• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2468-2487
• /
• 2015

In web searching, trustable and precise results are greatly affected by the inherent uncertainty in the input queries. Queries submitted to search engines are by nature ambiguous and constitute a significant proportion of the instances given to web search engines. Ambiguous queries pose real challenges for the web search engines due to versatility of information. Temporal based approaches whereas somehow reduce the uncertainty in queries but still lack to provide results according to users aspirations. Web search science has created an interest for the researchers to incorporate contextual information for resolving the uncertainty in search results. In this paper, we propose an Adaptive Disambiguation Approach (ADA) of hybrid nature that makes use of both the temporal and contextual information to improve user experience. The proposed hybrid approach presents the search results to the users based on their location and temporal information. A Java based prototype of the systems is developed and evaluated using standard dataset to determine its efficacy in terms of precision, accuracy, recall, and F1-measure. Supported by experimental results, ADA demonstrates better results along all the axes as compared to temporal based approaches.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.3
• /
• pp.122-128
• /
• 2013

This paper presents a detection algorithm that accurately finds the active area of a video player on monitors or smart TVs. Unlike the previous approaches, temporal difference-based detection algorithms or hooking programs, the proposed detection algorithm can locate the active video player by using the spatial and temporal correlation and a corner detection filter. First, an initial location of the video player is found using conventional temporal difference-based detection. Then, starting from the initial location, the four corners of the active video player are detected by the spatial edge information and the corner detection filter. The experimental results show that proposed algorithm provides fast detection speed and high accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4026-4040
• /
• 2019

In this paper, we present an approach for detecting slide transitions in lecture videos by introducing the spatio-temporal residual networks. Given a lecture video which records the digital slides, the speaker, and the audience by multiple cameras, our goal is to find keyframes where slide content changes. Since temporal dependency among video frames is important for detecting slide changes, 3D Convolutional Networks has been regarded as an efficient approach to learn the spatio-temporal features in videos. However, 3D ConvNet will cost much training time and need lots of memory. Hence, we utilize ResNet to ease the training of network, which is easy to optimize. Consequently, we present a novel ConvNet architecture based on 3D ConvNet and ResNet for slide transition detection in lecture videos. Experimental results show that the proposed novel ConvNet architecture achieves the better accuracy than other slide progression detection approaches.

• Advances in Computational Design
• /
• v.8 no.3
• /
• pp.219-236
• /
• 2023

In this paper, finite element modeling of the laser ultrasonics (LU) process in ablation regime is of interest. The momentum resulting from the removal of material from the specimen surface by the laser beam radiation in ablation regime is modeled as a pressure pulse. To model this pressure pulse, two equations are required: one for the spatial distribution and one for the temporal distribution of the pulse. Previous researchers have proposed various equations for the spatial and temporal distributions of the pressure pulse in different laser applications. All available equations are examined and the best combination of the temporal and spatial distributions of the pressure pulse that provides the most accurate results is identified. This combination of temporal and spatial distributions has never been used for modeling laser ultrasonics before. Then by using this new model, the effects of variations in pulse duration and laser spot radius on the shape, amplitude, and frequency spectrum of ultrasonic waves are studied. Furthermore, the LU in thermoelastic regime is simulated by this model and compared with LU in ablation regime. The interaction of ultrasonic waves with a defect is also investigated in the LU process in ablation regime. Good agreement of the results obtained from the new finite element model and available experimental data confirms the accuracy of the proposed model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2361-2376
• /
• 2023

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macro-averaged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.553-563
• /
• 2006

This study aims to produce land-cover maps of Korean peninsula using multi-temporal MODIS (Moderate Resolution Imaging Spectroradiometer) imagery. To solve the low spatial resolution of MODIS data and enhance classification accuracy, Linear Spectral Mixture Analysis (LSMA) was employed. LSMA allowed to determine the fraction of each surface type in a pixel and develop vegetation, soil and water fraction images. To eliminate clouds, MVC (Maximum Value Composite) was utilized for vegetation fraction and MinVC (Minimum Value Composite) for soil fraction image respectively. With these images, using ISODATA unsupervised classifier, southern part of Korean peninsula was classified to low and mid level land-cover classes. The results showed that vegetation and soil fraction images reflected phenological characteristics of Korean peninsula. Paddy fields and forest could be easily detected in spring and summer data of the entire peninsula and arable land in North Korea. Secondly, in low level land-cover classification, overall accuracy was 79.94% and Kappa value was 0.70. Classification accuracy of forest (88.12%) and paddy field (85.45%) was higher than that of barren land (60.71%) and grassland (57.14%). In midlevel classification, forest class was sub-divided into deciduous and conifers and field class was sub-divided into paddy and field classes. In mid level, overall accuracy was 82.02% and Kappa value was 0.6986. Classification accuracy of deciduous (86.96%) and paddy (85.38%) were higher than that of conifers (62.50%) and field (77.08%).

