• Journal of KIISE:Software and Applications
• /
• v.35 no.3
• /
• pp.179-188
• /
• 2008

An important issue in multiagent reinforcement learning is how an agent should team its optimal policy through trial-and-error interactions in a dynamic environment where there exist other agents able to influence its own performance. Most previous works for multiagent reinforcement teaming tend to apply single-agent reinforcement learning techniques without any extensions or are based upon some unrealistic assumptions even though they build and use explicit models of other agents. In this paper, basic concepts that constitute the common foundation of multiagent reinforcement learning techniques are first formulated, and then, based on these concepts, previous works are compared in terms of characteristics and limitations. After that, a policy model of the opponent agent and a new multiagent reinforcement learning method using this model are introduced. Unlike previous works, the proposed multiagent reinforcement learning method utilize a policy model instead of the Q function model of the opponent agent. Moreover, this learning method can improve learning efficiency by using a simpler one than other richer but time-consuming policy models such as Finite State Machines(FSM) and Markov chains. In this paper. the Cat and Mouse game is introduced as an adversarial multiagent environment. And effectiveness of the proposed multiagent reinforcement learning method is analyzed through experiments using this game as testbed.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.167-179
• /
• 2002

In this paper, we propose a new acoustic model for characterizing segmental features and an algorithm based upon a general framework of hidden Markov models (HMMs) in order to compensate the weakness of HMM assumptions. The segmental features are represented as a trajectory of observed vector sequences by a polynomial regression function because the single frame feature cannot represent the temporal dynamics of speech signals effectively. To apply the segmental features to pattern classification, we adopted segmental HMM(SHMM) which is known as the effective method to represent the trend of speech signals. SHMM separates observation probability of the given state into extra- and intra-segmental variations that show the long-term and short-term variabilities, respectively. To consider the segmental characteristics in acoustic model, we present segmental-feature HMM(SFHMM) by modifying the SHMM. The SFHMM therefore represents the external- and internal-variation as the observation probability of the trajectory in a given state and trajectory estimation error for the given segment, respectively. We conducted several experiments on the TIMIT database to establish the effectiveness of the proposed method and the characteristics of the segmental features. From the experimental results, we conclude that the proposed method is valuable, if its number of parameters is greater than that of conventional HMM, in the flexible and informative feature representation and the performance improvement.

• Journal of Communications and Networks
• /
• v.14 no.4
• /
• pp.374-384
• /
• 2012

Utilizing artificial noise (AN) is a good means to guarantee security against eavesdropping in a multi-inputmulti-output system, where the AN is designed to lie in the null space of the legitimate receiver's channel direction information (CDI). However, imperfect CDI will lead to noise leakage at the legitimate receiver and cause significant loss in the achievable secrecy rate. In this paper, we consider a delayed feedback system, and investigate the impact of delayed CDI on security by using a transmit beamforming and AN scheme. By exploiting the Gauss-Markov fading spectrum to model the feedback delay, we derive a closed-form expression of the upper bound on the secrecy rate loss, where $N_t$ = 2. For a moderate number of antennas where $N_t$ > 2, two special cases, based on the first-order statistics of the noise leakage and large number theory, are explored to approximate the respective upper bounds. In addition, to maintain a constant signal-to-interferenceplus-noise ratio degradation, we analyze the corresponding delay constraint. Furthermore, based on the obtained closed-form expression of the lower bound on the achievable secrecy rate, we investigate an optimal power allocation strategy between the information signal and the AN. The analytical and numerical results obtained based on first-order statistics can be regarded as a good approximation of the capacity that can be achieved at the legitimate receiver with a certain number of antennas, $N_t$. In addition, for a given delay, we show that optimal power allocation is not sensitive to the number of antennas in a high signal-to-noise ratio regime. The simulation results further indicate that the achievable secrecy rate with optimal power allocation can be improved significantly as compared to that with fixed power allocation. In addition, as the delay increases, the ratio of power allocated to the AN should be decreased to reduce the secrecy rate degradation.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1851-1856
• /
• 2006

