• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.556-570
• /
• 2021

The existing video expression recognition methods mainly focus on the spatial feature extraction of video expression images, but tend to ignore the dynamic features of video sequences. To solve this problem, a multi-mode convolution neural network method is proposed to effectively improve the performance of facial expression recognition in video. Firstly, OpenFace 2.0 is used to detect face images in video, and two deep convolution neural networks are used to extract spatiotemporal expression features. Furthermore, spatial convolution neural network is used to extract the spatial information features of each static expression image, and the dynamic information feature is extracted from the optical flow information of multiple expression images based on temporal convolution neural network. Then, the spatiotemporal features learned by the two deep convolution neural networks are fused by multiplication. Finally, the fused features are input into support vector machine to realize the facial expression classification. Experimental results show that the recognition accuracy of the proposed method can reach 64.57% and 60.89%, respectively on RML and Baum-ls datasets. It is better than that of other contrast methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.12
• /
• pp.4568-4587
• /
• 2014

Authentication of videos and images based on the content is becoming an important problem in information security. Unfortunately, previous studies lack the consideration of Kerckhoffs's principle in order to achieve this (i.e., a cryptosystem should be secure even if everything about the system, except the key, is public knowledge). In this paper, a solution to the problem of finding a relationship between a frame's index and its content is proposed based on the creative utilization of a robust manifold feature. The proposed solution is based on a novel semi-fragile watermarking scheme for H.264/AVC video content authentication. At first, the input I-frame is partitioned for feature extraction and watermark embedding. This is followed by the temporal feature extraction using the Isometric Mapping algorithm. The frame index is included in the feature to produce the temporal watermark. In order to improve security, the spatial watermark will be encrypted together with the temporal watermark. Finally, the resultant watermark is embedded into the Discrete Cosine Transform coefficients in the diagonal positions. At the receiver side, after watermark extraction and decryption, temporal tampering is detected through a mismatch between the frame index extracted from the temporal watermark and the observed frame index. Next, the feature is regenerate through temporal feature regeneration, and compared with the extracted feature. It is judged through the comparison whether the extracted temporal watermark is similar to that of the original watermarked video. Additionally, for spatial authentication, the tampered areas are located via the comparison between extracted and regenerated spatial features. Experimental results show that the proposed method is sensitive to intentional malicious attacks and modifications, whereas it is robust to legitimate manipulations, such as certain level of lossy compression, channel noise, Gaussian filtering and brightness adjustment. Through a comparison between the extracted frame index and the current frame index, the temporal tempering is identified. With the proposed scheme, a solution to the Kerckhoffs's principle problem is specified.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.6
• /
• pp.381-387
• /
• 2010

Both timbral features and spatial features are important in the assessment of multichannel audio coding systems. The prediction model, extending the ITU-R Rec. BS. 1387-1 to multichannel audio coding systems, with the use of spatial features such as ITDDist (Interaural Time Difference Distortion), ILDDist (Interaural Level Difference Distortion), and IACCDist (InterAural Cross-correlation Coefficient Distortion) was proposed by Choi et al. In that model, ITDDistswere only computed for low frequency bands (below 1500Hz), and ILDDists were computed only for high frequency bands (over 2500Hz) according to classical duplex theory. However, in the high frequency range, information in temporal envelope is also important in spatial perception, especially in sound localization. A new model to compute the ITD distortions of temporal envelopes in high frequency components is introduced in this paper to investigate the role of such ITD on spatial perception quantitatively. The computed ITD distortions of temporal envelopes in high frequency components were highly correlated with perceived sound quality of multichannel audio sounds.

• Journal of Korea Water Resources Association
• /
• v.38 no.1
• /
• pp.73-82
• /
• 2005

A soil moisture measuring method of a hillslope for Korean watershed is developed to configure spatial-temporal distribution of soil moisture. Intensive surveying of topography had been performed to make a digital elevation model(DEM). Flow distribution algorithms were applied and a distribution pattern of the measurement sensors was determined to maximize representative features of spatial variation of soil moisture. Inverse surveying provides appropriate information to install the waveguides in the field. Measurements were performed at the right side hillslope of Bumrunsa located at the Sulmachun watershed. A multiplex monitoring system has been established and spatial-temporal variation of soil moisture data has been measured for a rainfall-runoff event. Acquired soil moisture data show that physical hydrologic interpretations as well as the effectiveness of monitoring system. Lack of connectivity in vertical distribution of soil moisture suggests that preferential flow and macropore flux are important components in the hillslope hydrology.

