• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.136-146
• /
• 2022

Some surface defects make the weak quality of steel materials. To limit these defects, we advocate a one-stage detector model RetinaNet among diverse detection algorithms in deep learning. There are several backbones in the RetinaNet model. We acknowledged two backbones, which are ResNet50 and VGG19. To validate our model, we compared and analyzed several traditional models, one-stage models like YOLO and SSD models and two-stage models like Faster-RCNN, EDDN, and Xception models, with simulations based on steel individual classes. We also performed the correlation of the time factor between one-stage and two-stage models. Comparative analysis shows that the proposed model achieves excellent results on the dataset of the Northeastern University surface defect detection dataset. We would like to work on different backbones to check the efficiency of the model for real world, increasing the datasets through augmentation and focus on improving our limitation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.551-552
• /
• 2021

In this paper, we present a multi-class image scene classification method based on transformation learning. ImageNet classifies multiple classes of natural scene images by relying on pre-trained network models on large image datasets. In the experiment, we obtained excellent results by classifying the optimized ResNet model on Kaggle's Intel Image Classification data set.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.5 s.335
• /
• pp.29-38
• /
• 2005

In this paper, a new modified and optimized AntNet algorithm which can be implemented efficiently onto network processor is proposed. The AntNet that mimics the activities of the social insect is an adaptive agent-based routing algorithm. This method requires a complex arithmetic calculating system. However, since network processors have simple arithmetic units for a packet processing, it is very difficult to implement the original AntNet algorithm on network processors. Therefore, the proposed AntNet algorithm is a solution of this problem by decreasing arithmetic executing cycles for calculating a reinforcement value without loss of the adaptive performance. The results of the simulations show that the proposed algorithm is more suitable and efficient than the original AntNet algorithm for commercial network processors.

• The Journal of the Korea Contents Association
• /
• v.14 no.1
• /
• pp.537-547
• /
• 2014

In this paper, the ALT (ALTernative) board and a NetLogo extension module are developed for the active participatory simulation (APS) learning. Through the participatory simulation with HubNet each student can attend the experiment as one of clients. Only one HubNet server, however, is able to use an external device so that the bifocal modeling based learning with multiple users is impossible. In order to overcome the drawback, and enable clients participate into the experiment and collect the experimental data and the measured data, an ATmega 32 based board and its firmware are developed. In addition, Java extension module based on TCP/IP socket interfaces is developed to exchange the data with HubNet server. Finally, we show some NetLogo program examples to use the developed hardware and software for APS and seek the way to use them for science education.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.43 no.1
• /
• pp.28-37
• /
• 2007

In order to develop the biodegradable monofilament gill net for the protection of marine ecosystem and reduction of ghost fishing, enpol monofilament gill net was made for Chionoecetes opilio using polybutylene succinate as a biodegradable chip. Catching efficiency on 2 type monofilament gill net, PA and Enpol, were carried out using 2 commercial fishing boats around the fishing ground of Wang-dol rock from January 2004 to May 2006. Enpol monofilament gill net spun polybutylene succinate as a biodegradable chip was appeared high practicality for Chionoecetes opilio gill net. Target fishing ratio were 98% and 98.3% for the PA and enpol monfilament gill net, respectively. In addition, CPUE ratio of female and male(CL < 90mm) to Chionoecetes opilio caught in the enpol gill net were 25.3-40.3%, 14.0-22.1% less than PA gill net, respectively. However, CPUE ratio of male(CL > 90mm) to Chionoecetes opilio caught in the enpol gill net were 2.5-11.3% more than PA gill net. There was no difference in CPUE of female and male to Chionoecetes opilio caught using 2 gill nets as a result of the significance level of 5% by T-test.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.342-347
• /
• 1993

For a fast evolution, a memory-based implementation of a petri net is discussed. A sub-class petri net model called B-petri net is suggested to make a memory-based implementation feasible in a large size application. The suggested B-petri net is a binary-petri net since only a binary-typed decision, fork and join are allowed. The application of a B-petri nt is focused to a SFC(sequential function chart) program. The memory requirement, speed and computational load are compared with a petri net when they are implementated by a memory-based method.

