• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.54-63
• /
• 2023

High and intermittent loading cycles induce fatigue damage to transmission components, resulting in premature gearbox failure. To identify gearbox defects, numerous vibration-based diagnostics techniques, using several artificial intelligence (AI) algorithms, have recently been presented. In this paper, an optimized deep belief network (DBN) model for gearbox problem diagnosis was designed based on time-frequency visual pattern identification. To optimize the hyperparameters of the model, a particle swarm optimization (PSO) approach was integrated into the DBN. The proposed model was tested on two gearbox datasets: a wind turbine gearbox and an experimental gearbox. The optimized DBN model demonstrated strong and robust performance in classification accuracy. In addition, the accuracy of the generated datasets was compared using traditional ML and DL algorithms. Furthermore, the proposed model was evaluated on different partitions of the dataset. The results showed that, even with a small amount of sample data, the optimized DBN model achieved high accuracy in diagnosis.

• Computers and Concrete
• /
• v.33 no.4
• /
• pp.409-423
• /
• 2024

Using an extensive database, a sensitivity analysis across fifteen machine learning (ML) classifiers was conducted to evaluate the impact of various data manipulation techniques, evaluation metrics, and explainability tools. The results of this sensitivity analysis reveal that the examined models can achieve an accuracy ranging from 72-93% in predicting the fire-induced spalling of concrete and denote the light gradient boosting machine, extreme gradient boosting, and random forest algorithms as the best-performing models. Among such models, the six key factors influencing spalling were maximum exposure temperature, heating rate, compressive strength of concrete, moisture content, silica fume content, and the quantity of polypropylene fiber. Our analysis also documents some conflicting results observed with the deep learning model. As such, this study highlights the necessity of selecting suitable models and carefully evaluating the presence of possible outcome biases.

• Tuberculosis and Respiratory Diseases
• /
• v.47 no.3
• /
• pp.321-330
• /
• 1999

Background : Early diagnosis and proper antibiotic treatment are very important in the management of ventilator-associated pneumonia (VAP) because of its high mortality. Bronchoscopy with a protected specimen brush (PSB) has been considered the standard method to isolate the causative organisms of VAP. However, this method burdens consumer economically to purchase a PSB. Another useful method for the diagnosis of VAP is quantitative cultures of aspirated specimens through bronchoscopic bronchoalveolar lavage (BAL), for which the infusion of more than 120 m1 of saline has been recommended for adequate sampling of a pulmonary segment. However, occasionally it leads to deterioration of the patient's condition. We studied the diagnostic efficacy of minibronchoalveolar lavage (miniBAL), which retrieves only 25 ml of BAL fluid, in the isolation of causative organisms of VAP. Methods: We included 38 consecutive patients (41 cases) suspected of having VAP on the basis of clinical evidence, who had received antibiotics before the bronchoscopy. The two diagnostic techniques of PSB and miniBAL, which were performed one after another at the same pulmonary segment, 'were compared prospectively. The cut-off values for quantitative cultures to define causative bacteria of VAP were more than $10^3$ colony-forming units (cfu)/ml for PSB and more than $10^4$ cfu/ml for BAL. Results: The amount of instilled normal saline required to retrieve 25 ml of BAL fluid was $93{\pm}32 ml$ (mean${\pm}$SD). The detection rate of causative agents was 46.3% (19/41) with PSB and 43.9% (18/41) with miniBAL. The concordance rate of PSB and miniBAL in the bacterial culture was 85.4% (35/41). Although arterial blood oxygen saturation dropped significantly (p<0.05) during ($92{\pm}10%$) and 10 min after ($95{\pm}3%$) miniBAL compared with the baseline ($97{\pm}3%$), all except 3 cases were within normal ranges. The significantly elevated heart rate during ($l25{\pm}24$/min, p<0.05) miniBAL compared with the baseline ($1l1{\pm}22$/min) recovered again in 10 min after ($111{\pm}26$/min) miniBAL. Transient hypotension was developed during the procedure in two cases. The procedure was stopped in one case due to atrial flutter. Conclusion: MiniBAL is a safe and effective technique to detect the causative organisms of VAP.

