• Korean Journal of Remote Sensing
• /
• v.21 no.3
• /
• pp.189-211
• /
• 2005

This paper makes an effort to compare the recently evolved soft classification method based on Linear Spectral Mixture Modeling (LSMM) with the traditional hard classification methods based on Iterative Self-Organizing Data Analysis (ISODATA) and Maximum Likelihood Classification (MLC) algorithms in order to achieve appropriate results for mapping, monitoring and preserving valuable coastal wetland ecosystems of southern India using Indian Remote Sensing Satellite (IRS) 1C/1D LISS-III and Landsat-5 Thematic Mapper image data. ISODATA and MLC methods were attempted on these satellite image data to produce maps of 5, 10, 15 and 20 wetland classes for each of three contrast coastal wetland sites, Pitchavaram, Vedaranniyam and Rameswaram. The accuracy of the derived classes was assessed with the simplest descriptive statistic technique called overall accuracy and a discrete multivariate technique called KAPPA accuracy. ISODATA classification resulted in maps with poor accuracy compared to MLC classification that produced maps with improved accuracy. However, there was a systematic decrease in overall accuracy and KAPPA accuracy, when more number of classes was derived from IRS-1C/1D and Landsat-5 TM imagery by ISODATA and MLC. There were two principal factors for the decreased classification accuracy, namely spectral overlapping/confusion and inadequate spatial resolution of the sensors. Compared to the former, the limited instantaneous field of view (IFOV) of these sensors caused occurrence of number of mixture pixels (mixels) in the image and its effect on the classification process was a major problem to deriving accurate wetland cover types, in spite of the increasing spatial resolution of new generation Earth Observation Sensors (EOS). In order to improve the classification accuracy, a soft classification method based on Linear Spectral Mixture Modeling (LSMM) was described to calculate the spectral mixture and classify IRS-1C/1D LISS-III and Landsat-5 TM Imagery. This method considered number of reflectance end-members that form the scene spectra, followed by the determination of their nature and finally the decomposition of the spectra into their endmembers. To evaluate the LSMM areal estimates, resulted fractional end-members were compared with normalized difference vegetation index (NDVI), ground truth data, as well as those estimates derived from the traditional hard classifier (MLC). The findings revealed that NDVI values and vegetation fractions were positively correlated ($r^2$= 0.96, 0.95 and 0.92 for Rameswaram, Vedaranniyam and Pitchavaram respectively) and NDVI and soil fraction values were negatively correlated ($r^2$ =0.53, 0.39 and 0.13), indicating the reliability of the sub-pixel classification. Comparing with ground truth data, the precision of LSMM for deriving moisture fraction was 92% and 96% for soil fraction. The LSMM in general would seem well suited to locating small wetland habitats which occurred as sub-pixel inclusions, and to representing continuous gradations between different habitat types.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.29-35
• /
• 2019

The structure of the machinery industry due to the 4th industrial revolution is changing from precision and durability to intelligent and smart machinery through sensing and interconnection(IoT). There is a growing need for research on prognostics and health management(PHM) that can prevent abnormalities in processing machines and accurately predict and diagnose conditions. PHM is a technology that monitors the condition of a mechanical system, diagnoses signs of failure, and predicts the remaining life of the object. In this study, the vibration generated during machining is measured and a classification algorithm for normal and fault signals is developed. Arbitrary fault signal is collected by changing the conditions of un stable supply cutting oil and fixing jig. The signal processing is performed to apply the measured signal to the learning model. The sampling rate is changed for high speed operation and performed machine learning using raw signal without FFT. The fault classification algorithm for 1D convolution neural network composed of 2 convolution layers is developed.

• Journal of Korean Library and Information Science Society
• /
• v.34 no.2
• /
• pp.209-231
• /
• 2003

A literature analysis for the planning and implementation of information system was carried out to establish the oceanographic R&D results, the first in Korea. The study targeted from scientific & technical report and to oceanographic survey data. The focus of the analysis lies in the providing practical information retrieval service for oceanographic R&D results based on the framework of effective Dublin Core metadata. The analyses included information system organization, web information service process, data input-output process, web visualization process, and retrieval for planning and implementation of oceanographic survey data and scientific & technical report.

