• The KIPS Transactions:PartD
• /
• v.14D no.5
• /
• pp.491-500
• /
• 2007

In order to classify and manage on-line trading goods, the product classification scheme must be maintained. In most systems for handling product information, the classification scheme is managed manually by experts, which in general incurs a lot of time and cost. Effective management of classification system becomes more important as rapid development of industry expedites diversity and convergence of goods and services. There have been many researches on developing classification scheme, and continuing in this line of research, this paper proposes a new method for automatic generation of product classification scheme. Our main idea starts from the concept that a product is a set of attributes, and we propose a novel algorithm for automatically creating hierarchical classification scheme by utilizing inclusive relationships between products. We then prove the effectiveness of proposed algorithm by conducting an experiment.

• Journal of KIISE:Databases
• /
• v.32 no.2
• /
• pp.142-150
• /
• 2005

A shared disks (SD) cluster couples multiple computing nodes, and every node shares a common database at the disk level. A great deal of research indicates that the SD cluster is suitable to high performance transaction processing, but the aggregation of SD cluster with real-time processing has not been investigated at all. A real-time transaction has not only ACID properties of traditional transactions but also time constraints. By adopting cluster technology, the real-time services will be highly available and can exploit inter-node parallelism. In this paper, we first develop an experiment model of an SD-based real-time database system (SD-RTDBS). Then we investigate the feasibility of real-time transaction processing in the SD cluster using the experiment model. We also evaluate the cross effect of real-time transaction processing algorithms and SD cluster algorithms under a wide variety of database workloads.

• The Journal of the Korea Contents Association
• /
• v.13 no.9
• /
• pp.28-38
• /
• 2013

During the past decades, the B+-tree has been most widely used as an index file structure for disk-resident databases. For the disk based B+-tree, a node update can be cheaply performed just by modifying its associated disk page in place. However, in case that the B+-tree is stored on flash memory, the traditional algorithms of the B+-tree come to be useless due to the prohibitive cost of in-place updates on flash memory. For this reason, the earlier schemes for flash memory B+-trees usually take an approach that saves B+-tree changes from real-time updates into extra temporary storage. Although that approach can easily prevent frequent in-place updates in the B+-tree, it can suffer from a waste of storage space and prolonged search times. Particularly, it is not allowable to process range searches on the leaf node level. To resolve such problems, we devise a new scheme in which the leaf nodes and their parent node are stored together in a single flash block, called the p-node block.

• Journal of KIISE:Databases
• /
• v.36 no.6
• /
• pp.422-433
• /
• 2009

As an effort to secure Semantic Web, in this paper, we introduce an RDF access authorization model based on an ontology hierarchy and an RDF triple pattern. In addition, we apply the authorization model to RDF query validation for approved access authorizations. A subscribed SPARQL or RQL query, which has RDF triple patterns, can be denied or granted according to the corresponding access authorizations which have an RDF triple pattern. In order to efficiently perform the query validation process, we first analyze some primary authorization conflict conditions under RDF subsumption inference, and then we introduce an efficient query validation algorithm using the conflict conditions and Dewey graph labeling technique. Through experiments, we also show that the proposed validation algorithm provides a reasonable validation time and when data and authorizations increase it has scalability.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.544-549
• /
• 2006

This research is to introduce about Judgment System for Intelligent Movement(JSIM) that can perform assistance work of human brain. JSIM can order autonomous command and also it can be directly controlled by user. This research assumes that control object is limited to Mobile Robot(MR) Mobile robot offers image and ultrasonic sensor information to user carrying JSIM and it performs guide to user. JSIM having PDA and Sensor-box controls velocity and direction of the mobile robot by soft-computing method that inputs user's command and information that is obtained to mobile robot. Also it controls mobile robot to achieve various movement. This paper introduces wearable JSIM that communicates with around devices and that can do intelligent judgment. To verify the possibility of the proposed system, in real environment, the simulation of control and application problem lot mobile robot will be introduced. Intelligent algorithm in the proposed system is generated by mixed hierarchical fuzzy and neural network.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.781-783
• /
• 2014

