• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6D
• /
• pp.951-960
• /
• 2006

Structural pavement analysis considering lateral loads of moving vehicle was carried out in order to simulate passing vehicle loads under various interface conditions. To verify of existing multi-layer elastic analysis of layer interface effect parameters, this study compared outputs by using ABAQUS, a three dimensional finite element program and KENLAYER, multi-layer elastic analysis as vertical load was applied to the surface of asphalt pavements. Pavement performance depending on interface conditions was quantitatively evaluated and fundamental study of layer interface effect parameters was performed in this study. As results of the study, if only vertical loads of moving vehicle is applied, subdivision of either fully bonded or fully unbonded is enough to indicate interface effect parameters. On the other hand, when lateral loads are applied with vertical loads, pavement behavior and performance are greatly changed with respect to layer interface conditions. The thinner thickness of the asphalt layer is and the smaller elastic moduli of the asphalt layer is, the more pavement behavior is influenced by interface conditions. In addition, regression analysis equation analytically computing tensile strain which was considered thicknesses and elastic moduli of the asphalt layer and layer interface effect parameters at the bottom of the asphalt layer was presented using database from numerical analyses on national pavement model sections.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.175-178
• /
• 2008

While read operation on flash memory is fast and doesn't have any constraints, flash memory can not be overwritten on updating data, new data are updated in new area. If data are frequently updated, garbage collection, which is achieved by erasing blocks, should be performed to reclaim new area. Hence, because the number of erase operations is limited due to characteristics of flash memory, every block should be evenly written and erased. However, if data with access locality are processed by cost benefit algorithm with separation of hot block and cold block, though the performance of processing is high, wear-leveling is not even. In this paper, we propose CB-MG (Cost Benefit between Multi Group) algorithm in which hot data are allocated in one group and cold data in another group, and in which role of hot group and cold group is exchanged every period. Experimental results show that performance and wear-leveling of CB-MG provide better results than those of CB-S.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.11-19
• /
• 2014

The natural user interface/experience (NUI/NUX) is used for the natural motion interface without using device or tool such as mice, keyboards, pens and markers. Up to now, typical motion recognition methods used markers to receive coordinate input values of each marker as relative data and to store each coordinate value into the database. But, to recognize accurate motion, more markers are needed and much time is taken in attaching makers and processing the data. Also, as NUI/NUX framework being developed except for the most important intuition, problems for use arise and are forced for users to learn many NUI/NUX framework usages. To compensate for this problem in this paper, we didn't use markers and implemented for anyone to handle it. Also, we designed multi-modal NUI/NUX framework controlling voice, body motion, and facial expression simultaneously, and proposed a new algorithm of mouse operation by recognizing intuitive hand gesture and mapping it on the monitor. We implement it for user to handle the "hand mouse" operation easily and intuitively.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.4
• /
• pp.143-150
• /
• 2013

The purpose of this study is to suggest the methodology to develop variable-scale network model, which is able to induce large-scale road network in detailed level corresponding to small-scale linear objects with various abstraction in higher level. For this purpose, the definition of terms, the benefits and the specific procedures related with a variable-scale model were examined. Second, representation level and the components of layer to design the variable-scale map were presented. In addition, rule-based data generating method and indexing structure for higher LoD were defined. Finally, the implementation and verification of the model were performed to road network in study area (Jeju -do) so that the proposed algorithm can be practical. That is, generated variable scale road network were saved and managed in spatial database (Oracle Spatial) and performance analysis were carried out for the effectiveness and feasibility of the model.

• Journal of The Korean Association of Information Education
• /
• v.7 no.1
• /
• pp.113-129
• /
• 2003

The performance assessment is being importantly recognized and enforced in the education evaluation recently. It is not able to analyze learners synthetically because learners are assessed separately in every subjects and the other activities. On the basis of this problem, we designed and implemented the multi-dimensional processing tool. In this tool, the evaluation results of one subject area have an influence on the other related subject areas. In addition, this system helps teachers to establish and process performance assessment plan by providing all subjects database. And all of the information is processed as a whole and can be used in the counseling and school record. This system is based upon windows and can be extend to web based system later. We expect the performance assessment task can be simplified by using this system and students' ability can be assessed by various methods. This system will contribute to ensure the confidence of public education.

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.821-827
• /
• 2018

Affective computing has gained increasing interest in the recent years with the development of potential applications in Human computer interaction (HCI) and healthcare. Although momentous research has been done on human emotion recognition, however, in comparison to speech and facial expression less attention has been paid to physiological signals. In this paper, Electroencephalogram (EEG) signals from different brain regions were investigated using modified wavelet energy features. For minimization of redundancy and maximization of relevancy among features, mRMR algorithm was deployed significantly. EEG recordings of a publically available "DEAP" database have been used to classify four classes of emotions with Multi class Support Vector Machine. The proposed approach shows significant performance compared to existing algorithms.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.57-63
• /
• 2009

The rapid growth of computer-based image database, necessity of a system that can manage an image information is increasing. This paper presents a region-based image retrieval method using the combination of color(autocorrelogram), texture(CWT moments) and shape(Hu invariant moments) features. As a color feature, a color autocorrelogram is chosen by extracting from the hue and saturation components of a color image(HSV). As a texture, shape and position feature are extracted from the value component. For efficient similarity confutation, the extracted features(color autocorrelogram, Hu invariant moments, and CWT moments) are combined and then precision and recall are measured. Experiment results for Corel and VisTex DBs show that the proposed image retrieval algorithm has 94.8% Precision, 90.7% recall and can successfully apply to image retrieval system.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.592-599
• /
• 2020

This paper proposes a Convolutional Recurrent Neural Net (CRNN) structure that can simultaneously reflect both static and dynamic characteristics of seismic waveforms for various earthquake events classification. Addressing various earthquake events, including not only micro-earthquakes and artificial-earthquakes but also macro-earthquakes, requires both effective feature extraction and a classifier that can discriminate seismic waveform under noisy environment. First, we extract the static characteristics of seismic waveform through an attention-based convolution layer. Then, the extracted feature-map is sequentially injected as input to a multi-input single-output Long Short-Term Memory (LSTM) network structure to extract the dynamic characteristic for various seismic event classifications. Subsequently, we perform earthquake events classification through two fully connected layers and softmax function. Representative experimental results using domestic and foreign earthquake database show that the proposed model provides an effective structure for various earthquake events classification.

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2015.05a
• /
• pp.226-240
• /
• 2015

The purpose of this study is to establish a proper evaluation system for R&D performance by analyzing relationships between quantitative results of science& technology and national wealth. We analyzed 193,474 research papers in multi-disciplinary fields from SCOPUS database and explored co-relations between HCP production by section and national wealth. This research found a significant relationship between the number of HCP papers and GDP & GDP per capita by nation. Also, results from this study indicate that top 30 to 40 percent of researches should be reflected in the performance evaluation while these numbers could be flexible in accordance with the direction of national policy. In terms of future research, this study provides basis for designing more effective R&D performance evaluation systems.