Machine Learning Techniques for VLSI Chip Design

Cover
Title Page
Copyright Page
Contents
List of Contributors
Preface
Chapter 1 Applications of VLSI Design in Artificial Intelligence and Machine Learning
	1.1 Introduction
	1.2 Artificial Intelligence
	1.3 Artificial Intelligence & VLSI (AI and VLSI)
	1.4 Applications of AI
	1.5 Machine Learning
	1.6 Applications of ML
		1.6.1 Role of ML in Manufacturing Process
		1.6.2 Reducing Maintenance Costs and Improving Reliability
		1.6.3 Enhancing New Design
	1.7 Role of ML in Mask Synthesis
	1.8 Applications in Physical Design
		1.8.1 Lithography Hotspot Detection
		1.8.2 Pattern Matching Approach
	1.9 Improving Analysis Correlation
	1.10 Role of ML in Data Path Placement
	1.11 Role of ML on Route Ability Prediction
	1.12 Conclusion
	References
Chapter 2 Design of an Accelerated Squarer Architecture Based on Yavadunam Sutra for Machine Learning
	2.1 Introduction
	2.2 Methods and Methodology
		2.2.1 Design of an n-Bit Squaring Circuit Based on (n-1)-Bit Squaring Circuit Architecture
			2.2.1.1 Architecture for Case 1: A < B
			2.2.1.2 Architecture for Case 2: A > B
			2.2.1.3 Architecture for Case 3: A = B
	2.3 Results and Discussion
	2.4 Conclusion
	References
Chapter 3 Machine Learning–Based VLSI Test and Verification
	3.1 Introduction
	3.2 The VLSI Testing Process
		3.2.1 Off-Chip Testing
		3.2.2 On-Chip Testing
		3.2.3 Combinational Circuit Testing
			3.2.3.1 Fault Model
			3.2.3.2 Path Sensitizing
		3.2.4 Sequential Circuit Testing
			3.2.4.1 Scan Path Test
			3.2.4.2 Built-In-Self Test (BIST)
			3.2.4.3 Boundary Scan Test (BST)
		3.2.5 The Advantages of VLSI Testing
	3.3 Machine Learning’s Advantages in VLSI Design
		3.3.1 Ease in the Verification Process
		3.3.2 Time-Saving
		3.3.3 3Ps (Power, Performance, Price)
	3.4 Electronic Design Automation (EDA)
		3.4.1 System-Level Design
		3.4.2 Logic Synthesis and Physical Design
		3.4.3 Test, Diagnosis, and Validation
	3.5 Verification
	3.6 Challenges
	3.7 Conclusion
	References
Chapter 4 IoT-Based Smart Home Security Alert System for Continuous Supervision
	4.1 Introduction
	4.2 Literature Survey
	4.3 Results and Discussions
		4.3.1 Raspberry Pi-3 B+Module
		4.3.2 Pi Camera
		4.3.3 Relay
		4.3.4 Power Source
		4.3.5 Sensors
			4.3.5.1 IR & Ultrasonic Sensor
			4.3.5.2 Gas Sensor
			4.3.5.3 Fire Sensor
			4.3.5.4 GSM Module
			4.3.5.5 Buzzer
			4.3.5.6 Cloud
			4.3.5.7 Mobile
	4.4 Conclusions
	References
Chapter 5 A Detailed Roadmap from Conventional-MOSFET to Nanowire-MOSFET
	5.1 Introduction
	5.2 Scaling Challenges Beyond 100nm Node
	5.3 Alternate Concepts in MOFSETs
	5.4 Thin-Body Field-Effect Transistors
		5.4.1 Single-Gate Ultrathin-Body Field-Effect Transistor
		5.4.2 Multiple-Gate Ultrathin-Body Field-Effect Transistor
	5.5 Fin-FET Devices
	5.6 GAA Nanowire-MOSFETS
	5.7 Conclusion
	References
Chapter 6 Gate All Around MOSFETs-A Futuristic Approach
	6.1 Introduction
	6.1.1 Semiconductor Technology: History
	6.2 Importance of Scaling in CMOS Technology
		6.2.1 Scaling Rules
		6.2.2 The End of Planar Scaling
		6.2.3 Enhance Power Efficiency
		6.2.4 Scaling Challenges
			6.2.4.1 Poly Silicon Depletion Effect
			6.2.4.2 Quantum Effect
			6.2.4.3 Gate Tunneling
		6.2.5 Horizontal Scaling Challenges
			6.2.5.1 Threshold Voltage Roll-Off
			6.2.5.2 Drain Induce Barrier Lowering (DIBL)
			6.2.5.3 Trap Charge Carrier
			6.2.5.4 Mobility Degradation
	6.3 Remedies of Scaling Challenges
		6.3.1 By Channel Engineering (Horizontal)
			6.3.1.1 Shallow S/D Junction
			6.3.1.2 Multi-Material Gate
		6.3.2 By Gate Engineering (Vertical)
			6.3.2.1 High-K Dielectric
			6.3.2.2 Metal Gate
			6.3.2.3 Multiple Gate
