• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.2
• /
• pp.67-72
• /
• 2022

Ecological research relies on the interpretation of large amounts of visual data obtained from extensive wildlife surveys, but such large-scale image interpretation is costly and time-consuming. Using an artificial intelligence (AI) machine learning model, especially convolution neural networks (CNN), it is possible to streamline these manual tasks on image information and to protect wildlife and record and predict behavior. Ecological research using deep-learning-based object recognition technology includes various research purposes such as identifying, detecting, and identifying species of wild animals, and identification of the location of poachers in real-time. These advances in the application of AI technology can enable efficient management of endangered wildlife, animal detection in various environments, and real-time analysis of image information collected by unmanned aerial vehicles. Furthermore, the need for school education and social use on biodiversity and environmental issues using AI is raised. School education and citizen science related to ecological activities using AI technology can enhance environmental awareness, and strengthen more knowledge and problem-solving skills in science and research processes. Under these prospects, in this paper, we compare the results of our early 2013 study, which automatically identified African cichlid fish species using photographic data of them, with the results of reanalysis by CNN deep learning method. By using PyTorch and PyTorch Lightning frameworks, we achieve an accuracy of 82.54% and an F1-score of 0.77 with minimal programming and data preprocessing effort. This is a significant improvement over the previous our machine learning methods, which required heavy feature engineering costs and had 78% accuracy.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.154-162
• /
• 2022

Digital marketing tools are actively used in managing the development of park and recreation complexes to familiarize the population with the objects of natural heritage. This article aims to empirically evaluate digital marketing tools for popularizing the park and recreational complexes. The methodology was based on the concept of ecosystem value of park and recreation complexes as a natural heritage site. These methods included: identifying and selecting websites with information about park and recreation complexes in Slovakia and Ukraine. structural analysis of the main channels of online details about natural parks. Assessing the current state of online identity of the studied sites from the perspective of Internet users. The results indicate that to manage the development of park and recreational complexes developed their driven official websites in the Internet space, on which sections structure the information with the allocation of data on tourism and recreational potential. The article identifies additional digital marketing tools for managing the development of park and recreation complexes, particularly social networks and tourist websites. There is a sufficient amount of information about tourist recreation sites within these natural parks and tourist routes. Among the main problems of the websites: the information on the websites is entirely textual, there is a lack of sufficient data on social networks, despite the created official pages, there is no video content, which was more attracted tourists and visitors, allowing a visual assessment of the tourist potential; there is a problem of many communication channels to present the natural heritage of the countries. The research proves that the website is the primary and most common digital marketing tool for natural heritage, structuring information about tourism potential and recreation.

• Nuclear Engineering and Technology
• /
• v.54 no.5
• /
• pp.1825-1834
• /
• 2022

Performing high-fidelity computational fluid dynamics (HF-CFD) to predict the flow and heat transfer state of the coolant in the reactor core is expensive, especially in scenarios that require extensive parameter search, such as uncertainty analysis and design optimization. This work investigated the performance of utilizing a multi-fidelity reduced-order model (MF-ROM) in PWR rod bundles simulation. Firstly, basis vectors and basis vector coefficients of high-fidelity and low-fidelity CFD results are extracted separately by the proper orthogonal decomposition (POD) approach. Secondly, a surrogate model is trained to map the relationship between the extracted coefficients from different fidelity results. In the prediction stage, the coefficients of the low-fidelity data under the new operating conditions are extracted by using the obtained POD basis vectors. Then, the trained surrogate model uses the low-fidelity coefficients to regress the high-fidelity coefficients. The predicted high-fidelity data is reconstructed from the product of extracted basis vectors and the regression coefficients. The effectiveness of the MF-ROM is evaluated on a flow and heat transfer problem in PWR fuel rod bundles. Two data-driven algorithms, the Kriging and artificial neural network (ANN), are trained as surrogate models for the MF-ROM to reconstruct the complex flow and heat transfer field downstream of the mixing vanes. The results show good agreements between the data reconstructed with the trained MF-ROM and the high-fidelity CFD simulation result, while the former only requires to taken the computational burden of low-fidelity simulation. The results also show that the performance of the ANN model is slightly better than the Kriging model when using a high number of POD basis vectors for regression. Moreover, the result presented in this paper demonstrates the suitability of the proposed MF-ROM for high-fidelity fixed value initialization to accelerate complex simulation.

