• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.975-978
• /
• 2002

A new conception of public-key cryptography MEPKC, Petri net based Multi-stage-Encryption Public-Key Cryptography, has been proposed in onder to guarantee stronger network communication security. Different from an ordinary public-key cryptography that opens only a single public key to the public, MEPKC opens a key-generator that can generate multiple encryption keys and uses these keys to encrypt a plain text to a cipher text stage by stage. In this paper, we propose the methods how to carry out the encryption operations. First, we describe how to design a hash function H that is used to conceal the encryption keys from attack. Then, given with a key-generator (a Petri net supposed to possess a large number of elementary T-invariants), we discuss how to randomly generate a series of encryption keys, the elementary T-invariants. Finally, we show how to use these encryption keys to encrypt a plain text to a cipher text by applying a private key cryptography, say DES.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we used a deep learning model to detect and segment flame and smoke in real time from fires. To this end, well known U-NET was used to separate and divide the flame and smoke of the fire using multi-class. As a result of learning using the proposed technique, the values of loss error and accuracy are very good at 0.0486 and 0.97996, respectively. The IOU value used in object detection is also very good at 0.849. As a result of predicting fire images that were not used for learning using the learned model, the flame and smoke of fire are well detected and segmented, and smoke color were well distinguished. Proposed method can be used to build fire prediction and detection system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.498-500
• /
• 2022

CCTV protects people and assets safely by identifying dangerous situations and responding promptly. However, it is difficult to continuously monitor the increasing number of CCTV images. For this reason, there is a need for a device that continuously monitors CCTV images and notifies when abnormal behavior occurs. Recently, many studies using artificial intelligence models for image data analysis have been conducted. This study simultaneously learns spatial and temporal characteristic information between image data to classify various abnormal behaviors that can be observed in CCTV images. As an artificial intelligence model used for learning, we propose a multi-classification deep learning model that combines an end-to-end 3D convolutional neural network(CNN) and ResNet.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1036-1038
• /
• 2020

This paper proposes a novel automated liver segmentation using Multi-Dilated U-Nets. The proposed multidilation segmentation model has the advantage of considering both local and global shapes of the liver image. We use the CT images subject-wise, every 2D image is concatenated to 3D to calculate the IOU score and DICE score. The experimental results on Jeonbuk National University hospital dataset achieves better performance than the conventional U-Net.

• Journal of Fisheries and Marine Sciences Education
• /
• v.5 no.2
• /
• pp.90-97
• /
• 1993

Pair trawling is one of the important fishing methods for Korean fisheries, and is working in the western sea of Korea - the Yellow Sea and the East China Sea. On the engine power of the trawlers, 72% of 190 pairs of trawlers were equipped with 450ps class engine, and 21% with 450~750ps and merely 7% with in 750ps class 1980. Thereafter the engine power has grown up, so that 450~750ps occupy 28% and 750ps or more 27% in 1992. Main objective fishes of pair trawling were traditionally flat fishes, so the fundamental shape of pair trawl net was a four - seam net, but by the gradual shortage of flat fishes, roundfishes has been noticed. So the six - seam net which performs high opening of net mouth has been used widely since 1985. In the six - seam net, the length of wing was not so short in the beginning but became short in the later instead of the net pendant elongated, and also the pendant was separated into three pieces according to the change of wing structure. Since the 1990's, the objective fishes has gradually been changed into pelagic fishes, the fishing technique is required to fit the behavior of fishes. So the midwater trawling or the multi -layer trawling became required.

• Journal of Korea Multimedia Society
• /
• v.23 no.9
• /
• pp.1155-1163
• /
• 2020

Deep learning approach is emerging as a new way to improve the accuracy of tree species identification using bark image. However, the approach has not been studied enough because it is confronted with the problem of acquiring a large volume of bark image dataset. This study solved this problem by utilizing a pretrained off-the-shelf DCNN model. It compares the discrimination power of bark features extracted by each DCNN model. Then it extracts the features by using a selected DCNN model and feeds them to a multi-layer perceptron (MLP). We found out that the ResNet50 model is effective in extracting bark features and the MLP could be trained well with the features reduced by the principal component analysis. The proposed approach gives accuracy of 99.1% and 98.4% for BarkTex and Trunk12 datasets respectively.

• Journal of Internet Computing and Services
• /
• v.3 no.4
• /
• pp.19-26
• /
• 2002

Workflow Management Systems(WFMSs) is a software system that supports that specification and execution of business processes. In this paper, we proposed Multi Agent Based Workflow Modeling System which was implemented by Java application. The proposed workflow modeling system is divided into four agents; Session, Organization, Relevant Data. Invoked Application. We adapted ICN(Information Control Net) to check workflow model syntax, And the proposed modeling system provide the function to import/export WPDL which was defined in WfMC.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.9
• /
• pp.2234-2244
• /
• 1994

A process sequence of multi-operation cold forging for actual application in industry is designed with the rigid-plastic finite element method to form a constant velocity joint housing(CVJ housing). The material flow during the CVJ housing forming is axisymmetric until the final forging process for forming of ball grooves. This study treats the deformation as an axisymmetric case. The main objective of the process sequence design is to obtain preforms which satisfy the design criteria of near-net-shape product requiring less machining after forming. The process sequence design also investigates velocity distributions, effective strain distributions and forging loads, which are useful information in the real process design.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.4
• /
• pp.319-325
• /
• 2001

Recently. AGV systems are used to serve the raw material to each work stations automatically. There exists a trade-off between the adequate service supply and the number of purchased AGVs. Also, to reduce the overall production cost, the amount of inventory hold on the shop floor should be considered. In this paper, we present a heuristic technique for determining the number of AGVs which includes the net present fixed costs of each station, each purchased AGV, delivering cost, stock inventory cost, and safety stock inventory cost. Secondly, by using a genetic algorithm, the optimal number of AGVs and the optimal reorder quantity at each station are decided. Lastly, to verify then heuristic algorithm, we have done a computer simulation with different GA parameters.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.30A no.12
• /
• pp.135-146
• /
• 1993

A ner general multi-layer area router, called DINOSAUR, is presented in this paper. DINOSAUR can route various types of routing areas, such as L-shaped channel, switchbox with/without obstacles, and rectilinear area with/without internal modules/terminals. The DINOSAUR algorithm consists of three major stages: layerless maze routing, layering by coloring, and rip-up and reroute. In layerless maze roution stage, the route of each net is determined by modified maze algorithm without taking the conflicts(short. circuits) into account. In layering by coloring stage, the layer of each net is determinde by a heuristic coloring algorithm. When the conflicts are not removed, rip-up and reroute process is invoded. In rip-up and reroute stage, the conflicts are removed iteratively. Many test cases have been run, and on all the benchmark data known in the literature DINOSAUR has performed either better than or comparable to the other routers.