Artificial Intelligence for Fashion Industry in the Big Data Era (eBook)

Sébastien Thomassey, Xianyi Zeng (Herausgeber)

eBook Download: PDF

2018
X, 288 Seiten
Springer Singapore (Verlag)
978-981-13-0080-6 (ISBN)

Infos

This book provides an overview of current issues and challenges in the fashion industry and an update on data-driven artificial intelligence (AI) techniques and their potential implementation in response to those challenges. Each chapter starts off with an example of a data-driven AI technique on a particular sector of the fashion industry (design, manufacturing, supply or retailing), before moving on to illustrate its implementation in a real-world application

Sébastien Thomassey (PhD) is currently associate professor at the 'Ecole Supérieure des Arts et Industries Textiles' (ENSAIT) and the GEMTEX laboratory. He gained an MSc(Eng.) in textile and clothing production from the ENSAIT in 1999, an MSc in advanced data analysis from the Lille I University in 1999 and a PhD in automation and information technology from the Lille I University in 2002. He was an engineer in R&D at the French technical center for the textile/clothing, IFTH, from 1999 to 2002 and a researcher at the Mathematic and Operational Research Laboratory of the Polytechnic Institute of Mons in Belgium in 2003. His research is mainly focused on the implementation of soft computing and data mining techniques for modeling, simulation, supply and production chain optimization, forecasting sales of clothing products, clustering, classification and decision support systems for textile/apparel industry. His work has been published in refereed journals, such as Applied Soft Computing, Decision Support Systems, European Journal of Operational Research, and the International Journal of Production Economics,. He is actively involved in research projects in production and supply chain management, sales forecasting and clustering/classification of fashion products.

 

He has also participated in various European and national research projects related to sustainable textile design and management, simulation and optimization of manufacturing units, clustering and classification of 3D morphologies for intelligent sizing systems, and sales-forecast-based simulation in pricing strategy.

X.Y. Zeng received the B.Eng. degree from the Department of Science and Technology, Tsinghua University, Beijing, China, in 1986, and the Ph.D. degree from the Centre d'Automatique, Université des Sciences et Technologies de Lille, Villeneuve d'Ascq, France, in 1992. He is currently a Full Professor with the French Engineer School, Ecole Nationale Supérieure des Arts et Industries Textiles (ENSAIT), Roubaix, France. Since 2000, he has led the Human-Centered Design research team in ENSAIT. He has published two scientific books, more than 260 papers at reviewed international journals, and international conference proceedings. His research interests include: 1) intelligent decision support systems for fashion and material design, 2) modeling of human perception and cognition on industrial products, 3) intelligent wearable systems.

Dr. Zeng is currently an Associate Editor of International Journal of Computational Intelligence System and Journal of Fiber Bioengineering and Informatics, a Guest Editor of Special Issues for six international journals, and a senior member of IEEE. He has organized 12 international conferences and workshops since 1996. Since 2000, he has been the leader of three European projects, four national research projects funded by the French government, three bilateral research cooperation projects, and more than 20 industrial projects.

