Signal Processing to Drive Human-Computer Interaction EEG and eye-controlled interfaces

• Main Authors: Nikolopoulos, Spiros, Kumar, Chandan, Kompatsiaris, Ioannis
• Format: eBook Book
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 2020; Institution of Engineering and Technology (The IET); Institution of Engineering & Technology
• Edition: 1
• Subjects: Biomedical engineering; Electronics; Electronics engineering; General References; Human-computer interaction; Optics & Photonics; Signal and Image Processing & Sensors; Signal processing; Signals & Signal Processing; Software Engineering; TECHNOLOGY & ENGINEERING; electroencephalography; medical signal processing; handicapped aids; gaze tracking; brain-computer interfaces; human computer interaction; visual evoked potentials; multimedia computing; learning (artificial intelligence); patient rehabilitation; home computing

The evolution of eye tracking and brain-computer interfaces has given a new perspective on the control channels that can be used for interacting with computer applications. In this book leading researchers show how these technologies can be used as control channels with signal processing algorithms...

Table of Contents:

• Chapter 1: Introduction -- Part I: Reviewing existing literature on the benefits of BCIs, studying the computer use requirements and modeling the (dis)abilities of people with motor impairment -- Chapter 2: The added value of EEG-based BCIs for communication and rehabilitation of people with motor impairment -- Chapter 3: Brain–computer interfaces in a home environment for patients with motor impairment - the MAMEM use case -- Chapter 4: Persuasive design principles and user models for people with motor disabilities -- -- Part II: Algorithms and interfaces for interaction control through eyes and mind -- Chapter 5: Eye tracking for interaction: adapting multimedia interfaces -- Chapter 6: Eye tracking for interaction: evaluation methods -- Chapter 7: Machine-learning techniques for EEG data -- Chapter 8: BCIs using steady-state visual-evoked potentials -- Chapter 9: BCIs using motor imagery and sensorimotor rhythms -- Chapter 10: Graph signal processing analysis of NIRS signals for brain–computer interfaces -- -- Part III: Multimodal prototype interfaces that can be operated through eyes and mind -- Chapter 11: Error-aware BCIs -- Chapter 12: Multimodal BCIs - the hands-free Tetris paradigm -- Chapter 13: Conclusions --
• Title Page Preface Table of Contents 1. Introduction 2. The Added Value of EEG-Based BCIs for Communication and Rehabilitation of People with Motor Impairment 3. Brain-Computer Interfaces in a Home Environment for Patients with Motor Impairment - The MAMEM Use Case 4. Persuasive Design Principles and User Models for People with Motor Disabilities 5. Eye Tracking for Interaction: Adapting Multimedia Interfaces 6. Eye Tracking for Interaction: Evaluation Methods 7. Machine-Learning Techniques for EEG Data 8. BCIs Using Steady-State Visual-Evoked Potentials 9. BCIs Using Motor Imagery and Sensorimotor Rhythms 10. Graph Signal Processing Analysis of NIRS Signals for Brain-Computer Interfaces 11. Error-Aware BCIs 12. Multimodal BCIs - The Hands-Free Tetris Paradigm 13. Conclusions Index
• 11.5.3 Pragmatic typing protocol -- 11.5.4 Data analysis -- 11.5.5 System adjustment and evaluation -- 11.5.6 Results -- 11.6 Summary -- References -- 12. Multimodal BCIs - the hands-free Tetris paradigm | Elisavet Chatzilari, Georgios Liaros, Spiros Nikolopoulos, and Ioannis Kompatsiaris -- 12.1 Introduction -- 12.2 Gameplay design -- 12.3 Algorithms and associated challenges -- 12.3.1 Navigating with the eyes -- 12.3.2 Rotating with the mind -- 12.3.3 Regulating drop speed with stress -- 12.4 Experimental design and game setup -- 12.4.1 Apparatus -- 12.4.2 Events, sampling and synchronisation -- 12.4.3 EEG sensors -- 12.4.4 Calibration -- 12.5 Data processing and experimental results -- 12.5.1 Data segmentation -- 12.5.2 Offline classification -- 12.5.3 Online classification framework -- 12.6 Summary -- References -- 13. Conclusions | Chandan Kumar, Spiros Nikolopoulos, and Ioannis Kompatsiaris -- 13.1 Wrap-up -- 13.2 Open questions -- 13.3 Future perspectives -- Index
