• 한국통신학회논문지
• /
• 제31권9C호
• /
• pp.853-858
• /
• 2006

음성인식에서 TMHMM(Tied Mixture Hidden Markov Model)은 자유 매개변수의 수를 감소시키기 위한 좋은 접근이지만, GPDF(Gaussian Probability Density Function) 군집화 오류에 의해 음성인식의 오류를 발생시켰다. 본 논문은 TMHMM에서 발생하는 군집화 오류를 최소화하기 위하여 HCNN(Homogeneous Centroid Neural Network) 군집화 알고리즘을 제안한다. 제안된 알고리즘은 CNN(Centroid Neural Network)을 TMHMM상의 음향 특징벡터에 활용하였으며, 다른 상태에 소속된 확률밀도가 서로 겹쳐진 형태의 이질군집 지역에 더 많은 코드벡터를 할당하기 위해서 본 논문에서 새로 제안이 제안되는 이질성 거리척도를 사용 하였다. 제안된 알고리즘을 한국어 고립 숫자단어의 인식문제에 적용한 결과, 기존 K-means 알고리즘이나 CNN보다 각각 14.63%, 9,39%의 오인식률의 감소를 얻을 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.2037-2040
• /
• 2004

In this paper we introduce a new prototype based classifiers for overlapping data, where training pattern can be overlap on the feature space. The proposed classifier is based on the prototype from neural network classifier (NNC)[1] for overlap data. The method automatically chooses the initial center and two radiuses for each class. The center is used as a mean representative of training data for each class. The unclassified pattern is classified by measure distance from the class center. If the distance is in the lower (shorter radius) the unknown pattern has the high percentage of being in this class. If the distance is between the lower and upper (further radius), the pattern has the probability of being in this class or others. But if the distance is outside the upper, the pattern is not in this class. We borrow the words upper and lower from the rough set to represent the region of certainty [3]. The training algorithm to find number of cluster and their parameters (center, lower, upper) is presented. The clustering result is tested using patterns from Thai handwritten letter and the clustering result is very similar to human eyes clustering.

• Journal of Astronomy and Space Sciences
• /
• 제34권3호
• /
• pp.213-223
• /
• 2017

The deep space orbit determination software (DSODS) is a part of a flight dynamic subsystem (FDS) for the Korean Pathfinder Lunar Orbiter (KPLO), a lunar exploration mission expected to launch after 2018. The DSODS consists of several sub modules, of which the orbit determination (OD) module employs a weighted least squares algorithm for estimating the parameters related to the motion and the tracking system of the spacecraft, and subroutines for performance improvement and detailed analysis of the orbit solution. In this research, DSODS is demonstrated and validated at lunar orbit at an altitude of 100 km using actual Lunar Prospector tracking data. A set of a priori states are generated, and the robustness of DSODS to the a priori error is confirmed by the NASA planetary data system (PDS) orbit solutions. Furthermore, the accuracy of the orbit solutions is determined by solution comparison and overlap analysis as about tens of meters. Through these analyses, the ability of the DSODS to provide proper orbit solutions for the KPLO are proved.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 1996년도 특별강연 및 추계학술발표 개요집
• /
• pp.139-141
• /
• 1996

Among various welding parameters, the welding current which is inversely proportional to the tip-to-workpiece distance in GMAW is an essential parameter to monitor the GMAW process of horizontal fillet joints. For the case of weld defect such as overlap in horizontal fillet welding, therefore, the signal processing for process monitoring or automatic seam tracking should be modified by considering the weld pool surface geometry including the corresponding weld defect. In other words, the adequate signal processing algorithm is indispensible to improve the performance of the arc sensor. However, arc sensor algorithm already developed usually focus on weld seam tracing but do not considering the weld qualities. In this paper, various experiments were carried out to investigate the tendencies of the weld defects when weaving motion is added, and the experimental method based on 2$^n$ factorial design was proposed for deriving the mathematical model between the leg length and the various welding conditions. Moreover, a signal processing method based on the artificial neural network(Adaptive Resonance Theory) was proposed far discriminating the current signal of sound weld beads from that of weld beads with overlap. Finally, the algorithm for weld seam tracking combined with the mathematical modeling and the signal processing method was carried out to track the weld line in conjunction with the improvement of the weld qualities. The reliability of the proposed algorithms were evaluated through various experiments, which showed that the proposed algorithms could be effectively used for arc welding automation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권12호
• /
• pp.4819-4834
• /
• 2015

The spectral efficiency of cellular networks can be improved when proximate users engage in device-to-device (D2D) communications to communicate directly without going through a base station. However, D2D communications that are not properly designed may generate interference with existing cellular networks. In this paper, we study resource allocation and power control to minimize the probability of an outage and maximize the overall network throughput. We investigate three power control-based schemes: the Partial Co-channel based Overlap Resource Power Control (PC.OVER), Fractional Frequency Reuse based Overlap Resource Power Control (FFR.OVER) and Fractional Frequency Reuse based Adaptive Power Control (FFR.APC) and also compare their performance. In PC.OVER, a certain portion of the total bandwidth is dedicated to the D2D. The FFR.OVER and FFR.APC schemes combine the FFR techniques and the power control mechanism. In FFR, the entire frequency band is partitioned into two parts, including a central and edge sub-bands. Macrocell users (mUEs) transmit using uniform power in the inner and outer regions of the cell, and in all three schemes, the D2D receivers (D2DRs) transmit with low power when more than one D2DRs share a resource block (RB) with the macrocells. For PC.OVER and FFR.OVER, the power of the D2DRs is reduced to its minimum, and for the FFR.APC scheme, the transmission power of the D2DRs is iteratively adjusted to satisfy the signal to interference ratio (SIR) threshold. The three schemes exhibit a significant improvement in the overall system capacity as well as in the probability of a user outage when compared to a conventional scheme.

