• Steel and Composite Structures
• /
• v.46 no.2
• /
• pp.153-173
• /
• 2023

Rectangular concrete-filled steel tubular (RCFST) column, a type of concrete-filled steel tubular (CFST), is widely used in compression members of structures because of its advantages. This paper proposes a robust machine learning-based framework for predicting the ultimate compressive strength of RCFST columns under both concentric and eccentric loading. The gradient boosting neural network (GBNN), an efficient and up-to-date ML algorithm, is utilized for developing a predictive model in the proposed framework. A total of 890 experimental data of RCFST columns, which is categorized into two datasets of concentric and eccentric compression, is carefully collected to serve as training and testing purposes. The accuracy of the proposed model is demonstrated by comparing its performance with seven state-of-the-art machine learning methods including decision tree (DT), random forest (RF), support vector machines (SVM), deep learning (DL), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and categorical gradient boosting (CatBoost). Four available design codes, including the European (EC4), American concrete institute (ACI), American institute of steel construction (AISC), and Australian/New Zealand (AS/NZS) are refereed in another comparison. The results demonstrate that the proposed GBNN method is a robust and powerful approach to obtain the ultimate strength of RCFST columns.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.57-58
• /
• 2022

Concrete mix design is used as essential data for the quality of concrete, analysis of structures, and stable use of sustainable structures. However, since most of the formulation design is established based on the experience of experts, there is a lack of data to base it on. are suffering Accordingly, in this study, the purpose of this study is to build a predictive model to use the concrete mixing factor as basic data for calculation using the DNN technique. As for the data set for DNN model learning, OPC and ternary concrete data were collected according to the presence or absence of admixture, respectively, and the model was separated for OPC and ternary concrete, and training was carried out. In addition, by varying the number of hidden layers of the DNN model, the prediction performance was evaluated according to the model structure. The higher the number of hidden layers in the model, the higher the predictive performance for the prediction of the mixing elements except for the compressive strength factor set as the output value, and the ternary concrete model showed higher performance than the OPC. This is expected because the data set used when training the model also affected the training.

• Journal of Software Assessment and Valuation
• /
• v.15 no.2
• /
• pp.67-72
• /
• 2019

The recent explosion of data traffic, including cloud services, coupled with the Internet penetration has led to a surge in the need for ultra-fast optical networks that can efficiently connect the data center's reconfiguable resources. In this paper, the algorithms for controlling switching cell operation in the optical switch connection structure are proposed, and the resulting performance is compared and analyzed through simulation. Performance analysis results showed that the algorithm proposed in this paper has improved the probability of successful multi-connection setup by about 3 to 7% compared to the existing algorithm.

• Journal of Microbiology and Biotechnology
• /
• v.33 no.9
• /
• pp.1141-1148
• /
• 2023

Herein, we explored the potential of the apple's core microbiota for biological control of Erwinia amylovora, which causes fire blight disease, and analyzed the structure of the apple's bacterial community across different tissues and seasons. Network analysis results showed distinct differences in bacterial community composition between the endosphere and rhizosphere of healthy apples, and eight taxa were identified as negatively correlated with E. amylovora, indicating their potential key role in a new control strategy against the pathogen. This study highlights the critical role of the apple's bacterial community in disease control and provides a new direction for future research in apple production. In addition, the findings suggest that using the composition of the apple's core taxa as a biological control strategy could be an effective alternative to traditional chemical control methods, which have been proven futile and environmentally harmful.

• Journal of Powder Materials
• /
• v.30 no.6
• /
• pp.502-508
• /
• 2023

With the increasing demand for electronic products, the amount of multilayer ceramic capacitor (MLCC) waste has also increased. Recycling technology has recently gained attention because it can simultaneously address raw material supply and waste disposal issues. However, research on recovering valuable metals from MLCCs and converting the recovered metals into high-value-added materials remains insufficient. Herein, we describe an electrospinning (E-spinning) process to recover nickel from MLCCs and modulate the morphology of the recovered nickel oxide particles. The nickel oxalate powder was recovered using organic acid leaching and precipitation. Nickel oxide nanoparticles were prepared via heat treatment and ultrasonic milling. A mixture of nickel oxide particles and polyvinylpyrrolidone (PVP) was used as the E-spinning solution. A PVP/NiO nanowire composite was fabricated via E-spinning, and a nickel oxide nanowire with a network structure was manufactured through calcination. The nanowire diameters and morphologies are discussed based on the nickel oxide content in the E-spinning solution.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.217-223
• /
• 2023

