• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.3
• /
• pp.187-194
• /
• 2017

The present study introduces a method to parallelize k-means clustering algorithm for fast unsupervised classification of large satellite imagery. Known as a representative algorithm for unsupervised classification, k-means clustering is usually applied to a preprocessing step before supervised classification, but can show the evident advantages of parallel processing due to its high computational intensity and less human intervention. Parallel processing codes are developed by using multi-threading based on OpenMP. In experiments, a PC of 8 multi-core integrated CPU is involved. A 7 band and 30m resolution image from LANDSAT 8 OLI and a 8 band and 10m resolution image from Sentinel-2A are tested. Parallel processing has shown 6 time faster speed than sequential processing when using 10 classes. To check the consistency of parallel and sequential processing, centers, numbers of classified pixels of classes, classified images are mutually compared, resulting in the same results. The present study is meaningful because it has proved that performance of large satellite processing can be significantly improved by using parallel processing. And it is also revealed that it easy to implement parallel processing by using multi-threading based on OpenMP but it should be carefully designed to control the occurrence of false sharing.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.533-536
• /
• 2019

의존 구문 분석은 문장 구성 성분 간의 의존 관계를 분석하는 태스크로, 자연어 이해의 대표적인 과제 중 하나이다. 본 논문에서는 한국어 의존 구문 분석의 성능 향상을 위해 Deep Bi-Affine Network와 Left to Right Dependency Parser를 적용하고, 새롭게 한국어의 언어적 특징을 반영한 Right to Left Dependency Parser 모델을 제안한다. 3개의 의존 구문 분석 모델에 단어 표현을 생성하는 방법으로 ELMo, BERT 임베딩 방법을 적용하고 여러 종류의 모델을 앙상블하여 세종 의존 구문 분석 데이터에 대해 UAS 94.50, LAS 92.46 성능을 얻을 수 있었다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.2
• /
• pp.19-29
• /
• 2011

Due to the development of web technologies and the increasing use of smart devices such as smart phone, in recent various web services are widely used in many application fields. In this environment, the topic of supporting personalized and intelligent web services have been actively researched, and an analysis technique on a web-click stream generated from web usage logs is one of the essential techniques related to the topic. In this paper, for efficient analyzing a web-click stream of sequences, a sequential pattern mining technique is proposed, which satisfies the basic requirements for data stream processing and finds a refined mining result. For this purpose, a concept of interesting sequential patterns with a time-interval constraint is defined, which uses not on1y the order of items in a sequential pattern but also their generation times. In addition, A mining method to find the interesting sequential patterns efficiently over a data stream such as a web-click stream is proposed. The proposed method can be effectively used to various computing application fields such as E-commerce, bio-informatics, and USN environments, which generate data as a form of data streams.

• The KIPS Transactions:PartB
• /
• v.12B no.1 s.97
• /
• pp.17-24
• /
• 2005

In this paper, we will show that a control search methodology is a alternative method of a sequential search which is difficult in finding books for arrangement at library or a bookstore when books are out of place. To solve the problem of the sequential search, we apply a edge operator and the Hough Transform to boundary of a taken photograph image book. We generate histogram by a projected image from boundary range of selected books and select title areas from this and possible areas which are a character number of title, authors, a publishing company and an array sequence. Finally, we can select the final possible area of a book location by a curve fitting and a regression line extraction, and show utility through experiment.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.5
• /
• pp.1371-1379
• /
• 1997

Undetectable faults in a digital circuit are faults that no input patterms can detect.Identifying these faults in test geferation process is very time- consuming especially for sequential circuits .In this paper we present a new algorithm to identify unedtectable faults in sequential cirouits .In the alorithm. we identify uninitializable fip-flops and then, faults that prevent intialization of the fkip-flops(FPIs)are identified, finally propagation path of the FPI is checked. Time complexity of this algorithm is porportional to the product of the number of flip flops with at lest a self loop and the number of gates in the circuit. Experiments were performed on the ISCAS89 benchmark ciruits to show the feadibility of the proposed algorithm.We could identify large amount of undetectable faults(up to 50% of the number of flip-flops)in circuits with uninitializable flip-flops. Consider-ing that most of the time in test generation is cinsumed in identifying undetecatable faults, performance of test generator can be improved by using this algorithm as a pre-processing of test generation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.271-278
• /
• 2004

