• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.209-212
• /
• 2011

Triangulation is a typical method to locate or identify the location, which requires inherently at least three pre-recognized reference points. In some cases, owing to out of reachability to communication facility the target node can not reachable always to three base stations. This paper presents a predictive method, which can estimate the location of the moving target node in real time even though the target could not get in touch with all three base stations. The method is based on the PID-controlled Moving Objects Spatio-Temporal Model Algorithm. This can predict the moving direction of the moving target, and then combine with the past target position information to judge accurately the location.

• Journal of information and communication convergence engineering
• /
• v.9 no.5
• /
• pp.545-550
• /
• 2011

Trilateration is a typical method to locate an object, which requires inherently at least three prerecognized reference points. In some cases, owing to out of reachability to communication facilities the target node cannot be reachable always to three base stations. This paper presents a predictive method, which can identify the location of a moving target node in real time even though the target node could not get in touch with all three base stations. The method is based on the PIDcontrolled Moving Objects Spatio-Temporal Model Algorithm. Simulation results verify that this method can predict the moving direction of a moving target, and then combine with its past position information to judge accurately the location.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.977-985
• /
• 2020

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying Batch Normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93.42% and 67.82%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition.

• Journal of Information Processing Systems
• /
• v.16 no.3
• /
• pp.612-628
• /
• 2020

This paper presents a new approach for detecting abnormal behaviors in complex surveillance scenes where anomalies are subtle and difficult to distinguish due to the intricate correlations among multiple objects' behaviors. Specifically, a cascaded probabilistic topic model was put forward for learning the spatial context of local behavior and the temporal context of global behavior in two different stages. In the first stage of topic modeling, unlike the existing approaches using either optical flows or complete trajectories, spatio-temporal correlations between the trajectory fragments in video clips were modeled by the latent Dirichlet allocation (LDA) topic model based on Markov random fields to obtain the spatial context of local behavior in each video clip. The local behavior topic categories were then obtained by exploiting the spectral clustering algorithm. Based on the construction of a dictionary through the process of local behavior topic clustering, the second phase of the LDA topic model learns the correlations of global behaviors and temporal context. In particular, an abnormal behavior recognition method was developed based on the learned spatio-temporal context of behaviors. The specific identification method adopts a top-down strategy and consists of two stages: anomaly recognition of video clip and anomalous behavior recognition within each video clip. Evaluation was performed using the validity of spatio-temporal context learning for local behavior topics and abnormal behavior recognition. Furthermore, the performance of the proposed approach in abnormal behavior recognition improved effectively and significantly in complex surveillance scenes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2824-2838
• /
• 2013

There has been a lot of attention paid recently to analyze dynamic human gestures that vary over time. Most attention to dynamic gestures concerns with spatio-temporal features, as compared to analyzing each frame of gestures separately. For accurate dynamic gesture recognition, motion feature extraction algorithms need to find representative features that uniquely identify time-varying gestures. This paper proposes a new feature-extraction algorithm using temporal self-similarity based on a hierarchical human model. Because a conventional temporal self-similarity method computes a whole movement among the continuous frames, the conventional temporal self-similarity method cannot recognize different gestures with the same amount of movement. The proposed model-based temporal self-similarity method groups body parts of a hierarchical model into several sets and calculates movements for each set. While recognition results can depend on how the sets are made, the best way to find optimal sets is to separate frequently used body parts from less-used body parts. Then, we apply a multiclass support vector machine whose optimization algorithm is based on structural support vector machines. In this paper, the effectiveness of the proposed feature extraction algorithm is demonstrated in an application for taebo gesture recognition. We show that the model-based temporal self-similarity method can overcome the shortcomings of the conventional temporal self-similarity method and the recognition results of the model-based method are superior to that of the conventional method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3037-3054
• /
• 2019

Public bicycle system (PBS) is a new emerging and popular mode of public transportation. PBS data can be adopted to analyze human movement patterns. Previous work usually focused on specific scales, and the relationships between different levels of hierarchies are ignored. In this paper, we introduce a multi-scale and interactive visual analytics system to investigate human cycling movement and PBS usage condition. The system supports level-of-detail explorative analysis of spatio-temporal characteristics in PBS. Visual views are designed from global, regional and microcosmic scales. For the regional scale, a bicycle network is constructed to model PBS data, and an flow-based community detection algorithm is applied on the bicycle network to determine station clusters. In contrast to the previous used Louvain algorithm, our method avoids producing super-communities and generates better results. We provide two cases to demonstrate how our system can help analysts explore the overall cycling condition in the city and spatio-temporal aggregation of stations.

