Brain Informatics: 15th International Conference, BI 2022, Padua, Italy, July 15–17, 2022, Proceedings (Lecture Notes in Computer Science, 13406)

Preface
Organization
Contents
Cognitive and Computational Foundations of Brain Science
Estimating the Temporal Evolution of Synaptic Weights from Dynamic Functional Connectivity
	1 Introduction
	2 Simulated Spiking Network and Inference Pipeline
	3 Inferring the Presence of Synapses
	4 Inferring Synapse Type and Communication Delay
	5 Relationship Between Dynamic Functional Connectivity and the Temporal Evolution of Synaptic Weights
	6 Discussion
	References
From Concrete to Abstract Rules: A Computational Sketch
	1 Introduction
	2 Methods
		2.1 Model Details: HER
		2.2 Task
	3 Results
		3.1 Learning Curves
		3.2 Gating Weights
		3.3 Prediction Weights
		3.4 New Model
	4 Discussion
	References
Detection of Healthy and Unhealthy Brain States from Local Field Potentials Using Machine Learning
	1 Introduction
	2 Methodology
		2.1 Data Acquisition
		2.2 Signal Processing
		2.3 Machine Learning Classification Models
	3 Results
		3.1 Subject-Specific Model with ECG and Respiration
		3.2 Cross Subject Model with LFP
		3.3 LFP Anomality Detector
	4 Discussion
	5 Conclusion
	References
COSLETS: Recognition of Emotions Based on EEG Signals
	1 Introduction
	2 Related Work
	3 Proposed Method
		3.1 Discrete Cosine Transform (DCT)
		3.2 Wavelets
		3.3 Principal Component Analysis (PCA)
	4 Classification
	5 Experiments and Results
		5.1 Dataset
		5.2 Experimental Results and Performance Analysis
		5.3 Discussion and Conclusion
	References
.26em plus .1em minus .1emInfluences of Social Learning in Individual Perception and Decision Making in People with Autism: A Computational Approach
	1 Introduction
	2 Cognitive Model
	3 Methodology
		3.1 Participant's Demographic Data
		3.2 Experimental Paradigm
		3.3 Theoretical Foundations and Experimental Phases
		3.4 Data Analysis
	4 Results and Discussion
		4.1 Statistical Results from First and Second Phase
		4.2 Discussion
	5 Conclusion
	References
Investigations of Human Information Processing Systems
Analysis of Alpha Band Decomposition in Different Level-k Scenarios with Semantic Processing
	1 Introduction
	2 Materials and Methods
		2.1 Measures
		2.2 Experimental Design
	3 Results and Discussion
		3.1 EEG Preprocessing Scheme
		3.2 Alpha Band Decomposing Analysis in Coordination Process
	4 Conclusions and Future Work
	Appendix A: Alpha Band Decomposition and Relative Power Estimation
	References
Toward the Study of the Neural-Underpinnings of Dyslexia During Final-Phoneme Elision: A Machine Learning Approach
	1 Introduction
	2 Materials and Methods
		2.1 Experimental Paradigm and Data Collection
		2.2 Phoneme-Related Neural-Congruency Components
		2.3 Classification of Phoneme-Related Neural-Congruency Components
		2.4 Spatiotemporal Profiles of Phoneme-Related Neural-Congruency Components
	3 Results
	4 Discussion and Conclusion
	References s
Root-Cause Analysis of Activation Cascade Differences in Brain Networks
	1 Introduction
	2 Linear Threshold Model and Activation Cascades
	3 TRACED Algorithm
	4 A Case Study on Major Depressive Disorder
	5 Discussion
	A  Appendix
		A.1  Optimization of TRACED
	References
Unstructured Categorization with Probabilistic Feedback: Learning Accuracy Versus Response Time
	1 Introduction
	2 Materials and Methods
		2.1 Stimuli
		2.2 Procedure
		2.3 Observers
		2.4 Statistical Analyses
	3 Results
	4 Discussion
	5 Conclusions
	References
Brain Big Data Analytics, Curation and Management
Optimizing Measures of Information Encoding in Astrocytic Calcium Signals
	1 Introduction
	2 Computing Amount and Significance of Information in Astrocytic Calcium Activity
	3 Measuring Conditional Mutual Information to Evaluate Genuine Information Encoding
