• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• 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.

• Molecules and Cells
• /
• 제43권3호
• /
• pp.215-221
• /
• 2020

The olfactory bulb (OB) has an extremely higher proportion of interneurons innervating excitatory neurons than other brain regions, which is evolutionally conserved across species. Despite the abundance of OB interneurons, little is known about the diversification and physiological functions of OB interneurons compared to cortical interneurons. In this review, an overview of the general developmental process of interneurons from the angles of the spatial and temporal specifications was presented. Then, the distinct features shown exclusively in OB interneurons development and molecular machinery recently identified were discussed. Finally, we proposed an evolutionary meaning for the diversity of OB interneurons.

• 한국농림기상학회지
• /
• 제15권3호
• /
• pp.161-170
• /
• 2013

이 논문에서는 산지사면에서 나타나는 수문과정의 이해를 증진하기 위해서 관측된 토양수분의 분포와 거동을 수치지형분석을 통한 지형요소와의 상관관계를 연구하였다. 계절에 따른 강우 및 토양구조의 차이가 영향을 주는 사면 깊이 별 토양수분의 변동을 상관성 분석을 통해 도출하였다. 경기도 파주시 설마천 유역에 위치하고 있는 사면에서 봄, 여름, 가을 등 각 3계절을 대상으로 4월, 7월, 10월 기간의 토양수분 시계열 관측 자료를 사용하여, 지표면과 기반암의 표고 모형을 사용하여 다방향 흐름 알고리즘과 경사도, 곡률 등 18개 요소와의 상관관계를 분석하였다. 도출된 지형과 토양수분의 상관관계는 계절별로 강우의 양상과 토양 깊이에 따라 상이한 양상을 보여 주고 있다. 이러한 상관관계를 통해 사면에서 토양수분의 분포 및 흐름선을 예측하여 공간적인 분석을 도모하고, 토양수분의 거동을 가장 적합하게 모사하는 모형과 지형요소를 평가하고 도출할 수 있을 것이다.

• 대한전자공학회논문지SP
• /
• 제37권4호
• /
• pp.11-19
• /
• 2000

도로 위에 설치된 카메라에서 획득한 입력 영상으로부터 각 차선의 통과 차량수, 차량속도 도로 점유율, 차간 거리, 차종 등의 교통정보를 실시간으로 산출하는 기법은 지능형 교통 시스템(ITS)의 핵심 분야이다. 본 논문에서는 검지영역의 시공간 영상 분석에 의해 다양한 기상 조건과 그림자 등의 환경의 변화에 민감하지 않은 교통정보 산출기법을 제안한다. 각 차선에 2개의 검지영역을 설정하고 검지영역의 통계적 특성과 형상적 특성을 이용해 도로영역, 그림자 영역, 차량영역으로 분류하여 차량을 검지하며 시공간 영상 분석을 통하여 정량적 교통정보를 산출한다. 제안한 기법은 영상의 국부 검지영역 데이터만을 사용하므로 1초에 30 프레임이상의 실시간 처리가 가능하며 기상 조건과 그림자의 변화에 견실한 차량검지 및 교통정보 산출 능력을 구현할 수 있다.

• 한국전문물리치료학회지
• /
• 제21권3호
• /
• pp.80-88
• /
• 2014

Previous studies have reported that decreased cognitive ability has been consistently associated with significant declines in performance of one or both tasks under a dual-task walking condition. This study examined the relationship between specific cognitive abilities and the dual-task costs (DTCs) of spatio-temporal gait parameters in stroke patients. The spatio-temporal gait parameters were measured among 30 stroke patients while walking with and without a cognitive task (Stroop Word-Color Task) at the study participant's preferred walking speed. Cognitive abilities were measured using Computerized Neuropsychological Testing. Pearson's correlation coefficients (r) were calculated to quantify the associations between the neuropsychological measures and the DTCs in the spatio-temporal gait parameters. Moderate to strong correlations were found between the Auditory Continuous Performance test (ACPT) and the DTCs of the Single Support Time of Non-paretic (r=.37), the Trail Making A (TMA) test and the DTCs of Velocity (r=.71), TMA test and the DTCs of the Step Length of Paretic (r=.37), TMA test and the DTCs of the Step Length Non-paretic (r=.36), the Trail Making B (TMB) test and the DTCs of Velocity (r=.70), the Stroop Word-Color test and the DTCs of Velocity (r=-.40), Visual-span Backward (V-span B) test and the DTCs of Velocity (r=-.41), V-span B test and the DTCs of the Double Support Time of Non-paretic (r=.38), Digit-span Forward test and the DTCs of the Step Time of Non-paretic (r=-.39), and Digit-span Backward test and the DTCs of the Single Support Time of Paretic (r=.36). Especially TMA test and TMB test were found to be more strongly correlated to the DTCs of gait velocity than the other correlations. Understanding these cognitive features will provide guidance for identifying dual- task walking ability.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.413-415
• /
• 2022

