• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.503-512
• /
• 2020

The products using blowers include hand dryers, automatic car washers, dryers, and vacuum cleaners. The features of these products require a structure and control algorithm so that a strong wind is blown out at the moment. Electric motors according to the existing excitation method include a direct winding type, a decentralized type, a lottery type, and a permanent magnet type. Conventional electric motors have a disadvantage when the starting current is large during high-speed rotation and the number of rotations is irregular. In order to improve this, research on high-speed BLDC motor control has designed 800W-class high-speed BLDC motor control and circuit through driving circuit design, sensorless control algorithm, simulation, experiment, etc., and more than 95% high efficiency evaluation method of driving performance of controller, prototype experiments and verification were studied.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6009-6027
• /
• 2019

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.

• International Journal of Railway
• /
• v.8 no.1
• /
• pp.15-20
• /
• 2015

As a result of the current population concentrations in urban centers, demand for intercity transportation is increasing rapidly. Railway transportation is becoming popular as an intercity transportation because of its timely service, travel speeds and transport efficiency. Among the many railway systems, the innovative and environmentally friendly maglev system has been rated very highly as the next-generation intercity railway system. Linear induction motors are widely used for the propulsion of maglev trains because of their light weight and low construction costs. The urban maglev that was recently completed in Incheon airport site employs a 110km/h class linear induction motor. However, this system was designed to meet requirements for inner-city operations and is not suitable as an intercity transportation system, which requires medium to high speeds. Therefore, this study deals with the characteristics and designs of linear induction motors used for the propulsion of maglev trains that can be used as intercity trains. Rail car specifications for high-speed trains have been presented, and the characteristics of linear induction motors that can be used for the propulsion of these trains have been derived using the finite element method (FEM).

• Journal of fish pathology
• /
• v.6 no.1
• /
• pp.57-64
• /
• 1993

The properties and DNA structures of R plasmids differ depending on the species of the fish-pathogens Aeromonas hydrophila, A. salmonicida, Edwardsiella tarda, Enterococcus seriolicida, Pasteurella piscicida and Vibrio anguillarum. However, some R plasmids with the same resistance markers in similar DNA structures were found in A. hydrophila and E. tarda, as well as in A. hydrophila and A. salmonicida. R plasmids from V. anguillarum were classified into three groups according to their DNA structures. The first group was detected before 1977, the second from 1980 to 1983, and the third from 1989 to 1991. R plasmids have been retained within P. piscieida having the same DNA structures and detected at various locations and times. E. seriolicida strains carrying the same R plasmids, which were encoded with resistance to macrolide antibiotics(MLs), lincomycin(LIM), and TC, and to MLs, LIM, and CP. were distributed in yellowtail farms in various districts. The chloramphenicol-resistance(cat) gene of the R plasmids of P. piscicida was classified as CAT type I. The cat of the R plasmids of E, tarda. A. salmonicida was classified as type II. The cat of R plasmids of V. anguillarum was classified into two types. One type detected before 1977, was classified as CAT IV and the other type, detected after 1980, was classified as CAT II. Tetracycline-resistance (tet) V. anguillarum, isolated before 1977 and after 1981, was classified as Tet B and Tet G, respectively. The class D tet gene was widely distributed in R plasmids from fish-pathogens A. hydrophila, E. tarda, P. piscicida, and also V. anguillarum isolated after 1989.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.187-195
• /
• 2013

Most of former studies for car license plate detection restrict the image acquisition environment. The aim of this research is to diminish the restrictions by proposing a new method of using SIFT and neural network. SIFT can be used in diverse situations with less restriction because it provides size- and rotation-invariance and large discriminating power. SIFT extracted from the license plate image is divided into the internal(inside class) and the external(outside class) ones and the classifier is trained using them. In the proposed method, by just putting the various types of license plates, the trained neural network classifier can process all of the types. Although the classification performance is not high, the inside class appears densely over the plate region and sparsely over the non-plate regions. These characteristics create a local feature map, from which we can identify the location with the global maximum value as a candidate of license plate region. We collected image database with much less restriction than the conventional researches. The experiment and evaluation were done using this database. In terms of classification accuracy of SIFT keypoints, the correct recognition rate was 97.1%. The precision rate was 62.0% and recall rate was 50.2%. In terms of license plate detection rate, the correct recognition rate was 98.6%.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Clinical and Experimental Reproductive Medicine
• /
• v.37 no.1
• /
• pp.49-56
• /
• 2010

