• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1794-1806
• /
• 2023

This study presents a method for capturing photographs of users as input and converting them into 2D character animation sprites using a generative adversarial network-based artificial intelligence network. Traditionally, 2D character animations have been created by manually creating an entire sequence of sprite images, which incurs high development costs. To address this issue, this study proposes a technique that combines motion videos and sample 2D images. In the 2D sprite generation process that uses the proposed technique, a sequence of images is extracted from real-life images captured by the user, and these are combined with character images from within the game. Our research aims to leverage cutting-edge deep learning-based image manipulation techniques, such as the GAN-based motion transfer network (impersonator) and background noise removal (U² -Net), to generate a sequence of animation sprites from a single image. The proposed technique enables the creation of diverse animations and motions just one image. By utilizing these advancements, we focus on enhancing productivity in the game and animation industry through improved efficiency and streamlined production processes. By employing state-of-the-art techniques, our research enables the generation of 2D sprite images with various motions, offering significant potential for boosting productivity and creativity in the industry.

• Structural Engineering and Mechanics
• /
• v.84 no.3
• /
• pp.323-335
• /
• 2022

The main idea of the framework is to seamlessly combine a reasonably accurate and fast surrogate model with the importance sampling strategy. Developing a surrogate model for predicting structures' dynamic responses is challenging because it involves high-dimensional inputs and outputs. For this purpose, a novel surrogate model based on cutting-edge deep learning architectures specialized for capturing temporal relationships within time-series data, namely Long-Short term memory layer and Transformer layer, is designed. After being properly trained, the surrogate model could be utilized in place of the finite element method to evaluate structures' responses without requiring any specialized software. On the other hand, the importance sampling is adopted to reduce the number of calculations required when computing the failure probability by drawing more relevant samples near critical areas. Thanks to the portability of the trained surrogate model, one can integrate the latter with the Importance sampling in a straightforward fashion, forming an efficient framework called TTIS, which represents double advantages: less number of calculations is needed, and the computational time of each calculation is significantly reduced. The proposed approach's applicability and efficiency are demonstrated through three examples with increasing complexity, involving a 1D beam, a 2D frame, and a 3D building structure. The results show that compared to the conventional Monte Carlo simulation, the proposed method can provide highly similar reliability results with a reduction of up to four orders of magnitudes in time complexity.

• Ocean Systems Engineering
• /
• v.12 no.3
• /
• pp.359-384
• /
• 2022

We develop in this work a new well-balanced preserving-positivity path-conservative central-upwind scheme for Saint-Venant-Exner (SVE) model. The SVE system (SVEs) under some considerations, is a nonconservative hyperbolic system of nonlinear partial differential equations. This model is widely used in coastal engineering to simulate the interaction of fluid flow with sediment beds. It is well known that SVEs requires a robust treatment of nonconservative terms. Some efficient numerical schemes have been proposed to overcome the difficulties related to these terms. However, the main drawbacks of these schemes are what follows: (i) Lack of robustness, (ii) Generation of non-physical diffusions, (iii) Presence of instabilities within numerical solutions. This collection of drawbacks weakens the efficiency of most numerical methods proposed in the literature. To overcome these drawbacks a reformulation of the central-upwind scheme for SVEs (CU-SVEs for short) in a path-conservative version is presented in this work. We first develop a finite-volume method of the first order and then extend it to the second order via the averaging essentially non oscillatory (AENO) framework. Our numerical approach is shown to be well-balanced positivity-preserving and shock-capturing. The resulting scheme could be seen as a predictor-corrector method. The accuracy and robustness of the proposed scheme are assessed through a carefully selected suite of tests.

• Journal of Practical Engineering Education
• /
• v.16 no.2
• /
• pp.115-119
• /
• 2024

With the increase in the number of ICT industry workers, there is a demand for research on preventing VDT syndrome. However, existing posture correction products mostly rely heavily on cameras or sensors in wearable devices. In this paper, we have developed a posture correction system that utilizes built-in cameras and circular pressure sensors to collect posture information. Additionally, the system provides a personalized service by capturing the correct posture of the user initially and monitoring the user's posture based on that input. By precisely correcting postures during users' daily tasks, this system aims to prevent and improve VDT syndrome, ultimately enhancing the efficiency of ICT industry workers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.233-262
• /
• 2024

Due to the rapid evolution of vehicular ad hoc networks (VANETs), effective communication and security are now essential components in providing secure and reliable vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. However, due to their dynamic nature and potential threats, VANETs need to have strong security mechanisms. This paper presents a novel approach to improve VANET security by combining the Vehicular Delay-Tolerant Network (VDTN) protocol with the Deep Reinforcement Learning (DRL) technique known as the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. A store-carry-forward method is used by the VDTN protocol to resolve the problems caused by inconsistent connectivity and disturbances in VANETs. The TD3 algorithm is employed for capturing and detecting Worm Hole Attack (WHA) behaviors in VANETs, thereby enhancing security measures. By combining these components, it is possible to create trustworthy and effective communication channels as well as successfully detect and stop rushing attacks inside the VANET. Extensive evaluations and simulations demonstrate the effectiveness of the proposed approach, enhancing both security and communication efficiency.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1223-1237
• /
• 2024

