• Title/Summary/Keyword: data-driven model

Search Result 659, Processing Time 0.033 seconds

Seeking for the Determinants of Entrepreneurship from National Level Data (국가 특성이 창업활동에 미치는 영향 실증 분석)

  • Kim, Hyung Jun;Min, Tae Ki;Wang, Jingbu;Schuler, Diana;Oh, Keun Yeob
    • Asia-Pacific Journal of Business Venturing and Entrepreneurship
    • /
    • v.15 no.6
    • /
    • pp.55-65
    • /
    • 2020
  • The purpose of this study is to empirically analyze the factors that affect start-up activities at the national level. Unlike most existing research about entrepreneurship at the individual level, this empirical analysis makes use of the total early-stage entrepreneurial activity(TEA) index at national level. This was developed by the Global Entrepreneur Monitor (GEM) as the measure for the degree of entrepreneurship of the countries. Based on the previous studies, not only national income level and unemployment rate, but also other factors including the cultural characteristics of the countries were included in our regression model. Using GEM's panel data, we found that the effectiveness of the factors depends on the stage of economic development. In particular, we found 'U-shape' relationship between the level of per capita income and entrepreneurship activity by the panel regression analysis using quadratic function. This analysis result can explicitly confirm what the existing literature have explained descriptively. Furthermore, the governmental support programs are shown to have significantly positive effects on the entrepreneurship or start-up activities in the factor-driven and efficiency-driven economies. On the contrary, those programs were not very helpful in the innovative economies. Lastly, this research suggests that the 'education and training' and the 'entrepreneurial culture' be the supportive norm for new business regardless of the economic development level.

Structural Decomposition Analysis for Energy Consumption of Industrial Sector with Linked Energy Input-Output Table 00-05-08 (접속불변에너지산업연관표 00-05-08을 이용한 산업별 에너지소비 변화량의 구조분해분석)

  • Kim, Yoon Kyung;Jang, Woon Jeong
    • Environmental and Resource Economics Review
    • /
    • v.20 no.2
    • /
    • pp.255-289
    • /
    • 2011
  • This study made linked Energy IO Table 00-05-08 of 76 sectors in intermediate sectors and analyzed structural decomposition analysis in energy consumption change in industrial sector with both by aggregate data and micro data. Structural decomposition analysis focused value added level change, value added share change of each industry, output structural change of each industry and energy intensity change of each industry as factors. Supply side model based on Ghosh inverse matrix was applied as empirical model because Korea has export driven industrial structure. Empirical results with aggregate data showed that value added change increased energy consumption and output structural change of each industry decreased energy consumption in both 2000~2005 and 2005~2008. However value added share change and energy intensity change caused opposite direction in energy consumption change with time. Policy based on aggregate data can not evaluate effort of each industry in energy efficiency and make effective results because aggregate data delete character of each industry.

  • PDF

Development of Homogenization Data-based Transfer Learning Framework to Predict Effective Mechanical Properties and Thermal Conductivity of Foam Structures (폼 구조의 유효 기계적 물성 및 열전도율 예측을 위한 균질화 데이터 기반 전이학습 프레임워크의 개발)

  • Wonjoo Lee;Suhan Kim;Hyun Jong Sim;Ju Ho Lee;Byeong Hyeok An;Yu Jung Kim;Sang Yung Jeong;Hyunseong Shin
    • Composites Research
    • /
    • v.36 no.3
    • /
    • pp.205-210
    • /
    • 2023
  • In this study, we developed a transfer learning framework based on homogenization data for efficient prediction of the effective mechanical properties and thermal conductivity of cellular foam structures. Mean-field homogenization (MFH) based on the Eshelby's tensor allows for efficient prediction of properties in porous structures including ellipsoidal inclusions, but accurately predicting the properties of cellular foam structures is challenging. On the other hand, finite element homogenization (FEH) is more accurate but comes with relatively high computational cost. In this paper, we propose a data-driven transfer learning framework that combines the advantages of mean-field homogenization and finite element homogenization. Specifically, we generate a large amount of mean-field homogenization data to build a pre-trained model, and then fine-tune it using a relatively small amount of finite element homogenization data. Numerical examples were conducted to validate the proposed framework and verify the accuracy of the analysis. The results of this study are expected to be applicable to the analysis of materials with various foam structures.

