• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.273-279
• /
• 2021

In this paper, we propose an algorithm that shortens the learning time by performing individual learning using partitioning the deep learning structure. The proposed algorithm consists of four processes: network classification origin setting process, feature vector extraction process, feature noise removal process, and class classification process. First, in the process of setting the network classification starting point, the division starting point of the network structure for effective feature vector extraction is set. Second, in the feature vector extraction process, feature vectors are extracted without additional learning using the weights previously learned. Third, in the feature noise removal process, the extracted feature vector is received and the output value of each class is learned to remove noise from the data. Fourth, in the class classification process, the noise-removed feature vector is input to the multi-layer perceptron structure, and the result is output and learned. To evaluate the performance of the proposed algorithm, we experimented with the Extended Yale B face database. As a result of the experiment, in the case of the time required for one-time learning, the proposed algorithm reduced 40.7% based on the existing algorithm. In addition, the number of learning up to the target recognition rate was shortened compared with the existing algorithm. Through the experimental results, it was confirmed that the one-time learning time and the total learning time were reduced and improved over the existing algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.2948-2963
• /
• 2015

In the field of computer vision, visual surveillance systems have recently become an important research topic. Growth in this area is being driven by both the increase in the availability of inexpensive computing devices and image sensors as well as the general inefficiency of manual surveillance and monitoring. In particular, the ultimate goal for many visual surveillance systems is to provide automatic activity recognition for events at a given site. A higher level of understanding of these activities requires certain lower-level computer vision tasks to be performed. So in this paper, we propose an intelligent activity recognition model that uses a structure learning method and a classification method. The structure learning method is provided as a K2-learning algorithm that generates Bayesian networks of causal relationships between sensors for a given activity. The statistical characteristics of the sensor values and the topological characteristics of the generated graphs are learned for each activity, and then a neural network is designed to classify the current activity according to the features extracted from the multiple sensor values that have been collected. Finally, the proposed method is implemented and tested by using PETS2013 benchmark data.

• Journal of KIBIM
• /
• v.9 no.1
• /
• pp.42-51
• /
• 2019

Maintenance of aging structures has attracted societal attention. Maintenance of the aging structure can be efficiently performed with a digital twin. In order to maintain the structure based on the digital twin, it is required to accurately detect the damage of the structure. Meanwhile, deep learning-based damage detection approaches have shown good performance for detecting damage of structures. However, in order to develop such deep learning-based damage detection approaches, it is necessary to use a large number of data before and after damage, but there is a problem that the amount of data before and after the damage is unbalanced in reality. In order to solve this problem, this study proposed a method based on Generative adversarial network, one of Generative Model, for generating acceleration data usually used for damage detection approaches. As results, it is confirmed that the acceleration data generated by the GAN has a very similar pattern to the acceleration generated by the simulation with structural analysis software. These results show that not only the pattern of the macroscopic data but also the frequency domain of the acceleration data can be reproduced. Therefore, these findings show that the GAN model can analyze complex acceleration data on its own, and it is thought that this data can help training of the deep learning-based damage detection approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3780-3797
• /
• 2022

The estimation of radio map (RM) is a fundamental and critical task for the network planning and optimization performance of mobile communication. In this paper, a RM estimation method is proposed based on a deep dual learning structure. This method can simultaneously and accurately reconstruct the urban building map (UBM) and estimate the RM of the whole cell by only part of the measured reference signal receiving power (RSRP). Our proposed method implements UBM reconstruction task and RM estimation task by constructing a dual U-Net-based structure, which is named RadioCycle. RadioCycle jointly trains two symmetric generators of the dual structure. Further, to solve the problem of interference negative transfer in generators trained jointly for two different tasks, RadioCycle introduces a dynamic weighted averaging method to dynamically balance the learning rate of these two generators in the joint training. Eventually, the experiments demonstrate that on the UBM reconstruction task, RadioCycle achieves an F1 score of 0.950, and on the RM estimation task, RadioCycle achieves a root mean square error of 0.069. Therefore, RadioCycle can estimate both the RM and the UBM in a cell with measured RSRP for only 20% of the whole cell.

