• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.709-711
• /
• 2003

The purpose of this study is to detect the damaged red pine trees by pine wilt disease using high resolution satellite image of IKONOS Geo. IKONOS images are segmented with eCognition image processing software. A segment based maximum likelihood classification was performed to delineate the pine stand. The pine stands are regarded as a potential damage area. In order to develop a methodology to detect the location of damaged trees from the high resolution satellite image, black and white aerial photographs were used as a simulated image. The developed method based on filtering technique. A local maximum filter was adapted to detect the location of individual tree. This report presents a part of the first year results of an ongoing project.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1987.11a
• /
• pp.86-88
• /
• 1987

Accurate detection of the voicved segment in speech signals is important for robust pitch extraction. This paper describes an explicit detection algorithmfor detecting the voiced segment in speech signals. Thsi algoithm is based on the fluctuation properties of maximum magnitudes in each frame of speech signals. The performance of this detector is evaluated and compared to that obtained from manually classifying 150 recorded digit utterances.

• Korean Journal of Remote Sensing
• /
• v.26 no.5
• /
• pp.477-487
• /
• 2010

In North Korea, forests were intensively degraded by forest land reclamation for food production and firewood collection since the mid-1970s. These degraded forests have to be certainly recovered for economic support, environmental protection and disaster prevention. In order to provide detailed land cover information of forest recovery project (A/R CDM), this study was focused to develop an improved classification method for degraded forest using 2.5m SPOT-5 pan-sharpened image. The degraded forest of North Korea shows various different types of texture. This study used GLCM texture bands of segmented image with spectral bands during forest cover classification. When scale factor 40/shape factor 0.3 was used as a parameter set to generate segment image, segment image was generated on suitable segment scale that could classify types of degraded forest. Forest land cover types were classified with an optimum band combination of Band1, Band2, band3, GLCM dissimilarity (band2), GLCM homogeneity (band2) and GLCM standard deviation (band3). Segment-based classification method using spectral bands and texture bands reached an 80.4% overall accuracy, but the method using only spectral bands yielded an 70.3% overall accuracy. As using spectral and texture bands, a classification accuracy of stocked forest and unstocked forest showed an increase of 23~25%. In this research, SPOT-5 pan-sharpened high-resolution satellite image could provide a very useful information for classifying the forest cover of North Korea in which field data collection was not available for ground truth data and verification directly. And segment-based classification method using texture information improved classification accuracy of degraded forest.

• Journal of Information Processing Systems
• /
• v.13 no.6
• /
• pp.1527-1543
• /
• 2017

MiRNA is a biological short sequence, which plays a crucial role in almost all important biological process. MiRNA patterns are common sequence segments of multiple mature miRNA sequences, and they are of significance in identifying miRNAs due to the functional implication in miRNA patterns. In the proposed approach, the primary miRNA patterns are produced from sequence alignment, and they are then cut into short segment miRNA patterns. From the segment miRNA patterns, the candidate miRNA patterns are selected based on estimated probability, and from which, the potential miRNA patterns are further selected according to the classification performance between authentic and artificial miRNA sequences. Three parameters are suggested that bi-nucleotides are employed to compute the estimated probability of segment miRNA patterns, and top 1% segment miRNA patterns of length four in the order of estimated probabilities are selected as potential miRNA patterns.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4E
• /
• pp.21-27
• /
• 1996

In this paper, we propose a discriminative training algorithm for the stochastic segment model (SSM) in continuous speech recognition. As the SSM is usually trained by maximum likelihood estimation (MLE), a discriminative training algorithm is required to improve the recognition performance. Since the SSM does not assume the conditional independence of observation sequence as is done in hidden Markov models (HMMs), the search space for decoding an unknown input utterance is increased considerably. To reduce the computational complexity and starch space amount in an iterative training algorithm for discriminative SSMs, a hybrid architecture of SSMs and HMMs is programming using HMMs. Given the segment boundaries, the parameters of the SSM are discriminatively trained by the minimum error classification criterion based on a generalized probabilistic descent (GPD) method. With the discriminative training of the SSM, the word error rate is reduced by 17% compared with the MLE-trained SSM in speaker-independent continuous speech recognition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.2
• /
• pp.117-126
• /
• 2019

Legacy study for detecting arrhythmia have mostly used nonlinear method to increase classification accuracy. Most methods are complex to process and manipulate data and have difficulties in classifying various arrhythmias. Therefore it is necessary to classify various arrhythmia based on short-term data. In this study, we propose a feature extraction based on auto regressive modeling and an premature contraction arrhythmia classification method using SVM., For this purpose, the R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval segment is modelled. Also, we classified Normal, PVC, PAC through SVM in realtime by extracting four optimal segment length and AR order. The detection and classification rate of R wave and PVC is evaluated through MIT-BIH arrhythmia database. The performance results indicate the average of 99.77% in R wave detection and 99.23%, 97.28%, 96.62% in Normal, PVC, PAC classification.

• Aerospace Engineering and Technology
• /
• v.6 no.1
• /
• pp.213-221
• /
• 2007

This paper showed how to analysis the object-based classification for wildfire fuel type map using Hyperion hyperspectral remote sensing data acquired in April, 2002 and compared the results of the object-based classification with the results of the pixel-based classification. Our methodological approach for wildfire fuel type map firstly processed correcting abnormal pixels and atypical bands and also calibrating atmospheric noise for enhanced image quality. Fuel type map is characterized by the results of the spectral mixture analysis(SMA). Object-based approach was based on segment-based endmember selection, while pixel-based method used standard SMA. To validate and compare, we used true-color high resolution orthoimagery.

• Journal of Fisheries and Marine Sciences Education
• /
• v.25 no.2
• /
• pp.364-374
• /
• 2013

When the shorelines were contaminated by oil, oiled shorelines were assessed systematically by SCAT and guideline of cleanup activities and shorelines treatment endpoints based on SCAT were established and operated in case of well developed countries like USA and Canada. However, shorelines cleanup assessment technique are not established clearly in our country. In this study, we studied on the shorelines cleanup assessment technique suitable for Korean shorelines feature. That is, composition of SCAT organization, classification of shorelines and division of oiled shorelines by segment that are elements of SCAT were studied, and we suggest the measures related to above elements suitable for shorelines feature of our country.

• Speech Sciences
• /
• v.8 no.1
• /
• pp.77-91
• /
• 2001

This paper investigates the timing of Korean spoken in a news-reading speech style in order to improve the naturalness of durations used in Korean speech synthesis. Each segment in a corpus of 671 read sentences was annotated with 69 segmental and prosodic features so that the measured duration could be correlated with the context in which it occurred. A CART model based on the features showed a correlation coefficient of 0.79 with an RMSE (root mean squared prediction error) of 23 ms between actual and predicted durations in reserved test data. These results are comparable with recent published results in Korean and similar to results found in other languages. An analysis of the classification tree shows that phrasal structure has the greatest effect on the segment duration, followed by syllable structure and the manner features of surrounding segments. The place features of surrounding segments only have small effects. The model has application in Korean speech synthesis systems.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.05
• /
• pp.293-297
• /
• 1996

For the representative beat calculation and efficient rhythm analysis new method, that is, QRS typification were proposed. A problem that were resulted from pattern classification based on binary logic could be solved out by the fuzzy clustering and classification nodes could be reduced by using the proposed new feature vector. The accurate representative beat could be obtained by excluding the ST-T segment that happened outlier through ST-T segment typification procedure.