• Journal of KIISE:Databases
• /
• v.30 no.2
• /
• pp.176-183
• /
• 2003

Various techniques including histograms, sampling and parametric techniques have been proposed to estimate query result sizes for the query optimization. Histogram-based techniques are the most widely used form for the selectivity estimation in relational database systems. However, in the spatio-temporal databases for the moving objects, the continual changes of the data distribution suffer the direct utilization of the state of the art histogram techniques. Specifically for the future queries, we need another methodology that considers the updated information and keeps the accuracy of the result. In this paper we propose a novel approach based upon the duality and the marginal distribution to construct a histogram with very little time since the spatio-temporal histogram requires the data distribution defined by query predicates. We use data synopsis method in the dual space to construct spatio-temporal histograms. Our method is robust to changing data distributions during a certain period of time while the objects keep the linear movements. An additional feature of our approach supports the dynamic update incrementally and maintains the accuracy of the estimated result.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3598-3614
• /
• 2020

With the increase of motor vehicles and tourism demand, some traffic problems gradually appear, such as traffic congestion, safety accidents and insufficient allocation of traffic resources. Facing these challenges, a model of Spatio-Temporal Dilated Convolutional Network (STDGCN) is proposed for assistance of extracting highly nonlinear and complex characteristics to accurately predict the future traffic flow. In particular, we model the traffic as undirected graphs, on which graph convolutions are built to extract spatial feature informations. Furthermore, a dilated convolution is deployed into graph convolution for capturing multi-scale contextual messages. The proposed STDGCN integrates the dilated convolution into the graph convolution, which realizes the extraction of the spatial and temporal characteristics of traffic flow data, as well as features of road occupancy. To observe the performance of the proposed model, we compare with it with four rivals. We also employ four indicators for evaluation. The experimental results show STDGCN's effectiveness. The prediction accuracy is improved by 17% in comparison with the traditional prediction methods on various real-world traffic datasets.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.129-137
• /
• 2004

This paper presents a signature verification method that uses Gabor filter in computing similarity between signatures. In computing similarity to compare two on-line signatures, the temporal relationship between two signatures should be computed in advance. However, conventional point matching method using DP(dynamic programming) matching consumes much computation. In this paper, we propose a fast method for computing the temporal relationship between two on-line signatures by using the phase output of Gabor Inter applied on the on-line signature signals. Two similarity measures are defined in the method: Temporal Similarity and Temporally Arranged Feature Profile Similarity. With the proposed method, Ive could compare signatures 30 times faster than conventional method using DP matching.

• The KIPS Transactions:PartD
• /
• v.11D no.1
• /
• pp.69-82
• /
• 2004

A moving object has a special feature that it's spatial location, shape and size are changed as time goes. These changes of the object accompany the continuous movement that is called the trajectory. In this paper, we propose an index structure that users can retrieve the trajectory of a moving object with the access of a page. We also propose the multi-complex query that is a new query type for trajectory retrieval. In order to prove the excellence of our method, we compare and analyze the performance for query time and storage space through experiments in various environments. It is shown that our method outperforms the existing index structures when processing spatio-temporal trajectory queries on moving objects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5624-5638
• /
• 2016

A novel method based on Surf points is proposed to detect and lock-track single ground target in aerial videos. Videos captured by moving cameras contain complex motions, which bring difficulty in moving object detection. Our approach contains three parts: moving target template detection, search area estimation and target tracking. Global motion estimation and compensation are first made by grids-sampling Surf points selecting and matching. And then, the single ground target is detected by joint spatial-temporal information processing. The temporal process is made by calculating difference between compensated reference and current image and the spatial process is implementing morphological operations and adaptive binarization. The second part improves KALMAN filter with surf points scale information to predict target position and search area adaptively. Lastly, the local Surf points of target template are matched in this search region to realize target tracking. The long-term tracking is updated following target scaling, occlusion and large deformation. Experimental results show that the algorithm can correctly detect small moving target in dynamic scenes with complex motions. It is robust to vehicle dithering and target scale changing, rotation, especially partial occlusion or temporal complete occlusion. Comparing with traditional algorithms, our method enables real time operation, processing $520{\times}390$ frames at around 15fps.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.559-565
• /
• 2017

