QNet: an agglomerative method for the construction of phylogenetic networks from weighted quartets

We present QNet, a method for constructing split networks from weighted quartet trees. QNet can be viewed as a quartet analogue of the distance-based Neighbor-Net (NNet) method for network construction. Just as NNet, QNet works by agglomeratively computing a collection of circular weighted splits of the taxa set which is subsequently represented by a planar split network. To illustrate the applicability of QNet, we apply it to a previously published Salmonella data set. We conclude that QNet can provide a useful alternative to NNet if distance data are not available or a character-based approach is preferred. Moreover, it can be used as an aid for determining when a quartet-based tree-building method may or may not be appropriate for a given data set. QNet is freely available for download.     

A neural-network technique to learn concepts from electroencephalograms

A new technique is presented developed to learn multi-class concepts from clinical electroencephalograms (EEGs). A desired concept is represented as a neuronal computational model consisting of the input, hidden, and output neurons. In this model the hidden neurons learn independently to classify the EEG segments presented by spectral and statistical features. This technique has been applied to the EEG data recorded from 65 sleeping healthy newborns in order to learn a brain maturation concept of newborns aged between 35 and 51 weeks. The 39,399 and 19,670 segments from these data have been used for learning and testing the concept, respectively. As a result, the concept has correctly classified 80.1% of the testing segments or 87.7% of the 65 records.     

Neural mechanisms of infant learning: differences in frontal theta activity during object exploration modulate subsequent object recognition

Investigating learning mechanisms in infancy relies largely on behavioural measures like visual attention, which often fail to predict whether stimuli would be encoded successfully. This study explored EEG activity in the theta frequency band, previously shown to predict successful learning in adults, to directly study infants'' cognitive engagement, beyond visual attention. We tested 11-month-old infants (N = 23) and demonstrated that differences in frontal theta-band oscillations, recorded during infants'' object exploration, predicted differential subsequent recognition of these objects in a preferential-looking test. Given that theta activity is modulated by motivation to learn in adults, these findings set the ground for future investigation into the drivers of infant learning.     

Reflection of cortical activation pattern in the human EEG phase structure

Investigation was fulfilled on healthy subjects (22) and on outpatients (62). The EEG by the standard scheme as recorded at resting with open and closed eyes and under different functional loads. These records were processed in accordance with the EEC phase structure with the aid of computer animation technology. The main idea of the phase structure technology consists in rejection of one supporting lead. Time shifts were measured only between two neighbouring electrodes, so that the oscillations under comparison were always highly coherent. Time errors were evaluated according to crosscorrelation function maximum shift. The differences between high- and low-frequency EEG rhythms were shown to be only quantitative from the phase structure viewpoint. Qualitatively, the rhythm properties were equal and came to slow (second) phase structure oscillations. Low frequency activity compared to high frequency one was characterized by greater phase shifts from electrode to electrode. Phase shifts of potentials are forming the structure which, as a whole, is very similar in different people and is reproduced in different states. Initial EEG waves appearance is statistical linked with main sensory projections: visual (occiput), auditory (temples) and somatic (parietal region) with addition of frontal region. Redistribution of phase leadership in favor of occipital pole and to both temporal regions when eyes are open is described. It is apparently dependent on the sensory surge level from thalamus to a given cortex region. Phase gradient direction seems to reflect the cortex current density gradient which is parallel to surface. It can be used for localization of compact sources lying near to cortex.     

Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach

Deep learning techniques have recently made considerable advances in the field of artificial intelligence. These methodologies can assist psychologists in early diagnosis of mental disorders and preventing severe trauma. Major Depression Disorder (MDD) is a common and serious medical condition whose exact manifestations are not fully understood. So, early discovery of MDD patients helps to cure or limit the adverse effects. Electroencephalogram (EEG) is prominently used to study brain diseases such as MDD due to having high temporal resolution information, and being a noninvasive, inexpensive and portable method. This paper has proposed an EEG-based deep learning framework that automatically discriminates MDD patients from healthy controls. First, the relationships among EEG channels in the form of effective brain connectivity analysis are extracted by Generalized Partial Directed Coherence (GPDC) and Direct directed transfer function (dDTF) methods. A novel combination of sixteen connectivity methods (GPDC and dDTF in eight frequency bands) was used to construct an image for each individual. Finally, the constructed images of EEG signals are applied to the five different deep learning architectures. The first and second algorithms were based on one and two-dimensional convolutional neural network (1DCNN–2DCNN). The third method is based on long short-term memory (LSTM) model, while the fourth and fifth algorithms utilized a combination of CNN with LSTM model namely, 1DCNN-LSTM and 2DCNN-LSTM. The proposed deep learning architectures automatically learn patterns in the constructed image of the EEG signals. The efficiency of the proposed algorithms is evaluated on resting state EEG data obtained from 30 healthy subjects and 34 MDD patients. The experiments show that the 1DCNN-LSTM applied on constructed image of effective connectivity achieves best results with accuracy of 99.24% due to specific architecture which captures the presence of spatial and temporal relations in the brain connectivity. The proposed method as a diagnostic tool is able to help clinicians for diagnosing the MDD patients for early diagnosis and treatment.     

