• Journal of Digital Convergence
• /
• v.18 no.4
• /
• pp.243-250
• /
• 2020

Systematic farming can be planned and managed if long-term agricultural weather information of the plantation is available. Because the greatest risk factor for crop cultivation is the weather. In this study, a method for long-term predicting of agricultural weather using the GloSea5 and machine learning is presented for the cultivation of Chinese cabbage. The GloSea5 is a long-term weather forecast that is available up to 240 days. The deep neural networks and the spatial randomforest were considered as the method of machine learning. The longterm prediction performance of the deep neural networks was slightly better than the spatial randomforest in the sense of root mean squared error and mean absolute error. However, the spatial randomforest has the advantage of predicting temperatures with a global model, which reduces the computation time.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.154-161
• /
• 2018

As the number of smartphone users increases, research on indoor location recognition service is necessary. Access to indoor locations is predominantly WiFi, Bluetooth, etc., but in most quarters, WiFi is equipped with WiFi functionality, which uses WiFi features to provide WiFi functionality. The study uses the random forest algorithm, which employs the fingerprint index of the acquired WiFi and the use of the multI-value classification method, which employs the receiver signal strength of the acquired WiFi. As the data of the fingerprint, a total of 4 radio maps using the Mac address together with the received signal strength were used. The experiment was conducted in a limited indoor space and compared to an indoor location recognition system using an existing random forest, similar to the method proposed in this study for experimental analysis. Experiments have shown that the system's positioning accuracy as suggested by this study is approximately 5.8 % higher than that of a conventional indoor location recognition system using a random forest, and that its location recognition speed is consistent and faster than that of a study.

• Annual Conference of KIPS
• /
• 2015.10a
• /
• pp.1358-1360
• /
• 2015

본 논문에서는 MB-LBP(Multi-scale Block Local Binary Patterns)와 공간피라미드를 이용하여 생성된 특징을 랜덤 포레스트(Random Forest) 분류기에 적용하여 영상내의 표지판 속도를 인식하는 알고리즘을 제안한다. 입력 영상에서 표지판 영역은 다양한 위치와 크기를 가지며 주위 배경이 후보 영역에 포함되므로 먼저 입력 영상에 원형 Hough Transform을 적용하여 원형의 표지판 후보 영역만을 검출한다. 그 후 영상의 화질을 향상시키기 위해 히스토그램 평활화와 모폴로지 연산을 적용하여 표지판의 숫자 영역과 배경 영역의 대비를 높이도록 한다. 표지판의 크기 변화에 강건한 시스템의 구현을 위해 후보 영역에서 LBP(Local Binary Patterns)보다 우수한 성능을 보이는 MB-LBP를 적용하고, 다양한 크기의 속도 표지판을 인식하기 위해 공간 피라미드를 사용하여 지역적 특징과 전역적 특징 모두를 추출하였다. 추출된 특징은 랜덤 포레스트(Random Forest)를 이용하여 각 9개의 속도 표지판으로 분류, 각 속도별 클래스에 대한 인식 성능을 측정하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.1
• /
• pp.1-9
• /
• 2013

This paper propose a human action recognition method that uses bag-of-features (BoF) based on CS-LBP (center-symmetric local binary pattern) and a spatial pyramid in addition to the random forest classifier. To construct the BoF, an image divided into dense regular grids and extract from each patch. A code word which is a visual vocabulary, is formed by k-means clustering of a random subset of patches. For enhanced action discrimination, local BoF histogram from three subdivided levels of a spatial pyramid is estimated, and a weighted BoF histogram is generated by concatenating the local histograms. For action classification, a random forest, which is an ensemble of decision trees, is built to model the distribution of each action class. The random forest combined with the weighted BoF histogram is successfully applied to Standford Action 40 including various human action images, and its classification performance is better than that of other methods. Furthermore, the proposed method allows action recognition to be performed in near real-time.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.398-398
• /
• 2020