영화는 대표적인 경험재로 가치판단이 주관적이고 제품 수명주기가 매우 짧아 예측의 불확실성이 높기 때문에 이를 정량적인 방법으로 모형화하기는 쉽지 않다. 이러한 한계점에도 불구하고 한 영화의 상업적 성공을 예측하는 것은 영화 제작자나 배급사, 극장 등 모든 주체에게 수익과 직결되는 중요한 문제이기 때문에 지금까지 다양한 통계 모형이 제시되었다. 그러나 이들 모형의 대부분은 영화흥행에는 영향을 미치나 측정할 수 없는 효과를 반영하지 못한다거나, 추정 모수의 효과가 모든 영화에 대해서 같다는 동일성 가정으로 인해 영화간 이질성을 고려하지 못하고 있다. 따라서, 본 연구에서는 추정 모수의 사전분포를 모호사전분포로 정의함으로써 변수들의 불확실성을 반영할 수 있고, 영화간 이질성을 고려할 수 있는 베이지안 선택 모형을 제안하였다. 모수의 사후분포는 마코프체인 몬테카를로 기법인 깁스 샘플러를 이용하여 추정하였다. 또한, 감독, 배우, 장르 등의 영화 별 속성 변수뿐만 아니라, 입소문에 의한 영화관람 결정 등의 구전효과와 경쟁영화의 개봉으로 인한 효과를 반영할 수 있는 변수를 추가하여 모형의 정확성을 높였다. 2005년과 2006년 상반기에 상영된 영화를 바탕으로 모형을 구축하고 인공신경망 모형과 비교한 결과, 전체적인 예측 정확도에서는 인공신경망 모형과 비슷한 결과를 보이나 상업적으로 성공한 영화를 예측하는 데에는 베이지안 선택모형이 보다 더 우수한 것으로 나타났다. 또한, 개봉 주의 경쟁심화 정도 및 개봉 첫 주의 스크린 수 등이 영화 흥행에 가장 중요한 변수로 나타났으며, 영화 개봉 전 그 영화에 대한 기대치가 높을수록 흥행 성적 또한 좋음을 알 수 있었다. 배우의 힘 및 계절성, 영화 평점 등은 이질성을 고려하지 않은 전체수준에서는 통계적으로 유의하지 않은 것으로 나타났으나, 그룹 간 이질성을 반영한 모형에서는 어느 정도 흥행한 영화를 만들기 위해서는 고려되어야 할 요소로 나타났다.렇지 않을 경우 적절한 벤치마킹 대상을 도출할 때까지 추가적인 분석과정을 반복한다. 제안한 방법을 통하여 조직은 기술적 생산 가능성 외에도 다양한 조직 운영 관점에서 적절한 벤치마킹 대상을 선정할 수 있으며, 이에 따른 목표를 수립할 수 있을 것으로 기대한다. 또한 더 나아가 global efficiency 관점에서 효율적 조직이 되기 위하여 단계적인 벤치마킹 대상 선정과 이에 따른 목표를 수립하는데도 유용하리라 판단된다.$1.20{\pm}0.37L$, 72시간에 $1.33{\pm}0.33L$로 유의한 차이를 보였으므로(F=6.153, P=0.004), 술 후 폐환기능 회복에 효과가 있다. 4) 실험군과 대조군의 수술 후 노력성 폐활량은 수술 후 72시간에서 실험군이 $1.90{\pm}0.61L$, 대조군이 $1.51{\pm}0.38L$로 유의한 차이를 보였다(t=2.620, P=0.013). 5) 실험군과 대조군의 수술 후 일초 노력성 호기량은 수술 후 24시간에서 $1.33{\pm}0.56L,\;1.00{\ge}0.28L$로 유의한 차이를 보였고(t=2.530, P=0.017), 술 후 72시간에서 $1.72{\pm}0.65L,\;1.33{\pm}0.3L$로 유의한 차이를 보였다(t=2.540, P=0.016). 6) 대상자의 술 후 폐환기능에 영향을 미치는 요인은 성별로 나타났다. 이에 따른 폐환기능의 차이를 보면, 실험군의 술 후 노력성 폐활량이 48시간에 남자($1.78{\pm}0.61L$)가 여자($1.27{\pm}0.45L$)보다 더 높게 나타났으며 (t=2.170, P=0.042), 72시간에도 역시 남자($2.16{\pm}0.56L$)가 여자($1.50{\pm}0.47L$)보다 더

