Cover Image

Intelligent Secure Trustable Things.

Bibliographic Details
Main Author: Karner, Michael.
Other Authors: Peltola, Johannes., Jerne, Michael., Kulas, Lukas., Priller, Peter.
Format: eBook
Language:English
Published: Cham : Springer International Publishing AG, 2024.
Edition:1st ed.
Series:Studies in Computational Intelligence Series
Subjects:
Electronic books.
Online Access:Click to View
Table of Contents:
  • Intro
  • Acknowledgements
  • Contents
  • Contributors
  • Abbreviations
  • Introduction
  • Going to the Edge: Bringing Artificial Intelligence and Internet of Things Together
  • 1 Introduction
  • 2 Objectives
  • 3 Trustworthiness
  • 4 Building on a Sound Basis
  • 5 Driven Through Industrial Applications
  • 6 Building Technology for Intelligent, Secure, Trustworthy Things
  • 7 Reference Architecture for Trustworthy AIoT
  • 8 Summary
  • References
  • The Development of Ethical and Trustworthy AI Systems Requires Appropriate Human-Systems Integration
  • 1 Is Trustworthiness of AI a Problem?
  • 2 Current Initiatives to Address Trustworthiness of AI
  • 2.1 Guidelines and Regulations
  • 2.2 Implementation Support
  • 2.3 Observed Gaps in Current Initiatives
  • 3 From Technology-Centered to Human-Centered Development of Smart Technologies
  • 3.1 Orchestrating the Development of Ethical and Trustworthy AI
  • 4 Conclusions
  • References
  • The InSecTT Reference Architecture
  • 1 Introduction
  • 2 AI in IoT Architectures
  • 3 Overview of the InSecTT Architecture
  • 3.1 Evolution of the Bubble
  • 3.2 Modern Reference Architectures
  • 4 Entity Model
  • 5 Layered Model
  • 5.1 Level 0
  • 5.2 Level 1
  • 5.3 Level 2
  • 5.4 Hardware Interfaces
  • 6 Domain Model
  • 7 Functionality Model
  • 7.1 SW Interfaces
  • 8 Information Model
  • 9 AI Perspective of the Architecture
  • 10 Example Use Cases Alignment
  • 10.1 Overview
  • 10.2 Entity Model
  • 10.3 Functionality model
  • 10.4 Interfaces
  • 10.5 General Project Overview for Architecture Alignment
  • References
  • Structuring the Technology Landscape for Successful Innovation in AIoT
  • 1 Motivation
  • 2 How to Structure Research and Development to Enact an Ambitious Project Vision
  • 3 Requirements and Constraints
  • 4 Requirement Engineering Process
  • 5 Navigating the Landscape: Planning R&amp
  • D Work.
  • 6 External Alignment
  • 7 Documenting Scope, Work and Results
  • 8 Progress Assessment and Validation
  • 9 Demonstrators
  • 10 Preparing for Market: Exploitation
  • 11 InSecTT Exploitation Board (EB)
  • 12 Use Case Marketplace
  • 13 Open Innovation
  • 14 Publications to Prepare Markets
  • 15 Website and Social Networks
  • 16 Industrial Conferences, Trade Fairs and Podcasts
  • Technology Development
  • InSecTT Technologies for the Enhancement of Industrial Security and Safety
  • 1 Introduction
  • 2 Background
  • 2.1 Industrial Automation and Control Systems
  • 3 Selected InSecTT Technologies Targeting Security and Safety
  • 3.1 Access Control and Authentication Infrastructure
  • 3.2 Intrusion Detection Systems
  • 3.3 Tools, Simulators and Datasets
  • 3.4 Safety and Security Analysis for AGV Platooning
  • 4 Novelty and Applicability of Proposed Technologies
  • 5 Conclusions and Future Perspectives
  • References
  • Algorithmic and Implementation-Based Threats for the Security of Embedded Machine Learning Models
  • 1 Introduction
  • 2 Threat Models
  • 2.1 Formalism
  • 2.2 Adversarial Objectives
  • 2.3 The System Under Attack
  • 2.4 Knowledge and Capacity of an Adversary
  • 2.5 Attack Surface
  • 3 A Panorama of Algorithmic Attacks
  • 3.1 Confidentiality and Privacy Threats
  • 3.2 Integrity-Based Attacks
  • 3.3 Availability
  • 4 A Focus on Physical Attacks
  • 4.1 Model Extraction Based on Side-Channel Analysis
  • 4.2 Weight-Based Adversarial Attacks
  • 5 Protecting ML System
  • 5.1 Embedded Authentication Mechanism
  • 5.2 Main Defenses Against Algorithmic Attacks
  • 5.3 Countermeasures Against Physical Attacks
  • 6 Conclusion
  • References
  • Explainable Anomaly Detection of 12-Lead ECG Signals Using Denoising Autoencoder
  • 1 Introduction
  • 2 Anomaly Detection and Explainability in Deep Learning.
