• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.108-116
• /
• 2008

In this paper, we propose an algorithm that can estimate the distance using disparity based on stereo vision system, even though the obstacle is located in long ranges as well as short ranges. We use sub-pixel interpolation to minimize quantization errors which deteriorate the distance accuracy when calculating the distance with integer disparity, and also we use enhanced adaptive fuzzy strong tracking Kalman filter(EAFSTKF) to improve the distance accuracy and track the path optimally. The proposed method can solve the divergence problem caused by nonlinear dynamics such as various vehicle movements in the conventional Kalman filter(CKF), and also enhance the distance accuracy and reliability. Our simulation results show that the performance of our method improves by about 13.5% compared to other methods in point of root mean square error rate(RMSER).

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.02a
• /
• pp.166-176
• /
• 2002

A homonym could be disambiguated by another words in the context as nouns, predicates used with the homonym. This paper using semantic information (co-occurrence data) obtained from definitions of part of speech (POS) tagged UMRD-S$^1$), In this research, we have analyzed the result of an experiment on a homonym disambiguation system based on statistical model, to which Bayes'theorem is applied, and suggested a model established of the weight of sense rate and the weight of distance to the adjacent words to improve the accuracy. The result of applying the homonym disambiguation system using semantic information to disambiguating homonyms appearing on the dictionary definition sentences showed average accuracy of 98.32% with regard to the most frequent 200 homonyms. We selected 49 (31 substantives and 18 predicates) out of the 200 homonyms that were used in the experiment, and performed an experiment on 50,703 sentences extracted from Sejong Project tagged corpus (i.e. a corpus of morphologically analyzed words) of 3.5 million words that includes one of the 49 homonyms. The result of experimenting by assigning the weight of sense rate(prior probability) and the weight of distance concerning the 5 words at the front/behind the homonym to be disambiguated showed better accuracy than disambiguation systems based on existing statistical models by 2.93%,

• Journal of Biomedical Engineering Research
• /
• v.37 no.5
• /
• pp.161-167
• /
• 2016

Recent technological advances in sensor fabrication and bio-signal processing enabled non-constraint and non-intrusive measurement of human bio-signals. Especially, non-constraint measurement of ECG makes it available to estimate various human health parameters such as heart rate. Additionally, non-constraint ECG measurement of wheelchair user provides real-time health parameter information for emergency response. For accurate emergency response with low false alarm rate, it is necessary to discriminate quality levels of ECG measured using non-constraint approach. Health parameters acquired from low quality ECG results in inaccurate information. Thus, in this study, a machine learning based approach for three-class classification of ECG quality level is suggested. Three sensors are embedded in the back seat, chest belt, and handle of automatic wheelchair. For the two sensors embedded in back seat and chest belt, capacitively coupled electrodes were used. The accuracy of quality level classification was estimated using Monte Carlo cross validation. The proposed approach demonstrated accuracy of 94.01%, 95.57%, and 96.94% for each channel of three sensors. Furthermore, the implemented algorithm enables classification of user posture by detection of contacted electrodes. The accuracy for posture estimation was 94.57%. The proposed algorithm will contribute to non-constraint and robust estimation of health parameter of wheelchair users.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.19-26
• /
• 2012

The rapid increase of information imposes new demands of content management. The purpose of automatic audio segmentation and classification is to meet the rising need for efficient content management. With this reason, this paper proposes a high-accuracy algorithm that segments audio signals and classifies them into different classes such as speech, music, silence, and environment sounds. The proposed algorithm utilizes support vector machine (SVM) to detect audio-cuts, which are boundaries between different kinds of sounds using the parameter sequence. We then extract feature vectors that are composed of statistical data and they are used as an input of fuzzy c-means (FCM) classifier to partition audio-segments into different classes. To evaluate segmentation and classification performance of the proposed SVM-FCM based algorithm, we consider precision and recall rates for segmentation and classification accuracy for classification. Furthermore, we compare the proposed algorithm with other methods including binary and FCM classifiers in terms of segmentation performance. Experimental results show that the proposed algorithm outperforms other methods in both precision and recall rates.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.6 no.1
• /
• pp.3-12
• /
• 1988

The objective of this paper is to study the characteristics of combination method to correct both angle and distance errors simultaneously based on the least square adjustment methods. Changing the standard errors of distance and angle, the simulation errors of triangultion, trilateration, and combination result in some 39.8%, 33.9%, and 26.3% respectively. As the above, combination method shows more consistent accuracy than other methods. When considering the weight factor about error elements with independence, the diminishing rate of simulated average standard error represents a various change in each method. But considering them simultaneously, it shows a remarkable rate of diminishing 75.5%, 74.1%, and 69.2% in each method. And also, by growing the weight factor, accuracy of triangulation method is growing, whereas that of trilateration is diminishing. Therefore, determining the reasonable weight factors of distance and angle errors simultaneously in the analytical combination method, this method is expected to be one of more accurate and more effective methods for determining horizontal positions on the earth.

