• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1995.06a
• /
• pp.137-141
• /
• 1995

MASF is a kind of temporal filter proposed for noise reduction and temporal band limitation. MASF uses motion vectors to extract temporal information in spatial domain. Therefore, inaccurate motion information causes some distortions in MASF operation. Currently, bilinear interpolation after MBA(Block Matching Algorithm) is used for the motion estimation sheme of MASF. But, this method results in unreliable estimation when the object in image sequence has larger movement than the maximum displacement assumed in BMA or the input images are severely corrupted with noise. In order to solve this problem, we propose a hierarchical motion estimation algorithm for MASF. Experimental results show that the proposed method produces reliable output under large motion and noisy situations.

• Proceedings of the KOSOMBE Conference
• /
• v.1993 no.05
• /
• pp.90-93
• /
• 1993

In this study, Korean speech was recognized by using spatio-temporal recognition neural network. The subjects of speech are numeric speech from zero to nine and basic command which might be used for motorized wheelchair developed it own Lab. Rabiner and Sambur's method of speech detection was used in determining end-point of speech, speech parameter was extracted by using LPC 16 order. The recognition rate was over 90%.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.3
• /
• pp.366-375
• /
• 2012

This paper describes a design and temporal analysis of a hardware-in-the-loop (HIL) simulation environment for testing a motor control unit (MCU). The design concepts and main characteristics including unavoidable time delays of each component module are described. From temporal analysis results according to the module integration method, an appropriate solution is proposed to fix and minimize time delays. In order to verify the effectiveness of the proposed solution, the HIL test results are compared with the results of experiments and an offline simulation.

• Spatial Information Research
• /
• v.19 no.2
• /
• pp.65-70
• /
• 2011

Advertizing postal system combined with GIS and temporal/spatial mining techniques has been developed to activate advertizing service and conduct marketing campaign efficiently. In order to select customers accurately, this system provide purchase propensity information using sequential, cyclicpatterns and lifesytle information through RFM analysis and clustering technique. It is possible for corporate mailer to do customer oriented marketing campaign with the advertizing postal system as well as 'one-stop' service including target customer selection, mail production, and delivery request.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.06a
• /
• pp.377-381
• /
• 2001

An ATMS(Assumption-based Truth Maintenance System) has been widely used for maintaining the truth of information by detecting and solving contradictions in nile-based systems. But the ATMS can not correctly maintain the truth of the information in case that the generated information is satisfied within a time interval or includes data about temporal relations of events in time varying situations, because it has no mechanism manipulating temporal data. In this paper, The extended ATMS method is proposed, which can maintain the truth of the information in the inference system using information changing over time or temporal relations of events. In order to maintain contexts generated by relations of events, the label representation method is modified, the disjunction, conjunction simplification method in the label-propagation procedure and nogood handling method of the conventional ATMS are modified, too.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.470-472
• /
• 2003

The primary goal in this paper is to analyze urban growth patterns using multi-temporal remote sensing images and geographic information data. In order to accomplish this purpose, firstly data pre-processing is carried out, and then land-use maps are generated with ancillary data source by heads-up on-screen digitizing. Lastly, using the results of the previous stages, the patterns of land-use and urban changes are monitored by the proposed scheme. In this research, using the multi-temporal images and geographic information data, monitoring of urban growth was carried out with the application of urban land-use changes.

• Journal of information and communication convergence engineering
• /
• v.19 no.1
• /
• pp.42-47
• /
• 2021

Multimedia Authoring Tool is a tool for creating multimedia presentations. With this tool, a user can produce playable multimedia documents. A Multimedia Authoring Tool requires input in the form of a spatial layout and a temporal layout. Users can make many mistakes in creating multimedia presentations and verification is required in the Multimedia Authoring process in order to produce multimedia documents. In this study, two verification phases are proposed: Time Computation and Spatiotemporal Conflict Verification. In the experiment conducted for this study, two kinds of verification were carried out: The use of single-phase verification and the use of double-phase verifications. By using these two types of verification, it became easier to successfully detect errors in the spatial and temporal layouts, and the types of verification have also been successful in increasing the success of error detection.

• East Asian mathematical journal
• /
• v.34 no.5
• /
• pp.601-614
• /
• 2018

In this paper, we introduce an extrapolated higher order characteristic finite element method to approximate solutions of nonlinear Sobolev equations with a convection term and we establish the higher order of convergence in the temporal and the spatial directions with respect to $L^2$ norm.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.139-155
• /
• 2024

This study performed a multi-classification task to classify mesial temporal lobe epilepsy with left hippocampal sclerosis patients (left mTLE), mesial temporal lobe epilepsy with right hippocampal sclerosis (right mTLE), and healthy controls (HC) using magnetoencephalography (MEG) data. We applied various artificial neural networks and compared the results. As a result of modeling with convolutional neural networks (CNN), recurrent neural networks (RNN), and graph neural networks (GNN), the average k-fold accuracy was excellent in the order of CNN-based model, GNN-based model, and RNN-based model. The wall time was excellent in the order of RNN-based model, GNN-based model, and CNN-based model. The graph neural network, which shows good figures in accuracy, performance, and time, and has excellent scalability of network data, is the most suitable model for brain research in the future.

• Journal of KIISE:Information Networking
• /
• v.35 no.5
• /
• pp.374-383
• /
• 2008

IEEE 802.11 WLANs support various data rates in order to adapt to wireless channel condition. It is known that when some WLAN stations use a lower data rate than the others, total throughput is considerably degraded. The concept of temporal fairness which provides equal time to all stations has been introduced to alleviate this performance anomaly problem. However, most previous mechanisms assume that stations have infinite backlogs in the MAC layer and do not consider transport layer. In this paper, we first examine and analyze the performance of previous methods considering transport layer protocols. We then propose two new temporal fairness guarantee methods: AP priority and dynamic CWmin adjustment. We carried out extensive performance study via ns-2 computer simulations. The results show that the proposed methods provide temporal fairness and improve the throughput of WLANs in various environments.