• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.5
• /
• pp.543-548
• /
• 2014

Multiple-model based speech recognition framework (MMSR) has been known to be very successful in speech recognition. Since it uses multiple hidden Markov modes (HMMs) that corresponds to various noise types and signal-to-noise ratio (SNR) values, the selected acoustic model can have a close match with the test noisy speech. However, since the number of HMM sets is limited in practical use, the acoustic mismatch still remains as a problem. In this study, we experimentally determined the optimal SNR mapping between the test noisy speech and the HMM set to mitigate the mismatch between them. Improved performance was obtained by employing the SNR mapping instead of using the estimated SNR from the test noisy speech. When we applied the proposed method to the MMSR, the experimental results on the Aurora 2 database show that the relative word error rate reduction of 6.3% and 9.4% was achieved compared to a conventional MMSR and multi-condition training (MTR), respectively.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1113-1121
• /
• 2011

Recently, a variety of data mining techniques has been applied in various fields like healthcare, insurance, and internet shopping mall. Association rule mining is a popular and well researched method for discovering interesting relations among large set of data items. Association rule mining is the method to quantify the relationship between each set of items in very huge database based on the association thresholds. There are three primary quality measures for association rules; support and confidence and lift. In this paper we consider some similarity measures with negative co-occurrence frequencies which is widely used in cluster analysis or multi-dimensional analysis as association thresholds. The comparative studies with support, confidence and some similarity measures are shown by numerical example.

• The KIPS Transactions:PartA
• /
• v.17A no.2
• /
• pp.81-92
• /
• 2010

There has been some research in the equipment defect detection based on vibration information. Most research of them is based on vibration monitoring to determine the equipment defect or not. In this paper, we introduce more accurate system for engine defect detection based on vibration information and we focus on detection of engine defect for boat and system control. First, it uses the duplicated-checking method for vibration information to determine the engine defect or not. If there is a defect happened, we use the method using error part of vibration information basis with error range to determine which kind of error is happened. On the other hand, we use the engine trend analysis and standard of safety engine to implement the vibration information database. Our simulation results show that the probability of engine defect determination is 100% and the probability of engine defect classification and detection is 96%.

• Journal of the Korean Society for Library and Information Science
• /
• v.32 no.3
• /
• pp.81-96
• /
• 1998

This paper studied on problems and improvement method of description and headings in ${\ulcorner}Korean\;MARC\;on\;Disc\lrcorner$. By Korean MARC on Disc, it seems a great mistake that in abridged and full information, give the volumes next to statement of title and author. and even input copies of them respectively in case of multi-volume books. Also, frequently the essential abridged catalog information of a homonymic authors more than 10 which are written to Chinese are enumerated under one author name in Korean, using together with only one list. It is, therefore, effective and reasonable that Korean author headings be written to Korean language at first and be followed by Chinese, and then the subject of an author and the year of birth and death of author be indecated. For that, We should make out a conventional and reasonable subject heading list in advance to maintain the unity of subject, and build a exact authority database of Korean author name according to it.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.318-325
• /
• 2010

In this study, the wrapper database description language and model is suggested to collect product reviews from Korean shopping malls with multi-layer structures and are built in a variety of web languages. Above all, the wrapper based web crawlers have the website structure information to bring the exact desired data. The previously suggested wrapper based web crawler can collect HTML documents and the hierarchical structure of the target documents were only 2-3 layers. However, the Korean shopping malls in the study consist of not only HTML documents but also of various web language (JavaScript, Flash, and AJAX), and have a 5-layer hierarchical structure. A web crawler should have information about the review pages in order to visit the pages without visiting any non-review pages. The proposed wrapper contains the location information of review pages. We also propose a language grammar used in describing the location information.

• Advances in environmental research
• /
• v.6 no.1
• /
• pp.67-81
• /
• 2017

Mining activities play a significant role in environmental pollution by producing large amounts of tailings which comprise heavy metals. The impressive increase in mining activities in recent decades, due to their high influence on the industry of developing countries, duplicates the need for a substantial effort to develop and apply efficient measures of pollution control, mitigation, and abatement. In this study, our objective was to investigate the effect of simulation of the leachate, pH and inflow intensity of transport of $Pb^{2+}$, $Zn^{2+}$, and $Cd^{2+}$ through Lakan lead and zinc plant tailings, in Iran, and to evaluate the modeling efficiency by comparing the modeling results and the results obtained from previous column studies. We used the HP1 model and the PHREEQC database to simulate metals transport through a saturated soil column during a 15 day time period. The simulations assumed local equilibrium. As expected, a lower pH and inflow intensity increased metal transport. The retardation of heavy metals followed the order $Zn^{2+}$ > $Pb^{2+}$ > $Cd^{2+}$ and the removal concentrations of Cd, Pb, and Zn at the inflow intensity critical scenario, and Cd and Pb at inflow acidity critical scenario exceeded the allowable EPA and Iranian's 1053 standard thresholds. However, although the simulation results generally agreed well with the results of the column study, improvements are expected by using multi-dimensional models and a kinetic modeling approach for the reactions involved. The results of such investigations will be highly useful for designing preventative strategies to control reactive transport of hazardous metals and minimize their environmental effects.