Optimal information storage and the distribution of synaptic weights: perceptron versus Purkinje cell

It is widely believed that synaptic modifications underlie learning and memory. However, few studies have examined what can be deduced about the learning process from the distribution of synaptic weights. We analyze the perceptron, a prototypical feedforward neural network, and obtain the optimal synaptic weight distribution for a perceptron with excitatory synapses. It contains more than 50% silent synapses, and this fraction increases with storage reliability: silent synapses are therefore a necessary byproduct of optimizing learning and reliability. Exploiting the classical analogy between the perceptron and the cerebellar Purkinje cell, we fitted the optimal weight distribution to that measured for granule cell-Purkinje cell synapses. The two distributions agreed well, suggesting that the Purkinje cell can learn up to 5 kilobytes of information, in the form of 40,000 input-output associations.     

Learning and Long-Term Retention of Large-Scale Artificial Languages

Recovering discrete words from continuous speech is one of the first challenges facing language learners. Infants and adults can make use of the statistical structure of utterances to learn the forms of words from unsegmented input, suggesting that this ability may be useful for bootstrapping language-specific cues to segmentation. It is unknown, however, whether performance shown in small-scale laboratory demonstrations of “statistical learning” can scale up to allow learning of the lexicons of natural languages, which are orders of magnitude larger. Artificial language experiments with adults can be used to test whether the mechanisms of statistical learning are in principle scalable to larger lexicons. We report data from a large-scale learning experiment that demonstrates that adults can learn words from unsegmented input in much larger languages than previously documented and that they retain the words they learn for years. These results suggest that statistical word segmentation could be scalable to the challenges of lexical acquisition in natural language learning.     

Constructing circular phylogenetic networks from weighted quartets using simulated annealing

In this paper, we present a heuristic algorithm based on the simulated annealing, SAQ-Net, as a method for constructing phylogenetic networks from weighted quartets. Similar to QNet algorithm, SAQ-Net constructs a collection of circular weighted splits of the taxa set. This collection is represented by a split network. In order to show that SAQ-Net performs better than QNet, we apply these algorithm to both the simulated and actual data sets containing salmonella, Bees, Primates and Rubber data sets. Then we draw phylogenetic networks corresponding to outputs of these algorithms using SplitsTree4 and compare the results. We find that SAQ-Net produces a better circular ordering and phylogenetic networks than QNet in most cases. SAQ-Net has been implemented in Matlab and is available for download at http://bioinf.cs.ipm.ac.ir/softwares/saq.net.     

Adapting subject specific motor imagery EEG patterns in space–time–frequency for a brain computer interface

In this paper we propose a new technique that adaptively extracts subject specific motor imagery related EEG patterns in the space–time–frequency plane for single trial classification. The proposed approach requires no prior knowledge of reactive frequency bands, their temporal behavior or cortical locations. For a given electrode array, it finds all these parameters by constructing electrode adaptive time–frequency segmentations that are optimized for discrimination. This is accomplished first by segmenting the EEG along the time axis with Local Cosine Packets. Next the most discriminant frequency subbands are selected in each time segment with a frequency axis clustering algorithm to achieve time and frequency band adaptation individually. Finally the subject adapted features are sorted according to their discrimination power to reduce dimensionality and the top subset is used for final classification. We provide experimental results for 5 subjects of the BCI competition 2005 dataset IVa to show the superior performance of the proposed method. In particular, we demonstrate that by using a linear support vector machine as a classifier, the classification accuracy of the proposed algorithm varied between 90.5% and 99.7% and the average classification accuracy was 96%.     

