• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.331.1-334
• /
• 1998

본 논문에서는 금액을 인식 대상으로 하는 음성 인식 시스템의 성능 향상을 위하여 프레임 동기 네트워크(Frame Synchronous Network)을 이용하였다. 연속음 인식에서 인식 대상이 가지는 규칙을 적용했을 경우 성능 향상을 가져올 수 있다. 금액이 가지는 반복적인 특성과 자릿수의 상하 관계가 인식 성능에 미치는 효과를 이용하여 다양한 수준의 제약을 갖는 FSN을 제안하였다. 제안된 FSN의 성능을 다양한 환경과 특징 벡터에 대하여 이산 hidden Markov model[5]을 이용하여 실험을 수행하였다. 인식 결과 제안된 FSN을 이용하여 금액 어휘의 인식 성능을 향상시킬 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.32.3-32
• /
• 2001

This paper proposes a layered protocol to interpret voice commands of the user´s own language to a machine, to control it in real time. The layers consist of speech signal capturing layer, lexical analysis layer, interpretation layer and finally activation layer, where each layer tries to mimic the human counterparts in command following. The contents of a continuous voice command are captured by using Hidden Markov Model based speech recognizer. Then the concepts of Artificial Neural Network are devised to classify the contents of the recognized voice command ...

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.876-879
• /
• 2002

The paper presents the analysis and results of traffic measurements in the 155 Mbit/s real working ATM backbone network. The traffic is described as an ordered sequence of real-time cells. In this paper we analyze two timescales in which some form of a stochastic process is taking place: cell scale and burst scale. We present another way to describe the cell flow in ATM networks by definition the function, designed to be the probability of the burst of length ∫in n sequential slots.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.671-674
• /
• 1999

We report the new method for speaker recognition. Until now, many researchers have used HMM (Hidden Markov Model) with cepstral coefficient or neural network for speaker recognition. Here, we introduce the method of speaker recognition using eigenspace. This method can reduce the training and recognition time of speaker recognition system. In proposed method, we use the low rank model of the speech eigenspace. In experiment, we obtain good recognition result.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.17 no.32
• /
• pp.145-154
• /
• 1994

In this paper, monitoring processor in a circuit switched network is considered. Monitoring processor monitors communication links, and offers a grade of service in each link to controller. Such an information is useful for an effective maintenance of system. Two links with nonsymmetric system Parameters are considered. each link is assumed independent M/M/1/1 type. The Markov process is introduced to compute busy and idle portions of monitoring processor and monitored rate of each link. Inter-idle times and inter-monitoring times of monitoring processor between two links are respectively computed. A recursive formula is introduced to make computational procedure rigorous.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2220-2223
• /
• 2003

In this paper we used Support Vector Machines(SVMs) recently proposed as the loaming method, one of Artificial Neural Network, to divide continuous speech into phonemes, an initial, medial, and final sound, and then, performed continuous speech recognition from it. Decision boundary of phoneme is determined by algorithm with maximum frequency in a short interval. Recognition process is performed by Continuous Hidden Markov Model(CHMM), and we compared it with another phoneme divided by eye-measurement. From experiment we confirmed that the method, SVMs, we proposed is more effective in an initial sound than Gaussian Mixture Models(GMMs).

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2001.11a
• /
• pp.269-272
• /
• 2001

본 논문에서는 베이지안 네트워크와 통합 감사자료를 이용하여 시스템 사용자에 대한 비정상행위를 탐지하고 분석하는데 효과적인 모델을 제안하고자 한다. 이를 위해 리눅스 시스템에서의 여러 가지 감사자료들을 통합한 감사자료로부터 사용자의 행위에 대해 베이지안 네트워크로 구성하고자 한다. 베이지안 네트워크를 구성할 때 효율적인 학습이 가능한 Sparse Candidate 알고리즘을 적용하고, 감사자료의 일부가 결여되어 있는 경우에도 추론이 가능하도록 MCMC(Markov Chain Monte Carlo)의 일종인 Gibbs Sampling 방법을 적용한다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1990.04a
• /
• pp.326-334
• /
• 1990

A monitoring process of a communication network with two links is analyzed. The Markov process is introduced to compute busy and idle portions of monitoring processor and monitored rate of each link. Inter-idle times and inter-monitoring ties of monitoring processor between two links are respectively computed. A recursive formula is introduced to make the computational procedure rigorous.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.305-307
• /
• 2003

일반적으로 해킹이 이루어지기 위해서는 공격의 대상이 되는 시스템과 네트워크의 정보를 수집하는 사전단계가 필수적이다. 네트워크 포트 스캐닝은 이 시스템 정보 수집단계에서 중요한 역할을 하는 방법으로 주로 통신 프로토콜의 취약점을 이용하여 비정상적인 패킷을 보낸 후 시스템의 반응을 살피는 방법으로 수행된다. 본 논문에서는 마르코프 체인 모델을 이용한 비정상행위기법 기반의 포트 스캐닝을 탐지방법을 제안하고 여러 가지 은닉/비은닉 포트 스캐닝 방법에 대하여 좋은 성능을 나타냄을 보인다.

• Journal of Satellite, Information and Communications
• /
• v.10 no.2
• /
• pp.10-13
• /
• 2015

This paper proposed a novel user's information feedback algorithm for improving network energy harvesting rate. The proposed algorithm is focused on determining energy harvesting users comparing increasing ratio of the amount of harvesting energy versus emitted energy and network threshold ${\alpha}$, which is critical harvesting parameter. Using this method, we can increase the rate of network energy harvesting preventing emitted energy from wasting inefficiently. The result of experiment in this paper shows that user's information feedback algorithm makes network energy harvesting rate more efficiently when it uses threshold ${\alpha}=15%$ to determine energy harvesting users.