• Reproductive and Developmental Biology
• /
• v.32 no.4
• /
• pp.217-222
• /
• 2008

The techniques of IVM, IVF and IVC of canine oocytes may provide useful information for gamete salvage programs and the conservation of endangered canidae. This investigation has been made to determine the efficiency of in vitro maturation (IVM) as a basic experiment to study the development of canine oocytes after in vitro fertilization (IVF). The rate of oocytes developing to the Mil stage was higher in the hormone treated group (10 IU/ml hCG+eCG, 14.7%, p<0.05) than in the control group (0 IU/ml hCG+eCG, 10.0%). The monospermy and pronuclear rates of canine oocytes were investigated after caffeine treatment on IVF. Canine oocytes were fertilized in the Fert-TALP medium supplemented with 0, 10, 20 or 30 mM caffeine (Fert I, Fert II, Fert III or Fert IV, respectively). The highest pronuclear formation rate was obtained in the Fert I for 24 h IVF (6.7%, 6/89). Therefore, it is believed that unlike in other mammals, caffeine in canine IVF does not increase the efficiency of fertilization rate, and is not an important factor.

• Journal of Forest and Environmental Science
• /
• v.24 no.2
• /
• pp.111-118
• /
• 2008

Pull-out resistance tests of root were carried out for 7 shrub species which are mainly used greening of deteriorated forest slope. Mean pull-out resistance forces of Aralia elata, Salix koreensis and Stephanandra incisa were 37.26 kgf, 34.56 kgf and 26.00 kgf, respectively. The pull-out resistances were high as collar diameter and volume of the root increased. Correlations between root collar diameter and root volume were high in Rubus crataegifolius, but on the other hand, the correlation was lowest in Zanthoxylum schinifolium. There were significant differences in pull-out resistance by root collar diameters, and the difference of pull-out resistance by species showed only below 20 ml root volume.

• Journal of Korean Society of Water and Wastewater
• /
• v.18 no.5
• /
• pp.638-648
• /
• 2004

In many drinking water treatment plants, chlorination process is one of the main techniques used for the disinfection of water. This disinfecting treatment leads to the formation of haloacetic acid (HAAs). In this study, headspace solid-phase microextraction (HS-SPME) was studied as a possible alternative to liquid-liquid extraction for the analysis of HAAs in drinking water. The method involves direct derivatization of the acids to their methyl esters without methyl tert-butyl ether (MTBE) extraction, followed by HS-SPME with a $2cm-50/30{\mu}m$ divinylbenzene/carboxen/polydimethylsiloxane fiber. The effects of experimental parameters such as selection of SPME fiber, the volume of sulphuric acid and methanol, derivatization temperature and time, the addition of salts, extraction temperature and time, and desorption time on the analysis were investigated. Analytical parameters such as linearity, repeatability and limit of detection were also evaluated. The $2cm-50/30{\mu}m$-divinylbenzene/carboxen/polydimethylsiloxane fiber, sulphuric acid of 1ml, methanol of 3ml, derivatization temperature of $50^{\circ}C$ derivatization time of 2hrs, sodium chloride salt of 10g, extraction time of 30 minutes, extraction temperature of $20^{\circ}C$ and desorption time of 1 minute at $260^{\circ}C$ were selected as the optimal experimental conditions for the analysis of HAAs. The linearities ($r^2$), relative standard deviations (%RSD) and limits of detection (LOD) for HAAs were 0.9978~0.9991, 1.1~9.8% and $0.05{\sim}0.2{\mu}g/l$, respectively.

• Molecules and Cells
• /
• v.39 no.11
• /
• pp.807-813
• /
• 2016

Escherichia coli are important indicator organisms, used routinely for the monitoring of water and food safety. For quick, sensitive and real-time detection of E. coli we developed a 2'F modified RNA aptamer Ec3, by Cell-SELEX. The 31 nucleotide truncated Ec3 demonstrated improved binding and low nano-molar affinity to E. coli. The aptamer developed by us out-performs the commercial antibody and aptamer used for E. coli detection. Ec3(31) aptamer based E. coli detection was done using three different detection formats and the assay sensitivities were determined. Conventional Ec3(31)-biotin-streptavidin magnetic separation could detect E. coli with a limit of detection of $1.3{\times}10^6CFU/ml$. Although, optical analytic technique, biolayer interferometry, did not improve the sensitivity of detection for whole cells, a very significant improvement in the detection was seen with the E. coli cell lysate ($5{\times}10^4CFU/ml$). Finally we developed Electrochemical Impedance Spectroscopy (EIS) gap capacitance biosensor that has detection limits of $2{\times}10^4CFU/mL$ of E. coli cells, without any labeling and signal amplification techniques. We believe that our developed method can step towards more complex and real sample application.

