• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.3
• /
• pp.208-217
• /
• 2023

Accurate estimation of dormancy breaking and first bloom dates is crucial for effective fire blight control by disease model such as Maryblyt in apple orchards. The duration from dormancy breaking to first bloom in apple trees was influenced by daily minimum temperatures during the dormant period. The purpose of this study is to investigate the relationship between minimum temperatures during this period and the time taken for flowering to commence. Webcam data from eight apple orchards, equipped by the National Institute of Horticultural and Herbal Science, were observed from 2019 to 2023 to determine the dates of starting bloom (B1). Additionally, the dormancy breaking dates for these eight sites were estimated using an apple chill day model, with a value of -100.5 DD, based on collected weather data. Two regressions were performed to analyze the relationships: the first regression between the number of days under 0℃ (X₁) and the time from calculated dormancy breaking to observed first bloom (Y), resulting in Y = 0.87 × X₁ + 40.76 with R² = 0.84. The second regression examined the starting date of breaking dormancy (X₂) and the duration from dormancy breaking to observed first bloom (Y), resulting in Y = -1.07 × X₂ + 143.62 with R² = 0.92. These findings suggest that apple anti-chill days are significantly affected by minimum temperatures during the period from dormancy breaking to flowering, indicating their importance in fire blight control measures.

• Journal of Korean Society of Rural Planning
• /
• v.21 no.2
• /
• pp.33-49
• /
• 2015

The objective of this study was to predict land use change based on the land use change scenarios for the Hwangguji river watershed, South Korea. The land use change scenario was derived from the representative concentration pathways (RCP) 4.5 and 8.5 scenarios. The CLUE (conversion of land use and its effects) model was used to simulate the land use change. The CLUE is the modeling framework to simulate land use change considering empirically quantified relations between land use types and socioeconomic and biophysical driving factors through dynamical modeling. The Hwangguji river watershed, South Korea was selected as study area. Future land use changes in 2040, 2070, and 2100 were analyzed relative to baseline (2010) under the RCP4.5 and 8.5 scenarios. Binary logistic regressions were carried out to identify the relation between land uses and its driving factors. CN (Curve number) and impervious area based on the RCP4.5 and 8.5 scenarios were calculated and analyzed using the results of future land use changes. The land use change simulation of the RCP4.5 scenario resulted that the area of urban was forecast to increase by 12% and the area of forest was estimated to decrease by 16% between 2010 and 2100. The land use change simulation of the RCP8.5 scenario resulted that the area of urban was forecast to increase by 16% and the area of forest was estimated to decrease by 18% between 2010 and 2100. The values of Kappa and multiple resolution procedure were calculated as 0.61 and 74.03%. CN (III) and impervious area were increased by 0-1 and 0-8% from 2010 to 2100, respectively. The study findings may provide a useful tool for estimating the future land use change, which is an important factor for the future extreme flood.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.501-513
• /
• 2020

Cutter cutting tests for the cutter placement in the cutter head are being conducted through various studies. Although the cutter spacing at the minimum specific energy is mainly reflected in the cutter head design, since the optimum cutter spacing at the same cutter penetration depth varies depending on the rock conditions, studies on deciding the optimum cutter spacing should be actively conducted. The machine learning techniques such as the decision tree-based regression model and the SVM regression model were applied to predict the optimum cutter spacing ratio for the nonlinear relationship between cutter penetration depth and cutter spacing. Since the decision tree-based methods are greatly influenced by the number of data, SVM regression predicted optimum cutter spacing ratio according to the penetration depth more accurately and it is judged that the SVM regression will be effectively used to decide the cutter spacing when designing the cutter head if a large amount of data of the optimum cutter spacing ratio according to the penetration depth is accumulated.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.6
• /
• pp.239-248
• /
• 2018

Many new technologies are studied with the arrival of the 4th industrial revolution. In particular, emotional intelligence is one of the popular issues. Researchers are focused on emotional analysis studies for music services, based on artificial intelligence and pattern recognition. However, they do not consider how we recommend proper music according to the specific emotion of the user. This is the practical issue for music-related IoT applications. Thus, in this paper, we propose an probability-based music emotion classification technique that makes it possible to classify music with high precision based on the range of emotion, when developing music related services. For user emotion recognition, one of the popular emotional model, Russell model, is referenced. For the features of music, the average amplitude, peak-average, the number of wavelength, average wavelength, and beats per minute were extracted. Multiple regressions were derived using regression analysis based on the collected data, and probability-based emotion classification was carried out. In our 2 different experiments, the emotion matching rate shows 70.94% and 86.21% by the proposed technique, and 66.83% and 76.85% by the survey participants. From the experiment, the proposed technique generates improved results for music classification.

• Journal of Bio-Environment Control
• /
• v.27 no.4
• /
• pp.424-430
• /
• 2018

This study was carried out to estimate growth characteristics of hot pepper and to develop predicted models for the production yield based on the growth parameters and climatic elements. Sigmoid regressions for the prediction of growth parameters in terms of fresh and dry weight, plant height, and leaf area were designed with growing degree days (GDD). The biomass and leaf expansion of hot pepper plants were rapidly increased when 1,000 and 941 GDD. The relative growth rate (RGR) of hot pepper based on dry weight was formulated by Gaussian's equation RGR $(dry\;weight)=0.0562+0.0004{\times}DAT-0.00000557{\times}DAT^2$ and the yields of fresh and dry hot pepper at the 112 days after transplanting were estimated 1,387 and 291 kg/10a, respectively. Results indicated that the growth and yield of hot pepper were predicted by potential growth model under plastic tunnel cultivation. Thus, those models need to calibration and validation to estimate the efficacy of prediction yield in hot pepper using supplement a predicting model, which was based on the parameters and climatic elements.

