• Journal of KIISE:Software and Applications
• /
• v.37 no.6
• /
• pp.455-463
• /
• 2010

In this paper, we present an approach to sentence boundary detection for web documents that builds on statistical-based methods and uses rule-based correction. The proposed system uses the classification model learned offline using a training set of human-labeled web documents. The web documents have many word-spacing errors and frequently no punctuation mark that indicates the end of sentence boundary. As sentence boundary candidates, the proposed method considers every Ending Eomis as well as punctuation marks. We optimize engine performance by selecting the best feature, the best training data, and the best classification algorithm. For evaluation, we made two test sets; Set1 consisting of articles and blog documents and Set2 of web community documents. We use F-measure to compare results on a large variety of tasks, Detecting only periods as sentence boundary, our basis engine showed 96.5% in Set1 and 56.7% in Set2. We improved our basis engine by adapting features and the boundary search algorithm. For the final evaluation, we compared our adaptation engine with our basis engine in Set2. As a result, the adaptation engine obtained improvements over the basis engine by 39.6%. We proved the effectiveness of the proposed method in sentence boundary detection.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.31-38
• /
• 2018

Based on the measured data in the south western sea of Jeju Island during the SAVEX15(Shallow Water Acoustic Variability EXperiment 2015), the effect of internal waves on the PPD (Predictive Probability of Detection) of a sonar system was analyzed. The southern west sea of Jeju Island has complex flows due to internal waves and USC (Underwater Sound Channel). In this paper, sonar performance is predicted by probabilistic approach. The LFM (Linear Frequency Modulation) and MLS (Maximum Length Sequence) signals of 11 kHz - 31 kHz band of SAVEX15 data were processed to calculate the TL (Transmission Loss) and NL (Noise Level) at a distance of approximately 2.8 km from the source and the receiver. The PDF (Probability Density Function) of TL and NL is convoluted to obtain the PDF of the SE (Signal Excess) and the PPD according to the depth of the source and receiver is calculated. Analysis of the changes in the PPD over time when there are internal waves such as soliton packet and internal tide has confirmed that the PPD value is affected by different aspects.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.227-237
• /
• 2022

The most critical factors for detecting changes in very high-resolution satellite images are building positional inconsistencies and relief displacements caused by satellite side-view. To resolve the above problems, additional processing using a digital elevation model and deep learning approach have been proposed. Unfortunately, these approaches are not sufficiently effective in solving these problems. This study proposed a change detection method that considers both positional and topology information of buildings. Mask R-CNN (Region-based Convolutional Neural Network) was trained on a SpaceNet building detection v2 dataset, and the central points of each building were extracted as building nodes. Then, triangulated irregular network graphs were created on building nodes from temporal images. To extract the area, where there is a structural difference between two graphs, a change index reflecting the similarity of the graphs and differences in the location of building nodes was proposed. Finally, newly changed or deleted buildings were detected by comparing the two graphs. Three pairs of test sites were selected to evaluate the proposed method's effectiveness, and the results showed that changed buildings were detected in the case of side-view satellite images with building positional inconsistencies.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.267-286
• /
• 2023

The conversational agents such as AI speakers utilize voice conversation for human-computer interaction. Voice recognition errors often occur in conversational situations. Recognition errors in user utterance records can be categorized into two types. The first type is misrecognition errors, where the agent fails to recognize the user's speech entirely. The second type is misinterpretation errors, where the user's speech is recognized and services are provided, but the interpretation differs from the user's intention. Among these, misinterpretation errors require separate error detection as they are recorded as successful service interactions. In this study, various text separation methods were applied to detect misinterpretation. For each of these text separation methods, the similarity of consecutive speech pairs using word embedding and document embedding techniques, which convert words and documents into vectors. This approach goes beyond simple word-based similarity calculation to explore a new method for detecting misinterpretation errors. The research method involved utilizing real user utterance records to train and develop a detection model by applying patterns of misinterpretation error causes. The results revealed that the most significant analysis result was obtained through initial consonant extraction for detecting misinterpretation errors caused by the use of unregistered neologisms. Through comparison with other separation methods, different error types could be observed. This study has two main implications. First, for misinterpretation errors that are difficult to detect due to lack of recognition, the study proposed diverse text separation methods and found a novel method that improved performance remarkably. Second, if this is applied to conversational agents or voice recognition services requiring neologism detection, patterns of errors occurring from the voice recognition stage can be specified. The study proposed and verified that even if not categorized as errors, services can be provided according to user-desired results.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.444-452
• /
• 2024

This study proposes a deep learning architecture optimized for fire detection derived through Layer Importance Evaluation. In order to solve the problem of unnecessary complexity and operation of the existing Convolutional Neural Network (CNN)-based fire detection system, the operation of the inner layer of the model based on the weight and activation values was analyzed through the Layer Importance Evaluation technique, the layer with a high contribution to fire detection was identified, and the model was reconstructed only with the identified layer, and the performance indicators were compared and analyzed with the existing model. After learning the fire data using four transfer learning models: Xception, VGG19, ResNet, and EfficientNetB5, the Layer Importance Evaluation technique was applied to analyze the weight and activation value of each layer, and then a new model was constructed by selecting the top rank layers with the highest contribution. As a result of the study, it was confirmed that the implemented architecture maintains the same performance with parameters that are about 80% lighter than the existing model, and can contribute to increasing the efficiency of fire monitoring equipment by outputting the same performance in accuracy, loss, and confusion matrix indicators compared to conventional complex transfer learning models while having a learning speed of about 3 to 5 times faster.

