• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.11-14
• /
• 2018

The aim of this study is to rectify the misclassified image features and enhance the performance of image classification tasks by incorporating a channel- coding technique, widely used in telecommunication. Specifically, the proposed algorithm employs the error - correcting mechanism of convolutional coding combined with the convolutional neural networks (CNNs) that are the state - of- the- arts image classifier s. We develop an encoder and a decoder to employ the error - correcting capability of the convolutional coding. In the encoder, the label values of the image data are converted to convolutional codes that are used as target outputs of the CNN, and the network is trained to minimize the Euclidean distance between the target output codes and the actual output codes. In order to correct misclassified features, the outputs of the network are decoded through the trellis structure with Viterbi algorithm before determining the final prediction. This paper demonstrates that the proposed architecture advances the performance of the neural networks compared to the traditional one- hot encoding method.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2006.07a
• /
• pp.432-432
• /
• 2006

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.07a
• /
• pp.345-345
• /
• 2004

• Journal of Communications and Networks
• /
• v.5 no.2
• /
• pp.116-123
• /
• 2003

In this paper, we address the problem of designing multirate codes for a multiple-input and multiple-output (MIMO) system by restricting the receiver to be a successive decoding and interference cancellation type, when each of the antennas is encoded independently. Furthermore, it is assumed that the receiver knows the instantaneous fading channel states but the transmitter does not have access to them. It is well known that, in theory, minimummean- square error (MMSE) based successive decoding of multiple access (in multi-user communications) and MIMO channels achieves the total channel capacity. However, for this scheme to perform optimally, the optimal rates of each antenna (per-antenna rates) must be known at the transmitter. We show that the optimal per-antenna rates at the transmitter can be estimated using only the statistical characteristics of the MIMO channel in time-varying Rayleigh MIMO channel environments. Based on the results, multirate codes are designed using punctured turbo codes for a horizontal codedMIMOsystem. Simulation results show performances within about one to two dBs of MIMO channel capacity.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.101-107
• /
• 2017

LabVIEW coding for video dehazing was developed. The dark channel prior proposed by K. He was applied to remove fog based on a single image, and K. B. Gibson's median dark channel prior was applied, and implemented in LabVIEW. In other words, we improved the image processing speed by converting the existing fog removal algorithm, dark channel prior, to the LabVIEW system. As a result, we have developed a real-time fog removal system that can be commercialized. Although the existing algorithm has been utilized, since the performance has been verified real - time, it will be highly applicable in academic and industrial fields. In addition, fog removal is performed not only in the entire image but also in the selected area of the partial region. As an application example, we have developed a system that acquires clear video from the long distance by connecting a laptop equipped with LabVIEW SW that was developed in this paper to a 100~300 times zoom telescope.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4C
• /
• pp.397-402
• /
• 2009

Accurate estimation of time-selective fading channel is a difficult problem in OFDM(Orthogonal Frequency Division Multiplexing) system. There are many channel estimation algorithms that are very weak in noisy channel. For solving this problem, we use EM (Expectation-Maximization) algorithm for iterative optimization of the data. We propose an EM-LPC algorithm to estimate the time-selective fading. The proposed algorithm improves of the BER performance compared to EM based channel estimation algorithm and reduces the iteration number of the EM loop. We simulated the uncoded system. If coded system use the EM-LPC algorithm, the performance are enhanced because of the coding gain. The EM-LPC algorithm is able to apply to another communication system, not only OFDM systems. The image processing of the medical instruments that the demand of accurate estimation can also use the proposed algorithm.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.4
• /
• pp.99-105
• /
• 2012

Recently, there are many user selection algorithms in multi user multiple-input multiple-output (MU-MIMO) systems. One of well-known user selection methods is Semi orthogonal user selection (SUS). It is an algorithm maximizing channel capacity. However, it is applicable only when user's antenna is one. We propose a generalized user selection algorithm regardless of the number of user's antennas. In the proposed scheme, Base station (Bs) selects the first user who has the highest determinant of channel and generates a user group that correlation with first user's channel is less than allowance of correlation. Then, each determinant of channels made up of first user's channel and a user's channel in the generated group is calculated and BS selects the next user who has the highest determinant of that. BS selects following users by repeating above procedure. In this paper, we get better performance because of selecting users who have the highest determinant of channel as well as allowance of correlation optimally calculated through matrix operations.

• Journal of Advanced Navigation Technology
• /
• v.6 no.3
• /
• pp.203-210
• /
• 2002

In this paper, the BER performance of IEEE 802.11a OFDM WLAN system is obtained by simulation and it is shown that the proposed modified channel estimation algorithm improves the channel estimation performance of the system. The wireless channel used in channel simulation includes AWGN and delay spread channel implemented by TDL model. At first, the performance of OFDM WLAN system according to data rate and coding rate defined in standard is evaluated in AWGN channel. Then, imperfect channel estimation in indoor wireless channel is considered. After the performance of conventional channel estimation scheme using only two long training symbols is evaluated, and that of proposed modified channel estimation scheme using additional 8 short training symbol is compared with it. From the simulation results, it is shown that modified channel estimation scheme provides reduced channel estimation error and improves the channel estimation performance due to noise averaging effect with the same preamble format as defined in specification.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.163-165
• /
• 2008

In this paper we compare performance of exponential effective SINR mapping (EESM) with traditional actual value interface (AVI) approach for various modulation and coding schemes (MCS) in terms of coded bit error rate (BER) or block error rate (BLER) using different transmission schemes. This paper provides explanation and comparison of the two algorithms for single input single output (SISO), and single input multi-output (SIMO, 1X2) in OFDM systems. We calibrate the value of beta ($\beta$) in EESM using large number of channel realizations, here $\beta$ is a calibration constant. This paper also presents importance of beta value in EESM and how it improves the performance of OFDM wireless systems. We propose different modulation and coding schemes. Here we consider Standford university interim (SUI) channel models. Furthermore this paper also shows the detail observation of the two algorithms. Finally the conclusion review given for short summary.

• Journal of Convergence Society for SMB
• /
• v.6 no.4
• /
• pp.99-106
• /
• 2016

In this paper, we propose an adaptive FEC scheme in visible light communication using white LED. To this end, we investigate the red, green and blue mixing ratio of white LED in order to achieve the white color, and the mixing ratio of those wavelength can be defined as 4 types. Based on those properties, the FEC technique is applied to the wavelength band with the lowest mixing ratio according to mixing ratio types. At that point, we use a LDPC channel coding scheme as the FEC technique. Therefore, the proposed system can mitigate the reduction of data rate and improve total BER performance.