• ETRI Journal
• /
• v.46 no.1
• /
• pp.82-95
• /
• 2024

As automated essay scoring (AES) has progressed from handcrafted techniques to deep learning, holistic scoring capabilities have merged. However, specific trait assessment remains a challenge because of the limited depth of earlier methods in modeling dual assessments for holistic and multi-trait tasks. To overcome this challenge, we explore providing comprehensive feedback while modeling the interconnections between holistic and trait representations. We introduce the DualBERT-Trans-CNN model, which combines transformer-based representations with a novel dual-scale bidirectional encoder representations from transformers (BERT) encoding approach at the document-level. By explicitly leveraging multi-trait representations in a multi-task learning (MTL) framework, our DualBERT-Trans-CNN emphasizes the interrelation between holistic and trait-based score predictions, aiming for improved accuracy. For validation, we conducted extensive tests on the ASAP++ and TOEFL11 datasets. Against models of the same MTL setting, ours showed a 2.0% increase in its holistic score. Additionally, compared with single-task learning (STL) models, ours demonstrated a 3.6% enhancement in average multi-trait performance on the ASAP++ dataset.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.4
• /
• pp.101-107
• /
• 2010

The aim of this paper is to come up with a methodology of constructing an efficient model for multiple representations which can manage and reconcile real-time data about large-scale roads in Vector Domain. In other words, we suggested framework based on a bottom-up approach, which is allowed to integrate data from the network of the lowest level sequentially and perform automated matching in order to produce variable-scale map. Finally, we applied designed multi-LoD model to in-vehicle application.

• Steel and Composite Structures
• /
• v.4 no.6
• /
• pp.471-487
• /
• 2004

Modular steel scaffolds are commonly used as supporting scaffolds in building construction, and traditionally, the load carrying capacities of these scaffolds are obtained from limited full-scale tests with little rational design. Structural failure of these scaffolds occurs from time to time due to inadequate design, poor installation and over-loads on sites. In general, multi-storey modular steel scaffolds are very slender structures which exhibit significant non-linear behaviour. Hence, secondary moments due to both $P-{\delta}$ and $P-{\Delta}$ effects should be properly accounted for in the non-linear analyses. Moreover, while the structural behaviour of these scaffolds is known to be very sensitive to the types and the magnitudes of restraints provided from attached members and supports, yet it is always difficult to quantify these restraints in either test or practical conditions. The problem is further complicated due to the presence of initial geometrical imperfections in the scaffolds, including both member out-of-straightness and storey out-of-plumbness, and hence, initial geometrical imperfections should be carefully incorporated. This paper presents an extensive numerical study on three different approaches in analyzing and designing multi-storey modular steel scaffolds, namely, a) Eigenmode Imperfection Approach, b) Notional Load Approach, and c) Critical Load Approach. It should be noted that the three approaches adopt different ways to allow for the non-linear behaviour of the scaffolds in the presence of initial geometrical imperfections. Moreover, their suitability and accuracy in predicting the structural behaviour of modular steel scaffolds are discussed and compared thoroughly. The study aims to develop a simplified and yet reliable design approach for safe prediction on the load carrying capacities of multi-storey modular steel scaffolds, so that engineers can ensure safe and effective use of these scaffolds in building construction.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.690-693
• /
• 2004

This paper proposes a multi-resolution electrostatic potential field (MREPF) based solution to the mobile robot path planning and collision avoidance problem in 2D dynamic environment. The MREPF is an environment method in calculation time and updating field map. The large scale resolution map is added to EPF and this resolution map interacts with the small scale resolution map to find an optimal solution in real time. This approach can be interpreted with Atlantis model. The simulation studies show the efficiency of the proposed algorithm.

