• Journal of Korean Society on Water Environment
• /
• v.36 no.6
• /
• pp.611-620
• /
• 2020

Although process-based models have been a preferred approach for modeling freshwater aquatic systems over extended time intervals, the increasing utility of data-driven models in a big data environment has made the data-driven models increasingly popular in recent decades. In this study, international peer-reviewed journals for the relevant fields were searched in the Web of Science Core Collection, and an extensive literature review, which included total 2,984 articles published during the last two decades (2000-2020), was performed. The review results indicated that the rate of increase in the number of published studies using data-driven models exceeded those using process-based models since 2010. The increase in the use of data-driven models was partly attributable to the increasing availability of data from new data sources, e.g., remotely sensed hyperspectral or multispectral data. Consistently throughout the past two decades, South Korea has been one of the top ten countries in which the greatest number of studies using the data-driven models were published. Among the major data-driven approaches, i.e., artificial neural network, decision tree, and Bayesian model, were illustrated with case studies. Based on the review, this study aimed to inform the current state of knowledge regarding the biogeochemical water quality and ecological models using data-driven approaches, and provide the remaining challenges and future prospects.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.28 no.4
• /
• pp.133-142
• /
• 2023

In this paper, we built a data-driven artificial intelligence model using RNN-LSTM (Recurrent Neural Networks-Long Short-Term Memory) to predict the Lorenz system, and examined the possibility of whether this model can replace chaotic dynamic models. We confirmed that the data-driven model reflects the chaotic nature of the Lorenz system, where a small error in the initial conditions produces fundamentally different results, and the system moves around two stable poles, repeating the transition process, the characteristic of "deterministic non-periodic flow", and simulates the bifurcation phenomenon. We also demonstrated the advantage of adjusting integration time intervals to reduce computational resources in data-driven models. Thus, we anticipate expanding the applicability of data-driven artificial intelligence models through future research on refining data-driven models and data assimilation techniques for data-driven models.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.810-818
• /
• 2010

This paper presents a new framework for integrating untranscribed spoken content into the acoustic training of an automatic speech recognition system. Untranscribed spoken content plays a very important role for under-resourced languages because the production of manually transcribed speech databases still represents a very expensive and time-consuming task. We proposed two new methods as part of the training framework. The first method focuses on combining initial acoustic models using a data-driven metric. The second method proposes an improved acoustic training procedure based on unsupervised transcriptions, in which word endings were modified by broad phonetic classes. The training framework was applied to baseline acoustic models using untranscribed spoken content from parliamentary debates. We include three types of acoustic models in the evaluation: baseline, reference content, and framework content models. The best overall result of 18.02% word error rate was achieved with the third type. This result demonstrates statistically significant improvement over the baseline and reference acoustic models.

• Smart Structures and Systems
• /
• v.30 no.1
• /
• pp.35-47
• /
• 2022

Data-driven engineering is crucial for information delivery between design, fabrication, assembly, and maintenance of prefabricated structures. Design for manufacturing and assembly (DfMA) is a critical methodology for prefabricated bridge structures. In this study, a novel concept of digital engineering model that combined existing knowledge of DfMA with object-oriented parametric modeling technologies was developed. Three-dimensional (3D) geometry models and their data models for each phase of a construction project were defined for information delivery. Digital design models were used for conceptual design, including aesthetic consideration and possible variation during fabrication and assembly. The seismic performance of a bridge pier was evaluated by linking the design parameters to the calculated moment-curvature curves. Control parameters were selected to consider the tolerance control and revision of the digital models. Digitalized fabrication of the prefabricated members was realized using the digital fabrication model with G-code for a concrete printer or a robot. The fabrication error was evaluated and the design digital models were updated. The revised fabrication models were used in the preassembly simulation to guarantee constructability. For the maintenance of the bridge, the as-built information was defined for the prefabricated bridge piers. The results of this process revealed that data-driven information delivery is crucial for lifecycle management of prefabricated bridge piers.

• Electronics and Telecommunications Trends
• /
• v.36 no.5
• /
• pp.82-91
• /
• 2021

This study reviews application of data-driven anomaly detection techniques to the aviation domain. Recent advances in deep learning have inspired significant anomaly detection research, and numerous methods have been proposed. However, some of these advances have not yet been explored in aviation systems. After briefly introducing aviation safety issues, data-driven anomaly detection models are introduced. Along with traditional statistical and well-established machine learning models, the state-of-the-art deep learning models for anomaly detection are reviewed. In particular, the pros and cons of hybrid techniques that incorporate an existing model and a deep model are reviewed. The characteristics and applications of deep learning models are described, and the possibility of applying deep learning methods in the aviation field is discussed.

