• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.130-138
• /
• 2021

This paper presents an effective structure by applying various normalization to Convolutional Neural Networks (CNN) for seismic event classification. Normalization techniques can not only improve the learning speed of neural networks, but also show robustness to noise. In this paper, we analyze the effect of input data normalization and hidden layer normalization on the deep learning model for seismic event classification. In addition an effective model is derived through various experiments according to the structure of the applied hidden layer. As a result of various experiments, the model that applied input data normalization and weight normalization to the first hidden layer showed the most stable performance improvement.

• Research in Mathematical Education
• /
• v.9 no.1 s.21
• /
• pp.11-24
• /
• 2005

Problem solving is an important aspect of learning mathematics and has been extensively researched into by mathematics educators. In this paper we analyze the difficulties students encounter in various steps involved in solving problems involving physical and geometrical applications of mathematical concepts. Our research shows that, generally students, in spite of possessing adequate theoretical knowledge, have difficulties in identifying the hidden data present in the problems which are crucial links to their successful resolutions. Our research also shows that students have difficulties in solving problems involving constructions and use of symmetry.

• Journal of Multimedia Information System
• /
• v.4 no.1
• /
• pp.19-26
• /
• 2017

The compression of video for both full HD and UHD requires the inclusion of extra vertical lines to every video frame, named as the DTV essential hidden area (DEHA), for the effective functioning of the MPEG-2/4/H encoder, stream, and decoder. However, while the encoding/decoding process is dependent on the DEHA, the DEHA is conventionally viewed as a redundancy in terms of channel utilization or storage efficiency. This paper proposes a block mode DEHA method to more effectively utilize the DEHA. Partitioning video block images and then evenly filling the representative DEHA macroblocks with the average DC coefficient of the active video macroblock can minimize the amount of DEHA data entering the compressed video stream. Theoretically, this process results in smaller DEHA data entering the video stream. Experimental testing of the proposed block mode DEHA method revealed a slight improvement in the quality of the active video. Outside of this technological improvement to video quality, the attractiveness of the proposed DEHA method is also heightened by the ease that it can be implemented with existing video encoders.

• Journal of Positioning, Navigation, and Timing
• /
• v.8 no.4
• /
• pp.193-200
• /
• 2019

The auto-encoder network which is a good candidate to handle the modeling of the signal strength attenuation is designed for denoising and compensating the distortion of the received data. It provides a non-linear mapping function by iteratively learning the encoder and the decoder. The encoder is the non-linear mapping function, and the decoder demands accurate data reconstruction from the representation generated by the encoder. In addition, the adaptive network width which supports the automatic generation of new hidden nodes and pruning of inconsequential nodes is also implemented in the proposed algorithm for increasing the efficiency of the algorithm. Simulation results show that the proposed method can improve the neural network training surface to achieve the highest possible accuracy of the signal modeling compared with the conventional modeling method.

• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.155-166
• /
• 2002

Neural networks have been studied as a popular tool for classification and they are very flexible. Also, they are used for many applications of pattern classification and pattern recognition. This paper focuses on Bayesian approach to feed-forward neural networks with single hidden layer of units with logistic activation. In this model, we are interested in deciding the number of nodes of neural network model with p input units, one hidden layer with m hidden nodes and one output unit in Bayesian setup for fixed m. Here, we use the latent variable into the prior of the coefficient regression, and we introduce the 'sequential step' which is based on the idea of the data augmentation by Tanner and Wong(1787). The MCMC method(Gibbs sampler and Metropolish algorithm) can be used to overcome the complicated Bayesian computation. Finally, a proposed method is applied to a simulated data.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.2
• /
• pp.132-140
• /
• 2002

A momentum backpropagation neural network is prepared to carry out real-time dynamics simulations of a passenger car. A full-car model of fifteen degrees of freedom was constructed for vehicle dynamics analysis. Human body dynamics analysis was performed for a male driver(50 percentile Korean adult) restrained by a three point seatbelt system. The trained data using the neural network were obtained using a dynamic solver, ADAMS . The neural network were formed based on the dynamics of the simulator. The optimized hidden layer was obtained by selecting the optimal number of hidden layers. The driving scenario including bump passing and lane changing has been used for the estimation of the proposed neural network. A comparison between the trained data and neural network outputs is found to be satisfactory to show the applicability of the suggested approach.

• Journal of Information Processing Systems
• /
• v.8 no.2
• /
• pp.301-314
• /
• 2012

In this paper, two new approaches to align English-Arabic sentences in bilingual parallel corpora based on the Multi-Class Support Vector Machine (MSVM) and the Hidden Markov Model (HMM) classifiers are presented. A feature vector is extracted from the text pair that is under consideration. This vector contains text features such as length, punctuation score, and cognate score values. A set of manually prepared training data was assigned to train the Multi-Class Support Vector Machine and Hidden Markov Model. Another set of data was used for testing. The results of the MSVM and HMM outperform the results of the length based approach. Moreover these new approaches are valid for any language pairs and are quite flexible since the feature vector may contain less, more, or different features, such as a lexical matching feature and Hanzi characters in Japanese-Chinese texts, than the ones used in the current research.

• Genomics & Informatics
• /
• v.12 no.4
• /
• pp.145-150
• /
• 2014

Recent technical advances, such as chromatin immunoprecipitation combined with DNA microarrays (ChIp-chip) and chromatin immunoprecipitation-sequencing (ChIP-seq), have generated large quantities of high-throughput data. Considering that epigenomic datasets are arranged over chromosomes, their analysis must account for spatial or temporal characteristics. In that sense, simple clustering or classification methodologies are inadequate for the analysis of multi-track ChIP-chip or ChIP-seq data. Approaches that are based on hidden Markov models (HMMs) can integrate dependencies between directly adjacent measurements in the genome. Here, we review three HMM-based studies that have contributed to epigenetic research, from a computational perspective. We also give a brief tutorial on HMM modelling-targeted at bioinformaticians who are new to the field.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.327-328
• /
• 2014

클라우드 컴퓨팅 환경에서는 시스템의 성능 및 비용적인 측면에서 정보 공유의 용이성, 장소의 제약성 최소화, 저장 공간의 효율적 사용을 위해 분산 파일시스템을 이용하고 있다. 하지만 현재 HDFS의 복제 정책은 모든 데이터에 3개의 복제복을 유지하도록 하고 있다. 하지만 이러한 정책은 데이터의 중요도, 이용빈도수를 반영하지 못한 정책으로 상이한 서비스 품질 및 신뢰성 수준을 반영하지 못한다. 본 논문에서는 Hidden Markov Model을 이용하여 데이터의 이용 빈도수에 따라 복사본의 개수를 조절하는 알고리즘을 제안한다.

• Speech Sciences
• /
• v.7 no.4
• /
• pp.11-26
• /
• 2000

In this paper, we propose the HMM with the MIN module. Because initial and re-estimated variance vectors are important elements for performance in HMM recognition systems, we propose a method which compensates for the mismatched statistical feature of training and test data. The MIN module function is a differentiable function similar to the sigmoid function. Unlike a continuous density function, it does not include variance vectors of the data set. The proposed hybrid HMM/MIN module is a unified network in which the observation probability in the HMM is replaced by the MIN module neural network. The parameters in the unified network are re-estimated by the gradient descent method for the Maximum Likelihood (ML) criterion. In estimating parameters, the variance vector is not estimated because there is no variance element in the MIN module function. The experiment was performed to compare the performance of the proposed HMM and the conventional HMM. The experiment measured an isolated number for speaker independent recognition.