• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.8
• /
• pp.307-324
• /
• 2018

Recently, recurrent neural networks have been attracting attention in solving prediction problem of sequential data through structure considering time dependency. However, as the time step of sequential data increases, the problem of the gradient vanishing is occurred. Long short-term memory models have been proposed to solve this problem, but there is a limit to storing a lot of data and preserving it for a long time. Therefore, research on memory-augmented neural network (MANN), which is a learning model using recurrent neural networks and memory elements, has been actively conducted. In this paper, we describe the structure and characteristics of MANN models that emerged as a hot topic in deep learning field and present the latest techniques and future research that utilize MANN.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4098-4116
• /
• 2020

Mobile devices such as smartphones are very attractive targets for augmented reality (AR) services, but their limited resources make it difficult to increase the number of objects to be recognized. When the recognition process is scaled to a large number of objects, it typically requires significant computation time and memory. Therefore, most large-scale mobile AR systems rely on a server to outsource recognition process to a high-performance PC, but this limits the scenarios available in the AR services. As a part of realizing large-scale standalone mobile AR, this paper presents a solution to the problem of accuracy, memory, and speed for large-scale object recognition. To this end, we design our own basic feature and realize spatial locality, selective feature extraction, rough pose estimation, and selective feature matching. Experiments are performed to verify the appropriateness of the proposed method for realizing large-scale standalone mobile AR in terms of efficiency and accuracy.

• Journal of Digital Convergence
• /
• v.18 no.8
• /
• pp.29-35
• /
• 2020

This study identified the impact of augmented reality advertising on attitude toward advertising and memory according to the type of presence and flow level. The presence (cognitive, emotional, media) and flow level (high vs. low) of the augmented reality(AR) advertising were set as independent variables and analyzed by Two-Way MANOVA. As a result of the research, first, the augmented reality advertising attitude was positive when the emotional presence and flow level were high. Second, when the flow level is high, the ARM such as product attribute information increases, but when the flow level is low, the evaluation-oriented GRM increases. Third, emotional presence increases GRM when the flow level is high, but ARM increases when the flow level is low. Fourth, the memory effect was low regardless of the flow level. In the future research, it would be desirable to produce augmented reality advertisements through virtual brands in the generalization of research.

• Journal of Internet Computing and Services
• /
• v.11 no.6
• /
• pp.41-50
• /
• 2010

As time goes by, most of information escapes human being's memory even though he/she tries hard to remember the information. On the other hand, when a human being takes a look at an image, he/she recollects once forgotten past memories and relates a specific object in the photo with associated words, which trigger new memories. Beside, he/she feels the affection of that time by the recalled memory. Therefore, this paper proposes an augmented memory system that assists recollection of user's past memories by using the images in social network services and user's dictionary for associated words. In the proposed system, if a user selects an object in an image, words associated with the object is provided to the user. If the user selects one of the associated words, the proposed system offers the list of other images containing the object of the selected word. The repetition of the aforementioned process can make the user recollect his/her memory and stimulate his/her affection. It is expected that the proposed system will be useful for revitalizing social network services.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.7
• /
• pp.822-828
• /
• 2019

An Augmented Reality(AR) provides virtual information with a real environment, and the processor needs to access the memory for the AR system. However, the processor has the heavy workload as the technology improvement leads to increase the size of data. We need a specific module to reduce the workload to overcome the limitation. In this paper, we propose a Direct Memory Access(DMA) controller displaying image instead of the processor. We implemented the proposed DMA controller on a Field Programmable Gate Array(FPGA) and demonstrated the functionality of the DMA controller based on an Avalon Memory Mapped(Avalon-MM) interface. Also, the DMA controller is fabricated by using Magnachip/Hynix 0.35um CMOS technology and verified the feasibility of the embedded system.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.749-753
• /
• 1996

This paper presents a new method for first and second order eigen-sensitivity analysis of system matrix in augmented form. Eigen-sensitivity analysis provides invaluable informations in power system planning and operation. However, conventional eigen-sensitivity analysis methods, which need all the eigenvalues and eigenvectors, can not be applicable to large scale power systems due to large computer memory and computing time required. In the proposed method, all sensitivity computations for a mode are carried out using the augmented system matrix and its own eigenvalue and right & left eigenvectors. In other words sensitivity analysis for a mode does not need informations on the other eigenvalues and eigenvectors and sparsity technique can be fully utilized. Thus compuations can be done very efficiently with moderate computer memory and computing time even for large power systems. The proposed algorithm is tested for one machine infinite bus system.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.15 no.4
• /
• pp.20-25
• /
• 1978

Two augmented integrators are sufficient as memory elements to realize an arbitrary second-order voltage transfer funtion which has complex poles in left-half S-plane, where S is a complex variable. The augmented integrator is characterized by transfer funtion B/(S+A), where A and B are real constant.

• International Journal of Contents
• /
• v.9 no.1
• /
• pp.18-25
• /
• 2013

Recently, augmented reality has been proved immensely useful on a day to day basis when tied with location-based technology. In this paper, we present a new method for displaying augmented reality contents on mobile devices. We add 3D models on the view of the camera and use location-based services, motion sensors to calculate the transformation of models. Instead of remaining at a fixed position on camera view while moving around a 3D model, the model rotates on display in the opposite direction that the user is walking. We also design client as a ubiquitous client to reduce constraints on disk space and memory capacity on mobile devices. Implementation results show effective use in creating GPS-based 3D view augmented reality contents for Smart Mobile Devices.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.23-28
• /
• 2018

Recent approaches to Relation Extraction methods mostly tend to be limited to mention level relation extractions. These types of methods, while featuring high performances, can only extract relations limited to a single sentence or so. The inability to extract these kinds of data is a terrible amount of information loss. To tackle this problem this paper presents an Augmented External Memory Neural Network model to enable Global Relation Extraction. the proposed model's Global relation extraction is done by first gathering and analyzing the mention level relation extraction by the Augmented External Memory. Additionally the proposed model shows high level of performances in korean due to the fact it can take the often omitted subjects and objectives into consideration.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.847-857
• /
• 2018

As the number of malicious code increases steeply, cyber attack victims targeting corporations, public institutions, financial institutions, hospitals are also increasing. Accordingly, academia and security industry are conducting various researches on malicious code detection. In recent years, there have been a lot of researches using machine learning techniques including deep learning. In the case of research using Convolutional Neural Network, ResNet, etc. for classification of malicious code, it can be confirmed that the performance improvement is higher than the existing classification method. However, one of the characteristics of the target attack is that it is custom malicious code that makes it operate only for a specific company, so it is not a form spreading widely to a large number of users. Since there are not many malicious codes of this kind, it is difficult to apply the previously studied machine learning or deep learning techniques. In this paper, we propose a method to classify malicious codes when the amount of samples is insufficient such as targeting type malicious code. As a result of the study, we confirmed that the accuracy of 97% can be achieved even with a small amount of data by applying the Memory Augmented Neural Networks model.