• Journal of Korea Multimedia Society
• /
• v.11 no.10
• /
• pp.1325-1337
• /
• 2008

The difference of environments between training and recognition is the major reason of degradation of speech recognition. To solve this mismatch of environments, various noise processing methods have been studied. Among them, ERN(log-Energy dynamic Range Normalization) and SEN(Silence Energy Normalization) for normalization of log energy features show better performance than others. However, these methods have a problem that they can hardly achieve normalization for the relatively higher values of log energy features and the environmental mismatch caused by this problem becomes bigger especially in low SNR environments. To solve these problems, we propose applying ARMA filter as post-processing for smoothing log energy features by calculating the moving average in auto-regression scheme. From the recognition results conducted on Aurora 2.0 DB, the proposed method shows improved recognition results comparing with conventional methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.6
• /
• pp.283-288
• /
• 2016

In recent years, there have been many research efforts on Big Data, and many companies developed a variety of relevant products. Accordingly, we are able to store and analyze a large volume of log data, which have been difficult to be handled in the traditional computing environment. To handle a large volume of log data, which rapidly occur in multiple servers, in this paper we design a new data storage architecture to efficiently analyze those big log data through Apache Hive. We then design and implement anomaly detection methods, which identify abnormal status of servers from log data, based on moving average and 3-sigma techniques. We also show effectiveness of the proposed detection methods by demonstrating that our methods identifies anomalies correctly. These results show that our anomaly detection is an excellent approach for properly detecting anomalies from Hadoop log data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.34.1-34
• /
• 2002

1. Introduction 2. Focus of Expansion 3. Log-Polar Mapping 4. Egomotion and Optical Flow 5. Experimental Results 6. Conclusion. References.

• KIISE Transactions on Computing Practices
• /
• v.23 no.2
• /
• pp.128-133
• /
• 2017

In recent years, the number of systems for the analysis of large volumes of data is increasing. Hadoop, a representative big data system, stores and processes the large data in the distributed environment of multiple servers, where system-resource management is very important. The authors attempted to detect anomalies from the rapid changing of the log data that are collected from the multiple servers using simple but efficient anomaly-detection techniques. Accordingly, an Apache Hive storage architecture was designed to store the log data that were collected from the multiple servers in the Hadoop ecosystem. Also, three anomaly-detection techniques were designed based on the moving-average and 3-sigma concepts. It was finally confirmed that all three of the techniques detected the abnormal intervals correctly, while the weighted anomaly-detection technique is more precise than the basic techniques. These results show an excellent approach for the detection of log-data anomalies with the use of simple techniques in the Hadoop ecosystem.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.753-758
• /
• 2017

The ray-shooting problem is to find the first intersection point on the surface of given geometric objects where a ray moving along a straight line hits. Since rays are usually given in the form of queries, this problem is typically solved as follows. First, a data structure for a collection of objects is constructed as preprocessing. Then, the answer for each query ray is quickly computed using the data structure. In this paper, we consider the ray-shooting problem about the set of vertical line segments on the x-axis. We present a new data structure called a convex layer tree for n vertical line segments given by input. This is a tree structure consisting of layers of convex hulls of vertical line segments. It can be constructed in O(n log n) time and O(n) space and is easy to implement. We also present an algorithm to solve each query in O(log n) time using this data structure.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.8A
• /
• pp.671-678
• /
• 2005

This paper proposed symbol rate method which does not require a priori knowledge on the symbol rate and simplified modulation identification method to classify BPSK, QPSK, 8PSK signal. In order to estimate the unknown symbol rate, sliding FFT and simple moving average to estimate the spectrum of the signals is utilized, and sliding window and decimation, LPF blcok to estimate the proper symbol rate is used. Although conventional modulation ID method must use SNR value as the test statistics, the receiver cannot estimate the SNR value since the receiver cannot know the modulation type at the start of communication, and bit resolution is high due to using nonlinear function such as log, cosh. Therefore, we proposed the simplified fixed SNR value method. The performance of symbol rate estimation and modulation ID is shown using Monte Carlo computer simulation. This paper show that symbol rate estimation also has good performance in low SNR, and proposed simplified fixed SNR method has almost equivalent performance compared to conventional method.

