ChMinMaxPat: Investigations on Violence and Stress Detection Using EEG Signals DOI Creative Commons
Ömer Bektaş, Serkan Kırık, İrem Taşçı

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2666 - 2666

Published: Nov. 26, 2024

Background and Objectives: Electroencephalography (EEG) signals, often termed the letters of brain, are one most cost-effective methods for gathering valuable information about brain activity. This study presents a new explainable feature engineering (XFE) model designed to classify EEG data violence detection. The primary objective is assess classification capability proposed XFE model, which uses next-generation extractor, obtain interpretable findings EEG-based stress Materials Methods: In this research, two distinct signal datasets were used results. recommended utilizes channel-based minimum maximum pattern (ChMinMaxPat) extraction function, generates 15 vectors from data. Cumulative weight-based neighborhood component analysis (CWNCA) employed select informative features these vectors. Classification performed by applying an iterative ensemble t-algorithm-based k-nearest neighbors (tkNN) classifier each vector. Information fusion achieved through majority voting (IMV), consolidates tkNN Finally, Directed Lobish (DLob) symbolic language outputs leveraging identities selected features. Together, classifier, IMV-based fusion, DLob-based transform into self-organizing (SOXFE) framework. Results: ChMinMaxPat-based over 70% accuracy on both with leave-one-record-out (LORO) cross-validation (CV) 90% 10-fold CV. For dataset, DLob strings generated, providing based representations. Conclusions: SOXFE demonstrates high interpretability in detecting signals. contributes neuroscience enabling classification, underscoring potential importance clinical forensic applications.

Language: Английский

Zipper Pattern: An Investigation into Psychotic Criminal Detection Using EEG Signals DOI Creative Commons
Gülay TAŞCI, Prabal Datta Barua, Dahiru Tanko

et al.

Diagnostics, Journal Year: 2025, Volume and Issue: 15(2), P. 154 - 154

Published: Jan. 11, 2025

Background: Electroencephalography (EEG) signal-based machine learning models are among the most cost-effective methods for information retrieval. In this context, we aimed to investigate cortical activities of psychotic criminal subjects by deploying an explainable feature engineering (XFE) model using EEG dataset. Methods: study, a new dataset was curated, containing signals from and control groups. To extract meaningful findings dataset, presented channel-based extraction function named Zipper Pattern (ZPat). The proposed ZPat extracts features analyzing relationships between channels. selection phase XFE model, iterative neighborhood component analysis (INCA) selector used choose distinctive features. classification phase, employed ensemble distance-based classifier achieve high performance. Therefore, t-algorithm-based k-nearest neighbors (tkNN) obtain results. Directed Lobish (DLob) symbolic language derive interpretable results identities selected vectors in final ZPat-based model. Results: leave-one-record-out (LORO) 10-fold cross-validation (CV) were used. achieved over 95% accuracy on curated Moreover, connectome diagram related detection created DLob-based artificial intelligence (XAI) method. Conclusions: regard, both performance interpretability. Thus, contributes engineering, psychiatry, neuroscience, forensic sciences. is one pioneering XAI investigating criminal/criminal individuals.

Language: Английский

Citations

3
CubicPat: Investigations on the Mental Performance and Stress Detection Using EEG Signals DOI Creative Commons
Uğur İnce,

Yunus Talu,

Aleyna Duz

et al.

Diagnostics, Journal Year: 2025, Volume and Issue: 15(3), P. 363 - 363

Published: Feb. 4, 2025

Background\Objectives: Solving the secrets of brain is a significant challenge for researchers. This work aims to contribute this area by presenting new explainable feature engineering (XFE) architecture designed obtain results related stress and mental performance using electroencephalography (EEG) signals. Materials Methods: Two EEG datasets were collected detect stress. To achieve classification results, XFE model was developed, incorporating novel extraction function called Cubic Pattern (CubicPat), which generates three-dimensional vector coding channels. Classification obtained cumulative weighted iterative neighborhood component analysis (CWINCA) selector t-algorithm-based k-nearest neighbors (tkNN) classifier. Additionally, generated CWINCA Directed Lobish (DLob). Results: The CubicPat-based demonstrated both interpretability. Using 10-fold cross-validation (CV) leave-one-subject-out (LOSO) CV, introduced CubicPat-driven achieved over 95% 75% accuracies, respectively, datasets. Conclusions: interpretable deploying DLob statistical analysis.

Language: Английский

Citations

1
TATPat based explainable EEG model for neonatal seizure detection DOI Creative Commons

Türker Tuncer,

Şengül Doğan, İrem Taşçı

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 4, 2024

The most cost-effective data collection method is electroencephalography (EEG) to obtain meaningful information about the brain. Therefore, EEG signal processing very important for neuroscience and machine learning (ML). primary objective of this research detect neonatal seizures explain these using new version Directed Lobish. This uses a publicly available dataset get comparative results. In order classify signals, an explainable feature engineering (EFE) model has been proposed. EFE model, there are four essential phases phases: (i) automaton transformer-based extraction, (ii) selection deploying cumulative weight-based neighborhood component analysis (CWNCA), (iii) Lobish (DLob) Causal Connectome Theory (CCT)-based result generation (iv) classification t algorithm-based support vector (tSVM). first phase, we have used channel transformer numbers values divided into three levels named (1) high, (2) medium (3) low. By utilizing levels, created nodes (each node defines each level). extraction transition tables extracted. proposed function termed Triple Nodes Automaton-based Transition table Pattern (TATPat). contains 19 channels 9 (= 32) connection in defined automaton. Thus, presented TATPat extracts 3249 × 9) features from segment. To choose informative features, selector which CWNCA applied. cooperating findings DLob, results obtained. last phase high performance ensemble classifier (tSVM) obtained two validation techniques 10-fold cross-validation (CV) leave-one subject-out (LOSO) CV. generates DLob string by string, Moreover, attained 99.15% 76.37% accuracy LOSO CVs respectively. According performances, recommended TATPat-based good at classification. Also, artificial intelligence (XAI) since TTPat-based DLob.