• Journal of Intelligence and Information Systems
• /
• v.16 no.1
• /
• pp.93-116
• /
• 2010

Ensemble approach is applied to the detection modeling of illegal cash accommodation (ICA) that is the well-known type of fraudulent usages of credit cards in far east nations and has not been addressed in the academic literatures. The performance of fraud detection model (FDM) suffers from the imbalanced data problem, which can be remedied to some extent using an ensemble of many classifiers. It is generally accepted that ensembles of classifiers produce better accuracy than a single classifier provided there is diversity in the ensemble. Furthermore, recent researches reveal that it may be better to ensemble some selected classifiers instead of all of the classifiers at hand. For the effective detection of ICA, we adopt ensemble size reduction technique that prunes the ensemble of all classifiers using accuracy and diversity measures. The diversity in ensemble manifests itself as disagreement or ambiguity among members. Data imbalance intrinsic to FDM affects our approach for ICA detection in two ways. First, we suggest the training procedure with over-sampling methods to obtain diverse training data sets. Second, we use some variants of accuracy and diversity measures that focus on fraud class. We also dynamically calculate the diversity measure-Forward Addition and Backward Elimination. In our experiments, Neural Networks, Decision Trees and Logit Regressions are the base models as the ensemble members and the performance of homogeneous ensembles are compared with that of heterogeneous ensembles. The experimental results show that the reduced size ensemble is as accurate on average over the data-sets tested as the non-pruned version, which provides benefits in terms of its application efficiency and reduced complexity of the ensemble.

• Journal of Industrial Convergence
• /
• v.20 no.9
• /
• pp.91-98
• /
• 2022

This study was conducted to investigate the effect on subjective well-being and depression of the elderly with chronic diseases. Using data from the 15th Korea Welfare Panel in 2020, 3,910 people who responded that they had chronic diseases over the age of 65 were analyzed with stepwise regressions. As a result, the factors affecting the subjective well-being of the elderly with chronic diseases were in the order of satisfaction with leisure life, subjective health status, satisfaction with children relationship, satisfaction with family income, satisfaction with spouse. The explanatory power of this model was 32.0% (F=351.44 p<.001). And also, factors affecting depression were in order of subjective health status, satisfaction with spouse, satisfaction with social relationship, satisfaction with children relationship, satisfaction with leisure life, and satisfaction with family income. The explanatory power of this model was 21.4% (F=178.59, p<.001). Therefore, policy systems to support leisure life of the elderly with chronic disease and measures to induce participation in programs using community resources are needed. And health management programs and institutional support to improve subjective health status are also needed. In addition, it is expected that economic support at the national policy level and various program execution strategies and support personnel will be secured at the community level.

• Journal of Digital Convergence
• /
• v.13 no.4
• /
• pp.101-114
• /
• 2015

The purpose of this study is first to understand agent's turnover from both academic and perspectives. Then we suggest convergence of smart work paradigm and supervisor's support as the relieving factors of turnover, The research model of this study is based upon reviews of turnover literature, the smart work and supervisor's support as moderating variables from which research hypotheses were derived. The data came from the survey from financial sector agents such as banking, insurance, and others. The analyses has been done by SPSS 20.0, We used multiple regressions to test the effects of the tested variables on the dependent variable, job satisfaction. The results of this study find significant relations of smart work and supervisor's supports in relations to personal and job-related turnover. The implication is smart work and supervisor's supports play significant role in increasing job satisfactions. Major finding is too much supervisor's supports ignoring agent's situations may bring reverse effects on relieving turnover.

• Journal of Korean Society of Transportation
• /
• v.30 no.4
• /
• pp.95-106
• /
• 2012

Driver's capability of identifying the change in freeway alignments and environments is one of important factors associated with traffic safety on freeways. In particular, driver's visibility and recognition capability are highly dependent on the altitude of the sun by sunset, sunrise, and nighttime. The purpose of this study is to identify the characteristics of geometric conditions affecting crash occurrences at sunset, sunrise, and nighttime. Poisson and negative binomial regressions were adopted to predict freeway crash frequency in this study. Freeway crash data during 2007~2010 were used for developing the crash frequency models. A set of variables representing the characteristics of geometric conditions were identified as significant ones affecting crash occurrences. The results of this study would be useful in deriving effective countermeasures for preventing traffic crashes that mainly occur at sunset, sunrise, and nighttime on freeways.

• Korean Journal of Social Welfare
• /
• v.54
• /
• pp.203-220
• /
• 2003

The purpose of this study is to identify and empirically study the factors that significantly influence amount and types of Informal caregiving to severely disabled elderly who have functional limitations. For this research, a set of caregivers living with the severely elderly were surveyed. Among collected data, data for 211 caregivers were used for this study. The results suggest that a variety of factors determine informal caregivers do systematically determine their allocation of time to the provision of elderly care. The results of four OLS regressions using data surveyed are as follows. First, The hypothesized role of income is supported in model 1 of the four regression models. Second, the technological components of informal care production significantly influences caregiving hours include the number of ADLs and IADLS needs help, the number of caregivers in the team, the utilization of formal services. Third, any component of production technology of household goods do not significantly influence caregiving hours. Fourth, the components of preferences significantly influence caregiving hours include caregiver's participation in market work, willingness money to pay market-purchased care for the elderly.