• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.10C
• /
• pp.1007-1012
• /
• 2003

In order to accelerate the convergence speed of the conventional BP algorithm, constrained optimization techniques are applied to the BP algorithm. First, the noise-constrained least mean square algorithm and the zero noise-constrained LMS algorithm are applied (designated the NCBP and ZNCBP algorithms, respectively). These methods involve an important assumption: the filter or the receiver in the NCBP algorithm must know the noise variance. By means of extension and generalization of these algorithms, the authors derive an adaptive error-constrained BP algorithm, in which the error variance is estimated. This is achieved by modifying the error function of the conventional BP algorithm using Lagrangian multipliers. The convergence speeds of the proposed algorithms are 20 to 30 times faster than those of the conventional BP algorithm, and are faster than or almost the same as that achieved with a conventional linear adaptive filter using an LMS algorithm.

• ETRI Journal
• /
• v.26 no.5
• /
• pp.432-436
• /
• 2004

In this paper, we propose the modified uniformly most powerful (UMP) belief-propagation (BP)-based decoding algorithm which utilizes multiplicative and additive factors to diminish the errors introduced by the approximation of the soft values given by a previously proposed UMP BP-based algorithm. This modified UMP BP-based algorithm shows better performance than that of the normalized UMP BP-based algorithm, i.e., it has an error performance closer to BP than that of the normalized UMP BP-based algorithm on the additive white Gaussian noise channel for low density parity check codes. Also, this algorithm has the same complexity in its implementation as the normalized UMP BP-based algorithm.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.4 no.4
• /
• pp.195-200
• /
• 2009

As 4G mobile communication systems require high transmission rates with reliability, the need for efficient error correcting code is increasing. In this paper, a novel LDPC (Low Density Parity Check) decoder is introduced. The LDPC code is one of the most popular error correcting codes. In order to improve performance of the LDPC decoder, we use SNR (Signal-to-Noise Ratio) estimation results to adjust coefficients of modified UMP-BP (Uniformly Most Probable Belief Propagation) algorithm which is one of widely-used LDPC decoding algorithms. An advantage of Modified UMP-BP is that it is amenable to implement in hardware. We generate the optimal values by simulation for various SNRs and coefficients, and the values are stored in a look-up table. The proposed decoder decides coefficients of the modified UMP-BP based on SNR information. The simulation results show that the BER (Bit Error Rate) performance of the proposed LDPC decoder is better than an LDPC decoder using a conventional modified UMP-BP.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.686-692
• /
• 2022

In this paper, the matching error rates of modified area-based, energy-based algorithms, and learning-based structures were compared for stereo image matching. Census transform (CT) based on region and life propagation (BP) algorithm based on energy were selected, respectively.Existing algorithms have been improved and implemented in an embedded processor environment so that they can be used for stereo image matching in mobile systems. Even in the case of the learning base to be compared, a neural network structure that utilizes small-scale parameters was adopted. To compare the error rates of the three matching methods, Middlebury's Tsukuba was selected as a test image and subdivided into non-occlusion, discontinuous, and disparity error rates for accurate comparison. As a result of the experiment, the error rate of modified CT matching improved by about 11% when compared with the existing algorithm. BP matching was about 87% better than conventional CT in the error rate. Compared to the learning base using neural networks, BP matching was about 31% superior.

• Journal of Sensor Science and Technology
• /
• v.17 no.2
• /
• pp.87-94
• /
• 2008

Blood pressure (BP), one of the most important vital signs, is used to identify an emergency state and reflects the blood flow characteristics of the cardiovascular system. The conventional noninvasive method of measuring BP is inconvenient because patients must wear a cuff on their arm and the measurement process takes time. This paper proposes an algorithm for estimating the BP using the pulse transit time (PTT) of the photoplethysmography (PPG) and pressure pulse from finger at the same time as a more convenient way to measure the BP. After recording the electrocardiogram (ECG), measuring the pressure pulse, and performing PPG, we calculated the PTT from the acquired signals. Then, we used a multiple regression analysis to measure the systolic and diastolic BP indirectly. Comparing the BP measured indirectly using the proposed algorithm and the real BP measured with a sphygmomanometer, the systolic pressure had a mean error of ${\pm}3.240$ mmHg and a standard deviation of 2.530 mmHg, while the diastolic pressure had a satisfactory result, i.e., a mean error of ${\pm}1.807$ mmHg and a standard deviation of 1.396 mmHg. These results are more superior than existing method estimating blood pressure using the one PTT and satisfy the ANSI/AAMI regulations for certifying a sphygmomanometer i.e., the measurement error should be within a mean error of ${\pm}5$ mmHg and a standard deviation of 8 mmHg. These results suggest the possibility of applying our method to a portable, long-term BP monitoring system.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.23 no.3
• /
• pp.275-282
• /
• 2016

