EEG-Based Classification of Hypnotic Susceptibility Using Two-Dimensional Convolutional Neural Networks

Krzysztof Wrobel; Grzegorz M. Wojcik; Filip Postepski; Andrzej Kawiak; Katarzyna Zemla; Grzegorz Sedek

cs.LGOct 20, 2026

EEG-Based Classification of Hypnotic Susceptibility Using Two-Dimensional Convolutional Neural Networks

Authors: Krzysztof Wrobel, Grzegorz M. Wojcik, Filip Postepski, Andrzej Kawiak, Katarzyna Zemla, Grzegorz Sedek

Organizations: Department of Neuroinformatics and Biomedical Engineering, Institute of Computer Science, Maria Curie-Skłodowska University, Akademicka 9, 20-031 Lublin, Poland · Institute of Psychology, SWPS University, Chodakowska 19/31, 03-815 Warsaw, Poland

Abstract

Guided Imagery (GI) is a mind-based relaxation technique widely used in clinical and therapeutic settings. Objectively assessing whether a patient has entered a relaxed state remains a challenge for clinicians. This study investigates electroencephalography (EEG)-based classification of hypnotic susceptibility using two-dimensional Convolutional Neural Networks (2D CNNs) applied to minimally preprocessed signals, without manual feature extraction. Data were collected from 62 male participants (32 Control, 30 Hypno) using a 256-channel dense array amplifier during Guided Imagery or cognitive task conditions. A sliding-window framework evaluated up to 868 independent models across seven anatomically defined brain regions and 124 ten-second time windows. Segment-level random-split screening was followed by Leave-One-Subject-Out (LOSO) cross-validation to obtain subject-independent performance estimates, and an ensemble approach combined predictions across K = 10 windows. The best single-window model achieved accuracy of 0.82 on the random split. Under LOSO, anterior regions generalised better across subjects: the frontal region achieved mean accuracy of 0.646 (AUC: 0.692). An ensemble of K = 10 windows further improved the prefrontal region to mean accuracy of 0.738. The occipital region, dominant in random-split screening, collapsed to near-chance under LOSO, revealing subject-specific EEG fingerprinting rather than genuine group differences. Bandpass filtering and z-score normalisation suffice for competitive EEG classification without manual feature extraction. Anterior cortical regions are identified as the most generalisable neural markers of hypnotic susceptibility.

Figures & tables

Panel of Figure 1 — Figure 1: Top: overview of the EEG Laboratory at UMCS, Lublin, Poland. Bottom: EGI 256-channel EEG cap.

Region	$N$	Electrode identifiers (sorted)
Prefrontal	22	E2, E3, E10–E12, E18–E20, E25–E27, E31–E34, E37–E39, E46–E48, E222
Frontal	20	E4–E6, E13–E15, E21–E23, E28–E30, E35, E36, E40, E41, E214, E215, E223, E224
Temporal	72	E1, E49, E54–E58, E61–E64, E67–E75, E82, E83, E91–E95, E102–E104, E173, E178, E180, E181, E189–E195, E200–E204, E208–E213, E216–E221, E225–E229, E232, E233, E250–E256
Central	25	E7–E9, E16, E17, E24, E42–E44, E50–E52, E59, E65, E182–E184, E186, E195–E198, E205–E207
Parietal	41	E45, E53, E60, E66, E77–E81, E84–E90, E96–E101, E129–E132, E141–E144, E152–E155, E161–E164, E170, E171, E179
Occipital	40	E105–E119, E121–E128, E138–E140, E149–E151, E158–E160, E167–E169, E175–E177, E188, E199

Table 1: Electrode subsets per brain region in the 256-channel EGI GSN 130 cap. Electrode identifiers follow the EGI convention (E n ); consecutive identifiers are shown as ranges.

N

is the number of electrodes per region.

Figure 2: 2D-CNN architecture used for HIPNO/CONTROL EEG classification.

