• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.4
• /
• pp.42-49
• /
• 1997

A conventional adaptive noise canceller (ANC) using LMS algorithm suffers from the misadjustment of adaptive filter weights due to the gradient-estimate noise by input speech signal at steady state. In this paper, an ANC is proposed which uses the combination of VSLMS (variable step size LMS) and SA (sign algorithm) to improve steady state performance and convergence rate. SA algorithm is applied in speech region to prevent the weights from perturbing by output speech of ANC and VSLMS algorithm is applied to improve convergence rate and channel tracking ability in silence region and adaptive transient region. In compute rsimulation, the performance of the proposed VSLMS-SA combination algorithm is much better than LMS algorithm and the algorithm, recently proposed by greenberg, with adaptation step-size parameter determine dby sum method in convergence rate, channel tracking and steady state performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1C
• /
• pp.65-71
• /
• 2004

We improved the MLLR speaker adaptation algorithm with reduction of the order of HMM parameters using PCA(Principle Component Analysis) or ICA(Independent Component Analysis). To find a smaller set of variables with less redundancy, we adapt PCA(principal component analysis) and ICA(independent component analysis) that would give as good a representation as possible, minimize the correlations between data elements, and remove the axis with less covariance or higher-order statistical independencies. Ordinary MLLR algorithm needs more than 30 seconds adaptation data to represent higher word recognition rate of SD(Speaker Dependent) models than of SI(Speaker Independent) models, whereas proposed algorithm needs just more than 10 seconds adaptation data. 10 components for ICA and PCA represent similar performance with 36 components for ordinary MLLR framework. So, compared with ordinary MLLR algorithm, the amount of total computation requested in speaker adaptation is reduced by about 1/167 in proposed MLLR algorithm.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.4
• /
• pp.265-276
• /
• 2004

Genetic Algorithm(GA), that is shown stable performance to find an optimal solution, has been used as a method of solving large-scaled optimization problems with complex constraints in various applications. Since it takes so much time to execute a long computation process for iterative evolution and adaptation. In this paper, a hardware-based adaptive GA was proposed to reduce the serious computation time of the evolutionary process and to improve the accuracy of convergence to optimal solution. The proposed GA, based on steady-state model among continuos generation model, performs an adaptive mutation process with consideration of the evolution flow and the population diversity. The drawback of the GA, premature convergence, was solved by the proposed adaptation. The Performance improvement of convergence accuracy for some kinds of problem and condition reached to 5-100% with equivalent convergence speed to high-speed algorithm. The proposed adaptive GAP(Genetic Algorithm Processor) was implemented on FPGA device Xilinx XCV2000E of EHW board for face recognition.

• Journal of Communications and Networks
• /
• v.7 no.3
• /
• pp.243-247
• /
• 2005

We propose an efficient block least-mean-square (BLMS) adaptive algorithm, in conjunction with error control coding, for direct-sequence code division multiple access (DS-CDMA) systems. The proposed adaptive receiver incorporates decision feedback detection and channel encoding in order to improve the performance of the standard LMS algorithm in convolutionally coded systems. The BLMS algorithm involves two modes of operation: (i) The training mode where an uncoded training sequence is used for initial filter tap-weights adaptation, and (ii) the decision-directed where the filter weights are adapted, using the BLMS algorithm, after decoding/encoding operation. It is shown that the proposed adaptive receiver structure is able to compensate for the signal-to­noise ratio (SNR) loss incurred due to the switching from uncoded training mode to coded decision-directed mode. Our results show that by using the proposed adaptive receiver (with decision feed­back block adaptation) one can achieve a much better performance than both the coded LMS with no decision feedback employed. The convergence behavior of the proposed BLMS receiver is simulated and compared to the standard LMS with and without channel coding. We also examine the steady-state bit-error rate (BER) performance of the proposed adaptive BLMS and standard LMS, both with convolutional coding, where we show that the former is more superior than the latter especially at large SNRs ($SNR\;\geq\;9\;dB$).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4585-4603
• /
• 2015

