Computational Intelligence and Deep Learning Methods for Neuro-Rehabilitation Applications

Computational Intelligence and Deep Learning Methods for Neuro-Rehabilitation Applications

Computational Intelligence and Deep Learning Methods for Neuro-rehabilitation Applications explores the different possibilities of providing AI based neuro-rehabilitation methods to treat neurological disorders. This book provides in-depth knowledge on the challenges and solutions associated with th...

Full description

Bibliographic Details
Main Author: Hemanth, D. Jude (-)
Format: eBook
Language:Inglés
Published: San Diego : Elsevier Science & Technology 2023.
Edition:1st ed
Subjects:
Nervous system > Diseases > Patients > Rehabilitation.
Computational intelligence.
Deep learning (Machine learning) > Therapeutic use.
See on Biblioteca Universitat Ramon Llull:https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009835420506719
Table of Contents:
  • Front Cover
  • Computational Intelligence and Deep Learning Methods for Neuro-rehabilitation Applications
  • Computational Intelligence and Deep Learning Methods for Neuro-rehabilitation Applications
  • Copyright
  • Contents
  • Contributors
  • Preface
  • 1 - AI-based technologies, challenges, and solutions for neurorehabilitation: A systematic mapping
  • 1. Introduction
  • 1.1 Artificial intelligence
  • 1.2 Neurological disorders
  • 2. Recent developments and involvement of artificial intelligence in healthcare and neurorehabilitation
  • 3. Clinical challenges and robotic rehabilitation applications
  • 3.1 Clinical challenges
  • 3.2 Robotic rehabilitation applications
  • 4. High-tech collaborations driving neural rehabilitation
  • 4.1 Human-robot control interfaces
  • 4.1.1 Digital-neural interfaces
  • 4.1.2 Electromyography
  • 4.1.3 Brain-computer interfaces
  • 4.2 Neurorobotics
  • 4.2.1 Neuroexoskeletons
  • 4.2.2 Neuroprosthetics
  • 4.3 Virtual and augmented reality
  • 4.4 AI algorithms
  • 5. Selection of AI-based supportive technologies and tools for instigating neurorehabilitation
  • 6. Conclusions and future directions
  • References
  • Further reading
  • 2 - Complex approaches for gait assessment in neurorehabilitation
  • 1. Introduction
  • 2. Theoretical approach of gait analysis
  • 3. Gait pattern-theoretical and practical framing
  • 4. Clinical applications of gait analysis in neurorehabilitation
  • 4.1 Multiple sclerosis
  • 4.2 Hemiparesis
  • 4.3 Paraparesis postchemotherapy (postchemotherapy polyneuropathy CIPN)
  • 5. Case studies
  • 5.1 Case study 1
  • 5.2 Case study 2
  • 5.3 Case study 3
  • 6. Conclusions
  • References
  • 3 - Deep learning method for adult patients with neurological disorders under remote monitoring
  • 1. Introduction
  • 2. Related works
  • 2.1 Modern artificial intelligence
  • 2.2 Deep learning.
  • 2.3 Convolutional neural networks
  • 2.4 Data source
  • 2.5 Image classification
  • 3. Proposed methodology
  • 3.1 Image classification
  • 3.2 Object detection
  • 3.3 Recognition of human activity
  • 3.4 System architecture
  • 3.5 Monitoring application
  • 4. Discussions
  • 5. Conclusion
  • 6. Future scope
  • References
  • 4 - Rehabilitation for individuals with autism spectrum disorder using mixed reality virtual assistants
  • 1. Introduction
  • 2. Related work
  • 2.1 Common interventions in rehabilitation of ASD
  • 3. Exploring the virtual world with Microsoft HoloLens