Purpose: This study was done to examine the relationship between nursing students' hearing levels and accuracy of blood pressure (BP) measurements. Methods: Participants were 107 students who had finished their fundamental nursing practice and clinical practicum and who used earphones. Data were collected from October 13 to November 30, 2014 and from April 30 to May 19, 2015. Students' hearing thresholds were examined using an audiometer. Students were assigned to take two BP measurements on BP measurement training simulators, but only the second measurement was used for analysis. Results: All nursing students' hearing levels were within normal range, and there was no significant difference found among the settings for diastolic blood pressure. However, there were significant differences between low systolic blood pressure (SBP) (below 120mmHg) and high SBP (over 140mmHg) (z=9.02, p=.011). Measurement error in SBP showed a positive correlation with hearing threshold in the right ear at frequencies of 1000Hz and 500Hz. Conclusion: Findings indicate that BP measurement error is correlated with hearing threshold at some frequencies. To reduce measurement error, nursing students should be provided with health education about hearing and to improve training for students, further studies need to examine other factors influencing BP measurement error.

• ETRI Journal
• /
• v.34 no.5
• /
• pp.719-726
• /
• 2012

Messages are generally selected with the same probability in the encoding scheme of rateless codes for equal error protection. In addition, a belief propagation (BP) decoding scheme is generally used because of the low computational complexity. However, the probability of recovering a new message by BP decoding is reduced if both the recovered and unrecovered messages are selected uniformly. Thus, more codeword symbols than expected are required for the perfect recovery of message symbols. Therefore, a new encoding scheme with a nonuniform selection of messages is proposed in this paper. In addition, a BP-Gaussian elimination hybrid decoding scheme that complements the drawback of the BP decoding scheme is proposed. The performances of the proposed schemes are analyzed and compared with those of the conventional schemes.

• International journal of advanced smart convergence
• /
• v.10 no.2
• /
• pp.175-186
• /
• 2021

We have studied the speed regulation of the permanent magnet synchronous motor (PMSM) servo system in this paper. To optimize the PMSM servo system's speed-control performance with disturbances, a non-linear speed-control technique using a back-propagation neural network (BP-NN) algorithm forthe controller design of the PMSM speed loop is introduced. To solve the slow convergence speed and easy to fall into the local minimum problem of BP-NN, we develope an improved BP-NN control algorithm by limiting the range of neural network outputs of the proportional coefficient Kp, integral coefficient Ki of the controller, and add adaptive gain factor β, that is the internal gain correction ratio. Compared with the conventional PI control method, our improved BP-NN control algorithm makes the settling time faster without static error, overshoot or oscillation. Simulation comparisons have been made for our improved BP-NN control method and the conventional PI control method to verify the proposed method's effectiveness.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.9C
• /
• pp.1227-1234
• /
• 2004

In this paper, we propose a modified Normalized-BP algorithm by changing the normalization factor according to the reliability of updated messages. Proposed algorithm has almost same decoding complexity as Normalized-BP algorithm and achieves a bit-error probability of $10^4$within 0.02dB away from compared with LLR-BP algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.853-858
• /
• 1993

The error back-propagation(BP) algorithm is widely used for finding optimum weights of multi-layer neural networks. However, the critical drawback of the BP algorithm is its slow convergence of error. The major reason for this slow convergence is the premature saturation which is a phenomenon that the error of a neural network stays almost constant for some period time during learning. An inappropriate selections of initial weights cause each neuron to be trapped in the premature saturation state, which brings in slow convergence speed of the multi-layer neural network. In this paper, to overcome the above problem, Micro-Genetic algorithms(.mu.-GAs) which can allow to find the near-optimal values, are used to select the proper weights and slopes of activation function of neurons. The effectiveness of the proposed algorithms will be demonstrated by some computer simulations of two d.o.f planar robot manipulator.