  • 3 Denosisng Autoencoder as an Explainable Anomaly Detection Model for ECGs
  • 3.1 ECG Data Sets
  • 3.2 Model Architecture and Training
  • 3.3 Results of Denoising and the Exploration of the Latent Space
  • 4 Cloud-Based Service and Visualization of Explainable Anomaly Detection on ECGs
  • 5 Conclusion
  • References
  • Indoor Navigation with a Smartphone
  • 1 Introduction
  • 2 Encoding Information in QR
  • 3 Navigation
  • 4 Local to Global Coordinates
  • 5 Triage
  • 6 Future Work
  • 7 Conclusions
  • References
  • Reconfigurable Antennas for Trustable Things
  • 1 Introduction
  • 2 Electronically Steerable Parasitic Array Radiator Antenna for Trustable Things
  • 2.1 Concept
  • 2.2 Design
  • 2.3 Realization
  • 3 Applications
  • 3.1 Direction of Arrival Estimation
  • 3.2 Power Pattern Cross-Correlation Algorithm
  • 3.3 Interpolation-Based Estimation
  • 3.4 Multiplane Calibration for 2D DoA Estimation
  • 3.5 DoA-Based Object Positioning
  • 3.6 Single-Anchor Positioning System
  • 3.7 Calibration-Free Indoor Localization
  • 3.8 Other Applications
  • References
  • AI-Enhanced Connection Management for Cellular Networks
  • 1 Introduction
  • 2 Related Work
  • 2.1 Data Rate Estimation
  • 2.2 Interface Selection
  • 3 Use Case and Research Challenge
  • 4 Data Collection and Analysis
  • 5 Uplink Data Rate Estimation
  • 6 Interface Decision
  • 7 Conclusion
  • References
  • Vehicle Communication Platform to Anything-VehicleCAPTAIN
  • 1 Introduction
  • 2 Problem Statement
  • 3 VehicleCAPTAIN-A V2X Platform for Research and Development
  • 3.1 The Platform
  • 3.2 Message Library
  • 3.3 ROS2 Support
  • 4 Verification
  • 4.1 Test Methodology
  • 4.2 Results
  • 4.3 Discussion
  • 5 Key Performance Indicators
  • 5.1 Use Cases Within InSecTT
  • 5.2 Use Cases Within the Virtual Vehicle Research GmbH
  • 6 Conclusion
  • References.
