• Journal of fish pathology
• /
• v.11 no.1
• /
• pp.61-67
• /
• 1998

For rapid detection of iridovirus infection, a PCR-based diagnostic method was developed. The genomic DNA from mortality-associated iridovirus was cloned into pUC19 vector. The nucleotide sequences of these clones were compared with sequences of other genes from EMBL/GenBank databank. Based on the nucleotide sequences, PCR primers were prepared and used for PCR. The DNA amplification did not occur from the normal fish cells. In contrast, DNA was amplified from the iridovirus-infected fish cells and purified iridovirus. These results suggest that mortality-associated iridovirus can be detected from virus-infected cells within short time and this PCR-based diagnostic system provides a simple and accurate method for detecting the presence of iridovirus infection.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.184-192
• /
• 2022

Valve internal leakage is caused by damage to the internal parts of the valve, resulting in accidents and shutdowns of the piping system. This study investigated the possibility of a real-time leak detection method using the acoustic emission (AE) signal generated from the piping system during the internal leakage of a butterfly valve. Datasets of raw time-domain AE signals were collected and postprocessed for each operation mode of the valve in a systematic manner to develop a data-driven model for the detection and classification of internal leakage, by applying machine learning algorithms. The aim of this study was to determine whether it is possible to treat leak detection as a classification problem by applying two classification algorithms: support vector machine (SVM) and convolutional neural network (CNN). The results showed different performances for the algorithms and datasets used. The SVM-based binary classification models, based on feature extraction of data, achieved an overall accuracy of 83% to 90%, while in the case of a multiple classification model, the accuracy was reduced to 66%. By contrast, the CNN-based classification model achieved an accuracy of 99.85%, which is superior to those of any other models based on the SVM algorithm. The results revealed that the SVM classification model requires effective feature extraction of the AE signals to improve the accuracy of multi-class classification. Moreover, the CNN-based classification can be a promising approach to detect both leakage and valve opening as long as the performance of the processor does not degrade.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.1-11
• /
• 2023

Breast cancer is the disease that affects women the most worldwide. Due to the development of computer technology, the efficiency of machine learning has increased, and thus plays an important role in cancer detection and diagnosis. Deep learning is a field of machine learning technology based on an artificial neural network, and its performance has been rapidly improved in recent years, and its application range is expanding. In this paper, we propose a DNN-SVM hybrid model that combines the structure of a deep neural network (DNN) based on transfer learning and a support vector machine (SVM) for breast cancer classification. The transfer learning-based proposed model is effective for small training data, has a fast learning speed, and can improve model performance by combining all the advantages of a single model, that is, DNN and SVM. To evaluate the performance of the proposed DNN-SVM Hybrid model, the performance test results with WOBC and WDBC breast cancer data provided by the UCI machine learning repository showed that the proposed model is superior to single models such as logistic regression, DNN, and SVM, and ensemble models such as random forest in various performance measures.

• Current Optics and Photonics
• /
• v.4 no.1
• /
• pp.31-43
• /
• 2020

The feasibility of the application of terahertz electromagnetic waves in the diagnosis of prostate cancer was examined. Four samples of incomplete cancerous prostatic paraffin-embedded tissues were examined using terahertz spectral imaging (TPI) system and the results obtained by comparing the absorption coefficient and refractive index of prostate tumor, normal prostate tissue and smooth muscle from one of the paraffin tissue masses examined were reported. Three hundred and sixty cases of absorption coefficients from one of the paraffin tissues examined were used as raw data to classify these three tissues using the Principal Component Analysis (PCA) and Least Squares Support Vector Machine (LS-SVM). An excellent classification with an accuracy of 92.22% in the prediction set was achieved. Using the distribution information of THz reflection signal intensity from sample surface and absorption coefficient of the sample, an attempt was made to use the TPI system to identify the boundaries of the different tissues involved (prostate tumors, normal and smooth muscles). The location of three identified regions in the terahertz images (frequency domain slice absorption coefficient imaging, 1.2 THz) were compared with those obtained from the histopathologic examination. The tissue tumor region had a distinctively visible color and could well be distinguished from other tissue regions in terahertz images. Results indicate that a THz spectroscopy imaging system can be efficiently used in conjunction with the proposed advanced computer-based mathematical analysis method to identify tumor regions in the paraffin tissue mass of prostate cancer.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.722-729
• /
• 2010

