Detecting technological maturity from bibliometric patterns

Cauthen, Katherine; Rai, Prashant; Hale, Nicholas; Freeman, Laura; Ray, Jaideep

doi:10.1016/j.eswa.2022.117177

Detecting technological maturity from bibliometric patterns

Journal Article · Fri Apr 08 00:00:00 EDT 2022 · Expert Systems with Applications

DOI:https://doi.org/10.1016/j.eswa.2022.117177· OSTI ID:1870490

Cauthen, Katherine ^[1]; Rai, Prashant ^[2]; Hale, Nicholas ^[3]; Freeman, Laura ^[3]; Ray, Jaideep ^[2]

Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sandia National Lab. (SNL-CA), Livermore, CA (United States)
Virginia Tech Applied Research Corporation, Arlington, VA (United States)

We report the capability to identify emergent technologies based upon easily accessed open-source indicators, such as publications, is important for decision-makers in industry and government. The scientific contribution of this work is the proposition of a machine learning approach to the detection of the maturity of emerging technologies based on publication counts. Time-series of publication counts have universal features that distinguish emerging and growing technologies. We train an artificial neural network classifier, a supervised machine learning algorithm, upon these features to predict the maturity (emergent vs. growth) of an arbitrary technology. With a training set comprised of 22 technologies we obtain a classification accuracy ranging from 58.3% to 100% with an average accuracy of 84.6% for six test technologies. To enhance classifier performance, we augmented the training corpus with synthetic time-series technology life cycle curves, formed by calculating weighted averages of curves in the original training set. Training the classifier on the synthetic data set resulted in improved accuracy, ranging from 83.3% to 100% with an average accuracy of 90.4% for the test technologies. The performance of our classifier exceeds that of competing machine learning approaches in the literature, which report an average classification accuracy of only 85.7% at maximum. Moreover, in contrast to current methods our approach does not require subject matter expertise to generate training labels, and it can be automated and scaled.

View Accepted Manuscript (DOE)

Research Organization:: Sandia National Laboratories (SNL-CA), Livermore, CA (United States); Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA); Army Research Laboratory

Grant/Contract Number:: NA0003525

OSTI ID:: 1870490

Alternate ID(s):: OSTI ID: 1960895

Report Number(s):: SAND2022-4746J; 705120

Journal Information:: Expert Systems with Applications, Journal Name: Expert Systems with Applications Vol. 201; ISSN 0957-4174

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (29)

