• ETRI Journal
• /
• v.39 no.4
• /
• pp.443-454
• /
• 2017

In this paper, we propose a fine-grained mobile application clustering model using retrofitted document embedding. To automatically determine the clusters and their numbers with no predefined categories, the proposed model initializes the clusters based on title keywords and then merges similar clusters. For improved clustering performance, the proposed model distinguishes between an accurate clustering step with titles and an expansive clustering step with descriptions. During the accurate clustering step, an automatically tagged set is constructed as a result. This set is utilized to learn a high-performance document vector. During the expansive clustering step, more applications are then classified using this document vector. Experimental results showed that the purity of the proposed model increased by 0.19, and the entropy decreased by 1.18, compared with the K-means algorithm. In addition, the mean average precision improved by more than 0.09 in a comparison with a support vector machine classifier.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.157-168
• /
• 2014

We propose an novel artificial visual attention model that is capable of automatic detection and segmentation of saliency region on natural images in this paper. The proposed model is based on human visual perceptions in biological vision and contains there are main contributions. Firstly, we propose a novel framework of artificial visual attention model based on the opponent process theory using intensity and color features, and an entropy filter is designed to perceive salient regions considering the amount of information from intensity and color feature channels. The entropy filter is able to detect and segment salient regions in high segmentation accuracy and precision. Lastly, we also propose an adaptive combination method to generate a final saliency map. This method estimates scores about intensity and color conspicuous maps from each perception model and combines the conspicuous maps with weight derived from scores. In evaluation of saliency map by ROC analysis, the AUC of proposed model as 0.9256 approximately improved 15% whereas the AUC of previous state-of-the-art models as 0.7824. And in evaluation of salient region segmentation, the F-beta of proposed model as 0.7325 approximately improved 22% whereas the F-beta of previous state-of-the-art models.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.31-43
• /
• 2022

Traditional video compression has developed so far based on hybrid compression methods through motion prediction, residual coding, and quantization. With the rapid development of technology through artificial neural networks in recent years, research on image compression and video compression based on artificial neural networks is also progressing rapidly, showing competitiveness compared to the performance of traditional video compression codecs. In this paper, a new method capable of improving the performance of such an artificial neural network-based video compression model is presented. Basically, we take the rate-distortion optimization method using the auto-encoder and entropy model adopted by the existing learned video compression model and shifts some components of the latent information that are difficult for entropy model to estimate when transmitting compressed latent representation to the decoder side from the encoder side, and finally compensates the distortion of lost information. In this way, the existing neural network based video compression framework, MFVC (Motion Free Video Compression) is improved and the BDBR (Bjøntegaard Delta-Rate) calculated based on H.264 is nearly twice the amount of bits (-27%) of MFVC (-14%). The proposed method has the advantage of being widely applicable to neural network based image or video compression technologies, not only to MFVC, but also to models using latent information and entropy model.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.8
• /
• pp.3-8
• /
• 1999

Previous variable vocabulary speech recognition systems with context-independent acoustic modeling, could not represent the effect of neighboring phonemes. To solve this problem, we use allophone-based context-dependent acoustic model. This paper describes the method to improve acoustic model of the system effectively. Acoustic model is improved by using allophone clustering technique that uses entropy as a similarity measure and the optimal allophone model is generated by changing the number of allophones. We evaluate performance of the improved system by using Phonetically Optimized Words(POW) DB and PC commands(PC) DB. As a result, the allophone model composed of six hundreds allophones improved the recognition rate by 13% from the original context independent model m POW test DB.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.520-529
• /
• 2007

In this paper, we study the characteristics of parameters which are related to performance of MCTF which is a key technique for wavelet-based scalable video coding, and propose an improved MCTF method. The proposed MCTF method adopts the motion estimation of which motion vector field is distributed more uniformly using variable block sizes. By using the proposed method, the decomposition performance of temporal filter is improved, and the energy in high-frequency frames is reduced. It can help the entropy coder to generate lower bitrate. From simulation results, we verify the decomposed energy on high-frequency frame using the proposed method is reduced by 25.86% at the most in terms of variance of the high-frequency frame.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3121-3143
• /
• 2019