  • AI-Enhanced UWB-Based Localisation in Wireless Networks
  • 1 Introduction
  • 2 Method Overview
  • 3 AI for Solving UWB-Based Localisation Challenges
  • 3.1 Localisation Challenges
  • 3.2 AI Algorithms in UWB-Based Localisation Systems
  • 4 Overview of Related Work
  • 5 Application Example
  • 5.1 KNN for LOS/NLOS Detection
  • 5.2 KNN for Error Mitigation and Trustworthiness
  • 6 Conclusion
  • References
  • Industrial Applications
  • Approaches for Automating Cybersecurity Testing of Connected Vehicles
  • 1 Introduction
  • 2 State of the Art and Related Work
  • 3 Automotive Cybersecurtiy Lifecycle Management
  • 3.1 Threat Modeling
  • 4 Cybersecurity Testing
  • 4.1 Learning-Based Testing
  • 4.2 Model-Based Test Case Generation
  • 4.3 Testing Platform
  • 4.4 Automated Test Execution
  • 4.5 Fuzzing
  • 5 Conclusion
  • References
  • Solar-Based Energy Harvesting and Low-Power Wireless Networks
  • 1 Introduction
  • 1.1 Solar-Based Energy Harvesting
  • 2 Low-Power Network Protocols
  • 2.1 Bluetooth Low Energy
  • 2.2 IEEE 802.15.4 and Thread
  • 2.3 EPhESOS Protocol
  • 2.4 UWB Localisation
  • 3 Power Consumption in Different Scenarios
  • 3.1 Measurement Setup and Hardware
  • 3.2 Power Consumption with Increasing Update Period
  • 4 Available Energy in Real-World Scenarios
  • 5 Experimental Results
  • 6 Conclusion
  • References
  • Location Awareness in HealthCare
  • 1 Terminology and Technology
  • 1.1 Positioning, Localization, Tracking and Navigation
  • 1.2 RF-Based Indoor Localization Technologies
  • 1.3 Non-RF Based Localization Technologies
  • 2 Pedestrian Dead Reckoning (PDR)
  • 3 Others
  • 3.1 Outdoor Localization Technologies
  • 3.2 Technology Overview
  • 4 Designing an End-To-End IoT Solution
  • 4.1 Commissioning
  • 4.2 Low Power Wide Area Networks (LPWAN)
  • 4.3 Battery Lifetime
  • 4.4 Going from Indoor to Outdoor
  • 4.5 APIs for Location Services.
  • 4.6 Visualizing on a Map
  • 4.7 Security and Privacy Aspects
  • 5 Healthcare Use-Cases
  • 5.1 Asset Tracking
  • 5.2 Mass Casualty Incident (MCI)
  • 5.3 Bed Management
  • 5.4 Hospital Wayfinding
  • 6 Use-Case Concept Demonstrator
  • 6.1 Architecture
  • 6.2 GeoJSON Server
  • 6.3 Client Authentication
  • 6.4 FHIR Compatibility
  • 6.5 Location and Privacy
  • 6.6 Additional Features
  • 7 Conclusions/Next Steps
  • References
  • Driver Distraction Detection Using Artificial Intelligence and Smart Devices
  • 1 Introduction
  • 2 Definitions and Background
  • 3 System Design
  • 4 Machine Learning-Based Components
  • 4.1 Use Case Definition and Components' Architecture
  • 4.2 Data Acquisition and Pre-processing
  • 4.3 Machine Learning Model Training and Experimental Results
  • 4.4 Model Deployment on Smart Devices
  • 5 Dashboard Application for Driver Distraction
  • 6 Related Work
  • 7 Conclusion and Future Work
  • References
  • Working with AIoT Solutions in Embedded Software Applications. Recommendations, Guidelines, and Lessons Learned
  • 1 Introduction
  • 2 Project Description and Goals
  • 3 Project Design
  • 4 Machine Learning in Embedded Systems
  • 5 Communication Platform
  • 5.1 Design Layout
  • 5.2 Message Queuing with RabbitMQ
  • 5.3 Inter-Process Messaging
  • 6 Data Extraction
  • 7 Training Data Set and Model
  • 7.1 Design Stage 1
  • 7.2 Design Stage 2
  • 7.3 Alternative Model Setup
  • 8 Cloud or Edge?
  • 9 Security
  • 10 Conclusion
  • Appendix A
  • Appendix B
  • References
  • Artificial Intelligence for Wireless Avionics Intra-Communications
  • 1 Introduction
  • 2 Use Case Objectives
  • 3 Link Between Scenarios and Building Blocks
  • 4 State of the Art
  • 5 AI/IoT Added Value
  • 6 Scenarios
  • 6.1 Scenario 1: Interference Detection and Cancellation
  • 6.2 Scenario 2: Verification and Validation of WAICs
  • 6.3 Scenario 3: Battery-Less Devices.
  • 7 Performance Evaluation.

Similar Items