Inhalt

Preface 6
Contents 9
Introduction: Artificial Intelligence for Fashion Industry in the Big Data Era 11
References 16
Part I AI for Fashion Sales Forecasting 17
AI-Based Fashion Sales Forecasting Methods in Big Data Era 18
1 Introduction 18
2 AI-Based Fashion Sales Forecasting Methods 20
2.1 ANN and ELM-Based Methods 20
2.2 Fuzzy Logic-Based Methods 21
2.3 Support Vector Machines (SVMs) 21
3 Application of Big Data in Fashion Industry 22
4 AI-Based Fashion Sales Forecasting Methods in Big Data Era 23
4.1 Data Filtering 24
4.2 Feature Extraction 26
4.3 Data Training 27
4.4 Forecast Output 30
5 Conclusion 31
References 32
Enhanced Predictive Models for Purchasing in the Fashion Field by Applying Regression Trees Equipped with Ordinal Logistic Regression 36
1 Introduction 37
2 Related Work 38
3 Ordinal Logistic Regression (OLR) 39
3.1 Evaluation 41
4 Regression Trees 42
5 Algorithm 43
6 Experiments 47
6.1 Datasets 47
6.2 Experimental Setup and Evaluation 48
6.3 Results 49
6.4 Tree Illustration 51
7 Concluding Remarks 52
References 53
A Data Mining-Based Framework for Multi-item Markdown Optimization 55
1 Introduction 55
2 Grouping-Related Items 57
2.1 Associated Group Heuristic 59
2.2 k-Means Clustering 60
2.3 Constrained Clustering 61
3 Multiple Forecasts in Retail 63
4 Deterministic Dynamic Pricing Model 65
5 Empirical Study 67
5.1 Finding-Related Item Groups 68
5.2 Conducting Multivariate Regression Analysis Within Item Groups 70
5.3 Implementing Deterministic Multi-item Markdown Optimization Model 72
6 Concluding Remarks 74
References 76
Social Media Analytics for Decision Support in Fashion Buying Processes 79
1 Introduction 80
2 Theoretical Background 81
2.1 Social Media 82
2.2 Text Mining 84
3 Research Approach: Topic Detection and Tracking in Fashion Blogs 87
4 Results on Experimental Analyses of Fashion Blogs 94
4.1 Topic Detection—Single Colour Occurrences 94
4.2 Topic Detection—Co-occurred Colour Occurrences 96
4.3 Topic Tracking of Fashion Topics 96
5 Buyers Perspective—Discussion 98
6 Conclusion and Outlook 99
References 100
Part II AI for Textile Apparel Manufacturing and Supply Chain 102
Review of Artificial Intelligence Applications in Garment Manufacturing 103
1 Introduction 103
2 Applications of AI to Production Planning, Control, and Scheduling 105
2.1 Production Order Scheduling 105
2.2 Cut-Order Planning 106
2.3 Marker Making 107
2.4 Fabric Spreading and Cutting Schedules 108
2.5 Assembly-Line Balancing 110
2.6 Machine Layout Design 112
3 Garment Quality Control and Inspection 113
3.1 Seam and Fabric Sewing Performance 113
3.2 Sewing Automation Equipment 114
3.3 Assessing Seam Pucker 116
3.4 Detecting and Classifying Garments Defects 117
3.5 Dimensional Change Issue 119
4 Garment Quality Evaluation 119
4.1 Clothing Sensory Comfort 120
4.2 Clothing Thermal Properties 121
4.3 Garment Appearance Quality 122
5 Challenges Facing Adoption of AI Techniques in Clothing Industry 123
6 Conclusion 124
References 125
AI for Apparel Manufacturing in Big Data Era: A Focus on Cutting and Sewing 130
1 Introduction 130
2 Apparel Manufacturing Process 132
2.1 Cutting 133
2.2 Sewing 134
2.3 Finishing and Packing 136
3 Applications of the AI-Related Approaches 136
3.1 Literature Review Analysis 136
3.2 AI-Related Approaches Analysis 140
3.3 Conclusion 147
4 New Perspectives 150
References 153
A Discrete Event Simulation Model with Genetic Algorithm Optimisation for Customised Textile Production Scheduling 157
1 Introduction 157
2 State of the Art 159
2.1 Simulation in Manufacturing and Textile Production 159
2.2 Scheduling and Optimisation by Genetic Algorithm 160
2.3 Hybrid Model Integrating a Discrete Event Simulation Model with an Optimisation Model 162
3 Methodology 163
3.1 Description of the Manufacturing Unit 163
3.2 Production Parameters, Constraints and Simulation Logic 165
4 Experimentation and Results 168
4.1 Results Obtained from Before Optimisation 168
