Enthusiaathed Junior researcher who is interested in the brain and neuroscience. In particular, Brain-Computer Interface (BCI) systems.Currently, Master's Student at UNIVPM, Italy
This data set consists of over **** 240 two-minute EEG **** recordings **** obtained from 20 volu... more This data set consists of over **** 240 two-minute EEG **** recordings **** obtained from 20 volunteers. Resting-state **** and auditory stimuli experiments are included in the data. The goal is to develop an EEG-based Biometric system. The data includes resting-state EEG signals in both cases: eyes open and eyes closed. The auditory stimuli part consists of six experiments; Three with in- ear auditory stimuli and another three with bone-conducting auditory stimuli. The three stimuli for each case are a native song, a non-native song, and neutral music.
Background: Brain-Computer Interface (BCI) is becoming more reliable, thanks to the advantages of... more 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 a...
2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA), 2021
Opposed to classic authentication protocols based on credentials, biometric-based authentication ... more Opposed to classic authentication protocols based on credentials, biometric-based authentication has recently emerged as a promising paradigm for achieving fast and secure authentication of users. Among the several families of biometric features, electroencephalogram (EEG)-based biometrics is considered as a promising approach due to its unique characteristics. Classification systems based on machine learning allow processing of large amounts of data and performing accurate attribution of each signal to the most relevant group, thus representing an invaluable tool for EEG-based biometrics. This paper provides an experimental evaluation of the performance achievable by EEG-based biometrics employing machine learning. We consider several groups of EEG signals and propose a suitable feature extraction criterion. Then, the extracted features are used along with neural network-based classification algorithms, K Nearest Neighbours (KNN), and eXtreme Gradient Boost (XGBoost) for attributin...
Background: Brain-Computer Interface (BCI) is becoming more reliable, thanks to the
advantages of... more 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.
Day-by-day, artificial intelligence becomes more and more important in the field of healthcare. O... more Day-by-day, artificial intelligence becomes more and more important in the field of healthcare. One important application is Brain-Computer Interface (BCI) which has many advances in enhancing the life quality of patients who suffers from paralysis for a reason or another. Motor-Imaginary BCI (MI-BCI) is mostly used to control robotics and mechatronic systems, for example robotic arms, orthosis, prothesis and exoskeletons. This research evaluates the effect of different features on classification process of EEG signal in MI-BCI systems. In this study, five healthy subjects performed trailing imagery in order to acquire EEG signal dataset. Five feature groups were extracted (Power Spectral Density (PSD), Amplitude mean (AM), Standard Deviation (STD), Shannon Entropy (SE) and Differential Entropy (DE)) from EEG signal in MI-BCI of five different subjects. The features groups are classified using five classification technique "ANN, Decision tree, LDA, SVM, and KNN. The influence of features groups in classification performance was compared separately according to three classifier criteria (Accuracy, Precision and MCC). One-way ANOVA test was used to compare influence of features groups in classification performance. For classification accuracy and precision, significant differences were obtained in SVM and ANN classifiers for pairs of features which is fairly supported by the experimental and statistical data. The results of the research show that Power Spectral Density (PSD) feature shows great ability to describe EEG signal in MI-BCI field and considered as an effective feature in binary classifiers. Additionally, Differential Entropy (DE) is considered as a promising feature to be used in MI-BCI field. The results of this study will be used for developing bio-robots, bio-mechanical, and bio-mechatronic systems in ACIA Lab.
A pneumatically actuated antagonistic pair of muscles with joint mechanism (APMM) is supported an... more A pneumatically actuated antagonistic pair of muscles with joint mechanism (APMM) is supported and developed to be essential for bionic and biomimetic applications to emulate the biological muscles by realizing various kinds of locomotion based on normal electrical activity of biological muscles. This Paper aims to compare the response of antagonistic pairs of muscles mechanism (APMM) based on the pneumatic artificial muscles (PAMs) to an EMG signal that was acquired throw a designed circuit and an EMG Laboratory acquisition kit. The response is represented as a joint rotary displacement generated by the contraction and extension of the pneumatic artificial muscles. A statistical study was done to prove the efficiency of the designed circuit the response of antagonistic pairs of muscles mechanism. The statistical result showed that there is no significant difference of voltage data in both EMG acquired signal between reference kit and designed circuit. An excellent correlation behavior between the EMG control signal and the response of APMM as an angular displacement has been discussed and statistically analyzed.