• Annals of dermatology
• /
• v.30 no.6
• /
• pp.676-687
• /
• 2018

Background: Rosacea is associated with chronic systemic disease. However, research is lacking in Asian countries. Objective: To evaluate the association between rosacea and cardiovascular diseases (CVDs) related systemic comorbidities, and the use of antihypertensive and antihyperlipidemic drugs in Korea. Methods: A five-year retrospective study, using hospital database, was conducted in five medical centers for five years. Totally 1,399,528 patients were evaluated. Results: The overall frequency for diagnosed rosacea was 0.18% over five years (2,536 rosacea patients). Patients with diabetes and patients with dyslipidemia were more likely to have rosacea (odd ratio [OR] 2.724, 95% confidence interval [CI] 1.295~5.730, p=0.016; OR 1.788, 95% CI 1.445~2.212, p<0.001). Patients with CVD were less likely to have rosacea (OR 0.431, 95% CI 0.244~0.760, p=0.003). Patients with ${\alpha}$-blocker prescriptions and patients with ${\beta}$-blocker prescriptions showed a tendency diagnosed with rosacea frequently (OR 1.963, 95% CI 1.200~3.212, p=0.006; OR 3.939, 95% CI 3.512~4.419, p<0.001). Patients with [beta]-hydroxy-[beta]-methylglutaryl coenzyme A (HMG-CoA) reductase inhibitor, and those with fibrate, were prone to have rosacea (OR 1.599, 95% CI 1.390~1.839, p<0.001; OR 1.660, 95% CI 1.056~2.609, p=0.026). As adjusted results, among the patients who took HMG-CoA reductase inhibitor without dyslipidemia, rosacea was less likely to be diagnosed (OR 0.780, 95% CI 0.620~0.982, p=0.034). Conclusion: Rosacea is associated with chronic diseases and drugs.

• Korean Journal of Remote Sensing
• /
• v.25 no.4
• /
• pp.367-374
• /
• 2009

Recently, new GIS applications such as gee portal and spatial data infrastructure are emerging. These are related to web computing techniques or methodologies based on web 2.0 paradigm, open API of portal, open source GIS, and international GIS standards which are independently on developing. The product of these applications can be realized in the linkage of those components. In this study, a case implementation concerning linkage with Google maps API and open source middleware named Deegree is carried out, and the results are discussed for open source uses in geo portal. Open source middleware supports various levels and types of OGC standards, so that it enables web publishing in the several web standard formats and data exchanges and interoperable uses between external database servers. Also the (unction extensions and the multi tier-based architecture within geo portal for specific purpose are possible.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.03a
• /
• pp.187-194
• /
• 2008

Because the types and severities of most engine faults are various and complex, it is not easy that the conventional model based fault detection approach like the GPA(Gas Path Analysis) method can monitor all engine fault conditions. Therefore this study proposed newly a diagnostic algorithm for isolating and diagnosing effectively the faulted components of the smart UAV propulsion system, which has been developed by KARI(Korea Aerospace Research Institute), using the fuzzy logic and the neural network algorithms. A precise performance model should be needed to perform the model-based diagnostics. The based engine performance model was developed using SIMULINK. For the work and mass flow matching between components of the steady-state simulation, the state-flow library was applied. The proposed steady-state performance model can simulate off-design point performance at various flight conditions and part loads, and in order to evaluate the steady-state performance model their simulation results were compared with manufacturer's performance deck data. According to comparison results, it was confirm that the steady-state model well agreed with the deck data within 3% in all flight envelop. The diagnosis procedure of the proposed diagnostic system has the following steps. Firstly after obtaining database of fault patterns through performance simulation, then secondly the diagnostic system was trained by the FFBP networks. Thirdly after analyzing the trend of the measuring parameters due to fault patterns, then fourthly faulted components were isolated using the fuzzy logic. Finally magnitudes of the detected faults were obtained by the trained neural networks. Because the detected faults have almost same as degradation values of the implanted fault pattern, it was confirmed that the proposed diagnostic system can detect well the engine faults.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.31-39
• /
• 2006

This paper presents a novel approach to real-time recognition of 3D environment and objects for various applications such as intelligent robots, intelligent vehicles, intelligent buildings,..etc. First, we establish the three fundamental principles that humans use for recognizing and interacting with the environment. These principles have led to the development of an integrated approach to real-time 3D recognition and modeling, as follows: 1) It starts with a rapid but approximate characterization of the geometric configuration of workspace by identifying global plane features. 2) It quickly recognizes known objects in environment and replaces them by their models in database based on 3D registration. 3) It models the geometric details the geometric details on the fly adaptively to the need of the given task based on a multi-resolution octree representation. SIFT features with their 3D position data, referred to here as stereo-sis SIFT, are used extensively, together with point clouds, for fast extraction of global plane features, for fast recognition of objects, for fast registration of scenes, as well as for overcoming incomplete and noisy nature of point clouds.