• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.5
• /
• pp.102-108
• /
• 1996

Adaptive resonance theory (ART2) characterized by its built-in mechanism of handling the stability-plasticity switching and by the adaptive learning without forgetting informations learned in the past, is based on an unsupervised template matching. We propose an improved tow-stage learning algorithm for aRT2: the original unsupervised learning followed by a new supervised learning. Each of the output nodes, after the unsupervised learning, is labeled according to the category informations to reinforce the template pattern associated with the target output node belonging to the same category some dominant classes from exhausting a finite number of template patterns in ART2 inefficiently. Experimental results on a set of 2545 FLIR images show that the ART2 trained by the two-stage learning algorithm yields better accuracy than the original ART2, regardless of th esize of the network and the methods of evaluating the accuracy. This improvement shows the effectiveness of the two-stage learning process.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.101-106
• /
• 2023

With the recent surge in YouTube usage, there has been a proliferation of user-generated videos where individuals evaluate cosmetics. Consequently, many companies are increasingly utilizing evaluation videos for their product marketing and market research. However, a notable drawback is the manual classification of these product review videos incurring significant costs and time. Therefore, this paper proposes a deep learning-based cosmetics search algorithm to automate this task. The algorithm consists of two networks: One for detecting candidates in images using shape features such as circles, rectangles, etc and Another for filtering and categorizing these candidates. The reason for choosing a Two-Stage architecture over One-Stage is that, in videos containing background scenes, it is more robust to first detect cosmetic candidates before classifying them as specific objects. Although Two-Stage structures are generally known to outperform One-Stage structures in terms of model architecture, this study opts for Two-Stage to address issues related to the acquisition of training and validation data that arise when using One-Stage. Acquiring data for the algorithm that detects cosmetic candidates based on shape and the algorithm that classifies candidates into specific objects is cost-effective, ensuring the overall robustness of the algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.632-657
• /
• 2022

Detecting web attacks is a major challenge, and it is observed that the use of simple models leads to low sensitivity or high false positive problems. In this study, we aim to develop a robust two-stage deep learning based stacked ensemble web application firewall. Normal and abnormal classification is carried out in the first stage of the proposed WAF model. The classification process of the types of abnormal traffics is postponed to the second stage and carried out using an integrated stacked ensemble model. By this way, clients' requests can be served without time delay, and attack types can be detected with high sensitivity. In addition to the high accuracy of the proposed model, by using the statistical similarity and diversity analyses in the study, high generalization for the ensemble model is achieved. Within the study, a comprehensive, up-to-date, and robust multi-class web anomaly dataset named GAZI-HTTP is created in accordance with the real-world situations. The performance of the proposed WAF model is compared to state-of-the-art deep learning models and previous studies using the benchmark dataset. The proposed two-stage model achieved multi-class detection rates of 97.43% and 94.77% for GAZI-HTTP and ECML-PKDD, respectively.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• 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.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.26 no.1
• /
• pp.61-69
• /
• 2001

This paper presents a two stage game model which examines the effect of learning-by-doing and spillover. Increases in the firm’s cumulative experience lower its unit cost in future period. However, the firm’s rival also enjoys the experience via spillover. Unlike previous theoretical research model, a cost asymmetric market entry game model is developed between the incumbent firm and new entrant. Mathematical results show that the incumbent firm exploits the learning curve to gain future cost advantage, and that the diffusion of learning to the new entrant induces the incumbent firm to choose decreasing output strategically. As a main result, we show that the relative magnitude between the learning and spillover rate determines the market share ratio of competing firms.

• English Language & Literature Teaching
• /
• v.9 no.1
• /
• pp.131-152
• /
• 2003

The purpose of this study is to investigate the correlation between the introduction order of 9 English morphemes in the English textbook used in the middle school and the learning order of the morphemes by the 7th graders learning English as a foreign language. The subjects are 139 students in two middle schools, who learn English with different textbooks. The introduction order of each morpheme in two textbooks was examined according to its quantity and frequency. Data on the real learning order were collected through the written SLOPE test, and each morpheme was ranked by its group score. The introduction order of each morpheme in the textbook and the real learning order were analyzed by Spearman rank order correlation. It was shown that the correlation between the two was very low. This means that those textbooks do not take the learning order of English morphemes into account. Also it was shown that in the earlier stage of learning English the introduction order of each morpheme in the textbook had much influence on its learning order, but in the later stage such influence reduced gradually. This means that the learning order of English morphemes approaches the natural order as time passes by.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.6 no.1
• /
• pp.64-76
• /
• 2000

The purpose of this study is to identify the difference in learning styles, learning stages, and preferred nursing specialties between two groups of nursing programs, regular BSN and RN-BSN. The survey instrument was a simplified version of the Kolb's Learning-Style Instrument which was developed by the researcher, a self- reported learning style questionnaire with twelve questions related to the four learning stages. The sample of the study was the 218 nursing students in a university in Korea which consisted of 58 junior and 67 senior students in the regular BSN program, and 58 junior and 35 senior students in the RN-BSN program. Main findings of the study were as the following. 1) Over all, the major learning style was either the diverger or the accomodator; the most preferred learning stage was the concrete experience and the leastly preferred learning stage was the abstractive conceptualization learning stage; and the most preferred nursing specialty in the future was the clinical nursing. 2) Students in the BSN program preferred four learning stages with rather equal proportion, whereas the students in the RN-BSN program preferred the concrete experience learning stage as high as 60.3% and the abstractive conceptualization learning stage as low as 9.5%. 3)For the future career, the junior students of both programs preferred clinical and educational nursing areas, and the senior students of both programs preferred clinical and research areas. The main reason of the difference seemed to result from the different courses such as Health Education or Teaching Method for the juniors and the Nursing Research for the seniors of both groups. Because the sample of the study was limited to a university, it is difficult to generalize the study results for the entire nursing students in Korea. Continuous studies with larger numbers of nursing students and nurse educators, and experimental studies measuring the effects of new curricula are needed for the future.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.4_2
• /
• pp.687-697
• /
• 2022

An automated system is needed for the effectiveness of non-destructive testing. In order to utilize the radiographic testing data accumulated in the film, the types of welding defects were classified into 9 and the shape of defects were analyzed. Data was preprocessed to use deep learning with high performance in image classification, and a combination of one-stage/two-stage method and convolutional neural networks/Transformer backbone was compared to confirm a model suitable for welding defect detection. The combination of two-stage, which can learn step-by-step, and deep-layered CNN backbone, showed the best performance with mean average precision 0.868.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.648-650
• /
• 1998

This paper proposes a constructive algorithm for generating the Takagi-Sugeno type fuzzy model through the sequential learning from training data set. The proposed algorithm has a two-stage learning scheme that performs both structure and parameter learning simultaneously. The structure learning constructs fuzzy model using two growth criteria to assign new fuzzy rules for given observation data. The parameter learning adjusts the parameters of existing fuzzy rules using the LMS rule. To evaluate the performance of the proposed fuzzy modeling approach, well-known benchmark is used in simulation and compares it with other modeling approaches.