Video streaming services make up a large proportion of Internet traffic on both fixed and mobile access throughout the world. Adaptive streaming allows for dynamical adaptation of the bitrate with varying network conditions, to guarantee the best user experience. Adaptive bitrate algorithms face a significant challenge in correctly estimating the throughput as it varies widely over time. In this paper, we first evaluate the throughput estimation techniques and show that the method that we have used offers stable response to throughput fluctuations while maintaining a stable playback buffer. Then, we propose an adaptive bitrate scheme that intelligently selects the video bitrates based on the estimated throughput and buffer occupancy. We show that the proposed scheme improves viewing experience by achieving a high video rate without taking unnecessary risks and by minimizing the frequency of changes in the video quality. Furthermore, we show that it offers a stable response to short-term fluctuations and responds swiftly to large fluctuations. We evaluate our algorithm for both constant bitrate (CBR) and variable bitrate (VBR) video content by taking into account the segment sizes and show that it significantly improves the quality of video streaming.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.39.2-39
• /
• 2002

This paper presents adaptive add-on control algorithms for theconventional mode of operation of MEMS z-axis gyroscopes. This scheme is realized by adding an outer loop to a conventional force-balancing scheme that includes a parameter estimation algorithm. The parameter adaptation algorithm estimates the angular rate, identifies and compensates the quadrature error, and may permit on-line automatic mode tuning. The convergence and resolution analysis show that the proposed adaptive add-on control scheme prevents the angular rate estimate from being contaminated by the quadrature error, while keeping ideal resolution performance of a conventional force-balancing scheme.

• Proceedings of the IEEK Conference
• /
• 2004.06a
• /
• pp.281-284
• /
• 2004

This paper presents the design and implementation of a QoS based enhanced collaboration system in MDO. This is an efficient distributed communication tool between designers. It supports text communication, audio/video communication, file transfer and XML data sending/receiving. Specially, this system supports a dynamic QoS self-adaptation by using the improved direct adjustment algorithm (DAA+). The original direct adjustment algorithm adjusts the transmission rate according to the congestion level of the network, based on the end to end real time transport protocol (RTP), and controls the transmission rate by using the information of loss ratio in real time transport control protocol (RTCP). But the direct adjustment algorithm does not consider when the RTCP packets are lost. We suggest an improved direct adjustment algorithm to solve this problem. We apply our improved direct adjustment algorithm to our of QoS (Quality of Service) [1] based collaboration system and show the improved performance of transmission rate and loss ratio.

• The Journal of Korea Robotics Society
• /
• v.3 no.2
• /
• pp.81-90
• /
• 2008

While increasing demand of the service for the disabled and the elderly people, assistive technologies have been developed rapidly. The natural signal of human such as voice or gesture has been applied to the system for assisting the disabled and the elderly people. As an example of such kind of human robot interface, the Soft Remote Control System has been developed by HWRS-ERC in $KAIST^[1]$. This system is a vision-based hand gesture recognition system for controlling home appliances such as television, lamp and curtain. One of the most important technologies of the system is the hand gesture recognition algorithm. The frequently occurred problems which lower the recognition rate of hand gesture are inter-person variation and intra-person variation. Intra-person variation can be handled by inducing fuzzy concept. In this paper, we propose multivariate fuzzy decision tree(MFDT) learning and classification algorithm for hand motion recognition. To recognize hand gesture of a new user, the most proper recognition model among several well trained models is selected using model selection algorithm and incrementally adapted to the user's hand gesture. For the general performance of MFDT as a classifier, we show classification rate using the benchmark data of the UCI repository. For the performance of hand gesture recognition, we tested using hand gesture data which is collected from 10 people for 15 days. The experimental results show that the classification and user adaptation performance of proposed algorithm is better than general fuzzy decision tree.

• ETRI Journal
• /
• v.32 no.1
• /
• pp.160-162
• /
• 2010

For the acoustic models of embedded speech recognition systems, hidden Markov models (HMMs) are usually quantized and the original full space distributions are represented by combinations of a few quantized distribution prototypes. We propose a maximum likelihood objective function to train the quantized distribution prototypes. The experimental results show that the new training algorithm and the link structure adaptation scheme for the quantized HMMs reduce the word recognition error rate by 20.0%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9A
• /
• pp.1359-1371
• /
• 1999

In this paper, we propose an efficient explicit rate (ER) feedback switch algorithm for available bit rate (ABR) flow control. In order to improve the disadvantages of existing ER feedback switch algorithms with congestion avoidance, the proposed scheme adjusts the target utilization dynamically according to the queue length and its growth rate. also, we investigate the performance of the proposed switch algorithm and compare it with ERICA and NIST switches using simulation. Simulation results show that the proposed switch algorithm can control the cell emission rate of a source rapidly according to variations of available link bandwidth by using dynamic adaptation of target utilization. It also exhibits a better performance than the existing ER feedback switches in terms of queue length and link utilization.