In this paper, we propose a content-based audio genre classification algorithm that automatically classifies the query audio into five genres such as Classic, Hiphop, Jazz, Rock, Speech using digital sign processing approach. From the 20 seconds query audio file, the audio signal is segmented into 23ms frame with non-overlapped hamming window and 54 dimensional feature vectors, including Spectral Centroid, Rolloff, Flux, LPC, MFCC, is extracted from each query audio. For the classification algorithm, k-NN, Gaussian, GMM classifier is used. In order to choose optimum features from the 54 dimension feature vectors, SFS(Sequential Forward Selection) method is applied to draw 10 dimension optimum features and these are used for the genre classification algorithm. From the experimental result, we can verify the superior performance of the proposed method that provides near 90% success rate for the genre classification which means 10%∼20% improvements over the previous methods. For the case of actual user system environment, feature vector is extracted from the random interval of the query audio and it shows overall 80% success rate except extreme cases of beginning and ending portion of the query audio file.

• The KIPS Transactions:PartB
• /
• v.13B no.5 s.108
• /
• pp.553-560
• /
• 2006

Speech recognition has recently been investigated to produce more reliable recognition results in a noisy environment, by integrating diverse sources of information into the result derivation-level or producing new results through post-processing the prior recognition results. In this paper we propose a method which uses the user's usage patterns and the context information in speech command recognition for personal mobile devices to improve the recognition accuracy in a noisy environment. Sequential usage (or speech) patterns prior to the current command spoken are used to adjust the base recognition results. For the context information, we use the relevance between the current function of the device in use and the spoken command. Our experiment results show that the proposed method achieves about 50% of error correction rate over the base recognition system. It demonstrates the feasibility of the proposed method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.3
• /
• pp.170-175
• /
• 2009

In this paper, we propose real time automatic speaker verification (ASV) system to protect personal information on personal digital assistant (PDA) device. Recently, the capacity of PDA has extended and been popular, especially for mobile environment such as mobile commerce (M-commerce). However, there still exist lots of difficulties for practical application of ASV utility to PDA device because it requires too much computational complexity. To solve this problem, we apply the method to relieve the computational burden by performing the preprocessing such as spectral subtraction and speech detection during the speech utterance. Also by applying the hidden Markov model (HMM) optimal state alignment and the sequential probability ratio test (SPRT), we can get much faster processing results. The whole system implementation is simple and compact enough to fit well with PDA device's limited memory and low CPU speed.

• The Journal of the Korea Contents Association
• /
• v.13 no.6
• /
• pp.48-54
• /
• 2013

In these days, the state-of-art technologies employ the heterogeneous parallelization of CPU and GPU for fluid simulations in the field of computer graphics. In this paper, we present a novel CPU-GPU parallel algorithm that solves projection step of fluid simulation more efficiently than existing sequential CPU-GPU processing. Fluid simulation that requires high computational resources can be carried out efficiently by the proposed method.

• Journal of Communications and Networks
• /
• v.7 no.4
• /
• pp.417-428
• /
• 2005

The Voronoi diagram (VD) is the most suitable mechanism to find the nearest neighbor (NN) for mobile clients. In NN query processing, it is important to reduce the query response time, since a late query response may contain out-of-date information. In this paper, we study the issue of location dependent information services (LDISs) using a VD. To begin our study, we first introduce a broadcast-based spatial query processing methods designed to support NN query processing. In further sections, we introduce a generic method for location-dependent sequential prefetching and caching. The performance of this scheme is studied in different simulated environments. The core contribution of this research resides in our analytical proof and experimental results.