scholarly journals Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

2019 ◽  
Author(s):  
David Sabbagh ◽  
Pierre Ablin ◽  
Gaël Varoquaux ◽  
Alexandre Gramfort ◽  
Denis A. Engemann
Keyword(s):  
Ground Truth ◽  
Spatial Filtering ◽  
Supervised Machine Learning ◽  
Brain Dynamics ◽  
Source Power ◽  
Relative Contribution ◽  
Cognitive States ◽  
The Subject ◽  
Eeg Recordings ◽  
Generative Mechanisms

AbstractPredicting biomedical outcomes from Magnetoencephalography and Electroencephalography (M/EEG) is central to applications like decoding, brain-computer-interfaces (BCI) or biomarker development and is facilitated by supervised machine learning. Yet most of the literature is concerned with classification of outcomes defined at the event-level. Here, we focus on predicting continuous outcomes from M/EEG signal defined at the subject-level, and analyze about 600 MEG recordings from Cam-CAN dataset and about 1000 EEG recordings from TUH dataset. Considering different generative mechanisms for M/EEG signals and the biomedical outcome, we propose statistically-consistent predictive models that avoid source-reconstruction based on the covariance as representation. Our mathematical analysis and ground truth simulations demonstrated that consistent function approximation can be obtained with supervised spatial filtering or by embedding with Riemannian geometry. Additional simulations revealed that Riemannian methods were more robust to model violations, in particular geometric distortions induced by individual anatomy. To estimate the relative contribution of brain dynamics and anatomy to prediction performance, we propose a novel model inspection procedure based on biophysical forward modeling. Applied to prediction of outcomes at the subject-level, the analysis revealed that the Riemannian model better exploited anatomical information while sensitivity to brain dynamics was similar across methods. We then probed the robustness of the models across different data cleaning options. Environmental denoising was globally important but Riemannian models were strikingly robust and continued performing well even without preprocessing. Our results suggest each method has its niche: supervised spatial filtering is practical for event-level prediction while the Riemannian model may enable simple end-to-end learning.

Chromosomal Patterns of Microsatellite Variability Contrast Sharply in African and Non-African Populations of Drosophila melanogaster

Genetics ◽  
2002 ◽  
Vol 160 (1) ◽  
pp. 247-256
Author(s):  
M Kauer ◽  
B Zangerl ◽  
D Dieringer ◽  
C Schlötterer
Keyword(s):  
Chromosomal Polymorphism ◽  
Background Selection ◽  
Selective Sweeps ◽  
X Chromosomes ◽  
Evolutionary Forces ◽  
Relative Contribution ◽  
African Populations ◽  
Neutral Variation ◽  
Colonization Process ◽  
The Subject

Abstract Levels of neutral variation are influenced by background selection and hitchhiking. The relative contribution of these evolutionary forces to the distribution of neutral variation is still the subject of ongoing debates. Using 133 microsatellites, we determined levels of variability on X chromosomes and autosomes in African and non-African D. melanogaster populations. In the ancestral African populations microsatellite variability was higher on X chromosomes than on autosomes. In non-African populations X-linked polymorphism is significantly more reduced than autosomal variation. In non-African populations we observed a significant positive correlation between X chromosomal polymorphism and recombination rate. These results are consistent with the interpretation that background selection shapes levels of neutral variability in the ancestral populations, while the pattern in derived populations is determined by multiple selective sweeps during the colonization process. Further research, however, is required to investigate the influence of inversion polymorphisms and unequal sex ratios.

scholarly journals Kinetic aspects of calcium metabolism in lactating sheep offered herbages with different Ca concentrations and the effect of protein supplementation

1989 ◽  
Vol 61 (1) ◽  
pp. 45-58 ◽  
Author(s):  
J. S. Chrisp ◽  
A. R. Sykes ◽  
N. D. Grace
Keyword(s):  
White Clover ◽  
Calcium Metabolism ◽  
Lolium Multiflorum ◽  
Kinetic Studies ◽  
Protein Supplementation ◽  
Relative Contribution ◽  
Protein Status ◽  
Rate Of Absorption ◽  
The Subject ◽  
Protein Supply