• Knowledge Management Research
• /
• v.22 no.3
• /
• pp.91-106
• /
• 2021

With the recent rapid development of deep learning technology, the demand for analyzing huge text documents in the national R&D field from various perspectives is rapidly increasing. In particular, interest in the application of a BERT(Bidirectional Encoder Representations from Transformers) language model that has pre-trained a large corpus is growing. However, the terminology used frequently in highly specialized fields such as national R&D are often not sufficiently learned in basic BERT. This is pointed out as a limitation of understanding documents in specialized fields through BERT. Therefore, this study proposes a method to build an R&D KoBERT language model that transfers national R&D field knowledge to basic BERT using further pre-training. In addition, in order to evaluate the performance of the proposed model, we performed classification analysis on about 116,000 R&D reports in the health care and information and communication fields. Experimental results showed that our proposed model showed higher performance in terms of accuracy compared to the pure KoBERT model.

• Journal of the Korean Institute of Gas
• /
• v.23 no.4
• /
• pp.46-64
• /
• 2019

Technical practice code, KGS GC101 2018, for explosion hazard area selection and distance calculation of gas facility was enacted and implemented from July 12, 2018. This code includes whole contents of IEC60079-10-1 2015 (Explosive atmospheres Part 10-1: Classification of areas - Explosive gas atmospheres), and clarifies the interpretation of ambiguous standards or adds guidelines for standards. KGS GC101 is a method for classifying explosion hazard place types: (1) Determination of leak grade (2) Determination of leakage hole size (3) Determination of leakage flow (4) Determination of dilution class (5) Determination of ventilation effectiveness, finally (6) Determination of danger place (7) Explosion The range of dangerous places can be estimated. In order to easily calculate this process, the program (KGS-HAC v1.14, C-2018-020632) composed by Visual Basic for Application (Excel) language was produced by Korea Gas Safety Corporation. We will discuss how to use codes and programs to select and set up explosion hazard zones for field users.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.10
• /
• pp.1161-1168
• /
• 2014

As rapidly growing industry, ICT industry is emphasized for its importance and the demand to figure out for the performances of investment of R&D for ICT have been increasing. The performance for investment of R&D analyze mainly as commercialization, sales, hiring employee and intellectual property and so on. In this paper, we propose an analytical method for performance as focusing an application time of patent that are acquired as a result after perform the national project of ICT. We classify 4 subdivision technologies and 17 detailed classification of Korean industrial standard for 35,551 item of ICT area among national R&D project. This paper proposes computational method for required time about patent's performance. As a analyzed result we verify that the activity of technology's commercialization is most active in communication as 1.2 year of ICT among national project.

• Proceedings of the KIEE Conference
• /
• 1999.11d
• /
• pp.1000-1002
• /
• 1999

In this study, we were developed to provide a method for evaluating insulation systems for mold transformers with high-voltage ratings greater than 600V, in order to establish a uniform method for determining the temperature classification of mold transformer insulation system by testing rather than by chemical composition. Since these procedures are considered to be new, and have been tested exhaustively, further testing may prove the need for future revisions.

• Special Issue of the Society of Naval Architects of Korea
• /
• 2005.06a
• /
• pp.206-210
• /
• 2005

As design trends has changed to have flexible aft hull structure, increased power output and stiffer shafting system, owners and classification societies have more concerned about shaft alignment. In the shaft alignment analysis, there are many uncertainties which are related in propeller generated force, bearing stiffness, crank shaft model and etc. in this study, it is focused on the effect of crankshaft model by comparing between equivalent model and actual crankshaft model.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.441-442
• /
• 2022

This is a study on the design and operation software development of an accident response support service for MASS(maritime autonomous surface ship) that provides accident response support information according to ship accident classification when a ship accident occurs due to the operation of MASS

• Journal of Technology Innovation
• /
• v.19 no.2
• /
• pp.25-51
• /
• 2011

This study examine the firms fund R&D expenditures through cash and cash equivalents under financial distress in order to avoid huge adjustment costs that can be brought after R&D expenditures cut-down. Other study divided the firms' financial condition by only firms' year. This study identifies the firms' financial condition not only by a firm's year but also by firm size and Altman's Z-Score and K-Score. The results show that there are statistically negative relationship between R&D expenditures and cash and cash equivalents when firms are under financial distress. The results are same regardless of criteria of classification of firms' financial condition, which is consistent to the hypothesis. Young and small firms and firms with moderate possibility of bankruptcy fund R&D expenditures through cash and cash equivalent compared to the other firms. We can find the new evidence when we classify the firm by Z-Score and K-Score of Altman. The firms with high possibility of bankruptcy can not fund for R&D activities from cash, but only the firms with moderate possibility of bankruptcy fund R&D expenditures through cash and cash equivalent in the condition of financial distress. The evidence suggests that firms fund R&D expenditures by cash and cash equivalent when they are under financial distress. Findings provide an implication on the management of R&D expenditures and liquidity in the firms.