An improvement of extreme learning machine for compact single-hidden-layer feedforward neural networks

Recently, a novel learning algorithm called extreme learning machine (ELM) was proposed for efficiently training single-hidden-layer feedforward neural networks (SLFNs). It was much faster than the traditional gradient-descent-based learning algorithms due to the analytical determination of output weights with the random choice of input weights and hidden layer biases. However, this algorithm often requires a large number of hidden units and thus slowly responds to new observations. Evolutionary extreme learning machine (E-ELM) was proposed to overcome this problem; it used the differential evolution algorithm to select the input weights and hidden layer biases. However, this algorithm required much time for searching optimal parameters with iterative processes and was not suitable for data sets with a large number of input features. In this paper, a new approach for training SLFNs is proposed, in which the input weights and biases of hidden units are determined based on a fast regularized least-squares scheme. Experimental results for many real applications with both small and large number of input features show that our proposed approach can achieve good generalization performance with much more compact networks and extremely high speed for both learning and testing.     

Hebbian learning from higher-order correlations requires crosstalk minimization

Activity-dependent synaptic plasticity should be extremely connection specific, though experiments have shown it is not, and biophysics suggests it cannot be. Extreme specificity (near-zero “crosstalk”) might be essential for unsupervised learning from higher-order correlations, especially when a neuron has many inputs. It is well known that a normalized nonlinear Hebbian rule can learn “unmixing” weights from inputs generated by linearly combining independently fluctuating nonGaussian sources using an orthogonal mixing matrix. We previously reported that even if the matrix is only approximately orthogonal, a nonlinear-specific Hebbian rule can usually learn almost correct unmixing weights (Cox and Adams in Front Comput Neurosci 3: doi:10.3389/neuro.10.011.2009 2009). We also reported simulations that showed that as crosstalk increases from zero, the learned weight vector first moves slightly away from the crosstalk-free direction and then, at a sharp threshold level of inspecificity, jumps to a completely incorrect direction. Here, we report further numerical experiments that show that above this threshold, residual learning is driven instead almost entirely by second-order input correlations, as occurs using purely Gaussian sources or a linear rule, and any amount of crosstalk. Thus, in this “ICA” model learning from higher-order correlations, required for unmixing, requires high specificity. We compare our results with a recent mathematical analysis of the effect of crosstalk for exactly orthogonal mixing, which revealed that a second, even lower, threshold, exists below which successful learning is impossible unless weights happen to start close to the correct direction. Our simulations show that this also holds when the mixing is not exactly orthogonal. These results suggest that if the brain uses simple Hebbian learning, it must operate with extraordinarily accurate synaptic plasticity to ensure powerful high-dimensional learning. Synaptic crowding would preclude this when inputs are numerous, and we propose that the neocortex might be distinguished by special circuitry that promotes extreme specificity for high-dimensional nonlinear learning.     

LEDPatNet19: Automated Emotion Recognition Model based on Nonlinear LED Pattern Feature Extraction Function using EEG Signals

Electroencephalography (EEG) signals collected from human brains have generally been used to diagnose diseases. Moreover, EEG signals can be used in several areas such as emotion recognition, driving fatigue detection. This work presents a new emotion recognition model by using EEG signals. The primary aim of this model is to present a highly accurate emotion recognition framework by using both a hand-crafted feature generation and a deep classifier. The presented framework uses a multilevel fused feature generation network. This network has three primary phases, which are tunable Q-factor wavelet transform (TQWT), statistical feature generation, and nonlinear textural feature generation phases. TQWT is applied to the EEG data for decomposing signals into different sub-bands and create a multilevel feature generation network. In the nonlinear feature generation, an S-box of the LED block cipher is utilized to create a pattern, which is named as Led-Pattern. Moreover, statistical feature extraction is processed using the widely used statistical moments. The proposed LED pattern and statistical feature extraction functions are applied to 18 TQWT sub-bands and an original EEG signal. Therefore, the proposed hand-crafted learning model is named LEDPatNet19. To select the most informative features, ReliefF and iterative Chi2 (RFIChi2) feature selector is deployed. The proposed model has been developed on the two EEG emotion datasets, which are GAMEEMO and DREAMER datasets. Our proposed hand-crafted learning network achieved 94.58%, 92.86%, and 94.44% classification accuracies for arousal, dominance, and valance cases of the DREAMER dataset. Furthermore, the best classification accuracy of the proposed model for the GAMEEMO dataset is equal to 99.29%. These results clearly illustrate the success of the proposed LEDPatNet19.     

