Nibras AboAlzahab

Mr. Nibras AboAlzahab

Marche Polytechnic University Ancona
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 January 2021 in Brain Sciences
Verified
Journal Article
Open access
PDF file
Nibras AboAlzahabNibras AboAlzahab
Nibras AboAlzahab
LALuca Apollonio
Luca Apollonio
AIAngelo Di Iorio
Angelo Di Iorio
MAMuaaz Alshalak
Muaaz Alshalak
SISabrina Iarlori
Sabrina Iarlori
Camillo PorcaroCamillo Porcaro
Camillo Porcaro
Background: Brain-Computer Interface (BCI) is becoming more reliable, thanks to the advantages of Artificial Intelligence (AI). Recently, hybrid Deep Learning (hDL), which combines different DL algorithms, has gained momentum over the past five years. In this work, we proposed a review on hDL-based BCI starting from the seminal studies in 2015. Objectives: We have reviewed 47 papers that apply hDL to the BCI system published between 2015 and 2020 extracting trends and highlighting relevant aspects to the topic. Methods: We have queried four scientific search engines (Google Scholar, PubMed, IEEE Xplore and Elsevier Science Direct) and different data items were extracted from each paper such as the database used, kind of application, online/offline training, tasks used for the BCI, pre-processing methodology adopted, type of normalization used, which kind of features were extracted, type of DL architecture used, number of layers implemented and which optimization approach were used as well. All these items were then investigated one by one to uncover trends. Results: Our investigation reveals that Electroencephalography (EEG) has been the most used technique. Interestingly, despite the lower Signal-to-Noise Ratio (SNR) of the EEG data that makes pre-processing of that data mandatory, we have found that the pre-processing has only been used in 21.28% of the cases by showing that hDL seems to be able to overcome this intrinsic drawback of the EEG data. Temporal-features seem to be the most effective with 93.94% accuracy, while spatial-temporal features are the most used with 33.33% of the cases investigated. The most used architecture has been Convolutional Neural Network-Recurrent Neural Network CNN-RNN with 47% of the cases. Moreover, half of the studies have used a low number of layers to achieve a good compromise between the complexity of the network and computational efficiency. Significance: To give useful information to the scientific community, we make our summary table of hDL-based BCI papers available and invite the community to published work to contribute to it directly. We have indicated a list of open challenges, emphasizing the need to use neuroimaging techniques other than EEG, such as functional Near-Infrared Spectroscopy (fNIRS), deeper investigate the advantages and disadvantages of using pre-processing and the relationship with the accuracy obtained. To implement new combinations of architectures, such as RNN-based and Deep Belief Network DBN-based, it is necessary to better explore the frequency and temporal-frequency features of the data at hand.

21 October 2024 in SoftwareX
Verified
Journal Article
Open access
Nibras AboAlzahabNibras AboAlzahab
Nibras AboAlzahab
GRGiulia Rafaiani
Giulia Rafaiani
MBMassimo Battaglioni
Massimo Battaglioni
ACAna Cavalli
Ana Cavalli
FCFranco Chiaraluce
Franco Chiaraluce
MBMarco Baldi
Marco Baldi

28 October 2024 in Data in Brief
Verified
Journal Article
Open access
Nibras AboAlzahabNibras AboAlzahab
Nibras AboAlzahab
AIAngelo Di Iorio
Angelo Di Iorio
LALuca Apollonio
Luca Apollonio
MAMuaaz Alshalak
Muaaz Alshalak
AGAlessandro Gravina
Alessandro Gravina
BABilal Alchalabi
Bilal Alchalabi
This work aims to assess the use of electroencephalographic (EEG) signals as a means of biometric authentication. More than 240 recordings, each lasting 2 min, were gathered from 20 subjects involved in the data collection. Data include the results of experiments performed both in a resting state and in the presence of auditory stimuli. The resting-state EEG signals were acquired with both open and closed eyes. The auditory stimuli EEG signals consist of six experiments divided into two scenarios. The first scenario considers in-ear stimuli, while the second scenario considers bone-conducting stimuli. For each of the two scenarios, experiments include a native language song, a non-native language song and some neutral music. This data could be used to develop biometric systems for authentication or identification. Additionally, they could be used to study the effect of auditory stimuli such as music on EEG activity and to compare it with the resting state condition.

11 December 2024
Verified
Conference Paper
Closed access
Nibras AboAlzahabNibras AboAlzahab
Nibras AboAlzahab
ABAhmad Adnan Bsis Biomedical
Ahmad Adnan Bsis Biomedical
NANour Alshawa
Nour Alshawa
In the field of Brain-Computer Interface (BCI), electroencephalography, commonly referred to as EEG, is a neuroimaging technology that experiences widespread application. EEG signals, on the other hand, are susceptible to a wide variety of noises and artifacts, which can lead to a decrease in the quality of the data. Using transformer-based architectures, including attention-based models, the purpose of this research is to establish an automatic approach for reconstructing noisy EEG channels. There were three different noise scenarios that were taken into consideration, and they were zero-mashing, noise masking, and zero-noise masking. The reconstructing model combines convulsion neural networks (CNN) with a multi-head self attehtion transformer model. We designed the model to balance both performance and sustainability considerations. The findings indicate that the model was able to accomplish a high level of reconstructing skills, as indicated by the value of R2, which is equivalent to 0.8563 within a margin of error of 0.0543. In addition, considerations of sustainability were taken into account for the actual execution where the model size was restricted to less than 0.5 MB.

19 March 2024 in arXiv
Verified
Preprint
Open access
PDF file
Nibras AboAlzahabNibras AboAlzahab
Nibras AboAlzahab
Lorenzo ScaliseLorenzo Scalise
Lorenzo Scalise
Marco BaldiMarco Baldi
Marco Baldi
In the quest for optimal EEG-based biometric authentication, this study investigates the pivotal balance for accurate identification without sacrificing performance or adding unnecessary computational complexity. Through a methodical exploration of segment durations, and employing a variety of sophisticated machine learning models, the research seeks to pinpoint a threshold where EEG data provides maximum informational yield for authentication purposes. The findings are set to advance the field of non-invasive biometric technologies, proposing a practical approach to secure and user-friendly identity verification systems while also raising considerations for the real-world application of EEG-based biometric authentication beyond controlled environments.