Machine learning framework for analyzing last planner system (NEC) (Softcopy is also available)
Ambasana, Hetvi (PCM21135)
Machine learning framework for analyzing last planner system (NEC) (Softcopy is also available) - 2023 - xviii,73p.
TABLE OF CONTENTS
ABSTRACT i
UNDERTAKING iii
CERTIFICATE v
ACKNOWLEDGEMENTS vii
ABBREVIATIONS ix
TABLE OF CONTENTS xi
LIST OF FIGURES xv
LIST OF TABLES xvii
CHAPTER-1: INTRODUCTION 1
1.1 Construction Automation in Indian Construction Industry 1
1.2 Current Scenario of Construction Planning 2
1.3 Need of the Study 2
1.4 Research Objective 3
1.5 Scope of the Study 4
1.6 Research Methodology 4
1.7 Research Timeline 5
CHAPTER-2: LITERATURE REVIEW 7
2.1 Lean Management 7
2.2 Lean Construction 8
2.3 Machine Learning 8
2.4 Last Planner System 10
2.5 Application of Machine Learning in Construction Industry 13
2.5.1 Prior studies on application of Machine Learning in Construction 14
2.6 Machine Learning Models 15
2.6.1 Multiple Linear Regression 15
2.6.2 Support Vector Machines (SVM) 16
2.6.3 Artificial Neutral Network (ANN) 16
2.6.4 K-nearest neighbors (KNN) 17
2.6.5 Naïve Bayesian classification algorithms 17
2.6.6 Logistics Regression 17
2.6.7 Decisions Tree 18
2.6.8 Random Forest 18
2.7 Machine Learning and Last Planner System 18
2.8 Research Gap 19
CHAPTER-3: RESEARCH METHODOLODY 21
3.1 Literature Review 21
3.2 Current Industrial Practices 21
3.3 Raw Data Collection 22
3.4 Data Acquisition Model 22
3.5 Data pre-processing and cleaning 23
3.6 Label Encoding 23
3.7 Developing Machine Learning Model 23
3.8 Evaluate and refine the model 23
CHAPTER-4: DATA COLLECTION 25
4.1 Look Ahead Plans 25
4.1.1 Super-Specialty Healthcare Project 25
4.1.2 Medical Education and Research Institute 26
4.2 Constraints Log 27
4.3 Summary 27
CHAPTER-5: DATA ANALYSIS 29
5.1 Data Cleaning and pre-processing 29
5.1.1 Data Cleaning and Pre-processing manually 29
5.1.2 Data Cleaning and Pre-processing by using python code 30
5.2 Constraint Grouping Library 31
5.3 Model Training 33
5.3.1 Model Preparation 35
5.3.2 Machine Learning Model 36
5.3.3 Result 37
5.3.4 Hyperparameter Tuning 37
5.4 Testing the Model 38
5.4.1 Result 39
5.5 Model Evaluation 39
CHAPTER-6: CONCLUSION 43
6.1 Summary 44
6.2 Practical Implications 45
6.3 Theoretical Implications 45
6.4 Limitations of the study 46
6.5 Future scope 46
REFERENCES 49
APPENDIX 55
CEM TH-0432 / AMB
Machine learning framework for analyzing last planner system (NEC) (Softcopy is also available) - 2023 - xviii,73p.
TABLE OF CONTENTS
ABSTRACT i
UNDERTAKING iii
CERTIFICATE v
ACKNOWLEDGEMENTS vii
ABBREVIATIONS ix
TABLE OF CONTENTS xi
LIST OF FIGURES xv
LIST OF TABLES xvii
CHAPTER-1: INTRODUCTION 1
1.1 Construction Automation in Indian Construction Industry 1
1.2 Current Scenario of Construction Planning 2
1.3 Need of the Study 2
1.4 Research Objective 3
1.5 Scope of the Study 4
1.6 Research Methodology 4
1.7 Research Timeline 5
CHAPTER-2: LITERATURE REVIEW 7
2.1 Lean Management 7
2.2 Lean Construction 8
2.3 Machine Learning 8
2.4 Last Planner System 10
2.5 Application of Machine Learning in Construction Industry 13
2.5.1 Prior studies on application of Machine Learning in Construction 14
2.6 Machine Learning Models 15
2.6.1 Multiple Linear Regression 15
2.6.2 Support Vector Machines (SVM) 16
2.6.3 Artificial Neutral Network (ANN) 16
2.6.4 K-nearest neighbors (KNN) 17
2.6.5 Naïve Bayesian classification algorithms 17
2.6.6 Logistics Regression 17
2.6.7 Decisions Tree 18
2.6.8 Random Forest 18
2.7 Machine Learning and Last Planner System 18
2.8 Research Gap 19
CHAPTER-3: RESEARCH METHODOLODY 21
3.1 Literature Review 21
3.2 Current Industrial Practices 21
3.3 Raw Data Collection 22
3.4 Data Acquisition Model 22
3.5 Data pre-processing and cleaning 23
3.6 Label Encoding 23
3.7 Developing Machine Learning Model 23
3.8 Evaluate and refine the model 23
CHAPTER-4: DATA COLLECTION 25
4.1 Look Ahead Plans 25
4.1.1 Super-Specialty Healthcare Project 25
4.1.2 Medical Education and Research Institute 26
4.2 Constraints Log 27
4.3 Summary 27
CHAPTER-5: DATA ANALYSIS 29
5.1 Data Cleaning and pre-processing 29
5.1.1 Data Cleaning and Pre-processing manually 29
5.1.2 Data Cleaning and Pre-processing by using python code 30
5.2 Constraint Grouping Library 31
5.3 Model Training 33
5.3.1 Model Preparation 35
5.3.2 Machine Learning Model 36
5.3.3 Result 37
5.3.4 Hyperparameter Tuning 37
5.4 Testing the Model 38
5.4.1 Result 39
5.5 Model Evaluation 39
CHAPTER-6: CONCLUSION 43
6.1 Summary 44
6.2 Practical Implications 45
6.3 Theoretical Implications 45
6.4 Limitations of the study 46
6.5 Future scope 46
REFERENCES 49
APPENDIX 55
CEM TH-0432 / AMB