• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• ETRI Journal
• /
• v.41 no.4
• /
• pp.483-493
• /
• 2019

Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this perspective, we propose to revisit the idea of hand-crafted feature learning to avoid such a requirement from a dataset. The proposed tracking approach is composed of two phases, detection and tracking, according to how severely the appearance of a target changes. The detection phase addresses severe and rapid variations by learning a new appearance model that classifies the pixels into foreground (or target) and background. We further combine the raw pixel features of the color intensity and spatial location with convolutional feature activations for robust target representation. The tracking phase tracks a target by searching for frame regions where the best pixel-level agreement to the model learned from the detection phase is achieved. Our two-phase approach results in efficient and accurate tracking, outperforming recent methods in various challenging cases of target appearance changes.

• The Journal of Society for e-Business Studies
• /
• v.6 no.3
• /
• pp.63-80
• /
• 2001

The construction of the students knowledge in e-Learning systems, namely the student modeling, is a core component used to develop e-Learning systems. However, existing e-Learning systems have many problems to share the knowledge in a heterogeneous student model and a distributed knowledge base. Because the methods of the knowledge representation are different in each e-Learning systems, the accumulated knowledge cannot be used or shared without a great deal of difficulty. In order to share this knowledge, existing systems must reconstruct the knowledge bases. Consequently, we propose a new a Case Markup Language based on XML in order to overcome these problems. A distributed e-Learning systems fan have the advantage of easily sharing and managing the heterogeneous knowledge base proposed by CaseML. Moreover students can generate and share a case knowledge to use the communication protocol of agents. In this paper, we have designed and developed a CaseML by using a knowledge markup language. Furthermore, in order to construct an intelligent e-Learning systems, we have done our research based on the design and development of the intelligent agent system by using CaseML.

• Journal of Wind Energy
• /
• v.13 no.3
• /
• pp.33-42
• /
• 2022

In this paper, a semi-supervised machine learning technique applied to actual field vibration data acquired from Jeju-do wind turbines for predictive diagnosis of abnormal conditions of offshore wind turbines is introduced. Semi-supervised machine learning, which combines un-supervised learning with supervised learning, can be used to perform anomaly detection in situations where sufficient fault data cannot be obtained. The signal processing results using the spectrogram of the original signal were shown, and external data were used to overcome the problem that disturbance reactions easily occurred due to the imbalance between the number of normal and abnormal data. Out of distribution (OOD), which uses external data, is a technology that is regarded as abnormal data that is unlikely to occur in reality, but we were able to use it by expanding it. By rearranging the distribution of data in this way, classification can be performed more robustly. Specifically, by observing the trends of the abnormal score and the change in the feature of the representation layer, continuous learning was performed through a mixture of existing and new data.

• Journal of Korean Elementary Science Education
• /
• v.37 no.3
• /
• pp.309-322
• /
• 2018

There is no doubt that science -and, therefore, science education- is central to the lives of all (NGSS, 2013). This manuscript focuses on ideas in astronomy that are at the foundation of elementary students' understanding of the discipline: the apparent motion of the sun explaining the day / night cycle on Earth. According to prior research demonstrating that neither children nor adults hold a scientific understanding of the big ideas of astronomy (NRC, 1996), understanding of concepts may base students' progress towards more advanced understanding in the domain of astronomy. We have analyzed the logic of the domain and synthesized prior research assessing children's spatial representation from an earth- and a space based perspective to develop a set of learning trajectories that describe how students' initial ideas about apparent celestial motion as they take school science can be build upon. In this study elementary students' representations were compared by their resident context including urban and rural. This study may present a first look at the use of a learning progression framework in analyzing the structure of astronomy education. We discuss how this work may eventually lead towards the development and empirical testing of how children learn to describe and explain apparent patterns of celestial motion.

