• ETRI Journal
• /
• v.46 no.1
• /
• pp.127-136
• /
• 2024

The Korean language has written (formal) and spoken (phonetic) forms that differ in their application, which can lead to confusion, especially when dealing with numbers and embedded Western words and phrases. This fact makes it difficult to automate Korean speech recognition models due to the need for a complete transcription training dataset. Because such datasets are frequently constructed using broadcast audio and their accompanying transcriptions, they do not follow a discrete rule-based matching pattern. Furthermore, these mismatches are exacerbated over time due to changing tacit policies. To mitigate this problem, we introduce a data-driven Korean spoken-to-written transcription conversion technique that enhances the automatic conversion of numbers and Western phrases to improve automatic translation model performance.

• Journal of Astronomy and Space Sciences
• /
• v.25 no.2
• /
• pp.157-166
• /
• 2008

We have investigated a statistical relationship between sawtooth oscillations and geomagnetic storms during 2000-2004. First of all we selected a total of 154 geomagnetic storms based on the Dst index, and distinguished between different drivers such as Coronal Mass Ejection (CME) and Co-rotating Interaction Region (CIR). Also, we identified a total of 48 sawtooth oscillation events based on geosynchronous energetic particle data for the same 2000-2004 period. We found that out of the 154 storms identified, 47 storms indicated the presence of sawtooth oscillations. Also, all but one sawtooth event identified occurred during a geomagnetic storm interval. It was also found that sawtooth oscillation events occur more frequently for storms driven by CME $({\sim}62%)$ than for storms driven by CIR $({\sim}30%)$. In addition, sawtooth oscillations occurred mainly $({\sim}82%)$ in the main phase of storms for CME-driven storms while they occurred mostly $({\sim}78%)$ during the storm recovery phase for CIR-driven storms. Next we have examined the average characteristics of the Bz component of IMF, and solar wind speed, which were the main components for driving geomagnetic storm. We found that for most of the sawtooth events, the IMF Bz corresponds to -15 to 0 nT and the solar wind speed was in the range of $400{\sim}700km/s$. We found that there was a weak tendency that the number of teeth for a given sawtooth event interval was proportional to the southward IMF Bz magnitude.

• The KIPS Transactions:PartA
• /
• v.11A no.2
• /
• pp.129-142
• /
• 2004

As the Internet gets faster, the demand for high-speed routers that are capable of forwarding more than giga bits of data per second keeps increasing. In the previous research, Bitmap Trie algorithm was developed to rapidly execute LPM(longest prefix matching) process which is Well known as the Severe performance bottleneck. In this paper, we introduce a novel algorithm that drastically enhanced the performance of Bitmap. Trie algorithm by applying three techniques. First, a new table called the Count Table was devised. Owing to this table, we successfully eliminated shift operations that was the main cause of performance degradation in Bitmap Trie algorithm. Second, memory utilization was improved by removing redundant forwarding information from the Transfer Table. Lastly. the range of prefix lookup was diversified to optimize data accesses. On the other hand, the processing delays were classified into three categories according to their causes. They were, then, measured through the execution-driven simulation that provides the higher quality of the results than any other simulation techniques. We tried to assure the reliability of the experimental results by comparing with those that collected from the real system. Finally the Enhanced Bitmap Trie algorithm reduced 82% of time spent in previous algorithm.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.548-555
• /
• 2021

This paper outlines the basic concepts, approaches and research trends of fault diagnosis and fault tolerant control applied to industrial processes, facilities, and motor drives. The main role of fault diagnosis for industrial processes is to create effective indicators to determine the defect status of the process and then take appropriate measures against failures or hazadous accidents. The technologies of fault detection and diagnosis have been developed to determine whether a process has a trend or pattern, or whether a particular process variable is functioning normally. Firstly, data-driven based and model-based techniques were described. Secondly, fault detection and diagnosis techniques for industrial processes are described. Thirdly, passive and active fault tolerant control techniques are considered. Finally, major faults occurring in AC motor drives were listed, described their characteristics and fault diagnosis and fault tolerant control techniques are outlined for this purpose.

• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.346-358
• /
• 2018

Objectives: The association between obstructive sleep apnea (OSA) and mortality or serious cardiovascular events over a long period of time is not clearly understood. The aim of this observational study was to estimate the clinical effectiveness of continuous positive airway pressure (CPAP) treatment on an outcome variable combining mortality, acute myocardial infarction (AMI), and cerebrovascular insult (CVI) during a follow-up period of 15.5 years ($186{\pm}58$ months). Methods: The data set consisted of 978 patients with an apnea-hypopnea index (AHI) ${\geq}5.0$. One-third had used CPAP treatment. For the first time, a data-driven causal Bayesian network (DDBN) and a hypothesis-driven causal Bayesian network (HDBN) were used to investigate the effectiveness of CPAP. Results: In the DDBN, coronary heart disease (CHD), congestive heart failure (CHF), and diuretic use were directly associated with the outcome variable. Sleep apnea parameters and CPAP treatment had no direct association with the outcome variable. In the HDBN, CPAP treatment showed an average improvement of 5.3 percentage points in the outcome. The greatest improvement was seen in patients aged ${\leq}55$ years. The effect of CPAP treatment was weaker in older patients (>55 years) and in patients with CHD. In CHF patients, CPAP treatment was associated with an increased risk of mortality, AMI, or CVI. Conclusions: The effectiveness of CPAP is modest in younger patients. Long-term effectiveness is limited in older patients and in patients with heart disease (CHD or CHF).

• Journal of the korean society of oceanography
• /
• v.32 no.2
• /
• pp.75-84
• /
• 1997

Relation between the length scale and the wall proximity function in the Mellor-Yamada level 2.5 turbulence closure model has been investigated through various experiments using a range of wall proximity functions. The model performance has been evaluated quantitatively by comparing with laboratory data for wind-driven flow (Baines and Knapp, 1965) and for open-channel flows without and with adverse wind action (Tsuruya, 1985). Comparison shows that a symmetric wall proximity function used by Blumberg and Mellor(1987) gives rise to current profiles with better accuracy than asymmetric wall proximity functions considered. It is noted that in modelling homogeneous flows the length scale 1= 0.31${\|}$z${\|}$(1+z/h) can be used with tolerable accuracy.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.143-151
• /
• 2012

A new data-driven method for the design of a blind modulation frequency filter that suppresses the slow-varying noise components is proposed. The proposed method is based on the temporal local decorrelation of the feature vector sequence, and is done on an utterance-by-utterance basis. Although the conventional modulation frequency filtering approaches the same form regardless of the task and environment conditions, the proposed method can provide an adaptive modulation frequency filter that outperforms conventional methods for each utterance. In addition, the method ultimately performs channel normalization in a feature domain with applications to log-spectral parameters. The performance was evaluated by speaker-independent isolated-word recognition experiments under additive noise environments. The proposed method achieved outstanding improvement for speech recognition in environments with significant noise and was also effective in a range of feature representations.

• ETRI Journal
• /
• v.29 no.3
• /
• pp.300-304
• /
• 2007

This paper proposes a new data-driven method for high-pass approaches, which suppresses slow-varying noise components. Conventional high-pass approaches are based on the idea of decorrelating the feature vector sequence, and are trying for adaptability to various conditions. The proposed method is based on temporal local decorrelation using the information-maximization theory for each utterance. This is performed on an utterance-by-utterance basis, which provides an adaptive channel normalization filter for each condition. The performance of the proposed method is evaluated by isolated-word recognition experiments with channel distortion. Experimental results show that the proposed method yields outstanding improvement for channel-distorted speech recognition.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2235-2239
• /
• 2003

The aim of this research is to study and develop enabling technologies for home healthcare device with ubiquitous network. The motivation of this paper is to enable healthcare in home, to development the device for smart home health care. To achieve the aim, we must develop the prototype platform based on home gateways, distributed context user interface based on UPnP and support for information sharing with high speed power line communication and mobile infra-structures. And IPv6 is the base technology of this platform. In this paper, we concern that physical health, mental health and medical emergencies is all of home healthcare. With the smart device, we evaluate the connectivity, automatic information extraction and private data exchange and event driven message. The result of this paper is demonstration of smart device for ubiquitous communication in a healthcare application such as patient monitoring device and several information services. In conclusion, home healthcare will support more healthy and easy living for a human.

• Culinary science and hospitality research
• /
• v.23 no.6
• /
• pp.161-172
• /
• 2017

The purposes of this study were to examine if a decision making by a tourist sequentially or hierarchically occurs in a tourism destination and to test determinants that have an effect on both a sequential and non-sequential decision making. An instrument for the study was developed with three steps. A total of 420 and 380 questionnaire were collected respectively for the first two round surveys. For the third step, a pilot test was conducted with 30 respondents. And the data analysis utilized SPSS 18.0. A logistic regression analysis with variables of tourism activity and demography was employed to investigate the factors that affect a sequence of decision-making process. As an important result, the higher the age of the tourist in a tourism destination, the more conspicuous the consumption expenditure is made through the sequential decision-making process. Additionally, it is unreasonable to apply the premises and assumptions in extant consumer behavior to tourist behavior. The process of decision making by tourists in tourism areas is driven by either non-sequential or non-hierarchical decision-making process. More discussion and implications were provided.