• Journal of Digital Convergence
• /
• v.14 no.8
• /
• pp.233-243
• /
• 2016

Due to speech recognition problems in noisy environment, Audio Visual Speech Recognition (AVSR) system, which combines speech information and visual information, has been proposed since the mid-1990s,. and lip reading have played significant role in the AVSR System. This study aims to enhance recognition rate of utterance word using only lip shape detection for efficient AVSR system. After preprocessing for lip region detection, Convolution Neural Network (CNN) techniques are applied for utterance period detection and lip shape feature vector extraction, and Hidden Markov Models (HMMs) are then used for the recognition. As a result, the utterance period detection results show 91% of success rates, which are higher performance than general threshold methods. In the lip reading recognition, while user-dependent experiment records 88.5%, user-independent experiment shows 80.2% of recognition rates, which are improved results compared to the previous studies.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.5
• /
• pp.3-8
• /
• 2000

In this paper, we studied design and implementation of a robust speech recognition system in noisy car environment. The reference pattern used in the system is DMS(Dynamic Multi-Section). Two separate acoustic models, which are selected automatically depending on the noisy car environment for the speech in a car moving at below 80km/h and over 80km/h are proposed. PLP(Perceptual Linear Predictive) of order 13 is used for the feature vector and OSDP (One-Stage Dynamic Programming) is used for decoding. The system also has the function of editing the phone-book for voice dialing. The system yields a recognition rate of 89.75% for male speakers in SI (speaker independent) mode in a car running on a cemented express way at over 80km/h with a vocabulary of 33 words. The system also yields a recognition rate of 92.29% for male speakers in SI mode in a car running on a paved express way at over 80km/h.

• Journal of Korean Society for Geospatial Information Science
• /
• v.1 no.1 s.1
• /
• pp.117-125
• /
• 1993

GSIS is a system that contains spatially referenced data that can be analyzed and converted to information for a specific set of purpose, or application. The key feature of a GSIS is the analysis of data to produce new information. The current emphasis in the transportation is to implement GSIS in conjunction with real time systems Requirements for a transportation GSIS are very different from the traditional GSIS software that has been designed for environmental and natural resource applications. A transportation GSIS may need to include the ability for franc volume, forecasting, pavement management A regional transportation planning model is actually a set of models that are used to inventory and then forecast a region's population, employment, income, housing and the demand of automobile and transit in a region. The data such as adminstration bound, m of landuse, road networks, location of schools, offices with populations are used in this paper. Many of these data are used for analyzing of traffic volume, traffic demand, time of mad construction using GSIS.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.2
• /
• pp.11-22
• /
• 2004

Conventional algorithms of separating overlapped objects are mostly based on template matching methods and thus their application domain is restricted to 2D objects and the processing time increases when the number of templates (object models) does. To solve these problems, this paper proposes a new approach of separating the occluding object from the stack of 3D objects using the relationship between surfaces without any information on the objects. The proposed algorithm considers an object as a combination of surfaces which are consisted with a set of boundary edges. Overlap of 3D objects appears as overlap of surfaces and thus as crossings of edges in 2D image. Based on this observation, the types of edge crossings are classified from which the types of overlap of 3D objects can be identified. The relationships between surfaces are represented by an attributed graph where the types of overlaps are represented by relation values. Using the relation values, the surfaces pertained to the same object are discerned and the overlapping object on the top of the stack can be separated. The performance of the proposed algorithm has been proved by the experiments using the overlapped images of 3D objects selected among the standard industrial parts.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.120-126
• /
• 2020

We present a user recognition method using human body impulse response signals. The body compositions vary from person to person depending on the portion of water, muscle, and fat. In the body communication study, the body has been interpreted circuit models using capacitance and resistances, and its characteristics are determined by the body compositions. Therefore, the individual body channel is unique and can be used for user recognition. In this paper, we applied pseudo impulse signals to the left hand and recorded received signals from the right hand. The empirical mode decomposition (EMD) method removed noise from the received signals and 10 peak values are extracted. We set the differences between peak amplitudes as a key feature to identify individuals. We collected data from 6 subjects and achieved accuracy of 97.71% for the user recognition application.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.6
• /
• pp.1294-1301
• /
• 2014

