• Phonetics and Speech Sciences
• /
• v.12 no.2
• /
• pp.29-37
• /
• 2020

Recently, the neural network-based deep learning algorithm has dramatically improved performance compared to the classical Gaussian mixture model based hidden Markov model (GMM-HMM) automatic speech recognition (ASR) system. In addition, researches on end-to-end (E2E) speech recognition systems integrating language modeling and decoding processes have been actively conducted to better utilize the advantages of deep learning techniques. In general, E2E ASR systems consist of multiple layers of encoder-decoder structure with attention. Therefore, E2E ASR systems require data with a large amount of speech-text paired data in order to achieve good performance. Obtaining speech-text paired data requires a lot of human labor and time, and is a high barrier to building E2E ASR system. Therefore, there are previous studies that improve the performance of E2E ASR system using relatively small amount of speech-text paired data, but most studies have been conducted by using only speech-only data or text-only data. In this study, we proposed a semi-supervised training method that enables E2E ASR system to perform well in corpus in different domains by using both speech or text only data. The proposed method works effectively by adapting to different domains, showing good performance in the target domain and not degrading much in the source domain.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.431-447
• /
• 2021

Recently, the use of high-resolution satellites is increasing in many areas. In order to supply useful satellite images stably, it is necessary to establish automatic precision geometric correction technic. Geometric correction is the process that corrected geometric errors of satellite imagery based on the GCP (Ground Control Point), which is correspondence point between accurate ground coordinates and image coordinates. Therefore, in the automatic geometric correction process, it is the key to acquire high-quality GCPs automatically. In this paper, we proposed iterative precision geometry correction method. we constructed an image pyramid and repeatedly performed GCP chip matching, outlier detection, and precision sensor modeling in each layer of the image pyramid. Through this method, we were able to acquire high-quality GCPs automatically. we then improved the performance of geometric correction of high-resolution satellite images. To analyze the performance of the proposed method, we used KOMPSAT-3 and 3A Level 1R 8 scenes. As a result of the experiment, the proposed method showed the geometric correction accuracy of 1.5 pixels on average and a maximum of 2 pixels.

• Tunnel and Underground Space
• /
• v.34 no.5
• /
• pp.461-476
• /
• 2024

As the paradigm of urban development has recently changed to development of underground space, the road tunnels and railway tunnels are increasing to relieve traffic congestion. This technical notes is related to the development of underground spaces using NATM (New Austrian Tunneling Method). Limitations of conventional 2D blasting pattern design method were analyzed, and BIM-based automatic design method was developed to overcome them. Since it was developed to facilitate modeling of all safety facilities along a alignment using coordinates and GIS data, it can overcome the limitations of the number of safety facilities that can be considered and time required for conventional design. In the conventional design, the results of borehole test blasting were used to predict the blasting impact. However, the developed technology is possible to recalculate by applying the measurement results obtained from actual tunnel blasting, enabling rapid re-evaluation of the blasting impact on all safety facilities during construction, leading economical design. As a result of applying it to GTX-A5 and 6 sites, it took about 5 minutes, which is 1/480 compared to the conventional design method. In addition, the construction cost was reduced by about 8 billion won/km and the period was reduced by about 41 days/km. It is expected to be used as technical basis for calculating the optimal blasting pattern in the BIM-based design and construction management process.

• Journal of KIISE
• /
• v.43 no.3
• /
• pp.370-379
• /
• 2016

Recently personal media were produced in a variety of ways as a lot of smart devices have been spread and services using these data have been desired. Therefore, research has been actively conducted for the media analysis and recognition technology and we can recognize the meaningful object from the media. The system using the media ontology has the disadvantage that can't classify the media appearing in the video because of the use of a video title, tags, and script information. In this paper, we propose a system to automatically classify video using the objects shown in the media data. To do this, we use a description logic-based reasoning and a rule-based inference for event processing which may vary in order. Description logic-based reasoning system proposed in this paper represents the relation of the objects in the media as activity ontology. We describe how to another rule-based reasoning system defines an event according to the order of the inference activity and order based reasoning system automatically classify the appropriate event to the category. To evaluate the efficiency of the proposed approach, we conducted an experiment using the media data classified as a valid category by the analysis of the Youtube video.

• Journal of Korea Spatial Information System Society
• /
• v.1 no.1 s.1
• /
• pp.5-18
• /
• 1999

Recently, the necessity of automatic knowledge extraction from spatial data stored in spatial databases has been increased. Spatial data mining can be defined as the extraction of implicit knowledge, spatial relationships, or other knowledge not explicitly stored in spatial databases. In order to extract useful knowledge from spatial data, an object management system that can store spatial data efficiently, provide very fast indexing & searching mechanisms, and support a distributed computing environment is needed. In this paper, we designed and implemented an open object management system for spatial data mining, that supports efficient management of spatial, aspatial, and knowledge data. In order to develop this system, we used Open OODB that is a widely used object management system. However, the lark of facilities for spatial data mining in Open OODB, we extended it to support spatial data type, dynamic class generation, object-oriented inheritance, spatial index, spatial operations, etc. In addition, for further increasement of interoperability with other spatial database management systems or data mining systems, we adopted international standards such as ODMG 2.0 for data modeling, SDTS(Spatial Data Transfer Standard) for modeling and exchanging spatial data, and OpenGIS Simple Features Specification for CORBA for connecting clients and servers efficiently.