• Journal of the Korean Society of Costume
• /
• v.50 no.6
• /
• pp.21-31
• /
• 2000

The purpose of this study was to characterize the attitudes of Net generation customers toward purchasing fashion products or apparels through Cyber communication media. This study targeted 333 individuals aged from 14 to 24 purchasing fashion apparels through the Interned or PC communication. The data were analyzed by using frequency analysis, factor analysis, t-test, ANOVA by SASS package. The results of this study are as follows : 1. Fashion life-style of Net generation is classified into four groups - Fashion attached type, Web entertainment type, Web information type, Web media purchasing type. Net-Generation shows a little preference for brand. 2. As a result of the statistical analysis of each group's demographic variables, price is not so important when purchasing and according to the analysis of age, it proves that twenties are trendier than teenagers. 3. The most significant factor of information search is watching others' clothes and the most popular place for purchase is wholesale mall. Net-Generation has a little intention to purchase through Cyber communication media.

• Electronics and Telecommunications Trends
• /
• v.15 no.5 s.65
• /
• pp.73-85
• /
• 2000

인터넷 이용자와 트래픽의 급속한 증가는 인터넷의 이용에 많은 문제점들을 야기하고 있다. 각국은 차세대 인터넷에서의 기술 주도권 확보를 통하여 국가경쟁력을 강화하고 자국민의 삶의 질을 향상하고자 노력하고 있다. 미국의 NGI, Internet2, 캐나다의 CA*net이 대표적인 사례이다. 따라서 본 논문은 캐나다 정부가 주도적으로 전국 규모로 광 인터넷 네트워크 구축을 추진중에 있는 CA*net3에 대하여 추진 배경, 구축 및 운영 현황과 앞으로의 전개 방향을 살펴본다. 특히 CA*net3는 DWDM 기반의 코아 백본 네트워크와 CWDM과 기가 이더넷 기술에 기반을 두고 구축하고 있는 지역 네트워크(ORAN)로 이루어져 있다. 따라서 현재 추진중인 CA*net3 네트워크 구조에 대하여 중점적으로 살펴보며, 'Customer Empowered Networking Revolution'이라는 개념을 바탕으로 향후 추진하고자 하는 CA*net4 추진 동향에 대하여 자세히 살펴보고자 한다.

• Journal of Korean Institute of Industrial Engineers
• /
• v.21 no.4
• /
• pp.529-540
• /
• 1995

The paper deals with a procedure for constructing a composite surface interpolating a polygonal curve mesh defined from 3D scattered points. The procedure consists of a poly-angulation, construction of a curve net, and interpolation of the curve net. The poly-angulation contains a stage that changes a triangular edge net obtained from a triangulation into a poly-angular edge net. A curve net is constructed by replacing edges on the edge net with cubic Bezier curves. Finally, inside of an n-sided polygon is interpolated by n subdivided triangular subpatches. The method interpolates given point data with relatively few triangular subpatches. For an n-sided polygon, our method constructs an interpolant with n subdivided triangular subpatches while the existing triangular surface modeling needs 3(n-2) subpatches. The obtained surface is composed of quartic triangular patches which are $G^1$-continuous to adjacent patches.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.453-460
• /
• 2013

This study proposes a framework that enables efficient integration and usage of enterprise data using semantic based concept net. Integration of enterprise information that has been increasing geometrically in cloud environment. The concept net is very similar in approaching way to existing ontology. However, it builds correlation between object and concept to help user's information integration retrieval more efficiently. In this study, concept nets are divided into 3 kinds and are applied to the proposed framework independently. The concept net in this study is built in ontology format based on master information concept net, keyword concept net and business process concept net. This concept net enables retrieval and usage of data based on correlation among data according to user's request. Then, through combination of master information concept and keyword concept, it provides frequency trace of keyword and category thus improving convenience and speed of retrieval.