Small Sample Modelling Based on Deep and Broad Forest Regression
Theory and Industrial Application
- 1st Edition - November 1, 2025
- Authors: Wen Yu, Jian Tang, Junfei Qiao
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 3 1 5 6 4 - 0
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 3 1 5 6 5 - 7
Small Sample Modelling Based on Deep and Broad Forest Regression: Theory and Industrial Application delves into tree-structured methods in the industrial sector, encomp… Read more
Small Sample Modelling Based on Deep and Broad Forest Regression: Theory and Industrial Application delves into tree-structured methods in the industrial sector, encompassing classical ensemble learning, tree-structured deep forest classification, and broad learning systems with neural networks. It introduces an innovative deep/broad learning algorithm for small-sample industrial modeling tasks. The book is divided into two parts: methodology and practical application in dioxin emission modeling. Methodology sections include Preliminaries, Deep Forest Regression, Broad Forest Regression, and Fuzzy Forest Regression. The application part focuses on modeling dioxin emissions in municipal solid waste incineration. Throughout, various tree-structured strategies are presented, and the authors provide software systems for validating these methods. This book is suitable for advanced undergraduates, graduate engineering students, and practicing engineers looking for self-study resources.
- Introduces a novel deep and broad regression algorithm specifically designed for small sample industrial modeling. It covers Deep Forest Regression for Industrial Modeling, Broad Forest Regression for Industrial Modeling, and Fuzzy Forest Regression for Industrial Modeling
- Delves into recent results concerning the hot topic of deep and broad learning using non-neuron units for regression and the interpretability of fuzzy trees. These innovative methods are supported by the use of multi-dimensional benchmark data, providing solid confirmation
- Offers a real application case for industrial modeling by focusing on dioxin emission concentration. This case revolves around a strict controlled environment index of the municipal solid waste incineration (MSWI) process. The book provides offline modeling techniques such as improved deep forest regression and simplified deep forest regression
Advanced undergraduate students and graduate engineering students
PART I Methods
1. Preliminaries
1.1 Deep forest classification
1.2 Broad learning system
1.3 Decision tree for T-S fuzzy regression
2. Deep Forest Regression for Industrial Modeling
2.1 Basic deep forest regression method
2.2 Deep forest regression based on cross-layer fully connection
2.3 Simulation results
2.4 Conclusions
3. Broad Forest Regression for Industrial Modeling
3.1 Static broad forest regression method
3.2 Broad forest regression with increment learning
3.3 Simulation results
3.4 Conclusion
4. Fuzzy Forest Regression for Industrial Modeling
4.1 Fuzzy regression tree method
4.2 Fuzzy forest regression method
4.3 Time complexity analysis
4.4 Simulation results
4.5 Conclusion
PART II Application to Dioxin Emission Modeling
5. Deep Forest Regression Based on Feature Reduction and Feature Enhancement
5.1 Method strategy
5.2 Method implementation
5.3 Simulation results
5.4 Conclusion
6. Simplified Deep Forest Regression with Combined Feature Selection and Residual Error Fitting
6.1 Method strategy
6.2 Method implementation
6.3 Simulation results
6.4 Conclusion
7. Online Fuzzy Broad Forest Regression
7.1 Method strategy
7.2 Method implementation
7.3 Experimental Results
7.4 Conclusion References Appendix
1. Preliminaries
1.1 Deep forest classification
1.2 Broad learning system
1.3 Decision tree for T-S fuzzy regression
2. Deep Forest Regression for Industrial Modeling
2.1 Basic deep forest regression method
2.2 Deep forest regression based on cross-layer fully connection
2.3 Simulation results
2.4 Conclusions
3. Broad Forest Regression for Industrial Modeling
3.1 Static broad forest regression method
3.2 Broad forest regression with increment learning
3.3 Simulation results
3.4 Conclusion
4. Fuzzy Forest Regression for Industrial Modeling
4.1 Fuzzy regression tree method
4.2 Fuzzy forest regression method
4.3 Time complexity analysis
4.4 Simulation results
4.5 Conclusion
PART II Application to Dioxin Emission Modeling
5. Deep Forest Regression Based on Feature Reduction and Feature Enhancement
5.1 Method strategy
5.2 Method implementation
5.3 Simulation results
5.4 Conclusion
6. Simplified Deep Forest Regression with Combined Feature Selection and Residual Error Fitting
6.1 Method strategy
6.2 Method implementation
6.3 Simulation results
6.4 Conclusion
7. Online Fuzzy Broad Forest Regression
7.1 Method strategy
7.2 Method implementation
7.3 Experimental Results
7.4 Conclusion References Appendix
- Edition: 1
- Published: November 1, 2025
- Language: English
WY
Wen Yu
Wen Yu received the B.S. degree from Tsinghua University, Beijing, China in 1990 and the M.S. and Ph.D. degrees, both in Electrical Engineering, from Northeastern University, Shenyang, China, in 1992 and 1995, respectively. Since 1996, he has been with the National Polytechnic Institute (CINVESTAV-IPN), Mexico City, Mexico, where he is currently a professor and department chair of the Automatic Control Department. From 2002 to 2003, he held research positions with the Mexican Institute of Petroleum. He was a Senior Visiting Research Fellow with Queen’s University Belfast, Belfast, U.K., from 2006 to 2007, and a Visiting Associate Professor with the University of California, Santa Cruz, from 2009 to 2010. He gas published more than 100 research papers in reputed journals. His Google Scholar h-index is 33, the citation number is 4100. He serves as associate editors of IEEE Transactions on Cybernetics, Neurocomputing, and Journal of Intelligent and Fuzzy Systems. He is a member of the Mexican Academy of Sciences.
Affiliations and expertise
Professor and Department Chair, Automatic Control Department, National Polytechnic Institute (CINVESTAV-IPN), Mexico City, MexicoJT
Jian Tang
Jian Tang received a Ph.D. degree in control theory and control engineering from Northeastern University, China, in 2012. He is currently a Professor with the Faculty of Information Technology, Beijing University of Technology, Beijing, China. His current research interests include machine learning based on small sample data, intelligent modeling and control of complex industrial process, digital twin system of municipal solid waste incineration process.
Affiliations and expertise
Beijing University of Technology, ChinaJQ
Junfei Qiao
Junfei Qiao received B.S. and M.S. degrees in control engineering from Liaoning Technical University, China, in 1992 and 1995, respectively, and a Ph.D. degree in control theory and control engineering from Northeastern University, China, in 1998. He is currently a Professor with the Faculty of Information Technology, Beijing University of Technology, China. His current research interests include neural networks, intelligent systems, and modeling and optimal control of complex industrial processes.
Affiliations and expertise
Beijing University of Technology, China