• Korean Journal of Agricultural Science
• /
• v.49 no.4
• /
• pp.837-845
• /
• 2022

In this study, tomato maturity was estimated based on deep learning for a harvesting robot. Tomato images were obtained using a RGB camera installed on a monitoring robot, which was developed previously, and the samples were cropped to 128 × 128 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the mean-variance loss was used to learn implicitly the distribution of the data features by class. In the test stage, the tomato maturity was estimated as a continuous index, which has a range of 0 to 1, by calculating the expected class value. The results show that the F1-score of the classification was approximately 0.94, and the performance was similar to that of a deep learning-based classification task in the agriculture field. In addition, it was possible to estimate the distribution in each maturity stage. From the results, it was found that our approach can not only classify the discrete maturation stages of the tomatoes but also can estimate the continuous maturity.

• Asian-Australasian Journal of Animal Sciences
• /
• v.29 no.6
• /
• pp.775-781
• /
• 2016

A single trait linear mixed random regression test-day model was applied for the first time for analyzing the first lactation monthly test-day milk yield records in Karan Fries cattle. The test-day milk yield data was modeled using a random regression model (RRM) considering different order of Legendre polynomial for the additive genetic effect (4th order) and the permanent environmental effect (5th order). Data pertaining to 1,583 lactation records spread over a period of 30 years were recorded and analyzed in the study. The variance component, heritability and genetic correlations among test-day milk yields were estimated using RRM. RRM heritability estimates of test-day milk yield varied from 0.11 to 0.22 in different test-day records. The estimates of genetic correlations between different test-day milk yields ranged 0.01 (test-day 1 [TD-1] and TD-11) to 0.99 (TD-4 and TD-5). The magnitudes of genetic correlations between test-day milk yields decreased as the interval between test-days increased and adjacent test-day had higher correlations. Additive genetic and permanent environment variances were higher for test-day milk yields at both ends of lactation. The residual variance was observed to be lower than the permanent environment variance for all the test-day milk yields.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.1
• /
• pp.11-13
• /
• 2013

Background: Esophagus cancer, the third most common gastrointestinal cancer overall, demonstrates high incidence in parts of Iran. The counties of Iran vary in size, shape and population size. The aim of this study was to account for spatial support with Area-to-Area (ATA) Poisson Kriging to increase precision of parameter estimates and yield correct variance and create maps of disease rates. Materials and Methods: This study involved application/ecology methodology, illustrated using esophagus cancer data recorded by the Ministry of Health and Medical Education (in the Non-infectious Diseases Management Center) of Iran. The analysis focused on the 336 counties over the years 2003-2007. ATA was used for estimating the parameters of the map with SpaceStat and ArcGIS9.3 software for analysing the data and drawing maps. Results: Northern counties of Iran have high risk estimation. The ATA Poisson Kriging approach yielded variance increase in large sparsely populated counties. So, central counties had the most prediction variance. Conclusions: The ATAPoisson kriging approach is recommended for estimating parameters of disease mapping since this method accounts for spatial support and patterns in irregular spatial areas. The results demonstrate that the counties in provinces Ardebil, Mazandaran and Kordestan have higher risk than other counties.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.5
• /
• pp.25-34
• /
• 2008

By comparing two images, which are captured with the same scene at different time, we can detect a set of outliers, such as occluding objects due to moving vehicles. To reduce the influence from the different intensity properties of the images, an intensity compensation scheme, which is based on the polynomial regression model, is employed. For an accurate detection of outliers alleviating the influence from a set of outliers, a simple technique that reruns the regression is employed. In this paper, an algorithm that iteratively reruns the regression is theoretically analyzed by observing the convergence property of the estimates of the noise variance. Using a correction constant for the estimate of the noise variance is proposed. The correction enables the detection algorithm robust to the choice of thresholds for selecting outliers. Numerical analysis using both synthetic and Teal images are also shown in this paper to show the robust performance of the detection algorithm.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5D
• /
• pp.665-675
• /
• 2008

The objective of this paper is to provide an approximate cost estimating model for tunnel that can be utilized both in quick construction cost estimating for design alternatives, and in evaluating efficiently the cost effects according to the environmental changes during design and construction stage. To meet this requirement, this study analyzes critical cost factors influencing tunnel construction costs. The cost factors include 7 elements such as rock drilling method, advancing method, type of detonator, loader capacity, unit weight and soil volume change factor, length of tunnel. This paper investigates the cost variance according to the change of the cost factors. The result is expected to be used in formulating approximate tunnel cost estimating model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5D
• /
• pp.677-684
• /
• 2008