In this paper, separate probabilistic distribution models for voiced and unvoiced speech are estimated and utilized to improve speaker recognition performance. Also, in addition to the conventional mel-frequency cepstral coefficient, skewness, kurtosis, and harmonic-to-noise ratio are extracted and used for voiced speech intervals. Two kinds of scores for voiced and unvoiced speech are linearly fused with the optimal weight found by exhaustive search. The performance of the proposed speaker recognizer is compared with that of the conventional recognizer which uses mel-frequency cepstral coefficient and a unified probabilistic distribution function based on the Gassian mixture model. Experimental results show that the lower the number of Gaussian mixture, the greater the performance improvement by the proposed algorithm.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.8 no.6
• /
• pp.491-496
• /
• 2015

Cloud computing has emerged with promise to decrease the cost of server additional cost and expanding the data storage and ease for computer resource sharing and apply the new technologies. However, Cloud computing also raises many new security concerns due to the new structure of the cloud service models. Therefore, the secure user authentication is required when the user is using cloud computing. This paper, we propose the enhanced AdaBoost algorithm for access cloud security zone. The AdaBoost algorithm despite the disadvantage of not detect a face inclined at least 20, is widely used because of speed and responsibility. In the experimental results confirm that a face inclined at least 20 degrees tilted face was recognized. Using the FEI Face Database that can be used in research to obtain a result of 98% success rate of the algorithm perform. The 2% failed rate is due to eye detection error which is the people wearing glasses in the picture.

• Smart Structures and Systems
• /
• v.8 no.2
• /
• pp.173-190
• /
• 2011

As a practical and effective seismic resisting technology, the base isolation system has seen extensive applications in buildings and bridges. However, a few problems associated with conventional lead-rubber bearings have been identified after historical strong earthquakes, e.g., excessive permanent deformations of bearings and potential unseating of bridge decks. Recently the applications of shape memory alloys (SMA) have received growing interest in the area of seismic response mitigation. As a result, a variety of SMA-based base isolators have been developed. These novel isolators often lead to minimal permanent deformations due to the self-centering feature of SMA materials. However, a rational design approach is still missing because of the fact that conventional design method cannot be directly applied to these novel devices. In light of this limitation, a displacement-based design approach for highway bridges with SMA isolators is proposed in this paper. Nonlinear response spectra, derived from typical hysteretic models for SMA, are employed in the design procedure. SMA isolators and bridge piers are designed according to the prescribed performance objectives. A prototype reinforced concrete (RC) highway bridge is designed using the proposed design approach. Nonlinear dynamic analyses for different seismic intensity levels are carried out using a computer program called "OpenSees". The efficacy of the displacement-based design approach is validated by numerical simulations. Results indicate that a properly designed RC highway bridge with novel SMA isolators may achieve minor damage and minimal residual deformations under frequent and rare earthquakes. Nonlinear static analysis is also carried out to investigate the failure mechanism and the self-centering ability of the designed highway bridge.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.363-370
• /
• 2018

Ransomware detection has become a hot topic in computer security for protecting digital contents. Unfortunately, current signature-based and static detection models are often easily evadable by compress, and encryption. For overcoming the lack of these detection approach, we have proposed the dynamic ransomware detection system using data mining techniques such as RF, SVM, SL and NB algorithms. We monitor the actual behaviors of software to generate API calls flow graphs. Thereafter, data normalization and feature selection were applied to select informative features. We improved this analysis process. Finally, the data mining algorithms were used for building the detection model for judging whether the software is benign software or ransomware. We conduct our experiment using more suitable real ransomware samples. and it's results show that our proposed system can be more effective to improve the performance for ransomware detection.

• Journal of the Society of Naval Architects of Korea
• /
• v.34 no.1
• /
• pp.60-67
• /
• 1997

This paper presents the results of 3rd wind tunnel test for the wings of WIG R/C test models, 'Hanjin-1' & 'Hanjin-2'. We made 'Hanjin-1' in last May 1995 and had a success in test flight. And in order to grasp the aerodynamic characteristics of wings in ground effect, the measurements of lift and drag were carried out for the various kinds of wing. It was shown that lift and lift-drag ratio increase with decrease of the clearance, but the feature was considerably depended on the shape of wing section. In this case we select the three kind of wing. section, and then compare their characteristics especially for a stability in longitudinal motion. They are NACA6409 for 'Hanjin-1' and the two kinds of DHMTU for ekranoplans of Russia. Experimental results show that the pitching moments of DHMTU wing sections are smaller than NACA6409.