  • 3.1 Microsoft HoloLens, a wearable mixed reality device
  • 3.2 HoloLearn: Unpacking the mechanics of mixed reality learning
  • 3.3 Exploring the world of autism: A HoloLearn activity
  • 3.3.1 Setting the table activity
  • 3.3.2 HoloLearn's garbage collection efforts
  • 3.3.3 HoloLearn memory activity
  • 3.3.4 Virtual assistant
  • 3.3.5 Dress-up activity
  • 4. ASD pathways: Tools for rehabilitation and progress
  • 4.1 Autism XR
  • 4.2 Real social skills
  • 4.3 PRISMA
  • 4.4 Discussions
  • 5. Challenges faced
  • 6. Future directions
  • 7. Conclusion
  • References
  • 5 - Wearable sleeve for physiotherapy assessment using ESP32 and IMU sensor
  • 1. Introduction
  • 1.1 Existing methods
  • 1.2 Scope and objectives
  • 2. Literature survey
  • 3. Proposed system: Materials and methodology
  • 3.1 IMU sensor
  • 3.2 System architecture
  • 3.3 System implementation
  • 3.4 Installation of mircopython on ESP32
  • 3.5 Interfacing MPU9250 with ESP32
  • 3.6 Graphical user interface
  • 3.7 Updating the database on the server end
  • 3.8 Detecting the angle of the set
  • 3.9 Graphical report
  • 4. Experimental results and discussion
  • 4.1 Quantitative measures
  • 4.2 Quality measures
  • 5. Conclusion and future scope
  • References.
  • 6 - Machine learning for Developing neurorehabilitation-aided assistive devices
  • 1. Introduction
  • 1.1 Neurological disorders
  • 1.2 Neurorehabilitation and assistive technology
  • 2. Machine learning as a tool in assistive technology for neurorehabilitation
  • 2.1 Integration of ML in assistive technology and its applications
  • 3. Applications of ML-integrated assistive technology in neurorehabilitation
  • 3.1 Prosthetics and orthotics
  • 3.2 Augmentative and alternative communication devices
  • 3.3 Adaptive computer technology
  • 3.4 Mobility aids
  • 3.5 Sensory aids
  • 3.6 Cognitive aids
  • 3.7 Environmental control
  • 4. Conclusion
  • References
  • 7 - Deep learning and machine learning methods for patients with language and speech disorders
  • 1. Introduction
  • 1.1 Language and speech disorders: Types, diagnosis, and treatment
  • 1.1.1 Fluency speech disorders
  • 1.1.2 Resonance disorders
  • 1.1.3 Voice disorders
  • 1.1.4 Motor speech disorders
  • 1.1.5 Language disorders
  • 1.1.6 Acquired language disorders
  • 1.1.7 Speech sound disorders
  • 1.1.7.1 Deep learning and machine learning in AI
  • 1.1.7.1 Deep learning and machine learning in AI
  • 2. Research methodology
  • 2.1 Research questions
  • 2.2 Data collection and data analysis process
  • 3. DL and ML methods for patients with SLD
  • References
  • 8 - Machine learning for cognitive treatment planning in patients with neurodisorder and trauma injuries
  • 1. Introduction
  • 1.1 Multiple sclerosis
  • 1.1.1 Multiple sclerosis signs and symptoms
  • 1.1.2 Treatment of multiple sclerosis
  • 1.2 Parkinson's disease
  • 1.2.1 Signs and symptoms of Parkinson's disease
  • 1.2.2 Treatment process of Parkinson's disease
  • 1.2.3 Exercise and alternative treatments
  • 1.3 Importance of artificial intelligence in healthcare
  • 2. Related work
  • 3. Proposed methodology.
  • 3.1 Methodology for predicting stroke in patients who have already had one
  • 4. Results and discussion
  • 5. Conclusion
  • References
  • 9 - Artifacts removal techniques in EEG data for BCI applications: A survey
  • 1. Introduction