• 6.1.1 Study design -- 6.1.2 Participants -- 6.1.3 Experimental variables -- 6.1.4 Measurements -- 6.2 Evaluation of atomic interactions -- 6.2.1 Evaluation of gaze-based pointing and selection -- 6.2.2 Evaluation of gaze-based text entry -- 6.3 Evaluation of application interfaces -- 6.3.1 Comparative evaluation -- 6.3.2 Feasibility evaluation -- 6.4 Summary -- References -- 7. Machine-learning techniques for EEG data | Vangelis P. Oikonomou, Spiros Nikolopoulos, and Ioannis Kompatsiaris -- 7.1 Introduction -- 7.1.1 What is the EEG signal? -- 7.1.2 EEG-based BCI paradigms -- 7.1.3 What is machine learning? -- 7.1.4 What do you want to learn in EEG analysis for BCI application? -- 7.2 Basic tools of supervised learning in EEG analysis -- 7.2.1 Generalized Rayleigh quotient function -- 7.2.2 Linear regression modeling -- 7.2.3 Maximum likelihood (ML) parameter estimation -- 7.2.4 Bayesian modeling of ML -- 7.3 Learning of spatial filters -- 7.3.1 Canonical correlation analysis -- 7.3.2 Common spatial patterns -- 7.4 Classification algorithms -- 7.4.1 Linear discriminant analysis -- 7.4.2 Least squares classifier -- 7.4.3 Bayesian LDA -- 7.4.4 Support vector machines -- 7.4.5 Kernel-based classifier -- 7.5 Future directions and other issues -- 7.5.1 Adaptive learning -- 7.5.2 Transfer learning and multitask learning -- 7.5.3 Deep learning -- 7.6 Summary -- References -- 8. BCIs using steady-state visual-evoked potentials | Vangelis P. Oikonomou, Elisavet Chatzilari, Georgios Liaros, Spiros Nikolopoulos, and Ioannis Kompatsiaris -- 8.1 Introduction -- 8.2 Regression-based SSVEP recognition systems -- 8.2.1 Multivariate linear regression (MLR) for SSVEP -- 8.2.2 Sparse Bayesian LDA for SSVEP -- 8.2.3 Kernel-based BLDA for SSVEP (linear kernel) -- 8.2.4 Kernels for SSVEP -- 8.2.5 Multiple kernel approach -- 8.3 Results -- 8.4 Summary -- References
• 9. BCIs using motor imagery and sensorimotor rhythms | Kostas Georgiadis, Nikos A. Laskaris, Spiros Nikolopoulos, and Ioannis Kompatsiaris -- 9.1 Introduction to sensorimotor rhythm (SMR) -- 9.2 Common processing practices -- 9.3 MI BCIs for patients with motor disabilities -- 9.3.1 MI BCIs for patients with sudden loss of motor functions -- 9.3.2 MI BCIs for patients with gradual loss of motor functions -- 9.4 MI BCIs for NMD patients -- 9.4.1 Condition description -- 9.4.2 Experimental design -- 9.5 Toward a self-paced implementation -- 9.5.1 Related work -- 9.5.2 An SVM-ensemble for self-paced MI decoding -- 9.5.3 In quest of self-paced MI decoding -- 9.6 Summary -- References -- 10. Graph signal processing analysis of NIRS signals for brain-computer interfaces | Panagiotis C. Petrantonakis and Ioannis Kompatsiaris -- 10.1 Introduction -- 10.2 NIRS dataset -- 10.3 Materials and methods -- 10.3.1 Graph signal processing basics -- 10.3.2 Dirichlet energy over a graph -- 10.3.3 Graph construction algorithm -- 10.3.4 Feature extraction -- 10.3.5 Classification -- 10.3.6 Implementation issues -- 10.4 Results -- 10.5 Discussion -- 10.6 Summary -- References -- Part III: Multimodal prototype interfaces that can be operated through eyes and mind -- 11. Error-aware BCIs | Fotis P. Kalaganis, Elisavet Chatzilari, Nikos A. Laskaris, Spiros Nikolopoulos, and Ioannis Kompatsiaris -- 11.1 Introduction to error-related potentials -- 11.2 Spatial filtering -- 11.2.1 Subspace learning -- 11.2.2 Increasing signal-to-noise ratio -- 11.3 Measuring the efficiency - ICRT -- 11.4 An error-aware SSVEP-based BCI -- 11.4.1 Experimental protocol -- 11.4.2 Dataset -- 11.4.3 Implementation details - preprocessing -- 11.4.4 Results -- 11.5 An error-aware gaze-based keyboard -- 11.5.1 Methodology -- 11.5.2 Typing task and physiological recordings