• Geophysics and Geophysical Exploration
• /
• v.10 no.3
• /
• pp.183-190
• /
• 2007

The site effects of seismic stations were evaluated by conducting a simultaneous inversion of the stochastic point-source ground-motion model (STGM model; Boore, 2003) parameters based on the accumulated dataset of horizontal shear-wave Fourier spectra. A model parameter $K_0$ and frequency-dependent site amplification function A(f) were used to express the site effects. Once after a H/V ratio of the Fourier spectra was used as an initial estimate of A(f) for the inversion, the final A(f) which is considered to be the result of combined effect of the crustal amplification and loca lsite effects was calculated by averaging the log residuals at the site from the inversion and adding the mean log residual to the H/V ratio. The seismic stations were classified into five classes according to $logA_{1-10}^{max}$(f), the maximum level of the site amplification function in the range of 1 Hz < f < 10 Hz, i.e., A: $logA_{1-10}^{max}$(f) < 0.2, B: 0.2 $\leq$ $logA_{1-10}^{max}$(f) < 0.4, C: 0.4 $\leq$ $logA_{1-10}^{max}$(f) < 0.6, D: 0.6 $\leq$ $logA_{1-10}^{max}$(f) < 0.8, E: 0.8 $\leq$ $logA_{1-10}^{max}$(f). Implication of the classified result was supported by observing a shift of the dominant frequency of average A(f) for each classified stations as the class changes. Change of site classes after moving seismic stations to a better site condition was successfully described by the result of the station classification. In addition, the observed PGA (Peak Ground Acceleration)-values for two recent moderate earthquakes were well classified according to the proposed station classes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.737-743
• /
• 2017

The intelligent life-log system proposed in this paper is intended to identify and record a myriad of everyday life information as to the occurrence of various events based on when, where, with whom, what and how, that is, a wide variety of contextual information involving person, scene, ages, emotion, relation, state, location, moving route, etc. with a unique tag on each piece of such information and to allow users to get a quick and easy access to such information. Context awareness generates and classifies information on a tag unit basis using the auto-tagging technology and biometrics recognition technology and builds a situation information database. In this paper, we developed an active modeling method and an application that recognizes expressionless and smile expressions using lip lines to automatically record emotion information.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.1
• /
• pp.61-69
• /
• 2002

Active stereo vision system allows us to localize a target object by passing only the features of small disparities without heavy computation for identifying the target. This simple method, however, is not applicable to the situations where a distracting background is included or the target and other objects are located on the zero disparity area simultaneously To alleviate these problems, we combined filtering with foveation which employs high resolution in the center of the visual field and suppresses the periphery which is usually less interesting. We adopted an image pyramid or log-polar transformation for foveated imaging representation. We also extracted the stereo disparity of the target by using projection to keep the stereo disparity small during tracking. Our experiments show that log-polar transformation is superior to either an image pyramid or traditional method in separating a target from the distracting background and fairly enhances the tracking performance.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.747-751
• /
• 2017

The log has variable informations that are important and necessary to manage a network when accessed to network servers. These informations are used to reduce a cost and efficient manage a network through the meaningful prediction information extraction from the amount of user access. And, the network manager can instantly monitor the status of CPU, memory, disk usage ratio on network using the SNMP. In this paper, firstly, we have accumulated and analysed the 6 network logs and extracted the informations that used to predict the amount of user access. And then, we experimented the prediction simulation with the time series analysis such as moving average method and exponential smoothing. Secondly, we have simulated the usage ration of CPU, memory, and disk using Xian SNMP simulator and extracted the OID for the time series prediction of CPU, memory, and disk usage ration. And then, we presented the visual result of the variable experiments through the Excel and R programming language.