• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.99-104
• /
• 2022

Artificial intelligence is getting a crucial part of our lives with its incredible benefits. Machines outperform humans in recognizing objects in images, particularly in classifying people into correct age and gender groups. In this respect, age and gender classification has been one of the hot topics among computer vision researchers in recent decades. Deployment of deep Convolutional Neural Network(: CNN) models achieved state-of-the-art performance. However, the most of CNN based architectures are very complex with several dozens of training parameters so they require much computation time and resources. For this reason, we propose a new CNN-based classification algorithm with significantly fewer training parameters and training time compared to the existing methods. Despite its less complexity, our model shows better accuracy of age and gender classification on the UTKFace dataset.

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.139-147
• /
• 2017

Most of the information prevailing in the Internet space consists of textual information. So one of the main topics regarding the huge document analyses that are required in the "big data" era is the development of an automated understanding system for textual data; accordingly, the automation of the keyword extraction for text summarization and abstraction is a typical research problem. But the simple listing of a few keywords is insufficient to reveal the complex semantic structures of the general texts. In this paper, a text-visualization method that constructs a graph by computing the related degrees from the selected keywords of the target text is developed; therefore, two construction models that provide the edge relation are proposed for the computing of the relation degree among keywords, as follows: influence-interval model and word- distance model. The finally visualized graph from the keyword-derived edge relation is more flexible and useful for the display of the meaning structure of the target text; furthermore, this abstract graph enables a fast and easy understanding of the target text. The authors' experiment showed that the proposed abstract-graph model is superior to the keyword list for the attainment of a semantic and comparitive understanding of text.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.5
• /
• pp.563-569
• /
• 2012

The superheater and reheater tubes of a heavy-load fossil power plant boiler can be damaged by overheating, and therefore, the degree of overheating is assessed by measuring the oxide scale thickness inside the tube during outages. The tube temperature prediction from the oxide scale thickness measurement is necessarily accompanied by destructive tube sampling, and the result of tube temperature prediction cannot be expected to be accurate unless the selection of the overheated point is precise and the initial-operation tube temperature has been obtained. In contrast, if the tube temperature is to be predicted analytically, considerable effort (to carry out the analysis of combustion, radiation, convection heat transfer, and turbulence fluid dynamics of the gas outside the tube) is required. In addition, in the case of analytical tube temperature prediction, load changes, variations in the fuel composition, and operation mode changes are hardly considered, thus impeding the continuous monitoring of the tube temperature. This paper proposes a method for the short-term prediction of tube temperature; the method involves the use of boiler operation information and flow-network-analysis-based tube heat flux. This method can help in high-temperaturedamage monitoring when it is integrated with a practical tube-damage-assessment method such as the Larson-Miller Parameter.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.3
• /
• pp.153-164
• /
• 2007

The Access Grid (AG) provides collaboration environments over the IP multicast networks by enabling efficient exchange of multimedia contents among remote users; however, since lots of current networks are still multicast-disabled, it is not easy to deploy this multicast-based multi-party AG. For this problem, the AG provides multicast bridges as a solution by putting a relay server into the multicast networks. Multicast-disabled clients make UDP connections with this relay server and receive forwarded multicast traffics in unicast UDP packets. This solution is facing several limitations since it requires duplicate forwarding of the same packet for each unicast peer. Thus, in this paper, we propose an alternate solution for the multicast connectivity problem of the AG based on the UMTP (UDP multicast tunneling protocol). By taking advantage of flexibilities of UMTP, the proposed solution is designed to improve the efficiency of network and system utilization, to allow reuse of multicast-based AG applications without modification, and to partially address the NAT/firewall traversal issues. To verify the feasibility of proposed solution, we have implemented a prototype AG connectivity tool based on the UMTP, named as the AG Connector.

• Journal of Korean Society of Forest Science
• /
• v.78 no.2
• /
• pp.228-241
• /
• 1989

The objectives of this study are to identify flood disasters resulted from heavy rainstorm including earth and stone-debris avalanches and also to develope the scientific data to be needed for establishing the landslide-related disaster prevention countermeasures. For this study, 5 Gun (district) regions including Booyeo, Seochun, Gongju, Boryung, and Chungyang in Chungchongnam-do of the central part of Korea, in which severe landslide damages have been triggered during 3 days from July 21 to July 23, 1987, were investigated. Mostly, landslides having death of human lives triggered from 6 a.m, to 8 a,m. on July 22, and the principal factor was proved to be the continuous heavy rain ; the continuous rainfall of internal region for 3 days measured about 300-673 mm. The structural measures for slope failure prevention countermeasures at the hollow part of upper hillslope should be required. Natural drainage network on slopes should not be disturbed in case of land use alteration, such as a chestnut planting work on hillslopes behind the houses particularly. There are so many problems in recognition of landslide disaster prevention countermeasures including evacuation exercises. More actual education of countermeasures for control of flood and landslide should be put to practice through "civil defense education" and "inhabitants' meeting." In this context, existing Erosion Control Stations of 13 regions established in each Province should not be reduced. The designation criterion and surveying processes of "Landslide Prone Site" published by Forest Administration should also be improved scientifically.