• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.

• Korean Journal of Computational Design and Engineering
• /
• v.19 no.3
• /
• pp.253-262
• /
• 2014

3D city model, which consisted of the 3D building models and their geospatial position and orientation, is becoming a valuable resource in virtual reality, navigation systems, civil engineering, etc. The purpose of this research is to propose the new framework to generate the 3D city model that satisfies visual and physical requirements in ground oriented simulation system. At the same time, the framework should meet the demand of the automatic creation and cost-effectiveness, which facilitates the usability of the proposed approach. To do that, I suggest the framework that leverages the mobile mapping system which automatically gathers high resolution images and supplement sensor information like position and direction of the image. And to resolve the problem from the sensor noise and a large number of the occlusions, the fusion of digital map data will be used. This paper describes the overall framework with major process and the recommended or demanded techniques for each processing step.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.4
• /
• pp.119-131
• /
• 2011

In this paper, we explore the application of 2-D dual-tree discrete wavelet transform (DDWT), which is a directional and redundant transform, for image coding. DDWT main property is a more computationally efficient approach to shift invariance. Also, the DDWT gives much better directional selectivity when filtering multidimensional signals. The dual-tree DWT of a signal is implemented using two critically-sampled DWTs in parallel on the same data. The transform is 2-times expansive because for an N-point signal it gives 2N DWT coefficients. If the filters are designed is a specific way, then the sub-band signals of the upper DWT can be interpreted as the real part of a complex wavelet transform, and sub-band signals of the lower DWT can be interpreted as the imaginary part. The quincunx lattice is a sampling method in image processing. It treats the different directions more homogeneously than the separable two dimensional schemes. Quincunx lattice yields a non separable 2D-wavelet transform, which is also symmetric in both horizontal and vertical direction. And non-separable wavelet transformation can generate sub-images of multiple degrees rotated versions. Therefore, non-separable image processing using DDWT services good performance.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.40 no.2
• /
• pp.19-29
• /
• 2015

The purpose of this study is to suggest the grid search method for selecting an optimal decision tree model. It chooses optimal values for the maximum depth of tree and the minimum number of observations that must exist in a node in order for a split to be attempted. Therefore, the grid search method guarantees building a decision tree model that shows more precise and stable classifying performance. Through empirical analysis using data of job satisfaction of workplace reserve force commanders, we show that the grid search method helps us generate an optimal decision tree model that gives us hints for the improvement direction of labor conditions of Korean workplace reserve force commanders.

• Journal of Korean Society for Atmospheric Environment
• /
• v.14 no.E
• /
• pp.41-58
• /
• 1998

In this study, a wide range of volatile organic constituents of environmental tobacco smoke (ETS) were determined using an environmental chamber, where ETS is the sole source of target compounds. ETS was generated in an environmental chamber by a number of different cigarettes, including the Kentucky reference cigarette and eight different commercial brands. More than 30 compounds were measured simultaneously for a total of twelve experimental runs. The target compounds are classified into three major classes, i.e. vapor phase ETS markers including 3-ethnylpyridine (3-EP) and nicotine, carbonyl compounds including formaldehyde, and volatile organic compounds (VOCs). The results from the chamber study were used to generate characterized ratios of selected VOCs to 3-EP, a vapor phase ETS marker. Emission factors for VOCs associated with ETS were also estimated. The characteristic ratios appeared to be generally in good agreement with published data obtained by environmental chamber studies similar to this study. This implies that the ratios may be useful for identifying and quantifying the impact of ETS as a source of target compounds in 'real world' indoor environments, which is affected by a complex mixture of multi-sources. The environmental chamber method described here provides a direct and reliable method to compare the ETS generated by different cigarettes. The method can also be applied to the simultaneous determination of many different ETS components.

• Environmental Engineering Research
• /
• v.25 no.3
• /
• pp.267-273
• /
• 2020

This Hydrokinetic energy system is the process of extracting energy from rivers, canals and others sources to generate small scale electrical energy for decentralized usage. This study investigates the application of Soil and Water Assessment Tool (SWAT) in Geographical Information System (GIS) environment to evaluate the theoretical hydrokinetic energy potentials of selected Rivers (Asa, Awun and Oyun) all in Asa watershed, Kwara state, Nigeria. SWAT was interfaced with an open source GIS system to predict the flow and other hydrological parameters of the sub-basins. The model was calibrated and validated using observed stream flow data. Calibrated flow results were used in conjunction with other parameters to compute the theoretical hydrokinetic energy potentials of the Rivers. Results showed a good correlation between the observed flow and the simulated flow, indicated by ash Sutcliffe Efficiency (NSE) and R² of 0.76 and 0.85, respectively for calibration period, and NSE and R² of 0.70 and 0.74, respectively for the validation period. Also, it was observed that highest potential of 154.82 MW was obtained along River Awun while the lowest potential of 41.63 MW was obtained along River Asa. The energy potentials obtained could be harnessed and deployed to the communities around the watershed for their energy needs.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.11
• /
• pp.657-668
• /
• 2020

