• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.2A
• /
• pp.113-118
• /
• 2012

In this paper, we propose the removal of search point using motion vector correlation and distance between reference frames in H.264/AVC. We remove the search points in full search method and predictive motion vectors in enhanced predictive zonal search method. Since the probability that the reference frame far from the current frame is selected as the best reference frame is decreased, we apply the weighted average based on distance between the current and reference frame to determine the fianl search range. In general, the size of search range is smaller than initial search range. We reduce motion estimation time using the final search range in full search method. Also, the refinement process is adaptively applied to each reference frame. The proposed methods reduce the computational throughput of full search method by 57.13% and of enhanced predictive zonal search by 14.71% without visible performance degradation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.6
• /
• pp.90-97
• /
• 2003

This paper proposes a speech recognition based on HMM(Hidden Markov Model) using FSVQ(First Section Vector Quantization) and fuzzy concept. In the proposed paper, we generate codebook of First Section, and then obtain multi-observation sequences by order of large propabilistic values based on fuzzy rule from the codebook of the first section. Thereafter, this observation sequences of first section from codebooks is trained and in case of recognition, a word that has the most highest probability of first section is selected as a recognized word by same concept. Train station names are selected as the target recognition vocabulary and LPC cepstrum coefficients are used as the feature parameters. Besides the speech recognition experiments of proposed method, we experiment the other methods under same conditions and data. Through the experiment results, it is proved that the proposed method based on HMM using FSVQ and fuzzy concept is superior to tile others in recognition rate.

• Journal of KIISE:Information Networking
• /
• v.32 no.1
• /
• pp.110-122
• /
• 2005

Bluetooth has been reputed as a wireless networking technology supplying ad-hoc networks between digital devices. In particular, bluetooth scatternet is a most essential part for dynamic ad-hoc networks. But past researches on bluetooth scatternet has hardly treated dynamic scatternet environment. In this paper, we proposed a scatternet reformation algorithm for the case that some nodes escape from the scatternet. The proposed algorithm is a general algorithm which can be applied to many types of bluetooth scatternet regardless of the topology. The proposed algorithm has short reformation time delay because the process has only page process (not including inquiry process ). The algorithm is operated based on Recovery Node Vector which is composed of Recovery Master and Recovery Slave. In this paper, we performed the real hardware experiments for evaluating the performance of the proposed algorithm. In that experiments, we measured the reformation time and reformation probability. In comparison with the case including inquiry process, the proposed algorithm had the improvement in reformation time delay and we obtained high success rate over 97%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.6
• /
• pp.75-82
• /
• 2005

The robust feature vector selection method for the multiple frontal face detection is proposed in this paper. The proposed feature vector for the training and classification are integrated by means, amplitude projections, and its 1D Harr wavelet of the input image. And the statistical modeling is performed both for face and nonface classes. Finally, the estimated probability density functions (PDFs) are applied for the detection of multiple frontal faces in the still image. The proposed method can handle multiple faces, partially occluded faces, and slightly posed-angle faces. And also the proposed method is very effective for low quality face images. Experimental results show that detection rate of the propose method is $98.3\%$ with three false detections on the testing data, SET3 which have 227 faces in 80 images.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.4
• /
• pp.701-715
• /
• 2018

A reliability based design approach of the tunnel reinforcement with umbrella arch method was considered to better represent the uncertainties of the weak rock properties around the tunnel. For this, a machine learning approach called an Adaptive Support Vector Machine (ASVM) together with the limit equilibrium method were introduced to minimize the iteration numbers during the classification training of the tunnel stability. The proposed method was compared with the results of typical Monte Carlo simulations. It was concluded that the ASVM was very efficient and accurate to calculate the probability of failure having auxiliary umbrella arches and uncertain material properties of the tunnel. Future work will be concentrated on the refinement of the fast adaptation of the SVM classification so that the minimum number of numerical analyses can be used where the limit solution is not available.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.9
• /
• pp.765-774
• /
• 2013