• Korean Journal of Remote Sensing
• /
• v.29 no.5
• /
• pp.569-579
• /
• 2013

In this study, land-cover classification was implemented using features extracted from multi-temporal SAR data through 3D wavelet transform and the applicability of the 3D wavelet transform as a feature extraction approach was evaluated. The feature extraction stage based on 3D wavelet transform was first carried out before the classification and the extracted features were used as input for land-cover classification. For a comparison purpose, original image data without the feature extraction stage and Principal Component Analysis (PCA) based features were also classified. Multi-temporal Radarsat-1 data acquired at Dangjin, Korea was used for this experiment and five land-cover classes including paddy fields, dry fields, forest, water, and built up areas were considered for classification. According to the discrimination capability analysis, the characteristics of dry field and forest were similar, so it was very difficult to distinguish these two classes. When using wavelet-based features, classification accuracy was generally improved except built-up class. Especially the improvement of accuracy for dry field and forest classes was achieved. This improvement may be attributed to the wavelet transform procedure decomposing multi-temporal data not only temporally but also spatially. This experiment result shows that 3D wavelet transform would be an effective tool for feature extraction from multi-temporal data although this procedure should be tested to other sensors or other areas through extensive experiments.

• Journal of Korea Water Resources Association
• /
• v.54 no.11
• /
• pp.933-942
• /
• 2021

The surface image velocimetry was developed to measure river flow velocity safely and effectively in flood season. There are a couple of methods in the surface image velocimetry. Among them the spatio-temporal image velocimetry is in the spotlight, since it can estimate mean velocity for a period of time. For the spatio-temporal image velocimetry analyzes a series of images all at once, it can reduce analyzing time so much. It, however, has a little drawback to find out the main flow direction. If the direction of spatio-temporal image does not coincide to the main flow direction, it may cause singnificant error in velocity. The present study aims to propose a new method to find out the main flow direction by using a fast Fourier transform(FFT) to a spatio-temporal (image) volume, which were constructed by accumulating the river surface images along the time direction. The method consists of two steps; the first step for finding main flow direction in space image and the second step for calculating the velocity magnitude in main flow direction in spatio-temporal image. In the first step a time-accumulated image was made from the spatio-temporal volume along the time direction. We analyzed this time-accumulated image by using FFT and figured out the main flow direction from the transformed image. Then a spatio-temporal image in main flow direction was extracted from the spatio-temporal volume. Once again, the spatio-temporal image was analyzed by FFT and velocity magnitudes were calculated from the transformed image. The proposed method was applied to a series of artificial images for error analysis. It was shown that the proposed method could analyze two-dimensional flow field with fairly good accuracy.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.3
• /
• pp.182-190
• /
• 2021

Computational simulations of turbulent flows around a model ship have been performed to investigate an influence of TVD schemes on the accuracy of advective terms associated with ship resistances. Several TVD schemes including upwind, second-order upwind, vanLeer, and QUICK as well as a nonTVD linear scheme were studied by examining temporal and spatial characteristics of accuracy transition in adjacent cells to the hull. Even though vanLeer scheme was the most accurate among TVD schemes in both structured and unstructured grid systems, the ratio of accuracy switch from 2^nd order to 1^st order in vanLeer scheme was considerable compared with the 2^nd order linear scheme. Also, the accuracy transition was observed to be overally scattered in the unstructured grid while the accuracy transition in the structured grid appeared relatively clustered. It concluded that TVD schemes had to be carefully used in computational simulations of turbulent flows around a model ship due to the loss of accuracy despite its attraction of numerical stability.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.258-258
• /
• 2018

In this study, a hydraulic flow model and an error correction model are combined to improve the flood simulation accuracy. First, the hydraulic flow model is calibrated by optimizing the Manning's roughness coefficient that considers spatial and temporal variability. Then, an error correction model were used to correct the systematic errors of the calibrated hydraulic model. The error correction model is developed using Artificial Neural Networks (ANNs) that can estimate the systematic simulation errors of the hydraulic model by considering some state variables as inputs. The input variables are selected using parital mutual information (PMI) technique. It was found that the calibrated hydraulic model can simulate flood water levels with good accuracy. Then, the accuracy of estimated flood levels is improved further by using the error correction model. The method proposed in this study can be used to the flood control and water resources management as it can provide accurate water level eatimation.