Segmentation plays an important role in the field of image processing and computer vision. Intuitionistic fuzzy C-means (IFCM) clustering algorithm emerged as an effective technique for image segmentation in recent years. However, standard fuzzy C-means (FCM) and IFCM algorithms are sensitive to noise and initial cluster centers, and they ignore the spatial relationship of pixels. In view of these shortcomings, an improved algorithm based on IFCM is proposed in this paper. Firstly, we propose a modified non-membership function to generate intuitionistic fuzzy set and a method of determining initial clustering centers based on grayscale features, they highlight the effect of uncertainty in intuitionistic fuzzy set and improve the robustness to noise. Secondly, an improved nonlinear kernel function is proposed to map data into kernel space to measure the distance between data and the cluster centers more accurately. Thirdly, the local spatial-gray information measure is introduced, which considers membership degree, gray features and spatial position information at the same time. Finally, we propose a new measure of intuitionistic fuzzy entropy, it takes into account fuzziness and intuition of intuitionistic fuzzy set. The experimental results show that compared with other IFCM based algorithms, the proposed algorithm has better segmentation and clustering performance.

• Journal of Broadcast Engineering
• /
• v.12 no.4
• /
• pp.377-380
• /
• 2007

In this paper, an improved CABAC is proposed for the lossless compression in H.264/AVC. CABAC in the lossless coding is not as efficient as that in the lossy compression since it was developed for lossy coding. CABAC for the lossless coding in H.26과/AVC Advanced 4:4:4 Profile is applied without the change of the conventional binarization method. Thus, a binarization method considering the statistical characteristic of residual signals is proposed for the lossless coding in 0.264/AVC Advanced 4:4:4 Profile. The experimental results show that the proposed method obtains approximately 3.4% bitrate reduction in comparison to that of the conventional lossless coding.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.3
• /
• pp.57-63
• /
• 2011

The internet is currently becoming popularized and generalized in our daily life. Recently, a lot of hacking tools have appeared on the internet. And damage size and seriousness the measurement is impossible. The password security protects oneself and information is the tool which is essential for from the internet, if this emphasizes no matter how, does not go to extremes. If applies a encryption, a 7 character password is sufficient, so long as attackers don't pick easily guessed values. In this paper, entering password using the virtual keyboard, I propose a new and improved one time password algorithm using information a part of ID and final approval time.

• Smart Structures and Systems
• /
• v.31 no.2
• /
• pp.155-169
• /
• 2023

The quasi-static component of the moving vehicle-induced dynamic response is promising in damage detection as it is sensitive to bridge damage but insensitive to environmental changes. However, accurate extraction of quasi-static component from the dynamic response is challenging especially when the vehicle velocity is high. This paper proposes an adaptive quasi-static component extraction method based on the modified variational mode decomposition (VMD) algorithm. Firstly the analytical solutions of the frequency components caused by road surface roughness, high-frequency dynamic components controlled by bridge natural frequency and quasi-static components in the vehicle-induced bridge response are derived. Then a modified VMD algorithm based on particle swarm algorithm (PSO) and mutual information entropy (MIE) criterion is proposed to adaptively extract the quasi-static components from the vehicle-induced bridge dynamic response. Numerical simulations and real bridge tests are conducted to demonstrate the feasibility of the proposed extraction method. The results indicate that the improved VMD algorithm could extract the quasi-static component of the vehicle-induced bridge dynamic response with high accuracy in the presence of the road surface roughness and measurement noise.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.549-558
• /
• 2020

In this paper, the method is discussed such that the robustness of automatic initiated narrowband target tracking is improved in passive sonar. In the case of automatic tracking initiation as target in passive sonar, due to a number of clutter, the clutter is initiated as target and tracked which prohibits the operation capability. The associated probability and information entropy of measurements, extracted from detection data, is calculated to keep going on automatic target initiation and tracking of true target, but reduce the automatic initiation and tracking of clutter. If the association probability and information entropy of the extracted measurements is satisfied for the predefined conditions, the procedure of automatic initiation begins. Using sea-trial data, simulations are executed and the results from the proposed method indicate that it keeps the automatic target initiation and tracking of true target and suppresses the automatic target initiation and tracking of clutters in contrary to the conventional method.