Brain Region	Discriminative windows	Proportion (%)	Peak ACC	Mean ACC
Occipital	112/124	90.3	0.8026	0.7206
Parietal	95/124	76.6	0.7730	0.7087
Prefrontal	24/124	19.4	0.8224	0.7086
Central	20/124	16.1	0.8026	0.6998
Frontal	13/124	10.5	0.7829	0.7105
Temporal	0/124	0.0	—	—

Table 2: Classification performance of the CNN model across EEG brain regions. Discriminative windows are those exceeding the 0.67 accuracy threshold. Total number of analysed windows per region: 124.

Figure 3: Number of discriminative windows (ACC $>0.67$ ) per brain region out of 124 total analysed windows.

Figure 4: Peak and mean classification accuracy per brain region for regions with at least one discriminative window.

Figure 5: Proportion (%) of discriminative windows (ACC $>0.67$ ) out of 124 total windows per brain region.

Region	Window (s)	ACC	F1	Precision	Recall	AUC
Occipital	771–781	0.766	0.760	0.789	0.732	0.848
Parietal	1121–1131	0.799	0.800	0.803	0.797	0.899
Prefrontal	1101–1111	0.753	0.767	0.732	0.804	0.829
Central	1101–1111	0.688	0.678	0.704	0.654	0.757
Frontal	1121–1131	0.766	0.749	0.815	0.693	0.855

Table 3: Classification metrics for the best-performing window per discriminative region (HIPNO as positive class). Values are obtained by re-training the identified best window with a fixed random seed; run generate_best_metrics.py to reproduce.

Figure 6: Normalised confusion matrices for the best-performing window per discriminative brain region. Values represent row-normalised proportions; raw counts are shown in parentheses. Rows correspond to true labels; columns to predicted labels.

Figure 7: ROC curves for the five discriminative brain regions, computed from the best-performing window per region. Line styles distinguish regions for monochrome reproduction. AUC values are shown in the legend.

Region	Window (s)	Mean ACC $\pm$ Std	F1	Precision	Recall	AUC
Occipital	771–781	$0.453\pm 0.235$	0.434	0.435	0.434	0.429
Parietal	1121–1131	$0.631\pm 0.228$	0.627	0.613	0.641	0.680
Prefrontal	1101–1111	$0.624\pm 0.353$	0.616	0.608	0.624	0.681
Central	1101–1111	$0.591\pm 0.243$	0.582	0.576	0.588	0.599
Frontal	1121–1131	$0.646\pm 0.302$	0.638	0.633	0.641	0.692

Table 4: LOSO cross-validation results for the best window per discriminative region. ACC is mean

\pm

std across 62 folds; F1, Precision, Recall, and AUC are computed on concatenated fold predictions (HIPNO as positive class).

Figure 8: Per-subject accuracy distributions from LOSO cross-validation for each discriminative brain region. Each box represents the distribution of 62 fold accuracies. The dashed line marks the 0.67 discriminative threshold.

Figure 9: Aggregated normalised confusion matrices from LOSO cross-validation. Values are computed from the concatenated predictions of all 62 folds. Row-normalised proportions are shown; raw counts in parentheses.

Figure 10: Aggregated ROC curves from LOSO cross-validation, computed from concatenated fold predictions. AUC values are shown in the legend.

Region	Single ACC	Mean ACC $\pm$ Std	$\Delta$ ACC	F1	Precision	Recall	AUC
Prefrontal	0.624	$0.738\pm 0.361$	$+$ 0.114	0.722	0.744	0.701	0.761
Frontal	0.646	$0.667\pm 0.347$	$+$ 0.021	0.635	0.675	0.600	0.723
Central	0.591	$0.629\pm 0.338$	$+$ 0.038	0.584	0.637	0.539	0.629
Parietal	0.631	$0.609\pm 0.352$	$-$ 0.022	0.564	0.612	0.522	0.639
Occipital	0.453	$0.462\pm 0.352$	$+$ 0.009	0.429	0.441	0.417	0.472

Table 5: Ensemble LOSO results with K = 10 windows (soft voting). Single-window LOSO accuracy is included as reference.

\Delta

ACC is relative to the single-window baseline. ACC is mean

\pm

std across 62 folds; F1, Precision, Recall, and AUC are computed on concatenated fold predictions (HIPNO as positive class).