The paper provides an approximate cost estimating model that can be used for tunnel. Based on the previous study analyzed critical factors that have impact on tunnel construction cost, this paper establishes a cost variance index table that reflects the cost impacts due to the change of the critical cost factors. An estimating procedure is described utilizing the index table. For the verification of the suggested model, the comparison of the estimated construction cost with real project cost is performed. The estimated results range from 95%~111% of the real project costs. As an approximate tunnel cost estimating model, the model can be utilized to quickly estimate tunnel construction costs based on the conceptual information at the planning stage and to efficiently make a decision on design alternatives.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.4
• /
• pp.330-336
• /
• 2016

In this paper, we studied for modified bartlett method to estimate desired information signal. Constrained length of bartlett method is assigned as one, and estimate desired information signal to compensate for delay time. Modified bartlett method is an optimum direction-of-arrival (DoA) estimation algorithm to apply delay time compensation to update optimum weight. The optimum weight is used linear constrained minimum variance method(LCMV). Through simulation, we are comparative analysis proposed algorithm and general Bartlett and MUSIC method. In desired signal estimation, condition simulation is an array antenna element numbers 6 or 9 and desired information signals number 3. We show the superior performance of the proposed algorithm relative to the existing method in estimation of desired information signal.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.8C
• /
• pp.617-626
• /
• 2008

Opportunistic Beamforming (OBF) offers a way to provide the multiuser diversity even in slow fading channel by using randomly generated beam weights, leading to the substantially reduced feedback in the form of the instantaneous SNR from users. In spite of the advantage of the reduced feedback, the imperfect channel estimation might influence the quality of the estimated SNR and channel scheduler so bad that the selected AMC level would be higher than the achievable rate of the actual channel, resulting the corruption of transmitted packet. In this paper, we propose a conservative link adaptation, where the estimated SNR is scaled down by a conservative factor which minimizes the variance of the maximum difference between the actual channel SNR and the resultant SNR. To support the proposed scheme, we analyze the statistics of the difference of the channel SNR and the estimated SNR. Simulation results show that the introduction of conservative factor achieves more than two-fold performance improvement in the presence of channel estimation error and the fairness of PF scheduler is maintained when the least squared channel estimator is applied.

• Journal of Forest and Environmental Science
• /
• v.30 no.2
• /
• pp.233-242
• /
• 2014

Estimating above-ground biomass is important in establishing an applicable methodology of Measurement, Reporting and Verification (MRV) System for Reducing Emissions from Deforestation and Forest Degradation-Plus (REDD+). We developed an estimation model of diameter at breast height (DBH) from IKONOS-2 image that led to above-ground biomass estimation (AGB). The IKONOS image was preprocessed with dark object subtraction and topographic effect correction prior to watershed segmentation for tree crown delineation. Compared to the field observation, the overall segmentation accuracy was 64%. Crown detection percent had a strong negative correlation to tree density. In addition, satellite-based crown area had the highest correlation with the field measured DBH. We then developed the DBH allometric model that explained 74% of the data variance. In average, the estimated DBH was very similar to the measured DBH as well as for AGB. Overall, this method can potentially be applied to estimate AGB over a relatively large and remote tropical forest in Northern Borneo.

• Journal of the Korean GEO-environmental Society
• /
• v.9 no.7
• /
• pp.73-85
• /
• 2008

320 national groundwater monitoring stations have been constructed since 1995 and groundwater levels are measured automatically 4 times a day at each well. It has a difficulty to estimate an average recharge rate of watershed using the recharge rate of the monitoring site because of the lack of its representative on converting a point recharge rate into a spatial one. In this study, the relations between site characteristics (topography, hydraulics, geology, facilities, etc.) and recharge rates of 223 monitoring sites, which were selected using cluster analysis, were analyzed using statistical methods, and finally, regression models were constructed for a recharge rate estimation of non-measured areas. The independent variables for these simple regression models, 1) width of adjacent stream, 2) distance to the nearest stream, 3) topographic slope, and 4) rock type, are proposed using analysis of variance. These models have lots of advantages such as an easy data collection from topographic and geologic maps, a few input variables, and also simplicity in use. Suitability analysis from the comparison between estimation values and original ones at monitoring sites shows that these models are useful for a groundwater recharge estimation.