• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.870-877
• /
• 2020

A suction bucket foundation, especially useful at depths of more than 20m, is a method of construction. The method first places an empty upturned bucket at the target site. Then, the bucket is installed by sucking water or air into it to create negative pressure. For stability, it is crucial to secure the verticality of the bucket. However, inclination by the bucket may occur due to sea-bottom conditions. In general, a repeated intrusion-pulling method is used for securing verticality. However, it takes a long time to complete the job. In this paper, we propose a real-time suction bucket verticality monitoring system. Specifically, the system consists of a sensor unit that collects raw verticality data, a controller that processes the data and wirelessly transmits the information, and a display unit that shows verticality information of a circular steel pipe. The system is implemented using an inclination sensor and an embedded controller. Experimental results show that the proposed system can efficiently measure roll/pitch information with a 0.028% margin of error. Furthermore, we show that the system properly operates in a suction bucket-based model experiment.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.8
• /
• pp.1296-1303
• /
• 2014

This study was conducted to develop predictive models for the growth of Bacillus cereus on carrot treated with slightly acidic electrolyzed water (SAcEW) and ultrasonication (US) at different storage temperatures. In addition, the inactivation of B. cereus by US with SAcEW was investigated. US treatment with a frequency of 40 kHz and an acoustic energy density of 400 W/L at $40^{\circ}C$ for 3 min showed the maximum reduction of 2.87 log CFU/g B. cereus on carrot, while combined treatment of US (400 W/L, $40^{\circ}C$, 3 min) with SAcEW reached to 3.1 log CFU/g reduction. Growth data of B. cereus on carrot treated with SAcEW and US at different temperatures (4, 10, 15, 20, 25, 30, and $35^{\circ}C$) were collected and used to develop predictive models. The modified Gompertz model was found to be more suitable to describe the growth data. The specific growth rate (SGR) and lag time (LT) obtained from the modified Gompertz model were employed to establish the secondary models. The newly developed secondary models were validated using the root mean square error, bias factor, and accuracy factor. All results of these factors were in the acceptable range of values. After compared SGR and LT of B. cereus on carrot, the results showed that the growth of B. cereus on carrot treated with SAcEW and US was slower than that of single treatment. This result indicates that shelf life of carrot treated with SAcEW and US could be extended. The developed predictive models might also be used to assess the microbiological risk of B. cereus infection in carrot treated with SAcEW and US.

• Journal of Korean Society of Forest Science
• /
• v.78 no.3
• /
• pp.323-330
• /
• 1989

Pinass densiflora natural forests of four local forms in Korea were studies to investigate effective biomass estimation method. Dimension analysis was used and three allometric regression models, such as logWt=A+BlogD, logWt=$A+B1ogD^2H$ and 1ogWt=A+BlogD+ClogH were applied to estimate biomass, The most accurate estimation was made by the regression model of logWt=A+BlogD+ClogH where Wt is dry weight, D is diameter at breast height, and H is tree height. However, dry weights of cones and dead branches were remotely related to tree size factor, such as D and H. In the interest of practical use. generalized allometric regressions for all samples trees of four stands were computed and analysis of covariance was used to compare the allometric regressions among the four stands. Based on the test criteria applied in this study, significant differences were found in terms of error variance and regression intercept, not in terms of regression slope. These trends suggest a generalized biomass regression is not valid for accurate estimation over a range of four local form stands.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.19-29
• /
• 2003

This paper presents a novel hybrid classifier for face recognition with artificially generated virtual training samples. We utilize both the nearest neighbor approach in feature angle space and a connectionist model to obtain a synergy effect by combining the results of two heterogeneous classifiers. First, a classifier called the nearest feature angle (NFA), based on angular information, finds the most similar feature to the query from a given training set. Second, a classifier has been developed based on the recall of stored frontal projection of the query feature. It uses a frontal recall network (FRN) that finds the most similar frontal one among the stored frontal feature set. For FRN, we used an ensemble neural network consisting of multiple multiplayer perceptrons (MLPs), each of which is trained independently to enhance generalization capability. Further, both classifiers used the virtual training set generated adaptively, according to the spatial distribution of each person's training samples. Finally, the results of the two classifiers are combined to comprise the best matching class, and a corresponding similarit measure is used to make the final decision. The proposed classifier achieved an average classification rate of 96.33% against a large group of different test sets of images, and its average error rate is 61.5% that of the nearest feature line (NFL) method, and achieves a more robust classification performance.