Detecting epileptic seizure with different feature extracting strategies using robust machine learning classification techniques by applying advance parameter optimization approach

Epilepsy is a neurological disorder produced due to abnormal excitability of neurons in the brain. The research reveals that brain activity is monitored through electroencephalogram (EEG) of patients suffered from seizure to detect the epileptic seizure. The performance of EEG detection based epilepsy require feature extracting strategies. In this research, we have extracted varying features extracting strategies based on time and frequency domain characteristics, nonlinear, wavelet based entropy and few statistical features. A deeper study was undertaken using novel machine learning classifiers by considering multiple factors. The support vector machine kernels are evaluated based on multiclass kernel and box constraint level. Likewise, for K-nearest neighbors (KNN), we computed the different distance metrics, Neighbor weights and Neighbors. Similarly, the decision trees we tuned the paramours based on maximum splits and split criteria and ensemble classifiers are evaluated based on different ensemble methods and learning rate. For training/testing tenfold Cross validation was employed and performance was evaluated in form of TPR, NPR, PPV, accuracy and AUC. In this research, a deeper analysis approach was performed using diverse features extracting strategies using robust machine learning classifiers with more advanced optimal options. Support Vector Machine linear kernel and KNN with City block distance metric give the overall highest accuracy of 99.5% which was higher than using the default parameters for these classifiers. Moreover, highest separation (AUC = 0.9991, 0.9990) were obtained at different kernel scales using SVM. Additionally, the K-nearest neighbors with inverse squared distance weight give higher performance at different Neighbors. Moreover, to distinguish the postictal heart rate oscillations from epileptic ictal subjects, and highest performance of 100% was obtained using different machine learning classifiers.     

Predicting Epileptic Seizures in Advance

Epilepsy is the second most common neurological disorder, affecting 0.6–0.8% of the world''s population. In this neurological disorder, abnormal activity of the brain causes seizures, the nature of which tend to be sudden. Antiepileptic Drugs (AEDs) are used as long-term therapeutic solutions that control the condition. Of those treated with AEDs, 35% become resistant to medication. The unpredictable nature of seizures poses risks for the individual with epilepsy. It is clearly desirable to find more effective ways of preventing seizures for such patients. The automatic detection of oncoming seizures, before their actual onset, can facilitate timely intervention and hence minimize these risks. In addition, advance prediction of seizures can enrich our understanding of the epileptic brain. In this study, drawing on the body of work behind automatic seizure detection and prediction from digitised Invasive Electroencephalography (EEG) data, a prediction algorithm, ASPPR (Advance Seizure Prediction via Pre-ictal Relabeling), is described. ASPPR facilitates the learning of predictive models targeted at recognizing patterns in EEG activity that are in a specific time window in advance of a seizure. It then exploits advanced machine learning coupled with the design and selection of appropriate features from EEG signals. Results, from evaluating ASPPR independently on 21 different patients, suggest that seizures for many patients can be predicted up to 20 minutes in advance of their onset. Compared to benchmark performance represented by a mean S1-Score (harmonic mean of Sensitivity and Specificity) of 90.6% for predicting seizure onset between 0 and 5 minutes in advance, ASPPR achieves mean S1-Scores of: 96.30% for prediction between 1 and 6 minutes in advance, 96.13% for prediction between 8 and 13 minutes in advance, 94.5% for prediction between 14 and 19 minutes in advance, and 94.2% for prediction between 20 and 25 minutes in advance.     

Effects of cavities on EEG dipole localization and their relations with surface electrode positions

Effects of cavities in the human head on EEG dipole localization have been investigated by computer simulation. The human head is represented by a homogeneous spherical conductor including an eccentric spherical cavity which approximates effects of actual cavities inside the head. The homogeneous sphere model is used for assessing the effects caused by neglecting the cavity in the volume conductor model in the inverse dipole fitting procedure. Four electrode configurations have been examined to investigate their relation to the EEG inverse dipole solution. After examination of 2520 dipoles in the brain, the effects of cavities in the human head are found to be negligible when the dipole is located in the cortex or in the subcortex. When the dipole is located in the brain stem, the EEG inverse dipole solution is strongly affected by the cavity and is sensitive to the electrode configuration on the scalp. The EEG inverse dipole solution in the deep brain is sensitive to inhomogeneity in the lower part of the head when a single positive or negative potential pole is observed by the electrodes on the scalp, and at the same time is sensitive to the extent of the scalp covered by the electrodes. In conclusion, the electrodes should cover as much of the upper scalp as possible for deep source localization.     

