• The Journal of Internal Korean Medicine
• /
• v.41 no.6
• /
• pp.1052-1065
• /
• 2020

Objectives: To evaluate the reliability of a pattern identification tool for benign prostatic hyperplasia and to examine the relationship between pattern identification tool readings and IPSS and uroflowmetry. Methods: We analyzed 56 patients diagnosed with benign prostatic hyperplasia from December 27th, 2017 to December 26th, 2018 by two different Korean medical doctors and followed with a pattern identification tool and by IPSS and uroflowmetry. One week later, the patients were retested to analyze the reliability of the pattern identification tool, determined with the intraclass correlation coefficient (ICC) using the test-retest method. The correlation between IPSS and uroflowmetry was analyzed with the Pearson coefficient. Result: The reliability of the pattern identification tool for benign prostatic hyperplasia was evaluated as "poor agreement beyond chance" (ICC=0.349). The reliability of each pattern identification score was evaluated as "good" for Yang Deficiency of Kidney, Yin Deficiency of Kidney, Deficiency of Middle Qi, and Dampness-heat of Lower Energizer. The internal consistency was evaluated as "good" for Yang Deficiency of Kidney, Yin Deficiency of Kidney, and Dampness-heat of Lower Energizer, and as "excellent" for Deficiency of Middle Qi. The correlation between pattern identification and IPSS was evaluated as a "moderate positive correlation" for all pattern identifications. The average flow rate and maximum flow rate using uroflowmetry was evaluated with "moderate negative correlation" for Yang Deficiency of Kidney and Dampness-heat of Lower Energizer. Conclusion: The reliability of a pattern identification tool for benign prostatic hyperplasia was evaluated as "poor agreement beyond chance." Further research is needed.

• Korean Journal of Veterinary Service
• /
• v.23 no.1
• /
• pp.93-102
• /
• 2000

In this experiment, we studied the sero-positive rate of akabane virus in cattle from Jeju-do and analyzed the seroepidemiological features. In an analysis of 1,051 samples, the positive rate for neutralizing antibody in sera collected in nine regions on Jeju-do was 56.7%. The rate varied with the region. The positive rate was 69.6% in Aewol, 63.1% in Jeju city, 54.4% in Anduck, 51.0% in Hallim, 69.8% in Jocheun, 47.6% in Pyosun, 40% in Daejeong, 30.0% in Harkyung, 71.6% in Namwon, 24.5% in Sungsan, 133.,3% in Seokypo and 44.5% in Gujwa, respectively The rate also depended on the age of the cattle. The positive rate was 67.2% in calves 0- to 12-month old, 48.3% in cattle 13- to 24-month old, 65.4% in cattle 25- to 36-month old, and 65.4% in cattle more than ,B7 months old. To isolate the virus from calves with malformations including arthrogryposis and hydranencephaly, cerebral homogenates were inoculated into Vero cells, which were determined for cytopathic effect (CPE). Vero cells with CPE were examined for Akabane virus using an electron microscope (EM) and indirect immunofluorescent antibody test (EM). Typical virus particles with a width of 90-130nm and specific immunofluorescence in the cytoplasm of infected cells were sought for identification.

• International Journal of Internet, Broadcasting and Communication
• /
• v.7 no.2
• /
• pp.149-154
• /
• 2015

Biometric techniques for authentication using body parts such as a fingerprint, face, iris, voice, finger-vein and also photoplethysmography have become increasingly important in the personal security field, including door access control, finance security, electronic passport, and mobile device. Finger-vein images are now used to human identification, however, difficulties in recognizing finger-vein images are caused by capturing under various conditions, such as different temperatures and illumination, and noise in the acquisition camera. The human photoplethysmography is also important signal for human identification. In this paper To increase the recognition rate, we develop camera based identification method by combining finger vein image and photoplethysmography signal. We use a compact CMOS camera with a penetrating infrared LED light source to acquire images of finger vein and photoplethysmography signal. In addition, we suggest a simple pattern matching method to reduce the calculation time for embedded environments. The experimental results show that our simple system has good results in terms of speed and accuracy for personal identification compared to the result of only finger vein images.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.435-446
• /
• 2020