• Smart Structures and Systems
• /
• v.32 no.2
• /
• pp.123-133
• /
• 2023

This paper proposes a thermography-based coating thickness estimation method for steel structures using model-agnostic meta-learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured using an infrared (IR) camera. The measured heat responses are then analyzed using model-agnostic meta-learning to estimate the coating thickness, which is visualized throughout the inspection surface of the steel structure. Current coating thickness estimation methods rely on point measurement and their inspection area is limited to a single point, whereas the proposed method can inspect a larger area with higher accuracy. In contrast to previous ANN-based methods, which require a large amount of data for training and validation, the proposed method can estimate the coating thickness using only 10- pixel points for each material. In addition, the proposed model has broader applicability than previous methods, allowing it to be applied to various materials after meta-training. The performance of the proposed method was validated using laboratory-scale and field tests with different coating materials; the results demonstrated that the error of the proposed method was less than 5% when estimating coating thicknesses ranging from 40 to 500 ㎛.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.4
• /
• pp.115-123
• /
• 2003

It's difficult to find efforts for individualization other than suggesting simple, branching level learning materials among the developed courseware. The reason is primarily attributed to the facts that the courseware itself is not flexible, a fixed structure which is not reusable, and numerous costs and time should be consumed to develop one. In the same context of the appearance of the object-oriented concept in the method of software development, the concept of 'learning object' has appeared in the development of courses and contents, paving the way toward the possibility of designing versatile courses through the learning object. In the learning object-based course design, however, it still has similar shape and structure to the existing courseware, and the effort to realize the individualized learning by utilizing the learning object is not sufficient, as well. In this study, I suggest a outlined learning object model which can support the individualized learning by expanding the existing learning object, and based on th is model. design a instructional model that can show an individualized learning path, based on the ADDIE model.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.471-476
• /
• 2024

With the spread of various smart devices and computing devices, big data generation is occurring widely. Machine learning is an algorithm that performs reasoning by learning data patterns. Among the various machine learning algorithms, the algorithm that attracts attention is deep learning based on neural networks. Deep learning is achieving rapid performance improvement with the release of various applications. Recently, among deep learning algorithms, attempts to analyze data using graph structures are increasing. In this study, we present a graph generation method for transferring to a deep learning network. This paper proposes a method of generalizing node properties and edge weights in the graph generation process and converting them into a structure for deep learning input by presenting a matricization We present a method of applying a linear transformation matrix that can preserve attribute and weight information in the graph generation process. Finally, we present a deep learning input structure of a general graph and present an approach for performance analysis.

• Journal of the Korean earth science society
• /
• v.41 no.3
• /
• pp.291-306
• /
• 2020

In this study, we developed a learning progression for the structure of the solar system using multi-tier supply form items and validated its appropriateness. To this end, by applying Wilson's (2005) construct modeling approach, we set up 'solar system components,' 'size and distance pattern of solar system planets,' and 'solar system modeling' as the progress variables of the learning progression and constructed multi-tier supply form items for each of these variables. The items were applied to 150 fifth graders before and after the classes that dealt with the 'solar system and star' unit. To describe the results of the assessment, the students' responses to each item were categorized into five levels. By analyzing the Wright map that was created by applying the partial credit Rasch model, we validated the appropriateness of the learning progression based on the students' responses. In addition, the validity of the hypothetical pathway that was established in the learning progression was verified by tracking changes in the developmental level of students before and after the classes. The results of the research are as follows. The bottom-up research method that used multi-tier supply form items was able to elaborately set the empirical learning progression for the conceptualization of the structure of the solar system that is taught in elementary school. In addition, the validity of the learning progression was high, and the development of students was found to change with the learning progression.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.5
• /
• pp.171-177
• /
• 2018

Recently there are many image datasets which has variety of data class and point to extract general features. But in order to this variety data class and point, deep learning model trained this dataset has not good performance in heterogeneous data feature local area. In this paper, we propose the structure which use sub-category and openset object detection methods to train more robust model, named multi-branch tree using ASSL. By using this structure, we can have more robust object detection deep learning model in heterogeneous data feature environment.