• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.186-191
• /
• 2023

Neural Networks are widely used for huge variety of tasks solution. Machine Learning methods are used also for signal and time series analysis, including electrocardiograms. Contemporary wearable devices, both medical and non-medical type like smart watch, allow to gather the data in real time uninterruptedly. This allows us to transfer these data for analysis or make an analysis on the device, and thus provide preliminary diagnosis, or at least fix some serious deviations. Different methods are being used for this kind of analysis, ranging from medical-oriented using distinctive features of the signal to machine learning and deep learning approaches. Here we will demonstrate a neural network-based approach to this task by building an ensemble of 1D CNN classifiers and a final classifier of selection using logistic regression, random forest or support vector machine, and make the conclusions of the comparison with other approaches.

• KSBB Journal
• /
• v.24 no.6
• /
• pp.591-597
• /
• 2009

B-type natriuretic peptide is a neurohormone secreted in the cardiac ventricles. BNP levels are elevated in patients with ventricular dysfunction. Therefore, the concentration of BNP is important factor to reflect diagnosis and prognosis for cardiovascular disease. In this respect, anti-BNP scFv is an urgent requirement for early diagnosis in the field of biosensor. Herein, the genetic codes of anti-BNP scFv were chemically synthesized and cloned into both pET22b (+) and pColdⅣ vector, respectively. The recombinant scFv was successfully expressed as a functional form in cytoplasm of E. coli and detected through Western blot and ELISA. The highest level of functional expression of anti-BNP scFv was achieved using pET22b (+) vector at $15^{\circ}C$ by addition of 0.1 mM IPTG. Additionally, being exposed to both BNP and ANP, anti-BNP scFv specifically captured only BNP. Therefore, anti-BNP scFv expressed in this study will be applied to measure the concentration of BNP as a diagnostic recognition molecule.

• Journal of Veterinary Clinics
• /
• v.32 no.5
• /
• pp.473-475
• /
• 2015

A 12-year-old intact male, Alaskan Malamute dog, which lives in the countryside, was presented with inflammation and pain around perineal areas. Thorough examination revealed maggots and punched-out round holes lesion around the perineal region. Complete blood counts (CBC) and serum biochemical examinations showed no remarkable findings except mild anemia and mild thrombocytosis. The diagnosis was easily done, based on clinical signs and maggots identification. Cleaning with chlorhexidine, povidone-iodine lavage and hair clipping away from the lesions were performed soon after presentation. SNAP 4Dx Test (IDEXX Laboratories, Westbrook, ME, USA) was performed to rule out other vector-borne diseases since the ticks were found on the clipped area and vector-borne pathogens. The test result was negative. The dog in this case was treated with ivermectin (300 mcg/kg SC) one time. Also, treatments with amoxicillin clavulanate (20 mg/kg PO, BID) was established to prevent secondary bacterial infections. Then, myiasis resolved with 2 weeks and the affected area was healed.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.2
• /
• pp.835-838
• /
• 2016

Background: Lung cancer remains one of the most common cancers in the world, both in terms of new cases (about 13% of total per year) and deaths (nearly one cancer death in five), because of the high case fatality. Errors in lung cancer type or malignant growth determination lead to degraded treatment efficacy, because anticancer strategy depends on tumor morphology. Materials and Methods: We have made an attempt to evaluate effectiveness of machine learning algorithms in the task of lung cancer classification based on gene expression levels. We processed four publicly available data sets. The Dana-Farber Cancer Institute data set contains 203 samples and the task was to classify four cancer types and sound tissue samples. With the University of Michigan data set of 96 samples, the task was to execute a binary classification of adenocarcinoma and non-neoplastic tissues. The University of Toronto data set contains 39 samples and the task was to detect recurrence, while with the Brigham and Women's Hospital data set of 181 samples it was to make a binary classification of malignant pleural mesothelioma and adenocarcinoma. We used the k-nearest neighbor algorithm (k=1, k=5, k=10), naive Bayes classifier with assumption of both a normal distribution of attributes and a distribution through histograms, support vector machine and C4.5 decision tree. Effectiveness of machine learning algorithms was evaluated with the Matthews correlation coefficient. Results: The support vector machine method showed best results among data sets from the Dana-Farber Cancer Institute and Brigham and Women's Hospital. All algorithms with the exception of the C4.5 decision tree showed maximum potential effectiveness in the University of Michigan data set. However, the C4.5 decision tree showed best results for the University of Toronto data set. Conclusions: Machine learning algorithms can be used for lung cancer morphology classification and similar tasks based on gene expression level evaluation.

• Advances in pediatric surgery
• /
• v.5 no.2
• /
• pp.103-110
• /
• 1999

To estimate the normal anal canal pressure in neonates, anal manometry was performed in 46 normal babies less than 6 days of age. Twenty-eight of the subjects were boys and 18 girls. All the subjects passed meconium within 24 hours after birth. Birth weights were above 2.4 kg. There were no sexual differences in birth weight, birth height, gestational age, postnatal age, or Apgar score (p<0.05). The mean manometry values were; anal sphincter length $18.6{\pm}3.9$ mm, high pressure zone (HPZ) $9.2{\pm}3.6$ mm, vector volume $2027.2{\pm}2440.7$ mmHg2cm, maximum pressure $42.3{\pm}17.4$ mmHg, and position of the maximum pressure $6.0{\pm}22.4$ mm. Only the HPZ of boys was longer than those of girls (p=0.005). In squeezing state, HPZ and the position of maximun pressure were not changed from resting state. HPZ, vector volume, and maximum pressure in boys were higher than those in girls. As the birth weight increased, the anal sphincter length (p=0.001) and the HPZ increased (p=0.047). The resting pressures of the anal canal were evaluated in three portions; /23 upper portion, $12.8{\pm}8.6$ mmHg, middle portion, $20.3{\pm}10.8$ mmHg, and lower portion, $26.1{\pm}12.9$ mmHg. These normal values may serve as guidelines for the evaluation, diagnosis and treatment of neonatal anal diseases.

