• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.

• The KIPS Transactions:PartD
• /
• v.14D no.6
• /
• pp.573-584
• /
• 2007

As multimedia information recently increases fast, various types of retrieval of multimedia data are becoming issues of great importance. For the efficient multimedia data processing, semantics based retrieval techniques are required that can extract the meaning contents of multimedia data. Existing retrieval methods of multimedia data are annotation-based retrieval, feature-based retrieval and annotation and feature integration based retrieval. These systems take annotator a lot of efforts and time and we should perform complicated calculation for feature extraction. In addition. created data have shortcomings that we should go through static search that do not change. Also, user-friendly and semantic searching techniques are not supported. This paper proposes to develop S-MARS(Semantic Metadata-based Multimedia Annotation and Retrieval System) which can represent and extract multimedia data efficiently using MPEG-7. The system provides a graphical user interface for annotating, searching, and browsing multimedia data. It is implemented on the basis of the semantic metadata model to represent multimedia information. The semantic metadata about multimedia data is organized on the basis of multimedia description schema using XML schema that basically comply with the MPEG-7 standard. In conclusion. the proposed scheme can be easily implemented on any multimedia platforms supporting XML technology. It can be utilized to enable efficient semantic metadata sharing between systems, and it will contribute to improving the retrieval correctness and the user's satisfaction on embedding based multimedia retrieval algorithm method.

• The Journal of the Petrological Society of Korea
• /
• v.21 no.2
• /
• pp.151-171
• /
• 2012

The Permo-Triassic Songrim orogeny in the Korean peninsula was a major tectonic event involving complicated continental collisions at the eastern margin of Eurasia. Based on the previous studies on the metamorphic and deformations features of the Songrim orogeny, this paper presents metamorphic and structural characteristics and timing of the Songrim orogeny in the Taebaeksan basin, and discuss about correlation of the tectono-metamorphic evolution of the Taebaeksan basin with the Okcheon basin and the Imjingang belt with a combined analysis of bulk crustal shortening direction, metamorphic P-T and T-t (time) paths. The metapelites in the Pyeongan Supergroup in the northeastern margin of the Taebaeksan basin have experienced lower-temperature/medium-pressure (LT/MP) regional metamorphism followed by high-temperature contact metamorphism due to the Jurassic granite intrusion. The earlier LT/MP regional metamorphism produced two loops of clockwise P-T-d (deformation) paths combined with four deformation events ($D_1-D_4$). The first loop concomitant with $D_1$ and $D_2$ occurred at $400-500^{\circ}C$, 1.5-3.0 kbar, and related with growth of syn-$D_1$ chloritoid and andalusite, post-$D_1$ margarite, Ca-rich syn-$D_2$ or post-$D_2$ plagioclase. The second loop accompanying $D_3$ and $D_4$ occurred at $520-580^{\circ}C$, 2.0-6.0 kbar, and associated with the growth of syn-$D_3$ garnet and staurolite, and syn-$D_4$ and/or post-$D_4$ andalusite porphyroblasts. Furthermore the syn-$D_1$ chloritoid and andalusite porphyroblasts grew during E-W bulk crustal shortening, whereas the syn-$D_3$ garnet and staurolite, and the syn-$D_4$ and/or post-$D_4$ andalusite porphyroblasts have grown under N-S bulk crustal shortening. The similarity in the characteristics and timing of the metamorphism and bulk crustal shortening directions between the Okcheon and Imjingang belts suggest that the peak metamorphic conditions tend to increase toward the western part (Imjingang belt and southwestern part of the Gyeonggi Massif) from the eastern part (Taebaeksan basin). The E-W bulk crustal shortening influenced the eastern part of the Okcheon belt, whereas the N-S bulk crustal shortening resulted in strong deformation in the Imjingang and Okcheon belts. Consequently, the Permo-Triassic Songrim orogeny in the Korean peninsula is probably not only related to collision of the North and South China blocks, but also to the amalgamation of terrane fragments at the eastern Eurasia margin (e.g., collision of the Sino-Korean continent and the Hida-Oki terrane).

