The communication between the brain and external devices can be done with different methods, but at least one EEG signal recorder is needed in order to get the electrical activity of the brain plus an application to perform the processing of the raw data, moreover, an algorithm must be developed for the interpretation of the brain activity. In this paper two new adapted algorithms are proposed for EEG signal cleaning and also some basic features will be extracted in order to detect drowsiness. We used the physionet database  in order to perform these duties. Our contribution in this work is to adapt a zero-crossing filter for power supply noise removal and also the usage of the polynomial interpolation to remove the baseline artifact.
The human body generates many electrical signals that come from the action potentials. As known between the Scientifics and engineers each part of the human body delivers some signals and the difference between the electrical activities lies in two essential parameters, the first one is amplitude variation and the second one is the frequency. Our case of study in this paper; is the brain which generates many signals that can be acquired via electrodes from multiple regions of the skull. Those signals are called electroencephalographic signals (EEG).
The neural activity of the human brain starts between the 17th and 23rd week of prenatal development. It is believed that from this early stage and throughout life electrical signals generated by the brain represent not only the brain function but also the status of the whole body. This assumption plays an important role to motivate researchers for applying advanced digital signal processing methods to the electroencephalogram (EEG) signals measured from the human brain .
The EEG signals can be used to diagnosis several brain disorders like epilepsy, apnea, etc. one EEG signal that we record from one electrode consists of many waves as shown in figure (1). They are distinguished by their frequencies and their amplitude. They are called respectively alpha (α), theta (θ), beta (β), delta (), and gamma (γ). Berger mentioned about (α) and (β) in 1929, after seven years Walter announced delta () rhythm to represent all frequencies less than alpha (α) and also he called the range 4 – 7.5 Hz as theta (θ) wave. Then after that Jasper and Andrews used the symbol (γ) to describe waves which frequencies above 30Hz . The EEG signals can be used to detect drowsiness, no one can deny that this is the best way because firstly the brain is the source of all human behaviors including the sleep, that to say we are dealing with the early step of drowsiness even before it is seen in the external human body. Secondly, the EEG has many advantages over other methods of sleep detection as bellow : – EEG is perfectly noninvasive, without any exposure to radiation or high magnetic field, – EEG devices can be made small, portable and not expensive – The EEG sensor signal has a high temporal resolution and can be recorded in an open environment, – EEG can be acquired without an active response from subjects.
Hence the EEG is the most efficient method for monitoring the brain activity of healthy persons during daily life including drowsiness detection which is our target in this work  .
The raw signal consists of many noises such as line noise electronic components noise , environment magnetic interference, patient-related artifacts (muscle noise, EMG, ECG, EOG… ), etc. In order to remove these artifacts, we have to make a decision if we need to do multichannel filtering or a single-channel one. Several previous works e.g.   , the single-channel processing methods employ various techniques including linear regression, filtering, wavelet transform, and empirical mode decomposition (EMD). The whole-channel processing methods are based on BSS to estimate a set of hidden sources from an observed mixture of those sources with only limited information.
This paper gives an overview of the EEG signal and purposes of an adapted algorithm for EEG signal cleaning in order to detect drowsiness state. In the following sections, we started by characterizing the EEG signal then we mentioned all artifacts that can affect the raw EEG signal and how to remove each one of them, after that, two new adapted algorithms of cleaning are simulated using Matlab software. Finally, some features are extracted in order to detect the drowsiness.
To carrying out this paper two essential tasks have been done. The first one is EEG signal cleaning using two methods wavelet transform and zero-crossing method. The second task is the feature extraction when we mentioned about waves separation and predefined thresholding voltage. We used the physionet database  in order to perform these duties. After that next duty is to perform all measurements and processing we did in this work to real subjects in order to test the precision and the effectiveness of our algorithms.
The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.
KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.
Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.
The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.
FULL Paper PDF file:EEG signal cleaning for drowsiness detection
EEG signal cleaning for drowsiness detection
2020 International Conference on Electrical and Information Technologies (ICEIT), Rabat, Morocco, 2020, pp. 1-5,
PDF reference and original file: Click here
Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.