Augmented intelligence is an alternate approach of artificial intelligence (AI), which emphasizes AI's assistive role. Augmented intelligence enhances human skills of reasoning in a robotic system or software by simulating expectancy, educational mining, problem solving, recollection, sequencing, and decision-making capabilities. It is based on a combination of techniques such as machine learning, deep learning and cognitive computing.
This book explains artificial intelligence models that support assistive processes in different situations.
The contributors aim to provide information to a diverse audience with groundbreaking developments in mathematical computing.
The book presents 8 chapters on these topics:
- Educational data mining in augmented reality virtual learning environment
- Brain and computer interfaces
- Tree-based tools for chemometric analysis of infrared spectra
- Applications of deep learning in medical engineering
- Bankruptcy prediction model using an enhanced boosting classifier
- Reputation systems for mobile agent security
- The crow search algorithm
- COVID-19 diagnosis and treatment
The contents attempt to integrate various facets of augmented Intelligence, by describing recent research developments and advanced topics of interest to academicians and researchers working on machine learning problems and AI.
Table of Contents
Chapter 1 Integrating Educational Data Mining In Augmented Reality Virtual Learning Environment- Carlos Ankora And D. Aju 1.1. Introduction
- 1.2. Virtual Learning Environments (Vle)
- 1.3. Augmented Reality (Ar)
- 1.3.1. Elements Of Ar In A Vle
- 1.3.2. Target Markers Used In Ar Applications
- 1.3.3. Hardware Platforms/Peripherals
- 1.3.4. Ar Applications In Education
- 1.4. Development Of Methodology For Ar In Vle
- 1.4.1. Agile Methodology
- 1.4.2. Developing Ar-Vle Using Agile Scrum
- 1.5. Ar System Development For Vle
- 1.5.1. Designing The 3D Models
- Blender
- 1.5.2. Developing The Ar Modules
- Unity 3D
- 1.6. Educational Data Mining In Ar-Vle
- Conclusion
- Consent For Publication
- Conflict Of Interest
- Acknowledgements
- References
- Kuldeep Singh Kaswan And Jagjit Singh Dhatterwal 2.1. Introduction
- 2.2. What Is Bci?
- 2.3. Bci Sensor World Overview
- 2.4. History Of Implantable Electrodes
- 2.5. Types Of Microelectrodes
- 2.5.1. Mass-Fabricated Microelectrodes
- 2.5.2. Silicon-Based Microelectrodes
- 2.5.3. Ceramic-Based Microelectrodes
- 2.5.4. Polyimide Microelectrode
- 2.5.5. Microelectrodes Connectors
- 2.5.6. Ecog Strip Electrodes
- 2.6. Bci Eeg Sensors
- 2.7. Modeling And Signal Processing Of Bmi/Bci Techniques Of Multi Micro Electrode Array
- 2.7.1. Binned Conceptual Data Models
- 2.7.2. Eeg/Ecog Recordings
- 2.8. Hardware Implementation
- 2.8.1. Paralysis Patients Restoring Movement
- 2.8.2. Eeg-Based Brain-Computer Interfaces
- 2.8.3. Direct Brain-Computer Interfaces
- 2.8.4. Recording, Extracting, And Decoding Neural Motor Commands
- 2.8.5. Predict Limb Movement Kinematics Use Of Multivariate Regression Analysis (Mra) 34 2.8.6. Monkey Brain Motor Commands Of Extraction
- 2.8.7. Biofeedback Changes Coding Of Robot Arm Movement
- 2.9. Brain Control Of Multiple-Output Functions
- 2.10. Biomimetic Robot Research
- 2.10.1. The Rationale For Biomimetic Hand Prostheses
- 2.10.2. Research Approach To Bio Mechatronics At Sssa
- 2.10.3. Using Direct Bcis To Control Biomimetic Robotic Prostheses
- Conclusion
- Consent For Publication
- Conflict Of Interest
- Acknowledgements
- References
- Lucas A.C. Minho, Bárbara E.A. De Magalhães And Alexandre G.M. De Freitas 3.1. Introduction
- 3.2. Decision Trees (Dt)
- 3.3. Random Forest (Rf)
- 3.4. Experiments
- 3.5. Dimensionality Reduction In Raw Spectroscopic Space
- 3.5.1. Importance Measurements And Feature Ranking With Random Forest
- 3.5.1.1. Boruta Wrapper Algorithm