• Proceedings of the Korean Society of Developmental Biology Conference
• /
• 2003.10a
• /
• pp.128-128
• /
• 2003

The aims of this study are 1) to test oocytes and embryos collected from in-vivo and in-vitro to achieving the valuable protocol by culturing, vitrifying and thawing of oocytes/embryos, and 2) to transfer them to recipient, and finally have resulted in pregnancies from recipient females after surgical or nonsurgical transfer. In vitro maturation and fertilization were performed according to the procedures of Funahashi et al. Fertilized oocytes were cultured in glucose-free NCSU 23 supplemented with 5 mM sodium pyruvate, 0.5 mM sodium lactate and 4 mg/ml bovine serum albumin for 2 days at 39$^{\circ}C$, and 10% fetal bovine serum was added to the culture medium thereafter. Embryos were treated with 7.5$\square$g/ml cytochalasin-B for 30 min, centrifuged at 13,000 ${\times}$ g for 13 min and then exposed sequentially to an ethylene glycol (EG) vitrification solution, aspirated into OPSs, and plunged/thawed into/from liquid nitrogen. In vivo embryos were surgically collected from three donors after Al. Forty-six embryos (18, 9 and 19 embryos, respectively) were washed 3 times in mPBS+10%FBS, followed treatments : cultured, centrifuged, vitrified, recovered and transferred to recipients as in vitro prepared embryos. Three recipients received surgically 34(control), 188 and 184 embryos (derived from abattoir), respectively. Another three recipients were received nonsurgically 150, 100 and 150 embryos, respectively. All recipient sows exhibited delayed returns to estrus. To our knowledge, these results suggest that required an improved techniques, more vigorous embryos preparation and cleaner uterous condition(use gilt).

• Korean Journal of Animal Reproduction
• /
• v.21 no.2
• /
• pp.111-116
• /
• 1997

We determined the effects of follicular fluid fractions in the maturation medium on bovine oocyte maturation, fertilization and subsequent development, as well as on number of cells in blastocysts following culture. Follicular fluid and oocytes from bovine follicles less than 5 mm in diameter were collected from the ovaries of slaughtered cows. Follicular fluid was separated into different molecular weight fractions by untrafiltration through a membrane using a centrifuge at 500$\times$g, for 2h. For the maturation medium, follicular fluid fractions (30%, v/v), whole fluid (30%) or PVP(3mg/ml) were added to TCM 199(0.1$\mu\textrm{g}$/ml estradiol-17$\beta$, 100IU hCG). After maturation for 24h, oocytes were fertilized in vitro with bull frozen-thawed spermatozoa and cultured on a monolayer of granulosa cells for 9 days after fertilization. There were no differences in maturation rates or fertilization rates among any maturation conditions. The rates of development to >2-cell stage of the oocytes were significantly decreased when fraction of follicular fluid below 10,000 MW were added into maturation medium, compared with control and fraction above 10,000 MW(26.0% vs 40.8% to 64.0%, respectveily. p<0.01). Likewise, the rates of development to blastocysts of fertilized oocytes were significantly decreased in maturation medium containing fraction of follicular fluid (<10,000 MW). The average cell number of blastocysts derived from oocytes that matured in the fraction(>10,000 MW) of follicular fluid was 154.7$\pm$13.7. These embryos contained more cells than those matured in whole follicular fluid, or the fraction(<10, 000 MW) of follicular fluid or control(107.0$\pm$8.4, 91.8$\pm$11.8 and 95.8$\pm$6.2, respectively). In conclusion, we found that fractions of follicular fluid contained factors stimulating or inhibiting oocyte cytoplasmic matruation. These suggest that a factor(s) inducing cytoplasmic maturation of oocytes may exist in >10,000 MW fraction of follicular fluid.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.244-249
• /
• 2017

Steganalysis is to detect information hidden by steganography inside general data such as images. There are stegoanalysis techniques that use machine learning (ML). Existing ML approaches to steganalysis are based on extracting features from stego images and modeling them. Recently deep learning-based methodologies have shown significant improvements in detection accuracy. However, all the existing methods, including deep learning-based ones, have a critical limitation in that they can only detect stego images that are created by a specific steganography method. In this paper, we propose a generalized steganalysis method that can model multiple types of stego images using deep learning. Through various experiments, we confirm the effectiveness of our approach and envision directions for future research. In particular, we show that our method can detect each type of steganography with the same level of accuracy as that of a steganalysis method dedicated to that type of steganography, thereby demonstrating the general applicability of our approach to multiple types of stego images.