• Sleep Medicine and Psychophysiology
• /
• v.19 no.1
• /
• pp.27-34
• /
• 2012

Objectives: The analysis of heart rate variability (HRV) is a useful non-invasive tool to investigate the autonomic nerve function. Previous studies on the relationship between HRV and depression have been reported controversial results. Similarly, the correlation between the serum lipids and depression is debatable. The purpose of this study is to examine the relationship between heart rate variability, lipid profile and depression. Methods: A total of 42 patients with major depressive disorder (MDD) and 32 age and sex-matched normal subjects who had no previous history of major medical and mental illnesses were recruited for this study. A structured-interview was used to assess the general characteristics and psychiatric illness. HRV measures were assessed by time-domain and frequency-domain analyses. Psychological symptoms were measured using the Hamilton rating scale for anxiety (HAM-A), Hamilton rating scale for depression (HAM-D). In addition, the evaluation for lipid profile was performed by blood test. Results: In serum lipid profile test, MDD group showed higher cholesterol ($197.68{\pm}42.94$ mg/dL vs. $176.85{\pm}34.68$ mg/dL, p=0.044), TG ($139.45{\pm}92.54$ mg/dL vs. $91.4{\pm}65.68$ mg/dL, p=0.018), LDL ($130.03{\pm}33.18$ vs. $106.62{\pm}27.08$, p=0.004) level than normal control group. In HRV time domain analyses, the standard deviation of the NN interval (SDNN) was decreased in MDD group than normal control group, but was not significant ($32.82{\pm}14.33$ ms vs. $40.36{\pm}21.40$ms, p=0.078). ApEn (Approximate Entrophy) was significantly increased in MDD group than normal control group ($1.13{\pm}0.11$ vs. $0.91{\pm}0.18$, p<0.001). ApEn was correlated with LDL level (r=0.277, p=0.028), HAM-D scores (r=0.534, p<0.001) and HAM-A scores (r=0.470, p<0.001). Conclusions: MDD patients showed increased ApEn, one of the HRV measurement. And this ApEn was correlated with LDL, HAM-D and HAM-A scores. In this study, the analysis of ApEn would be a useful test of MDD.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.36 no.3
• /
• pp.337-347
• /
• 2009

Dental caries during infantile and early childhood period is a complex disease resulting from multiple caries factors. Streptococcus mutans(S. mutans) plays a critical role in the initiation of caries, and its early transmission through mothers provides a strong etiologic factor for future development of caries in the primary dentition. Therefore, early detection of caries risk factor is important for prevention of caries. Recent studies about etiologic factors of caries have brought advent of various tools for caries risk assessment in order to predict progress of caries more accurately. Cariogram is a common tool for caries risk assessment, which illustrates present caries risk assessment and correlation of caries risk factors for an individual graphically. The aim of this study was to assess if there is any correlation in the level of S. mutans and caries activity and to verify the effect of caries risk factors between children with age ranging from 3 to 5 years with severe early childhood caries(S-ECC) and their mothers using caries-related salivary test and Cariogram. The results of this study were as follows. 1. Children with S-ECC had a statistically higher level of Streptococcus mutans compared to caries-free children(p<0.05). 2. There was significant correlation between mothers and their children in the aspect of the level of Streptococcus mutans(p<0.05). 3. When caries activity was assessed using Cariogram, significant correlation between mothers and their children was found(p<0.05). 4. When each caries risk factor was evaluated for its affect on caries activity, host was more influential factor compared to microorganism and diet in children. Based on these results, we could conclude that assessing the level of S. mutans can be an effective tool for predicting possibility of caries formation in future. Since prediction of future caries progression and evaluation of caries risk factor became possible with Cariogram, we may conduct early and preventive measures for treatment of caries.