1. Two experiments are described in which kinetic aspects of calcium metabolism were studied in housed lactating sheep consuming different fresh herbage species. The importance of protein supply was also investigated.2. In Expt. 1, two groups (n 4) were offered, ad lib., a freshly cut ryegrass (Lolium perenne L.)-white clover (Trifolium repens L.) pasture containing 5·48 g Ca/kg dry matter (DM). One group was supplemented daily with 100 g protected casein. A third group (n 4) was offered, ad lib., freshly cut oats-Tama ryegass (Lolium multiflorum L.) herbage which had a lower Ca content of 3·07 g Ca/kg DM. Stable Ca and nitrogen balances were carried out during the first 7 weeks of lactation. At this stage 180 μCi45Ca were administered for Ca kinetic studies.3. In Expt 2, eight sheep were offered, ad lib., a fresh ryegrass–white clover pasture, and paired on the basis of their udder size. One member of each pair was supplemented daily with 100 g casein via the abomasum and the amount of milk removed was equalized between pairs. Ca and N balances (12 d) and Ca kinetic studies (280 μCi 45Ca) were carried out during weeks 2 and 5 of lactation.4. Rate of absorption of Ca increased, while rate of Ca secretion in milk and resorption from bone decreased as lactation progressed. Ca balances changed from negative to positive as lactation progressed in sheep offered ryegrass–white clover, but, while improving, were always negative in sheep offered oats–Tama ryegrass. Protein supplementation increased (18%) milk production of the ewes in Expt 1 and their retention of N in Expt 2.5. The proportion of utilized Ca derived from the diet, as opposed to the skeleton, tended to increase as a result of protein supplementation.6. Availability of Ca from ryegrass–white clover ranged from 0.19 to 0.32, even though only 50% of the net Ca requirement was derived from the diet. Availability of Ca from the oats–Tama ryegrass diet was similar, though in this case less than 20% of the net Ca requirement was derived from the diet. It was concluded that availability of Ca from forage diets may be lower than previously anticipated.7. Faecal endogenous loss ranged from 16 to 40 mg Ca/kg body-weight per d, and was similar on both diets.8. These and other findings are used to discuss more fully the subject of Ca nutrition in sheep, in particular, the implications of the strong homeostatic control of Ca absorption and the influence of protein status on the relative contribution of the diet and the skeleton in meeting the net Ca requirement of the ewe during lactation.

Automatic Acquisition of Image Filtering and Object Extraction Procedures from Ground-Truth Samples

2009 ◽  
Vol 13 (2) ◽  
pp. 115-127 ◽  
Author(s):  
Shahryar Rahnamayan ◽  
◽  
Hamid R. Tizhoosh ◽  
Magdy M.A. Salama ◽  
Keyword(s):  
Image Processing ◽  
Expert Knowledge ◽  
Patent Application ◽  
Ground Truth ◽  
Image Filtering ◽  
Target Object ◽  
Object Extraction ◽  
Learning Approaches ◽  
Training Samples ◽  
The Subject

Knowledge- and sample-based learning approaches play a pivotal role in image processing. However, the acquisition and integration of expert knowledge (for the former) and providing a sufficiently large number of training samples (for the latter) are generally hard to perform and time-consuming tasks. Hence, learning image processing tasks from a few gold/ground-truth samples, prepared by the user, is highly desirable. This paper demonstrates how the combination of an optimizer (e.g., genetic algorithm) and image processing tools (e.g., parameterized morphology operations) can be used to generate image processing procedures for image filtering and object extraction. For this purpose, the approach receives the original and the user-prepared image (filtered image or image with extracted target object) as a gold sample which reflects the user's expectations. After carrying out the training or optimization phase, the optimal procedure is generated and ready to be applied to new images. The feasibility of our approach is investigated for two individual image processing categories, namely filtering and object extraction, by well-prepared synthetic images. The proposed architecture and the employed methodologies are explained in detail. Experimental results are provided as well.The subject matter in this work is covered by a US provisional patent application.