• Korean Journal of Materials Research
• /
• v.32 no.4
• /
• pp.216-222
• /
• 2022

The capacity of high nickel Li(Ni_xCo_yMn_1-x-y)O₂ (NCM, x ≥ 0.8) cathodes is known to rapidly decline, a serious problem that needs to be solved in a timely manner. It was reported that cathode materials with the {010} plane exposed toward the outside, i.e., a radial structure, can provide facile Li⁺ diffusion paths and stress buffer during repeated cycles. In addition, cathodes with a core-shell composition gradient are of great interest. For example, a stable surface structure can be achieved using relatively low nickel content on the surface. In this study, precursors of the high-nickel NCM were synthesized by coprecipitation in ambient atmosphere. Then, a transition metal solution for coprecipitation was replaced with a low nickel content and the coprecipitation reaction proceeded for the desired time. The electrochemical analysis of the core-shell cathode showed a capacity retention of 94 % after 100 cycles, compared to the initial discharge capacity of 184.74 mA h/g. The rate capability test also confirmed that the core-shell cathode had enhanced kinetics during charging and discharging at 1 A/g.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.4
• /
• pp.1392-1413
• /
• 2022

In order to meet the rapid development of the unmanned aerial vehicle (UAV) communication needs, cooperative spectrum sensing (CSS) helps to identify unused spectrum for the primary users (PU). However, multi-UAV mode (MUM) requires the large communication resource in a cognitive UAV network, resulting in a severe decline of spectrum efficiency (SE) and energy efficiency (EE) and increase of energy consumption (EC). On this account, we extend the traditional 2D spectrum space to 3D spectrum space for the UAV network scenario and enable UAVs to proceed with spectrum sensing behaviors in this paper, and propose a novel multi-slot mode (MSM), in which the sensing slot is divided into multiple mini-slots within a UAV. Then, the CSS process is developed into a composite hypothesis testing problem. Furthermore, to improve SE and EE and reduce EC, we use the sequential detection to make a global decision about the PU channel status. Based on this, we also consider a truncation scenario of the sequential detection under the sensing delay constraint, and further derive a closed-form performance expression, in terms of the CSS performance and cooperative efficiency. At last, the simulation results verify that the performance and cooperative efficiency of MSM outperforms that of the traditional MUM in a low EC.

• Journal of the Korean Society of Safety
• /
• v.37 no.1
• /
• pp.70-77
• /
• 2022

The total number of Korean restaurants using delivery applications has substantially increased from 7.6% in 2018 to 11.2% in 2019. In 2020, the gross sales in the food delivery service market reached approximately 17 trillion won; this amount is virtually six times that in 2017 (i.e., 2 trillion won). Meanwhile, the annual average death toll of motorcycle riders increased by 3.5%, whereas the number of deaths due to other traffic accidents decreased by 8.2%. Consequently, the foregoing has become a critical social problem. Despite the continuing increase in the number of delivery riders due to the rapid expansion of the delivery industry, no appropriate safety management system has been established. Moreover, the government is experiencing difficulties in assessing the exact situation because of the absence of competent authority. In this study, fundamental data on the characteristics of delivery work and motorcycle accidents were collected through surveys and interviews; then, the influencing factors of traffic accidents were analyzed. Different influencing factors were identified: work experience as a rider; number of deliveries; whether to accept delivery requests in transit; manner of accepting delivery requests; and traffic law violations, such as speeding (for faster delivery) and running a red light. Because the motorcycle delivery industry has a relatively low job-entry barrier (i.e., special qualifications are not required), the riding skills of riders must be improved, and delivery companies must be technically developed to achieve a safe working environment. The results of this study can be utilized as fundamental data for system development or structural improvement of the delivery industry.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.1-10
• /
• 2021

The ability to recognize human emotions by computer vision is a very important task, with many potential applications. Therefore the demand for emotion recognition using not only RGB images but also thermal images is increasing. Compared to RGB images, thermal images has the advantage of being less affected by lighting conditions but require a more sophisticated recognition method with low-resolution sources. In this paper, we propose a Divide and Conquer-based CNN training strategy to improve the performance of facial thermal image-based emotion recognition. The proposed method first trains to classify difficult-to-classify similar emotion classes into the same class group by confusion matrix analysis and then divides and solves the problem so that the emotion group classified into the same class group is recognized again as actual emotions. In experiments, the proposed method has improved accuracy in all the tests than when recognizing all the presented emotions with a single CNN model.