대도시 상류부에 위치한 댐의 과도한 방류 또는 급작스러운 붕괴는 대규모의 인명 또는 재산피해를 야기할 수 있으며, 다양한 댐 유입량 조건에 따른 침수양상을 파악하는 것은 수재해 대응능력 향상에 필수적이다. 그러나 다양한 과다한 댐 방류 또는 붕괴유량에 따른 침수 범위는 도시의 내수침수와 달리 매우 넓은 지형조건을 고려하며 침수 범위가 광범위하게 나타날 수 있다. 이는 다양한 댐 유입량 조건에 따른 침수 지도를 생성 및 파악하는데 어려움을 가중시키며, 특히 댐 운영에 따른 침수양상을 실시간으로 파악하는데 어려움을 가중시킨다. 본 연구에서는 저빈도부터 PMF(Probable Maximum Flood) 조건까지의 다양한 댐 유입량자료를 바탕으로, 1차원 하천홍수해석을 실시하였다. 연구 대상으로 팔당댐에 대한 댐 해석을 실시하였으며, 팔당댐 하류에 위치한 서울시에 대한 영향을 분석하였다. 1차원 해석 결과로 산정되는 각하도 단면 별 홍수위자료와 GIS을 연계하여 다양한 발생빈도를 나타내는 유입량에 대한 침수지도를 생성하였으며, 기존에 제시된 발생빈도에 따른 침수지도 외에 임의 빈도의 침수지도를 실시간으로 생성할 수 있는 랜덤포레스트 회귀 모형을 구축하였다. 위의 과정들을 통해 다양한 유입량 조건에 따른 연구대상 지역에서의 침수예상도를 분석할 수 있었으며, 서울시 전반적으로 나타날 수 있는 침수심의 공간적 분포를 파악할 수 있었다. 주어진 침수 지도를 이용하여 서울시에 대한 인구 및 건축물의 경제적 가치 자료를 이용하여 추가적인 홍수 위험도 분석이 가능할 것으로 보이며, 임의 빈도에 대하여 실시간으로 침수를 예측할 수 있는 랜덤포레스트와 연계할 수 있다. 제시된 방법론은 댐의 과다한 방류량과 붕괴 현상을 재현하며, 도시의 수재해 대응능력 향상을 위한 기초자료를 제공할 수 있을 것으로 보인다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.4
• /
• pp.52-67
• /
• 2020

Recently, the Arctic has been exposed to snow-covered land due to melting permafrost every year, and the Korea Geographic Information Institute(NGII) provides polar spatial information service by establishing spatial information of the polar region. However, there is a lack of spatial information on vegetation sensitive to climate change. This research used a multi-temporal Sentinel-2 image to perform land cover classification of the Ny-Ålesund in Arctic Svalbard. In the pre-processing step, 10 bands and 6 vegetation spectral index were generated from multi-temporal Sentinel-2 images. In image-classification step is consisted of extracting the vegetation area through 8-class land cover classification and performing the vegetation species classification. The image classification algorithm used Random Forest to evaluate the accuracy and calculate feature importance through Out-Of-Bag(OOB). To identify the advantages of multi- temporary Sentinel-2 for vegetation classification, the overall accuracy was compared according to the number of images stacked and vegetation spectral index. Overall accuracy was 77% when using single-time Sentinel-2 images, but improved to 81% when using multi-time Sentinel-2 images. In addition, the overall accuracy improved to about 83% in learning when the vegetation index was used additionally. The most important spectral variables to distinguish between vegetation classes are located in the Red, Green, and short wave infrared-1(SWIR1). This research can be used as a basic study that optimizes input characteristics in performing the classification of vegetation in the polar regions.