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.112-121
• /
• 1997

In this paper, we study a model parameter compensation method for noise-robust speech recognition. We study model parameter compensation on a sentence by sentence and no other informations are used. Parallel model combination(PMC), well known as a model parameter compensation algorithm, is implemented and used for a reference of performance comparision. We also propose a modified PMC method which tunes model parameter with an association factor that controls average variability of gaussian mixtures and variability of single gaussian mixture per state for more robust modeling. We obtain a re-estimation solution of environmental variables based on the expectation-maximization(EM) algorithm in the cepstral domain. To evaluate the performance of the model compensation methods, we perform experiments on speaker-independent isolated word recognition. Noise sources used are white gaussian and driving car noise. To get corrupted speech we added noise to clean speech at various signal-to-noise ratio(SNR). We use noise mean and variance modeled by 3 frame noise data. Experimental result of the VTS approach is superior to other methods. The scheme of the zero order VTS approach is similar to the modified PMC method in adapting mean vector only. But, the recognition rate of the Zero order VTS approach is higher than PMC and modified PMC method based on log-normal approximation.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.96-105
• /
• 1998

The aim of this paper is to propose the method of WDHMM(Weighted DHMM), using the MLP-VQ for the improvement of speaker-independent connect-digit recognition system. MLP neural-network output distribution shows a probability distribution that presents the degree of similarity between each pattern by the non-linear mapping among the input patterns and learning patterns. MLP-VQ is proposed in this paper. It generates codewords by using the output node index which can reach the highest level within MLP neural-network output distribution. Different from the old VQ, the true characteristics of this new MLP-VQ lie in that the degree of similarity between present input patterns and each learned class pattern could be reflected for the recognition model. WDHMM is also proposed. It can use the MLP neural-network output distribution as the way of weighing the symbol generation probability of DHMMs. This newly-suggested method could shorten the time of HMM parameter estimation and recognition. The reason is that it is not necessary to regard symbol generation probability as multi-dimensional normal distribution, as opposed to the old SCHMM. This could also improve the recognition ability by 14.7% higher than DHMM, owing to the increase of small caculation amount. Because it can reflect phone class relations to the recognition model. The result of my research shows that speaker-independent connected-digit recognition, using MLP-VQ and WDHMM, is 84.22%.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.141-141
• /
• 2017

The ubiquitin-proteasome pathway is the major regulatory mechanism in a number of cellular processes for selective degradation of proteins and involves three steps: (1) ATP dependent activation of ubiquitin by E1 enzyme, (2) transfer of activated ubiquitin to E2 and (3) transfer of ubiquitin to the protein to be degraded by E3 complex. F-box proteins are subunit of SCF complex and involved in specificity for a target substrate to be degraded. F-box proteins regulate many important biological processes such as embryogenesis, floral development, plant growth and development, biotic and abiotic stress, hormonal responses and senescence. However, little is known about the F-box genes in wheat. The draft genome sequence of wheat (IWGSC Reference Sequence v1.0 assembly) used to analysis a genome-wide survey of the F-box gene family in wheat. The Hidden Markov Model (HMM) profiles of F-box (PF00646), F-box-like (PF12937), F-box-like 2 (PF13013), FBA (PF04300), FBA_1 (PF07734), FBA_2 (PF07735), FBA_3 (PF08268) and FBD (PF08387) domains were downloaded from Pfam database were searched against IWGSC Reference Sequence v1.0 assembly. RNA-seq paired-end libraries from different stages of wheat, such as stages of seedling, tillering, booting, day after flowering (DAF) 1, DAF 10, DAF 20, and DAF 30 were conducted and sequenced by Illumina HiSeq2000 for expression analysis of F-box protein genes. Basic analysis including Hisat, HTseq, DEseq, gene ontology analysis and KEGG mapping were conducted for differentially expressed gene analysis and their annotation mappings of DEGs from various stages. About 950 F-box domain proteins identified by Pfam were mapped to wheat reference genome sequence by blastX (e-value < 0.05). Among them, more than 140 putative F-box protein genes were selected by fold changes cut-offs of > 2, significance p-value < 0.01, and FDR<0.01. Expression profiling of selected F-box protein genes were shown by heatmap analysis, and average linkage and squared Euclidean distance of putative 144 F-box protein genes by expression patterns were calculated for clustering analysis. This work may provide valuable and basic information for further investigation of protein degradation mechanism by ubiquitin proteasome system using F-box proteins during wheat development stages.