Mobile ad hoc network(MANET) consists of node that has mobility. MANET has increased overhead that caused by frequent topology changes. For reducing overhead, hierarchical network that communicates through cluster head node has been researched. When traffic is concentrated on cluster head node, cluster member node can't send message. To solve this problem, we proposed Step Parent algorithm. Proposed algorithm, cluster member node checks traffic of cluster head node using route path of other cluster head node in efficient coverage area. When cluster head node has increased traffic, cluster member node make a new route path by route path by routing path to another cluster head node. So cluster member node sends a message to destination node, we check improving delivery ratio.

• Smart Media Journal
• /
• v.10 no.3
• /
• pp.23-30
• /
• 2021

Although the manufacturing time series data clustering technique is an important grouping solution in the field of detecting and improving manufacturing large data-based equipment and process defects, it has a disadvantage of low accuracy when applying the existing static data target clustering technique to time series data. In this paper, an evolutionary computation-based time series cluster analysis approach is presented to improve the coherence of existing clustering techniques. To this end, first, the image shape resulting from the manufacturing process is converted into one-dimensional time series data using linear scanning, and the optimal sub-clusters for hierarchical cluster analysis and split cluster analysis are derived based on the Pearson distance metric as the target of the transformation data. Finally, by using a genetic algorithm, an optimal cluster combination with minimal similarity is derived for the two cluster analysis results. And the performance superiority of the proposed clustering is verified by comparing the performance with the existing clustering technique for the actual manufacturing process image.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.4
• /
• pp.91-103
• /
• 2006

This paper proposes a methodology to evaluate the quality and level of difficulty of fingerprint image databases, which leads to objective evaluation for the performance of fingerprint recognition system. Influencing factors to fingerprint matching are defined and the matching performance between two fingerprint images is evaluated using segmentation and orientation filed. In this study, a hierarchical processing method is proposed to measure an orientation field, which is able to improve the matching speed and accuracy. The results of experiments demonstrate that the defined influencing factors can describe the characteristics of fingerprint databases. Level of difficulty for fingerprint databases enables the performance of fingerprint recognition algorithms to be evaluated and compared even with different databases.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.987-994
• /
• 2020

In this paper, we studied the effect of kernel size of CNN layer on performance in acoustic noise attenuators. This system uses a deep learning algorithm using a neural network adaptive prediction filter instead of using the existing adaptive filter. Speech is estimated from a single input speech signal containing noise using a 100-neuron, 16-filter CNN filter and an error back propagation algorithm. This is to use the quasi-periodic property in the voiced sound section of the voice signal. In this study, a simulation program using Tensorflow and Keras libraries was written and a simulation was performed to verify the performance of the noise attenuator for the kernel size. As a result of the simulation, when the kernel size is about 16, the MSE and MAE values are the smallest, and when the size is smaller or larger than 16, the MSE and MAE values increase. It can be seen that in the case of an speech signal, the features can be best captured when the kernel size is about 16.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.13-20
• /
• 2019

Recently, object detection technology based on CNN has been actively studied. Object detection technology is used as an important technology in autonomous vehicles, intelligent image analysis, and so on. In this paper, we propose a rotation change robust object detection system by applying MI-FL (Moment Invariant-Feature Layer) to SSD (Single Shot Multibox Detector) which is one of CNN-based object detectors. First, the features of the input image are extracted based on the VGG network. Then, a total of six feature layers are applied to generate bounding boxes by predicting the location and type of object. We then use the NMS algorithm to get the bounding box that is the most likely object. Once an object bounding box has been determined, the invariant moment feature of the corresponding region is extracted using MI-FL, and stored and learned in advance. In the detection process, it is possible to detect the rotated image more robust than the conventional method by using the previously stored moment invariant feature information. The performance improvement of about 4 ~ 5% was confirmed by comparing SSD with existing SSD and MI-FL.