• Clinical and Experimental Pediatrics
• /
• v.65 no.5
• /
• pp.239-249
• /
• 2022

Cells survive and proliferate through complex interactions among diverse molecules across multiomics layers. Conventional experimental approaches for identifying these interactions have built a firm foundation for molecular biology, but their scalability is gradually becoming inadequate compared to the rapid accumulation of multiomics data measured by high-throughput technologies. Therefore, the need for data-driven computational modeling of interactions within cells has been highlighted in recent years. The complexity of multiomics interactions is primarily due to their nonlinearity. That is, their accurate modeling requires intricate conditional dependencies, synergies, or antagonisms between considered genes or proteins, which retard experimental validations. Artificial intelligence (AI) technologies, including deep learning models, are optimal choices for handling complex nonlinear relationships between features that are scalable and produce large amounts of data. Thus, they have great potential for modeling multiomics interactions. Although there exist many AI-driven models for computational biology applications, relatively few explicitly incorporate the prior knowledge within model architectures or training procedures. Such guidance of models by domain knowledge will greatly reduce the amount of data needed to train models and constrain their vast expressive powers to focus on the biologically relevant space. Therefore, it can enhance a model's interpretability, reduce spurious interactions, and prove its validity and utility. Thus, to facilitate further development of knowledge-guided AI technologies for the modeling of multiomics interactions, here we review representative bioinformatics applications of deep learning models for multiomics interactions developed to date by categorizing them by guidance mode.

• Journal of KIBIM
• /
• v.9 no.4
• /
• pp.41-50
• /
• 2019

Digital models for a cable-stayed bridge are defined considering data-driven engineering from design to construction. Algorithms for digital object generation of each component of the cable-stayed bridge were developed. Using these algorithms, Level-3 BIM practices can be realized from design stages. Based on previous practices, digital object library can be accumulated. Basic digital models are modified according to given design conditions by a designer. Once design models are planned, various applications using the models are linked the models such as estimation, drawings and mechanical properties. Federated bridge models are delivered to construction stages. In construction stage, the models can be efficiently revised according to the changed situations during construction phases. In this paper, measured coordinates are imported to the model generation algorithms and revised models are obtained. Augmented reality devices and their applications are proposed. AR simulations in construction site and in office condition are tested. From this pilot test of digital models, it can be said that Level-3 BIM practices can be realized by using in-house modeling algorithms according to different purposes.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.35 no.2
• /
• pp.45-52
• /
• 2019

BEMS(Building Energy Management Systems) have been applied to office buildings and collect relevant building energy data, e.g. temperatures, mass flow rates and energy consumptions of building mechanical systems and indoor spaces. The aforementioned measured data can be beneficially utilized for developing data-driven machine learning models which can be then used as part of MPC(Model Predictive Control) and/or optimal control strategies. In this study, the authors developed ANN(Artificial Neural Network) models of an AHU (Air Handling Unit) and a chiller for a real-life office building using BEMS data. Based on the ANN models, the authors developed optimal control strategies, e.g. daily operation schedule with regard to optimal start and stop of the AHU and the chiller (500 RT). It was found that due to the optimal start and stop of the AHU and the chiller, 4.5% and 16.4% of operation hours of the AHU and the chiller could be saved, compared to an existing operation.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.496-500
• /
• 2015

International construction projects are inherently more risky than domestic projects with multi-dimensional uncertainties that require complementary risk management at both the country and project levels. However, despite a growing need for systematic country evaluations, most studies have focused on project-level decisions and lack country-based approaches for firms in the construction industry. Accordingly, this study suggests data-driven approaches for evaluating countries using two quantitative models. The first is a two-stage country segmentation model that not only screens negative countries based on country attractiveness (macro-segmentation) but also identifies promising countries based on the level of past project performance in a given country (micro-segmentation). The second is a multi-criteria country segmentation model that combines a firm's business objective with the country evaluation process based on Kraljic's matrix and fuzzy preference relations (FPR). These models utilize not only secondary data from internationally reputable institutions but also performance data on Korean firms from 1990 to 2014 to evaluate 29 countries. The proposed approaches enable firms to enhance their decision-making capacity for evaluating and selecting countries at the early stage of corporate strategy development.

• Journal of Biomedical Engineering Research
• /
• v.35 no.5
• /
• pp.142-150
• /
• 2014

The key to model-based iterative reconstruction (MBIR) algorithms for transmission computed tomography lies in the ability to accurately model the data formation process from the emitted photons produced in the transmission source to the measured photons at the detector. Therefore, accurately modeling the system matrix that accounts for the data formation process is a prerequisite for MBIR-based algorithms. In this work we compared quantitative performance of the three representative ray-driven methods for calculating the system matrix; the ray-tracing method (RTM), the distance-driven method (DDM), and the strip-area based method (SAM). We implemented the ordered-subsets separable surrogates (OS-SPS) algorithm using the three different models and performed simulation studies using a digital phantom. Our experimental results show that, in spite of the more advanced features in the SAM and DDM, the traditional RTM implemented in the OS-SPS algorithm with an edge-preserving regularizer out-performs the SAM and DDM in restoring complex edges in the underlying object. The performance of the RTM in smooth regions was also comparable to that of the SAM or DDM.