• Journal of Korean Library and Information Science Society
• /
• v.39 no.4
• /
• pp.283-304
• /
• 2008

This is to develop Intelligent Retrieval System which can automatically present early query's category terms(association terms connected with knowledge structure of relevant terminology) through learning function and it changes searching form automatically and runs it with association terms. For the reason, this theoretical study of Intelligent Automatic Indexing System abstracts expert's index term through learning and clustering algorism about automatic classification, text mining(categorization), and document category representation. It also demonstrates a good capacity in the aspects of expense, time, recall ratio, and precision ratio.

• Korean Institute of Interior Design Journal
• /
• v.16 no.4
• /
• pp.119-126
• /
• 2007

A prototype design process visualization and guidance system, is being developed. Its purpose is to visualize the design process in more intuitive manner so that one can get an insight to the complicated aspects of the design process. By providing a tangible utility to the design process performed by the expert designers or guided by the system, novice designers will be greatly helped to learn how to approach a certain class of design. Not only as an analysis tool to represent the characteristics of the design process, the system will be useful also for learning design process. A design ontology is being developed to provide the system with a knowledge-base, representing designer's activities associated with various design information during the conceptual design process, and then to be utilized for a computer environment for design analysis and guidance. To develop the design ontology, a conceptual framework of design activity model is proposed, and then the model has been tested and elaborated through investigating the nature of the early conceptual design. A design process representation model is conceptualized based on the ontology, and reflected into the development of the system. This paper presents the development process of the visualization system, modeling of design process ontology, and how the system could be utilized for the analysis and learning of conceptual design methods using computer mediated design support environment.

• Education of Primary School Mathematics
• /
• v.18 no.3
• /
• pp.203-216
• /
• 2015

This study analyzed changes of representations which had come up in the problem-solving process of math-gifted 6th grade students that ACODESA had been applied. The class was designed on a ACODESA procedure that enhancing the use of varied representations, and conducted for 40minutes, 4 times over the period. The recorded videos and interviews with the students were transcribed for analysing data. According to the result of the analysis, which adopted Despina's using type of representation, there appeared types of 'adding', 'elaborating', and 'reducing'. This study found that there is need for a class design that can make personal representations into that of public through small group discussions and confirmation in the problem-solving process.

• Journal of Science Education
• /
• v.43 no.1
• /
• pp.173-193
• /
• 2019

An expert teachers' instruction can be helpful to other teachers because good teaching effectively guides students to develop meaningful learning. Feynman is an excellent physics lecturer as well as one of the greatest physicists of the 20th century who presented and explained physics with his unique teaching style based on his great store of knowledge. However, it is not easy to capture and visualize teaching because it is not only the complex phenomena interrelated to various factors with the content to be taught but also the tacit representation. In this study, the framework of knowledge & belief based on the integrated mental model theory was used as a tool to capture and visualize complex and tacit representation of Feynman's teaching of 'The theory of gravitation,' a chapter in The Feynman Lectures on Physics. Feynman's teaching was found to go beyond the transmission of physics concepts by showing that components of the framework of knowledge & belief were effectively intertwined and integrated in his teaching and the storyline was well-organized. On the basis of these discussions, the implications of Feynman's teaching analyzed within the framework of knowledge & belief for physics teacher education are derived. Finally, the characteristics of the framework of knowledge & belief as tools for the analysis of teaching are presented.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1771-1777
• /
• 2023

With the advancements of deep learning, many semantic segmentation-based methods for land cover classification have been proposed. However, existing deep learning-based models only use image information and cannot guarantee spatiotemporal consistency. In this study, we propose a land cover classification model using geographical coordinates. First, the coordinate features are extracted through the Coordinate Hash Encoder, which is an extension of the Multi-resolution Hash Encoder, an implicit neural representation technique, to the longitude-latitude coordinate system. Next, we propose an architecture that combines the extracted coordinate features with different levels of U-net decoder. Experimental results show that the proposed method improves the mean intersection over union by about 32% and improves the spatiotemporal consistency.