• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.17 no.4
• /
• pp.391-398
• /
• 2011

SHS(Ship-Handling Simulator) is virtual generation of vessel traffic situation under various environmental conditions. Recent, with the introduction of MSA(Maritime Safety Audit), SHS is being used as a key facility to determine the safety of navigation. However, the current audit techniques specified in the implementation guidance of MSA have been prepared by generalizing common procedures and evaluation methods used by institutions operating simulator systems. Therefore, they need to be reviewed and supplemented. This study analyzed the adequacy of current audit techniques based on the limitations and problems, then suggested the advanced scheme of SHS such as standardization of ship models, standard manoeuvring and evaluation method. The results of this research will contribute to improving the quantification and reliability of audit techniques used in the MSA as well as upgrading of the simulator system.

• Journal of the Society of Disaster Information
• /
• v.14 no.2
• /
• pp.194-202
• /
• 2018

Purpose: It is necessary to set up a standardized method for classifying mixed soil layer that contains sand, gravel and boulder for engineering purposes. Method: Different size of soils was classified mixed soil layer by suggests unified soil classification method. Results: This paper suggests unified soil classification model for different size of soils where many authorities have their own system. Conclusion: Soil stratum classification method using appearing frequencies of gravels and weight ratio of boulders could be used to judgement in many cases.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.07a
• /
• pp.310-311
• /
• 2015

Ships' tracking data are being monitored and collected by vessel traffic service center in real time. In this paper, we intend to contribute to vessel traffic service operators' decision making through extracting ships' tracking patterns and models based on these data. Support Vector Machine algorithm was used for vessel track modeling to handle and process the data sets and k-fold cross validation was used to select the proper parameters. Proposed data processing methods could support vessel traffic service operators' decision making on case of anomaly detection, calculation ships' dead reckoning positions and etc.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1547-1554
• /
• 2008

This paper proposes a fire shunt guidance system model based on rule, it presents suitable shunt route in real-time according to collected fire information of the building inside using wireless sensor networks. So, this system model is composed of the sensor alert module, the behavior suggestion module, and the emergency device control module. The sensor alert module uses rule-base algorithm that monitored the information to collect periodically in wireless sensor networks. And, the behavior suggestion module proposed a suitable behavior, this module supports to judge the fire area with danger sensor list. Additional, the emergency device control module controls a related emergency device according to the suggested behavior and to present on a control screen. We experiment the fire shunt guidance system based on Internet Web for operation verification of the proposed system. Consequently, this study supports people safety with the behavior suggestion according to the context information when an emergency situation happens.

• Journal of Advanced Navigation Technology
• /
• v.15 no.1
• /
• pp.140-146
• /
• 2011

In this paper, we propose a fast object classification method based on texture and color information for video surveillance. We take the advantage of local patches by extracting SURF and color histogram from images. SURF gives intensity content information and color information strengthens distinctiveness by providing links to patch content. We achieve the advantages of fast computation of SURF as well as color cues of objects. We use Bag of Word models to generate global descriptors of a region of interest (ROI) or an image using the local features, and Na$\ddot{i}$ve Bayes model for classifying the global descriptor. In this paper, we also investigate discriminative descriptor named Scale Invariant Feature Transform (SIFT). Our experiment result for 4 classes of the objects shows 95.75% of classification rate.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.70-75
• /
• 2014

Super-resolution near-field structure (super-RENS) read-out samples are affected by a nonlinear and noncausal channel, which results in inter-symbol interference (ISI). In this study, we investigate asymmetry or domain bloom in super-RENS in terms of equalization. Domain bloom is caused by writing process in optical recording. We assume in this work that the asymmetry symbol conversion scheme is to generate asymmetric symbols, and then a linear finite impulse response filter can model the read-out channel. For equalizing this overall nonlinear channel, the read-out signals are deconvolved with the finite impulse response filter and its output is decided based on the decision rule table that is developed from the asymmetry symbol conversion scheme. The proposed equalizer is investigated with the simulations and the real super-RENS samples in terms of raw bit error rate.

• Information Systems Review
• /
• v.8 no.3
• /
• pp.135-152
• /
• 2006

This study has been performed to analyze and identify some factors which has impact on the level of consumers' acceptance for the mobile ads. For better results and more reasonable generalization of the results, this study targets consumers in two such countries as Korea and U.S.A. This research investigates the determinants of consumer's acceptance for the mobile Ads. Based on TAM(Technology Acceptance Model) and Flow theory, our research adopts some factors for a theoretical model such as entertainment, information, irritation, credibility, flow experience, attitudes and acceptance intention. For examining an implied relationships by this research model, a survey was conducted by collecting research data from students and consumers of mobile ads in Korea, and U.S.A. This data was analyzed based on using AMOS, the structural equation modeling and a second-generation multi variant technique, and has gained distinct advantages over other technique.

• Information Systems Review
• /
• v.9 no.1
• /
• pp.1-21
• /
• 2007

This research investigates the determinants of consumer's acceptance for the mobile Ads. Based on TAM(Technology Acceptance Model) and Flow theory, our research adopts some factors for a theoretical model such as entertainment, information, irritation, credibility, flow experience, attitudes and acceptance intention. For examining an implied relationships by this research model, a field study using survey methodology for data collection was conducted. This data was analyzed based on using AMOS, the structural equation modeling and a second generation multi variant technique, and has gained distinct advantages over other technique. After some model modification according to model generating strategy approach, this study shows that entertainment, irritation, credibility and flow experience have significant effects on the attitudes. And also, this attitudes have acceptance intention in mobile Ads. In conclusion, implications are discussed along with limitations and further research direction.

• Journal of Broadcast Engineering
• /
• v.18 no.2
• /
• pp.311-318
• /
• 2013

This paper deals with a noise reduction algorithm which uses the binary masking in the time-frequency domain. To improve speech intelligibility in noise, noise-masked speech is decomposed into time-frequency units and mask "0" is assigned to masker-dominant region removing time-frequency units where noise is dominant compared to speech. In the previous research, Gaussian mixture models were used to classify the speech-dominant region and noise-dominant region which correspond to mask "1" and mask "0", respectively. In each frequency band, data were collected and trained to build the Gaussian mixture models and detection procedure is performed to the test data where each time-frequency unit belongs to speech-dominant region or noise-dominant region. In this paper, we consider the correlation of masks in the frequency domain and propose a post-processing method which exploits the Viterbi algorithm.