Autonomous vehicles use onboard sensors to sense the surrounding environment. In complex autonomous driving scenarios, the detection and recognition capabilities are constrained, which may result in serious accidents. An efficient way to enhance the detection and recognition capabilities is establishing collaborations with the neighbor vehicles. However, the collaborations introduce additional challenges in terms of the data heterogeneity, communication cost, and data privacy. In this paper, a novel personalized federated learning framework is proposed for addressing the challenges and enabling efficient collaborations in autonomous driving environment. For obtaining a global model, vehicles perform local training and transmit logits to a central unit instead of the entire model, and thus the communication cost is minimized, and the data privacy is protected. Then, the inference similarity is derived for capturing the characteristics of data heterogeneity. The vehicles are divided into clusters based on the inference similarity and a weighted aggregation is performed within a cluster. Finally, the vehicles download the corresponding aggregated global model and train a personalized model which is personalized for the cluster that has similar data distribution, so that accuracy is not affected by heterogeneous data. Experimental results demonstrate significant advantages of our proposed method in improving the efficiency of collaborative perception and reducing communication cost.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.24 no.5
• /
• pp.454-460
• /
• 2012

The purpose of the present work is to investigate the removal characteristics of positively charged filters for capturing negatively charged particles such as bacteria and virus in water. In order to reduce the pressure drop and increase the filtration efficiency, the filter media, modified by charge modifier having positive functional groups, is developed and evaluated. Improved liquid filters have been developed with the modified surface charge to capture and adsorb particles by electrokinetic interaction between the filter surface and particles contained in an aqueous liquid. The positively charged filter media is composed of glass fiber, cellulose and poly-ethylenimine resin for positively charging with the variation of volume ratio. The zeta potential value of the positively charged filter is +37.92 mV at the glass fiber and cellulose content ratio of 50 : 50 with resin content of 100%, while that of the PSL test particle is -23.5 mV at pH 7. The removal efficiency of the electro-positively charged filter is 98% for PSL particles of 0.11 ${\mu}m$, while that of the negatively charged filter is 7%. The positively charged filter media showed the potential to be an effective method for removing fine particles from the contaminated water for liquid filtration.

• Journal of Ocean Engineering and Technology
• /
• v.23 no.5
• /
• pp.25-31
• /
• 2009

The most important component of wind turbine is rotor blades. The developing method of wind turbine was focused on design of rotor blade. By the way, the design of a rotating body is more decisive process in order to adjust the performance of wind turbine. For instance, the design allows the designer to specify the wind characteristics derived by topographical map. The iterative solver is then used to adjust one of the selected inputs so that the desired rotating performance which is directly related to power generating capacity and efficiency is achieved. Furthermore, in order to save the money for manufacturing the rotor blades and to decrease the maintenance fee of wind power generation plant, while decelerating the cut-in speed of rotor. Therefore, the design and manufacturing of rotating body is understood as a substantial technology of wind power generation plant development. The aiming of this study is building-up the profitable approach to designing of rotating body as a system for the wind power generation plant. The process was conducted in two steps. Firstly, general designing and it’s serial testing of rotating body for voltage measurement. Secondly, the serial test results above were examined with the CFD code. Then, the analysis is made on the basis of amount of electricity generated by rotor-blades and of cut-in speed of generator.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.21 no.3
• /
• pp.459-464
• /
• 2012

The point of impact, the shot group, and the flight traces depend on the combination of unique features which decide moving traces of the arrow (paradox of the archer, length of the arrow shaft, weight, angle of the feather, and spline of the arrow shaft). The more dense the impact points in the shot group and the earlier elimination of paradox of the archer, the higher assessment is given for the product. However, there is no way to objectively assess the efficiency and quality of the arrow, and there is no numeric data to be used as the basis for comparison with other products. Although capturing the images of flying arrow using a high-speed motion picture camera is possible, we are limited to observation from specific view angle only. Hence, the criteria for efficiency and quality assessment are mostly based on subjective opinions of experts or hunters, or review on consumers' remarks. In this paper, we propose a hardware composition that are based on three detection frames consisting of line lasers and photo diode arrays without the high-speed motion picture camera. Predicated on measured coordinates data, a nobel method for the archer's paradox measurement, a key parameter that determine the arrow's trajectory, and corresponding numerical analysis model is proposed.

• Journal of Advanced Navigation Technology
• /
• v.28 no.4
• /
• pp.472-479
• /
• 2024

Half of the world's total population lives in cities, continuous urbanization is progressing, and the urban population is expected to exceed two-thirds of the total population by 2050. To resolve this phenomenon, the Korean government is focusing on building a new urban air mobility (UAM) industrial ecosystem. Airlines are also part of the UAM industry ecosystem and are preparing to improve efficiency in safe operations, passenger safety, aircraft operation efficiency, and punctuality. This study performs demand forecasting using time series data on the number of daily passengers on Korean Air's Gimpo to Jeju route from 2019 to 2023. For this purpose, statistical and machine learning models such as SARIMA, Prophet, CatBoost, and Random Forest are applied. Methods for effectively capturing passenger demand patterns were evaluated through various models, and the machine learning-based Random Forest model showed the best prediction results. The research results will present an optimal model for accurate demand forecasting in the aviation industry and provide basic information needed for operational planning and resource allocation.