• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2787-2800
• /
• 2022

The aging society increases emergency situations of the elderly living alone and a variety of social crimes. In order to prevent them, techniques to detect emergency situations through voice are actively researched. This study proposes CutPaste-based anomaly detection model using multi-scale feature extraction in time series streaming data. In the proposed method, an audio file is converted into a spectrogram. In this way, it is possible to use an algorithm for image data, such as CNN. After that, mutli-scale feature extraction is applied. Three images drawn from Adaptive Pooling layer that has different-sized kernels are merged. In consideration of various types of anomaly, including point anomaly, contextual anomaly, and collective anomaly, the limitations of a conventional anomaly model are improved. Finally, CutPaste-based anomaly detection is conducted. Since the model is trained through self-supervised learning, it is possible to detect a diversity of emergency situations as anomaly without labeling. Therefore, the proposed model overcomes the limitations of a conventional model that classifies only labelled emergency situations. Also, the proposed model is evaluated to have better performance than a conventional anomaly detection model.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.1-8
• /
• 2023

In this paper, we propose a black ice detection platform framework using Convolutional Neural Networks (CNNs). To overcome black ice problem, we introduce a real-time based early warning platform using CNN-based architecture, and furthermore, in order to enhance the accuracy of black ice detection, we apply a multi-scale dilation convolution feature fusion (MsDC-FF) technique. Then, we establish a specialized experimental platform by using a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Experimental results of a real-time black ice detection platform show the better performance of our proposed network model compared to conventional image segmentation models. Our proposed platform have achieved real-time segmentation of road black ice areas by deploying a road black ice area segmentation network on the edge device Jetson Nano devices. This approach in parallel using multi-scale dilated convolutions with different dilation rates had faster segmentation speeds due to its smaller model parameters. The proposed MsCD-FF Net(2) model had the fastest segmentation speed at 5.53 frame per second (FPS). Thereby encouraging safe driving for motorists and providing decision support for road surface management in the road traffic monitoring department.

• Journal of Electrical Engineering and Technology
• /
• v.5 no.1
• /
• pp.16-20
• /
• 2010

Recently, the smart grid has become a hot issue and interest in related power sources have increased accordingly. The implementation of a smart grid can enable many generation resources to be linked to the power system, including small-scale reactors for the purpose of co-generation. Research on small-scale reactors is being carried out all over the world. Similarly, Korea is also conducting research on multi-purpose regional energy systems using nuclear energy. This paper proposes a real-time data acquisition and analysis system for small-scale reactors, and is known as the REX-10 (Regional Energy rX 10 MVA). This analysis requires real-time simulations for the power system since it needs data communication with a remote REX-10. A RTDS (Real Time Digital Simulator) has been used for the simulation, and a SCADA/HMI system interfaced with the RTDS is proposed for the purpose of monitoring and control of the regional energy system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.690-693
• /
• 2004

This paper proposes a multi-resolution electrostatic potential field (MREPF) based solution to the mobile robot path planning and collision avoidance problem in 2D dynamic environment. The MREPF is an environment method in calculation time and updating field map. The large scale resolution map is added to EPF and this resolution map interacts with the small scale resolution map to find an optimal solution in real time. This approach can be interpreted with Atlantis model. The simulation studies show the efficiency of the proposed algorithm.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.27 no.12
• /
• pp.767-775
• /
• 2014

New material design has obtained tremendous attention in material science community as the performance of new materials, especially in nano length scale, could be greatly improved to applied in modern industry. In certain conditions limiting experimental synthesis of these new materials, new approach by computer simulation has been proposed to be applied, being able to save time and cost. Recent development of computer systems with high speed, large memory, and parallel algorithms enables to analyze individual atoms using first principle calculation to predict quantum phenomena. Beyond the quantum level calculations, mesoscopic scale and continuum limit can be addressed either individually or together as a multi-scale approach. In this article, we introduced current endeavors on material design using analytical theory and computer simulations in multi-length scales and on multi-physical properties. Some of the physical phenomena was shown to be interconnected via a cross-link rule called 'cross-property relation'. It is suggested that the computer simulation approach by multi-physics analysis can be efficiently applied to design new materials for multi-functional characteristics.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.13 no.1
• /
• pp.17-26
• /
• 2007

Recently, the importance of the living environment for elderly people and its network is increasing. At the same time, the small-scale and multi-functional apartment house in which they can live is continuously required in Japan. For these reasons, it is appearing a new type of housing, Group-Living, where one lives together with others. It represents a way of communal living which is based on service at home. There are various problems such as felicity of each space, connections between the different areas, insufficiency of positioning on the aged welfare. Hence this research targets are grasp the present condition of Group-Living, to inquire the Space composition and types of it in Tokyo Area, and to suggest the direction of improvement of the small-scale and multi-functional apartment house for the aged.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.2
• /
• pp.91-95
• /
• 2011

In this paper, we present an improved multi-scale gradient algorithm. The proposed algorithm works the effectively handling of both step and blurred edges. In the proposed algorithm, the image sharpening operator is sharpening the edges and contours of the objects. This operation gives an opportunity to get noise reduced image and step edged image. After that, multi-scale gradient operator works on noise reduced image in order to get a gradient image. The gradient image is segmented by watershed transform. The approach of region merging is used after watershed transform. The region merging is carried out according to the region area and region homogeneity. The region number of the proposed algorithm is 36% shorter than that of the existing algorithm because the proposed algorithm produces a few irrelevant regions. Moreover, the computational time of the proposed algorithm is relatively fast in comparison with the existing one.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03a
• /
• pp.355-358
• /
• 2008

In order to investigate the physical mechanism of the energy cascade in homogeneous isotropic turbulence, we introduce Galilean-invariant energy and its transfer rate in the real space as a function of position, time and scale. By using a database of direct numerical simulations (DNS) of homogeneous isotropic turbulence, it is shown that (i) fully developed turbulence consists of multi-scale coherent vortices of tubular shapes, (ii) the energy at each scale is mainly confined in vortex tubes with the radii of the same order of the length scale, and (iii) the energy transfer takes place around pairs (especially, anti-parallel pairs) of such vortex tubes. Based on these observations, it is suggested that the energy cascade can be caused, in the real space, by the process of the stretching and creation of smaller (i.e. thinner) vortex tubes by the straining field around pairs of larger (i.e. fatter) vortex tubes. Indeed, it is quite easy to find such events (in our DNS fields) which strongly support this scenario of the energy cascade.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.10a
• /
• pp.355-358
• /
• 2008

In order to investigate the physical mechanism of the energy cascade in homogeneous isotropic turbulence, we introduce Galilean-invariant energy and its transfer rate in the real space as a function of position, time and scale. By using a database of direct numerical simulations (DNS) of homogeneous isotropic turbulence, it is shown that (i) fully developed turbulence consists of multi-scale coherent vortices of tubular shapes, (ii) the energy at each scale is mainly confined in vortex tubes with the radii of the same order of the length scale, and (iii) the energy transfer takes place around pairs (especially, anti-parallel pairs) of such vortex tubes. Based on these observations, it is suggested that the energy cascade can be caused, in the real space, by the process of the stretching and creation of smaller (i.e. thinner) vortex tubes by the straining field around pairs of larger (i.e. fatter) vortex tubes. Indeed, it is quite easy to find such events (in our DNS fields) which strongly support this scenario of the energy cascade.