scholarly journals Data augmentation based on dynamical systems for the classification of brain states

2020 ◽  
Author(s):  
Yonatan Sanz Perl ◽  
Carla Pallavicini ◽  
Ignacio Perez Ipiña ◽  
Morten Kringelbach ◽  
Gustavo Deco ◽  
...  
Keyword(s):  
Computational Models ◽  
Data Augmentation ◽  
Machine Learning Algorithms ◽  
Sleep Cycle ◽  
Great Promise ◽  
Brain State ◽  
Computer Assisted ◽  
Whole Brain ◽  
Brain States

AbstractThe application of machine learning algorithms to neuroimaging data shows great promise for the classification of physiological and pathological brain states. However, classifiers trained on high dimensional data are prone to overfitting, especially for a low number of training samples. We describe the use of whole-brain computational models for data augmentation in brain state classification. Our low dimensional model is based on nonlinear oscillators coupled by the empirical SC of the brain. We use this model to enhance a dataset consisting of functional magnetic resonance imaging recordings acquired during all stages of the human wake-sleep cycle. After fitting the model to the average FC of each state, we show that the synthetic data generated by the model yields classification accuracies comparable to those obtained from the empirical data. We also show that models fitted to individual subjects generate surrogates with enough information to train classifiers that present significant transfer learning accuracy to the whole sample. Whole-brain computational modeling represents a useful tool to produce large synthetic datasets for data augmentation in the classification of certain brain states, with potential applications to computer-assisted diagnosis and prognosis of neuropsychiatric disorders.

scholarly journals Perturbations in dynamical models of whole-brain activity dissociate between the level and stability of consciousness

2021 ◽  
Vol 17 (7) ◽  
pp. e1009139
Author(s):  
Yonatan Sanz Perl ◽  
Carla Pallavicini ◽  
Ignacio Pérez Ipiña ◽  
Athena Demertzi ◽  
Vincent Bonhomme ◽  
...  
Keyword(s):  
Computational Models ◽  
Brain Activity ◽  
Relevant Information ◽  
Complete Characterization ◽  
Brain State ◽  
Whole Brain ◽  
Brain Injured ◽  
Level Of Consciousness ◽  
The Stability ◽  
Injured Patients

Consciousness transiently fades away during deep sleep, more stably under anesthesia, and sometimes permanently due to brain injury. The development of an index to quantify the level of consciousness across these different states is regarded as a key problem both in basic and clinical neuroscience. We argue that this problem is ill-defined since such an index would not exhaust all the relevant information about a given state of consciousness. While the level of consciousness can be taken to describe the actual brain state, a complete characterization should also include its potential behavior against external perturbations. We developed and analyzed whole-brain computational models to show that the stability of conscious states provides information complementary to their similarity to conscious wakefulness. Our work leads to a novel methodological framework to sort out different brain states by their stability and reversibility, and illustrates its usefulness to dissociate between physiological (sleep), pathological (brain-injured patients), and pharmacologically-induced (anesthesia) loss of consciousness.

scholarly journals Multivariate mixed kernel density estimators and their application in machine learning for classification of biological objects based on spectral measurements

2019 ◽  
Vol 43 (4) ◽  
pp. 677-691
Author(s):  
A.A. Sirota ◽  
A.O. Donskikh ◽  
A.V. Akimov ◽  
D.A. Minakov
Keyword(s):  
Machine Learning ◽  
Density Estimation ◽  
Data Augmentation ◽  
Kernel Density ◽  
Machine Learning Algorithms ◽  
Spectral Measurements ◽  
Density Estimates ◽  
Biological Objects ◽  
Density Estimators

A problem of non-parametric multivariate density estimation for machine learning and data augmentation is considered. A new mixed density estimation method based on calculating the convolution of independently obtained kernel density estimates for unknown distributions of informative features and a known (or independently estimated) density for non-informative interference occurring during measurements is proposed. Properties of the mixed density estimates obtained using this method are analyzed. The method is compared with a conventional Parzen-Rosenblatt window method applied directly to the training data. The equivalence of the mixed kernel density estimator and the data augmentation procedure based on the known (or estimated) statistical model of interference is theoretically and experimentally proven. The applicability of the mixed density estimators for training of machine learning algorithms for the classification of biological objects (elements of grain mixtures) based on spectral measurements in the visible and near-infrared regions is evaluated.

scholarly journals Awakening: Predicting external stimulation to force transitions between different brain states

2019 ◽  
Vol 116 (36) ◽  
pp. 18088-18097 ◽  
Author(s):  
Gustavo Deco ◽  
Josephine Cruzat ◽  
Joana Cabral ◽  
Enzo Tagliazucchi ◽  
Helmut Laufs ◽  
...  
Keyword(s):  
Fundamental Problem ◽  
Effective Connectivity ◽  
Brain State ◽  
Whole Brain ◽  
External Stimulation ◽  
Neuropsychiatric Diseases ◽  
Brain Modeling ◽  
Brain States ◽  
Definition Of ◽  
The Brain