인간의 관절은 인간의 신체를 구성하는 요소로 인간의 행동을 분석하는데 유용한 정보로 활용될 수 있기 때문에 관절 정보를 이용한 행동인식에 대한 많은 연구가 진행되었다. 하지만 각각의 독립적인 관절 정보만을 이용해서 시시각각 변화하는 인간의 행동을 인식하는 것은 매우 복잡한 문제이다. 따라서 학습에 사용할 부가적인 정보 추출 방법과 과거의 상태를 기반으로 현재 상태를 판단하는 고려하는 알고리즘이 필요하다. 본 논문에서는 연결된 관절들의 위치 관계와 각 관절의 위치가 시간의 흐름에 따라 변화하는 것을 고려한 행동 인식 기법을 제안한다. 사전 학습된 관절 추출 모델을 이용하여 각 관절의 위치 정보를 획득하고 연결된 관절 사이의 차 벡터를 이용하여 뼈대 정보를 추출한다. 그리고 두 가지 형태의 입력에 맞춰 간소화된 신경망을 구성하고 LSTM을 더하여 시·공간적 특징을 추출하도록 한다. 9개의 행동으로 구성된 데이터 셋을 이용하여 실험한 결과 각 관절 및 뼈대의 시·공간적 관계 특징을 고려하여 행동 인식 정확도를 측정하였을 때 단일 관절 정보만을 이용한 결과에 비해 뛰어난 성능을 보임을 확인하였다.

• 한국정밀공학회지
• /
• 제26권2호
• /
• pp.126-132
• /
• 2009

This study examined the differences in spatio-temporal parameters, joint angle, ground reaction force (GRF), and joint power according to the changes of gait speed for trans-tibial amputees to investigate the features of the energy-storing foot for sports. The subjects walked at normal speed and at fast speed, wearing a single-axis type foot (Korec) and an energy-storing foot for sports (Renegade) respectively. The results showed that Renegade yielded faster gait speed as well as more symmetric gait pattern, compared to Korec. However, as gait speed was increased, there was no significant difference in kinematics, ground reaction force, and joint power between two artificial foots. This was similar to the results from previous studies regarding the energy-storing foot, where the walking velocity and gait symmetry have been improved. Nevertheless, the result of this study differed from the previous ones which reported that joint angle, joint power, and GRF increased as the gait speed increased except spatio-temporal parameters.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1995년도 추계학술대회논문집
• /
• pp.46-55
• /
• 1995

The multimedia documents becomes the most natural user interface for CSCW(Conputer Supported Cooperative Work) in distributed environment. The objective of this study is to propose a multimedia document architecture and to develop a system that can manage it well. The new architecture is for revisable documents and is the basic layer for hypermedia documents. A good document architecture for CSCW must support pointing, marking, and editing over a part of documents. The user views, version control, and full- content search are also desirable features. In this paper, we discuss the basic concept of a new document architecture for CSCW. We also present the user interfaces for spatio-temporal compositions of multimedia documents.

• International Journal of Contents
• /
• 제4권2호
• /
• pp.24-28
• /
• 2008

In this paper, we propose a new approach for content-based video retrieval using non-parametric based motion classification in the shot-based video indexing structure. Our system proposed in this paper has supported the real-time video retrieval using spatio-temporal feature comparison by measuring the similarity between visual features and between motion features, respectively, after extracting representative frame and non-parametric motion information from shot-based video clips segmented by scene change detection method. The extraction of non-parametric based motion features, after the normalized motion vectors are created from an MPEG-compressed stream, is effectively fulfilled by discretizing each normalized motion vector into various angle bins, and by considering the mean, variance, and direction of motion vectors in these bins. To obtain visual feature in representative frame, we use the edge-based spatial descriptor. Experimental results show that our approach is superior to conventional methods with regard to the performance for video indexing and retrieval.