• Intro -- Contents -- About the editors -- Preface -- 1. Introduction | Spiros Nikolopoulos, Chandan Kumar, and Ioannis Kompatsiaris -- 1.1 Background -- 1.2 Rationale -- 1.3 Book objectives -- Part I: Reviewing existing literature on the benefits of BCIs, studying the computer use requirements and modeling the (dis)abilities of people with motor impairment -- 2. The added value of EEG-based BCIs for communication and rehabilitation of people with motor impairment | Ioulietta Lazarou, Spiros Nikolopoulos, and Ioannis Kompatsiaris -- 2.1 Introduction -- 2.2 BCI systems -- 2.3 Review question -- 2.4 Methods -- 2.4.1 Search strategy -- 2.4.2 Types of participants and model systems -- 2.4.3 Data synthesis - description of studies-target population characteristics -- 2.5 EEG-based BCI systems for people with motor impairment -- 2.5.1 EEG-based BCIs for communication and control -- 2.5.2 EEG-based BCIs for rehabilitation and training -- 2.6 Discussion -- 2.7 Summary -- References -- 3. Brain-computer interfaces in a home environment for patients with motor impairment-the MAMEM use case | Sevasti Bostantjopoulou, Zoe Katsarou, and Ioannis Danglis -- 3.1 Introduction -- 3.1.1 Parkinson's disease -- 3.1.2 Patients with cervical spinal cord injury -- 3.1.3 Patients with neuromuscular diseases -- 3.2 Computer habits and difficulties in computer use -- 3.2.1 Patients with PD -- 3.2.2 Patients with cervical spinal cord injuries -- 3.2.3 Patients with NMDs -- 3.3 MAMEM platform use in home environment -- 3.3.1 Subjects selection -- 3.3.2 Method -- 3.3.3 Results -- 3.4 Summary -- References -- 4. Persuasive design principles and user models for people with motor disabilities | Sofia Fountoukidou, Jaap Ham, Uwe Matzat, and Cees Midden -- 4.1 Methods for creating user models for the assistive technology -- 4.1.1 User profiles -- 4.1.2 Personas
• 4.2 Persuasive strategies to improve user acceptance and use of an assistive device -- 4.2.1 Selection of persuasive strategies -- 4.2.2 Developing persuasive strategies for Phase I: user acceptance and training -- 4.2.3 Developing persuasive strategies for Phase II: Social inclusion -- 4.2.4 Conclusions -- 4.3 Effectiveness of the proposed persuasive and personalization design elements -- 4.3.1 The evaluation of Phase I field trials -- 4.3.2 The evaluation of the assistive technology in a lab study -- 4.4 Implications for persuasive design requirements -- 4.4.1 Implication for user profiles and personas -- 4.4.2 Updated cognitive user profile -- 4.4.3 Updated requirements for personalization -- 4.4.4 Updated requirements for persuasive design -- 4.4.5 Implications for Phase II persuasive design strategies -- 4.4.6 Conclusions -- 4.5 Summary -- References -- Part II: Algorithms and interfaces for interaction control through eyes and mind -- 5. Eye tracking for interaction: adapting multimedia interfaces | Raphael Menges, Chandan Kumar, and Steffen Staab -- 5.1 Tracking of eye movements -- 5.1.1 Anatomy of the eye -- 5.1.2 Techniques to track eye movements -- 5.1.3 Gaze signal processing -- 5.2 Eye-controlled interaction -- 5.2.1 Selection methods -- 5.2.2 Unimodal interaction -- 5.2.3 Multimodal interaction -- 5.2.4 Emulation software -- 5.3 Adapted multimedia interfaces -- 5.3.1 Adapted single-purpose interfaces -- 5.3.2 Framework for eye-controlled interaction -- 5.3.3 Adaptation of interaction with multimedia in the web -- 5.4 Contextualized integration of gaze signals -- 5.4.1 Multimedia browsing -- 5.4.2 Multimedia search -- 5.4.3 Multimedia editing -- 5.5 Summary -- References -- 6. Eye tracking for interaction: evaluation methods | Chandan Kumar, Raphael Menges, Korok Sengupta, and Steffen Staab -- 6.1 Background and terminology