Imagined Object Recognition Using EEG-Based Neurological Brain Signals

Saini, Rajkumar; Prabhu, Sameer; Upadhyay, Richa; Rakesh, Sumit; Chippa, Prakash Chandra; Mokayed, Hamam; Liwicki, Marcus; Liwicki, Foteini

doi:10.1007/978-3-031-07005-1_26

Cited by 5 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The models include Gaussian Naive Bayes (NB), K-Nearest Neighbors (KNN), Linear Support Vector Machine (SVM), Random Forest, Gradient Boost, and XGBoost. These models were evaluated using different sets of features derived from electroencephalogram (EEG) data (statistical and wavelet) 31 , Wacom tablet data 32 , or a combination of both. Feature extraction is a process in which relevant information is extracted from raw data to represent it in a more compact and meaningful form.…”

Section: Technical Validationmentioning

confidence: 99%

“…The feature extraction process from EEG signals involves normalizing (Z-score normalization) the data channel-wise to ensure consistency. Several statistical features 31 are derived from the normalized data, including the sum of values, energy, standard deviation, root mean square (RMS), skewness, and kurtosis. These features capture the overall activity, power, variability, magnitude, asymmetry, and peakedness of the signals.…”

Section: Technical Validationmentioning

confidence: 99%

“…These features capture the overall activity, power, variability, magnitude, asymmetry, and peakedness of the signals. Wavelets have also been used to extract wavelet-based features 31,33 from EEG signals. In this work, the DB4 wavelet is used for the wavelet decomposition of the EEG signals.…”

Section: Technical Validationmentioning

confidence: 99%

“…(GPU: single V100 NVidia) Machine (SVM), Random Forest, Gradient Boost, XGBoost, EEGNet, and ResNet50 similar to24 . These models were evaluated using different sets of features derived from electroencephalogram (EEG) data (statistical and wavelet)25 , Wacom tablet data26 , or a combination of both. Feature extraction is a process in which relevant information is extracted from raw data to represent it in a more compact and meaningful form.…”

mentioning

confidence: 99%

See 3 more Smart Citations

SignEEG v1.0 : Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

Mishra,

Kumar,

Gupta

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Noninvasive electroencephalography (EEG) is a method for measuring electrical brain activity from the surface of the scalp. Recent developments in artificial intelligence accelerate the automatic recognition of brain patterns, allowing more reliable and increasingly faster Brain-Computer interfaces, including biometric applications. Biometric research is also focusing on multimodal systems using EEG along with other modalities. This paper presents a new multimodalSignEEG v1.0dataset based on EEG and hand-drawn signatures from 70 subjects. EEG signals and hand-drawn signatures have been collected withEmotiv InsightandWacom Onesensors, respectively. The multimodal data consists of three paradigms with increasing brain functioning: (i) visualizing a signature image, (ii) doing a signature in mind, and (iii) physically drawing a signature. Extensive experiments have been done in order to provide a solid baseline with machine learning classifiers. We release the raw, pre-processed data and easy-to-follow implementation details.

show abstract

Section: Technical Validationmentioning

confidence: 99%

Section: Technical Validationmentioning

confidence: 99%

Section: Technical Validationmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

SignEEG v1.0 : Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

Mishra,

Kumar,

Gupta

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Imagined speech classification exploiting EEG power spectrum features

Hossain,

Khan,

Kader

2024

Med Biol Eng Comput

View full text Add to dashboard Cite

SignEEG v1.0: Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

Mishra,

Kumar,

Gupta

et al. 2024

Sci Data

Self Cite

View full text Add to dashboard Cite

Handwritten signatures in biometric authentication leverage unique individual characteristics for identification, offering high specificity through dynamic and static properties. However, this modality faces significant challenges from sophisticated forgery attempts, underscoring the need for enhanced security measures in common applications. To address forgery in signature-based biometric systems, integrating a forgery-resistant modality, namely, noninvasive electroencephalography (EEG), which captures unique brain activity patterns, can significantly enhance system robustness by leveraging multimodality’s strengths. By combining EEG, a physiological modality, with handwritten signatures, a behavioral modality, our approach capitalizes on the strengths of both, significantly fortifying the robustness of biometric systems through this multimodal integration. In addition, EEG’s resistance to replication offers a high-security level, making it a robust addition to user identification and verification. This study presents a new multimodal SignEEG v1.0 dataset based on EEG and hand-drawn signatures from 70 subjects. EEG signals and hand-drawn signatures have been collected with Emotiv Insight and Wacom One sensors, respectively. The multimodal data consists of three paradigms based on mental, & motor imagery, and physical execution: i) thinking of the signature’s image, (ii) drawing the signature mentally, and (iii) drawing a signature physically. Extensive experiments have been conducted to establish a baseline with machine learning classifiers. The results demonstrate that multimodality in biometric systems significantly enhances robustness, achieving high reliability even with limited sample sizes. We release the raw, pre-processed data and easy-to-follow implementation details.

show abstract

Imagined Object Recognition Using EEG-Based Neurological Brain Signals

Cited by 5 publications

References 26 publications

SignEEG v1.0 : Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

SignEEG v1.0 : Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

Imagined speech classification exploiting EEG power spectrum features

SignEEG v1.0: Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

Contact Info

Product

Resources

About