	6.4 Role of High-K in CMOS Miniaturization
	6.5 Current Mosfet Technologies
	6.6 Conclusion
	References
Chapter 7 Investigation of Diabetic Retinopathy Level Based on Convolution Neural Network Using Fundus Images
	7.1 Introduction
	7.2 The Proposed Methodology
	7.3 Dataset Description and Feature Extraction
		7.3.1 Depiction of Datasets
		7.3.2 Preprocessing
		7.3.3 Detection of Blood Vessels
		7.3.4 Microaneurysm Detection
	7.4 Results and Discussions
	7.5 Conclusions
	References
Chapter 8 Anti-Theft Technology of Museum Cultural Relics Using RFID Technology
	8.1 Introduction
	8.2 Literature Survey
	8.3 Software Implementation
	8.4 Components
		8.4.1 Arduino UNO
		8.4.2 EM18 Reader Module
		8.4.3 RFID Tag
		8.4.4 LCD Display
		8.4.5 Sensors
			8.4.5.1 Fire Sensor
			8.4.5.2 IR Sensor
		8.4.6 Relay
	8.5 Working Principle
		8.5.1 Working Principle
	8.6 Results and Discussions
	8.7 Conclusions
	References
Chapter 9 Smart Irrigation System Using Machine Learning Techniques
	9.1 Introduction
	9.2 Hardware Module
		9.2.1 Soil Moisture Sensor
		9.2.2 LM35-Temperature Sensor
		9.2.3 POT Resistor
		9.2.4 BC-547 Transistor
		9.2.5 Sounder
		9.2.6 LCD 16x2
		9.2.7 Relay
		9.2.8 Push Button
		9.2.9 LED
		9.2.10 Motor
	9.3 Software Module
		9.3.1 Proteus Tool
		9.3.2 Arduino Based Prototyping
	9.4 Machine Learning (Ml) Into Irrigation
	9.5 Conclusion
	References
Chapter 10 Design of Smart Wheelchair with Health Monitoring System
	10.1 Introduction
	10.2 Proposed Methodology
	10.3 The Proposed System
	10.4 Results and Discussions
	10.5 Conclusions
	References
Chapter 11 Design and Analysis of Anti-Poaching Alert System for Red Sandalwood Safety
	11.1 Introduction
	11.2 Various Existing Proposed Anti-Poaching Systems
	11.3 System Framework and Construction
	11.4 Results and Discussions
	11.5 Conclusion and Future Scope
	References
Chapter 12 Tumor Detection Using Morphological Image Segmentation with DSP Processor TMS320C6748
	12.1 Introduction
	12.2 Image Processing
		12.2.1 Image Acquisition
		12.2.2 Image Segmentation Method
	12.3 TMS320C6748 DSP Processor
	12.4 Code Composer Studio
	12.5 Morphological Image Segmentation
		12.5.1 Optimization
	12.6 Results and Discussions
	12.7 Conclusions
	References
Chapter 13 Design Challenges for Machine/Deep Learning Algorithms
	13.1 Introduction
	13.2 Design Challenges of Machine Learning
		13.2.1 Data of Low Quality
		13.2.2 Training Data Underfitting
		13.2.3 Training Data Overfitting
		13.2.4 Insufficient Training Data
		13.2.5 Uncommon Training Data
		13.2.6 Machine Learning Is a Time-Consuming Process
		13.2.7 Unwanted Features
		13.2.8 Implementation is Taking Longer Than Expected
		13.2.9 Flaws When Data Grows
		13.2.10 The Model’s Offline Learning and Deployment
		13.2.11 Bad Recommendations
		13.2.12 Abuse of Talent
		13.2.13 Implementation
		13.2.14 Assumption are Made in the Wrong Way
		13.2.15 Infrastructure Deficiency
		13.2.16 When Data Grows, Algorithms Become Obsolete
		13.2.17 Skilled Resources are Not Available
		13.2.18 Separation of Customers
		13.2.19 Complexity
		13.2.20 Results Take Time
		13.2.21 Maintenance
		13.2.22 Drift in Ideas
		13.2.23 Bias in Data
		13.2.24 Error Probability
		13.2.25 Inability to Explain
	13.3 Commonly Used Algorithms in Machine Learning
		13.3.1 Algorithms for Supervised Learning
		13.3.2 Algorithms for Unsupervised Learning
		13.3.3 Algorithm for Reinforcement Learning
	13.4 Applications of Machine Learning
		13.4.1 Image Recognition
		13.4.2 Speech Recognition
		13.4.3 Traffic Prediction
		13.4.4 Product Recommendations
		13.4.5 Email Spam and Malware Filtering
	13.5 Conclusion
	References
About the Editors
Index
EULA