• Structural Monitoring and Maintenance
• /
• v.9 no.3
• /
• pp.221-235
• /
• 2022

Among nondestructive damage detection methods, impedance-based methods have been recognized as an effective technique for damage identification in many kinds of structures. This paper proposes a method to detect cracks in metal structures by combining electro-mechanical impedance (EMI) responses and artificial neural networks (ANN). Firstly, the theories of EMI responses and impedance-based damage detection methods are described. Secondly, the reliability of numerical simulations for impedance responses is demonstrated by comparing to pre-published results for an aluminum beam. Thirdly, the proposed method is used to detect cracks in the beam. The RMSD (root mean square deviation) index is used to alarm the occurrence of the cracks, and the multi-layer perceptron (MLP) ANN is employed to identify the location and size of the cracks. The selection of the effective frequency range is also investigated. The analysis results reveal that the proposed method accurately detects the cracks' occurrence, location, and size in metal structures.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.1
• /
• pp.79-87
• /
• 2012

In the case that the probability density function has a discontinuity point, Huh (2002) estimated the location and jump size of the discontinuity point based on the difference between the right and left kernel density estimators using the one-sided kernel function. In this paper, we consider the cross-validation, made by the right and left maximum likelihood cross-validations, for the bandwidth selection in order to estimate the location and jump size of the discontinuity point. This method is motivated by the one-sided cross-validation of Hart and Yi (1998). The finite sample performance is illustrated by simulated example.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.3
• /
• pp.561-567
• /
• 2010

Multiclassification is typically performed using voting scheme methods based on combining a set of binary classifications. In this paper we use multiclassification method with a hat matrix of least squares support vector machine (LS-SVM), which can be regarded as the revised one-against-all method. To tackle multiclass problems for large data, we use the $Nystr\ddot{o}m$ approximation and the quadratic Renyi entropy with estimation in the primal space such as used in xed size LS-SVM. For the selection of hyperparameters, generalized cross validation techniques are employed. Experimental results are then presented to indicate the performance of the proposed procedure.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.41-49
• /
• 2021

All application programs, including malware, call the Application Programming Interface (API) upon execution. Recently, using those characteristics, attempts to detect and classify malware based on API Call information have been actively studied. However, datasets containing API Call information require a large amount of computational cost and processing time. In addition, information that does not significantly affect the classification of malware may affect the classification accuracy of the learning model. Therefore, in this paper, we propose a method of extracting a essential feature set after reducing the dimensionality of API Call information by applying various feature selection methods. We used CICAndMal2020, a recently announced Android malware dataset, for the experiment. After extracting the essential feature set through various feature selection methods, Android malware classification was conducted using CNN (Convolutional Neural Network) and the results were analyzed. The results showed that the selected feature set or weight priority varies according to the feature selection methods. And, in the case of binary classification, malware was classified with 97% accuracy even if the feature set was reduced to 15% of the total size. In the case of multiclass classification, an average accuracy of 83% was achieved while reducing the feature set to 8% of the total size.

• Journal of Distribution Science
• /
• v.11 no.12
• /
• pp.71-81
• /
• 2013

Purpose - This study investigated the effects of consumers' selection criteria for environment-friendly agricultural products on purchase intention and the effects of consumers' attitudes and the reliability of environment-friendly agricultural products on purchase intention by using the theory of planned behavior. Subjective norms of variables of behavioral intention, attitudes toward behavior and control of the behavior were used to create selection criteria, consumers' attitudes and reliability of environment-friendly agricultural products. The study investigated the effects of consumers' selection criteria, attitudes, and reliability of environment-friendly agricultural products on purchase intention constructing models and hypotheses of mediation and moderation between selection criteria for agricultural products and purchase intention by consumers' attitudes and reliability. Research design, data, and methodology - The findings were as follows: first, consumers' selection criteria for environment-friendly agricultural products had a significantly affirmative influence upon purchase intention. Health was the most important factor of selection criteria convenience was more important than quality and familiarity was next. Consumers' attitudes and trust had a significant influence on purchase intention. Second, testing showed that consumers' attitude and trust partially mediated selection criteria: sub-factors and purchase intention were important in selection criteria. Third, testing showed that consumers' attitude and trust had a significant moderation effect between selection criteria and purchase intention. In the test of the moderation effect between sub-factors of selection criteria and purchase intention, consumers' attitude had a significantly positive influence upon health, convenience, and familiarity, and had no significant influence upon quality and purchase intention. Consumers' trust had no significant influence upon health, convenience, and quality. Results - The study provided several theoretical implications: first, an empirical analysis was undertaken with selection criteria for environmental-friendly agricultural products, consumers' attitude, and trust to investigate subjective norms, attitude toward behavior and control of behavior based on the theory of planned behavior. Second, this study investigated both the mediation effect and moderation effect of consumers' subjective norms on attitudes toward behavior, the mediating effects of perceived behavior control and changes of behavioral intention depending upon size and direction of the variables. This study also provided several practical implications. Conclusions - First, consumption of environment-friendly agricultural products did not increase despite rapid increase of production therefore, promotion of consumption and distribution was needed considering the supply and demand of the products. Second, definite standards for selection criteria were suggested to build up consumers' attitude and trust. Consumers' attitude could be improved by factors including the brand of environment-friendly agricultural products, consistent quality, solving physiological problems caused by adverse effects of environmental problems, supplementary approaches, treatment of adverse effects by eating food, and the development and supply of products in accordance with changes of lifestyle. Finally, consumers' demand for sub-factors of selection criteria could be much higher than health, convenience, and quality of the products. Therefore, a process was needed that could continuously check consumers' needs for the products. Limitations were described at the end of the study.