• The Journal of Korean Society of Virology
• /
• v.27 no.2
• /
• pp.151-160
• /
• 1997

In view of the potential of replicase protein as a diagnostic reagent for human caliciviruses (HuCVs), we have cloned and over-expressed this gene from the Snow Mountain-like Korean strains in Escherichia coli as a fusion protein with glutathione S-transferase (GST), and described the preliminary antigenic characterization of the recombinant products. Each 470bp fragment corresponding to highly conserved region of RNA-dependent RNA polymerase was generated by RT-PCR from stools of two diarrheal children, cloned in pMOSBlue T-vector, and subcloned between the EcoRI and SalI restriction sites of pGEX-4T-3, a GST gene fusion vector, yielding $pGCV_{pol}$. This construct expressed a Snow Mountain-like HuCV replicase under the control of the IPTG-inducible tac promoter. An extract prepared by sonication of the E. coli cell inclusion bodies bearing $pGCV_{pol}$ products was purified and analyzed by SDS-PAGE. After Coomassie blue staining, it was shown that the recombinant replicase migrated on the gels with an approximate molecular mass of 46.5 kDa, that was subsequently cleaved into a 26 kDa GST fragment and a 20.5 kDa replicase protein upon digestion with thrombin protease. The replicase was recognized on immunoblotting with the sera from symptomatic children with the HuCV-associated diarrhea but not by asymptomatic sera from adults. The results presented the first biological activity of individually expressed HuCV replicase subunit and provided important reagents for diagnosis of HuCV infection.

• Journal of the Korea Society for Simulation
• /
• v.20 no.2
• /
• pp.77-85
• /
• 2011

It is believed that the anomalies or diseases of human organs are identified by the analysis of the patterns. This paper proposes a new classification technique for the identification of cancer disease using the proteome patterns obtained from two-dimensional polyacrylamide gel electrophoresis(2-D PAGE). In the new classification method, three different classification methods such as support vector machine(SVM), multi-layer perceptron(MLP) and k-nearest neighbor(k-NN) are extended by multi-boosting method in an array of subclassifiers and the results of each subclassifier are merged by ensemble method. Genetic algorithm was applied to obtain optimal feature set in each subclassifier. We applied our method to empirical data set from cancer research and the method showed the better accuracy and more stable performance than single classifier.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.17-24
• /
• 2014

This paper proposes a fault detection method for low-speed rolling element bearings of an induction motor using acoustic emission signals and histogram modeling. The proposed method performs envelop modeling of the histogram of normalized fault signals. It then extracts and selects significant features of each fault using partial autocorrelation coefficients and distance evaluation technique, respectively. Finally, using the extracted features as inputs, the support vector regression (SVR) classifies bearing's inner, outer, and roller faults. To obtain optimal classification performance, we evaluate the proposed method with varying an adjustable parameter of the Gaussian radial basis function of SVR from 0.01 to 1.0 and the number of features from 2 to 150. Experimental results show that the proposed fault identification method using 0.64-0.65 of the adjustable parameter and 75 features achieves 91% in classification performance and outperforms conventional fault diagnosis methods as well.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1333-1342
• /
• 2018

Until now, Electroencephalography(: EEG) has been the most important and convenient method for the diagnosis and treatment of epilepsy. However, it is difficult to identify the wave characteristics of an epileptic EEG signals because it is very weak, non-stationary and has strong background noise. In this paper, we analyse the effect of dimensionality reduction methods on Epileptic EEG feature selection and classification. Three dimensionality reduction methods: Pincipal Component Analysis(: PCA), Kernel Principal Component Analysis(: KPCA) and Linear Discriminant Analysis(: LDA） were investigated. The performance of each method was evaluated by using Support Vector Machine SVM, Logistic Regression(: LR), K-Nearestneighbor(: K-NN), Decision Tree(: DR) and Random Forest(: RF). From the experimental result, PCA recorded 75% of highest accuracy in SVM, LR and K-NN. KPCA recorded 85% of best performance in SVM and K-KNN while LDA achieved 100% accuracy in K-NN. Thus, LDA dimensionality reduction is found to provide the best classification result for epileptic EEG signal.

• The Journal of the Korea Contents Association
• /
• v.21 no.4
• /
• pp.825-832
• /
• 2021

In this study, by selecting specific aptamers that selectively detection on P. gingivalis, the main cause of periodontal disease, and purifying and identifying protein molecules that bind to the selected aptamers, the mechanism of action of P. gingivalis was investigated. A DNA library having 39 random sequences was prepared, and aptamers with specificity for P. gingivalis were selected using the SELEX method, and the nucleotide sequence was analyzed by cloning using PCR2.1 cloning vector. 8 of aptamers with different nucleotide sequences were selected, and modified weston blot was performed using APG-3 among the selected aptamers to identify 11 proteins that act directly, and proteins were analyzed. As a result, a protein that selectively binds to P. gingivalis was isolated and identified. Therefore, aptamer selectively binds and attaches to proteins related to inhibition of sugar metabolism and cell activity of P. gingivalis, suggesting the possibility of a sensor for diagnosis of periodontal disease.