• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.2 no.1
• /
• pp.41-60
• /
• 1998

This paper derives a consistent and bias corrected extension of Akaike's Information Criterion (AIC), $AIC_{bc}$, based on Kullback-Leibler information. This criterion has terms that penalize the overparametrization more strongly for small and large samples than that of AIC. The overfitting problem of the asymptotically efficient model selection criteria for small and large samples will be overcome. The $AIC_{bc}$ also provides a consistent model order selection. Thus, it is widely applicable to data with small and/or large sample sizes, and to cases where the number of free parameters is a relatively large fraction of the sample size. Relationships with other model selection criteria such as $AIC_c$ of Hurvich, CAICF of Bozdogan and etc. are discussed. Empirical performances of the $AIC_{bc}$ are studied and discussed in better model order choices of a linear regression model using a Monte Carlo experiment.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.58 no.1
• /
• pp.1-9
• /
• 2022

In this study, the selection action on the mesh in the net pot for whelk (Buccinum opisthoplectum) is experimentally considered, and the selectivity was compared by the SELECT model and the Nashimoto's method with the probability model according to the contact shape of the mesh and the whelk. The experiments of the mesh size selectivity was conducted for two mesh sizes: 70 mm (inner stretched size 65.4 mm) and 44 mm (inner stretched size 39.5 mm). Selectivity experiments were conducted three times in total for each mesh size used 264 whelks. In addition, Nashimoto's method analyzed the retention probability using probability model for whether the mesh passed or not based on the carapace width of the whelk. As a result of the selectivity analysis, the 50% selection carapace width for the mesh size of 70 mm was similar to 43.62 mm in the SELECT model and 42.64 mm in the Nashimoto's method. However, the 44 mm mesh with relatively small mesh size showed differences of 40.01 mm and 26.80 mm, respectively. As for the mesh size selectivity of whelk, it was found that the smaller the mesh size, the lower the selectivity. In addition, in the selectivity study on the mesh size of whelk, an evaluation method that closely considers the contact shape between the mesh and the target species is required.

• The KIPS Transactions:PartD
• /
• v.9D no.5
• /
• pp.887-896
• /
• 2002

Based on SPICE (Software Process Improvement and Capability dEtermination) evaluation model, SPIRE (Software Process Improvement in Regions of Europe) is developed and published as a process improvement model for small and medium size organizations. However, practical selection guidelines or mapping rules between business goals and software processes do not exist within SPIRE. This research aims to construct an objective reference mapping table between business goals and software processes, and to propose a process selection method using the mapping table. The mapping table is constructed by the convergence of domestic software process experts' opinions using Delphi techniques. In the suggested process selection method, target processes are selected using the intuition of project participants or project managers as well as the reference mapping table. The feasibility of the proposed selection method has been reviewed by applying to two small software companies. Using the reference mapping table, we could select key processes which were passed over by project managers.

• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.201-208
• /
• 2015

With services such as SNS and facebook, Big Data popularize the use of small size such as micro blogs are increasing. However, the problem of accuracy and computational cost of the search result of big data of a small size is unresolved. In this paper, we propose a subnet selection techniques based probability to improve the browsing speed of the small size of the text information from big data environments, such as micro-blogs. The proposed method is to configure the subnets to give to the attribute information of the data increased the probability data search speed. In addition, the proposed method improves the accessibility of the data by processing a pair of the connection information between the probability of the data constituting the subnet to easily access the distributed data. Experimental results showed the proposed method is 6.8% higher detection rates than CELF algorithm, the average processing time was reduced by 8.2%.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.1
• /
• pp.73-84
• /
• 2023

This study aims to identify the current sizing communication issues of menswear on retail websites and to suggest an effective size information presentation method. Based on sales frequency and awareness in the Korean menswear market, 22 brand websites were selected, and size-related information was investigated using 7 types of representative apparel items. The current diverse types of size codes had limitations in delivering actual product size information. Many websites preferred to display garment dimensions rather than basic body measurements, which is the suggested size designation method in Korean Standard. The websites posted fit model photos and customer reviews. However, the body size specifications, which consumers can use as a useful reference, were often omitted. There was also a high uncertainty in product size selection, with only the basic body measurement information listed, and there was a high deviation of garment dimensions within the same basic body measurements. The product size distribution did not match actual Korean body types. Based on the findings, we suggested improved effective sizing communication methods. These methods will contribute to a better online shopping environment for both consumers and retail sellers.

