Chipless Rfid Systems Using Advanced Artificial Intelligence

his book shows you how to develop a hybrid mm-wave chipless Radio Frequency Identification (RFID) system, which includes chipless tag, reader hardware, and detection algorithm that use image processing and machine learning (ML) techniques. It provides the background and information you need to apply the concepts of Artificial Intelligence (AI) into detection and chipless tag signature printable on normal plastic substrates, instead of the conventional peak/nulls in the frequency tags. You'll learn how to incorporate new AI detection techniques along with cloud computing to lower costs. You'll also be shown a cost-effective means of image construction, which can lower detection errors. The book focuses on side-looking-aperture-radar (SLAR) with a combination of deep learning to provide a much safer means of chipless detection than the current inverse synthetic-aperture radar (iSAR) techniques. Each chapter includes practical examples of design, and a QA section to answer the possible doubts in simpler phrases. With its emphasis on mm-wave band and the practical side of design and engineering of the chipless tags, reader, and detection algorithms, this is an excellent resource for industry engineers, design engineers and university researchers. Chipless RFID Systems Using Advanced Artificial Intelligence Contents Preface 1 Introduction 1.1 Overview Model of RFID 1.2 Different Types of RFID 1.3 Different Types of Chipless RFID 1.4 Market Aspects for Chipless RFID 1.5 RFID Frequency Spectrum 1.6 Challenges in Implementing Chipless RFID in the mm-Wave Spectrum 1.7 Book Outline References 2 Chipless Tag Design 2.1 Introduction 2.2 Chipless RFID Tags 2.2.1 Time-Domain Tags 2.2.2 Frequency-Domain Tags 2.2.3 Image-Based Tags 2.2.4 Letter-Based Tags 2.2.5 Screen Printing for the Chipless Tags 2.2.6 Screen Printing Experimental Observations 2.3 Letter-Based Tag Design 2.3.1 Effect of Substrate on Backscattered Signal 2.3.2 Encoding Capacity Considerations 2.3.3 Tag Design Based on the Peyote Alphabet 2.3.4 Peyote Tag Frequency Response 2.4 Backscattering Theory and RCS Calculations 2.5 Tag Performance Simulations 2.5.1 Tag Design Improvement 2.5.2 Discussion of the Results 2.6 Tag Response Measurements 2.7 Conclusions 2.8 Tag Design Questions and Answers References 3 Chipless Reader Design 3.1 Introduction 3.2 Chipless RFID Readers 3.2.1 Frequency-Based Readers 3.2.2 Image-Based Readers 3.3 A 60-GHz System Block Diagram 3.3.1 Maximum Reader Power and Link Budget Calculations 3.3.2 Maximum Reading Distance Calculations 3.4 60-GHz TX/RX Boards 3.5 Designing and Integration: RF, IF, Controller, and Peripheral Circuits 3.5.1 60-GHz Transmitter/Receiver 3.5.2 Local Voltage-Controlled Oscillator 3.5.3 Gain/Phase Comparator 3.5.4 Digital Control Board 3.5.5 Peripheral Circuits 3.6 Reader Characterization 3.6.1 Scanning Time and Frequency Resolution Calculations 3.6.2 RCS Calibrations 3.7 Conclusions 3.8 Chipless Reader Questions and Answers References 4 Tag Decoding 4.1 Introduction 4.2 Machine Learning and Pattern Recognition 4.2.1 Tag Decoding Using Feedforward Networks and Backpropagation 4.2.2 Feedforward Concept 4.2.3 Support Vector Machines 4.2.4 KNN as a Lazy Learner 4.2.5 Decision Trees Ensembles 4.2.6 Deep Learning Methods and Frameworks 4.2.7 Machine Learning in Chipless RFID and the Gaps 4.3 Data Collection Methodology 4.3.1 Data Collection in the Simulations 4.3.2 Data Collection in the Experiments 4.4 Using Feedforward Networks 4.4.1 Feedforward Network Results 4.5 Using Pattern Recognition Methods 4.5.1 Pattern Recognizer Results 4.6 Using CW-SLAR Imaging 4.6.1 One-Port VNA 4.6.2 Two-Port Reader 4.6.3 Computational Costs 4.6.4 Tag Imaging and Experimental Results 4.7 A Reliable Tag Decoder Architecture 4.8 Conclusions 4.9 Chipless Tag Decoding Questions and Answers References 5 Cloud-Based Deep Learning 5.1 Introduction 5.2 Cloud Computing Considerations 5.2.1 Cloud Computing Challenges 5.3 Cloud Computing Hardware Architecture 5.3.1 IaaS Model 5.3.2 SaaS Model 5.4 Deep Learner in Action 5.4.1 2-D Image Representation of 1-D Frequency Data 5.4.2 Data Augmentation 5.4.3 Deep Learner Structure 5.4.4 Deep Learning Results 5.5 A Reliable Reader Based on Cloud Deep Learning 5.6 Conclusions 5.7 Cloud-Based Deep Learning Questions and Answers References 6 Conclusions 6.1 Conclusions 6.2 Fulfilling Research Goals 6.3 Recommendations for Future Work References Appendix ACode Listing Appendix BPCB Layout List of Acronyms About the Authors Index