K-complex detection using a hybrid-synergic machine learning method
- Authors: Vu, Huy Quan , Li, Gang , Sukhorukova, Nadezda , Beliakov, Gleb , Liu, Shaowu , Philippe, Carole , Amiel, Hélène , Ugon, Adrien
- Date: 2012
- Type: Text , Journal article
- Relation: IEEE Transactions on Systems, Man and Cybernetics Part C : Applications and Reviews Vol. 42, no. 6 (2012), p. 1478-1490
- Full Text: false
- Reviewed:
- Description: Sleep stage identification is the first step in modern sleep disorder diagnostics process. K-complex is an indicator for the sleep stage 2. However, due to the ambiguity of the translation of the medical standards into a computer-based procedure, reliability of automated K-complex detection from the EEG wave is still far from expectation. More specifically, there are some significant barriers to the research of automatic K-complex detection. First, there is no adequate description of K-complex that makes it difficult to develop automatic detection algorithm. Second, human experts only provided the label for whether a whole EEG segment contains K-complex or not, rather than individual labels for each subsegment. These barriers render most pattern recognition algorithms inapplicable in detecting K-complex. In this paper, we attempt to address these two challenges, by designing a new feature extraction method that can transform visual features of the EEG wave with any length into mathematical representation and proposing a hybrid-synergic machine learning method to build a K-complex classifier. The tenfold cross-validation results indicate that both the accuracy and the precision of this proposed model are at least as good as a human expert in K-complex detection. © 1998-2012 IEEE.
- Description: 2003010569
IoT-powered deep learning brain network for assisting quadriplegic people
- Authors: Vinoj, P. , Jacob, Sunil , Menon, Varun , Balasubramanian, Venki , Piran, Md Jalil
- Date: 2021
- Type: Text , Journal article
- Relation: Computers and Electrical Engineering Vol. 92, no. (2021), p.
- Full Text: false
- Reviewed:
- Description: Brain-Computer Interface (BCI) systems have recently emerged as a prominent technology for assisting paralyzed people. Recovery from paralysis in most patients using the existing BCI-based assistive devices is hindered due to the lack of training and proper supervision. The system's continuous usage results in mental fatigue, owing to a higher user concentration required to execute the mental commands. Moreover, the false-positive rate and lack of constant control of the BCI systems result in user frustration. The proposed framework integrates BCI with a deep learning network in an efficient manner to reduce mental fatigue and frustration. The Deep learning Brain Network (DBN) recognizes the patient's intention for upper limb movement by a deep learning model based on the features extracted during training. DBN correlates and maps the different Electroencephalogram (EEG) patterns of healthy subjects with the identified pattern's upper limb movement. The stroke-affected muscles of the paralyzed are then activated using the obtained superior pattern. The implemented DBN consisting of four healthy subjects and a quadriplegic patient achieved 94% accuracy for various patient movement intentions. The results show that DBN is an excellent tool for providing rehabilitation, and it delivers sustained assistance, even in the absence of caregivers. © 2021
The effect of transcranial pulsed current stimulation at 4 and 75 Hz on electroencephalography theta and high gamma band power: A pilot study
- Authors: Dissanayaka, Thusharika , Zoghi, Maryam , Hill, Aron , Farrell, Michael , Egan, Gary , Jaberzadeh, Shapour
- Date: 2020
- Type: Text , Journal article
- Relation: Brain Connect Vol. 10, no. 9 (2020), p. 520-531
- Full Text: false
- Reviewed:
- Description: Transcranial pulsed current stimulation (tPCS) is an emerging noninvasive brain stimulation technique that has shown significant effects on cortical excitability. To date, electrophysiological measures of the efficiency of monophasic tPCS have not been reported. We aimed to explore the effects of monophasic anodal and cathodal-tPCS (a-tPCS/c-tPCS) at theta (4 Hz) and gamma (75 Hz) frequencies on theta and high gamma electroencephalography (EEG) oscillatory power. In a single-blind, randomized, sham-controlled crossover design, 15 healthy participants were randomly assigned into 5 experimental sessions in which they received a-PCS/c-tPCS at 4 and 75 Hz or sham stimulation over the left primary motor cortex (M1) for 15 min at an intensity of 1.5 mA. Changes in theta and high gamma oscillatory power were recorded at baseline, immediately after, and 30 min after stimulation using EEG at rest with eyes open. a-tPCS at 4 Hz showed a significant increase in theta power compared with sham, whereas c-tPCS at 4 Hz had no significant effect on theta power. a-tPCS at 75 Hz produced no changes in high gamma power compared with sham. Importantly, c-tPCS at 75 Hz led to a significant reduction in high gamma power compared with baseline, as well as compared with c-tPCS at 4 Hz and sham stimulation. The results demonstrate the modulation of oscillatory brain activity by monophasic tPCS, and highlight the need for future studies on a larger scale to confirm these initial findings. Impact statement Transcranial pulsed current stimulation (tPCS) is a novel brain stimulation technique. Recently, tPCS has been introduced to directly modulate brain oscillations by applying pulsatile current over the target brain area. Using both anodal and cathodal monophasic tPCS at theta and gamma frequencies, we demonstrate the ability of the stimulation to modulate brain activity. The present findings are the first direct electroencephalography evidence of an interaction between tPCS and ongoing oscillatory activity in the human motor cortex. Our work recommends tPCS as a tool for investigating human brain oscillations and open more studies in this area.
Validation of a multidirectional locomotive dual-task paradigm to evaluate task-related differences in event-related electro-cortical activity
- Authors: Duncan, Shelley , Gosling, Angela , Panchuk, Derek , Polman, Remco
- Date: 2019
- Type: Text , Journal article
- Relation: Behavioural Brain Research Vol. 361, no. (2019), p. 122-130
- Full Text: false
- Reviewed:
- Description: A fundamental aspect of everyday function is the ability to simultaneously execute both cognitive and motor tasks. The ability to perform such tasks is commonly assessed using a dual-task paradigm that has the capacity to manipulate both cognitive and motor components of an action. Dual-task performance provides an opportunity to obtain an insight into how cognitive and motor function are affected during natural tasks (e.g., locomotion). The following study aimed to determine the effectiveness of using a goal-directed multidirectional locomotor task to measure differences in task-related (tasks of increasing difficulty) electro-cortical activity. In the single-task condition participants walked around a grid-based track, performing directional changes at each intersection in response to a sensory stimulus. In the dual-task condition participants performed the same primary task while performing a simultaneous memory recall task. Behavioural differences in trial completion time and electro-cortical activity were identified in relation to the posterior N2 and P3 component mean amplitudes. The results showed that, while performing a higher-level cognitive task during walking (dual-task), interference arises in a shared system that influences neural mechanisms involved in attention and selection for action, and later cognitive processes recruited in working memory and cognitive control. This study extends previous work and shows that performing a more complex cognitive task while walking, elicits interference effects sensitive to higher-level cognitive processes, and takes the next step towards measurement of electro-cortical activity within naturalistic environments. © 2018 Elsevier B.V.