• Progress in Medical Physics
• /
• v.14 no.4
• /
• pp.211-217
• /
• 2003

The Principal component analysis (PCA) is a well-known data analysis method that is useful in linear feature extraction and data compression. The PCA is a linear transformation that applies an orthogonal rotation to the original data, so as to maximize the retained variance. PCA is a classical technique for obtaining an optimal overall mapping of linearly dependent patterns of correlation between variables (e.g. neurons). PCA provides, in the mean-squared error sense, an optimal linear mapping of the signals which are spread across a group of variables. These signals are concentrated into the first few components, while the noise, i.e. variance which is uncorrelated across variables, is sequestered in the remaining components. PCA has been used extensively to resolve temporal patterns in neurophysiological recordings. Because the retinal signal is stochastic process, PCA can be used to identify the retinal spikes. With excised rabbit eye, retina was isolated. A piece of retina was attached with the ganglion cell side to the surface of the microelectrode array (MEA). The MEA consisted of glass plate with 60 substrate integrated and insulated golden connection lanes terminating in an 8${\times}$8 array (spacing 200 $\mu$m, electrode diameter 30 $\mu$m) in the center of the plate. The MEA 60 system was used for the recording of retinal ganglion cell activity. The action potentials of each channel were sorted by off­line analysis tool. Spikes were detected with a threshold criterion and sorted according to their principal component composition. The first (PC1) and second principal component values (PC2) were calculated using all the waveforms of the each channel and all n time points in the waveform, where several clusters could be separated clearly in two dimension. We verified that PCA-based waveform detection was effective as an initial approach for spike sorting method.

• Progress in Medical Physics
• /
• v.26 no.4
• /
• pp.286-293
• /
• 2015

The purpose of this study was to evaluate the set up accuracy using stereotactic body frame and frameless immobilizer for lung stereotactic body radiation therapy (SBRT). For total 40 lung cancer patients treated by SBRT, 20 patients using stereotactic body frame and other 20 patients using frameless immobilizer were separately enrolled in each group. The setup errors of each group depending on the immobilization methods were compared and analyzed. All patients received the dose of 48~60 Gy for 4 or 5 fractions. Before each treatment, a patient was first localized to the treatment isocenter using room lasers, and further aligned with a series of image guidance procedures; orthogonal kV radiographs, cone-beam CT, orthogonal fluoroscopy. The couch shifts during these procedures were recorded and analyzed for systematic and random errors of each group. Student t-test was performed to evaluate significant difference depending on the immobilization methods. The setup reproducibility was further analyzed using F-test with the random errors excluding the systematic setup errors. In addition, the ITV-PTV margin for each group was calculated. The setup errors for SBF were $0.05{\pm}0.25cm$ in vertical direction, $0.20{\pm}0.38cm$ in longitudinal direction, and $0.02{\pm}0.30cm$ in lateral direction, respectively. However the setup errors for frameless immobilizer showed a significant increase of $-0.24{\pm}0.25cm$ in vertical direction while similar results of $0.06{\pm}0.34cm$, $-0.02{\pm}0.25cm$ in longitudinal and lateral directions. ITV-PTV margins for SBF were 0.67 cm (vertical), 0.99 cm (longitudinal), and 0.83 cm (lateral), respectively. On the other hand, ITV-PTV margins for Frameless immobilizer were 0.75 cm (vertical), 0.96 cm (longitudinal), and 0.72 cm (lateral), indicating less than 1 mm difference for all directions. In conclusion, stereotactic body frame improves reproducibility of patient setup, resulted in 0.1~0.2 cm in both vertical and longitudinal directions. However the improvements are not substantial in clinic considering the effort and time consumption required for SBF setup.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.5 no.1
• /
• pp.1-10
• /
• 1972