• Korean System Dynamics Review
• /
• v.16 no.2
• /
• pp.75-100
• /
• 2015

The purpose of this study is to analyze causation of Ecosystem service's trade-off(ES trade-off) and to establish baseline data for wise spatial planning and management. In order to understand why and how ES trade-off occurs, systems thinking and causal loops were employed. The causal loop of ecosystem service creation cycle includes profits quantification process, decision making process, spatial planning and management process, and ecosystem services creation process. The profits quantification process has a limitation that all ecosystem service categories were not included in profits quantification, because quantification method for cultural services is insufficient. These problems led to unequal discussion opportunity in decision making process. ES trade-off occurs through transition of ecosystem function in spatial scale and temporal scale. In spatial scale, land-use variation and resource-use variation contribute to change an ecosystem function for different ES category by spatial planning and management. In temporal scale, a change of an ecosystem function for different ES category is influenced by ecological succession, seasonal change and land cover variation, which are parameter from environmental features. This study presented that spatial planning and management should ecosystem service assessment in order to enhance balanced ecosystem services.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.86-93
• /
• 2024

The development of functional magnetic resonance imaging (fMRI) has significantly contributed to mapping brain functions and understanding brain networks during rest. This paper proposes a CNN-LSTM-based classification model to classify the progression stages of Alzheimer's disease. Firstly, four preprocessing steps are performed to remove noise from the fMRI data before feature extraction. Secondly, the U-Net architecture is utilized to extract spatial features once preprocessing is completed. Thirdly, the extracted spatial features undergo LSTM processing to extract temporal features, ultimately leading to classification. Experiments were conducted by adjusting the temporal dimension of the data. Using 5-fold cross-validation, an average accuracy of 96.4% was achieved, indicating that the proposed method has high potential for identifying the progression of Alzheimer's disease by analyzing fMRI data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2754-2768
• /
• 2013

Video fingerprints generated from global features are usually vulnerable against general geometric transformations. In this paper, a novel video fingerprinting algorithm is proposed, in which a new spatio-temporal gradient is designed to represent the spatial and temporal information for each frame, and a new partition scheme, based on concentric circle and rings, is developed to resist the attacks efficiently. The centroids of spatio-temporal gradient orientations (CSTGO) within the circle and rings are then calculated to generate a robust fingerprint. Our experiments with different attacks have demonstrated that the proposed approach outperforms the state-of-the-art methods in terms of robustness and discrimination.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.4
• /
• pp.1181-1190
• /
• 2006

Statistical analyses for spatial data are important features for various types of fields. Spatial data are taken at specific locations or within specific regions and their relative positions are recorded. Lattice data are synoptic observation covering an entire spatial region, like cancer rates corresponding to each county in a state. Until now, the echelon analysis has been applied only to univariate spatial data. As a result, it is impossible to detect the hotspots on the multivariate spatial data In this paper, we expand the spatial data to time series structure. And then we analyze them on the time space and detect the hotspots. Echelon dendrogram has been made by piling up each multivariate spatial data to bring time spatial data. We perform the structural analysis of temporal spatial data.

• Journal of Environmental Science International
• /
• v.21 no.2
• /
• pp.189-202
• /
• 2012

Power spectral analysis for $PM_{10}$ observed at 10 cities in the Korean Peninsula from 2004 to 2010 was carried out to examine the spatial and temporal features of $PM_{10}$ evolution cycle. The power spectrum analysis proposed 9 typical cycles (0.5 day, 1day, 5.4day, 8~10day, 19~21day, 26day, 56day, 180day and 365day) for $PM_{10}$ evolution and the cycles are strongly associated with dilution and transportation due to the meterological influence. The spectrum intensity of 5.4day and 26day $PM_{10}$ evolution cycles mainly depend on the advection cycles of synoptic pressures system and long-term variation of climatological forcing, respectively. The intensity of $PM_{10}$ evolution with longer temporal cycles than one day tends to be stronger in La ni$\tilde{n}$a period in comparison with that in El ni$\tilde{n}$o period. Mean of typical intensity of $PM_{10}$ evolution in La ni$\tilde{n}$a period estimated to be 30% larger than El ni$\tilde{n}$o period. Thus the global scale meteorological phenomena such as El ni$\tilde{n}$o and La ni$\tilde{n}$a also can influence the variation of wind system in the Korean Peninsula and $PM_{10}$ evolution. but global scale forcing tends to influence different manner for $PM_{10}$ evolution in accordance with its temporal cycles.

• Journal of Internet Computing and Services
• /
• v.8 no.2
• /
• pp.1-13
• /
• 2007

GPS/GIS and RFID technologies have been changing the paradigm af our society toward ubiquitous era. Especially, geographically distributed mobile agents with transporting objects need to be automatically recognizable and traceable under certain conditions. To do this, fundamental theories and technologies are required to specify and verify spatial and temporal behaviors of agents on geographical space. This paper presents a new formal method, called Calculus of Real-Time Distribution, Mobility, and Interaction (CaRDMI), for this purpose. For specification, CaRDMI defines a map, mobile agents with transporting objects. The movement of on agent is represented by a path on the map, consisting of a list of nodes and a list of edges with spatial and temporal constraints. Interactive constraints among agents are represented by synchronization modes on objects at nodes. These constraints are distinguishable features of CaRDMI from other methods. Especially, many-to-many timed synchronization constraints are noticeable. For verification, CaRDMI presents the spatial, temporal and interactive deduction rules and the spatial and temporal equivalence relations.