This data set consists of over **** 240 two-minute EEG **** recordings **** obtained from 20 volu... more This data set consists of over **** 240 two-minute EEG **** recordings **** obtained from 20 volunteers. Resting-state **** and auditory stimuli experiments are included in the data. The goal is to develop an EEG-based Biometric system. The data includes resting-state EEG signals in both cases: eyes open and eyes closed. The auditory stimuli part consists of six experiments; Three with in- ear auditory stimuli and another three with bone-conducting auditory stimuli. The three stimuli for each case are a native song, a non-native song, and neutral music.
Background: Brain-Computer Interface (BCI) is becoming more reliable, thanks to the advantages of... more 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 a...
2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA), 2021
Opposed to classic authentication protocols based on credentials, biometric-based authentication ... more Opposed to classic authentication protocols based on credentials, biometric-based authentication has recently emerged as a promising paradigm for achieving fast and secure authentication of users. Among the several families of biometric features, electroencephalogram (EEG)-based biometrics is considered as a promising approach due to its unique characteristics. Classification systems based on machine learning allow processing of large amounts of data and performing accurate attribution of each signal to the most relevant group, thus representing an invaluable tool for EEG-based biometrics. This paper provides an experimental evaluation of the performance achievable by EEG-based biometrics employing machine learning. We consider several groups of EEG signals and propose a suitable feature extraction criterion. Then, the extracted features are used along with neural network-based classification algorithms, K Nearest Neighbours (KNN), and eXtreme Gradient Boost (XGBoost) for attributin...
Background: Brain-Computer Interface (BCI) is becoming more reliable, thanks to the
advantages of... more 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.
Day-by-day, artificial intelligence becomes more and more important in the field of healthcare. O... more Day-by-day, artificial intelligence becomes more and more important in the field of healthcare. One important application is Brain-Computer Interface (BCI) which has many advances in enhancing the life quality of patients who suffers from paralysis for a reason or another. Motor-Imaginary BCI (MI-BCI) is mostly used to control robotics and mechatronic systems, for example robotic arms, orthosis, prothesis and exoskeletons. This research evaluates the effect of different features on classification process of EEG signal in MI-BCI systems. In this study, five healthy subjects performed trailing imagery in order to acquire EEG signal dataset. Five feature groups were extracted (Power Spectral Density (PSD), Amplitude mean (AM), Standard Deviation (STD), Shannon Entropy (SE) and Differential Entropy (DE)) from EEG signal in MI-BCI of five different subjects. The features groups are classified using five classification technique "ANN, Decision tree, LDA, SVM, and KNN. The influence of features groups in classification performance was compared separately according to three classifier criteria (Accuracy, Precision and MCC). One-way ANOVA test was used to compare influence of features groups in classification performance. For classification accuracy and precision, significant differences were obtained in SVM and ANN classifiers for pairs of features which is fairly supported by the experimental and statistical data. The results of the research show that Power Spectral Density (PSD) feature shows great ability to describe EEG signal in MI-BCI field and considered as an effective feature in binary classifiers. Additionally, Differential Entropy (DE) is considered as a promising feature to be used in MI-BCI field. The results of this study will be used for developing bio-robots, bio-mechanical, and bio-mechatronic systems in ACIA Lab.
A pneumatically actuated antagonistic pair of muscles with joint mechanism (APMM) is supported an... more A pneumatically actuated antagonistic pair of muscles with joint mechanism (APMM) is supported and developed to be essential for bionic and biomimetic applications to emulate the biological muscles by realizing various kinds of locomotion based on normal electrical activity of biological muscles. This Paper aims to compare the response of antagonistic pairs of muscles mechanism (APMM) based on the pneumatic artificial muscles (PAMs) to an EMG signal that was acquired throw a designed circuit and an EMG Laboratory acquisition kit. The response is represented as a joint rotary displacement generated by the contraction and extension of the pneumatic artificial muscles. A statistical study was done to prove the efficiency of the designed circuit the response of antagonistic pairs of muscles mechanism. The statistical result showed that there is no significant difference of voltage data in both EMG acquired signal between reference kit and designed circuit. An excellent correlation behavior between the EMG control signal and the response of APMM as an angular displacement has been discussed and statistically analyzed.
Uploads
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.
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.