• ETRI Journal
• /
• v.30 no.6
• /
• pp.765-773
• /
• 2008

Spatial correlation is a result of insufficient antenna spacing among multiple antenna elements, while temporal correlation is caused by Doppler spread. This paper compares the effect of spatial and temporal correlation in order to investigate the performance of multiuser scheduling algorithms in multiple-input multiple-output (MIMO) broadcast channels. This comparison includes the effect on the ergodic capacity, on fairness among users, and on the sum-rate capacity of a multiuser scheduling algorithm utilizing statistical channel state information in spatio-temporally correlated MIMO broadcast channels. Numerical results demonstrate that temporal correlation is more meaningful than spatial correlation in view of the multiuser scheduling algorithm in MIMO broadcast channels. Indeed, the multiuser scheduling algorithm can reduce the effect of the Doppler spread if it exploits the information of temporal correlation appropriately. However, the effect of spatial correlation can be minimized if the antenna spacing is sufficient in rich scattering MIMO channels regardless of the multiuser scheduling algorithm used.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.11
• /
• pp.1910-1915
• /
• 2008

The load analysis for the distribution system and facilities has relied on measurement equipment. Moreover, load monitoring incurs huge costs in terms of installation and maintenance. This paper presents a new model to analyze wherein facilities load under a feeder every 15 minutes using meter reading data that can be obtained from a power consumer every 15 minute or a month even without setting up any measuring equipment. After the data warehouse is constructed by interfacing the legacy system required for the load calculation, the relationship between the distribution system and the power consumer is established. Once the load pattern is forecasted by applying clustering and classification algorithm of temporal data mining techniques for the power customer who is not involved in Automatic Meter Reading(AMR), a single-line diagram per feeder is created, and power flow calculation is executed. The calculation result is analyzed using various temporal and spatial analysis methods such as Internet Geographic Information System(GIS), single-line diagram, and Online Analytical Processing (OLAP).

• Geophysics and Geophysical Exploration
• /
• v.21 no.3
• /
• pp.139-149
• /
• 2018

The resistivity monitoring is a practical method to resolve changes in resistivity of underground structures over time. With the advance of sophisticated automatic data acquisition system and rapid data communication technology, resistivity monitoring has been widely applied to understand spatio-temporal changes of subsurface. In this study, a new 4D inversion algorithm is developed, which can effectively emphasize significant changes of underground resistivity with time. To overcome the overly smoothing problem in 4D inversion, the Lagrangian multipliers in the space-domain and time-domain are determined automatically so that the proportion of the model constraints to the misfit roughness remains constant throughout entire inversion process. Furthermore, a focusing model constraint is added to emphasize significant spatio-temporal changes. The performance of the developed algorithm is demonstrated by the numerical experiments using the synthetic data set for a time-lapse model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.1142-1146
• /
• 2009

A rainfall simulation and forecasting technique that can generate daily rainfall sequences conditional on multi-model ensemble GCMs is developed and applied to data in Korea for the major rainy season. The GCM forecasts are provided by APEC climate center. A Weather State Based Downscaling Model (WSDM) is used to map teleconnections from ocean-atmosphere data or key state variables from numerical integrations of Ocean-Atmosphere General Circulation Models to simulate daily sequences at multiple rain gauges. The method presented is general and is applied to the wet season which is JJA(June-July-August) data in Korea. The sequences of weather states identified by the EM algorithm are shown to correspond to dominant synoptic-scale features of rainfall generating mechanisms. Application of the methodology to seasonal rainfall forecasts using empirical teleconnections and GCM derived climate forecast are discussed.