• Title/Summary/Keyword: associated random variable

Search Result 44, Processing Time 0.021 seconds

Estimation of Fractional Urban Tree Canopy Cover through Machine Learning Using Optical Satellite Images (기계학습을 이용한 광학 위성 영상 기반의 도시 내 수목 피복률 추정)

  • Sejeong Bae ;Bokyung Son ;Taejun Sung ;Yeonsu Lee ;Jungho Im ;Yoojin Kang
    • Korean Journal of Remote Sensing
    • /
    • v.39 no.5_3
    • /
    • pp.1009-1029
    • /
    • 2023
  • Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R2 of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R2 of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.

Machine Learning Based MMS Point Cloud Semantic Segmentation (머신러닝 기반 MMS Point Cloud 의미론적 분할)

  • Bae, Jaegu;Seo, Dongju;Kim, Jinsoo
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.5_3
    • /
    • pp.939-951
    • /
    • 2022
  • The most important factor in designing autonomous driving systems is to recognize the exact location of the vehicle within the surrounding environment. To date, various sensors and navigation systems have been used for autonomous driving systems; however, all have limitations. Therefore, the need for high-definition (HD) maps that provide high-precision infrastructure information for safe and convenient autonomous driving is increasing. HD maps are drawn using three-dimensional point cloud data acquired through a mobile mapping system (MMS). However, this process requires manual work due to the large numbers of points and drawing layers, increasing the cost and effort associated with HD mapping. The objective of this study was to improve the efficiency of HD mapping by segmenting semantic information in an MMS point cloud into six classes: roads, curbs, sidewalks, medians, lanes, and other elements. Segmentation was performed using various machine learning techniques including random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and gradient-boosting machine (GBM), and 11 variables including geometry, color, intensity, and other road design features. MMS point cloud data for a 130-m section of a five-lane road near Minam Station in Busan, were used to evaluate the segmentation models; the average F1 scores of the models were 95.43% for RF, 92.1% for SVM, 91.05% for GBM, and 82.63% for KNN. The RF model showed the best segmentation performance, with F1 scores of 99.3%, 95.5%, 94.5%, 93.5%, and 90.1% for roads, sidewalks, curbs, medians, and lanes, respectively. The variable importance results of the RF model showed high mean decrease accuracy and mean decrease gini for XY dist. and Z dist. variables related to road design, respectively. Thus, variables related to road design contributed significantly to the segmentation of semantic information. The results of this study demonstrate the applicability of segmentation of MMS point cloud data based on machine learning, and will help to reduce the cost and effort associated with HD mapping.

Biomechanical Analysisz of Varying Backpack Loads on the Lower Limb Moving during Downhill Walking (내림 경사로 보행시 배낭 무게에 따른 하지 움직임의 운동역학적 분석)

  • Chae, Woen-Sik;Lee, Haeng-Seob;Jung, Jae-Hu;Kim, Dong-Soo
    • Korean Journal of Applied Biomechanics
    • /
    • v.25 no.2
    • /
    • pp.191-198
    • /
    • 2015
  • Objective : The purpose of this study was to conduct biomechanical analysis of varying backpack loads on the lower limb movements during downhill walking over $-20^{\circ}$ ramp. Method : Thirteen male university students (age: $23.5{\pm}2.1yrs$, height: $175.7{\pm}4.6cm$, weight: $651.9{\pm}55.5N$) who have no musculoskeletal disorder were recruited as the subjects. Each subject walked over $20^{\circ}$ ramp with four different backpack weights (0%, 10%, 20% and 30% of body weight) in random order at a speed of $1.0{\pm}0.1m/s$. Five digital camcorders and two force plates were used to obtain 3-d data and kinetics of the lower extremity. For each trial being analyzed, five critical instants were identified from the video recordings. Ground reaction force, loading rate, decay rate, and resultant joint moment of the ankle and the knee were determined by the inverse dynamics analysis. For each dependent variable, one-way ANOVA with repeated measures was used to determine whether there were significant differences among four different backpack weight conditions (p<.05). When a significant difference was found, post hoc analyses were performed using the contrast procedure. Results : The results of this study showed that the medio-lateral GRFs at RHC in 20% and 30% body weight were significantly greater than the corresponding value in 0% of body weight. A consistent increase in the vertical GRFs as backpack loads increased was observed. The valgus joint movement of the knee at RTO in 30% body weight was significantly greater than the corresponding values in 0% and 10% body weight. The increased valgus moment of 30% body weight observed in this phase was associated with decelerating and stabilizing effects on the knee joint. The results also showed that the extension and valgus joint moments of the knee were systematically affected by the backpack load during downhill walking. Conclusion : Since downhill walking while carrying heavy external loads in a backpack may lead to excessive knee joint moment, damage can occur to the joint structures such as joint capsule and ligaments. Therefore, excessive repetitions of downhill walking should be avoided if the lower extremity is subjected to abnormally high levels of load over an extended period of time.

The Associated Factors of Health Examinations Behaviors among Some Elderly Persons in Urban and Rural Areas (일부 도시·농촌지역 고령자의 건강검진 수진행동에 관련된 요인)

  • Kim, Yong-Ik;Cho, Young-Chae
    • Journal of agricultural medicine and community health
    • /
    • v.29 no.1
    • /
    • pp.1-14
    • /
    • 2004
  • Objectives: We investigated the factors related to health examination behaviors, sociodemographic aspects and lifestyles of elderly persons with different social backgrounds, and compared sexual and regional differences in urban and rural elderlies. Methods: The total study subjects(464 individuals) from urban(236) and rural areas(228), recruited by a stratified cluster random sampling were interviewed and examined about their sociodemographic profiles, daily lifestyles, subjective health status, conditions concerning use of medical resources, hearing acuity, visual acuity and ADL(activity of daily living), and whether they receive health examination or not. For statistical analysis, Chi-square test was used for sexual and regional comparisons among the groups who have been given a health examination and the one who have not. Results: In urban areas, the rate of having underwent health examination was 54.5% in men and 46.9% in women, and in rural areas, it was 59.8% in men and 42.7% in women, showing its higher rate in men than in women in both areas. For regional differences between the group who have taken a health examination and the one who have not, there was a significant difference in terms of age, family pattern, current job, monthly household income, owning a house, drinking status, eating habit, subjective health status, whether they have taken outpatient medical service for the recent 3 months or not, anxiety for the health, and IADL conditions according to whether the community is rural or urban. In multiple regressions, the influential factors on the health examination behaviors were selected such as having their own house, their family doctor, amnesia, urinary incontinence and chronic disease in urban districts. But in rural districts, the variables were selected such as having or not of their family doctor, urinary incontinence, anxiety for the health, educational level, their own house and chronic disease. Conclusions: It is suggested that the approach to the health examination of an older patient requires substantial consideration of highly variable individual sociodemographic characteristics involving regional attributes as well as their daily life styles, subjective health status, status of performing health examination, physical health status and ADL conditions.

  • PDF