• Korean Journal of Remote Sensing
• /
• v.27 no.3
• /
• pp.379-388
• /
• 2011

At present, GEOBIA (Geographic Object-based Image Analysis), heir of OBIA (Object-based Image Analysis), is regarded as an important methodology by object-oriented paradigm for remote sensing, dealing with geo-objects related to image segmentation and classification in the different view point of pixel-based processing. This also helps to directly link to GIS applications. Thus, GEOBIA software is on the booming. The main theme of this study is to look into the applicability of geo-spatial processing open source to GEOBIA. However, there is no few fully featured open source for GEOBIA which needs complicated schemes and algorithms, till It was carried out to implement a preliminary system for GEOBIA running an integrated and user-oriented environment. This work was performed by using various open sources such as OTB or PostgreSQL/PostGIS. Some points are different from the widely-used proprietary GEOBIA software. In this system, geo-objects are not file-based ones, but tightly linked with GIS layers in spatial database management system. The mean shift algorithm with parameters associated with spatial similarities or homogeneities is used for image segmentation. For classification process in this work, tree-based model of hierarchical network composing parent and child nodes is implemented by attribute join in the semi-automatic mode, unlike traditional image-based classification. Of course, this integrated GEOBIA system is on the progressing stage, and further works are necessary. It is expected that this approach helps to develop and to extend new applications such as urban mapping or change detection linked to GIS data sets using GEOBIA.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.859-870
• /
• 1997

Computerized map reading system is one of the most important application areas in the image processing.A map databaes can be used for a wide range of scial activities such as narural resource assessment,regional plan-ming,and reaffic nabigation system. The road segments,however,are extracted as briken in the area where they are overlapped and interupted by chracters and symbols.Few approaches have been taken to complete road segnents interupted by map symbols.In this paper,a movel approach for the extracation and completion of road segements interupted by map symbols is proposed using neural networks.The system is applied to 1/25,000 scaled maps published by the Grographical Survey Unstitute of Ministry of Construction of Korea.It will be shown that the system can extract and reconstruct road segmetns for the various areas of maps sucessfully.

• Journal of Advanced Navigation Technology
• /
• v.7 no.1
• /
• pp.14-21
• /
• 2003

We investigated the optimum pump light power compensating distorted WDM signal due to both chromatic dispersion and self phase modulation (SPM). The considered system is $3{\times}40$ Gbps intensity modulation direct detection (IM/DD) WDM transmission system with path-averaged intensity approximation (PAIA) mid-span spectral inversion (MSSI) as compensation method. This system have highly nonlinear dispersion shifted fiber (HNL-DSF) as nonlinear medium of optical phase conjugator (OPC) in the mid-way of total transmission line. We confirmed that HNL-DSF is an useful nonlinear medium in OPC for wideband WDM transmission, and the excellent compensation is obtained when the pump light power of HNL-DSF OPC was selected to equalize the conjugated light power into the second half fiber section with the input WDM signal light power depending on total transmission length. By this approach, it is verified the possibility to realize a long-haul high capacities WDM system by using PAIA MSSI compensation method, which have HNL-DSF OPC with optimal pump light power depending on transmission length.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.3
• /
• pp.74-85
• /
• 2021

Global Navigation Satellite System (GNSS) receivers are intrinsically vulnerable to radio frequency jamming signals due to the fundamental property of radio navigation systems. A GNSS jamming monitoring system that is capable of jamming detection, classification and localization is essential for infrastructure for autonomous driving systems. For these 3 functionalities, a GNSS jamming monitoring network consisting of a multiple of low-cost GNSS receivers distributed in a certain area is needed, and the precise time synchronizaion between multiple independent GNSS receivers in the network is an essential element. This paper presents a precise time synchronization method based on the direct use of Time Difference of Arrival (TDOA) technique in signal domain. A block interpolation method is additionally incorporated into the method in order to maintain the precision of time synchronization even with the relatively low sampling rate of the received signals for computational efficiency. The feasibility of the proposed approach is verified in the numerical simualtions.

• Biotechnology and Bioprocess Engineering:BBE
• /
• v.5 no.2
• /
• pp.84-91
• /
• 2000

Mycopasma contamination of tissue culture cells easily evades detection and, thus, represents a continous therat to cell biologists. In case where infected cell can not simply be replaced, attempts have to be made to eradicate mycoplacma from the tissue culture cells. A variety of anti-microbial agents have been shown to be toxic to mycoplasma strains ; however, cell associated mycoplasma are often protected from antibiotics at concentrations shown to be effective in vitro. Antibiotic concentrations high enough to be lethal to cell as sociated mycoplasmas frequently are also detrimentrations to the host cells, while moderately increased antibiotic levels tolerated by the host cells often lead to only temporary growth suppression and/or to the emergence of mycoplasma strains resistanct even to high concentrations of the antibiotis applied. Hare, a genetic approach for the elimination of mycoplasma from tissue culture cells that overcomes thens limitations is described. By expression of a selection marker conferring resistance to an otherwise toxic agent, Acholeplasma laidlawii infected BHK-21 cells used as the model system were enabled to temporarily tolerate antibiotic concentrations high enough to be lethal to cell associated mycopalsma while leaving the host cells unharmed. Upon successful mycoplasma eradicated, cultvation of the cured host cells in the absence of the selective agent yielded revertant cell clones that had regained susceptibillity to the toxic agent. Cressation of the selection marker expression was shown to result from the loss of the selection marker DNA, which is a consequence of the fact that the stable and permanent integration of foreign DNA in eucaryotic cell chrosomes is highly inefficient. Thus, the cells were cured from mycoplasma yet remained biochemically unaltered.