• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.5
• /
• pp.64-75
• /
• 2000

This paper proposes a color sample selection method that produces a uniform distribution in the display gamut plus a color reproduction method for using a uniform color sample In contrast to the conventional method, the proposed uniform color samples are selected m CIELAB, a device-independent color space, instead of RGB (red, green, and yellow) or CMY (cyan, magenta, and yellow) space, device-dependent color spaces To evaluate the performance of the proposed color samples, they were applied to color space conversion using both a regression model and neural network As a result, in the case of a color sample of the same size, the color space conversion method using the proposed samples showed a lower color difference for color conversions using either neural or regression.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.1-7
• /
• 2007

In order to recognize a vehicle license plate, the region of the license plate should be extracted from a vehicle image. Then, character region should be separated from the background image and characters are recognized using some neural networks with selected feature vectors. Of course, choice of feature vectors which serve as the basis of the character recognition has an important effect on recognition result as well as reduction of data amount. In this paper, we propose a novel feature extraction method in which number images are decomposed into linear combination of eigennumbers and show the validity of this method by applying to the recognition of numeric characters in license plates. The experimental results show the recognition rate of 95.3% for about 500 vehicle images with multi-layer perceptron neural network in the eigennumber space. Compared with the conventional mesh feature, it shows a better recognition rate by 5%.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.46-63
• /
• 1995

This thesis described an unlimited vocabulary connected speech recognition system using Time Delay Neural Network(TDNN). The recognition unit is the diphone unit which includes the transition section of two phonemes, and the number of diphone unit is 329. The recognition processing of korean connected speech is composed by three part; the feature extraction section of the input speech signal, the diphone recognition processing and post-processing. In the feature extraction section, the extraction of diphone interval in input speech signal is carried and then the feature vectors of 16th filter-bank coefficients are calculated for each frame in the diphone interval. The diphone recognition processing is comprised by the three stage hierachical structure and is carried using 30 Time Delay Neural Networks. particularly, the structure of TDNN is changed so as to increase the recognition rate. The post-processing section, mis-recognized diphone strings are corrected using the probability of phoneme transition and the probability o phoneme confusion and then the eojeols (Korean word or phrase) are formed by combining the recognized diphones.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.615-621
• /
• 2020

In this paper, we propose a multi-site based earthquake event classification method using graph convolution networks. In the traditional earthquake event classification methods using deep learning, they used single-site observation to estimate seismic event class. However, to achieve robust and accurate earthquake event classification on the seismic observation network, the method using the information from the multi-site observations is needed, instead of using only single-site data. Firstly, our proposed model employs convolution neural networks to extract informative embedding features from the single-site observation. Secondly, graph convolution networks are used to integrate the features from several stations. To evaluate our model, we explore the model structure and the number of stations for ablation study. Finally, our multi-site based model outperforms up to 10 % accuracy and event recall rate compared to single-site based model.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.556-578
• /
• 2020

There are many different researches about how to analyze issues based on real-time news streams. But, there are few researches which analyze issues hierarchically from news articles and even a previous research of hierarchical issue analysis make clustering speed slower as the increment of news articles. In this paper, we propose a hierarchical and incremental clustering for semi real-time issue analysis on news articles. We trained siamese neural network based weighted cosine similarity model, applied this model to k-means algorithm which is used to make word clusters and converted news articles to document vectors by using these word clusters. Finally, we initialized an issue cluster tree from document vectors, updated this tree whenever news articles happen, and analyzed issues in semi real-time. Through the experiment and evaluation, we showed that up to about 0.26 performance has been improved in terms of NMI. Also, in terms of speed of incremental clustering, we also showed about 10 times faster than before.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1299-1311
• /
• 2017

Sounds based machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines using the sounds emitted by these machines. Conventional methods that use mathematical models have been found inaccurate because of the complexity of the industry machinery systems and the obvious existence of nonlinear factors such as noises. Therefore, any fault diagnosis issue can be treated as a pattern recognition problem. We present here an automatic fault diagnosis system of hand drills using discrete wavelet transform (DWT) and pattern recognition techniques such as principal component analysis (PCA) and artificial neural networks (ANN). The diagnosis system consists of three steps. Because of the presence of many noisy patterns in our signals, we first conduct a filtering analysis based on DWT. Second, the wavelet coefficients of the filtered signals are extracted as our features for the pattern recognition part. Third, PCA is performed over the wavelet coefficients in order to reduce the dimensionality of the feature vectors. Finally, the very first principal components are used as the inputs of an ANN based classifier to detect the wear on the drills. The results show that the proposed DWT-PCA-ANN method can be used for the sounds based automated diagnosis system.

• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1165-1173
• /
• 2017

Deep learning method, which is one of the most famous machine learning algorithms, has proven its applicability in various applications and is widely used in digital signal processing. However, it is difficult to apply deep learning technology to IoT devices with limited CPU performance and memory capacity, because a large number of training samples requires a lot of memory and computation time. In particular, if the Arduino with a very small memory capacity of 2K to 8K, is used, there are many limitations in implementing the algorithm. In this paper, we propose a method to optimize the ELM algorithm, which is proved to be accurate and efficient in various fields, on Arduino board. Experiments have shown that multi-class learning is possible up to 15-dimensional data on Arduino UNO with memory capacity of 2KB and possible up to 42-dimensional data on Arduino MEGA with memory capacity of 8KB. To evaluate the experiment, we proved the effectiveness of the proposed algorithm using the data sets generated using gaussian mixture modeling and the public UCI data sets.

• Journal of Internet Computing and Services
• /
• v.17 no.5
• /
• pp.97-110
• /
• 2016

Cryptanalysis is very important step for auditing and checking strength of any cryptosystem. Some of these cryptosystem ensures confidentiality and security of large information exchange from source to destination using symmetric key cryptography. The cryptanalyst investigates the strengths and identifies weakness key as well as enciphering algorithm. With increase in key size the time and effort required to guess the correct key increases so trend is increase key size from 8, 16, 24, 32, 56, 64, 128 and 256 bits to strengthen the cryptosystem and thus algorithm continues without compromise on the cost of time and computation. Automatic Variable Key (AVK) approach is an alternative to the approach of fixing up key size and adding security level with key variability adds new dimension in the development of secure cryptosystem. Likewise, whenever any new cryptographic method is invented to replace per-existing vulnerable cryptographic method, its deep analysis from all perspectives (Hacker / Cryptanalyst as well as User) is desirable and proper study and evaluation of its performance is must. This work investigates AVK based cryptic techniques, in future to exploit benefits of advances in computational methods like ANN, GA, SI etc. These techniques for cryptanalysis are changing drastically to reduce cryptographic complexity. In this paper a detailed survey and direction of development work has been conducted. The work compares these new methods with state of art approaches and presents future scope and direction from the cryptic mining perspectives.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.83-86
• /
• 2019

도시화 과정에서 도시의 생활폐기물 문제가 빠르게 증가되고 있고, 효과적이지 못한 생활폐기물 관리는 도시의 오염을 악화시키고 물리적인 환경오염과 경제적인 부분에서 극심한 문제들을 야기시킬 수 있다. 게다가 부피가 커서 관리하기 힘든 대형 생활폐기물들이 증가하여 도시 발전에도 방해가 된다. 생활폐기물을 처리하는데 있어 대형 생활폐기물 품목에 대해서는 요금을 청구하여 처리한다. 다양한 유형의 대형 생활폐기물을 수동으로 분류하는 것은 시간과 비용이 많이 든다. 그 결과 대형 생활폐기물을 자동으로 분류하는 시스템을 도입하는 것이 중요하다. 본 논문에서는 대형 생활폐기물 분류를 위한 시스템을 제안하며, 이 논문의 4 가지로 분류된다. 1) 높은 정확도와 강 분류(roust classification) 수행에 적합한 Convolution Neural Network(CNN) 모델 중 VGG-19, Inception-V3, ResNet50 의 정확도와 속도를 비교한다. 제안된 20 개의 클래스의 대형 생활폐기물의 데이터 셋(data set)에 대해 가장 높은 분류의 정확도는 86.19%이다. 2) 불균형 데이터 문제를 처리하기 Class Weight VGG-19(CW-VGG-19)와 Extreme Gradient Boosting VGG-19 두 가지 방법을 사용하였다. 3) 20 개의 클래스를 포함하는 데이터 셋을 수동으로 수집 및 검증하였으며 각 클래스의 컬러 이미지 수는 500 개 이상이다. 4) 딥 러닝(Deep Learning) 기반 모바일 애플리케이션을 개발하였다.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.77-97
• /
• 2017

A recent sharp increase of the biomedical literature causes researchers to struggle to grasp the current research trends and conduct creative studies based on the previous results. In order to alleviate their difficulties in keeping up with the latest scholarly trends, numerous attempts have been made to develop specialized analytic services that can provide direct, intuitive and formalized scholarly information by using various text mining technologies such as information extraction and event detection. This paper introduces and evaluates total 8 Convolutional Neural Network (CNN) models for extracting biomedical events from academic abstracts by applying various feature utilization approaches. Also, this paper conducts performance comparison evaluation for the proposed models. As a result of the comparison, we confirmed that the Entity-Type-Fully-Connected model, one of the introduced models in the paper, showed the most promising performance (72.09% in F-score) in the event classification task while it achieved a relatively low but comparable result (21.81%) in the entire event extraction process due to the imbalance problem of the training collections and event identify model's low performance.