	4 Spatial Information in CA1 Astrocytes During Spatial Navigation
	5 Conclusions
	References
Introducing the Rank-Biased Overlap as Similarity Measure for Feature Importance in Explainable Machine Learning: A Case Study on Parkinson’s Disease
	1 Introduction
	2 Materials and Methods
		2.1 Participants
		2.2 Clinical and Imaging Features
		2.3 Sampling of the Dataset
		2.4 Machine Learning Analysis
		2.5 Rank-Biased Overlap (RBO)
	3 Results
		3.1 Machine Learning Analysis
		3.2 RBO Scores
	4 Discussion and Conclusions
	References
Prediction of Neuropsychological Scores from Functional Connectivity Matrices Using Deep Autoencoders
	1 Introduction
	2 Materials and Methods
		2.1 Datasets
		2.2 Dimensionality Reduction
		2.3 Data Augmentation and Transfer Learning
		2.4 Regularized Regression
	3 Results
		3.1 Dimensionality Reduction
		3.2 Regularized Regression
		3.3 Getting Deeper on Augmentation and Transfer Techniques
	4 Conclusion
	References
Classifying EEG Signals of Mind-Wandering Across Different Styles of Meditation
	1 Introduction
	2 Motivation
		2.1 Impact on Cognition
		2.2 Technological Considerations
	3 Dataset Description
	4 Methods
		4.1 Feature Extraction
		4.2 Validation
		4.3 Classifiers
		4.4 Visualization
	5 Results
		5.1 Classification Insights
		5.2 Lower Dimensional Visualization Insights
	6 Discussion and Conclusion
	7 Limitation
	References
Feature Fusion-Based Capsule Network for Cross-Subject Mental Workload Classification
	1 Introduction
	2 Methods
		2.1 Experiment and Dataset
		2.2 Feature Extraction and Fusion
		2.3 Model Architecture
		2.4 Dynamic Routing
		2.5 Loss Function
	3 Result
		3.1 Methods Comparison
	4 Conclusion
	References
Brain Source Reconstruction Solution Quality Assessment with Spatial Graph Frequency Features
	1 Introduction
	2 EEG/MEG Source Imaging Problem
	3 Method
	4 Result
	5 Discussion and Limitation
	References
Enhancing the MR Neuroimaging by Using the Deep Super-Resolution Reconstruction
	1 Introduction
	2 Method
		2.1 The Preprocessing Component
		2.2 The Super-Resolution Component
		2.3 The Evaluation Component
	3 Results and Discussions
		3.1 MR Neuroimage Acquisition and Preprocessing
		3.2 The Super-Resolution Results of the MR Neuroimaging
		3.3 Quantitative Analysis Based on No-Reference Indicators
	4 Conclusion
	References
Towards Machine Learning Driven Self-guided Virtual Reality Exposure Therapy Based on Arousal State Detection from Multimodal Data
	1 Introduction
	2 Related Work
	3 ML Model Pipeline and Data Set
	4 Result Analysis
	5 Challenges and Future Research Directions
	6 Conclusion
	References
Convex Hull in Brain Tumor Segmentation
	1 Introduction
	2 Literature Review
	3 Methodology
		3.1 Pre-processing
		3.2 Tumor Area Extraction
		3.3 Convex Hull Generation
		3.4 Convex Hull Accuracy Detection
	4 Experimental Results
		4.1 Datasets
		4.2 Performance Metrics
		4.3 Results and Discussion
	5 Conclusion
	References
Informatics Paradigms for Brain and Mental Health Research
Computer-Aided Diagnosis Framework for ADHD Detection Using Quantitative EEG
	1 Introduction
	2 Materials and Method
		2.1 Dataset
		2.2 Proposed Method
	3 Results and Discussions
	4 Conclusion
	References
A Machine Learning Approach for Early Detection of Postpartum Depression in Bangladesh
	1 Introduction
	2 Related Works
		2.1 PPD in Bangladesh Perspective
		2.2 Machine Learning for PPD Detection
	3 Materials and Methodology
		3.1 Sampling
		3.2 Measures
		3.3 Data Collection Procedure
		3.4 Data Preparation
		3.5 Statistical Approach for Data Analysis
		3.6 Machine Learning Approach for PPD Detection
	4 Result
		4.1 Correlation of the Socio-demographic Features with PPD
		4.2 Prevalence of PPD
		4.3 Effect of Machine Learning Classifier Models
	5 Discussion
		5.1 Key Findings and Contributions
		5.2 Limitations
	6 Conclusion
	References
