• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.367-373
• /
• 2022

As deep learning-based autonomous driving technology develops, artificial intelligence models for various purposes have been studied. Based on these studies, several models were used simultaneously to develop autonomous driving systems. It can occur by increasing hardware resource consumption. We propose a multi-tasks model using a shared backbone to solve this problem. This can solve the increase in the number of backbones for using AI models. As a result, in the proposed lightweight model, the model parameters could be reduced by more than 50% compared to the existing model, and the speed could be improved. In addition, each lane can be classified through lane detection using the instance segmentation method. However, further research is needed on the decrease in accuracy compared to the existing model.

• Plant Journal
• /
• v.18 no.1
• /
• pp.55-61
• /
• 2022

In this study, I analyzed the effect of slagging caused by blending bituminous coal and subbituminous coal while maintaining the generator output, combustion conditions, and ventilation conditions for 870MW thermal power plant designed with bituminous coal. Accordingly I proposed an acceptable method of blending coal method. the blending ratio of sub-bituminous coal was adjusted to 10%, 20%, 40%, 60%, 80%, etc. to confirm ultimate analysis, proximate analysis, ash fusion temperature change, slagging indices, etc. Proper blending coal conditions are blending with sub-bituminous coal at 40% or less, ratio of base component to acid component(B/A) is 0.4 or less or 1 or more, total alkali(TA) is 3.5 or less, fusion slagging index(Rfs) is 1,345℃ or more, and ash content is 13% or less in ultimate analysis, the ash content in proximate analysis is 15% or less, and the initial deformation temperature(IDT) should be at least 1,200℃ or more

• Journal of Appropriate Technology
• /
• v.6 no.2
• /
• pp.146-150
• /
• 2020

Assistive technologies for people with disabilities are often marginalized in the Fourth Industrial Revolution. In this paper, we intend to present the possibility of acquiring tactile information through the tactile display adapting an electromagnetic actuator. The multi-layered display designed for tactile communication has innovatively narrowed the size and spacing of cells in order to express pictures, maps, and graphics. This display has enabled the visually impaired to touch two-dimensional information combining with other assistive technologies so that. It would also provide a technical source of access to STEM education (Science, Technology, Engineering, and Mathematics) so that students will perform better and be better prepared for advanced education. Moreover, it can be applied to public infrastructure and transportation in smart-city projects on the globe. Hence, this paper introduces the principle of Electromagnetic-actuator and how it can be utilized in many diverse areas.

• Journal of the Korean Society of Radiology
• /
• v.16 no.7
• /
• pp.825-833
• /
• 2022

In 3D printing technology, materials that can be printed are increasing along with the development of material engineering, and materials that can be used in the field of radiation are also increasing. Therefore, depending on the composition and density of the materials used, the applied field can be different and applied, so the composition and characteristics of the materials must also be considered. In this study, 10 filaments with different properties were selected using a 3D printer of the FDM (Fused Deposition Modeling) method, and the brightness change of each filament was checked using a diagnostic X-ray generator, and the CT number was measured through CT. I wanted to find a material similar to bone. As a result, a material called silicon carbide was found, which has a similar brightness and CT number to bone. It is thought that further research will be presented as basic data for various studies with a density similar to that of human bones.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1846-1852
• /
• 2021

In modern society, various digital devices are being distributed in a wide range of fields due to the fourth industrial revolution and the development of IoT technology. However, noise is generated in the process of acquiring or transmitting an image, and not only damages the information, but also affects the system, causing errors and incorrect operation. AWGN is a representative noise among image noise. As a method for removing noise, prior research has been conducted, and among them, AF, A-TMF, and MF are the representative methods. Existing filters have a disadvantage that smoothing occurs in areas with high frequency components because it is difficult to consider the characteristics of images. Therefore, the proposed algorithm calculates the standard deviation distribution to effectively eliminate noise even in the high frequency domain, and then calculates the final output by applying the probability density function weight of the Laplace distribution using the curve fitting method.

