Robustness of functional connectivity metrics for EEG-based personal identification over task-induced intra-class and inter-class variations

Fraschini, Matteo; Pani, Sara Maria; Didaci, Luca; Marcialis, Gian Luca

doi:10.1016/j.patrec.2019.03.025

Cited by 54 publications

(49 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• The proposed method is sensitive to inter-class variety as well as intra-class variety and can find and retrieve the most similar images, despite the diversity within the class [45,46];…”

Section: Visual Representation Of Proposed Method's Retrieval For Cormentioning

confidence: 99%

An efficient image descriptor for image classification and CBIR

Shakarami¹,

Tarrah

2020

Optik

View full text Add to dashboard Cite

Pattern recognition and feature extraction of images always have been important subjects in improving the performance of image classification and Content-Based Image Retrieval (CBIR). Recently, Machine Learning and Deep Learning algorithms are utilized widely in order to achieve these targets. In this research, an efficient method for image description is proposed which is developed by Machine Learning and Deep Learning algorithms. This method is created using combination of an improved AlexNet Convolutional Neural Network (CNN), Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) descriptors. Furthermore, the Principle Component Analysis (PCA) algorithm has been used for dimension reduction. The experimental results demonstrate the superiority of the offered method compared to existing methods by improving the accuracy, mean Average Precision (mAP) and decreasing the complex computation. The experiments have been run on Corel-1000, OT and FP datasets.

show abstract

Section: Visual Representation Of Proposed Method's Retrieval For Cormentioning

confidence: 99%

An efficient image descriptor for image classification and CBIR

Shakarami¹,

Tarrah

2020

Optik

View full text Add to dashboard Cite

show abstract

“…In summary, the state-of-the-art reports different approaches for subject identification. There are some proposals for feature extraction [4], [9], for classification [3], [4], [9], [10] and others using different neuro-paradigms [4], [11]- [14]. In addition, more aspects of the subject can be exploited to improve the performances of the proposals.…”

Section: Related Workmentioning

confidence: 99%

Event-related potential from EEG for a two-step Identity Authentication System

Moctezuma

Molinas

2019

2019 IEEE 17th International Conference on Industrial Informatics (INDIN)

View full text Add to dashboard Cite

Current problems related to high-level security access are increasing, leaving organizations and persons unsafe. A recent good candidate to create a robust identity authentication system is based on brain signals recorded with electroencephalograms (EEG). In this paper, EEG-based brain signals of 56 channels, from event-related potentials (ERPs), are used for Subject identification. The ERPs are from positive or negative feedback-related responses of a P300-speller system. The feature extraction part was done with empirical mode decomposition (EMD) extracting 2 intrinsic mode functions (IMFs) per channel, that were selected based on the Minkowski distance. After that, 4 features are computed per IMF; 2 energy features (instantaneous and teager energy) and 2 fractal features (Higuchi and Petrosian fractal dimension). Support vector machine (SVM) was used for the classification stage with an accuracy index computed using 10folds cross-validation for evaluating the classifier's performance. Since high-density EEG information was available, the wellknown backward-elimination and forward-addition greedy algorithms were used to reduce or increase the number of channels, step by step. Using the proposed method for subject identification from a positive or negative feedback-related response and then identify the subject will add a layer to improve the security system. The results obtained show that subject identification is feasible even using a low number of channels: E.g., 0.89 of accuracy using 5 channels with a mixed population and 0.93 with a male-only population.

show abstract

“…Electroencephalographic (EEG) time-frequency [8] and connectivity-based [9], [10] features have shown subject-specific characteristics comparable in terms of performance to other more common fingerprints. Nevertheless, the performance of EEG-based biometric systems seems to be not independent from the specific connectivity metric, scarcely investigated in terms of permanence and tend to decrease in a between-tasks scenario [11]. From this new perspective, with the clear evidence that functional brain networks vary across individuals, few studies investigated to what extent these subject-specific traits are stable over time and over different states.…”

Section: Introductionmentioning

confidence: 99%

“…PSD has been shown to capture relevant subject-specific information [8] and represents one of the more simple and interpretable EEG features. PLV, in combination with weighted Minimum Norm Estimator (wMNE) [16], provides a good estimate of the functional brain organization in EEG [17] and, despite the PLV is not completely independent from the PSD [18], is known to be affected by volume conduction and signal leakage, it still performs better than other common connectivity metrics in terms of subject authentication [11]. Moreover, as previously stated, the PLV was recently used at scalp-level to investigate variability and stability of largescale cortical oscillation patterns [13].…”

Section: Introductionmentioning

confidence: 99%

Subject, session and task effects on power, connectivity and network centrality: A source-based EEG study

Pani

Ciuffi

Demuru

et al. 2020

Biomedical Signal Processing and Control

Self Cite

View full text Add to dashboard Cite

Inter-subjects' variability in functional brain networks has been extensively investigated in the last few years. In this context, unveiling subject-specific characteristics of EEG features may play an important role for both clinical (e.g., biomarkers) and bio-engineering purposes (e.g., biometric systems and brain computer interfaces). Nevertheless, the effects induced by multi-sessions and task-switching are not completely understood and considered. In this work, we aimed to investigate how the variability due to subject, session and task affects EEG power, connectivity and network features estimated using sourcereconstructed EEG time-series. Our results point out a remarkable ability to identify subject-specific EEG traits within a given task together with striking independence from the session. The results also show a relevant effect of task-switching, which is comparable to individual variability. This study suggests that power and connectivity EEG features may be adequate to detect stable (over-time) individual properties within predefined and controlled tasks.

show abstract

Robustness of functional connectivity metrics for EEG-based personal identification over task-induced intra-class and inter-class variations

Cited by 54 publications

References 26 publications

An efficient image descriptor for image classification and CBIR

An efficient image descriptor for image classification and CBIR

Event-related potential from EEG for a two-step Identity Authentication System

Subject, session and task effects on power, connectivity and network centrality: A source-based EEG study

Contact Info

Product

Resources

About