• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.8
• /
• pp.1195-1200
• /
• 2013

In this paper, we proposed an enhanced Max-Min neural network by auto-tuning of learning rate using fuzzy control method. For the reduction of training time required in the competition stage, the method was proposed that arbitrates dynamically the learning rate by applying the numbers of the accuracy and the inaccuracy to the input of the fuzzy control system. The experiments using real concrete crack images showed that the enhanced Max-Min neural network was effective in the recognition of direction of the extracted cracks.

• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.2
• /
• pp.101-105
• /
• 2018

In this paper, the kernel regression model is applied for the case study of gas turbine abnormal state analysis. In addition to vibration analysis at the remote site, the kernel regression model technique can is useful for analyzing abnormal state of rotor vibration signals of gas turbine in power plant. In monitoring based on data-driven techniques correlated measurements, the fault free training data of shaft vibration obtained during normal operations of gas turbine are used to develop a empirical model based on auto-associative kernel regression. This data-driven model can be used to predict virtual measurements, which are compared with real-time data, generating residuals. Any faults in the system may cause statistically abnormal changes in these residuals and could be detected. As the result, the kernel regression model provides information that can distinguish anomalies such as sensor failure in a shaft vibration signal.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.111-117
• /
• 2017

The National Competency Standards (NCS) was designed to implement a competence-based society and solve the problem of inconsistency between the industrial field and education, training, and certification system. This study designed and developed the Korean NCS core vocational competence system, in accordance with the NCS, as an infrastructure to solve fundamental problems such as re-education and the social costs that are incurred in the workplace. Further, this study designed and developed standard indicators to evaluate the technical performance of the system for the global advancement of the Korean NCS core vocational competence system. The NCS core vocational competence system has been developed as an appropriate response type for multiple devices such as computers, tablet PCs, and cellular phones. For the global advancement of the Korean NCS core vocational competence system, this study designed and developed 10 performance evaluation indicators in accordance with 10 global standards, such as linkage-target operating system, interface protocol, packet format, encryption, class component, simultaneous access number, supervisor-to-testtaker response speed, server-to-admin response speed, auto-recovery speed for test answers, and real-time answer transmission speed.

• Journal of Navigation and Port Research
• /
• v.34 no.5
• /
• pp.311-317
• /
• 2010

Mobile Harbor(MH) is a new paradigm for maritime transport system introduced in Korea, the target of which is to carry out ship-to-ship cargo operation rapidly and effectively even under a condition of sea state 3. A MH ship is moored alongside a large container vessel anchored at the defined anchorage and also equipped with gantry cranes for handling containers. The MH study concerned includes rapid container handling system, optimum design for floating structure, hybrid berthing & cargo operation system, design for cargo handling crane, etc. This paper is to deal with a conceptual design of a stabilized mooring system and mooring equipment under a condition of ship-to-ship mooring. In this connection, we suggest a positioning control winch system in order to control heave motions of the MH ship which is to add constant brakepower and stabilized function to an auto-tension winch and mooring equipment used currently in large container ships.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.4
• /
• pp.337-346
• /
• 2021

Detection of abnormal signal generally can be done by using features of normal signals as main information because of data imbalance. This paper propose an efficient method for abnormal signal detection using parallel AutoEncoder (AE) which can use features of abnormal signals as well. The proposed Parallel AE (PAE) is composed of a normal and an abnormal reconstructors having identical AE structure and train features of normal and abnormal signals, respectively. The PAE can effectively solve the imbalanced data problem by sequentially training normal and abnormal data. For further detection performance improvement, additional binary classifier can be added to the PAE. Through experiments using public acoustic data, we obtain that the proposed PAE shows Area Under Curve (AUC) improvement of minimum 22 % at the expenses of training time increased by 1.31 ~ 1.61 times to the single AE. Furthermore, the PAE shows 93 % AUC improvement in detecting abnormal underwater acoustic signal when pre-trained PAE is transferred to train open underwater acoustic data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.467-479
• /
• 2022