Prediction problems are widely used in medical domains. For example, computer aided diagnosis or prognosis is a key component in a CDSS (Clinical Decision Support System). SVMs with nonlinear kernels like RBF kernels, have shown superior accuracy in prediction problems. However, they are not preferred by physicians for medical prediction problems because nonlinear SVMs are difficult to visualize, thus it is hard to provide intuitive interpretation of prediction results to physicians. Nomogram was proposed to visualize SVM classification models. However, it cannot visualize nonlinear SVM models. Localized Radial Basis Function (LRBF) was proposed which shows comparable accuracy as the RBF kernel while the LRBF kernel is easier to interpret since it can be linearly decomposed. This paper presents a new tool named VRIFA, which integrates the nomogram and LRBF kernel to provide users with an interactive visualization of nonlinear SVM models, VRIFA visualizes the internal structure of nonlinear SVM models showing the effect of each feature, the magnitude of the effect, and the change at the prediction output. VRIFA also performs nomogram-based feature selection while training a model in order to remove noise or redundant features and improve the prediction accuracy. The area under the ROC curve (AUC) can be used to evaluate the prediction result when the data set is highly imbalanced. The tool can be used by biomedical researchers for computer-aided diagnosis and risk factor analysis for diseases.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.112-124
• /
• 2010

Studies that can find resolutions to problems of subjective psychiatric analysis must be performed and indeed they are in the process. However there still lies many problems in researches of mentality examination, which should be the foundation of finding potential resolutions. One of the biggest problems in the conventional system is that there are many different opinions by psychiatrists depending on their educations and experiences. There is no objective standard on the subjects and there is no effective psychiatric analysis method. Also, the characteristic of such examinations is that it cannot be applied to disabilities, foreigners and infants alyce the examination is ch examinconversation. The objective of this atudy is to standardize TAT(Thematic Apperception Test)analysiBallken index method so that subjective data from the examination can be excluded and the examination thus maklysithe examination objectified. Furthermore, objective result and patients' brain wave pattern is read with BCI(Brain Computer Interface) ch exaTherenvironment to Alsare it to brain wave characteristics vectors to reate brain-wave characteristics vector DB. Therefore, such DB can be utilize durlysithe examination and diagnosis to reate objective examination method and standardized diagnosis system. Thus, mentality examination can be performed only with brain-wave scans with BCI based TAT system.

• Korean Journal of Agricultural Science
• /
• v.43 no.1
• /
• pp.21-27
• /
• 2016

Apple stem grooving virus (ASGV), Apple chlorotic leaf spot virus (ACLSV), and Apple stem pitting virus (ASPV) have been known to induce top working disease causing economical damage in apple. Occurrences of these three viruses in pome fruit trees, including apple, have been reported around the world. The transmission of the three viruses was reported by grafting, and there was no report of transmission through mechanical contact, insect vector, or seed except some herbaceous hosts of ASGV. As RNA extraction methods for fruit trees, Reverse Transcriptase-Polymerase Chain Reaction (RT-PCR) and multiplex RT-PCR techniques have been improved for reliability and stability, and low titer viruses that could not be detected in the past have become detectable. We studied the seed transmission ability of three apple viruses through apple seedling diagnosis using RT-PCR. Nineteen seeds obtained from commercially grown apple were germinated and two of the resulting plants were ASGV positive. Seven clones of the amplified ASGV coat protein (CP) genes of these isolates were sequenced. Overall sequence identities were 99.84% (nucleotide) and 99.76% (amino acid). Presence of a previously unreported single nucleotide and amino acid variation conserved in all of these clones suggests a possible association with seed transmission of these 'S' isolates. A phylogenetic tree constructed using ASGV CP nucleotide sequences showed that isolate S sequences were grouped with Korean, Chinese, Indian isolates from apple and Indian isolates from kiwi.

