본 연구는 기계 학습 기반의 자동 분류 기법을 적용함으로써 유망 기술의 선정 과정에 활용할 수 있는 의사결정 지원 시스템의 구현 방안을 제시하는 것을 목표로 한다. 연구 수행을 위해 전체 시스템의 아키텍처를 구축하고 세부 연구 단계를 진행하였다. 우선, 유망 기술 후보 아이템을 선정하고 빅데이터 시스템을 활용하여 추세 데이터를 자동 생성하였다. 기술 발전의 개념 모델과 패턴 분류 체계를 정의한 후 자동 분류 실험을 통해 효율적인 기계 학습 방안을 제시하였다. 마지막으로 시스템의 분석 결과를 해석하고 활용 방안을 도출하고자 하였다. 본 연구에서 제안한 동적 시간 와핑(DTW) 기법과 k-최근접 이웃(kNN) 분류 모델을 결합한 DTW-kNN 기반의 분류 실험에서 최대 87.7%의 식별 성능을 보여주었으며, 특히 추세의 변동이 심한 'eventual' 정의 구간에서는 유클리디언 거리(ED) 알고리즘 대비 39.4% 포인트의 최대 성능 차이를 보여주어 제안 모델의 우수함을 확인할 수 있었다. 또한, 시스템이 제시하는 분석 결과를 통해, 대량의 추세 데이터를 입력받아 유형별로 자동 분류하고 필터링하는 과정에 본 의사결정 지원 시스템을 효과적으로 활용할 수 있음을 확인하였다.
본 연구는 기계 학습 기반의 자동 분류 기법을 적용함으로써 유망 기술의 선정 과정에 활용할 수 있는 의사결정 지원 시스템의 구현 방안을 제시하는 것을 목표로 한다. 연구 수행을 위해 전체 시스템의 아키텍처를 구축하고 세부 연구 단계를 진행하였다. 우선, 유망 기술 후보 아이템을 선정하고 빅데이터 시스템을 활용하여 추세 데이터를 자동 생성하였다. 기술 발전의 개념 모델과 패턴 분류 체계를 정의한 후 자동 분류 실험을 통해 효율적인 기계 학습 방안을 제시하였다. 마지막으로 시스템의 분석 결과를 해석하고 활용 방안을 도출하고자 하였다. 본 연구에서 제안한 동적 시간 와핑(DTW) 기법과 k-최근접 이웃(kNN) 분류 모델을 결합한 DTW-kNN 기반의 분류 실험에서 최대 87.7%의 식별 성능을 보여주었으며, 특히 추세의 변동이 심한 'eventual' 정의 구간에서는 유클리디언 거리(ED) 알고리즘 대비 39.4% 포인트의 최대 성능 차이를 보여주어 제안 모델의 우수함을 확인할 수 있었다. 또한, 시스템이 제시하는 분석 결과를 통해, 대량의 추세 데이터를 입력받아 유형별로 자동 분류하고 필터링하는 과정에 본 의사결정 지원 시스템을 효과적으로 활용할 수 있음을 확인하였다.
This study aims to present a method for implementing a decision support system that can be used for selecting emerging technologies by applying a machine learning-based automatic classification technique. To conduct the research, the architecture of the entire system was built and detailed research ...
This study aims to present a method for implementing a decision support system that can be used for selecting emerging technologies by applying a machine learning-based automatic classification technique. To conduct the research, the architecture of the entire system was built and detailed research steps were conducted. First, emerging technology candidate items were selected and trend data was automatically generated using a big data system. After defining the conceptual model and pattern classification structure of technological development, an efficient machine learning method was presented through an automatic classification experiment. Finally, the analysis results of the system were interpreted and methods for utilization were derived. In a DTW-kNN-based classification experiment that combines the Dynamic Time Warping(DTW) method and the k-Nearest Neighbors(kNN) classification model proposed in this study, the identification performance was up to 87.7%, and particularly in the 'eventual' section where the trend highly fluctuates, the maximum performance difference was 39.4% points compared to the Euclidean Distance(ED) algorithm. In addition, through the analysis results presented by the system, it was confirmed that this decision support system can be effectively utilized in the process of automatically classifying and filtering by type with a large amount of trend data.
This study aims to present a method for implementing a decision support system that can be used for selecting emerging technologies by applying a machine learning-based automatic classification technique. To conduct the research, the architecture of the entire system was built and detailed research steps were conducted. First, emerging technology candidate items were selected and trend data was automatically generated using a big data system. After defining the conceptual model and pattern classification structure of technological development, an efficient machine learning method was presented through an automatic classification experiment. Finally, the analysis results of the system were interpreted and methods for utilization were derived. In a DTW-kNN-based classification experiment that combines the Dynamic Time Warping(DTW) method and the k-Nearest Neighbors(kNN) classification model proposed in this study, the identification performance was up to 87.7%, and particularly in the 'eventual' section where the trend highly fluctuates, the maximum performance difference was 39.4% points compared to the Euclidean Distance(ED) algorithm. In addition, through the analysis results presented by the system, it was confirmed that this decision support system can be effectively utilized in the process of automatically classifying and filtering by type with a large amount of trend data.