• Journal of Korean Academy of Nursing Administration
• /
• v.1 no.2
• /
• pp.268-284
• /
• 1995

This study was designed to test effects of nursing ethics education (NEE) on moral reasoning and ethical decision making of subjects. This NEE that was teached for 10 hours course was composed of these : Nurses' ethical code, moral responsibility, Moral value and professional accountability, Respect for human life, General ethics, Theory and Norms of biomedical ethics, Ethical decision making model and Discussion about hypothetical ethical dilemmas Twenty-five senior student nurses were sampled from four year college of nursing from Nov. 3rd, 1993 to Nov. 24th, 1993. Data were collected through self-reported questionnaires included two kinds of tests. Rest's Defining Issues Test was adopted to measure the stage of moral development, which was classified with the stage 2 (instrumental relativist orientation), the stage 3 (interpersonal concordance), the stage 4 (law and order), the stage 5A (societal consensus), and the stage 5B (intuitional humanism), the stage 6 (universal ethical practice). In particular, the level of principled thinking (P) was measured by summing these scores of the stages 5A, 5B, and 6. The possible range of P is 0 to 95. As for measuring the levels of morality and nursing dilemma, Crisham's Nursing Dilemma Test was adopted. This test generated the morality score(MS) and the dilemma score (DS). The data were analyzed by t-test, ANOVA, Kruskal-Wallis test, Mc Nemar's test and Pearson correlation coefficients. The results were as follows ; 1. For the Moral Reasoning both before and after NEE, The Mean score of the stage 5A was significantly higher than that of other stages.(P=0.0001) Before NEE, the mean score of the stage 4 was significantly different from stage 2, 3, 5A, and after NEE, different from stage 2, 5B,6. 2. The analysis of change of moral development level revealed that the score of stage 4 increased after NEE.(P=0.0004) 3. The Effect of NEE for the mean score of 5A, 6, P after education was significantly different by birth place. 4. With regard to the five dilemmas postulated such as forcing medication performing cardiac pulmonary resuscitation, reporting a medication error, informing diagnosis to terminally ill adult, and providing new-nurse orientation, the mean score of the MS and the DS was no significant difference with general characteristics of the students. Effect of NEE morality score and dilemma score after education was no significant difference. 5. As for the correlations between moral reasoning and decision making, the score of the stage 2, 5A, 6, DS was positively correlated with the scores of before and after. Positive correlation was also observed between the scores of stage 2 and stage 4, stage 3 and 6. On the other hand, the score of P was negatively correlated with the scores of stage 2 and of stage 4 and of stage 5A. The score of the stage 5A was also negatively correlated with the score of the sge 6.

• The Journal of the Korea Contents Association
• /
• v.11 no.10
• /
• pp.19-29
• /
• 2011

A Blog provides commentary, news, or content on a particular subject. The important part of many blogs is interactive format. Sometimes, there is a heated debate on a topic and any article becomes a political or sociological issue. In this paper, we proposed a method to predict the popularity of an article in advance. First, we used hit count as a factor to predict the popularity of an article. We defined the saturation point and derived a model to predict the hit count of the saturation point by a correlation coefficient of the early hit count and hit count of the saturation point. Finally, we predicted the virtual temperature of an article using 4 types(explosive, hot, warm, cold). We can predict the virtual temperature of Internet discussion articles using the hit count of the saturation point with more than 70% accuracy, exploiting only the first 30 minutes' hit count. In the hot, warm, and cold categories, we can predict more than 86% accuracy from 30 minutes' hit count and more than 90% accuracy from 70 minutes' hit count.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.12 no.4
• /
• pp.232-237
• /
• 2010