In this paper, we propose a new model for the conditional generation of music, considering key and rhythm, fundamental elements of music. MIDI sheet music is converted into a WAV format, which is then transformed into a Mel Spectrogram using the Short-Time Fourier Transform (STFT). Using this information, key and rhythm details are classified by passing through two Convolutional Neural Networks (CNNs), and this information is again fed into the Music Transformer. The key and rhythm details are combined by differentially multiplying the weights and the embedding vectors of the MIDI events. Several experiments are conducted, including a process for determining the optimal weights. This research represents a new effort to integrate essential elements into music generation and explains the detailed structure and operating principles of the model, verifying its effects and potentials through experiments. In this study, the accuracy for rhythm classification reached 94.7%, the accuracy for key classification reached 92.1%, and the Negative Likelihood based on the weights of the embedding vector resulted in 3.01.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.6_3
• /
• pp.1183-1195
• /
• 2023

In this study, we collected and analyzed domestic and international studies related to watersheds in the forest sector. Keyword co-occurrence analysis was conducted using the VOSviewer program to identify the research areas of domestic and international studies and the network structure to compare research trends. As a result, the number of research articles in international watershed-related studies showed an overall increasing trend, and the research areas were diverse and located close to each other, indicating that many convergence studies were conducted. On the other hand, the number of papers in domestic watershed-related studies seems to have stagnated overall from the past to the present, and the research areas are mainly focused on forest disasters and hydrology, with limited interdisciplinary convergence studies. In addition, in both domestic and international studies, watersheds are currently mentioned as research sites rather than management or analysis units in the forest sector. It is important to actively promote interdisciplinary research in Korea to provide a scientific and balanced basis for watershed-level forest management planning.

• Steel and Composite Structures
• /
• v.49 no.6
• /
• pp.633-643
• /
• 2023

In this study, the natural frequencies of Functional Graded Materials (FGM) plates are predicted using Artificial Neural Network (ANN). A model based on Third-order Shear Deformation Theory (TSDT) and FEM is used to train the ANN model. Different training methods are tested to simulate input and output dependency. As this is a parametric model, several architectures and optimization algorithms were tested. The proposed model allows us to minimize the CPU time to evaluate candidate material properties for FGM plate material selection and demonstrate their influence on dynamic behavior. Consequently, the time required for the FGM design process (candidate materials for material selection) and the geometric optimization of the FGM structure would remain reasonable. The ANN model can help industries to produce FGM plates with good mechanical properties of the selected materials. I addition, this model can be used to directly predict vibration behavior by testing a large number of FGM plates, representing all possible combinations of metals and ceramics in today's industry, without having to solve any eigenvalue problems.

• Computers and Concrete
• /
• v.33 no.3
• /
• pp.285-299
• /
• 2024

Recently, many engineering computations have realized their digital transformation to Machine Learning (ML)-based systems. Predicting the behavior of a structure, which is mainly computed with structural analysis software, is an essential step before construction for efficient structural analysis. Especially in the seismic-based design procedure of the structures, predicting the lateral load capacity of reinforced concrete (RC) columns is a vital factor. In this study, a novel ML-based model is proposed to predict the maximum lateral load capacity of RC columns under varying axial loads or cyclic loadings. The proposed model is generated with a Deep Neural Network (DNN) and compared with traditional ML techniques as well as a popular commercial structural analysis software. In the design and test phases of the proposed model, 319 columns with rectangular and square cross-sections are incorporated. In this study, 33 parameters are used to predict the maximum lateral load capacity of each RC column. While some traditional ML techniques perform better prediction than the compared commercial software, the proposed DNN model provides the best prediction results within the analysis. The experimental results reveal the fact that the performance of the proposed DNN model can definitely be used for other engineering purposes as well.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.4
• /
• pp.347-357
• /
• 2024

Oxide semiconductor gas sensors are widely used for detecting toxic, explosive, and flammable gases due to their simple structure, cost-effectiveness, and potential integration into compact devices. However, their reliable gas detection is hindered by a longstanding issue known as humidity dependence, wherein the sensor resistance and gas response change significantly in the presence of moisture. This problem has persisted since the inception of oxide semiconductor gas sensors in the 1960s. This paper explores the root causes of humidity dependence in oxide semiconductor gas sensors and presents strategies to address this challenge. Mitigation strategies include functionalizing the gas-sensing material with noble metal/transition metal oxides and rare-earth/rare-earth oxides, as well as implementing a moisture barrier layer to prevent moisture diffusion into the gas-sensing film. Developing oxide semiconductor gas sensors immune to humidity dependence is expected to yield substantial socioeconomic benefits by enabling medical diagnosis, food quality assessment, environmental monitoring, and sensor network establishment.