Showing papers in "International Journal of Neural Systems in 2014"

An optimization spiking neural p system for approximately solving combinatorial optimization problems.

Abstract: Membrane systems (also called P systems) refer to the computing models abstracted from the structure and the functioning of the living cell as well as from the cooperation of cells in tissues, organs, and other populations of cells. Spiking neural P systems (SNPS) are a class of distributed and parallel computing models that incorporate the idea of spiking neurons into P systems. To attain the solution of optimization problems, P systems are used to properly organize evolutionary operators of heuristic approaches, which are named as membrane-inspired evolutionary algorithms (MIEAs). This paper proposes a novel way to design a P system for directly obtaining the approximate solutions of combinatorial optimization problems without the aid of evolutionary operators like in the case of MIEAs. To this aim, an extended spiking neural P system (ESNPS) has been proposed by introducing the probabilistic selection of evolution rules and multi-neurons output and a family of ESNPS, called optimization spiking neural P system (OSNPS), are further designed through introducing a guider to adaptively adjust rule probabilities to approximately solve combinatorial optimization problems. Extensive experiments on knapsack problems have been reported to experimentally prove the viability and effectiveness of the proposed neural system.

A high-speed brain speller using steady-state visual evoked potentials

Abstract: Implementing a complex spelling program using a steady-state visual evoked potential (SSVEP)-based brain–computer interface (BCI) remains a challenge due to difficulties in stimulus presentation and target identification. This study aims to explore the feasibility of mixed frequency and phase coding in building a high-speed SSVEP speller with a computer monitor. A frequency and phase approximation approach was developed to eliminate the limitation of the number of targets caused by the monitor refresh rate, resulting in a speller comprising 32 flickers specified by eight frequencies (8–15 Hz with a 1 Hz interval) and four phases (0°, 90°, 180°, and 270°). A multi-channel approach incorporating Canonical Correlation Analysis (CCA) and SSVEP training data was proposed for target identification. In a simulated online experiment, at a spelling rate of 40 characters per minute, the system obtained an averaged information transfer rate (ITR) of 166.91 bits/min across 13 subjects with a maximum individual ITR of 192.26 bits/min, the highest ITR ever reported in electroencephalogram (EEG)-based BCIs. The results of this study demonstrate great potential of a high-speed SSVEP-based BCI in real-life applications.

Frequency recognition in SSVEP-based BCI using multiset canonical correlation analysis.

Abstract: Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Despite its efficiency, a potential problem is that using pre-constructed sine-cosine waves as the required reference signals in the CCA method often does not result in the optimal recognition accuracy due to their lack of features from the real electro-encephalo-gram (EEG) data. To address this problem, this study proposes a novel method based on multiset canonical correlation analysis (MsetCCA) to optimize the reference signals used in the CCA method for SSVEP frequency recognition. The MsetCCA method learns multiple linear transforms that implement joint spatial filtering to maximize the overall correlation among canonical variates, and hence extracts SSVEP common features from multiple sets of EEG data recorded at the same stimulus frequency. The optimized reference signals are formed by combination of the common features and completely based on training data. Experimental study with EEG data from 10 healthy subjects demonstrates that the MsetCCA method improves the recognition accuracy of SSVEP frequency in comparison with the CCA method and other two competing methods (multiway CCA (MwayCCA) and phase constrained CCA (PCCA)), especially for a small number of channels and a short time window length. The superiority indicates that the proposed MsetCCA method is a new promising candidate for frequency recognition in SSVEP-based BCIs.

Detection of driving fatigue by using noncontact emg and ecg signals measurement system

Abstract: Driver fatigue can be detected by constructing a discriminant mode using some features obtained from physiological signals. There exist two major challenges of this kind of methods. One is how to collect physiological signals from subjects while they are driving without any interruption. The other is to find features of physiological signals that are of corresponding change with the loss of attention caused by driver fatigue. Driving fatigue is detected based on the study of surface electromyography (EMG) and electrocardiograph (ECG) during the driving period. The noncontact data acquisition system was used to collect physiological signals from the biceps femoris of each subject to tackle the first challenge. Fast independent component analysis (FastICA) and digital filter were utilized to process the original signals. Based on the statistical analysis results given by Kolmogorov-Smirnov Z test, the peak factor of EMG (p < 0.001) and the maximum of the cross-relation curve of EMG and ECG (p < 0.001) were selected as the combined characteristic to detect fatigue of drivers. The discriminant criterion of fatigue was obtained from the training samples by using Mahalanobis distance, and then the average classification accuracy was given by 10-fold cross-validation. The results showed that the method proposed in this paper can give well performance in distinguishing the normal state and fatigue state. The noncontact, onboard vehicle drivers' fatigue detection system was developed to reduce fatigue-related risks.