In this paper, we present a cooperative compressed spectrum sensing scheme for correlated signals in decentralized wideband cognitive radio networks. Compressed sensing is a signal processing technique that can recover signals which are sampled below the Nyquist rate with high probability, and can solve the necessity of high-speed analog-to-digital converter problem for wideband spectrum sensing. In compressed sensing, one of the main issues is to design recovery algorithms which accurately recover original signals from compressed signals. In this paper, in order to achieve high recovery performance, we consider the multiple measurement vector model which has a sequence of compressed signals, and propose a cooperative sparse Bayesian recovery algorithm which models the temporal correlation of the input signals.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.241-250
• /
• 2005

New product development (NPD) is defined as the transformation of a market opportunity and a set of assumptions about product technology into a product available for sale. Managers charged with project selection decisions in the NPD process, such as go/no-go choices and specific resource allocation decisions, are faced with a complicated problem. Therefore, the ability to develop new successful products has identifies as a major determinant in sustaining a firm's competitive advantage. The purpose of this study is to develop a new evaluation model for NPD project selection in the high -tech industry using support vector machines (SYM). The evaluation model is developed through two phases. In the first phase, binary (go/no-go) classification prediction model, i.e. SVM for high-tech NPD project selection is developed. In the second phase. using the predicted output value of SVM, feasibility grade is calculated for the final NPD project decision making. In this study, the feasibility grades are also divided as three level grades. We assume that the frequency of NPD project cases is symmetrically determined according to the feasibility grades and misclassification errors are partially minimized by the multiple grades. However, the horizon of grade level can be changed by firms' NPD strategy. Our proposed feasibility grade method is more reasonable in NPD decision problems by considering particularly risk factor of NPD in viewpoints of future NPD success probability. In our empirical study using Korean NPD cases, the SVM significantly outperformed ANN and logistic regression as benchmark models in hit ratio. And the feasibility grades generated from the predicted output value of SVM showed that they can offer a useful guideline for NPD project selection.

• Journal of Korea Multimedia Society
• /
• v.12 no.8
• /
• pp.1155-1163
• /
• 2009

This paper proposes an automatic facial expression generation system of vector graphic character using gaussian process model. Proposed method extracts the main feature vectors from twenty-six facial data of character redefined based on Russell's internal emotion state. Also by using new gaussian process model, SGPLVM, we find low-dimensional feature data from extracted high-dimensional feature vectors, and learn probability distribution function (PDF). All parameters of PDF are estimated by maximization the likelihood of learned expression data, and these are used to select wanted facial expressions on two-dimensional space in real time. As a result of simulation, we confirm that proposed facial expression generation tool is working in the small facial expression datasets and can generate various facial expressions without prior knowledge about relation between facial expression and emotion.

• ETRI Journal
• /
• v.35 no.1
• /
• pp.100-108
• /
• 2013

In this paper, a feature extraction (FE) method is proposed that is comparable to the traditional FE methods used in automatic speech recognition systems. Unlike the conventional spectral-based FE methods, the proposed method evaluates the similarities between an embedded speech signal and a set of predefined speech attractor models in the reconstructed phase space (RPS) domain. In the first step, a set of Gaussian mixture models is trained to represent the speech attractors in the RPS. Next, for a new input speech frame, a posterior-probability-based feature vector is evaluated, which represents the similarity between the embedded frame and the learned speech attractors. We conduct experiments for a speech recognition task utilizing a toolkit based on hidden Markov models, over FARSDAT, a well-known Persian speech corpus. Through the proposed FE method, we gain 3.11% absolute phoneme error rate improvement in comparison to the baseline system, which exploits the mel-frequency cepstral coefficient FE method.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.22 no.6
• /
• pp.874-887
• /
• 1998

A 2-frame PTV (particle tracking velocimetry) system using the concept of match probability between two consequent image frames has been developed to obtain instantaneous velocity fields. The overall 2-frame PTV system including image pre-processing, tracking algorithm and post-processing routine was implemented to apply to real flows. The developed 2-frame PTV system has several advantages such as high recovery ratio of velocity vectors, low error ratio and small computational time compared with the conventional 4-frame PTV and the FFT-based cross-correlation PIV technique. The 2-frame PTV system was applied to a turbulent channel flow over a rectangular block to check its reliability and usefulness. Total 96 sequential image frames have been captured and processed to get both mean and fluctuating velocity vector fields over the recirculating region. The mean velocity and turbulent intensity profiles were well agreed with hte LDV measurements in the separated region behind the block. Time-averaged reattachment length is about 6.3 times of the block height.