• Journal of Korean Society of Water and Wastewater
• /
• v.29 no.1
• /
• pp.1-9
• /
• 2015

A combined treatment system using multiple source water is becoming important as an alternative to conventional water supply for small-scale water systems. In this research, combined water treatment systems were investigated for simultaneous use of multi-source water including rainwater, ground water, river water, and reclaimed wastewater. A laboratory-scale system was developed to systematically compare various combinations of water treatment processes, including sand filtration, microfiltration (MF), granular activated carbon (GAC), and nanofiltration (NF). Results showed that the efficiency of combined water treatment systems was affected by the quality of feed waters. In addition, a simply approach based on the concept of linear combination was suggested to support a decision-making for the optimum water treatment systems with the consideration of final water quality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.12
• /
• pp.2374-2391
• /
• 2011

A variety of reconstruction methods has been developed to convert a set of scattered points generated from real models into explicit forms, such as polygonal meshes, parametric or implicit surfaces. In this paper, we present a method to construct multi-scale implicit surfaces from scattered points using multiscale kernels based on kernel and multi-resolution analysis theories. Our approach differs from other methods in that multi-scale reconstruction can be done without additional manipulation on input data, calculated functions support level of detail representation, and it can be naturally expanded for n-dimensional data. The method also works well with point-sets that are noisy or not uniformly distributed. We show features and performances of the proposed method via experimental results for various data sets.

• Molecules and Cells
• /
• v.44 no.7
• /
• pp.433-443
• /
• 2021

Multi-omics approaches are novel frameworks that integrate multiple omics datasets generated from the same patients to better understand the molecular and clinical features of cancers. A wide range of emerging omics and multi-view clustering algorithms now provide unprecedented opportunities to further classify cancers into subtypes, improve the survival prediction and therapeutic outcome of these subtypes, and understand key pathophysiological processes through different molecular layers. In this review, we overview the concept and rationale of multi-omics approaches in cancer research. We also introduce recent advances in the development of multi-omics algorithms and integration methods for multiple-layered datasets from cancer patients. Finally, we summarize the latest findings from large-scale multi-omics studies of various cancers and their implications for patient subtyping and drug development.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.2
• /
• pp.131-136
• /
• 2023

Nanocomposites have been considered innovative composite materials that have multi-functionality and high performance. Because the incorporation of nanoscale fillers may significantly improve the electrical, mechanical, and thermal properties of composites, numerous extensive studies on the characterization of nanocomposites with nanoscale fillers have been performed. In particular, the development of nanocomposites using carbon-based nanoscale fillers (e.g., carbon nanotubes, carbon black, graphene nanoplates) have attracted much interest in the composite field. This paper provides a review of recent advances in the electrical/mechanical characteristics of nanocomposites, which are essential for their practical applications. Furthermore, this paper revisits the recent research on multi-scale modeling, which is a promising approach for predicting the characteristics of nanocomposites. The current challenges and future development potentials for multi-scale modeling are also discussed.

• Coupled systems mechanics
• /
• v.7 no.5
• /
• pp.509-524
• /
• 2018

A hierarchical multi-scale modeling strategy devoted to the study of a Bitumen-Bound Gravel (BBG) is presented in this paper. More precisely, the paper investigates the temperature-dependent linear viscoelastic of the material when submitted to low deformations levels and moderate number of cycles. In such a hierarchical approach, 3D digital Representative Elementary Volumes are built and the outcomes at a scale (here, the sub-mesoscale) are used as input data at the next higher scale (here, the mesoscale). The viscoelastic behavior of the bituminous phases at each scale is taken into account by means of a generalized Maxwell model: the bulk part of the behavior is separated from the deviatoric one and bulk and shear moduli are expanded into Prony series. Furthermore, the viscoelastic phases are considered to be thermorheologically simple: time and temperature are not independent. This behavior is reproduced by the Williams-Landel-Ferry law. By means of the FE simulations of stress relaxation tests, the parameters of the various features of this temperature-dependent viscoelastic behavior are identified.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.1-8
• /
• 2023

In this paper, we propose a black ice detection platform framework using Convolutional Neural Networks (CNNs). To overcome black ice problem, we introduce a real-time based early warning platform using CNN-based architecture, and furthermore, in order to enhance the accuracy of black ice detection, we apply a multi-scale dilation convolution feature fusion (MsDC-FF) technique. Then, we establish a specialized experimental platform by using a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Experimental results of a real-time black ice detection platform show the better performance of our proposed network model compared to conventional image segmentation models. Our proposed platform have achieved real-time segmentation of road black ice areas by deploying a road black ice area segmentation network on the edge device Jetson Nano devices. This approach in parallel using multi-scale dilated convolutions with different dilation rates had faster segmentation speeds due to its smaller model parameters. The proposed MsCD-FF Net(2) model had the fastest segmentation speed at 5.53 frame per second (FPS). Thereby encouraging safe driving for motorists and providing decision support for road surface management in the road traffic monitoring department.