• Journal of the Korean association of regional geographers
• /
• v.17 no.4
• /
• pp.432-442
• /
• 2011

Climatic variables such as temperature and precipitation tend to vary both in space and in time simultaneously. Thus, it is necessary to include space-time autocorrelation into conventional spatial interpolation methods for reliable time-series mapping. This paper introduces and applies space-time variogram modeling and space-time kriging to generate time-series temperature maps using hourly Automatic Weather System(AWS) temperature observation data for a one-month period. First, temperature observation data are decomposed into deterministic trend and stochastic residual components. For trend component modeling, elevation data which have reasonable correlation with temperature are used as secondary information to generate trend component with topographic effects. Then, space-time variograms of residual components are estimated and modelled by using a product-sum space-time variogram model to account for not only autocorrelation both in space and in time, but also their interactions. From a case study, space-time kriging outperforms both conventional space only ordinary kriging and regression-kriging, which indicates the importance of using space-time autocorrelation information as well as elevation data. It is expected that space-time kriging would be a useful tool when a space-poor but time-rich dataset is analyzed.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.10
• /
• pp.7-16
• /
• 2007

In this paper, we introduce a new design environment for efficient multiprocessor system-on-chip design space exploration. The design environment takes a process network model as input system specification. The process network model has been widely used for modeling signal processing applications because of its excellent modeling power. However, it has limitation in predictability, which could cause severe problem for real time systems. This paper proposes a new approach that enables static analysis of a process network model by converting it to a hierarchical synchronous dataflow model. For efficient design space exploration in the early design step, mapping application to target architectures has been a crucial part for finding better solution. In this paper, we propose an efficient mapping algorithm. Our mapping algorithm supports both single bus architecture and multiple bus architecture. In the experiments, we show that the automatic conversion approach of the process network model for static analysis is performed successfully for several signal processing applications, and show the effectiveness of our mapping algorithm by comparing it with previous approaches.

• Journal of radiological science and technology
• /
• v.35 no.2
• /
• pp.133-139
• /
• 2012

For the examination of nuclear medicine, myocardial scan is a good method to evaluate a hemodynamic importance of coronary heart disease. but, the automatized qualitative measurement is additionally necessary to improve the decoding efficiency. we suggests the creation of cardiac three-dimensional model and model of three-dimensional cardiac thickness as a new measurement. For the experiment, cardiac reduced cross section was obtained from SPECT. Next, the pre-process was performed and image segmentation was fulfilled by level set. for the modeling of left cardiac thickness, it was realized by applying difference equation of two-dimensional laplace equation. As the result of experiment, it was successful to measure internal wall and external wall and three-dimensional modeling was realized by coordinate. and, with laplace formula, it was successful to develop the thickness of cardiac wall. through the three-dimensional model, defects were observed easily and position of lesion was grasped rapidly by the revolution of model. The model which was developed as the support index of decoding will provide decoding information to doctor additionally and reduce the rate of false diagnosis as well as play a great role for diagnosing IHD early.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1615-1627
• /
• 2020

The purpose of this study is to compare and analyze the performance of KOMPSAT-3 Digital Surface Model (DSM) made in overseas testbed area. To that end, we collected the KOMPSAT-3 in-track stereo image taken in San Francisco, the U.S. The stereo geometry elements (B/H, converse angle, etc.) of the stereo image taken were all found to be in the stable range. By applying precise sensor modeling using Ground Control Point (GCP) and DSM automatic generation technique, DSM with 1 m resolution was produced. Reference materials for evaluation and calibration are ground points with accuracy within 0.01 m from Compass Data Inc., 1 m resolution Elevation 1-DSM produced by Airbus. The precision sensor modeling accuracy of KOMPSAT-3 was within 0.5 m (RMSE) in horizontal and vertical directions. When the difference map was written between the generated DSM and the reference DSM, the mean and standard deviation were 0.61 m and 5.25 m respectively, but in some areas, they showed a large difference of more than 100 m. These areas appeared mainly in closed areas where high-rise buildings were concentrated. If KOMPSAT-3 tri-stereo images are used and various post-processing techniques are developed, it will be possible to produce DSM with more improved quality.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.381-386
• /
• 2023

Many existing test case generation researchers extract test cases from models. However, research on generating test cases from natural language requirements is required in practice. For this purpose, the combination of natural language analysis and requirements engineering is very necessary. However, Requirements analysis written in Korean is difficult due to the diverse meaning of sentence expressions. We research test case generation through natural language requirement definition analysis, C3Tree model, cause-effect graph, and decision table steps as one of the test case generation methods from Korean natural requirements. As an intermediate step, this paper generates test cases from C3Tree model-based decision tables using meta-modeling. This method has the advantage of being able to easily maintain the model-to-model and model-to-text transformation processes by modifying only the transformation rules. If an existing model is modified or a new model is added, only the model transformation rules can be maintained without changing the program algorithm. As a result of the evaluation, all combinations for the decision table were automatically generated as test cases.