The aim of the research presented in this paper is to assess the predictive capabilities of technology forecasting of morphological analysis employed with machine learning algorithms. Forecasting precision is desired to be as high as achievable; however, there are many limitations of morphological analysis in forecasting that includes both methodical approaches as well as technological constraints. Morphological analysis is characterized with domain specific presumptions and exclusive judgments that adds greater uncertainties and hinders advancements in technology. In this paper, a novel hybrid model is proposed with an aim to increase forecasting accuracy. Machine learning techniques such as Support Vector Machine (SVM), Naive Bayes (NB), and Logistic Regression are integrated with morphological analysis in the proposed model. The output achieved could enable decision-makers with more reliable predictions. Trend research has been carried out very carefully in order to design an effective system. Various scenarios are considered in planning the approach of the proposed system where the Delphi method is also considered. The result of the simulation study shows clearly that the proposed model yields higher prediction accuracy which could provide valuable insights to decision-makers when navigating and exploring technology forecasting.
Evaluating Predictive Efficacy of Machine Learning-Based Morphological Analysis for Technological Forecasting
Smart Innovation, Systems and Technologies
Congress on Control, Robotics, and Mechatronics ; 2024 ; Warangal, India February 03, 2024 - February 04, 2024
Proceedings of the Second Congress on Control, Robotics, and Mechatronics ; Chapter : 5 ; 43-53
2024-10-31
11 pages
Article/Chapter (Book)
Electronic Resource
English
TIBKAT | 1962
|Methods of Technological Forecasting
NTIS | 1977
|Methods of technological forecasting
TIBKAT | 1977
|