• Asian-Australasian Journal of Animal Sciences
• /
• v.18 no.5
• /
• pp.613-619
• /
• 2005

Indigenous Yakutian cattle' adaptation to the hardest subarctic conditions makes them a valuable genetic resource for cattle breeding in the Siberian area. Since early last century, crossbreeding between native Yakutian cattle and imported Simmental and Kholmogory breeds has been widely adopted. In this study, variations at 22 polymorphic microsatellite loci in 5 populations of Yakutian, Kholmogory, Simmental, Yakutian-Kholmogory and Yakutian-Simmental cattle were analysed to estimate the genetic contribution of Yakutian cattle to the two hybrid populations. Three statistical approaches were used: the weighted least-squares (WLS) method which considers all allele frequencies; a recently developed implementation of a Markov chain Monte Carlo (MCMC) method called likelihood-based estimation of admixture (LEA); and a model-based Bayesian admixture analysis method (STRUCTURE). At population-level admixture analyses, the estimate based on the LEA was consistent with that obtained by the WLS method. Both methods showed that the genetic contribution of the indigenous Yakutian cattle in Yakutian-Kholmogory was small (9.6% by the LEA and 14.2% by the WLS method). In the Yakutian-Simmental population, the genetic contribution of the indigenous Yakutian cattle was considerably higher (62.8% by the LEA and 56.9% by the WLS method). Individual-level admixture analyses using STRUCTURE proved to be more informative than the multidimensional scaling analysis (MDSA) based on individual-based genetic distances. Of the 9 Yakutian-Simmental animals studied, 8 showed admixed origin, whereas of the 14 studied Yakutian-Kholmogory animals only 2 showed Yakutian ancestry (>5%). The mean posterior distributions of individual admixture coefficient (q) varied greatly among the samples in both hybrid populations. This study revealed a minor existing contribution of the Yakutian cattle in the Yakutian-Kholmogory hybrid population, but in the Yakutian-Simmental hybrid population, a major genetic contribution of the Yakutian cattle was seen. The results reflect the different crossbreeding patterns used in the development of the two hybrid populations. Additionally, molecular evidence for differences among individual admixture proportions was seen in both hybrid populations, resulting from the stochastic process in crossing over generations.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.20
• /
• pp.8993-9004
• /
• 2014

Background: The incidence rate and the treatment costs of hepatocellular carcinoma (HCC) are high, especially in Thailand. Previous studies indicated that early detection by a surveillance program could help by down-staging. This study aimed to compare the costs and health outcomes associated with the introduction of a HCC surveillance program with no program and to estimate the budget impact if the HCC surveillance program were implemented. Materials and Methods: A cost utility analysis using a decision tree and Markov models was used to compare costs and outcomes during the lifetime period based on a societal perspective between alternative HCC surveillance strategies with no program. Costs included direct medical, direct non-medical, and indirect costs. Health outcomes were measured as life years (LYs), and quality adjusted life years (QALYs). The results were presented in terms of the incremental cost-effectiveness ratio (ICER) in Thai THB per QALY gained. One-way and probabilistic sensitivity analyses were applied to investigate parameter uncertainties. Budget impact analysis (BIA) was performed based on the governmental perspective. Results: Semi-annual ultrasonography (US) and semi-annual ultrasonography plus alpha-fetoprotein (US plus AFP) as the first screening for HCC surveillance would be cost-effective options at the willingness to pay (WTP) threshold of 160,000 THB per QALY gained compared with no surveillance program (ICER=118,796 and ICER=123,451 THB/QALY), respectively. The semi-annual US plus AFP yielded more net monetary benefit, but caused a substantially higher budget (237 to 502 million THB) than semi-annual US (81 to 201 million THB) during the next ten fiscal years. Conclusions: Our results suggested that a semi-annual US program should be used as the first screening for HCC surveillance and included in the benefit package of Thai health insurance schemes for both chronic hepatitis B males and females aged between 40-50 years. In addition, policy makers considered the program could be feasible, but additional evidence is needed to support the whole prevention system before the implementation of a strategic plan.

• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1597-1609
• /
• 2004

A lot of lipreading system has been proposed to compensate the rate of speech recognition dropped in a noisy environment. Previous lipreading systems work on some specific conditions such as artificial lighting and predefined background color. In this paper, we propose a real-time lipreading system which allows the motion of a speaker and relaxes the restriction on the condition for color and lighting. The proposed system extracts face and lip region from input video sequence captured with a common PC camera and essential visual information in real-time. It recognizes utterance words by using the visual information in real-time. It uses the hue histogram model to extract face and lip region. It uses mean shift algorithm to track the face of a moving speaker. It uses PCA(Principal Component Analysis) to extract the visual information for learning and testing. Also, it uses HMM(Hidden Markov Model) as a recognition algorithm. The experimental results show that our system could get the recognition rate of 90% in case of speaker dependent lipreading and increase the rate of speech recognition up to 40～85% according to the noise level when it is combined with audio speech recognition.