With the ability to learn rules from training data, the machine learning model can classify unknown objects. At the same time, the dimension of hyperspectral data is usually large, which may cause an over-fitting problem. In this research, an identification methodology of tea diseases was proposed based on spectral reflectance and machine learning, including the feature selector based on the decision tree and the tea disease recognizer based on random forest. The proposed identification methodology was evaluated through experiments. The experimental results showed that the recall rate and the F1 score were significantly improved by the proposed methodology in the identification accuracy of tea disease, with average values of 15%, 7%, and 11%, respectively. Therefore, the proposed identification methodology could make relatively better feature selection and learn from high dimensional data so as to achieve the non-destructive and efficient identification of different tea diseases. This research provides a new idea for the feature selection of high dimensional data and the non-destructive identification of crop diseases.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.441-447
• /
• 2022

In this paper, we propose a pill identification model using engraved text feature and image feature such as shape and color, and compare it with an identification model that does not use engraved text feature to verify the possibility of improving identification performance by improving recognition rate of the engraved text. The data consisted of 100 classes and used 10 images per class. The engraved text feature was acquired through Keras OCR based on deep learning and 1D CNN, and the image feature was acquired through 2D CNN. According to the identification results, the accuracy of the text recognition model was 90%. The accuracy of the comparative model and the proposed model was 91.9% and 97.6%. The accuracy, precision, recall, and F1-score of the proposed model were better than those of the comparative model in terms of statistical significance. As a result, we confirmed that the expansion of the range of feature improved the performance of the identification model.

• ETRI Journal
• /
• v.34 no.2
• /
• pp.168-174
• /
• 2012

In Advanced Television Systems Committee (ATSC) terrestrial digital television (DTV) systems, additional very low-rate data can be transmitted by modulating the amplitude and polarity of the transmitter identification (TxID) signal. Although the additional data transmission scheme offers reliable transmission and has a very large coverage area, it has a limitation on the data rate. In this paper, we propose a novel additional data transmission scheme based on the TxID sequences of the ATSC DTV system and Walsh modulation. The proposed scheme not only increases the data rate significantly, but also offers a virtually identical coverage area compared to a conventional scheme.

• Smart Media Journal
• /
• v.12 no.2
• /
• pp.56-65
• /
• 2023

In broadcasts such as news and coverage programs, voice is modulated to protect the identity of the informant. Adjusting the pitch is commonly used voice modulation method, which allows easy voice restoration to the original voice by adjusting the pitch. Therefore, since broadcast voice modulation methods cannot properly protect the identity of the speaker and are vulnerable to security, a new voice modulation method is needed to replace them. In this paper, using the Lightweight speech de-identification model as the evaluation target model, we compare speech de-identification performance with broadcast voice modulation method using pitch modulation. Among the six modulation methods in the Lightweight speech de-identification model, we experimented on the de-identification performance of Korean speech as a human test and EER(Equal Error Rate) test compared with broadcast voice modulation using three modulation methods: McAdams, Resampling, and Vocal Tract Length Normalization(VTLN). Experimental results show VTLN modulation methods performed higher de-identification performance in both human tests and EER tests. As a result, the modulation methods of the Lightweight model for Korean speech has sufficient de-identification performance and will be able to replace the security-weak broadcast voice modulation.