Muscles versus bones: catfishes as a case study for a discussion on the relative contribution of myological and osteological features in phylogenetic reconstructions

2004 ◽  
Vol 54 (4) ◽  
pp. 373-391 ◽  
Author(s):  
Rui Diogo
Keyword(s):  
Morphological Variation ◽  
Phylogenetic Trees ◽  
High Reliability ◽  
Phylogenetic Analyses ◽  
Data Sets ◽  
Large Set ◽  
Relative Contribution ◽  
Phylogenetic Reconstructions ◽  
The Subject

AbstractThe levels of homoplasy and phylogenetic reliability of different types of data sets have since long intrigued evolutionary scientists. This paper provides, to the author's knowledge, the first assessment of the relative contribution of a large set of myological and osteological characters in simultaneous phylogenetic analyses. The biological taxon used as a case study for this comparison was the highly diverse and cosmopolitan teleost Siluriformes (catfishes) which, with 34 families, about 437 genera and more than 2700 species, represents about one third of all freshwater fishes and one of the most diverse vertebrate groups. Such a direct comparison of the relative contribution of these two types of data sets has the advantage that the homoplasy levels and the phylogenetic trees being compared refer to the same group and, more importantly, to the very same terminal taxa. The overall analysis of the results presented in this work seems to indicate that: (1) osteological structures display a greater morphological variation than myological ones; (2) this difference (which is very likely overenhanced by the fact that the phylogenetic variation of osteological structures has historically been the subject of many more studies and descriptions than myological ones) is particularly notable in small taxa, such as genera or species; (3) myological characters provide, however, a high proportion of informative characters for disclosing the relationships between larger taxa, and, thus, for disclosing the phylogeny of the higher clades in which these taxa are included. These results raise some puzzling, general questions. For instance, what are the reasons for the seemingly greater morphological variation of osteological structures? And why is this greater morphological variation of osteological structures in relation to myological structures particularly pronounced in low ranking taxa? Does natural selection eventually act, in certain cases, more on bones than on muscles? Is the development of myological structures eventually more constrained than that of osteological features? What explains the apparently high reliability of muscular characters to disclose the higher-level phylogeny of higher taxa? More direct comparisons, either of other major groups of teleosts or of vertebrates in general, are clearly needed to infer if the patterns found in the direct comparison of this work correspond to a more general phylogenetic pattern, or instead refer to a particular situation found in the order Siluriformes.

scholarly journals Effect of number and placement of EEG electrodes on measurement of neural tracking of speech

PLoS ONE ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. e0246769 ◽  
Author(s):  
Jair Montoya-Martínez ◽  
Jonas Vanthornhout ◽  
Alexander Bertrand ◽  
Tom Francart
Keyword(s):  
Reconstruction Error ◽  
Optimal Number ◽  
Selection Strategy ◽  
Practical Applications ◽  
Auditory Neuroscience ◽  
Eeg Data ◽  
Subject Specific ◽  
Independent Case ◽  
The Subject ◽  
Eeg Recordings

Measurement of neural tracking of natural running speech from the electroencephalogram (EEG) is an increasingly popular method in auditory neuroscience and has applications in audiology. The method involves decoding the envelope of the speech signal from the EEG signal, and calculating the correlation with the envelope of the audio stream that was presented to the subject. Typically EEG systems with 64 or more electrodes are used. However, in practical applications, set-ups with fewer electrodes are required. Here, we determine the optimal number of electrodes, and the best position to place a limited number of electrodes on the scalp. We propose a channel selection strategy based on an utility metric, which allows a quick quantitative assessment of the influence of a channel (or a group of channels) on the reconstruction error. We consider two use cases: a subject-specific case, where the optimal number and position of the electrodes is determined for each subject individually, and a subject-independent case, where the electrodes are placed at the same positions (in the 10-20 system) for all the subjects. We evaluated our approach using 64-channel EEG data from 90 subjects. In the subject-specific case we found that the correlation between actual and reconstructed envelope first increased with decreasing number of electrodes, with an optimum at around 20 electrodes, yielding 29% higher correlations using the optimal number of electrodes compared to all electrodes. This means that our strategy of removing electrodes can be used to improve the correlation metric in high-density EEG recordings. In the subject-independent case, we obtained a stable decoding performance when decreasing from 64 to 22 channels. When the number of channels was further decreased, the correlation decreased. For a maximal decrease in correlation of 10%, 32 well-placed electrodes were sufficient in 91% of the subjects.