Development of Web-based Construction-Site-Safety-Management Platform Using Artificial Intelligence (인공지능을 이용한 웹기반 건축현장 안전관리 플랫폼 개발)

  • Siuk Kim;Eunseok Kim;Cheekyeong Kim
    • Journal of the Computational Structural Engineering Institute of Korea
    • /
    • v.37 no.2
    • /
    • pp.77-84
    • /
    • 2024
  • In the fourth industrial-revolution era, the construction industry is transitioning from traditional methods to digital processes. This shift has been challenging owing to the industry's employment of diverse processes and extensive human resources, leading to a gradual adoption of digital technologies through trial and error. One critical area of focus is the safety management at construction sites, which is undergoing significant research and efforts towards digitization and automation. Despite these initiatives, recent statistics indicate a persistent occurrence of accidents and fatalities in construction sites. To address this issue, this study utilizes large-scale language-model artificial intelligence to analyze big data from a construction safety-management information network. The findings are integrated into on-site models, which incorporate real-time updates from detailed design models and are enriched with location information and spatial characteristics, for enhanced safety management. This research aims to develop a big-data-driven safety-management platform to bolster facility and worker safety by digitizing construction-site safety data. This platform can help prevent construction accidents and provide effective education for safety practices.

Denoising Self-Attention Network for Mixed-type Data Imputation (혼합형 데이터 보간을 위한 디노이징 셀프 어텐션 네트워크)

  • Lee, Do-Hoon;Kim, Han-Joon;Chun, Joonghoon
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.11
    • /
    • pp.135-144
    • /
    • 2021
  • Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

Development of Local Stem Volume Table for Pinus densiflora S. et Z. Using Tree Stem Taper Model (수간곡선 모델을 이용한 소나무의 지방별 수간재적표 개발)

  • Kang, Jin-Taek;Son, Yeong-Mo;Kim, So-Won;Lee, Sun-Jeoung;Park, Hyun
    • Korean Journal of Agricultural and Forest Meteorology
    • /
    • v.16 no.4
    • /
    • pp.327-335
    • /
    • 2014
  • Current volume tables might underestimate or overestimate the volumes of individual trees in a specific region because the tables were made using the data from broad regions within South Korea. Therefore, to solve this problem, this study was conducted to develop local stem volume tables reflecting the local growth pattern and properties using stem taper equations in the regions of Hongcheon and Yeongju. We developed the local stem volume table for Pinus densiflora, which is the widely planted species in South Korea. To derive the most suitable taper equation for estimating the stem volume of region, three models of Max & Burkhart, Kozak and Parresol et al. were applied and their fitness were statistically analyzed by using the Fitness Index, Bias, and Standard Error of Bias. The result showed that there is a significant difference among the three models, and the Fitness Index of the Kozak model was highest compared to the other models. Therefore, the Kozak model was chosen for generating stem taper equation and stem volume tables for P. densiflora. The result from the developed stem volume tables of each region was compared to the current stem volume tables with driven by the data of tree growth obtained throughout the nation. The result showed that there is a significant difference (0.000< ${\alpha}=0.05$) in two regions, Hongcheon and Yeongju, and also there is a significant difference (0.000< ${\alpha}=0.05$) between the two regions.

An Empirical Investigation into the Role of Core-Competency Orientation and IT Outsourcing Process Management Capability (핵심역량 지향성과 프로세스 관리역량이 IT 아웃소싱 성과에 미치는 연구)

  • Kim, Yong-Jin;Nam, Ki-Chan;Song, Jae-Ki;Koo, Chul-Mo
    • Asia pacific journal of information systems
    • /
    • v.17 no.3
    • /
    • pp.131-146
    • /
    • 2007
  • Recently, the role of IT service providers has been enlarged from managing a single function or system to reconstructing entire information management processes in new ways to contribute to shareholder value across the enterprise. This movement toward extensive and complex outsourcing agreements has been driven by the assumption that outsourcing information technology functions is a reliable approach to maximizing resource productivity. Hiring external IT service providers to manage part or all of its information-related services helps a firm focus on its core business and provides better services to its clients, thus obtaining sustainable competitive advantage. This practice of focusing on the strategic aspect of outsourcing is referred to as strategic sourcing where the focus is capability sourcing, not procurement. Given the importance of the strategic outsourcing, however, to our knowledge, there is little empirical research on the relationship between the strategic outsourcing orientation and outsourcing performance. Moreover, there is little research on the factor that makes the strategic outsourcing effective. This study is designed to investigate the relationship between strategic IT outsourcing orientation and IT outsourcing performance and the process through which strategic IT outsourcing orientation influences outsourcing performance, Based on the framework of strategic orientation-performance and core competence based management, this study first identifies core competency orientation as a proper strategic orientation pertinent to IT outsourcing and IT outsourcing process management capability as the mediator to affect IT outsourcing performance. The proposed research model is then tested with a sample of 200 firms. The findings of this study may contribute to the literature in two ways. First, it draws on the strategic orientation - performance framework in developing its research model so that it can provide a new perspective to the well studied phenomena. This perspective allows practitioners and researchers to look at outsourcing from an angle that emphasizes the strategic decision making to outsource its IT functions. Second, by separating the concept of strategic orientation and outsourcing process management capability, this study provides practices with insight into how the strategic orientation can work effectively to achieve an expected result. In addition, the current study provides a basis for future studies that examine the factors affecting IT outsourcing performance with more controllable factors such as IT outsourcing process management capability rather than external hard-to-control factors including trust and relationship management. This study investigates the major factors that determine IT outsourcing success. Based on strategic orientation and core competency theories, we develop the proposed research model to investigate the relationship between core competency orientation and IT outsourcing performance and the mediating role of IT outsourcing process management capability on IT outsourcing performance. The model consists of two independent variables (core-competency-orientation and IT outsourcing process management capability), and two dependent variables (outsourced task complexity and IT outsourcing performance). Comprehensive data collection was conducted through an outsourcing association. The survey data were analyzed using a structural analysis method. IT outsourcing process management capability was found to mediate the effect of core competency orientation on both outsourced task complexity and IT outsourcing performance. Further analysis and findings are discussed.

