• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.5
• /
• pp.407-415
• /
• 2016

Recent wireless communication trends have emphasized the importance of energy-efficient transmission. In this paper, link adaptation with machine learning mechanism for maximum energy efficiency in multiple-input multiple-output orthogonal frequency division multiplexing(MIMO-OFDM) wireless system is considered. For reflecting frequency-selective MIMO-OFDM channels, two-dimensional capacity(2D-CAP) feature space is proposed. In addition, machine-learning-based bit and power adaptation(ML-BPA) algorithm that performs classification-based link adaptation is presented. Simulation results show that 2D-CAP feature space can represent channel conditions accurately and bring noticeable improvement in link adaptation performance. Compared with other feature spaces, including ordered postprocessing signal-to-noise ratio(ordSNR) feature space, 2D-CAP has distinguished advantages in either efficiency performance or computational complexity.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.106-109
• /
• 1997

For the practical isolated word recognition system, the ability to reject the out-of -vocabulary(OOV) is required. In this paper, we present a rejection method which uses the clustered phoneme modeling combined with postprocessing by likelihood ratio scoring. Our baseline speech recognition system was based on the whole-word continuous HMM. And 6 clustered phoneme models were generated using statistical method from the 45 context independent phoneme models, which were trained using the phonetically balanced speech database. The test of the rejection performance for speaker independent isolated words recogntion task on the 22 section names shows that our method is superior to the conventional postprocessing method, performing the rejection according to the likelihood difference between the first and second candidates. Furthermore, this clustered phoneme models do not require retraining for the other isolated word recognition system with different vocabulary sets.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.442-452
• /
• 2001

In this paper, we proposed a postprocessing algorithm for quantization effects reduction in block coded images using the block classification and adaptive filtering. The proposed method consists of classification, adaptive inter-block filtering, and intra-block filtering. First, each block is classified into one of seven classes based on the characteristics of 8$\times$8 DCT coefficients. Then each block boundary is filtered by adaptive inter-block fitters according to the block classification. finally for blocks which are classified into edge block, intra-block filtering is performed. Experimental results show that the proposed method gives better results than the conventional methods from both a subjective and an objective viewpoint.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.4
• /
• pp.65-77
• /
• 1999

There are two problems which will be processed to graft a continuous speech recognition results into natural language processing technique. First, the speaking's unit isn't consistent with text's spacing unit. Second, when it is to be pronounced the phonological alternation phenomena occur inside morphemes or among morphemes. In this paper, we implement the postprocessing system of a continuous speech recognition that above all, solve two problems using the eo-jeol generator and syllable recoveror and morphologically analyze the generated results and then correct the failed results through the corrector. Our system experiments with two kinds of speech corpus, i.e., a primary school text book and editorial corpus. The successful percentage of the former is 93.72%, that of the latter is 92.26%. As results of experiment, we verified that our system is stable regardless the sorts of corpus.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.8
• /
• pp.1782-1790
• /
• 2011

The goal of image processing is to improve the perceptual aspect and visual appearance of images for human viewers. The objectives of image enhancement vary according to its specific application and an image enhancement techniques used for a specific objective may not be accepted in some other applications. In this paper we review some of conventional enhancement techniques, such as histogram shrink, equalization, and the conservative adaptive contrast enhancement filter. And also, The adaptive contrast enhancement filter has optimized the applied values of variables which is configured rightly the medical image field. In the postprocessing, we used the histogram equalization method. As a result, the inputs which used a medical images has enhanced the edges of a result images which has applied the proposed filter. And also, because of the postprocessing, the image outlines has been lightened.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.9
• /
• pp.1702-1709
• /
• 1994

In the postprocessing of Hangul recognition system, the storage structure of contextual information is an important matter for the recognition rate and speed of the entire system. Trie in general is used to represent the context as word dictionary, but the memory space efficiency of the structure is low. Therefore we propose a new structure for word dictionary that has better space efficiency and the equivalent merits of trie. Because Hangul is a compound language, the language can be represented by phonemes or by characters. In the representation by phonemes(P-mode) the retrieval is fast, but the space efficiency is low. In the representation by characters(C-mode) the space efficiency is high, but the retrieval is slow. In this paper the two representation methods are combined to form a hybrid representation(H-mode). At first an optimal level for the combination is selected by two characteristic curves of node utilization and dispersion. Then the input words are represented with trie structure by P-mode from the first to the optimal level, and the rest are represented with sequentially linked list structure by C-mode. The experimental results for the six kinds of word set show that the proposed structure is more efficient. This result is based on the fact that the retrieval for H-mode is as fast as P-mode and the space efficiency is as good as C-mode.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.275-281
• /
• 2004

