• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.509-516
• /
• 2004

Semantic interpretation of image is incomplete without some mechanism for understanding semantic content that is not directly visible. For this reason, human assisted content-annotation through natural language is an attachment of textual description to image. However, keyword-based retrieval is in the level of syntactic pattern matching. In other words, dissimilarity computation among terms is usually done by using string matching not concept matching. In this paper, we propose a method for computerized semantic similarity calculation In WordNet space. We consider the edge, depth, link type and density as well as existence of common ancestors. Also, we have introduced method that applied similarity measurement on semantic image retrieval. To combine wi#h the low level features, we use the spatial color distribution model. When tested on a image set of Microsoft's 'Design Gallery Line', proposed method outperforms other approach.

• International Journal of Contents
• /
• v.9 no.4
• /
• pp.1-10
• /
• 2013

The electroencephalogram (EEG) time series is a measure of electrical activity received from multiple electrodes placed on the scalp of a human brain. It provides a direct measurement for characterizing the dynamic aspects of brain activities. These EEG signals are formed from a series of spatial and temporal data with multiple dimensions. Missing data could occur due to fault electrodes. These missing data can cause distortion, repudiation, and further, reduce the effectiveness of analyzing algorithms. Current methodologies for EEG analysis require a complete set of EEG data matrix as input. Therefore, an accurate and reliable imputation approach for missing values is necessary to avoid incomplete data sets for analyses and further improve the usage of performance techniques. This research proposes a new method to automatically recover random consecutive missing data from real world EEG data based on Linear Dynamical System. The proposed method aims to capture the optimal patterns based on two main characteristics in the coevolving EEG time series: namely, (i) dynamics via discovering temporal evolving behaviors, and (ii) correlations by identifying the relationships between multiple brain signals. From these exploits, the proposed method successfully identifies a few hidden variables and discovers their dynamics to impute missing values. The proposed method offers a robust and scalable approach with linear computation time over the size of sequences. A comparative study has been performed to assess the effectiveness of the proposed method against interpolation and missing values via Singular Value Decomposition (MSVD). The experimental simulations demonstrate that the proposed method provides better reconstruction performance up to 49% and 67% improvements over MSVD and interpolation approaches, respectively.

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.583-590
• /
• 2016

Recently, the rapidly increasing interest in IoT in almost all areas of casual human life has led to wide acceptance of speech recognition as a means of HCI. Simultaneously, the demand for speech recognition systems for mobile environments is increasing rapidly. The server-based speech recognition systems are typically fast and show high recognition rates; however, an internet connection is necessary, and complicated server computation is required since a voice is recognized by units of words that are stored in server databases. In this paper, we present a novel method for recognizing the Korean vowel 'ㅗ', as a part of a phoneme based Korean speech recognition system. The proposed method involves analyses of waveform patterns in the time domain instead of the frequency domain, with consequent reduction in computational cost. Elementary algorithms for detecting typical waveform patterns of 'ㅗ' are presented and combined to make final decisions. The experimental results show that the proposed method can achieve 89.9% recognition accuracy.

• Journal of Korea Multimedia Society
• /
• v.3 no.1
• /
• pp.23-33
• /
• 2000

In this paper, we describe an algorithm which can extract human faces with natural pose from complex backgrounds. This method basically adopts the concept that facial region has the nearly same gray level for all pixels within appropriately scaled blocks. Based on the idea, we develop a hierarchial process that first, a block image data with pyramid structure of input image is generated, and some candidate regions for facial regions in the block image are Quickly determined, then finally the detailed facial features; organs are decided. To find the features easily, we introduce a local gray level transform which emphasizes dark and small regions, and estimate the geometrical triangle constraints among the facial features. The merit of our method is that we can be freed from the parameter assignment problem since the algorithm utilize a simple brightness computation, consequently robust systems not being depended on specific parameter values can be easily constructed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.7
• /
• pp.646-652
• /
• 2013

