Artificial intelligence: a survey on evolution, models, applications and future trends

Lu, Yang

doi:10.1080/23270012.2019.1570365

Cited by 370 publications

(157 citation statements)

References 86 publications

Supporting

Mentioning

153

Contrasting

Unclassified

Order By: Relevance

“…Digital manufacturing transformation (II) can be achieved by adopting technologies such as robots and drones, 3D printing, computing, and blockchain. The most relevant feature of this transformation is that manufacturers retain the traditional business paradigm (selling products) while at the same time improve their routines (Bibby and Dehe 2018;Lu 2017). Productivity and quality are the major goals of this type of transformation (Yadav, Shankar, and Singh 2020;Tortorella, Giglio, and van Dun 2019).…”

Section: Discussionmentioning

confidence: 99%

“…At any rate, Industry 4.0 is a transformation enabled by a series of technologies which provide new and improved approaches to value creation, proposition, and capture (e.g. enhanced productivity, better quality products, better working conditions, sustainability, development of innovative capabilities and new revenue models) (Chiarini, Belvedere, and Grando 2020;Bibby and Dehe 2018;Lu 2017;Tsolakis et al 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Industry’s 4.0 transformation process: how to start, where to aim, what to be aware of

Calabrese

Dora

Ghiron

et al. 2020

Production Planning & Control

View full text Add to dashboard Cite

Industry 4.0 has fused digitalisation with traditional industrial processes bridging the physical and virtual worlds and opening unimagined possibilities for 21st century business growth. Research is still evolving toward the development of frameworks linking Industry's 4.0 enabling technologies to specific goals and to their impact on the manufacturers' businesses. A systematic review of all peer-reviewed managerial research is performed to extract Industry's 4.0 enabling technologies, barriers and goals. A framework linking technologies, barriers, and goals is then developed together with a web application based on its contents. The use of the framework is demonstrated through its application to two specific empirical case studies. The review shows that there are 9 classes of Industry's 4.0 enabling technologies, whose different arrangements lead to the achievement of up to 15 business goals that can be thwarted by 21 barriers. The pursuit of these goals leads to three different destinations, i.e., three diverse digital transformations of the manufacturing firms. This paper provides a holistic framework that analyses the relationships among Industry's 4.0 enabling technologies, barriers and goals. It appeals to managers who can use its contents along with the web application to derive recommendations and suggestions tailored to their Industry's 4.0 journeys.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Industry’s 4.0 transformation process: how to start, where to aim, what to be aware of

Calabrese

Dora

Ghiron

et al. 2020

Production Planning & Control

View full text Add to dashboard Cite

show abstract

“…Finding hidden relations within such data is now possible using massive computational power. New computer-intensive methods have been developed or are now available or possible (Reshef et al, 2011), including the broad field of artificial intelligence (AI) or machine learning (ML) which have produced a variety of approaches (Lu, 2019). Artificial intelligence includes a series of evolution-inspired techniques, brought together in the sub-field of evolutionary computation, of which the most studied and well-known probably are genetic algorithms (Holland, 1975).…”

Section: Introductionmentioning

confidence: 99%

Automated Discovery of Relationships, Models, and Principles in Ecology

et al. 2020

View full text Add to dashboard Cite

Ecological systems are the quintessential complex systems, involving numerous high-order interactions and non-linear relationships. The most used statistical modeling techniques can hardly accommodate the complexity of ecological patterns and processes. Finding hidden relationships in complex data is now possible using massive computational power, particularly by means of artificial intelligence and machine learning methods. Here we explored the potential of symbolic regression (SR), commonly used in other areas, in the field of ecology. Symbolic regression searches for both the formal structure of equations and the fitting parameters simultaneously, hence providing the required flexibility to characterize complex ecological systems. Although the method here presented is automated, it is part of a collaborative human–machine effort and we demonstrate ways to do it. First, we test the robustness of SR to extreme levels of noise when searching for the species-area relationship. Second, we demonstrate how SR can model species richness and spatial distributions. Third, we illustrate how SR can be used to find general models in ecology, namely new formulas for species richness estimators and the general dynamic model of oceanic island biogeography. We propose that evolving free-form equations purely from data, often without prior human inference or hypotheses, may represent a very powerful tool for ecologists and biogeographers to become aware of hidden relationships and suggest general theoretical models and principles.

show abstract

“…The second includes the new methods developed on the basis of artificial intelligence (AI). AI has had an increasingly wide application in a wide range of research fields (Lu, 2019), where artificial neural networks (ANN) and support vector machines (SVM) are currently popular AI algorithms which can be used in classification and forecasting (Akman, Karaman, & Kuzey, 2020; Crone, Hibon, & Nikolopoulos, 2011; Kim, 2003; Kock & Teräsvirta, 2014; Pai & Lin, 2005; Shi, Xu, & Liu, 1996; Shi, Xu, & Liu, 1999; Vafeiadis et al, 2018; Wegener, Spreckelsen, Basse, & Mettenheim, 2016; Xie, Mao, & Wang, 2015; Yuan, Li, Guan, & Xu, 2010; Zhang, 2003).…”

Section: Introductionmentioning

confidence: 99%

A hybrid model for financial time‐series forecasting based on mixed methodologies

et al. 2020

View full text Add to dashboard Cite

This paper proposes a hybrid model that combines ensemble empirical mode decomposition (EEMD), autoregressive integrated moving average (ARIMA), and Taylor expansion using a tracking differentiator to forecast financial time series. Specifically, the financial time series is decomposed by EEMD into some subseries. Then, the linear portion of each subseries is forecasted by the linear ARIMA model, while the nonlinear portion is predicted by the nonlinear Taylor expansion model. The forecasting results of the linear and nonlinear models are combined into the predicted result of each subseries. The final prediction result is obtained by combining the prediction values of all the subseries. The empirical results with real financial time series data demonstrate that this new hybrid approach outperforms the benchmark hybrid models considered in this paper.

show abstract

Artificial intelligence: a survey on evolution, models, applications and future trends

Cited by 370 publications

References 86 publications

Industry’s 4.0 transformation process: how to start, where to aim, what to be aware of

Industry’s 4.0 transformation process: how to start, where to aim, what to be aware of

Automated Discovery of Relationships, Models, and Principles in Ecology

A hybrid model for financial time‐series forecasting based on mixed methodologies

Contact Info

Product

Resources

About