• Asian-Australasian Journal of Animal Sciences
• /
• v.32 no.4
• /
• pp.485-493
• /
• 2019

Objective: This study was undertaken to investigate the genetic characteristics of Berkshire (BS), Landrace (LR), and Yorkshire (YS) pig breeds raised in the Great Grandparents pig farms using the single nucleotide polymorphisms (SNP) information. Methods: A total of 25,921 common SNP genotype markers in three pig breeds were used to estimate the expected heterozygosity ($H_E$), polymorphism information content, F-statistics ($F_{ST}$), linkage disequilibrium (LD) and effective population size ($N_e$). Results: The chromosome-wise distribution of $F_{ST}$ in BS, LR, and YS populations were within the range of 0-0.36, and the average $F_{ST}$ value was estimated to be $0.07{\pm}0.06$. This result indicated some level of genetic segregation. An average LD ($r^2$) for the BS, LR, and YS breeds was estimated to be approximately 0.41. This study also found an average $N_e$ of 19.9 (BS), 31.4 (LR), and 34.1 (YS) over the last 5th generations. The effective population size for the BS, LR, and YS breeds decreased at a consistent rate from 50th to 10th generations ago. With a relatively faster $N_e$ decline rate in the past 10th generations, there exists possible evidence for intensive selection practices in pigs in the recent past. Conclusion: To develop customized chips for the genomic selection of various breeds, it is important to select and utilize SNP based on the genetic characteristics of each breed. Since the improvement efficiency of breed pigs increases sharply by the population size, it is important to increase test units for the improvement and it is desirable to establish the pig improvement network system to expand the unit of breed pig improvement through the genetic connection among breed pig farms.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.11
• /
• pp.549-556
• /
• 2020

Real estate markets play an essential role in the economic development of both developed and developing countries. Investment decisions in private real estate demand the consideration of several qualitative and quantitative criteria. Especially in Vietnam, demand for housing, apartments are rising which has resulted because of the migration from rural to urban areas. This study aims to determine the influencing factors of the real estate purchasing behavior and then recommend a grey Multi-Criteria Decision Making (MCDM) support model to evaluate real estate alternatives based on a numerical example in Vietnam. A set of essential criteria are identified based on experts' opinion, and the proposed determinants are initial investment, maintenance cost, prestige location, distance to interesting places, parking lot, public transportation, property condition, total area size, number of rooms, and neighbors. The subjective weights were obtained by using the Decision-Making Trial and Evaluation Laboratory (DEMATEL) model, and the Grey Relational Analysis (GRA) technique is employed to prioritize and rank real estate alternatives. The results reveal that this approach can be useful to make purchasing decisions for many kinds of real estate property under uncertain business environments. These findings indicate that the presented hybrid model has advantages in granting flexibility to the preferences of decision makers.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.3
• /
• pp.133-144
• /
• 2000

Genetic Algorithm(GA) has been known as a method of solving large-scaled optimization problems with complex constraints in various applications. Since a major drawback of the GA is that it needs a long computation time, the hardware implementations of Genetic Algorithm Processors(GAP) are focused on in recent studies. In this paper, a hardware-oriented GA was proposed in order to save the hardware resources and to reduce the execution time of GAP. Based on steady-state model among continuos generation model, the proposed GA used modified tournament selection, as well as special survival condition, with replaced whenever the offspring's fitness is better than worse-fit parent's. The proposed algorithm shows more than 30% in convergence speed over the conventional algorithm in simulation. Finally, by employing the efficient pipeline parallelization and handshaking protocol in proposed GAP, above 30% of the computation speed-up can be achieved over survival-based GA which runs one million crossovers per second (1㎒), when device speed and size of application are taken into account on prototype. It would be used for high speed processing such of central processor of evolvable hardware, robot control and many optimization problems.

• Journal of the Korean Wood Science and Technology
• /
• v.49 no.5
• /
• pp.491-503
• /
• 2021

Wood identification is regularly performed by observing the wood anatomy, such as colour, texture, fibre direction, and other characteristics. The manual process, however, could be time consuming, especially when identification work is required at high quantity. Considering this condition, a convolutional neural networks (CNN)-based program is applied to improve the image classification results. The research focuses on the algorithm accuracy and efficiency in dealing with the dataset limitations. For this, it is proposed to do the sample selection process or only take a small portion of the existing image. Still, it can be expected to represent the overall picture to maintain and improve the generalisation capabilities of the CNN method in the classification stages. The experiments yielded an incredible F1 score average up to 93.4% for medium sample area sizes (200 × 200 pixels) on each CNN architecture (VGG16, ResNet50, MobileNet, DenseNet121, and Xception based). Whereas DenseNet121-based architecture was found to be the best architecture in maintaining the generalisation of its model for each sample area size (100, 200, and 300 pixels). The experimental results showed that the proposed algorithm can be an accurate and reliable solution.

• Journal of the Korean Society of Safety
• /
• v.30 no.1
• /
• pp.28-33
• /
• 2015

Three phase heaters in 7 buildings of 2 sites were examined for precise diagnosis. The sample size was 626. Precise examinations of current and the heater wiring status revealed contact failures and arcs in equipments that had CUF larger than 10%. Contact failures and arcs may cause electrical fire. Therefore, the correlation between the CUF and the imperfections in heater equipment and its wiring was analyzed for three phase heaters. In addition, the protection devices used for detection of heater imperfections were found to be unsuitable for the purpose. Current status of the protection devices was analyzed, and suggestions for improvements were made for new standards of the protection device selection.