• Smart Structures and Systems
• /
• v.29 no.2
• /
• pp.267-278
• /
• 2022

Pre-stressed concrete circular spun piles are widely used in various infrastructure projects around the world and offer an economical deep foundation system with consistent and superior quality compared to cast in-situ and other concrete piles. Conventional methods for measuring the lateral response of piles have been limited to conventional instrumentation, such as electrical based gauges and pressure transducers. The problem with existing technology is that the sensors are not able to assist in recording the lateral stiffness changes of the pile which varies along the length depending on the distribution of the flexural moments and appearance of tensile cracks. This paper describes a full-scale bending test of a 1-m diameter spun pile of 30 m long and instrumented using advanced fibre optic distributed sensor, known as Brillouin Optical Time Domain Analysis (BOTDA). Optical fibre sensors were embedded inside the concrete during the manufacturing stage and attached on the concrete surface in order to measure the pile's full-length flexural behaviour under the prescribed serviceability and ultimate limit state. The relationship between moments-deflections and bending moments-curvatures are examined with respect to the lateral forces. Tensile cracks were measured and compared with the peak strains observed from BOTDA data which corroborated very well. By analysing the moment-curvature response of the pile, the structure can be represented by two bending stiffness parameters, namely the pre-yield (EI) and post-yield (EI_cr), where the cracks reduce the stiffness property by 89%. The pile deflection profile can be attained from optical fibre data through closed-form solutions, which generally matched with the displacements recorded by Linear Voltage Displacement Transducers (LVDTs).

• Geomechanics and Engineering
• /
• v.28 no.6
• /
• pp.599-611
• /
• 2022

Tendon reinforced cemented soil is applied extensively in foundation stabilisation and improvement, especially in areas with soft clay. To solve the deterioration problem led by steel corrosion, the glass fiber-reinforced polymer (GFRP) tendon is introduced to substitute the traditional steel tendon. The interface bond strength between the cemented soil matrix and GFRP tendon demonstrates the outstanding mechanical property of this composite. However, the lack of research between the influence factors and bond strength hinders the application. To evaluate these factors, back propagation neural network (BPNN) is applied to predict the relationship between them and bond strength. Since adjusting BPNN parameters is time-consuming and laborious, the particle swarm optimisation (PSO) algorithm is proposed. This study evaluated the influence of water content, cement content, curing time, and slip distance on the bond performance of GFRP tendon-reinforced cemented soils (GTRCS). The results showed that the ultimate and residual bond strengths were both in positive proportion to cement content and negative to water content. The sample cured for 28 days with 30% water content and 50% cement content had the largest ultimate strength (3879.40 kPa). The PSO-BPNN model was tuned with 3 neurons in the input layer, 10 in the hidden layer, and 1 in the output layer. It showed outstanding performance on a large database comprising 405 testing results. Its higher correlation coefficient (0.908) and lower root-mean-square error (239.11 kPa) were obtained compared to multiple linear regression (MLR) and logistic regression (LR). In addition, a sensitivity analysis was applied to acquire the ranking of the input variables. The results illustrated that the cement content performed the strongest influence on bond strength, followed by the water content and slip displacement.

• KNOM Review
• /
• v.24 no.1
• /
• pp.20-28
• /
• 2021

Extensive use of social media applications and mobile devices continues to increase data traffic. Social media applications generate an endless and massive amount of multimedia traffic, specifically video traffic. Many social media platforms such as YouTube, Daily Motion, and Netflix generate endless video traffic. On these platforms, only a few popular videos are requested many times as compared to other videos. These popular videos should be cached in the user vicinity to meet continuous user demands. MEC has emerged as an essential paradigm for handling consistent user demand and caching videos in user proximity. The problem is to understand how user demand pattern varies with time. This paper analyzes three publicly available datasets, MovieLens 20M, MovieLens 100K, and The Movies Dataset, to find the user request pattern over time. We find hourly, daily, monthly, and yearly trends of all the datasets. Our resulted pattern could be used in other research while generating and analyzing the user request pattern in MEC-based video caching scenarios.