This paper investigates the effect of market structure, including some bank-specific variables and macroeconomic conditions, on the profitability of Indonesian Islamic rural banks. We apply the structure conduct performance (SCP) and the relative market power (RMP) hypothesis. Panel data comprising 142 Islamic rural banks from 2013Q1 to 2018Q4 are employed. This study breaks them apart, associated with the level of economic development consisting of Java as developed regions and outside Java as less developed regions. This study employs static and dynamic panel regression. The GMM method, however, is appropriate because of the dynamic nature of profitability. Our results confirm the SCP hypothesis and fail to support the RMP hypothesis. The higher market concentration allows Islamic rural banks to generate a significantly higher profit by conducting a collusive strategy. More interestingly, the collusive behavior may result in more profit for Islamic rural banks located in the developed regions than those in less developed regions. Evidence also highlights the importance of operating efficiency and impaired financing on profitability. High operating efficiency and low impaired financing can improve profit. Our results suggest that capitalizing market share by improving efficiency and optimizing financing contracts between PLS and non-PLS contracts also improve profit.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.10
• /
• pp.1-8
• /
• 2020

The objective of the study is to investigate the effect of growth opportunities on capital structure and dividend policy in Indonesia. The study employs panel data of companies listed on Indonesia Stock Exchange that distribute dividends from 2007 to 2017. Fixed and random effect regression models are used. Findings based on growth opportunities on capital structure and dividend policy in Indonesia are in line with the existing theory (i.e., contracting theory). Growth opportunities have a significant negative correlation with debt ratio and dividend yield, which suggests that firms with high growth opportunities are discouraged to generate debt to resolve underinvestment and asset-substitution problem. Firms with more investment opportunities tend to adopt a low dividend payout policy because the cash flows will be used up for investment. The positive impact of firm size on leverage is due to the low bankruptcy risk and cost of a large company. Profitability has a positive impact on the dividend policy because profitable companies can reserve larger free cash flows and, thus, pay higher dividends. The positive influence of ownership on leverage is interpreted by the unwillingness of majority stockholders to commit to equity financing in order to avoid reducing the ownership and preserve control of the company.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.1
• /
• pp.46-52
• /
• 2004

In this paper, we introduce a case study of developing a miniature humanoid robot which has 16 degrees of freedom, 42 cm heights, and 1.5kg weights. For easy implimentation, the integrated RC-servo motors are adopted as actuators and a digital camera is equipped on its head. So, it can transmit vision data to a remote host computer via wireless modem. The robot can perform staircase walking as well as straight walking and turning to any direction. The user-interface program running on the host computer contains a robot graphic simulator and a motion editor which are used to generate and verify the robot's walking motion. The experimental results show that the robot has various walking capability including straight walking, turning, and stairs walking.

• Journal of KIISE:Software and Applications
• /
• v.26 no.1
• /
• pp.93-93
• /
• 1999

Researches on digit recognition have been conducted actively for a long time because the classes to recognize are much fewer than other character sets and because it is very likely thatthe digit recognition can be applied to many problems in real world, The recent studies on designingrecognition system with high performance are in progress with two different aspects. One is toconstruct a recognizer using several features at the same time, and the other is to use severalrecognizers. In this paper, we propose a multistage combination method to recognize the unconstrainedhandwritten numerals. The method is a two-stage combination method which uses multiplecombination methods at the same time unlike the existing methods with only one combination method.The recognizers are first combined by several combination methods of different classes simultaneously,and then the results of them are combined by another combination method to generate a final result.Five recognizers and eight combination methods are used in the proposed system. The experimentalresults showed that the recognition rates on CENPARMI and CEDAR data were 97.75% and 98.6%,respectively and the recognition performance could be improved as the process passed through stages,We could get the best performance by combining the combination methods of different classes, whichmeans there are a complementary relation among them, The proposed method can be considered asan extended version of the existing combination methods.