Isotropic sequence order learning using a novel linear algorithm in a closed loop behavioural system

In this article, we present an isotropic algorithm for sequence order learning. Its central goal is to learn the causal relation between two (or more) inputs in order to react to the earliest incoming signal after successful learning (like in typical classical conditioning situations). We implement this algorithm in a behaving system (a robot) thereby creating a closed loop situation where the learner's actions influence its own sensor inputs to the end of creating an autonomous agent. Autonomous behaviour implies that learning goals are internally defined within the organism's capabilities. Standard learning models for sequence learning (e.g. temporal difference (TD)-learning) need an externally defined reward. This, however, is in conflict with the requirement of an implicitly defined internal goal in autonomous behaviour. Therefore, in this study we present a system in which the external reward is replaced by a reflex loop. This loop explicitly includes the environment. Every reflex loop has the inherent disadvantage, which is that its re-actions occur each time just after a reflex-eliciting sensor event and thus 'too late'. However, a reflex can serve as the internal reference for sequence order learning, which has the task of eliminating this disadvantage by creating earlier anticipatory actions. In our system learning is achieved by modifying synaptic weights of a linear neuron with a correlation based learning rule which involves the derivative of the neuron's output. All input lines are entirely isotropic. The synaptic weight change curve of this rule is strongly related to the temporal Hebb learning rule, which was found in spike timing experiments. We find that after learning the reflex loop is replaced in functional terms with an earlier anticipatory action (and pathway). In addition, we observed that the synaptic weights stabilise as soon as the reflex remains silent.     

Short-term prediction of chaotic time series by using RBF network with regression weights

We propose a framework for constructing and training a radial basis function (RBF) neural network. The structure of the gaussian functions is modified using a pseudo-gaussian function (PG) in which two scaling parameters sigma are introduced, which eliminates the symmetry restriction and provides the neurons in the hidden layer with greater flexibility with respect to function approximation. We propose a modified PG-BF (pseudo-gaussian basis function) network in which the regression weights are used to replace the constant weights in the output layer. For this purpose, a sequential learning algorithm is presented to adapt the structure of the network, in which it is possible to create a new hidden unit and also to detect and remove inactive units. A salient feature of the network systems is that the method used for calculating the overall output is the weighted average of the output associated with each receptive field. The superior performance of the proposed PG-BF system over the standard RBF are illustrated using the problem of short-term prediction of chaotic time series.     

Neocortical Dynamics: Implications for Understanding the Role of Neurofeedback and Related Techniques for the Enhancement of Attention

For nearly 25 years, EEG biofeedback (neurofeedback) has been utilized in research and clinical settings for the treatment and investigation of a number of disorders ranging from attention deficit hyperactivity disorder to seizure disorders as well as many other established and investigational applications. Until recently, mechanisms underlying the generation and origins of EEG have been poorly understood but now are beginning to become much more clarified. Now it is important to combine the information gathered on the genesis of EEG and neocortical dynamics with the findings from neurofeedback investigations. This will help us to develop models of how neurofeedback might operate in producing the changes in EEG and in clinical symptomatology. We know that the cortex operates in terms of resonant loops between neocortical columns of cells known as local, regional, and global resonances. These resonances determine the specific EEG frequencies and are often activated by groups of cells in the thalamus known as pacemakers. There are complex excitatory and inhibitory interactions within the cortex and between the cortex and the thalamus that allow these loops to operate and provide the basis for learning. Neurofeedback is a technique for modifying these resonant loops, and hence, modifying the neurophysiological and neurological basis for learning and for the management of a number of neurologically based disorders. This paper provides an introduction to understanding EEG and neocortical dynamics and how these concepts can be used to explain the results of neurofeedback training and other interventions particularly in the context of understanding attentive mechanisms and for the management of attention deficit/hyperactivity disorders.     

Function of attention in learning process in the olfactory bulb

It has been suggested that in the olfactory bulb, odor information is processed through parallel channels and learning depends on the cognitive environment. The synapse’s spike effective time is defined as the effective time for a spike from pre-synapse to post-synapse, which varies with the type of synapse. A learning model of the olfactory bulb was constructed for synapses with varying spike effective times. The simulation results showed that such a model can realize the multi-channel processing of information in the bulb. Furthermore, the effect of the cognitive environment on the learning process was also studied. Different feedback frequencies were used to express different attention states. Considering the information’s multi-channel processing requirement for learning, a learning rule considering both spike timing and average spike frequency is proposed. Simulation results showed that habituation and anti-habituation of an odor in the olfactory bulb might be the result of learning guided by a common local learning rule but at different attention states.     

Function of attention in learning process in the olfactory bulb

Biological experiments[1—8] have shown that in the olfactory bulb, odor information is encoded into spatio-temporal patterns and processed in multi-channels. In the bulb, the information is divided into basic information and fine information, which are encoded into average spiking frequency (long-term pattern) and synchronization of spikes[1—8] respectively. Compared with other structures in which information is encoded into spatio-temporal patterns, the olfactory bulb抯 structure is rather …