I. Park & B. Yoon. (2018). Technological opportunity discovery for technological convergence based on the prediction of technology knowledge flow in a citation network. Journal of Informetrics, 12(4), 1199-1222. DOI : 10.1016/j.joi.2018.09.007
MIT. (2022). 2022 10 Breakthrough Technologies. MIT Technology Review. https://www.technologyreview.com/2022/02/23/1045416/10-breakthrough-technologies-2022/
D. E. O'Leary. (2008). Gartner's Hype Cycle and Information System Research Issues. International Journal of Accounting Information Systems 9(4), 240-252. DOI : 10.1016/j.accinf.2008.09.001
KISTEP. (2022). A Study on the Selection of KISTEP Future Key Technologies in 2022. KISTEP. https://www.kistep.re.kr/reportDetail.es?mida10305020000&rpt_tp831-006&rpt_noRES0220220075
D. H. Jeong & H. S. Joo. (2018). Discovering Interdisciplinary Convergence Technologies Using Content Analysis Technique Based on Topic Modeling. Journal of the Korean Society for information Management, 35, 77-100. DOI : 10.3743/KOSIM.2018.35.3.077
J. Fenn & M. Raskino. (2009). Understanding Gartner's Hype Cycles. Gartner. https://www.gartner.com/en/documents/1069314
O. Dedehayir & M. Steinert. (2016). The hype cycle model: A review and future directions. Technological Forecasting and Social Change, 108, 28-41. DOI : 10.1016/j.techfore.2016.04.005
A. Caiani, A. Godin & S. Lucarelli. (2015). Innovation and Finance: A Stock Flow Consistent Analysis of Great Surges of Development. in The Evolution of Economic and Innovation Systems. Springer. DOI : 10.1007/978-3-319-13299-0_17
L. Kanger & J. Schota. (2019). Deep transitions: Theorizing the long-term patterns of socio-technical change. Environmental Innovation and Societal Transitions, 32, 7-21. DOI : 10.1016/j.eist.2018.07.006
C. Perez. (2003). Technological Revolutions and Financial Capital: The Dynamics of Bubbles and Golden Ages. Cheltenham, UK: Cambridge University Press. DOI : 10.1017/S002205070348193X
E. Keogh. (2005). Exact indexing of dynamic time warping. Knowledge and Information Systems, 7(3), 358-386. DOI : 10.1007/s10115-004-0154-9
K. Yang & C. Shahabi. (2007). An efficient k nearest neighbor search for multivariate time series. Information and Computation, 205(1), 65-98. DOI : 10.1016/j.ic.2006.08.004
H. H. Hsu, A. C. Yang & M. D. Lu. (2011). KNN-DTW Based Missing Value Imputation for Microarray Time Series Data. Journal of Computers, 6(3), 418-425. DOI : 10.4304/jcp.6.3.418-425
D. H. Jeong. (2019). Enhancing Classification Performance of Temporal Keyword Data by Using Moving Average-based Dynamic Time Warping Method. Journal of the Korean Society for information Management, 36(4), 83-105. DOI : 10.3743/KOSIM.2019.36.4.083
H. Abe & S. Tsumoto. (2010). Trend detection from large text data. 2010 IEEE International Conference on Systems, Man and Cybernetics (SMC), 310-315. DOI : 10.1109/ICSMC.2010.5641682
M. Lee, S. Kim, H. Kim & J. Lee. (2022). Technology Opportunity Discovery using Deep Learning-based Text Mining and a Knowledge Graph. Technological Forecasting and Social Change, 180. DOI : 10.1016/j.techfore.2022.121718
M. N. Hwang, M. H. Cho, M. G. Hwang & D. H. Jeong. (2011). Trend Analysis of Technical Terms Using Term Life Cycle Modeling. Korea Information Processing Society, 18D(6), 493-500. DOI : 10.3745/KIPSTD.2011.18D.6.493
B. Fung. (2014. 04. 17.). Hypothetical technology is fun. Real technology creeps us out. Washington Post. https://www.washingtonpost.com/news/the-switch/wp/2014/04/17/hypothetical-technology-is-fun-real-technology-creeps-us-out/
S. Salvador & P. Chan. (2007). Toward accurate dynamic time warping in linear time and space. Intelligent Data Analysis, 11(5), 561-580. DOI : 10.3233/IDA-2007-11508
A. Bagnall, J. Lines, A. Bostrom, J. Large & E. Keogh. (2017). The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Mining and Knowledge Discovery, 31(3), 606-660. DOI: 10.1007/s10618-016-0483-9
AI-Helper
※ AI-Helper는 부적절한 답변을 할 수 있습니다.