  • 1.1 Signal capturing block
  • 1.2 Processing of signals block
  • 1.3 Signal preprocessing
  • 1.4 Feature extraction
  • 1.5 Classification
  • 1.6 Application interface
  • 1.7 Applications
  • 1.8 Feedback
  • 2. Artifacts removal techniques
  • 3. Conclusion
  • References
  • Further reading
  • 10 - Deep learning system of naturalistic communication in brain-computer interface for quadriplegic patient
  • 1. Introduction
  • 2. Related works
  • 3. Dataset
  • 4. Methodology
  • 4.1 Convolutional neural network
  • 4.1.1 CNN layers
  • 4.1.2 Pooling layer
  • 4.1.3 Fully connected layer
  • 4.2 AlexNet
  • 4.2.1 Softmax
  • 4.2.2 ReLU
  • 4.2.3 Data augmentation
  • 4.2.4 Dropout
  • 4.3 Computer vision
  • 4.4 Image recognition
  • 5. Experimental results
  • 6. Discussion
  • 7. Conclusion
  • References
  • 11 - Motor imaginary tasks-based EEG signals classification using continuous wavelet transform and LSTM network
  • 1. Introduction
  • 2. Material and methodology
  • 2.1 Dataset (PhysioNet)
  • 2.2 EEG preprocessing and feature extraction
  • 2.2.1 Continuous wavelet transform
  • 2.2.2 Features
  • 2.2.2.1 Entropy features
  • 2.2.2.1 Entropy features
  • 2.2.2.1.1 Shannon Entropy
  • 2.2.2.1.1 Shannon Entropy
  • 2.2.2.1.2 Sure entropy
  • 2.2.2.1.2 Sure entropy
  • 2.2.2.2 Statistical features
  • 2.2.2.2 Statistical features
  • 2.2.2.2.1 Mean
  • 2.2.2.2.1 Mean
  • 2.2.2.2.2 Standard deviation
  • 2.2.2.2.2 Standard deviation
  • 2.2.2.2.3 Skewness
  • 2.2.2.2.3 Skewness
  • 2.2.2.2.4 Normalized standard deviation
  • 2.2.2.2.4 Normalized standard deviation
  • 2.2.2.2.5 Kurtosis
  • 2.2.2.2.5 Kurtosis
  • 2.2.2.2.6 Energy
  • 2.2.2.2.6 Energy.
  • 2.2.2.2.7 Normalized energy
  • 2.2.2.2.7 Normalized energy
  • 2.2.2.3 Fractal dimension
  • 2.2.2.3 Fractal dimension
  • 2.2.2.3.1 Higuchi fractal dimension
  • 2.2.2.3.1 Higuchi fractal dimension
  • 2.2.2.3.2 Katz fractal dimension
  • 2.2.2.3.2 Katz fractal dimension
  • 2.3 Classification
  • 2.3.1 Long short-term memory technique
  • 2.3.1.1 Results and discussions
  • 2.3.1.1 Results and discussions
  • 2.4 Performance measures
  • 2.5 Classification performance evaluation
  • 3. Conclusion
  • References
  • Further reading
  • 12 - Enhancing human brain activity through a systematic study conducted using graph theory and probability concept ...
  • 1. Introduction
  • 2. Methodology
  • 2.1 Bayesian inference
  • 2.2 Probability density
  • 3. Hydar influence in brain activity
  • 3.1 Movement of actual robot
  • 4. Artificial intelligence framework
  • 5. Experiments conducted using Hydar
  • 5.1 Experiment-The first
  • 5.2 Experiment-Observe what is expected
  • 5.3 Experiment-Different forward models
  • 5.4 Experiment-Higher embedding orders
  • 5.5 Experiment-Colored noise
  • 5.6 Experiment-White noise
  • 5.7 Plotting 4D probabilistic atlas maps
  • 5.8 Plotting a statistical map
  • 5.9 Glass brain visualization
  • 6. Survey on impact of technology in mental health
  • 6.1 Have/had mental health disorder
  • 6.2 Companies taking mental health seriously
  • 6.3 Discussing mental health at work
  • 6.4 Mental health having consequences on career
  • 6.5 Being open about mental health with friends and family
  • 6.6 Percentages of people with mental health disorders out of all respondents in the United States
  • 7. Conclusion
  • References
  • Index
  • Back Cover.

Similar Items