A fundamental problem in systems neuroscience is how to force a transition from one brain state to another by external driven stimulation in, for example, wakefulness, sleep, coma, or neuropsychiatric diseases. This requires a quantitative and robust definition of a brain state, which has so far proven elusive. Here, we provide such a definition, which, together with whole-brain modeling, permits the systematic study in silico of how simulated brain stimulation can force transitions between different brain states in humans. Specifically, we use a unique neuroimaging dataset of human sleep to systematically investigate where to stimulate the brain to force an awakening of the human sleeping brain and vice versa. We show where this is possible using a definition of a brain state as an ensemble of “metastable substates,” each with a probabilistic stability and occurrence frequency fitted by a generative whole-brain model, fine-tuned on the basis of the effective connectivity. Given the biophysical limitations of direct electrical stimulation (DES) of microcircuits, this opens exciting possibilities for discovering stimulation targets and selecting connectivity patterns that can ensure propagation of DES-induced neural excitation, potentially making it possible to create awakenings from complex cases of brain injury.

scholarly journals A Comparative Study of the Impact of Data Augmentation in Machine Learning Based Classification Accuracy

2021 ◽  
Author(s):  
Arif Jahangir
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Machine Learning Algorithms ◽  
Quadratic Discriminant Analysis ◽  
Crucial Importance ◽  
Markov Transition Matrix ◽  
Original Dataset ◽  
Markov Transition ◽  
The Impact

Traumatic Brain Injury is the primary cause of death and disability all over the world. Monitoring the intracranial pressure (ICP) and classifying it for hypertension signals is of crucial importance. This thesis explores the possibility of a better classification of the ICP signal and detection of hypertensive signal prior to the actual occurrence of the hypertensive episodes. This study differ from other approaches astime series is converted into images by Gramian angular field and Markov transition matrix and augmented with data. Due to unbalanced data, the effect of smote extended nearest neighbour algorithm for balancing the data is examined. We use various machine learning algorithms to classify the ICP signals. The results obtained shoe that Ada boost performance is the best among compared algorithms. F1 score of the Ada boost is 0.95 on original dataset, and 0.9967 on balanced and augmented dataset. Quadratic Discriminant Analysis F1 score is 1 when data is augmented and balanced.

scholarly journals Perturbations in dynamical models of whole-brain activity dissociate between the level and stability of consciousness

2020 ◽  
Author(s):  
Yonatan Sanz Perl ◽  
Carla Pallavicini ◽  
Ignacio Pérez Ipiña ◽  
Athena Demertzi ◽  
Vincent Bonhomme ◽  
...  
Keyword(s):  
Computational Models ◽  
Brain Activity ◽  
Relevant Information ◽  
Complete Characterization ◽  
Brain State ◽  
Whole Brain ◽  
Brain Injured ◽  
Level Of Consciousness ◽  
The Stability ◽  
Injured Patients

AbstractConsciousness transiently fades away during deep sleep, more stably under anesthesia, and sometimes permanently due to brain injury. The development of an index to quantify the level of consciousness across these different states is regarded as a key problem both in basic and clinical neuroscience. We argue that this problem is ill-defined since such an index would not exhaust all the relevant information about a given state of consciousness. While the level of consciousness can be taken to describe the actual brain state, a complete characterization should also include its potential behavior against external perturbations. We developed and analyzed whole-brain computational models to show that the stability of conscious states provides information complementary to their similarity to conscious wakefulness. Our work leads to a novel methodological framework to sort out different brain states by their stability and reversibility, and illustrates its usefulness to dissociate between physiological (sleep), pathological (brain-injured patients), and pharmacologically-induced (anesthesia) loss of consciousness.

scholarly journals Data augmentation based on dynamical systems for the classification of brain states

2020 ◽  
Vol 139 ◽  
pp. 110069 ◽  
Author(s):  
Yonatan Sanz Perl ◽  
Carla Pallavicini ◽  
Ignacio Perez Ipiña ◽  
Morten Kringelbach ◽  
Gustavo Deco ◽  
...  
Keyword(s):  
Dynamical Systems ◽  
Data Augmentation ◽  
Brain States

scholarly journals A Novel and Robust Approach to Detect Tuberculosis Using Transfer Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Omar Faruk ◽  
Eshan Ahmed ◽  
Sakil Ahmed ◽  
Anika Tabassum ◽  
Tahia Tazin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Computer Assisted ◽  
Promising Technique ◽  
Suggested Approach ◽  
X Ray ◽  
Chest X Ray ◽  
Deep Learning Model