• Current Photovoltaic Research
• /
• v.11 no.2
• /
• pp.49-53
• /
• 2023

Expanding the supply of BIPV is crucial to strengthening the competitiveness of the photovoltaic industry and achieving Nationally Determined Contributions through the zero-energy building mandatory policy. BIPV is a technology that integrates into the building envelope to generate electricity and provide functions as a building material. It is suitable for domestic environments with many high-rise buildings due to the narrow land area and urbanization. To expand the supply of BIPV, economics, safety, and aesthetics must be ensured. In this study, a color BIPV module with a color PET film applied as a front material was manufactured for aesthetic and economic feasibility. The relationship between power output and transmittance according to color was analyzed. By analyzing the power output of the module and the transmittance of the film, the wavelength band (transmittance reduction band) that has the greatest effect on efficiency was analyzed regarding the color of the film. The red film showed the narrowest transmittance reduction band and the lowest degree of decrease in transmittance, making it ideal for minimizing the efficiency decrease rate compared to existing ones.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.91-102
• /
• 2022

As artificial intelligence develops, AI chatbot systems are actively taking place. For example, in public institutions, the use of chatbots is expanding to work assistance and professional knowledge services in civil complaints and administration, and private companies are using chatbots for interactive customer response services. In this study, we propose a scenario-based AI voice chatbot system to reduce museum operating costs and provide interactive guidance services to visitors. The implemented voice chatbot system consists of a watcher object that detects the user's voice by monitoring a specific directory in real-time, and an event handler object that outputs AI's response voice by performing inference by model sequentially when a voice file is created. And Including a function to prevent duplication using thread and a deque, GPU operations are not duplicated during inference in a single GPU environment.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.573-580
• /
• 2006

The Saturation headway is a major parameter in estimating the intersection capacity and setting the signal timing. But Existing algorithms are still far from being robust in dealing with factors related to the variation of saturation headways at signalized intersections. So this study apply the fuzzy inference system using ANFIS. The ANFIS provides a method for the fuzzy modeling procedure to learn information about a data set, in order to compute the membership function parameters that best allow the associated fuzzy inference system to track the given input/output data. The climate conditions and the degree of brightness were chosen as the input variables when the rate of heavy vehicles is 10-25 %. These factors have the uncertain nature in quantification, which is the reason why these are chosen as the fuzzy variables. A neuro-fuzzy inference model to estimate saturation headways at signalized intersections was constructed in this study. Evaluating the model using the statistics of $R^2$, MAE and MSE, it was shown that the explainability of the model was very high, the values of the statistics being 0.993, 0.0289, 0.0173 respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.253-255
• /
• 2022

Thanks to the 4th industrial revolution and the development of various communication media, technologies such as artificial intelligence and automation are being grafted into industrial sites in various fields, and accordingly, the importance of data processing is increasing. Image noise removal is a pre-processing process for image processing, and is mainly used in fields requiring high-level image processing technology. Various studies have been conducted to remove noise, but various problems arise in the process of noise removal, such as image detail preservation, texture restoration, and noise removal in a special area. In this paper, we propose a switching mask filter based on the noise intensity to preserve the detailed image information during the impulse noise removal process. The proposed filter algorithm obtains the final output by switching to the extended mask when it is determined that the density is higher than the reference value when noise is determined in the area designated as the filtering mask. Simulation was conducted to evaluate the performance of the proposed algorithm, and the performance was analyzed compared to the existing method.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.450-455
• /
• 2023

Among single-phase photovoltaic inverters that can avoid excessive leakage current caused by the large parasitic capacitance of photovoltaic panels, a boost converter followed by a half-bridge inverter is the simplest and has the smallest leakage current. However, due to the high DC-link voltage, the rated voltage of the switching devices is high and the switching loss is large. This paper proposes a new circuit topology which can operate as a buck-boost inverter by adding two bidirectional switches to the output side of the half-bridge inverter instead of removing the boost converter. By reducing two stages of power conversion through the high-voltage DC-link to one stage, power loss can be reduced without increasing costs and leakage current. The feasibility of the proposed circuit topology is verified by computer simulation and power loss calculation.