• Magazine of the Korean Society of Agricultural Engineers
• /
• v.41 no.6
• /
• pp.33-43
• /
• 1999

Drought is a serious diaster in agriculutre, especially to upland crops. Hence, the Agricultural Drought Analysis Model (ADAM) that is integratable with GIS was applied to analyae agriculture drought in upland. ADAM is composed of two sub-models , one is a Soil Water Balance Model (SWBM) and the other is a Drougth Analysis Model (DAM) that is based on the Runs theory. The ADAM needs weather data, rainfall data and soil physical characteristics data as input and calculates daily soil moisture contents. GIS was integrated to the ADAM for the calculation of regional soil moisture using digitized landuse map, detaile dsoil map, thiessen network and district boundary . For the agriculutral drought analysis, the ADAM adapt the Runs theory for analyzing drought duration, severity and magnitude . Log-Pearson Type-III probability distribution function and Kolmogorov-Smirnov test were used to test the fitness of good of the model. The integration of ADAM with GIS was successfully implemented and would be operated effectively for the regional drought analysis.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.261-262
• /
• 2006

According to the previous work, various well known methods including maximum a posteriori probability classifier (MAP) and multi layer perceptron networks classifier (MLP) showed competitive results. Since even the small errors often leads to a fatal result, we investigated the method that reduces classification error perfectly by screening out some ambiguous patterns. Those ambiguous patterns can be examined by routine biopsy. We incorporated an ambiguous category in MAP and MLP. Classification results involving 216 spectra gave 100% sensitivity for the case of MLP.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.6
• /
• pp.803-812
• /
• 2017

This paper proposes a local path planning method for stable autonomous driving in rough terrain. There are various path planning techniques such as candidate paths, star algorithm, and Rapidly-exploring Random Tree algorithms. However, such existing path planning has limitations to reflecting the stability of unmanned ground vehicles. This paper suggest a path planning algorithm that considering the stability of unmanned ground vehicles. The algorithm is based on the genetic algorithm and assumes to have probability based obstacle map and elevation map. The simulation result show that the proposed algorithm can be used for real-time local path planning in rough terrain.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.11
• /
• pp.1398-1406
• /
• 2004

The nonlinear signals from an impedance meter for the area average void fraction in two-phase flow have been analyzed to construct a phase space trajectory. The pseudo phase space was constructed with the time delay and proper dimensions. The time delay and the embedding dimension were chosen by the average mutual information and by the false nearest neighborhood, respectively. The attractor-density-map of projected states was used to produce the two dimensional probability distribution functions (2D-PDF). Since the developed 2D-PDF showed clear distinction of the flow patterns, the flow regime identification was made with three rules and with the 2D-PDF. Also, the transition criteria of Mishima-Ishii agree well with the present results.

• Korean Journal of Remote Sensing
• /
• v.21 no.5
• /
• pp.417-423
• /
• 2005

A fuzzy approach using an EM algorithm for image classification is presented. In this study, a double compound stochastic image process is assumed to combine a discrete-valued field for region-class processes and a continuous random field for observed intensity processes. The Markov random field is employed to characterize the geophysical connectedness of a digital image structure. The fuzzy classification is an EM iterative approach based on mixture probability distribution. Under the assumption of the double compound process, given an initial class map, this approach iteratively computes the fuzzy membership vectors in the E-step and the estimates of class-related parameters in the M-step. In the experiments with remotely sensed data, the MRF-based method yielded a spatially smooth class-map with more distinctive configuration of the classes than the non-MRF approach.

• International Journal of Computer Science & Network Security
• /
• v.22 no.1
• /
• pp.55-60
• /
• 2022

Churn prediction is a critical long-term problem for many business like music, games, magazines etc. The churn probability can be used to study many aspects of a business including proactive customer marketing, sales prediction, and churn-sensitive pricing models. It is quite challenging to design machine learning model to predict the customer churn accurately due to the large volume of the time-series data and the temporal issues of the data. In this paper, a parallel artificial neural network is proposed to create a highly-accurate customer churn model on a large customer dataset. The proposed model has achieved significant improvement in the accuracy of churn prediction. The scalability and effectiveness of the proposed algorithm is also studied.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.8
• /
• pp.590-596
• /
• 2004

This paper Presents a new self-adaptation algorithm based on maximum a posteriori (MAP) eigenvoice for Korean connected digit recognition. The proposed MAP eigenvoice is developed by introducing a probability density model for the eigenvoice coefficients. The Proposed approach provides a unified framework that incorporates the Prior model into the conventional eigenvoice estimation. In self-adaptation system we use only one adaptation utterance that will be recognized, we use MAP eigenvoice that is most robust adaptation. In series of self-adaptation experiments on the Korean connected digit recognition task. we demonstrate that the performance of the proposed approach is better than that of the conventional eigenvoice algorithm for a small amount of adaptation data.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.3
• /
• pp.249-255
• /
• 2007

Under the situation of a fire, it is difficult for a rescue robot to use sensors such as vision sensor, ultrasonic sensor or laser distance sensor because of diffusion, refraction or block of light and sound by dense smoke. But, braille blocks that are installed for the visaully impaired at public places such as subway stations can be used as a map for autonomous mobile robot's localization and navigation. In this paper, we developed a laser sensor stan device which can detect braille blcoks in spite of dense smoke and integrated the device to the robot developed to carry out rescue mission in various hazardous disaster areas at KIST. We implemented MCL algorithm for robot's attitude estimation according to the scanned data and transformed a braille block map to a topological map and designed a nonlinear path tracking controller for autonomous navigation. From various simulations and experiments, we could verify that the developed laser sensor device and the proposed localization method are effective to autonomous tracking of braille blocks and the autonomous navigation robot system can be used for rescue under fire.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.201-208
• /
• 2015

3D image must have depth image for depth information in order for 3D realistic media broadcasting. We used generally belief propagation algorithm to solve probability model. Belief propagation algorithm is operated by message passing between nodes corresponding to each pixel. The high resolution image will be able to precisely represent but that required much computational complexity for 3D representation. We proposed fast stereo matching algorithm using belief propagation with multi-resolution based wavelet or lifting. This method can be shown efficiently computational time at much iterations for accurate disparity map.

• Korean Journal of Remote Sensing
• /
• v.23 no.1
• /
• pp.33-42
• /
• 2007

In this paper, an iterative MAP approach using a Bayesian model based on the lognormal distribution for image intensity and a GRF for image texture is proposed for despeckling the SAR images that are corrupted by multiplicative speckle noise. When the image intensity is logarithmically transformed, the speckle noise is approximately Gaussian additive noise, and it tends to a normal probability much faster than the intensity distribution. MRFs have been used to model spatially correlated and signal-dependent phenomena for SAR speckled images. The MRF is incorporated into digital image analysis by viewing pixel types as slates of molecules in a lattice-like physical system defined on a GRF Because of the MRF-SRF equivalence, the assignment of an energy function to the physical system determines its Gibbs measure, which is used to model molecular interactions. The proposed Point-Jacobian Iterative MAP estimation method was first evaluated using simulation data generated by the Monte Carlo method. The methodology was then applied to data acquired by the ESA's ERS satellite on Nonsan area of Korean Peninsula. In the extensive experiments of this study, The proposed method demonstrated the capability to relax speckle noise and estimate noise-free intensity.