EU's Galileo project is a market-based GNSS (Global Navigation Satellite System) that is under development. It is expected that Galileo will provide the positioning services based on new technologies in 2020s. Because Galileo E1 signal for OS (Open Service) shares the same center frequency with GPS L1 C/A signal, CBOC (Composite Binary Offset Carrier) modulation scheme is used in the E1 signal to guarantee interoperability between two systems. With E1 signal consisting of a data channel and a pilot channel at the same frequency band, there exist several options in designing signal acquisition for Assisted-Galileo receivers. Furthermore, compared to SNR worksheet of Assisted-GPS, some factors should be examined in Assisted-Galileo due to different correlation profile and code length of E1 signal. This paper presents SNR worksheets of Galileo E1 signals in E1-B and E1-C channel. Three implementation losses that are quite different from GPS are mainly analyzed in establishing SNR worksheets. In the worksheet, hybrid long integration of 1.5s is considered to acquire weak signal less than -150dBm. Simulation results show that the final SNR of E1-B signal with -150dBm is 19.4dB and that of E1-C signal is 25.2dB. Comparison of relative computation shows that E1-B channel is more profitable to acquire the strongest signal in weak signal environment. With information from the first satellite signal acquisition, fast acquisition of the weak signal around -155dBm can be performed with E1-C signal in the subsequent satellites.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.24 no.5
• /
• pp.569-576
• /
• 2011

In this paper a new analysis procedure for evaluation of progressive collapse resisting capacity of a structure was proposed based on the nonlinear static analysis procedure. The proposed procedure produces analysis results identical to those obtained by the linear static analysis procedure specified in the GSA guidelines without iteration, therefore saving a lot of computation time and excluding the possibility of human errors during the procedure. To verify the validity of the proposed procedure, the two methods were applied to the analysis of a reinforced concrete moment frame and a steel braced frame subjected to loss of a first story column and the results were compared. According to the analysis results, the two methods produce identical results in the prediction of progressive collapse and the hinge formation. As iterative analysis is not required in the proposed method, significant amount of analysis time is saved in the proposed analysis procedure.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.4
• /
• pp.493-498
• /
• 2004

A novel approach for path planning of a polygonal robot is presented. Traditional path planners perform extensive geometric searching to find the optimal path or to prove that there is no solution. The computation required to prove that there is no solution is equivalent to exhaustive search of the motion space, which is typically very expensive. Humans seems to use a set of several different path planning strategies to analyse the situation of the obstacles in the environment, and quickly recognize whether the path-planning problem is easy to solve, hard to solve or has no solution. This human path-planning strategies have motivated the development of the presented algorithm that combines qualitative shape reasoning and exhaustive geometric searching to speed up the path planning process. It has three planning stages consisting of identification of no-solution cases based on an enclosure test, a qualitative reasoning stage, and finally a complete search algorithm in case the previous two stages cannot determine of the existence of a solution path.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.68-76
• /
• 1998

In this paper, a new morphological image segmentation algorithm of hierarchical structure by binary split is proposed. It splits a region with the lowest quality into two regions using only two markers having the highest contrast. Therefore, it improves the quality of image with limited regions and reduces contour information which is not sensitive to human visual system, when compared with the conventional algorithm. It is appropriate to PSTN, LAN, and mobile networks, of which the available transmission bandwidth is very limited, because the number of regions can be controlled. And the proposed algorithm shows very simple structure because it doesn't need post processing to eliminate small regions and reduces much computation by using only structuring element of small size at simplification step of each hierarchical structure when compared with the conventional algorithm.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.2
• /
• pp.297-305
• /
• 2016

This study aims to analyze characteristics of environmental load for the construction phase of PSC beam bridge based on Life Cycle Assessment. For detail computation of environmental load, the construction materials and energy consumption are derived from the BOQ, also connecting with environmental load by Korea LCI Database Information Network. The characteristic of environmental impact was analyzed by 25 cases and cut-off ratio was 80% to 94%. The result sorted by construction materials revealed that environmental load were 53.3% for ready-mixed concrete, 9.6% for wire rod, 7.8% for rebar, 6.8% for cement, 5.5% for plywood, and 5.2% for energy. Furthermore, the result of environmental impact revealed that 45.5% for global warming, 30.4% for abiotic resources depletion, 10.5% for human toxicity, and 8.9% for photochemical oxidant creation. In the future, we can make a decision considering environmental load based on LCA at design phase.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.777-782
• /
• 2020

In this paper, we propose CNN-based HMI system using Doppler radar and voice sensor, and present hardware design and implementation results. To overcome the limitation of single sensor monitoring, the proposed HMI system combines data from two sensors to improve performance. The proposed system exhibits improved performance by 3.5% and 12% compared to a single radar and voice sensor-based classifier in noisy environment. In addition, hardware to accelerate the complex computational unit of CNN is implemented and verified on the FPGA test system. As a result of performance evaluation, the proposed HMI acceleration platform can be processed with 95% reduction in computation time compared to a single software-based design.