• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• Journal of Korea Game Society
• /
• v.6 no.3
• /
• pp.43-50
• /
• 2006

This study is to develop a learning program supporting how to teach multi-level of students in number and operating field in the elementary school. Mathematics requires different teaching ways for various standards of student in the school. However, in most of elementary school teachers are having hard time giving the proper lesson for each student due to the lack of supplementary classes and the excessive numbers of students in a class. Thus this research provides "Game-type learning Program" and supports individual learning lessons to give each student an opportunity to form a correct concept of number and operation. This system sets up suitable steps for each student by checking their leaning progress and accomplishment. When a student has a trouble, can give a help or show specific things which could be related with the matter. As a result, students have got more interests in studying math, furthermore, actually, the help and giving a clue helped students a lot in settling the problems.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.231-234
• /
• 2004

Ratio that robot occupies is low level worldwide fairly in suspension wire, electricity electron and neutralization learning industry and domestic industry of this is staring in average love. Can speak that grafting of robotic machine and neutralization learning industry is high in terms of side of creation of the added value or progress of technology rightly hereupon. This research raises or designed multi-function handling robot that can make welding, assembly conveniently catching large size work water

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.474-478
• /
• 2024

In this paper, we proposes a deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers. The proposed deep learning network is specifically designed for pharmaceutical containers by using data produced in real manufacturing environments, leading to more accurate quality inspection. Additionally, the use of an inline-capable deep learning network allows for an increase in inspection speed. The development of the deep learning network for quality inspection in the multi-camera inline inspection system consists of three steps. First, a dataset of approximately 10,000 images is constructed from the production site using one line camera for foreign substance inspection and three area cameras for dimensional inspection. Second, the pharmaceutical container data is preprocessed by designating regions of interest (ROI) in areas where defects are likely to occur, tailored for foreign substance and dimensional inspections. Third, the preprocessed data is used to train the deep learning network. The network improves inference speed by reducing the number of channels and eliminating the use of linear layers, while accuracy is enhanced by applying PReLU and residual learning. This results in the creation of four deep learning modules tailored to the dataset built from the four cameras. The performance of the proposed deep learning network for quality inspection in the multi-camera inline inspection system for pharmaceutical containers was evaluated through experiments conducted by a certified testing agency. The results show that the deep learning modules achieved a classification accuracy of 99.4%, exceeding the world-class level of 95%, and an average classification speed of 0.947 seconds, which is superior to the world-class level of 1 second. Therefore, the effectiveness of the proposed deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers has been demonstrated.

• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.

• The Journal of Information Systems
• /
• v.29 no.2
• /
• pp.27-50
• /
• 2020

Purpose The research on the effective use of IS needs to embrace the alignment to organization learning process, which expands the limited focus on dynamic capability of IS use. In addition, it should be done in multi-level analysis with system, user, task, and organization. The current study suggests the inclusion of multi-level analysis of effective use of IS in the perspective of exploration and exploitation. Design/methodology/approach This review selected the representative studies in IS discipline which have investigated the effective use of IS, dynamic capability, operational capability, exploration, exploitation, or organizational learning. In the search of academic archives with those keywords, seventeen papers which have been most cited were chosen and validated whether the focus constructs are directly theorized or validated the suggested keywords. In addition, the level of analysis was verified whether it includes one or more levels of system, individual, task, or organization. Based on the initial analysis of dynamic capability, the further review of research on explorational and exploitational capabilities was implemented. Findings The present review study on previous literature on effective use of IS presented that it is largely implemented in the level of individual but few of them has included organization level. Similarly, the direct investigation of explorational and exploitational use of IS has not been done so much. The needs of study on effective use of IS in depth have been inquired for a decade. However, the review presented that it still lacks profound theories and empirical validations compared to those of adoption stage of IS. Based on the review, future research on the transition between explorational and exploitational use of IS is suggested.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.750-759
• /
• 2019

Presently, the extraction of hand-crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high-level abstract representations from the time-frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning-based architecture for multi-platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.

• Journal of the Korea Society for Simulation
• /
• v.3 no.2
• /
• pp.69-76
• /
• 1994

Traditionally, simulation-based learning games which are known as flight-simulators have been constructed as a black-box game. Within a black-box game, game-players can view and modify only a part of model parameters. Game-players cannot change the structure of a simulation model. In a black-box game, game-players cannot understand and learn the system structure which is responsible for the system behavior. In this paper, the multi-tasking at the level of operating systems is exploited to enhance the transparency of simulation-based learning game. The white-box game or transparent-box game allows game-players ot view and modify the model structure. The multi-tasking solution for white-box learning game is implemented with Smalltalk language on MS-/windows operating system.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.