While global solar radiation is an essential input variable in crop models, the observation stations are relatively sparse compared with other meteorological elements. Instead of using measured solar radiation, the Angstrom-Prescott model estimates have been widely used. Monthly data for solar radiation and sunshine duration are a convenient basis for deriving Angstrom-Prescott coefficients (a, b), but it is uncertain whether daily solar radiation could be estimated with a sufficient accuracy by the monthly data - derived coefficients. We derived the Angstrom-Prescott coefficients from the 25 years observed global solar radiation and sunshine duration data at 18 locations across South Korea. In order to figure out any improvements in estimating daily solar radiation by replacing monthly data with daily data, the coefficients (a, b) for each month were derived separately from daily data and monthly data. Local coefficients for eight validation sites were extracted from the spatially interpolated maps of the coefficients and used to estimate daily solar radiation from September 2008 to August 2009 when, pyranometers were operated at the same sites for validation purpose. Comparison with the measured radiation showed a better performance of the daily data - derived coefficients in estimating daily global solar radiation than the monthly data - derived coefficients, showing 9.3% decrease in the root mean square error (RMSE).

• The KIPS Transactions:PartA
• /
• v.12A no.6 s.96
• /
• pp.523-530
• /
• 2005

When a PCI 2.2 bus master requests data using Memory Read command, a target device may hold PCI bus without data to be transferred for long time because a target device needs time to prepare data infernally. Because the usage efficiency of the PCI bus and the data transfer efficiency are decreased due to this situation, the PCI specification recommends to use the Delayed Transaction mechanism to improve the system performance. But the mechanism cann't fully improve performance because a target device doesn't know the exact size of prefetched data. In the previous work, we propose a new method called Prefetch Request when a bus master intends to read data from the target device. In this paper, we design PCI 2.2 controller and local device that support the proposed method. The designed PCI 2.2 controller has simple local interface and it is used to convert the PCI protocol into the local protocol. So the typical users, who don't know the PCI protocol, can easily design the PCI target device using the proposed PCI controller. We propose the basic behavioral verification, hardware design verification, and random test verification to verify the designed hardware. We also build the test bench and define assembler instructions. And we propose random testing environment, which consist of reference model, random generator ,and compare engine, to efficiently verify corner case. This verification environment is excellent to find error which is not detected by general test vector. Also, the simulation under the proposed test environment shows that the proposed method has the higher data transfer efficiency than the Delayed Transaction about $9\%$.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.133-140
• /
• 2022

We investigate the performance of deep learning-based Korean language models on a task of predicting the score range of Korean essays written by foreign students. We construct a data set containing a total of 304 essays, which include essays discussing the criteria for choosing a job ('job'), conditions of a happy life ('happ'), relationship between money and happiness ('econ'), and definition of success ('succ'). These essays were labeled according to four letter grades (A, B, C, and D), and a total of eleven essay score range prediction experiments were conducted (i.e., five for predicting the score range of 'job' essays, five for predicting the score range of 'happiness' essays, and one for predicting the score range of mixed topic essays). Three deep learning-based Korean language models, KoBERT, KcBERT, and KR-BERT, were fine-tuned using various training data. Moreover, two traditional probabilistic machine learning classifiers, naive Bayes and logistic regression, were also evaluated. Experiment results show that deep learning-based Korean language models performed better than the two traditional classifiers, with KR-BERT performing the best with 55.83% overall average prediction accuracy. A close second was KcBERT (55.77%) followed by KoBERT (54.91%). The performances of naive Bayes and logistic regression classifiers were 52.52% and 50.28% respectively. Due to the scarcity of training data and the imbalance in class distribution, the overall prediction performance was not high for all classifiers. Moreover, the classifiers' vocabulary did not explicitly capture the error features that were helpful in correctly grading the Korean essay. By overcoming these two limitations, we expect the score range prediction performance to improve.