EEG Signal Processing and Machine Learning. Saeid Sanei

−60 to 10 mV. During this process [23]:

      1 When the dendrites of a nerve cell receive the stimulus the Na+ channels will open.

      2 If the opening is sufficient to drive the interior potential from −70 mV up to −55 mV, the process continues.

      3 As soon as the action threshold is reached, additional Na+ channels (sometimes called voltage‐gated channels) open. The Na+ influx drives the interior of the cell membrane up to about +30 mV. The process to this point is called depolarization.

      4 Then Na+ channels close and the K+ channels open. Since the K+ channels are much slower to open, the depolarization has time to be completed. Having both Na+ and K+ channels open at the same time would drive the system towards neutrality and prevent the creation of the AP.Figure 1.5 Changing the membrane potential for a giant squid by closing the Na channels and opening K channels.(Source: adapted from Ka Xiong Charand [23].)

      5 Having the K+ channels open, the membrane begins to repolarize back towards its rest potential.

      6 The repolarization typically overshoots the rest potential to a level of approximately −90 mV. This is called hyperpolarization, and would seem to be counterproductive, but it is actually important in the transmission of information. Hyperpolarization prevents the neuron from receiving another stimulus during this time, or at least raises the threshold for any new stimulus. Part of the importance of hyperpolarization is in preventing any stimulus already sent up an axon from triggering another AP in the opposite direction. In other words, hyperpolarization assures that the signal is proceeding in one direction.

      After hyperpolarization, the Na⁺/K⁺ pumps eventually bring the membrane back to its resting state of −70 mV.

      The nerve requires approximately two milliseconds before another stimulus is presented. During this time no AP can be generated. This is called the refractory period. The generation of EEG signals is next described.

1.5 EEG Generation

      An EEG signal is an indirect measurement of currents that flow during synaptic excitations of the dendrites of many pyramidal neurons in the cerebral cortex. When the brain cells (neurons) are activated, the synaptic currents are produced and propagate through the dendrites. This current generates a magnetic field measurable by EMG machines and a secondary electrical field over the scalp measurable by EEG systems.

Figure 1.6 Structure of a neuron.

Figure 1.7 The head layers from brain to scalp.

Differences of electrical potentials are caused by summed post‐synaptic graded potentials from pyramidal cells that create electrical dipoles between the soma (body of a neuron) and apical dendrites which branch from neurons (Figure 1.6). The current in the brain is generated mostly due to pumping the positive ions of sodium, Na⁺, potassium, K⁺, calcium, or Ca⁺⁺, and the negative ion of Cl⁻, through the neuron membranes in the direction governed by the membrane potential [24].

The human head consists of three main layers of scalp, skull, brain (Figure 1.7) including many other thin layers in‐between. In addition, the scalp consists of different layers such as skin, connective tissue, which is a thin layer of fat and fibrous tissue lying beneath the skin, the loose areolar connective tissue, and the pericranium, which is the periosteum of the skull bones and provides nutrition to bone and capacity for repair. Conversely, the brain is covered by a thin layer of cortex, which encompasses various brain tissues. The cortex includes arachnoid, meninges, dura, epidural, and subarachnoid space. The skull attenuates the signals approximately one hundred times more than the soft tissue. Conversely, most of the noise is generated either within the brain (internal noise) or over the scalp (system noise or external noise). Therefore, only large populations of active neurons can generate enough potential to be recordable using the scalp electrodes. These signals are later amplified greatly for display purposes. Approximately 10¹¹ neurons are developed at birth when the CNS becomes complete and functional [25]. This makes an average of 10⁴ neurons per cubic millimetre. Neurons are interconnected into neural nets through synapses. Adults have approximately 5.10¹⁴ synapses. The number of synapses per neuron increases with age, whereas the number of neurons decreases with age.

      Given the diversity in electric and dielectric properties of the head layers, the distribution of attenuation of brain discharges including cortical, subcortical, and hippocampal activities is not uniform over the scalp and is subject to nonlinearity. Therefore, to model the neuronal pathways or localization of brain activity sources an accurate head electrical model should be available.

From an anatomical point of view the brain may be divided into three parts: the cerebrum, cerebellum, and brain stem (Figure 1.8). The cerebrum consists of both left and right lobes of the brain with highly convoluted surface layers called the cerebral cortex.

      The cerebrum includes the regions for movement initiation, conscious awareness of sensation, complex analysis, and expression of emotions and behaviour. The cerebellum coordinates voluntary movements of muscles and balance maintaining.

      The brain stem controls involuntary functions such as respiration, heart regulation, biorhythms, neurohormones, and hormone secretion [26].

      The study of EEG paves the way for diagnosis of many neurological disorders and other abnormalities in the human body. The acquired EEG signals from a human (and also from animals) may for example be used for investigation of the following clinical problems [26, 27]:

       Monitoring alertness, coma, and brain death.

       Locating areas of damage following head injury, stroke, and tumour.

       Testing afferent pathways (by EPs).

       Monitoring cognitive engagement (alpha rhythm).

       Producing biofeedback situations.

       Controlling anaesthesia depth (servo anaesthesia).

       Investigating epilepsy and locating seizure origin.

       Testing epilepsy drug effects.

       Assisting in experimental cortical excision of epileptic focus.

       Monitoring the brain development.

       Testing drugs for convulsive effects.

       Investigating sleep disorders and physiology.

       Investigating mental disorders. Figure 1.8 Diagrammatic representation of the major parts of the brain.

       Recognition of emotions for autistics.

       Monitoring mental fatigue for pilots and drivers.

       Providing a hybrid data recording system together with other imaging modalities.

       This list confirms the rich potential for EEG analysis and motivates the need for advanced signal processing techniques to aid the clinician in their interpretation. We next proceed to describe the brain rhythms, which are expected to be measured within EEG signals.

       Some