Geodetic surveying using precise GPS equipment are used without analysis with a statistical verification of GPS observed value and it was preformed by necessity to integration projection of digital topographic map and nautical Chart for integration geographic information system construction. The purpose of this study proposes method that improve accuracy of GPS observed value and direction that integrally manage digital topographic map and electronic nautical chart in analyzing the boundary line error between digital topographic map and nautical Chart. For improvement of the precision of GPS observed value, the author studied precision-analysis of GPS observed value by geometric strength and variance factor in 3 control points used in GPS network adjustment. This study compare the whole boundary point error When producing EDM measurement using this GPS observation results and setting digital topographic map and nautical chart by these boundary.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.5
• /
• pp.13-19
• /
• 2000

The blind segmentation method, which segments input speech data into recognition unit without any prior knowledge, plays an important role in continuous speech recognition system and corpus generation. As no prior knowledge is required, this method is rather simple to implement, but in general, it suffers from bad performance when compared to the knowledge-based segmentation method. In this paper, we introduce a method to improve the performance of a blind segmentation of Korean continuous speech by postprocessing the segment boundaries obtained from the blind segmentation. In the preprocessing stage, the candidate boundaries are extracted by a clustering technique based on the GLR(generalized likelihood ratio) distance measure. In the postprocessing stage, the final phoneme boundaries are selected from the candidates by utilizing a simple a priori knowledge on the syllabic structure of Korean, i.e., the maximum number of phonemes between any consecutive nuclei is limited. The experimental result was rather promising : the proposed method yields 25% reduction of insertion error rate compared that of the blind segmentation alone.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.1
• /
• pp.205-213
• /
• 2011

The Long Term Evolution (LTE) system is designed to provide a high quality data service for fast moving mobile users. It is based on the Orthogonal Frequency Division Multiplexing (OFDM) and relies its channel estimation on the training samples which are systematically built within the transmitting data. Either a preamble or a lattice type is used for the distribution of training samples and the latter suits better for the multipath fading channel environment whose channel frequency response (CFR) fluctuates rapidly with time. In the lattice-type structure, the estimation of the CFR makes use of the least squares estimate (LSE) for each pilot samples, followed by an interpolation both in time-and in frequency-domain to fill up the channel estimates for subcarriers corresponding to data samples. All interpolation schemes should rely on the pilot estimates only, and thus, their performances are bounded by the quality of pilot estimates. However, the additive noise give rise to high fluctuation on the pilot estimates, especially in a communication environment with low signal-to-noise ratio. These high fluctuations could be monitored in the alternating high values of the first forward differences (FFD) between pilot estimates. In this paper, we analyzed statistically those FFD values and propose a postprocessing algorithm to suppress high fluctuations in the noisy pilot estimates. The proposed method is based on a localized adaptive moving-average filtering. The performance of the proposed technique is verified on a multipath environment suggested on a 3GPP LTE specification. It is shown that the mean-squared error (MSE) between the actual CFR and pilot estimates could be reduced up to 68% from the noisy pilot estimates.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.1
• /
• pp.1-11
• /
• 2002

This study set up a purpose in the efficient utilization of security target objects. This purpose is the following: Firstly, this study analyzed problem about deleted areas for security described on aerial photography image. Secondly, this study made clustering and labeling to recognize censored areas of image. Finally, this study tried to maximize various utilizability of digital image data through postprocessing algorithm. Based on these courses, the results of this study appeared that brightness value of image increased depending on topography and quantities of topographic features. It was estimated that these was able to utilized by useful estimative data in judging information of topography and topographic features included in the total image. Besides, in the image recognition and postprocessing, the better result value was not elicited than in a mountainous region. Because it was included that a lots of topography and topographic features was similarly recognized with the process for deletion of the existing security target objects in urban and suburb region. This result appeared that the topography and quantities of topographic features absolutely affected the recognition and processing of image.