• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.10
• /
• pp.2121-2128
• /
• 2012

This paper proposed the real time face area detection using Wavelet transform and the strong detection algorithm that satisfies the efficiency of computation and detection performance at the same time was proposed. The detected face image recognizes the face by configuring the low-dimensional face symbol through the principal component analysis. The proposed method is well suited for real-time system construction because it doesn't require a lot of computation compared to the existing geometric feature-based method or appearance-based method and it can maintain high recognition rate using the minimum amount of information. In addition, in order to reduce the wrong recognition or recognition error occurred during face recognition, the input symbol of Hidden Markov Model is used by configuring the feature values projected to the unique space as a certain symbol through clustering algorithm. By doing so, any input face will be recognized as a face model that has the highest probability. As a result of experiment, when comparing the existing method Euclidean and Mahananobis, the proposed method showed superior recognition performance in incorrect matching or matching error.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.4
• /
• pp.11-17
• /
• 2017

Organizations are experiencing an ever-growing concern of how to prevent confidential information leakage from internal employees. Those who have authorized access to organizational data are placed in a position of power that could well be abused and could cause significant damage to an organization. In this paper, we investigate the task of detecting such insider through a method of modeling a user's normal behavior in order to detect anomalies in that behavior which may be indicative of an data leakage. We make use of Hidden Markov Models to learn what constitutes normal behavior, and then use them to detect significant deviations from that behavior. Experiments have been made to determine the optimal HMM parameters and our result shows detection capability of 20% false positive and 80% detection rate.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.50-59
• /
• 1997

In this paper, we implement an automatic speech segmentation and labeling system which marks phone boundaries automatically for constructing the Korean speech database. We specify and implement the system based on conventional speech segmentation and labeling techniques, and also develop the graphic user interface(GUI) on Hangul $Motif^{TM}$ environment for the users to examine the automatic alignment boundaries and to refine them easily. The developed system is applied to 16kHz sampled speech, and the labeling unit is composed of 46 phoneme-like units(PLUs) and silence. The system uses both of the phonetic and orthographic transcription as input methods of linguistic information. For pattern-matching method, hidden Markov models(HMM) is employed. Each phoneme model is trained using the manually segmented 445 phonetically balanced word (PBW) database. In order to evaluate the performance of the system, we test it using another database consisting of sentence-type speech. According to our experiment, 74.7% of phoneme boundaries are within 20ms of the true boundary and 92.8% are within 40ms.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1
• /
• pp.14-23
• /
• 1994

In this paper, speech units appropriate for recognition of Korean language have been studied. For better speech recognition, co-articulatory effects within an utterance should be considered in the selection of a recognition unit. One way to model such effects is to use larger units of speech. It has been found that diphone is a good recognition unit because it can model transitional legions explicitly. When diphone is used, stationary phoneme models may be inserted between diphones. Computer simulation for isolated word recognition was done with 7 word database spoken by seven male speakers. Best performance was obtained when transition regions between phonemes were modeled by two-state HMM's and stationary phoneme regions by one-state HMM's excluding /b/, /d/, and /g/. By merging rarely occurring diphone units, the recognition rate was increased from $93.98\%$ to $96.29\%$. In addition, a local interpolation technique was used to smooth a poorly-modeled HMM with a well-trained HMM. With this technique we could get the recognition rate of $97.22\%$ after merging some diphone units.

• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.453-470
• /
• 2013

In this paper, we consider a Bayesian analysis of the dose-effect relationship of cadmium to evaluate a benchmark dose(BMD). For this purpose, two dose-response curves commonly used in the toxicity study are fitted based on Bayesian methods to the data collected from the scientific literature on cadmium toxicity. Specifically, Bayesian meta-analysis and hierarchical modeling build an overall dose-effect relationship that use a piecewise linear model and Hill model, where the inter-study heterogeneity and inter-individual variability of dose and effect such as gender, age and ethnicity are accounted. Estimation of the unknown parameters is made by using a Markov chain Monte Carlo algorithm based user-friendly software WinBUGS. Benchmark dose estimates are evaluated for various cut-offs and compared with different tested subpopulations with with gender, age and ethnicity based on these two Bayesian hierarchical models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.2
• /
• pp.683-701
• /
• 2012