Language: Английский

Citations

4
QuadTPat: Quadruple Transition Pattern-based explainable feature engineering model for stress detection using EEG signals DOI Creative Commons

Veysel Yusuf Cambay,

İrem Taşçı, Gülay TAŞCI

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 9, 2024

The most cost-effective data collection method is electroencephalography (EEG), which obtains meaningful information about the brain. Therefore, EEG signal processing crucial for neuroscience and machine learning (ML). a new stress dataset has been collected, an explainable feature engineering (XFE) model proposed using Directed Lobish (DLob) symbolic language. first phase of this research phase, was gathered from 310 participants. This collected contains two classes: (i) (ii) control. An XFE presented to detect automatically. four main phases, these are channel transformer quadruple transition pattern (QuadTPat)-based generation, selection deploying cumulative weighted neighborhood component analysis (CWNCA), (iii) results creation with DLob (iv) classification t algorithm-based k-nearest neighbors (tkNN) classifier. generates string, were obtained string. Moreover, attained 92.95% 73.63% accuracy, 10-fold leave-one subject-out (LOSO) cross-validations (CV). According performances, recommended QuadTPat-based good classification. Also, artificial intelligence (XAI) since TTPat-based cooperating DLob.

Language: Английский

Citations

4
Novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals DOI Creative Commons
Mehmet Ali Gelen,

Prabal Datta Barua,

İrem Taşçı

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 1, 2025

This paper presents a novel, explainable feature engineering framework for classifying EEG and ECG signals with high accuracy. The proposed method employs the Order Transition Pattern (OTPat) extractor. presented OTPat extractor captures both channel/column-based patterns (spatial features) using all channels each point signal/row-based (temporal by extracting features from individual overlapping blocks. extracted are then refined cumulative weighted iterative neighborhood component analysis (CWINCA) selection classified t‑algorithm k‑nearest neighbors (tkNN) classifier. Finally, two symbolic languages, Directed Lobish (DLob) Cardioish, generate interpretable results in form of cortical cardiac connectome diagrams. OTPat-based XFE model achieves over 95% accuracy on several datasets reaches 86.07% an 8‑class artifact dataset. These demonstrate performance clear interpretability, highlighting model's potential robust biomedical signal classification.

Language: Английский

Citations

0
An explainable EEG epilepsy detection model using friend pattern DOI Creative Commons
Türker Tuncer, Şengül Doğan

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 15, 2025

Language: Английский

Citations

0
TPat: Transition pattern feature extraction based Parkinson’s disorder detection using FNIRS signals DOI
Türker Tuncer, İrem Taşçı, Burak Taşçı

et al.

Applied Acoustics, Journal Year: 2024, Volume and Issue: 228, P. 110307 - 110307

Published: Sept. 27, 2024

Language: Английский

Citations

3
Automated EEG-based language detection using directed quantum pattern technique DOI
Şengül Doğan,

Türker Tuncer,

Prabal Datta Barua

et al.

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 167, P. 112301 - 112301

Published: Oct. 5, 2024

Language: Английский

Citations

2
Minimum and Maximum Pattern-Based Self-Organized Feature Engineering: Fibromyalgia Detection Using Electrocardiogram Signals DOI Creative Commons

Veysel Yusuf Cambay,

Abdul Hafeez‐Baig, Emrah Aydemir

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2708 - 2708

Published: Nov. 30, 2024

The primary objective of this research is to propose a new, simple, and effective feature extraction function investigate its classification ability using electrocardiogram (ECG) signals.

Language: Английский

Citations

2
ChMinMaxPat: Investigations on Violence and Stress Detection Using EEG Signals DOI Creative Commons
Ömer Bektaş, Serkan Kırık, İrem Taşçı

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2666 - 2666

Published: Nov. 26, 2024

Background and Objectives: Electroencephalography (EEG) signals, often termed the letters of brain, are one most cost-effective methods for gathering valuable information about brain activity. This study presents a new explainable feature engineering (XFE) model designed to classify EEG data violence detection. The primary objective is assess classification capability proposed XFE model, which uses next-generation extractor, obtain interpretable findings EEG-based stress Materials Methods: In this research, two distinct signal datasets were used results. recommended utilizes channel-based minimum maximum pattern (ChMinMaxPat) extraction function, generates 15 vectors from data. Cumulative weight-based neighborhood component analysis (CWNCA) employed select informative features these vectors. Classification performed by applying an iterative ensemble t-algorithm-based k-nearest neighbors (tkNN) classifier each vector. Information fusion achieved through majority voting (IMV), consolidates tkNN Finally, Directed Lobish (DLob) symbolic language outputs leveraging identities selected features. Together, classifier, IMV-based fusion, DLob-based transform into self-organizing (SOXFE) framework. Results: ChMinMaxPat-based over 70% accuracy on both with leave-one-record-out (LORO) cross-validation (CV) 90% 10-fold CV. For dataset, DLob strings generated, providing based representations. Conclusions: SOXFE demonstrates high interpretability in detecting signals. contributes neuroscience enabling classification, underscoring potential importance clinical forensic applications.

Language: Английский

Citations

1