Epilepsy Detection from EEG Data Using a Hybrid CNN-LSTM Model
	1 Introduction
	2 Related Work
	3 Methodology
		3.1 Data Collection
		3.2 Convolutional Neural Network (CNN)
		3.3 Long Term Short Term Memory (LSTM)
		3.4 Proposed Hybrid CNN-LSTM Model
	4 Result and Discussion
		4.1 System Configuration
		4.2 Hyperpararmeters Tuning
		4.3 Performance Matrix
		4.4 Result
	5 Conclusion and Future Work
	References
Classifying Brain Tumor from MRI Images Using Parallel CNN Model
	1 Introduction
	2 Literature Review
	3 Methodology
		3.1 Dataset
		3.2 Data Preprocessing
		3.3 Data Augmentation
		3.4 Feature Extraction
		3.5 Classification
	4 Experimental Results and Evaluation
		4.1 Result
		4.2 Performance Matrix
		4.3 Comparison of Different Models
	5 Conclusion and Future Work
	References
Triplet-Loss Based Siamese Convolutional Neural Network for 4-Way Classification of Alzheimer's Disease
	1 Introduction
	2 Review of Recent Literature
	3 A Brief Overview of the Triplet-Loss Siamese CNN
		3.1 Siamese CNN Architecture
		3.2 Triplet Loss
		3.3 The ConvNet Encoders
	4 Experimental Results
	5 Conclusion and Future Work
	References
Understanding Syntax Structure of Language After a Head Injury
	1 Introduction
	2 Previous Research
	3 TBI Corpus
		3.1 Data Description and Feature Set
	4 The Approach
		4.1 The Rationale Behind Grammar Productions
	5 Experiments
		5.1 Experimental Setting
	6 Results
		6.1 Discussion
		6.2 Advantages and Limitations
	7 Conclusions and Further Work
	References
A Belief Rule Based Expert System to Diagnose Alzheimer's Disease Using Whole Blood Gene Expression Data
	1 Introduction
	2 Related Work
	3 Methodology
		3.1 BRBES
		3.2 Dataset
		3.3 Model Training
	4 Results and Discussion
	5 Conclusion
	References
Feature-Selected Graph Spatial Attention Network for Addictive Brain-Networks Identification
	1 Introduction
	2 Method
		2.1 Graph Spatial Attention Encoder
		2.2 Bayesian Feature Selector
		2.3 Classifier and Loss Function
	3 Experiments
		3.1 Ablation Study
		3.2 Identification Performance
		3.3 Interpretable Brain Regional Biomarkers
	4 Conclusion
	References
Brain-Machine Intelligence and Brain-Inspired Computing
Biologically Inspired Neural Path Finding
	1 Introduction
	2 Related Work
		2.1 Artificial Neural Networks, ANNs
		2.2 Graph Representation
		2.3 Reinforcement Learning, RL
		2.4 Shortest Path Algorithms
	3 Framework
	4 Experiments
		4.1 Unseen Test Data
		4.2 Fixed Structure, Fixed Number of Nodes
		4.3 Variable Structure, Fixed Number of Nodes
		4.4 Loss Functions
		4.5 Comparision with BrainNetCNN Approach
		4.6 Relative Prediction Time
		4.7 Evaluation on a Real World Dataset
	5 Conclusion
	References
A Second-Order Adaptive Social-Behavioural Model for Individual and Duo Motor Learning
	1 Introduction
	2 Background Literature
	3 Method Used
	4 Simulation Results
	5 Verification and Validation of the Model
	6 Discussion
	References
EEG Signal Classification Using Shallow FBCSP ConvNet with a New Cropping Strategy
	1 Introduction
	2 Related Work
		2.1 FBCSP - Filter Bank Common Spatial Pattern
		2.2 Shallow FBCSP ConvNet
		2.3 Cropping Strategy
		2.4 Other ConvNets
	3 A Novel Cropping Method for EEG Classification
		3.1 A New Cropping Strategy
		3.2 Model Construction and Work Flow
	4 Experimental Analysis
		4.1 Data and Preprocessing
		4.2 Experimental Results of Shallow FBCSP ConvNet
		4.3 Experimental Results of Other Models
	5 Conclusion and Future work
	References
Becoming Attuned to Each Other Over Time: A Computational Neural Agent Model for the Role of Time Lags in Subjective Synchrony Detection and Related Behavioral Adaptivity
	1 Introduction
	2 Background Perspectives
	3 The Self-modeling Network Modeling Approach Used
	4 The Adaptive Neural Agent Model
	5 Simulation Results
	6 Discussion
	References
Author Index