Automated Well-Log Processing and Lithology Classification by Identifying Optimal Features Through Unsupervised and Supervised Machine-Learning Algorithms

SPE Journal ◽  
2020 ◽  
Vol 25 (05) ◽  
pp. 2778-2800 ◽  
Author(s):  
Harpreet Singh ◽  
Yongkoo Seol ◽  
Evgeniy M. Myshakin
Keyword(s):  
Machine Learning ◽  
Case Studies ◽  
Ground Truth ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Well Logs ◽  
Petroleum Engineering ◽  
Well Log ◽  
Classification Problems ◽  
Rock Types

Summary The application of specialized machine learning (ML) in petroleum engineering and geoscience is increasingly gaining attention in the development of rapid and efficient methods as a substitute to existing methods. Existing ML-based studies that use well logs contain two inherent limitations. The first limitation is that they start with one predefined combination of well logs that by default assumes that the chosen combination of well logs is poised to give the best outcome in terms of prediction, although the variation in accuracy obtained through different combinations of well logs can be substantial. The second limitation is that most studies apply unsupervised learning (UL) for classification problems, but it underperforms by a substantial margin compared with nearly all the supervised learning (SL) algorithms. In this context, this study investigates a variety of UL and SL ML algorithms applied on multiple well-log combinations (WLCs) to automate the traditional workflow of well-log processing and classification, including an optimization step to achieve the best output. The workflow begins by processing the measured well logs, which includes developing different combinations of measured well logs and their physics-motivated augmentations, followed by removal of potential outliers from the input WLCs. Reservoir lithology with four different rock types is investigated using eight UL and seven SL algorithms in two different case studies. The results from the two case studies are used to identify the optimal set of well logs and the ML algorithm that gives the best matching reservoir lithology to its ground truth. The workflow is demonstrated using two wells from two different reservoirs on Alaska North Slope to distinguish four different rock types along the well (brine-dominated sand, hydrate-dominated sand, shale, and others/mixed compositions). The results show that the automated workflow investigated in this study can discover the ground truth for the lithology with up to 80% accuracy with UL and up to 90% accuracy with SL, using six routine well logs [vp, vs, ρb, ϕneut, Rt, gamma ray (GR)], which is a significant improvement compared with the accuracy reported in the current state of the art, which is less than 70%.

scholarly journals Decode Brain System: A Dynamic Adaptive Convolutional Quorum Voting Approach for Variable-Length EEG Data

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Tao Xu ◽  
Yun Zhou ◽  
Zekai Hou ◽  
Wenlan Zhang
Keyword(s):  
Time Window ◽  
Brain Activity ◽  
Sliding Window ◽  
Variable Length ◽  
Cognitive State ◽  
Human Beings ◽  
Processing Variable ◽  
Cognitive States ◽  
Eeg Data ◽  
Eeg Recordings

The brain is a complex and dynamic system, consisting of interacting sets and the temporal evolution of these sets. Electroencephalogram (EEG) recordings of brain activity play a vital role to decode the cognitive process of human beings in learning research and application areas. In the real world, people react to stimuli differently, and the duration of brain activities varies between individuals. Therefore, the length of EEG recordings in trials gathered in the experiment is variable. However, current approaches either fix the length of EEG recordings in each trial which would lose information hidden in the data or use the sliding window which would consume large computation on overlapped parts of slices. In this paper, we propose TOO (Traverse Only Once), a new approach for processing variable-length EEG trial data. TOO is a convolutional quorum voting approach that breaks the fixed structure of the model through convolutional implementation of sliding windows and the replacement of the fully connected layer by the 1 × 1 convolutional layer. Each output cell generated from 1 × 1 convolutional layer corresponds to each slice created by a sliding time window, which reflects changes in cognitive states. Then, TOO employs quorum voting on output cells and determines the cognitive state representing the entire single trial. Our approach provides an adaptive model for trials of different lengths with traversing EEG data of each trial only once to recognize cognitive states. We design and implement a cognitive experiment and obtain EEG data. Using the data collecting from this experiment, we conducted an evaluation to compare TOO with a state-of-art sliding window end-to-end approach. The results show that TOO yields a good accuracy (83.58%) at the trial level with a much lower computation (11.16%). It also has the potential to be used in variable signal processing in other application areas.