• Parasites, Hosts and Diseases
• /
• v.56 no.1
• /
• pp.61-70
• /
• 2018

We developed a Rapid Diagnostic Test (RDT) kit for detecting IgG/IgM antibodies against Zika virus (ZIKV) using monoclonal antibodies to the envelope (E) and non-structural protein 1 (NS1) of ZIKV. These proteins were produced using baculovirus expression vector with Sf9 cells. Monoclonal antibodies J2G7 to NS1 and J5E1 to E protein were selected and conjugated with colloidal gold to produce the Zika IgG/IgM RDT kit (Zika RDT). Comparisons with ELISA, plaque reduction neutralization test (PRNT), and PCR were done to investigate the analytical sensitivity of Zika RDT, which resulted in 100% identical results. Sensitivity and specificity of Zika RDT in a field test was determined using positive and negative samples from Brazil and Korea. The diagnostic accuracy of Zika RDT was fairly high; sensitivity and specificity for IgG was 99.0 and 99.3%, respectively, while for IgM it was 96.7 and 98.7%, respectively. Cross reaction with dengue virus was evaluated using anti-Dengue Mixed Titer Performance Panel (PVD201), in which the Zika RDT showed cross-reactions with DENV in 16.7% and 5.6% in IgG and IgM, respectively. Cross reactions were not observed with West Nile, yellow fever, and hepatitis C virus infected sera. Zika RDT kit is very simple to use, rapid to assay, and very sensitive, and highly specific. Therefore, it would serve as a choice of method for point-of-care diagnosis and large scale surveys of ZIKV infection under clinical or field conditions worldwide in endemic areas.

• Research in Plant Disease
• /
• v.18 no.3
• /
• pp.231-235
• /
• 2012

Indian citrus ring spot virus (ICRSV) is known to cause a serious disease to citrus, especially to Kinnow mandarin, the popular cultivated citrus species in India. In this study, we developed diagnostic systems based on enzyme-linked immunosorbent assay (ELISA). In order to generate antibodies against ICRSV coat protein, we overexpressed the coat protein in Escherichia coli using the pET15b expression vector containing an optimized ICRSV coat protein gene. The recombinant ICRSV coat protein was overexpressed as soluble form at $37^{\circ}C$ upon IPTG induction. The protein was purified to 95% in purity by Ni-NTA column chromatography. The purified protein was immunized to rabbit for the generation of polyclonal antibody (PAb). The PAb showed a specific immunoreaction to recombinant ICRSV coat protein in western blot analysis and ELISA. Diluted rabbit antisera (10,000 fold) could detect less than 10 ng and 5 ng of the target protein in western blot and ELISA analysis, respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.16-22
• /
• 2010

Electrocardiogram(ECG) analysis and arrhythmia recognition are critical for diagnosis and treatment of ill patients. Cardiac arrhythmia is a condition in which heart beat may be irregular and presents a serious threat to the patient recovering from ventricular tachycardia (VT) and ventricular fibrillation (VF). Other arrhythmias like atrial premature contraction (APC), Premature ventricular contraction (PVC) and superventricular tachycardia (SVT) are important in diagnosing the heart diseases. This paper presented new method to classify various arrhythmias contrary to other techniques which are limited to only two or three arrhythmias. ECG is decomposed into Intrinsic Mode Functions (IMFs) by Empirical Mode Decomposition (EMD). Burg algorithm was performed on IMFs to obtain AR coefficients which can reduce the dimension of feature vector and utilized as Multi-class SVM inputs which is basically extended from binary SVM. We chose optimal parameters for SVM classifier, applied to arrhythmias classification and achieved the accuracies of detecting NSR, APC, PVC, SVT, VT and VP were 96.8% to 99.5%. The results showed that EMD was useful for the preprocessing and feature extraction and multi-class SVM for classification of cardiac arrhythmias, with high usefulness.