• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.479-482
• /
• 2021

시계열 형태의 데이터는 다양한 분야에서 수집되고 응용되기 때문에 정확한 시계열 예측은 많은 분야에서 운영 효율성을 높일 수 있는 중요한 분석 방법으로 고려된다. 그중 다층 수평 예측은 사용자에게 전반적인 시계열 데이터 경향성을 제공할 수 있다. 하지만 다양한 정보를 포함하는 시계열 데이터는 데이터에 내재한 이질성(heterogeneity)까지 포괄적으로 고려한 방법을 통해서만 정확한 예측을 할 수 있다. 하지만 지금까지 많은 시계열 분석 모델들이 데이터의 이질성을 반영하지 못했다. 이러한 한계를 보완하고자 우리는 Temporal Fusion Transformer 모델을 사용하여 실생활과 밀접한 관련이 있는 데이터에 적용하여 이질성을 고려한 향상된 예측을 수행하였다. 실제, 주식 데이터와 미세 먼지 데이터와 같은 실생활 시계열 데이터에 적용하였고 실험 결과 기존 모델보다 Mean Squared Error(MSE)가 0.3487 낮은 것을 확인하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.299-308
• /
• 2014

Various literatures related computing of information processing have been recently shown the researches inspired from the remarkably excellent human capabilities which recognize and categorize very complex visual patterns such as body motions and facial expressions. Applied from human's outstanding ability of perception, the classification function of visual sequences without context information is specially crucial task for computer vision to understand both the coding and the retrieval of spatio-temporal patterns. This paper presents a biological process based action recognition model of computer vision, which is inspired from visual information processing of human brain for action recognition of visual sequences. Proposed model employs the structure of neural fields of bio-inspired visual perception on detecting motion sequences and discriminating visual patterns in human brain. Experimental results show that proposed recognition model takes not only into account several biological properties of visual information processing, but also is tolerant of time-warping. Furthermore, the model allows robust temporal evolution of classification compared to researches of action recognition. Presented model contributes to implement bio-inspired visual processing system such as intelligent robot agent, etc.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.11
• /
• pp.1645-1654
• /
• 1993

Unlike a noise removal recursive temporal filter, this paper presents a temporal filter which improves visual quality and data compression efficiency. In general, for the temporal band-limitation, temporal aliasing should be considered. Since most of a video signal has temporally aliased components, it is desirable to consider them. From a signal processing point of view, it is impossible to realize the filtering not afeced by the aliasings. However, in this paper, efficient filtering with de-aliasing characteristics is proposed. Considering the location of a video signal, temporal filtering can be accomplished by the spatial filtering along the motion vector trajectory (Motion Adaptive Spatial Filter). This filtered result dose not include the aliasings. Besides the efficient band-limitation, temporal noise is also reduced. For the evaluation of the MASF, its realization and filtering characteristics will be discussed in ditail.

• ETRI Journal
• /
• v.22 no.3
• /
• pp.41-51
• /
• 2000

An important use of data warehousing is to provide temporal views over the history of source data. It is significant that nearly all data warehouses are dependent on relational database technology, yet relational databases provide little or no real support for temporal data. Therefore, in is difficult to obtain accurate information for time-varying data. In this paper, we are going to design a temporal data warehouse to support time-varying data efficiently. For this purpose, we present a method to support temporal query by combining a temporal query process layer with the relational database which is used as a source database in an existing data warehouse. We introduce the Temporal Aggregate Tree Strategy (TATS), and suggest its algorithm for the way to aggregate the time-varying data that is changed by the time when the temporal view is created. In addition, The TATS and the materialized view creation method of the existing data warehouse have been evaluated. As a result, the TATS reduces the size of the fact table and it shows a good performance for the comparison factor in case of processing the query for time-varying data.

• The KIPS Transactions:PartC
• /
• v.11C no.1
• /
• pp.63-74
• /
• 2004

Temporal locality of Web server references is one of the important characteristics to be considered in the design of a Web caching strategy, and it is important to measure the temporal locality exactly. Various methods to estimate the temporal locality have been proposed, however, Web server designers have still troubles in its measurement by using the tools that don't reflect the interarrival time of document requests. In this paper, we propose a measurement tool for short-term temporal locality based on request interarrival time, and discuss the simulation results based on the flares from NLANR and NASA Web sites. The results show that the proposed tool estimates the short-term temporal locality more exactly than that based on a stack.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.1
• /
• pp.21-31
• /
• 1999

In this paper we study on an interface connection between spatial operators and temporal operators to support the unified operations for spationtemporal data. The integration development of the spatiotemporal operations will be defined as a common use of spatiotemporal relationship operators by spatiotemporal referencing macros. additionally we propose an integration algorithm of a history operator and temporal relationship operators. Then the proposed system will be implemented on the commercial GIS software and evaluated by examples of spatiotemporal query expressions. Here, our integration of spatial and temporal operators will provide spatiotemporal query expressions with a useful framework.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.11 no.3
• /
• pp.329-336
• /
• 2000

An important problem associated with adaptive sidelobe canceller(SLC) systems is that their performance deteriorates with an increase in jammers arriving from different directions. Generally the number of jammers which can be effectively cancelled is limited by the number of the auxiliary elements in a SLC system. But the single-auxiliary-element with tapped delay line adaptive filter can effectively cancel multiple jammers. Therefore this paper proposed the spatio-temporal processing structure cascading adaptive array and tapped delay line adaptive filter and showed that this could obtain more rapid convergence rate and an increase of DOF without increasing the number of element.

• The KIPS Transactions:PartD
• /
• v.12D no.1 s.97
• /
• pp.43-50
• /
• 2005

The Processing domains of spatio-temporal databases are divided into time-series databases for moving objects and sequence databases for discrete historical objects. Recently the selectivity estimation techniques for query optimization in spatio-temporal databases have been studied, but focused on query optimization in time-series databases. There wat no previous work on the selectivity estimation techniques for sequence databates as well. Therefore, we construct T-Minskew histogram for query optimization In sequence databases and propose a selectivity estimation method using the T-Minskew histogram. Furthermore we propose an effective histogram maintenance technique for food performance of the histogram.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.1
• /
• pp.1-13
• /
• 1994

The Temporal Database Management Testbed supports valid and transaction time. In this paper, we discuss the design and implementation of a testbed of a temporal database management system in main memory. The testbed consists of a syntactic analyzer, a semantic analyzer, a code generator, and an interpreter. The syntactic analyzer builds a parse tree from a temporal query. The semantic analyzer then checks it for correctness against the system catalog. The code generator builds an execution tree termed ann update network. We employ an incremental view materialization for the execution tree. After building the execution tree, the interpreter activates each node of the execution tree. Also, the indexing structure and the concurrency control are discussed in the testbed.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.4
• /
• pp.1-9
• /
• 1998

Temporal Databases store all of informations by time varying, so the temporal query processor has to process very large information. Therefore, we propose an efficient method of query processing by using the relevance checking algorithm of input query and view definition. The relevance checking algorithm of query investigates relevance between the input query of user about base relation and the execution tree of view definition stored in system catalog. And related input query with view definition have a process of the query translation to the execution tree of view. So temporal query processor is able to increase performance of query processor by reducing the number of tuple.