- 3.5.1.2. Feature Subset Selection With Boruta
- 3.6. Robustness Of Tree-Based Algorithms To Noise
- 3.7. Tree-Based Algorithms In Discriminant Analysis
- Conclusion
- Notes
- Consent For Publication
- Conflict Of Interest
- Acknowledgements
- References
- Sumit Kumar Jindal, Sayak Banerjee, Ritayan Patra And Arin Paul 4.1. Historical Overview Of Deep Learning
- 4.1.1. Machine Learning
- 4.1.2. Neural Networks
- 4.1.3. Deep Learning
- 4.2. Activation Functions
- 4.2.1. Binary Activation Function
- 4.2.2. Sigmoid And Softmax Activation Function
- 4.2.3. Tanh Activation Function
- 4.2.4. Relu And Leaky Relu Activation Function
- 4.3. Optimizers And Loss
- 4.3.1. Optimizers
- 4.3.1.1. Adagrad
- 4.3.1.2. Rmsprop
- 4.3.1.3. Adam Optimizer
- 4.3.2. Loss Functions
- 4.3.2.1. Mean Squared Error Loss
- 4.3.2.2. Cross - Entropy Loss
- 4.4. Image Recognition And Classification
- 4.4.1. Convolution Layer
- 4.4.2. Pooling Layer
- 4.4.3. Full Connection
- 4.5. Audio Signal Processing
- 4.6. Deep Learning In Detection Of Sleep Apnea
- 4.6.1. System Design
- 4.6.2. Detection Of Apnea Or Hypopnea Event
- 4.6.3. Deep Learning Model
- 4.6.4. Evaluation Of The Model
- 4.7. Deep Learning In Cardiac Arrhythmia Detection
- 4.7.1. System Design
- 4.7.2. Deep Learning Model
- 4.7.3. Evaluation Of The Model
- 4.8. Deep Learning In Detection Of Brain Tumours
- 4.8.1. System Design
- 4.8.2. Deep Learning Model
- 4.8.3. Training The Model
- 4.8.4. Result
- Discussion And Future Works
- Consent For Publication
- Conflict Of Interest
- Acknowledgements
- References
- Makram Soui, Nada Namani Zitouni, Salima Smiti, Kailash Kumar And Ahmad Aljabr 5.1. Introduction
- 5.2. Related Work
- 5.2.1. Statistical Techniques
- 5.2.2. Artificial Intelligent Techniques
- 5.2.2.1. Machine Learning Techniques
- 5.2.2.2. Deep Learning Techniques
- 5.3. Background
- 5.3.1. Feature Selection (Fs) Algorithms
- 5.3.1.1. Sequential Feature Selection (Sfs)
- 5.3.1.2. Particle Swarm Optimization (Pso)
- 5.3.1.3. Random Subset Feature Selection (Rsfs)
- 5.3.2. Rule-Based Classifiers
- 5.3.2.1. Decision Tree Classifier: Cart
- 5.3.2.2. Decision Tree Classifier: J48 (C4.5)
- 5.3.2.3. Oner Classifier
- 5.3.2.4. Part Classifier
- 5.3.3. Ensemble Methods
- 5.3.3.1. Random Forest Classifier
- 5.3.3.2. Boosting Techniques
- 5.4.2.3. Proposed Method
- 5.4.1. Feature Selection Phase
- 5.4.2. Classification Phase
- 5.4.3. Testing Sub-Phase
- 5.5. Validation
- 5.5.1. Research Questions
- 5.5.2. Description Of The Experimental Database
- 5.5.3. Evaluation Criteria
- 5.6. Results And Discussion
- 5.6.1. Parameter Settings
- 5.6.2. Results For Research Question 1
- 5.6.3. Results For Research Question 2
- Conclusion
- Consent For Publication
- Conflict Of Interest
- Acknowledgements
- References
- Priyanka Mishra 6.1. Introduction
- 6.2. Trust Based Reputation System
- 6.3. Related Works
- 6.4. Mrep Model
- 6.5. Detection Methodology
- 6.6. Simulation Results
- Conclusion
- Consent For Publication
- Conflict Of Interest
- Acknowledgements
- References
- Ali Aloss, Barnali Sahu And Om Prakash Jena 7.1. Introduction
- 7.2. Crow Search Optimization
- 7.2.1. Overview Of Crow Search Optimization
- 7.2.2. Features Of Crow Search Algorithm
- 7.2.3. Algorithm Structure Of Cso
- 7.2.4. Pseudocode Of Csa
- 7.3. Csa Studies
- 7.3.1. Modifications Of Csa
- 7.3.1.1. Chaotic Csa(Ccsa)
- 7.3.1.2. Fuzzy Csa(Fcsa)
- 7.3.1.3. Other Updates Of Csa
- 7.3.2. Hybridization
- 7.3.3. Multi-Objective And Binary Optimization.
- 7.3.4. Other Applications: To Date, Csa Has Been Used In Many Other Applications In Varied Academic And Industrial Fields. Table 5 Shows The Other Applications Of Csa.
- 7.4. Application Of Csa In Medical Domain
- 7.5. Discussion And Critical Analysis
- Conclusion
Author
- Om Praksh Jena
- Alok Ranjan Tripathy
- Brojo Kishore Mishra
- Ahmed A. Elngar