Figure 11: Per-subject accuracy distributions from ensemble LOSO cross-validation (K = 10) for each discriminative brain region. The dashed line marks the 0.67 discriminative threshold.

Figure 12: Aggregated normalised confusion matrices from ensemble LOSO cross-validation (K = 10), computed from concatenated predictions across all 62 folds. Row-normalised proportions are shown; raw counts in parentheses.

Figure 13: Aggregated ROC curves from ensemble LOSO cross-validation (K = 10), computed from concatenated fold predictions. AUC values are shown in the legend.

Classification

Classification maps observations to discrete labels, including familiar, unknown, hierarchical, or multiple categories.

See all 413 papers

Region-Specific EEG Classification of Hypnotic Susceptibility Using a Sliding-Window 2D CNN: A Subject-Independent Evaluation
Oct 20, 2026Krzysztof Wrobel, Grzegorz M. WojcikClassification Cross-Subject EEG Decoding
Department of Neuroinformatics and Biomedical Engineering, Institute of Computer Science, Maria Curie-Skłodowska University, Lublin, Poland
Spatiotemporal Convolutions on EEG signal -- A Representation Learning Perspective on Efficient and Explainable EEG Classification with Convolutional Neural Nets
May 5, 2026Laurits Dixen, Stefan Heinrich, Paolo BurelliEfficient Neural Network Inference MI Classification
IT University of Copenhagen Denmark
Classification of IED-free EEG Responses for Assisted Epilepsy Diagnosis
May 19, 2026Giacomo Zanardini, Ryan Moesman, Paul van der Kleij +2Electroencephalography EEG Decoding
Signal Processing Systems, Delft University of Technology, Delft, The Netherlands · Department of Neurology, Erasmus Medical Center, Rotterdam, The Netherlands

Oct 20, 2026J/K move · Enter open · S save

Region-Specific EEG Classification of Hypnotic Susceptibility Using a Sliding-Window 2D CNN: A Subject-Independent Evaluation

Krzysztof Wrobel, Grzegorz M. Wojcik

Department of Neuroinformatics and Biomedical Engineering, Institute of Computer Science, Maria Curie-Skłodowska University, Lublin, Poland

Classification Cross-Subject EEG Decoding EEG Decoding

Open paper AskPDF arXiv

We investigate whether a 2D Convolutional Neural Network (CNN) trained on minimally preprocessed EEG signals can classify hypnotic susceptibility across distinct brain regions. Sixty-two male participants (32 Control, 30 Guided Imagery / Hipno group) underwent a 20-minute EEG recording using a 256-channel EGI cap. A sliding-window approach evaluates all 10-second windows within the recording for each of seven predefined brain regions (prefrontal, frontal, temporal, central, parietal, occipital, and facial), yielding up to 868 independently trained models. Initial screening with a segment-level 90/10 random split showed that five regions exceeded the 0.67 accuracy threshold, with the occipital region achieving the highest mean accuracy (0.721) across 90.3% of windows. Subject-independent evaluation via Leave-One-Subject-Out (LOSO) cross-validation, however, substantially revised this picture: occipital performance collapsed to near-chance (mean ACC 0.453, AUC 0.429), revealing that high random-split accuracy was driven by subject-specific EEG fingerprints rather than genuine group differences. In contrast, the frontal and prefrontal regions maintained above-chance LOSO accuracy (0.646 and 0.624, respectively), demonstrating genuine generalisability. These results underscore the necessity of subject-independent validation in EEG-based classification studies and highlight anterior cortical regions as more reliable neural markers of hypnotic susceptibility.

Abstract

Classification

Explore similar work

Region-Specific EEG Classification of Hypnotic Susceptibility Using a Sliding-Window 2D CNN: A Subject-Independent Evaluation

Spatiotemporal Convolutions on EEG signal -- A Representation Learning Perspective on Efficient and Explainable EEG Classification with Convolutional Neural Nets

Classification of IED-free EEG Responses for Assisted Epilepsy Diagnosis