• Archives of Craniofacial Surgery
• /
• v.20 no.1
• /
• pp.17-23
• /
• 2019

Background: The resection of head and neck cancer can result in postoperative defect. Many patients have difficulty swallowing and masticating, and some have difficulty speaking. Various types of flaps are used for palatal reconstruction, but flap selection remains controversial. Therefore, our study will suggest which flap to choose during palatal reconstruction. Methods: Thirteen patients who underwent palatal reconstruction from 30 January, 1989 to 4 October, 2016 at our institution. Size was classified as small when the width was < $4cm^2$, medium when it was $4-6cm^2$, and large when it was ${\geq}6cm^2$. Based on speech evaluation, the subjects were divided into a normal group and an easily understood group. After surgery, we assessed whether flap selection was appropriate through the evaluation of flap success, complications, and speech evaluation. Results: Defect size ranged from $1.5{\times}2.0cm$ to $5.0{\times}6.0cm$. In four cases, the defect was in the anterior third of the palate, in eight cases it was in the middle, and there was one case of whole palatal defect. There were three small defects, two medium-sized defects, and eight large defects. Latissimus dorsi free flaps were used in six of the eight large defects in the study. Conclusion: The key to successful reconstructive surgery is appropriate selection of the flap with reference to the characteristics of the defect. Depending on the size and location of the defect, the profiles of different flaps should be matched with the recipient from the outset.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.29 no.6
• /
• pp.1-7
• /
• 2015

Road lighting is designed with a goal of achieving the related standards on luminance, uniformity ratio and glare. Unless the luminaire with LID which is perfect for road conditions is used, a situation which fails to meet lighting standards may occur. The study examined the relationship of maximum spacing with average road luminance and longitudinal uniformity. Based on the result of the analysis, this study evaluated luminaire with what characteristics are suitable to achieve lighting requirements of the roads and suggested methods of selection for luminaires depending on the size of the road.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.9A
• /
• pp.712-718
• /
• 2009

This paper proposes the optimal transmission parameter selection method for an energy efficient Wireless Personal Area Network (WPAN) system which is applicable to the Maritime Telematics targeting for various ship models. Since the transmission parameter selection is an important factor for WPAN system to decide its energy efficiency, we propose an energy consumption model for ship area network (SAN) employing IEEE 802.15.3 based TDMA HR-WPAN model and analyzes the effect of transmission parameter selection on the performance of energy consumption. In particular, the main performance decision parameter of the SAN applying HR-WPAN is path loss, since it is very varied according to the material of shipbuilding such as steel (large ship), FRP (medium size ship) and compound wood (small ship). Thus, we analyzed and demonstrated that the proper transmission parameter selection among transmit power, PHY data rate and fragment size for each ship model guarantee the energy efficiency.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10A
• /
• pp.769-775
• /
• 2009

This paper proposes the optimal transmission parameter selection method for an energy efficient Wireless Personal Area Network (WPAN) system which is applicable to the Maritime Telematics targeting for various ship models. Since the transmission parameter selection is an important factor for WPAN system to decide its energy efficiency, we propose an energy consumption model for ship area network (SAN) employing IEEE 802.15.3 based TDMA HR-WPAN model and analyzes the effect of transmission parameter selection on the performance of energy consumption. In particular, the main performance decision parameter of the SAN applying HR-WPAN is path loss, since it is very varied according to the material of shipbuilding such as steel (large ship), FRP (medium size ship) and compound wood (small ship). Thus, we analyzed and demonstrated that the proper transmission parameter selection among transmit power, PHY data rate and fragment size for each ship model guarantee the energy efficiency.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.232-240
• /
• 2022

To fulfill user expectations, the rapid evolution of software techniques and approaches has necessitated reliable and flawless software operations. Aging prediction in the software under operation is becoming a basic and unavoidable requirement for ensuring the systems' availability, reliability, and operations. In this paper, an improved evolutionary computing-driven extreme learning scheme (ECD-ELM) has been suggested for object-oriented software aging prediction. To perform aging prediction, we employed a variety of metrics, including program size, McCube complexity metrics, Halstead metrics, runtime failure event metrics, and some unique aging-related metrics (ARM). In our suggested paradigm, extracting OOP software metrics is done after pre-processing, which includes outlier detection and normalization. This technique improved our proposed system's ability to deal with instances with unbalanced biases and metrics. Further, different dimensional reduction and feature selection algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA), and T-Test analysis have been applied. We have suggested a single hidden layer multi-feed forward neural network (SL-MFNN) based ELM, where an adaptive genetic algorithm (AGA) has been applied to estimate the weight and bias parameters for ELM learning. Unlike the traditional neural networks model, the implementation of GA-based ELM with LDA feature selection has outperformed other aging prediction approaches in terms of prediction accuracy, precision, recall, and F-measure. The results affirm that the implementation of outlier detection, normalization of imbalanced metrics, LDA-based feature selection, and GA-based ELM can be the reliable solution for object-oriented software aging prediction.