• Journal of Korea Game Society
• /
• v.17 no.2
• /
• pp.17-26
• /
• 2017

Excessive use of the internet and smart phones have become a social issue. The level of engagement has both positive and negative effects such as good performance or indulgence phenomenon, respectively. This study was to develop an algorithm to determine the engagement state based on cardiovascular response. The participants were asked to play a pattern matching game and the experimental design was divided into cooperation and competition task to provide the level of engagement. The correlation between heart rate and amplitude was analyzed according to each task. The regression equation and accuracy were verified by polynomial regression analysis. The results showed that heart rate and amplitude were positively correlated when the task was a game, and negatively correlated when there was a reference task. The accuracy of classifying between game and reference task was 89%. The accuracy between tasks was confirmed to be 76.5%. This study is expected to be used to quantitatively evaluate the level of engagement in real time.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.86.1-86.1
• /
• 2011

We are developing a new universal spectropolarimeter on the Domeless Solar Telescope (DST) at the Hida Observatory to realize precise spectropolarimetric observations in a wide range of wavelength in visible and near infrared. The system aims to open a new window of plasma diagnostics by using Zeeman effect, Hanle effect, Stark effect, impact polarization, and atomic polarization for measuring the external magnetic field, electric field, or an anisotropy in the excitation of the atoms. The polarimeter is a successor of formerly developed polarimeter on DST, which make possible to observe a polarization in a photospheric spectral line with polarimetric accuracy of 10-2 (Kiyohara et al. 2004). The new system consists of a 60cm aperture vacuum telescope, a high dispersion vacuum spectrograph, polarization modulator / analyzer composed of a rotating waveplate whose retardation is constant for a wide range of wavelength and Wallaston prism, and a fast and large format CCD camera or IR camera. Spectral images in both orthogonal polarizations are taken simultaneously with a frame rate of ~20Hz while the waveplate rotates continuously in a rate of 1rev./sec. Thus It takes 5 ~ 60 sec to observe polarization with accuracy of 10-3 in a wide wavelength range (400 - 1100nm). We also examined a polarimetric model of the telescope with accuracy of 10-3 to calibrate instrumental polarization on some wavelengths. In this talk, I will focus on the performance of the instrument.

• Korean Journal of Clinical Laboratory Science
• /
• v.41 no.4
• /
• pp.189-195
• /
• 2009

Lung cancer is a type of cancer with high mortality; its 5-year survival rate is at a low 14%. Related cytological tests include sputum, bronchial brushing, bronchial washing and fine needle aspiration cytology test etc. From the test specimens in which sputum, bronchial brushing, bronchial washing, and fine needle aspiration cytology were performed, the sensitivity, specificity and accuracy between cytology test and histology test. In the sputum test, sensitivity was 27.71% and specificity was 98.02%, and the bronchial brushing test showed sensitivity of 93.33% and a specificity of 91.3%. The bronchial washing test was a sensitivity of 53.7% and its specificity was 98.9%, and the fine needle aspiration cytology test showed sensitivity and specificity were 88.46% and 72.97%, respectively. In the specimens diagnosed as normal at the sputum test, malignant diagnosis was found in 21 specimens of bronchial brushing, 30 cases of bronchial washings and 37 cases of fine needle aspiration cytology specimens. In the specimens diagnosed as normal at the bronchial washing test, malignant diagnosis was found in 5 specimens of sputum, 7 specimens of bronchial brushin and 1 cases of fine needle aspiration cytology. One specimens found to be normal in fine needle aspiration cytology turned out to maligant in sputum test. The result of this research shows that, in diagnosis lung cancer, a test method of high sensitivity and specificity should be pursued. However, depending on the location and malignancy of the illness, diagnosis may not be obtained in some cases. Therefore, we conclude that the cytological tests performed for lung cancer testing such as sputum, bronchial brushing, bronchial washing, and fine needle aspiration cytology should be carried out in a mutually complementary manner.

• The Korean Journal of Pain
• /
• v.35 no.3
• /
• pp.319-326
• /
• 2022

Background: As the internet usage becomes easily accessible, the patients are more frequently searching about diseases and medical/non-medical treatments. Considering that complex regional pain syndrome (CRPS) is a debilitating disease, it is important to check the information that patients are accessing. Therefore, this study aimed to investigate the reliability, sufficiency, and accuracy of the YouTube videos about CRPS. Methods: This study is a descriptive research which is derived by searching videos using the keyword 'complex regional pain syndrome' on YouTube. Relevance-based sequencing was used to sort the videos. Sources and video parameters were documented. To evaluate the accuracy, reliability and content quality of the videos, Global Quality Score, Journal of American Medical Association Benchmark Criteria and Modified DISCERN Questionnaire scales were used. Results: A total of 167 videos were included in this study. The majority of the videos originated from USA (80.2%, n = 134). The median number of views was 639 and the viewing rate was 73.3. Most of the videos had partially sufficient data and the interaction index viewing rate parameters for videos with high content quality were greater than videos with low content quality (P = 0.010, P = 0.014). Conclusions: Our results showed that videos about CRPS on YouTube mostly had partially sufficient data and include intermediate-high quality contents. Moreover, high-content quality videos had higher viewing rates, interaction indexes, number of likes, longer durations, as well as better reliability and accuracy scores. Videos with high quality and reliable content are needed to reduce misinformation about CRPS.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.570-590
• /
• 2024

Breast cancer ranks among the most prevalent forms of malignancy and foremost cause of death by cancer worldwide. It is not preventable. Early and precise detection is the only remedy for lowering the rate of mortality and improving the probability of survival for victims. In contrast to present procedures, thermography aids in the early diagnosis of cancer and thereby saves lives. But the accuracy experiences detrimental impact by low sensitivity for small and deep tumours and the subjectivity by physicians in interpreting the images. Employing deep learning approaches for cancer detection can enhance the efficacy. This study explored the utilization of thermography in early identification of breast cancer with the use of a publicly released dataset known as the DMR-IR dataset. For this purpose, we employed a novel approach that entails the utilization of a pre-trained MobileNetV2 model and fine tuning it through transfer learning techniques. We created three models using MobileNetV2: one was a baseline transfer learning model with weights trained from ImageNet dataset, the second was a fine-tuned model with an adaptive learning rate, and the third utilized early stopping with callbacks during fine-tuning. The results showed that the proposed methods achieved average accuracy rates of 85.15%, 95.19%, and 98.69%, respectively, with various performance indicators such as precision, sensitivity and specificity also being investigated.