Diagnosis of Valve Internal Leakage for Ship Piping System using Acoustic Emission Signal-based Machine Learning Approach (선박용 밸브의 내부 누설 진단을 위한 음향방출신호의 머신러닝 기법 적용 연구)

  • Lee, Jung-Hyung
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.28 no.1
    • /
    • pp.184-192
    • /
    • 2022
  • Valve internal leakage is caused by damage to the internal parts of the valve, resulting in accidents and shutdowns of the piping system. This study investigated the possibility of a real-time leak detection method using the acoustic emission (AE) signal generated from the piping system during the internal leakage of a butterfly valve. Datasets of raw time-domain AE signals were collected and postprocessed for each operation mode of the valve in a systematic manner to develop a data-driven model for the detection and classification of internal leakage, by applying machine learning algorithms. The aim of this study was to determine whether it is possible to treat leak detection as a classification problem by applying two classification algorithms: support vector machine (SVM) and convolutional neural network (CNN). The results showed different performances for the algorithms and datasets used. The SVM-based binary classification models, based on feature extraction of data, achieved an overall accuracy of 83% to 90%, while in the case of a multiple classification model, the accuracy was reduced to 66%. By contrast, the CNN-based classification model achieved an accuracy of 99.85%, which is superior to those of any other models based on the SVM algorithm. The results revealed that the SVM classification model requires effective feature extraction of the AE signals to improve the accuracy of multi-class classification. Moreover, the CNN-based classification can be a promising approach to detect both leakage and valve opening as long as the performance of the processor does not degrade.

Analysis of Precipitation Characteristics of Regional Climate Model for Climate Change Impacts on Water Resources (기후변화에 따른 수자원 영향 평가를 위한 Regional Climate Model 강수 계열의 특성 분석)

  • Kwon, Hyun-Han;Kim, Byung-Sik;Kim, Bo-Kyung
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.28 no.5B
    • /
    • pp.525-533
    • /
    • 2008
  • Global circulation models (GCMs) have been used to study impact of climate change on water resources for hydrologic models as inputs. Recently, regional circulation models (RCMs) have been used widely for climate change study, but the RCMs have been rarely used in the climate change impacts on water resources in Korea. Therefore, this study is intended to use a set of climate scenarios derived by RegCM3 RCM ($27km{\times}27km$), which is operated by Korea Meteorological Administration. To begin with, the RCM precipitation data surrounding major rainfall stations are extracted to assess validation of the scenarios in terms of reproducing low frequency behavior. A comprehensive comparison between observation and precipitation scenario is performed through statistical analysis, wavelet transform analysis and EOF analysis. Overall analysis confirmed that the precipitation data driven by RegCM3 shows capabilities in simulating hydrological low frequency behavior and reproducing spatio-temporal patterns. However, it is found that spatio-temporal patterns are slightly biased and amplitudes (variances) from the RCMs precipitation tend to be lower than the observations. Therefore, a bias correction scheme to correct the systematic bias needs to be considered in case the RCMs are applied to water resources assessment under climate change.

Label Assignment Schemes for MPLS Traffic Engineering (MPLS 트래픽 엔지니어링을 위한 레이블 할당 방법)

  • 이영석;이영석;옥도민;최양희;전병천
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.25 no.8A
    • /
    • pp.1169-1176
    • /
    • 2000
  • In this paper, label assignment schemes considering the IP flow model for the efficient MPLS traffic engineering are proposed and evaluated. Based on the IP flow model, the IP flows are classified into transient flows and base flows. Base flows, which last for a long time, transmit data in high bit rate, and be composed of many packets, have good implications for the MPLS traffic engineering, because they usually cause network congestion. To make use of base flows for the MPLS traffic engineering, we propose two base flow classifiers and label assignment schemes where transient flows are allocated to the default LSPs and base flows to explicit LSPs. Proposed schemes are based on the traffic-driven label triggering method combined with a routing tabel. The first base flow classifier uses both flow size in packet counts and routing entries, and the other one, extending the dynamic X/Y flow classifier, is based on a cut-through ratio. Proposed schemes are shown to minimize the number of labels, not degrading the total cut-through ratio.

  • PDF