Deep learning has emerged as a promising technique for a variety of elements of infectious disease monitoring and detection, including tuberculosis. We built a deep convolutional neural network (CNN) model to assess the generalizability of the deep learning model using a publicly accessible tuberculosis dataset. This study was able to reliably detect tuberculosis (TB) from chest X-ray images by utilizing image preprocessing, data augmentation, and deep learning classification techniques. Four distinct deep CNNs (Xception, InceptionV3, InceptionResNetV2, and MobileNetV2) were trained, validated, and evaluated for the classification of tuberculosis and nontuberculosis cases using transfer learning from their pretrained starting weights. With an F1-score of 99 percent, InceptionResNetV2 had the highest accuracy. This research is more accurate than earlier published work. Additionally, it outperforms all other models in terms of reliability. The suggested approach, with its state-of-the-art performance, may be helpful for computer-assisted rapid TB detection.

scholarly journals A Comparative Study of the Impact of Data Augmentation in Machine Learning Based Classification Accuracy

2021 ◽  
Author(s):  
Arif Jahangir
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Machine Learning Algorithms ◽  
Quadratic Discriminant Analysis ◽  
Crucial Importance ◽  
Markov Transition Matrix ◽  
Original Dataset ◽  
Markov Transition ◽  
The Impact

Traumatic Brain Injury is the primary cause of death and disability all over the world. Monitoring the intracranial pressure (ICP) and classifying it for hypertension signals is of crucial importance. This thesis explores the possibility of a better classification of the ICP signal and detection of hypertensive signal prior to the actual occurrence of the hypertensive episodes. This study differ from other approaches astime series is converted into images by Gramian angular field and Markov transition matrix and augmented with data. Due to unbalanced data, the effect of smote extended nearest neighbour algorithm for balancing the data is examined. We use various machine learning algorithms to classify the ICP signals. The results obtained shoe that Ada boost performance is the best among compared algorithms. F1 score of the Ada boost is 0.95 on original dataset, and 0.9967 on balanced and augmented dataset. Quadratic Discriminant Analysis F1 score is 1 when data is augmented and balanced.

Classification of Ecological Data by Deep Learning

2020 ◽  
Vol 34 (13) ◽  
pp. 2052010
Author(s):  
Shaobo Liu ◽  
Frank Y. Shih ◽  
Gareth Russell ◽  
Kimberly Russell ◽  
Hai Phan
Keyword(s):  
Deep Learning ◽  
Computational Models ◽  
Data Augmentation ◽  
Small Data ◽  
Learning Models ◽  
Ecological Data ◽  
Accuracy Rate ◽  
Learning Techniques ◽  
Residual Block

Ecologists have been studying different computational models in the classification of ecological species. In this paper, we intend to take advantages of variant deep-learning models, including LeNet, AlexNet, VGG models, residual neural network, and inception models, to classify ecological datasets, such as bee wing and butterfly. Since the datasets contain relatively small data samples and unbalanced samples in each class, we apply data augmentation and transfer learning techniques. Furthermore, newly designed inception residual and inception modules are developed to enhance feature extraction and increase classification rates. As comparing against currently available deep-learning models, experimental results show that the proposed inception residual block can avoid the vanishing gradient problem and achieve a high accuracy rate of 92%.

scholarly journals Brain State Intelligence and Cognitive Health Through EEG Date Modeling

2021 ◽  
Vol 12 (1) ◽  
pp. 46-61
Author(s):  
Hong Lin ◽  
Jonathan Garza ◽  
Gregor Schreiber ◽  
Minghao Yang ◽  
Yunwei Cui
Keyword(s):  
Data Analysis ◽  
Initial Step ◽  
Machine Learning Algorithms ◽  
Computer Interface ◽  
Brain State ◽  
Data Sets ◽  
Web Interface ◽  
Feedback Systems ◽  
Eeg Data ◽  
Brain States

Electroencephalographic data modeling is widely used in developing applications in the areas of healthcare, as well as brain-computer interface. One particular study is to use meditation research to reach out to the high-end applications of EEG data analysis in understanding human brain states and assisting in promoting human healthcare. The analysis of these states could be the initial step in a process to first predict and later allow individuals to control these states. To this end, the authors begin to build a system for dynamic brain state analysis using EEG data. The system allows users to transit EEG data to an online database through mobile devices, interact with the web server through web interface, and get feedback from EEG data analysis programs on real-time bases. The models perform self-adjusting based on the data sets available in the database. Experimental results obtained from various machine-learning algorithms indicate great potential in recognizing user's brain state with high accuracy. This method will be useful in quick-prototyping onsite brain states feedback systems.

Sign in / Sign up

Export Citation Format

Share Document