• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.1
• /
• pp.1-7
• /
• 2021

In this paper, we presented the experimental basis for the theoretical background and robustness of the Convolutional Neural Network for object recognition based on artificial intelligence. An experimental result was performed to visualize the weighting filters and feature maps for each layer to determine what characteristics CNN is automatically generating. experimental results were presented on the trend of learning error and identification error rate by checking the relevance of the weight filter and feature map for learning error and identification error. The weighting filter and characteristic map are presented as experimental results. The automatically generated characteristic quantities presented the results of error rates for moving and rotating robustness to geometric changes.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.4
• /
• pp.69-76
• /
• 2008

The self-organizing feature map(SOFM) among a number of neural network uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are moved toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors of the 1-dimensional string, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the opposite direction of input vector. According to simulation results one can conclude that the method using string and the modified neural network is useful tool to mobile robot for the global path planning.

• Kyungpook Mathematical Journal
• /
• v.61 no.4
• /
• pp.889-896
• /
• 2021

Let 𝜙 be an entire self map on ℂ and let 𝜓 be an entire function on ℂ. A weighted composition operator induced by 𝜙 with weight 𝜓 is given by C_𝜓,𝜙. In this paper we investigate under what conditions the weighted composition operators C_𝜓,𝜙 on the Fock space over ℂ induced by 𝜙 with weight of the form $k_c({\zeta})=e^{{\langle}{\zeta},c{\rangle}-{\frac{{\mid}c{\mid}^2}{2}}}$ is normaloid and essentially normaloid.

• Journal of Korea Multimedia Society
• /
• v.11 no.5
• /
• pp.692-702
• /
• 2008

Path planning is gaining more weight in computer games and virtual reality as the number of self-moving characters increases. In the roadmap approach, the map of possible paths is built in advance to plan paths for a character, whose advantage is to provide high-quality paths. On the other hand, a disadvantage is that the road map doesn't reflect properties of characters such as their sizes because they move on the same map once the road map is constructed. In this paper we propose an efficient method to build a different road map for each character so that it can use its own map for path-planning. This method is efficient because the whole map is built once by applying the Visibility Graph regardless of the number of characters and walkable paths are incrementally inserted according to the sizes of characters. The effects of using separate roadmaps are demonstrated through simulations and the trade-offs accompanied with these effects are analyzed.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.283-295
• /
• 2021

This paper proposes a method for generating dense depth map using information of color images and depth map generated based on lidar based on self-organizing map. The proposed depth map upsampling method consists of an initial depth prediction step for an area that has not been acquired from LiDAR and an initial depth filtering step. In the initial depth prediction step, stereo matching is performed on two color images to predict an initial depth value. In the depth map filtering step, in order to reduce the error of the predicted initial depth value, a self-organizing map technique is performed on the predicted depth pixel by using the measured depth pixel around the predicted depth pixel. In the process of self-organization map, a weight is determined according to a difference between a distance between a predicted depth pixel and an measured depth pixel and a color value corresponding to each pixel. In this paper, we compared the proposed method with the bilateral filter and k-nearest neighbor widely used as a depth map upsampling method for performance comparison. Compared to the bilateral filter and the k-nearest neighbor, the proposed method reduced by about 6.4% and 8.6% in terms of MAE, and about 10.8% and 14.3% in terms of RMSE.

• Environmental Engineering Research
• /
• v.23 no.1
• /
• pp.84-91
• /
• 2018

The present study deals with the management of groundwater resources of an important agriculture track of north-western part of Saudi Arabia. Due to strategic importance of the area efforts have been made to estimate aquifer proneness to attenuate contamination. This includes determining hydrodynamic behavior of the groundwater system. The important parameters of any vulnerability model are geological formations in the region, depth to water levels, soil, rainfall, topography, vadose zone, the drainage network and hydraulic conductivity, land use, hydrochemical data, water discharge, etc. All these parameters have greater control and helps determining response of groundwater system to a possible contaminant threat. A widely used DRASTIC model helps integrate these data layers to estimate vulnerability indices using GIS environment. DRASTIC parameters were assigned appropriate ratings depending upon existing data range and a constant weight factor. Further, land-use pattern map of study area was integrated with vulnerability map to produce pollution risk map. A comparison of DRASTIC model was done with GOD and AVI vulnerability models. Model validation was done with $NO_3$, $SO_4$ and Cl concentrations. These maps help to assess the zones of potential risk of contamination to the groundwater resources.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11b
• /
• pp.208-211
• /
• 2005

This paper describes the development process of steering system for reduce idle vibration through the data level of frequency and sensitivity. High stiffness and light weight vehicle is a major target in the refinement of passenger cars to meet customers' contradictable requirements between NVH performance and fuel economy. The target frequency of the steering system is set by benchmarking of a competitive vehicle and the vibration mode map is used to separate steering column modes from resonance of body structure and engine idle rpm. This paper descirbes the analysis approach process for high stiffness of steering system and the design guideline is suggested about steering column and support system by using mother car at initial design stage. We used a patent map in order to analyze accurately a technical trend and suggested the design process using dynamic damper of steering system considering sensitivity. And we established techniques of analysis on steering system and evaluated the level of accuracy of analysis through correlating the test and analysis results. It makes possible to design the good NVH performance vehicle at initial design stage and save vehicles to be used in tests. These improvements can lead to shortening the time needed to develop better vehicles.

• Journal of Korea Multimedia Society
• /
• v.25 no.9
• /
• pp.1266-1272
• /
• 2022

With the recent development of computer vision technology, image processing-based mechanical devices are being developed to realize autonomous driving. The camera-taken images of image processing-based machines are invisible due to scattering and absorption of light in foggy conditions. This lowers the object recognition rate and causes malfunction. The safety of the technology is very important because the malfunction of autonomous driving leads to human casualties. In order to increase the stability of the technology, it is necessary to apply an efficient haze removal algorithm to the camera. In the conventional haze removal method, since the haze removal operation is performed regardless of the haze concentration of the input image, excessive haze is removed and the quality of the resulting image is deteriorated. In this paper, we propose an automatic haze removal method that removes haze according to the haze density of the input image by applying Ngo's Haziness Degree Evaluator (HDE) to Kim's haze removal algorithm using Hazy Particle Map. The proposed haze removal method removes the haze according to the haze concentration of the input image, thereby preventing the quality degradation of the input image that does not require haze removal and solving the problem of excessive haze removal. The superiority of the proposed haze removal method is verified through qualitative and quantitative evaluation.

• ETRI Journal
• /
• v.44 no.1
• /
• pp.51-61
• /
• 2022

In this paper, we introduced a novel voxel-wise UV parameterization and view-dependent texture synthesis for the immersive rendering of a truncated signed distance field (TSDF) scene model. The proposed UV parameterization delegates a precomputed UV map to each voxel using the UV map lookup table and consequently, enabling efficient and high-quality texture mapping without a complex process. By leveraging the convenient UV parameterization, our view-dependent texture synthesis method extracts a set of local texture maps for each voxel from the multiview color images and separates them into a single view-independent diffuse map and a set of weight coefficients for an orthogonal specular map basis. Furthermore, the view-dependent specular maps for an arbitrary view are estimated by combining the specular weights of each source view using the location of the arbitrary and source viewpoints to generate the view-dependent textures for arbitrary views. The experimental results demonstrate that the proposed method effectively synthesizes texture for an arbitrary view, thereby enabling the visualization of view-dependent effects, such as specularity and mirror reflection.