Der strategische Einsatz von Technologien Sommerlatte, Tom; Deschamps, Jean-Philippe Management im Zeitalter der Strategischen Führung https://doi.org/10.1007/978-3-322-93117-7_3	book	January 1986
The hunt for S -shaped growth paths in technological innovation: a patent study * Andersen, Birgitte Journal of Evolutionary Economics, Vol. 9, Issue 4 https://doi.org/10.1007/s001910050093	journal	December 1999
The co-evolution of knowledge and collaboration networks: the role of the technology life-cycle van der Pol, Johannes; Rameshkoumar, Jean-Paul Scientometrics, Vol. 114, Issue 1 https://doi.org/10.1007/s11192-017-2579-4	journal	November 2017
A bibliometric method for assessing technological maturity: the case of additive manufacturing Lezama-Nicolás, René; Rodríguez-Salvador, Marisela; Río-Belver, Rosa Scientometrics, Vol. 117, Issue 3 https://doi.org/10.1007/s11192-018-2941-1	journal	November 2018
The normal distribution as a model of technological substitution Stapleton, Earl Technological Forecasting and Social Change, Vol. 8, Issue 3 https://doi.org/10.1016/0040-1625(76)90008-1	journal	January 1976
The Weibull distribution as a general model for forecasting technological change Sharif, M. Nawaz; Islam, M. Nazrul Technological Forecasting and Social Change, Vol. 18, Issue 3 https://doi.org/10.1016/0040-1625(80)90026-8	journal	November 1980
Development of a technological S-curve for tire cord textiles Merino, Donald N. Technological Forecasting and Social Change, Vol. 37, Issue 3 https://doi.org/10.1016/0040-1625(90)90028-T	journal	May 1990
A method to select between Gompertz and logistic trend curves Franses, Philip Hans Technological Forecasting and Social Change, Vol. 46, Issue 1 https://doi.org/10.1016/0040-1625(94)90016-7	journal	May 1994
The dynamics of technological innovation: The case of the chemical industry Achilladelis, Basil; Schwarzkopf, Albert; Cines, Martin Research Policy, Vol. 19, Issue 1 https://doi.org/10.1016/0048-7333(90)90032-2	journal	February 1990
The dynamics of technological innovation: The sector of antibacterial medicines Achilladelis, Basil Research Policy, Vol. 22, Issue 4 https://doi.org/10.1016/0048-7333(93)90001-X	journal	August 1993
Innovation forecasting Watts, Robert J.; Porter, Alan L. Technological Forecasting and Social Change, Vol. 56, Issue 1 https://doi.org/10.1016/S0040-1625(97)00050-4	journal	September 1997
The dynamics of technological innovation: the case of the pharmaceutical industry Achilladelis, Basil; Antonakis, Nicholas Research Policy, Vol. 30, Issue 4 https://doi.org/10.1016/S0048-7333(00)00093-7	journal	April 2001
Managing the transition of technology life cycle Kim, B. Technovation, Vol. 23, Issue 5 https://doi.org/10.1016/S0166-4972(02)00168-2	journal	May 2003
Performance analysis of technology using the S curve model: the case of digital signal processing (DSP) technologies Nieto, Mariano; Lopéz, Francisco; Cruz, Fernando Technovation, Vol. 18, Issue 6-7 https://doi.org/10.1016/S0166-4972(98)00021-2	journal	January 1998
Technology trends analysis and forecasting application based on decision tree and statistical feature analysis Kim, Jinhyung; Hwang, Myunggwon; Jeong, Do-Heon Expert Systems with Applications, Vol. 39, Issue 16 https://doi.org/10.1016/j.eswa.2012.05.021	journal	November 2012
The technology life cycle: Conceptualization and managerial implications Taylor, Margaret; Taylor, Andrew International Journal of Production Economics, Vol. 140, Issue 1 https://doi.org/10.1016/j.ijpe.2012.07.006	journal	November 2012
Start-ups as technology life cycle indicator for the early stage of application: An analysis of the battery value chain Sick, Nathalie; Bröring, Stefanie; Figgemeier, Egbert Journal of Cleaner Production, Vol. 201 https://doi.org/10.1016/j.jclepro.2018.08.036	journal	November 2018
Patent indicators for the technology life cycle development Haupt, Reinhard; Kloyer, Martin; Lange, Marcus Research Policy, Vol. 36, Issue 3 https://doi.org/10.1016/j.respol.2006.12.004	journal	April 2007
A systematic approach for integrated trend analysis—The case of etching Wu, Feng-Shang; Hsu, Chun-Chi; Lee, Pei-Chun Technological Forecasting and Social Change, Vol. 78, Issue 3 https://doi.org/10.1016/j.techfore.2010.08.006	journal	March 2011
Technology level evaluation methodology based on the technology growth curve Ryu, Jiyeon; Byeon, Soon Cheon Technological Forecasting and Social Change, Vol. 78, Issue 6 https://doi.org/10.1016/j.techfore.2011.01.003	journal	July 2011
Technology life cycle analysis method based on patent documents Gao, Lidan; Porter, Alan L.; Wang, Jing Technological Forecasting and Social Change, Vol. 80, Issue 3 https://doi.org/10.1016/j.techfore.2012.10.003	journal	March 2013
Technology maturity assessment based on blog analysis Albert, Till; Moehrle, Martin G.; Meyer, Stefan Technological Forecasting and Social Change, Vol. 92 https://doi.org/10.1016/j.techfore.2014.08.011	journal	March 2015
Identification and monitoring of possible disruptive technologies by patent-development paths and topic modeling Momeni, Abdolreza; Rost, Katja Technological Forecasting and Social Change, Vol. 104 https://doi.org/10.1016/j.techfore.2015.12.003	journal	March 2016
Stochastic technology life cycle analysis using multiple patent indicators Lee, Changyong; Kim, Juram; Kwon, Ohjin Technological Forecasting and Social Change, Vol. 106 https://doi.org/10.1016/j.techfore.2016.01.024	journal	May 2016
Technological innovation strategy: how do technology life cycles change by technological area Byun, Jeongeun; Sung, Tae-Eung; Park, Hyun-Woo Technology Analysis & Strategic Management, Vol. 30, Issue 1 https://doi.org/10.1080/09537325.2017.1297397	journal	March 2017
Forecasting of Fuel cell technology in hybrid and electric vehicles using Gompertz growth curve Nagula, Manohar Journal of Statistics and Management Systems, Vol. 19, Issue 1 https://doi.org/10.1080/09720510.2014.1001601	journal	January 2016
Technological forecasting techniques and competitive intelligence: tools for improving the innovation process Denise Lemos, Ângela; Carlos Porto, Antonio Industrial Management & Data Systems, Vol. 98, Issue 7 https://doi.org/10.1108/02635579810227698	journal	November 1998
How to analyze technology lifecycle from the perspective of patent characteristics? the cases of DVDs and hard drives: Patent characteristics for understanding technology lifecycle Su, Hsin-Ning R&D Management, Vol. 48, Issue 3 https://doi.org/10.1111/radm.12279	journal	July 2017
An Experimental Application of the DELPHI Method to the Use of Experts Dalkey, Norman; Helmer, Olaf Management Science, Vol. 9, Issue 3 https://doi.org/10.1287/mnsc.9.3.458	journal	April 1963

Similar Records

Physics-Based Method for Generating Fully Synthetic IV Curve Training Datasets for Machine Learning Classification of PV Failures

Journal Article · Tue Jul 12 00:00:00 EDT 2022 · Energies · OSTI ID:1875971

Classifying Cancer Pathology Reports with Hierarchical Self-Attention Networks

Journal Article · Tue Oct 15 00:00:00 EDT 2019 · Artificial Intelligence in Medicine · OSTI ID:1785219

Improving the Accuracy of Nearest-Neighbor Classification Using Principled Construction and Stochastic Sampling of Training-Set Centroids

Journal Article · Mon Jan 25 23:00:00 EST 2021 · Entropy · OSTI ID:1762549

Related Subjects

97 MATHEMATICS AND COMPUTING
artificial neural network
data augmentation
machine learning
technology life cycle

Detecting technological maturity from bibliometric patterns

Citation Formats

References (29)

Similar Records

Related Subjects