Electroencephalography based detection of cognitive state during learning tasks: An extensive approach

2021 ◽  
Vol 25 (2) ◽  
pp. 157-178
Author(s):  
Theparambil Asharaf Suhail ◽  
◽  
Kottanayil Pally Indiradevi ◽  
Ekkarakkudy Makkar Suhara ◽  
Poovathinal Azhakan Suresh ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Cognitive Performance ◽  
Mental State ◽  
Assessment Model ◽  
Support Vector ◽  
Cognitive State ◽  
Linear Discriminant ◽  
Cognitive States ◽  
Learning Tasks ◽  
The Subject

Detecting cognitive states during learning tasks is an essential component in neurocognitive experiments for assessing and enhancing the cognitive performance of individuals. Studies have demonstrated that mental state recognition systems utilizing brain signals are proficient in the automated monitoring of learners’ cognitive states. The current study focuses on developing an efficient individualized and cross-subject cognitive state assessment model based on Electroencephalography (EEG) patterns during learning tasks. For this study, EEGs of 20 healthy subjects were recorded during a resting state followed by a learning task and examined EEG activations patterns in a wide perspective of feature types and rhythms. The extracted features included time-domain features such as Hjorth parameters, Wavelet-based features, and Spectral entropy. Three classifiers, Support Vector Machine, k-Nearest Neighbor, and Linear Discriminant Analysis were employed to recognize the mental state. A new EEG-based attention index using band ratios is proposed and is demonstrated as an effective predictor for recognizing attentive reading. The proposed model can yield recognition performance with an accuracy of 92.9% in the subject-dependent approach and 77.2% in the subject-independent approach with the Support Vector Machine Classifier. The findings are useful for the design and development of neurofeedback systems that monitor and enhance the cognitive performance in healthy individuals, as well as in individuals with cognitive deficits.

Validation of ground truth fire debris classification by supervised machine learning

2021 ◽  
Vol 26 ◽  
pp. 100358
Author(s):  
Michael E. Sigman ◽  
Mary R. Williams ◽  
Nicholas Thurn ◽  
Taylor Wood
Keyword(s):  
Machine Learning ◽  
Ground Truth ◽  
Supervised Machine Learning ◽  
Fire Debris

scholarly journals An Integrative Approach to Analyze Eeg Signals and Human Brain Dynamics in Different Cognitive States

2017 ◽  
Vol 7 (4) ◽  
pp. 287-299 ◽  
Author(s):  
Jeffrey Jonathan (Joshua) Davis ◽  
Chin-Teng Lin ◽  
Grant Gillett ◽  
Robert Kozma
Keyword(s):  
Mental Arithmetic ◽  
Mental States ◽  
Brain Regions ◽  
Brain Dynamics ◽  
Integrative Approach ◽  
Frequency Bands ◽  
Cognitive States ◽  
Eeg Data ◽  
Brain States ◽  
Qualitative Exploration

Abstract Electroencephalograph (EEG) data provide insight into the interconnections and relationships between various cognitive states and their corresponding brain dynamics, by demonstrating dynamic connections between brain regions at different frequency bands. While sensory input tends to stimulate neural activity in different frequency bands, peaceful states of being and self-induced meditation tend to produce activity in the mid-range (Alpha). These studies were conducted with the aim of: (a) testing different equipment in order to assess two (2) different EEG technologies together with their benefits and limitations and (b) having an initial impression of different brain states associated with different experimental modalities and tasks, by analyzing the spatial and temporal power spectrum and applying our movie making methodology to engage in qualitative exploration via the art of encephalography. This study complements our previous study of measuring multichannel EEG brain dynamics using MINDO48 equipment associated with three experimental modalities measured both in the laboratory and the natural environment. Together with Hilbert analysis, we conjecture, the results will provide us with the tools to engage in more complex brain dynamics and mental states, such as Meditation, Mathematical Audio Lectures, Music Induced Meditation, and Mental Arithmetic Exercises. This paper focuses on open eye and closed eye conditions, as well as meditation states in laboratory conditions. We assess similarities and differences between experimental modalities and their associated brain states as well as differences between the different tools for analysis and equipment.

Sign in / Sign up

Export Citation Format

Share Document