4.2 GA Hybrid Model Optimisation Results 169
4.3 Results Obtained from the Best Sequence by GA Hybrid Model 171
4.4 Discussion 172
5 Conclusion and Scope 173
References 173
An Intelligent Fashion Replenishment System Based on Data Analytics and Expert Judgment 176
1 Introduction 176
2 Literature Review 177
3 Methodology and Implementation 179
3.1 Notation 181
3.2 Extra Features of the Proposal 185
3.3 Internal Marketplace 186
3.4 Optimal Allocation 188
4 Pilot Study and Results 191
4.1 Test Impact Evaluation 192
5 Conclusions 196
References 198
Blockchain-Based Secured Traceability System for Textile and Clothing Supply Chain 199
1 Introduction 199
2 Understanding T& C Supply Chain
3 Traceability 201
4 What Is Blockchain and How It Differs from Regular Digital Ledger? 203
5 Traceability in the T& C Supply Chain and Blockchain
6 Use Case Example 205
7 Limitations of Blockchain-Based Traceability System 207
8 Conclusions 209
References 209
Part III AI for Garment Design and Comfort 211
Artificial Intelligence Applied to Multisensory Studies of Textile Products 212
1 Novel Sensory Methodologies for Fabric Hand Study 212
2 Prediction of Emotional Preference from Fabric Tactile Properties Based on a Fuzzy-Genetic Model 214
2.1 Sensory Experiments on Suiting Fabrics 215
2.2 Predictive Model Based on a Fuzzy-Genetic Algorithm 217
3 Visuo-haptic Perception of Fabric Tactile Properties Based on a Fuzzy Inclusion Approach 227
3.1 Consistency Between Visual and Haptic Perception of Fabric Tactile Properties 227
3.2 Visual Interpretation of Fabric Tactile Properties 236
4 General Conclusion 242
References 244
Evaluation of Fashion Design Using Artificial Intelligence Tools 246
1 Introduction 246
2 Experimental Work 247
2.1 Experiment I Production Pattern Design and 3D Virtual Try-on 248
2.2 Experiment II Evaluation and Adjustment of the 3D Try-on Perception 250
3 Results and Discussion 255
4 Conclusions 256
Bibliography 256
Garment Wearing Comfort Analysis Using Data Mining Technology 258
1 Introduction 258
2 Method 260
2.1 Action Design for Measuring Clothing Pressures 260
2.2 Measurement of Clothing Pressures 261
3 Results and Discussion 262
3.1 Data Preprocessing and Analysis 262
3.2 Factor Analysis 263
3.3 Wearing Comfort Analysis on Different Human Body Parts 266
3.4 Limitation 269
4 Conclusions and Prospects 270
References 271
Garment Fit Evaluation Using Machine Learning Technology 273
1 Introduction 274
2 General Principle and Formalization 276
2.1 General Principle 276
2.2 Formalization of the Concepts and Data 277
3 Learning Data Acquisition 278
3.1 Preparation Work for Experiments 278
3.2 Experiment I: Acquisition of the Data on Garment Fit 279
3.3 Experiment II: Acquisition of the Data on Digital Clothing Pressures 280
4 Modeling the Relation Between Clothing Pressures and Garment Fit Level 281
5 Model Validation 282
6 Discussion 283
6.1 Influence of the Difference Between Real and Digital Pressures on the Prediction Results 283
6.2 Application Prospect 283
6.3 Limitation and Future Research 284
7 Conclusion 285
References 285
15 Erratum to: Artificial Intelligence for Fashion Industry in the Big Data Era 289
Erratum to:& #6

Produkt-Details

• Erscheint lt. Verlag: 16.5.2018
• Reihe/Serie: Springer Series in Fashion Business
• Reihe/Serie: Springer Series in Fashion Business
• Zusatzinfo: X, 288 p. 81 illus., 33 illus. in color.
• Verlagsort: Singapore
• Sprache: englisch
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Technik
• Themenwelt: Wirtschaft ► Betriebswirtschaft / Management ► Marketing / Vertrieb
• Schlagworte: Artificial intelligence in fashion industry • Artificial intelligence in fashion retailing • Decision making in apparel supply chain • Decision support system for garment industry • Intelligent systems for apparel industry • textile engineering
• ISBN-10: 981-13-0080-1 / 9811300801
• ISBN-13: 978-981-13-0080-6 / 9789811300806