• Asia Marketing Journal
• /
• v.12 no.3
• /
• pp.1-24
• /
• 2010

Typically, marketing literature on innovation diffusion has focused on the pre-adoption process and only a few studies explicitly examined consumers' post-adoption behavior of innovative mobile services. Besides, prior use diffusion research has considered the variables that determine the consumers' initial adoption in explaining the post adoption usage behavior. However, behavioral sciences and individual psychology suggest that social influences are a potentially important determinant of usage behavior as well. The purpose of this study is to investigate into the effects of network factor and brand identification as social influences on the consumers' use diffusion or continued usage intention of a mobile service. Network factor designates consumer perception of the usefulness of a network, which embraces the concept of network externality and that of critical mass. Brand identification captures distinct aspects of social influence on technology acceptance that is not captured by subjective norm in situations where the technology use is voluntary. Additionally, this study explores the effect of the use diffusion on the brand switching intention, a generally unexplored form of post-adoption behavior. There are only a few empirical studies in the literature addressing the issue of IT user switching. In this study, the use diffusion comprises of rate of use and variety of use. The research hypotheses are as follows; H1. Network factor will have a positive influence on the rate of use of mobile services. H2. Network factor will have a positive influence on variety of use of mobile services. H3. Network factor will have a positive influence on continued usage intention. H4. Brand identification will have a positive influence on the rate of use. H5. Brand identification will have a positive influence on variety of use. H6. Brand identification will have a positive influence on continued usage intention. H7. Rate of use of mobile services are positively related to continued usage intention. H8. Variety of Use of mobile services are positively related to continued usage intention. H9. Rate of use of mobile services are negatively related to brand switching intention. H10. Variety of Use of mobile services are negatively related to brand switching intention. With the assistance of a marketing service company, a total of 1023 questionnaires from an online survey were collected. The survey was conducted only on those who have received or given a mobile service called "Gifticon". Those who answered insincerely were excluded from the analysis, so we had 936 observations available for a further stage of data analysis. We used structural equation modeling and overall fit was good enough (CFI=0.933, TLI=0.903, RMSEA=0.081). The results show that network factor and brand identification significantly increase the rate of use. But only brand identification increases variety of use. Also, network factor, brand identification and the use diffusion are positively related to continued usage intention. But the hypotheses that the use diffusion are positively related to brand switching intention were rejected. This result implies that continued usage intention cannot guarantee reducing brand switching intention.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1042-1045
• /
• 2003

In this paper, we propose the speaker identification system that uses vowel that has speaker's characteristic. System is divided to speech feature extraction part and speaker identification part. Speech feature extraction part extracts speaker's feature. Voiced speech has the characteristic that divides speakers. For vowel extraction, formants are used in voiced speech through frequency analysis. Vowel-a that different formants is extracted in text. Pitch, formant, intensity, log area ratio, LP coefficients, cepstral coefficients are used by method to draw characteristic. The cpestral coefficients that show the best performance in speaker identification among several methods are used. Speaker identification part distinguishes speaker using Neural Network. 12 order cepstral coefficients are used learning input data. Neural Network's structure is MLP and learning algorithm is BP (Backpropagation). Hidden nodes and output nodes are incremented. The nodes in the incremental learning neural network are interconnected via weighted links and each node in a layer is generally connected to each node in the succeeding layer leaving the output node to provide output for the network. Though the vowel extract and incremental learning, the proposed system uses low learning data and reduces learning time and improves identification rate.

• Journal of Biosystems Engineering
• /
• v.27 no.5
• /
• pp.451-458
• /
• 2002

This paper introduces that livestock can be effectively managed by an individual electronic identification system. The proposed system was composed of the original code transmitter, receiver, personal computer, micro-processor, and RS485 telecommunications module. In the individual electronic identification system, the signal including encoded information of a milk-cow was transmitted from an original code transmitter to a micro-processor through RS485 telecommunications module. The transmitted signal can be successfully displayed in a personal computer. This system can be managed by 9999 individuals with a original code transmitter. The recognition rate of an individual electronic identification system was 98.5% and also auto-feeder operates very well. an individual electronic identification system was developed for automation of stockbreeding management. To automate the breeding management, it is necessary to obtain and analyze the individual information distinguished from others preferentially.