Working memory (WM), which plays a vital role in daily activities, is a memory system that temporarily stores and processes information when people are engaged in complex cognitive activities. The influence of music on WM has been widely studied. In this work, we conducted a series of n-back memory experiments with different task difficulties and multiple trials on 14 subjects under the condition of no music and Alpha wave leading music. The analysis of behavioral data show that the change of music condition has significant effect on the accuracy and time of memory reaction (p<0.01), both of which are improved after the stimulation of Alpha wave music. Behavioral results also suggest that short-term training has no significant impact on working memory. In the further analysis of electrophysiology (EEG) data recorded in the experiment, auto-regressive (AR) model is employed to extract features, after which an average classification accuracy of 82.9% is achieved with support vector machine (SVM) classifier in distinguishing between before and after WM enhancement. The above findings indicate that Alpha wave leading music can improve WM, and the combination of AR model and SVM classifier is effective in detecting the brain activity changes resulting from music stimulation.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.4
• /
• pp.412-417
• /
• 2015

The IMO MEPC has been increasingly strengthening the emission standard for marine environment protection. In particular, nitrogen oxide (NOx) emissions of all ocean-going ships built from 2016 will be required to comply with the Tier-III regulation. In this study, a vanadia based SCR (Selective Catalytic Reduction) system developed for ship application was installed on a diesel engine for power generation of the training ship T/S SAENURI in Mokpo National Maritime University. For the present study, the exhaust pipeline of the generator diesel engine was modified to fit the urea SCR system. This study investigated the NOx reduction performance according to the two kind of injection method of urea solution (40%): Auto mode through the PLC (Programable Logic Control) and Manual mode. We were able to find the ammonia slip conditions when in manual mode method. So, the optimal urea injection quantity can be controlled at each engine load (25, 35, 50%) condition. It was achieved 80% reduction on nitrogen oxide. Furthermore, we found that the NOx reduction performance was better with the load up-down (while down to 25% from 50%) than the load down-up (while up to 50% from 25%) test.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.701-715
• /
• 2021

The drastic advance of recent deep learning technologies is heavily dependent on training datasets which are essential to train models by themselves with less human efforts. In comparison with the work to design deep learning models, preparing datasets is a long haul; at the moment, in the domain of vision intelligent, datasets are still being made by handwork requiring a lot of time and efforts, where workers need to directly make labels on each image usually with GUI-based labeling tools. In this paper, we overview the current status of vision datasets focusing on what datasets are being shared and how they are prepared with various labeling tools. Particularly, in order to relieve the repetitive and tiring labeling work, we present an interactive smart image annotating system with which the annotation work can be transformed from the direct human-only manual labeling to a correction-after-checking by means of a support of automatic labeling. In an experiment, we show that automatic labeling can greatly improve the productivity of datasets especially reducing time and efforts to specify regions of objects found in images. Finally, we discuss critical issues that we faced in the experiment to our annotation system and describe future work to raise the productivity of image datasets creation for accelerating AI technology.

• Journal of Biosystems Engineering
• /
• v.36 no.1
• /
• pp.40-47
• /
• 2011

Image analysis algorithm for the quality evaluation of ginseng seedling was investigated. The images of ginseng seedling were acquired with a color CCD camera and processed with the image analysis methods, such as binary conversion, labeling, and thinning. The processed images were used to calculate the length and weight of ginseng seedlings. The length and weight of the samples could be predicted with standard errors of 0.343 mm, and 0.0214 g respectively, $R^2$ values of 0.8738 and 0.9835 respectively. For the evaluation of the three quality grades of Gab, Eul, and abnormal ginseng seedlings, features from the processed images were extracted. The features combined with the ratio of the lengths and areas of the ginseng seedlings efficiently differentiate the abnormal shapes from the normal ones of the samples. The grade levels were evaluated with an efficient pattern recognition method of support vector machine analysis. The quality grade of ginseng seedling could be evaluated with an accuracy of 95% and 97% for training and validation, respectively. The result indicates that color image analysis with support vector machine algorithm has good potential to be used for the development of an automatic sorting system for ginseng seedling.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.