A lot of studies have been conducted to recognize the motion state or behavior of the user using the acceleration sensor built in the smartphone. In this paper, we applied the neural networks to the 3-axis acceleration information of smartphone to study human behavior. There are performance issues in applying time series data to neural networks. We proposed a multi-temporal neural networks which have trained three neural networks with different time windows for feature extraction and uses the output of these neural networks as input to the new neural network. The proposed method showed better performance than other methods like SVM, AdaBoot and IBk classifier for real acceleration data.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.5
• /
• pp.71-78
• /
• 2014

The RFID-tag objects can be recognized by a distinct reader where it is installed. The RFID-tag objects are likely described as storages rather than the mobiles in the use of GPS. As RFID tags are large in number compared to moving objects, so the storing and retrieval costs are highly expensive. Here, two solutions for spatio-temporal model taking account of the feature in the tagged objects are proposed. First, the moving-tag objects are expressed by the terms "now" as well as "path location". Second, the size of storing index was noticeably reduced by not saving the tag information of palletizing products but mapping the tagged objects.

• Journal of Biomedical Engineering Research
• /
• v.27 no.4
• /
• pp.170-179
• /
• 2006

The purpose of this study was to investigate the spatiotemporal cortical activation pattern and functional connectivity during visual perception of words. 61 channel recordings of electroencephalogram were obtained from 15 subjects while they were judging the meaning of Korean, English, and Chinese words with concrete meanings. We examined event-related potentials (ERP) and applied independent component analysis (ICA) to find and separate simultaneously activated neural sources. Spectral analysis was also performed to investigate the gamma-band activity (GBA, 30-50 Hz) which is known to reflect feature binding. Five significant ERP components were identified and left hemispheric dominance was observed for most sites. Meaningful differences of amplitudes and latencies among languages were observed. It seemed that familiarity with each language and orthographic characteristics affected the characteristics of ERP components. ICA helped confirm several prominent sources corresponding to some ERP components. The results of spectral and time-frequency analyses showed distinct GBAs at prefrontal, frontal, and temporal sites. The GBAs at prefrontal and temporal sites were significantly correlated with the LPC amplitude and response time. The differences in spatiotemporal patterns of GBA among languages were not prominent compared to the inter-individual differences. The gamma-band coherence revealed short-range connectivity within frontal region and long-range connectivity between frontal, posterior, and temporal sites.

• Phonetics and Speech Sciences
• /
• v.11 no.2
• /
• pp.1-13
• /
• 2019

This study explored the relationship between accurate vowel production and proficiency levels in L2 English produced by Korean EFL adult learners. To this end, nine English vowels /i, ɪ, ɛ, æ, ʌ, ɔ, ɑ, ʊ, u/ were selected and adjacent vowels paired up (e.g., /i/-/ɪ/, /u/-/ʊ/, /ɛ/-/æ/, /ʌ/-/ɔ/, /ɔ/-/ɑ/). The spectral features of the pairs were measured instrumentally, namely F1 (indicating tongue height) and F2 (indicating tongue backness). Meanwhile, the durations as well as spectral features of the tense and lax counterparts in /i/-/ɪ/ and /u/-/ʊ/ were measured, as both temporal and spectral features are important in distinguishing them. The findings of this study confirm that higher-rated speakers were better able to distinguish the contrasts in the front vowel pairs /i/-/ɪ/ and /ɛ/-/æ/ than lower-rated learners, but in the central and back vowel pairs /u/-/ʊ/and /ʌ/-/ɔ/ (though not /ɔ/-/ɑ/), Korean EFL learners generally showed difficulty distinguishing adjacent vowels with spectral cues. On the other hand, the durations of the tense and lax vowels showed that the lower-rated speakers were less able to use the temporal feature to differentiate tense vowels from their lax counterparts, unlike previous studies that found that in general Korean learners depend excessively on the temporal cue to distinguish tense and lax vowels.

• Atmosphere
• /
• v.23 no.1
• /
• pp.33-37
• /
• 2013

In meteorology, exploitation of Kalman filter as a data assimilation system is virtually impossible due to simultaneous requirements of adjoint model and large computer resource. The other substitute of utilizing ensemble Kalman filter is only affordable by compensating an enormous usage of computing resource. Furthermore, the latter employs ensemble integration sets for evolving the background error covariance matrix by compensating the dynamical feature of the temporal evolution of weather conditions. We propose a new implementation method that works without the adjoint model by utilizing the explicit expression of the background error covariance matrix in backward evolution. It will also break a barrier in the evolution of the covariance matrix. The method may be applied with a slight modification to the real time assimilation or the retrospective analysis.