• Journal of Wetlands Research
• /
• v.23 no.1
• /
• pp.27-34
• /
• 2021

In this study, the main influencing factors of the occurrence of cyanobacteria at each of the eight Multifunctional weirs were derived using a random forest, and a categorical prediction model based on a Algal bloom warning system was developed. As a result of examining the importance of variables in the random forest, it was found that the upstream points were directly affected by weir operation during the occurrence of cyanobacteria. This means that cyanobacteria can be managed through efficient security management. DO and E.C were indicated as major influencers in midstream. The midstream section is a section where large-scale industrial complexes such as Gumi and Gimcheon are concentrated as well as the emissions of basic environmental facilities have a great influence. During the period of heatwave and drought, E.C increases along with the discharge of environmental facilities discharged from the basin, which promotes the outbreak of cyanobacteria. Those monitoring sites located in the middle and lower streams are areas that are most affected by heat waves and droughts, and therefore require preemptive management in preparation for the outbreak of cyanobacteria caused by drought in summer. Through this study, the characteristics of cyanobacteria at each point were analyzed. It can provide basic data for policy decision-making for customized cyanobacteria management.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.547-560
• /
• 2023

Recently, research on predicting ground classification using machine learning techniques, TBM excavation data, and ground data is increasing. In this study, a multi-classification prediction study for uniaxial compressive strength (UCS) was conducted by applying random forest model based on a decision tree among machine learning techniques widely used in various fields to machine data and ground data acquired at three slurry shield TBM sites. For the classification prediction, the training and test data were divided into 7:3, and a grid search including 5-fold cross-validation was used to select the optimal parameter. As a result of classification learning for UCS using a random forest, the accuracy of the multi-classification prediction model was found to be high at both 0.983 and 0.982 in the training set and the test set, respectively. However, due to the imbalance in data distribution between classes, the recall was evaluated low in class 4. It is judged that additional research is needed to increase the amount of measured data of UCS acquired in various sites.

• Journal of Korea Water Resources Association
• /
• v.57 no.5
• /
• pp.321-332
• /
• 2024

Understanding the status of surface cover in riparian zones is essential for river management and flood disaster prevention. Traditional survey methods rely on expert interpretation of vegetation through vegetation mapping or indices. However, these methods are limited by their ability to accurately reflect dynamically changing river environments. Against this backdrop, this study utilized satellite imagery to apply the Random Forest method to assess the distribution of vegetation in rivers over multiple years, focusing on the Naeseong Stream as a case study. Remote sensing data from Sentinel-2 imagery were combined with ground truth data from the Naeseong Stream surface cover in 2016. The Random Forest machine learning algorithm was used to extract and train 1,000 samples per surface cover from ten predetermined sampling areas, followed by validation. A sensitivity analysis, annual surface cover analysis, and accuracy assessment were conducted to evaluate their applicability. The results showed an accuracy of 85.1% based on the validation data. Sensitivity analysis indicated the highest efficiency in 30 trees, 800 samples, and the downstream river section. Surface cover analysis accurately reflects the actual river environment. The accuracy analysis identified 14.9% boundary and internal errors, with high accuracy observed in six categories, excluding scattered and herbaceous vegetation. Although this study focused on a single river, applying the surface cover classification method to multiple rivers is necessary to obtain more accurate and comprehensive data.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.69-72
• /
• 2020

Log Structured Merged Tree(LSM-Tree)구조를 사용하여 빠른 데이터 쓰기 성능을 보유한 RocksDB에는 쓰기 증폭과 공간 증폭 현상이 발생한다. 쓰기 증폭은 과도한 쓰기 연산을 유발하여 데이터 처리 성능 저하와 플래시 메모리 기반 장치의 수명 저하를 초래하며, 공간 증폭은 데이터 저장 공간 점유로 인한 저장 공간 부족 문제를 야기한다. 본 논문에서는 쓰기 증폭과 공간 증폭 완화를 위해 RocksDB 의 성능에 영향 주는 주요 파라미터를 추출하고, 기계학습 기법인 랜덤 포레스트를 사용하여 추출한 파라미터가 쓰기 증폭과 공간 증폭에 미치는 영향을 분석하였다. 실험결과 쓰기 증폭과 공간 증폭에 영향을 많이 주는 주요 요소를 선별하였고 다른 파라미터에 대비해서 성능 격차가 61.7% 더 나타낸 것을 발견하였다.