IEEE 802.11 standard has achieved huge success in the past decade and is still under development to provide higher physical data rate and better quality of service (QoS). An important problem for the development and optimization of IEEE 802.11 networks is the modeling of the MAC layer channel access protocol. Although there are already many theoretic analysis for the 802.11 MAC protocol in the literature, most of the models focus on the saturated traffic and assume infinite buffer at the MAC layer. In this paper we develop a unified analytical model for IEEE 802.11 MAC protocol in ad hoc networks. The impacts of channel access parameters, traffic rate and buffer size at the MAC layer are modeled with the assistance of a generalized Markov chain and an M/G/1/K queue model. The performance of throughput, packet delivery delay and dropping probability can be achieved. Extensive simulations show the analytical model is highly accurate. From the analytical model it is shown that for practical buffer configuration (e.g. buffer size larger than one), we can maximize the total throughput and reduce the packet blocking probability (due to limited buffer size) and the average queuing delay to zero by effectively controlling the offered load. The average MAC layer service delay as well as its standard deviation, is also much lower than that in saturated conditions and has an upper bound. It is also observed that the optimal load is very close to the maximum achievable throughput regardless of the number of stations or buffer size. Moreover, the model is scalable for performance analysis of 802.11e in unsaturated conditions and 802.11 ad hoc networks with heterogenous traffic flows.

• 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.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.3
• /
• pp.170-175
• /
• 2009

In this paper, we propose real time automatic speaker verification (ASV) system to protect personal information on personal digital assistant (PDA) device. Recently, the capacity of PDA has extended and been popular, especially for mobile environment such as mobile commerce (M-commerce). However, there still exist lots of difficulties for practical application of ASV utility to PDA device because it requires too much computational complexity. To solve this problem, we apply the method to relieve the computational burden by performing the preprocessing such as spectral subtraction and speech detection during the speech utterance. Also by applying the hidden Markov model (HMM) optimal state alignment and the sequential probability ratio test (SPRT), we can get much faster processing results. The whole system implementation is simple and compact enough to fit well with PDA device's limited memory and low CPU speed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.2
• /
• pp.213-218
• /
• 2013

One of the most popular approaches to parameter adaptation in hidden Markov model (HMM) based systems is the maximum likelihood linear regression (MLLR) technique. In our previous study, we proposed factored MLLR (FMLLR) where each MLLR parameter is defined as a function of a control vector. We presented a method to train the FMLLR parameters based on a general framework of the expectation-maximization (EM) algorithm. Using the proposed algorithm, supplementary information which cannot be included in the models is effectively reflected in the adaptation process. In this paper, we apply the FMLLR algorithm to a pitch sequence as well as spectrum parameters. In a series of experiments on artificial generation of expressive speech, we evaluate the performance of the FMLLR technique and also compare with other approaches to parameter adaptation in HMM-based speech synthesis.

• Geophysics and Geophysical Exploration
• /
• v.5 no.4
• /
• pp.262-271
• /
• 2002

This study presents a practical procedure for the Bayesian inversion of geophysical data. We have applied geostatistical techniques for the acquisition of prior model information, then the Markov Chain Monte Carlo (MCMC) method was adopted to infer the characteristics of the marginal distributions of model parameters. For the Bayesian inversion of dipole-dipole array resistivity data, we have used the indicator kriging and simulation techniques to generate cumulative density functions from Schlumberger array resistivity data and well logging data, and obtained prior information by cokriging and simulations from covariogram models. The indicator approach makes it possible to incorporate non-parametric information into the probabilistic density function. We have also adopted the MCMC approach, based on Gibbs sampling, to examine the characteristics of a posteriori probability density function and the marginal distribution of each parameter.