매칭과 RANSAC(RANdom SAample Consensus)기반의 다중 평면 방식을 통해 증강현실(Augmented Reality, AR)에서 정확하게 위험 상황을 알려줄 수 있는 장애물 감지 시스템을 제안한다. RGB카메라로부터 얻은 영상을 기반으로 장애물을 검출하는 접근법은 영상에 의존하기 때문에 조명에 따른 특징 검출이 부정확하고, 조명이나 자연광 또는 날씨의 영향을 받기 때문에 장애물 검출이 어려워진다. 또한, 복잡한 지형에서 생성되는 다수의 평면은 장애물을 감지하는데 있어서 오차가 커지는 원인이 된다. 이 문제를 완화하기 위해 본 논문에서는 DB기반의 특징 매칭을 통해 조명에 관계없이 장애물을 효율적이고 정확하게 감지한다. 또한, 다중 평면을 RANSAC을 통해 단일 평면으로 정규화하여 특징점을 분류하기 위한 기준을 새롭게 계산한다. 결과적으로 제안하는 방법은 조명, 자연광, 날씨에 관계없이 효율적으로 장애물을 감지할 수 있고, 높낮이나 다른 지형에서도 안정적으로 표면을 감지할 수 있기 때문에 사용자의 안전성 확보에 활용할 수 있을 거라 기대한다. 제안하는 방법은 모바일 디바이스에서 실험한 결과가 대부분 안정적으로 실내/외의 장애물들을 인지하였다.