• Nano
• /
• 제13권11호
• /
• pp.1850126.1-1850126.10
• /
• 2018

Flexible strain sensors, as the core member of the family of smart electronic devices, along with reasonable sensing range and sensitivity plus low cost, have rose a huge consumer market and also immense interests in fundamental studies and technological applications, especially in the field of biomimetic robots movement detection and human health condition monitoring. In this paper, we propose a new flexible strain sensor based on thick CVD graphene film and its low-cost fabrication strategy by using the commercial adhesive tape as flexible substrate. The tensile tests in a strain range of ~30% were implemented, and a gage factor of 30 was achieved under high strain condition. The optical microscopic observation with different strains showed the evolution of cracks in graphene film. Together with commonly used platelet overlap theory and percolation network theory for sensor resistance modeling, we established an overlap destructive resistance model to analyze the sensing mechanism of our devices, which fitted the experimental data very well. The finding of difference of fitting parameters in small and large strain ranges revealed the multiple stage feature of graphene crack evolution. The resistance fallback phenomenon due to the viscoelasticity of flexible substrate was analyzed. Our flexible strain sensor with low cost and simple fabrication process exhibits great potential for commercial applications.

• Journal of Communications and Networks
• /
• 제7권1호
• /
• pp.76-86
• /
• 2005

Today's wireless access networks consist of several tiers that overlap each other. Provisioning of real time undisrupted communication to mobile users, anywhere and anytime through these heterogeneous overlay networks, is a challenging task. We extend the end-to-end approach for the handoff management in hybrid wireless data network by designing a fully mobile-controlled handoff for mobile devices equipped with dual mode interfaces. By handoff, we mean switching the communication between interfaces connected to different subnets. This mobile-controlled handoff scheme reduces the service disruption time during both horizontal and vertical handoffs and does not require any modification in the access networks. We exploit the IP diversity created by the dual interfaces in the overlapping area by simultaneously connecting to different subnets and networks. Power saving is achieved by activating both interfaces only during the handoff period. The performance evaluation of the handoff is carried out by a simple mathematical analysis. The analysis shows that with proper network engineering, exploiting the speed of mobile node and overlapping area between subnets can reduce service disruption and power consumption during handoff significantly. We believe that with more powerful network interfaces our proposal of dual interfaces can be realized.

• 정보보호학회논문지
• /
• 제29권6호
• /
• pp.1393-1401
• /
• 2019

최근 시스템에 음성 인증 기능이 탑재됨에 따라 화자(Speaker)를 정확하게 인증하는 중요성이 높아지고 있다. 이에 따라 다양한 방법으로 화자를 인증하는 모델이 제시되어 왔다. 본 논문에서는 Short-time Fourier transform(STFT)를 적용한 새로운 화자 인증 모델을 제안한다. 이 모델은 기존의 Mel-Frequency Cepstrum Coefficients(MFCC) 추출 방법과 달리 윈도우 함수를 약 66.1% 오버랩하여 화자 인증 시 정확도를 높일 수 있다. 새로운 화자 인증 모델을 제안한다. 이 때, LSTM 셀을 적용한 Recurrent Neural Network(RNN)라는 딥러닝 모델을 사용하여 시변적 특징을 가지는 화자의 음성 특징을 학습하고, 정확도가 92.8%로 기존의 화자 인증 모델보다 5.5% 정확도가 높게 측정되었다.

• ETRI Journal
• /
• 제26권5호
• /
• pp.467-474
• /
• 2004

In a High Altitude Platform (HAP) cellular communications network, each cell may be served by a dedicated spot-beam antenna. The antennas' beam properties and their spatial overlap control the co-channel interference. In prior literature, radiation patterns have been approximated by a main lobe followed by a constant sidelobe floor. A network of 121 cells has been studied and the method is here extended to the use of more realistic radiation patterns based on the theoretical aperture antenna patterns. This allows for the comparison of the effect of different aperture field tapers, which lead to reduced sidelobe levels and hence higher system capacity but also a more massive antenna payload.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 추계학술대회 논문집
• /
• pp.1138-1144
• /
• 2008

To study the feasibility of applying wireless communication technology to the control of train for the effective control of train and for the reduction of cost and time to construct the necessary infra structure, we investigate into the application of the existing commercial WCDMA network to CBTC (communication-based train control) to grasp the obstacles and propose the solutions to circumvent them. The obstacles can be categorized into the hand-off problem, the interference problem near the stations, and the problem of radio shadow areas. We propose, as solutions, the cell overlap method and multi-terminal approach for the hand-off problem, the cell sectoring method for the interference problem, and establishment of new base stations along the railroad both to provide the wireless train control and communication service to the customers on the train which was otherwise impossible because of the shadowing effect.