Advances in neuroimaging, genomic, motion tracking, eye-tracking and many other technology-based data collection methods have led to a torrent of high dimensional datasets, which commonly have a small number of samples because of the intrinsic high cost of data collection involving human participants. High dimensional data with a small number of samples is of critical importance for identifying biomarkers and conducting feasibility and pilot work, however it can lead to biased machine learning (ML) performance estimates. Our review of studies which have applied ML to predict autistic from non-autistic individuals showed that small sample size is associated with higher reported classification accuracy. Thus, we have investigated whether this bias could be caused by the use of validation methods which do not sufficiently control overfitting. Our simulations show that K-fold Cross-Validation (CV) produces strongly biased performance estimates with small sample sizes, and the bias is still evident with sample size of 1000. Nested CV and train/test split approaches produce robust and unbiased performance estimates regardless of sample size. We also show that feature selection if performed on pooled training and testing data is contributing to bias considerably more than parameter tuning. In addition, the contribution to bias by data dimensionality, hyper-parameter space and number of CV folds was explored, and validation methods were compared with discriminable data. The results suggest how to design robust testing methodologies when working with small datasets and how to interpret the results of other studies based on what validation method was used.
We report inkjet printing of an organic nanoparticle-based surface pre-treatment onto textiles to enable all inkjet-printed graphene e-textiles.
The electroencephalogram (EEG) is a widely used non-invasive method for monitoring the brain. It is based upon placing conductive electrodes on the scalp which measure the small electrical potentials that arise outside of the head due to neuronal action within the brain. Historically this has been a large and bulky technology, restricted to the monitoring of subjects in a lab or clinic while they are stationary. Over the last decade much research effort has been put into the creation of "wearable EEG" which overcomes these limitations and allows the long term non-invasive recording of brain signals while people are out of the lab and moving about. This paper reviews the recent progress in this field, with particular emphasis on the electrodes used to make connections to the head and the physical EEG hardware. The emergence of conformal "tattoo" type EEG electrodes is highlighted as a key next step for giving very small and socially discrete units. In addition, new recommendations for the performance validation of novel electrode technologies are given, with standards in this area seen as the current main bottleneck to the wider take up of wearable EEG. The paper concludes by considering the next steps in the creation of next generation wearable EEG units, showing that a wide range of research avenues are present.
Electroencephalography (EEG) is a procedure that records brain activity in a non-invasive manner. The cost and size of EEG devices has decreased in recent years, facilitating a growing interest in wearable EEG that can be used out-of-the-lab for a wide range of applications, from epilepsy diagnosis, to stroke rehabilitation, to Brain-Computer Interfaces (BCI). A major obstacle for these emerging applications is the wet electrodes, which are used as part of the EEG setup. These electrodes are attached to the human scalp using a conductive gel, which can be uncomfortable to the subject, causes skin irritation, and some gels have poor long-term stability. A solution to this problem is to use dry electrodes, which do not require conductive gel, but tend to have a higher noise floor. This paper presents a novel methodology for the design and manufacture of such dry electrodes. We manufacture the electrodes using low cost desktop 3D printers and off-the-shelf components for the first time. This allows quick and inexpensive electrode manufacturing and opens the possibility of creating electrodes that are customized for each individual user. Our 3D printed electrodes are compared against standard wet electrodes, and the performance of the proposed electrodes is suitable for BCI applications, despite the presence of additional noise.
Study Objectives Closed-loop auditory stimulation (CLAS) is a method for enhancing slow oscillations (SOs) through the presentation of auditory clicks during sleep. CLAS boosts SOs amplitude and sleep spindle power, but the optimal timing for click delivery remains unclear. Here, we determine the optimal time to present auditory clicks to maximize the enhancement of SO amplitude and spindle likelihood. Methods We examined the main factors predicting SO amplitude and sleep spindles in a dataset of 21 young and 17 older subjects. The participants received CLAS during slow-wave-sleep in two experimental conditions: sham and auditory stimulation. Post-stimulus SOs and spindles were evaluated according to the click phase on the SOs and compared between and within conditions. Results We revealed that auditory clicks applied anywhere on the positive portion of the SO increased SO amplitudes and spindle likelihood, although the interval of opportunity was shorter in the older group. For both groups, analyses showed that the optimal timing for click delivery is close to the SO peak phase. Click phase on the SO wave was the main factor determining the impact of auditory stimulation on spindle likelihood for young subjects, whereas for older participants, the temporal lag since the last spindle was a better predictor of spindle likelihood. Conclusions Our data suggest that CLAS can more effectively boost SOs during specific phase windows, and these differ between young and older participants. It is possible that this is due to the fluctuation of sensory inputs modulated by the thalamocortical networks during the SO.
Highly miniaturised, wearable computing and communication systems allow unobtrusive, convenient and long term monitoring of a range of physiological parameters. For long term operation from the physically smallest batteries, the average power consumption of a wearable device must be very low. It is well known that the overall power consumption of these devices can be reduced by the inclusion of low power consumption, real-time compression of the raw physiological data in the wearable device itself. Compressive sensing is a new paradigm for providing data compression: it has shown significant promise in fields such as MRI; and is potentially suitable for use in wearable computing systems as the compression process required in the wearable device has a low computational complexity. However, the practical performance very much depends on the characteristics of the signal being sensed. As such the utility of the technique cannot be extrapolated from one application to another. Long term electroencephalography (EEG) is a fundamental tool for the investigation of neurological disorders and is increasingly used in many non-medical applications, such as brain-computer interfaces. This article investigates in detail the practical performance of different implementations of the compressive sensing theory when applied to scalp EEG signals.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.