Studies on the circulation and water masses in the continental shelf break region of the East China Sea are Summerized as follows : 1. The main stream of the Kuroshio flowing north-east near $29^{\circ}N\;Lat\;127^{\circ}E$ tong of the East China Sea in summer is narrow in width. Moving toward east, it becomes twice as wide in Tokora Strait, Japan. 2. In the main stream area of the Kuroshio, the surface Waters in the Upper layer (0-250m) are influenced by the coastal waters of China, and the counter current submerges under the surface water. Therefore, the mixing waters are found in its intermediate layer. 3. Water mass between Amami Island and the continental shelf of the East China Sea consists of main stream water, counter current water, gyration water and mixed water with coastal waters. 4. The maximum velocity of current in this waters was 139cm/sec. The volume transport was estimated approximately as $24.2\;\times\;10^6m^3/sec$. It was less than $33\;\times\;10^6m^3/sec$ in the region between Okinawa and continental shelf of the East China Sea. 5. Surface waters east of $29^{\circ}N\;Lat\;128^{\circ}E$ Long flows toward Amami Island, Okinawa Island, and Hachi Ju San Island, while those west of the region flow toward the Korea-strait, Cheju Island, coastal waters of Kyusyu, and the Pacific Ocean through Tokora Strait. The velocity of the current was estimated approximately as $0.3\~0.5$ miles per hour. 6. The bottom waters in the continental shelf break region flow toward the Korea Strait, Cheju Island and the coastal water of Kyusyu, while that of the continental shelf flows toward the Yellow Sea, 7, The characteristics of the Kuroshio water is changed remarkably by the mixing with the coastal water of China.

• Progress in Medical Physics
• /
• v.15 no.3
• /
• pp.161-166
• /
• 2004

A simplistic quality assurance (QA) method was designed for a Linac built-in enhanced dynamic wedge (EDW), which can be utilized to make wedged beam distributions. For the purpose of implementing the EDW symmetry QA, a film dosimetry system, low speedy dosimetry film, film densitometer and 3D RTP system were used, and the films irradiated by means of a 60$^{\circ}$ Reversed wedge pair (REWP) method. The profiles were then analyzed in terms of their symmetries, including partial treatment, which is the case of stopping it abruptly during EDW irradiation, and the measured and calculated values compared using the Cad Plan Golden Segmented Treatment Table (Golden STT). The result of this experiment was in good agreement, within 1 %, of the 'reversed wedge pair counterbalance effect'. For the QA of the effective wedge factor (EWF), the authors measured EWFs in relation to the 10$^{\circ}$, 15$^{\circ}$, 20$^{\circ}$, 25$^{\circ}$, 30$^{\circ}$, 45$^{\circ}$ and 60$^{\circ}$ EDW, which were compared with the calculated values using the correction factor derived from the Golden STT and the log files produced automatically during the process of EDW irradiation. By means of this method it was capable of check up the safety of effective wedge factor without any other dosimetry system. The EDW QA was able to be completed within 1 hour from irradiation to analysis as a consequence of the simplified QA procedure, with maximized effectiveness. Unlike the metal wedge system, the EDW system was heavily dependent on the dose rates and jaw movements; therefore, its features could potentially cause inaccuracy. The frequent simplistic QA for the EDW is essential, and could secure against the flaw of dynamic treatment that uses the EDW.

• Science of Emotion and Sensibility
• /
• v.19 no.1
• /
• pp.95-110
• /
• 2016

Uncanny valley refers to the condition where the affinity of a human-like object decreases dramatically if the object becomes extremely similar to human, and has been hypothesized to derive from the cognitive load of categorical conflict against an uncanny object. According to the hypothesis, the present study ran an oddball task consisting of trials each displaying one among a non-human, human and uncanny face, and measured event-related potentials (ERPs) for each trial condition. In Experiment 1, a non-human face was presented in 80% of the trials (standard) whereas a human face for another 10% trials (target) and an uncanny face for the remaining 10% trials (uncanny). Participants' responses were relatively inaccurate and delayed in both the target and uncanny oddball trials, but neither P3 nor N170 component differed across the three trial conditions. Experiment 2 used 3-D rendered realistic faces to increase the degree of categorical conflict, and found the behavioral results were similar to Experiment 1. However, the peak amplitude of N170 of the target and uncanny trials were higher than the standard trials while P3 mean amplitudes for both the target and uncanny trials were comparable but higher than the amplitude for the standard trials. P3 latencies were delayed in the order of the standard, target, and uncanny trials. The changes in N170 and P3 patterns across the experiments appear to arise from the categorical conflict that the uncanny face must be categorized as a non-target according to the oddball-task requirement despite its perceived category of a human face. The observed increase of cognitive load following the added reality to the uncanny face also indicates that the cognitive load, supposedly responsible for the uncanny experience, would depend on the increase of categorical conflict information subsequent to added stimulus complexity.