Objective: To investigate assisted reproductive technology (ART) outcomes in women with WHO class I anovulation compared with control group. Design: Retrospective case-control study. Methods: Twenty-three infertile women with hypogonadotropic hypogonadism (H-H) who undertook ART procedure from August 2003 to January 2009 were enrolled in this study. A total of 59 cycles (H-H group) were included; Intra-uterine insemination with super-ovulation (SO-IUI, 32 cycles), in vitro fertilization with fresh embryo transfer (IVF-ET, 18 cycles) and subsequent frozenthawed embryo transfer (FET, 9 cycles). Age and BMI matched 146 cycles of infertile women were collected as control group; 64 cycles of unexplained infertile women for SO-IUI and 54 cycles of IVF-ET and 28 cycles of FET with tubal factor. We compared ART and pregnancy outcomes such as clinical pregnancy rate (CPR), clinical abortion rate (CAR), and live birth rate (LBR) between the two groups. Results: There was no difference in the mean age ($32.7{\pm}3.3$ vs. $32.6{\pm}2.7$ yrs) and BMI ($21.0{\pm}3.1$ vs. $20.8{\pm}3.1kg/m^2$) between two groups. Mean levels of basal LH, FSH, and $E_2$ in H-H group were $0.62{\pm}0.35$ mIU/ml, $2.60{\pm}2.30$ mIU/ml and $10.1{\pm}8.2$ pg/ml, respectively. For ovarian stimulation, H-H group needed higher total amount of gonadotropin injected and longer duration for ovarian stimulation (p<0.001). In SO-IUI cycles, there was no significant difference of CPR, CAR, and LBR between the two groups. In IVF-ET treatment, H-H group presented higher mean $E_2$ level on hCG day ($3104.8{\pm}1020.2$ pg/ml vs. $1878.3{\pm}1197.7$ pg/ml, p<0.001) with lower CPR (16.7 vs. 37.0%, p=0.11) and LBR (5.6 vs. 33.3%, p=0.02) and higher CAR (66.7 vs. 10.0%, p=0.02) compared with the control group. However, subsequent FET cycles showed no significant difference of CPR, CAR, and LBR between the two groups. Conclusion: H-H patients need higher dosage of gonadotropin and longer duration for ovarian stimulation compared with the control groups. Significantly poor pregnancy outcomes in IVF-ET cycles of H-H group may be due to detrimental endometrial factors caused by higher $E_2$ level and the absence of previous hormonal exposure on endometrium.

• Journal of Korean Society of Transportation
• /
• v.22 no.4 s.75
• /
• pp.147-158
• /
• 2004

A class of SWP(Stochastic Wane Propagation) models microscopically mimics individual vehicles' stochastic behavior and traffic jam propagation with simplified car-following models based on CA(Cellular Automata) theory and macroscopically captures dynamic traffic flow relationships based on statistical physics. SWP model, a program-oriented model using both discrete time-space and integer data structure, can simulate a huge road network with high-speed computing time. However, the model has shortcomings to both the capturing of low speed within a jam microscopically and that of the density and back propagation speed of traffic congestion macroscopically because of the generation of spontaneous jam through unrealistic collision avoidance. In this paper, two additional rules are integrated into the NaSch model. The one is SMR(Stopping Maneuver Rule) to mimic vehicles' stopping process more realistically in the tail of traffic jams. the other is LAR(Low Acceleration Rule) for the explanation of low speed characteristics within traffic jams. Therefore, the CA car-following model with the two rules prevents the lockup condition within a heavily traffic density capturing both the stopping maneuver behavior in the tail of traffic jam and the low acceleration behavior within jam microscopically, and generates more various macroscopic traffic flow mechanism than NaSch model's with the explanation of propagation speed and density of traffic jam.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.6
• /
• pp.587-593
• /
• 2020

The securing safety of ferry ships on the domestic coast is evaluated by comparing the external force applied and the securing device based on the cargo weight and hull acceleration that can exist at the loaded position. The hull acceleration based on the domestic standard, which is the basis for securing safety evaluation, is applied without reflecting the characteristics of the ship and the sailing conditions. In this study, a total of 12 acceleration measurements were performed at four points of the hull of a ship with a DWT 6,800 ton class 15.5 knots passing through Busan-Jeju to analyze the hull acceleration of the domestic coastal ferry ship. Data were collected for the buoy. For a theoretical comparative analysis of the limited measurement results, the response amplitude operator (RAO) was analyzed through frequency-response analysis by numerical simulation, and acceleration analysis for the four points was performed using the RAO results. Based on the acceleration comparison, differences in the degree of each position were observed, but in the case of the Y-axis acceleration, the analysis was 1.81 m/s², and the measurement was 1.47 m/s². The analyzed simulation result was as high as 0.34 m/s². Moreover, analysis was performed at 22 % level, and measurement at 18 % level.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.9 no.3
• /
• pp.309-321
• /
• 2007

Since the first diesel passenger car hit the local road in late 2005, the share of diesel cars is growing significantly; possibly up to the level as in the western Europe. In this study, the effects of introduction of diesel passenger cars on the ventilation rate and facility capacity are analyzed for the three individual cases with different basic exhaust rate based on the vehicle age, the vehicle class percentage and the smoke exhaust rate. The target tunnel for this comparative study is a typical 2 km-long 2-lane highway tunnel. Case 1 assuming the current local design standards and the diesel vehicles comprising 40% of the total passenger cars on the road required more ventilation rate and facility capacity than in the case only with the current standards. Case 2 which is the real tunnel currently in the designing stage taking into account the vehicle age but ignoring the diesel vehicle ratio, and Case 3 on the contrary considering the both factors show similar level of ventilation characteristics as EURO-3 emission regulation. Application of the emission standard set by the Ministry of Environment for newly manufactured vehicles in the current local tunnel design standard indicates higher requirements than for EURO-2 regulation, whereas the emission standard came into effect in 2006 results in the ventilation characteristics similar to EURO-4. This study aims at providing fundamental information for assessing the basic emission rate and determining the optimal ventilation rate and facility capacity considering the growing percentage of diesel cars and gradually decreasing level of smoke emission forced by the relevant laws.