An erp-based bci using an oddball paradigm with different faces and reduced errors in critical functions

Abstract: Recent research has shown that a new face paradigm is superior to the conventional "flash only" approach that has dominated P300 brain-computer interfaces (BCIs) for over 20 years. However, these face paradigms did not study the repetition effects and the stability of evoked event related potentials (ERPs), which would decrease the performance of P300 BCI. In this paper, we explored whether a new "multi-faces (MF)" approach would yield more distinct ERPs than the conventional "single face (SF)" approach. To decrease the repetition effects and evoke large ERPs, we introduced a new stimulus approach called the "MF" approach, which shows different familiar faces randomly. Fifteen subjects participated in runs using this new approach and an established "SF" approach. The result showed that the MF pattern enlarged the N200 and N400 components, evoked stable P300 and N400, and yielded better BCI performance than the SF pattern. The MF pattern can evoke larger N200 and N400 components and more stable P300 and N400, which increase the classification accuracy compared to the face pattern.

Aggregation of sparse linear discriminant analyses for event-related potential classification in brain-computer interface.

Abstract: Two main issues for event-related potential (ERP) classification in brain–computer interface (BCI) application are curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classifi...

A genetic graph-based approach for partitional clustering.

Abstract: Clustering is one of the most versatile tools for data analysis. In the recent years, clustering that seeks the continuity of data (in opposition to classical centroid-based approaches) has attracted an increasing research interest. It is a challenging problem with a remarkable practical interest. The most popular continuity clustering method is the spectral clustering (SC) algorithm, which is based on graph cut: It initially generates a similarity graph using a distance measure and then studies its graph spectrum to find the best cut. This approach is sensitive to the parameters of the metric, and a correct parameter choice is critical to the quality of the cluster. This work proposes a new algorithm, inspired by SC, that reduces the parameter dependency while maintaining the quality of the solution. The new algorithm, named genetic graph-based clustering (GGC), takes an evolutionary approach introducing a genetic algorithm (GA) to cluster the similarity graph. The experimental validation shows that GGC increases robustness of SC and has competitive performance in comparison with classical clustering methods, at least, in the synthetic and real dataset used in the experiments.

Multi-strategy coevolving aging particle optimization.

Abstract: We propose Multi-Strategy Coevolving Aging Particles (MS-CAP), a novel population-based algorithm for black-box optimization. In a memetic fashion, MS-CAP combines two components with complementary algorithm logics. In the first stage, each particle is perturbed independently along each dimension with a progressively shrinking (decaying) radius, and attracted towards the current best solution with an increasing force. In the second phase, the particles are mutated and recombined according to a multi-strategy approach in the fashion of the ensemble of mutation strategies in Differential Evolution. The proposed algorithm is tested, at different dimensionalities, on two complete black-box optimization benchmarks proposed at the Congress on Evolutionary Computation 2010 and 2013. To demonstrate the applicability of the approach, we also test MS-CAP to train a Feedforward Neural Network modeling the kinematics of an 8-link robot manipulator. The numerical results show that MS-CAP, for the setting considered in this study, tends to outperform the state-of-the-art optimization algorithms on a large set of problems, thus resulting in a robust and versatile optimizer.

Evaluation and application of a hybrid brain computer interface for real wheelchair parallel control with multi-degree of freedom.

Abstract: There have been many attempts to design brain–computer interfaces (BCIs) for wheelchair control based on steady state visual evoked potential (SSVEP), event-related desynchronization/synchronizatio...

Automated seizure detection using EKG.

Abstract: Changes in heart rate, most often increases, are associated with the onset of epileptic seizures and may be used in lieu of cortical activity for automated seizure detection. The feasibility of this aim was tested on 241 clinical seizures from 81 subjects admitted to several Epilepsy Centers for invasive monitoring for evaluation for epilepsy surgery. The performance of the EKG-based seizure detection algorithm was compared to that of a validated algorithm applied to electrocorticogram (ECoG). With the most sensitive detection settings [threshold T: 1.15; duration D: 0 s], 5/241 seizures (2%) were undetected (false negatives) and with the highest [T: 1.3; D: 5 s] settings, the number of false negative detections rose to 34 (14%). The rate of potential false positive (PFP) detections was 9.5/h with the lowest and 1.1/h with the highest T, D settings. Visual review of 336 ECoG segments associated with PFPs revealed that 120 (36%) were associated with seizures, 127 (38%) with bursts of epileptiform discharges and only 87 (26%) were true false positives. Electrocardiographic (EKG)-based seizure onset detection preceded clinical onset by 0.8 s with the lowest and followed it by 13.8 s with the highest T, D settings. Automated EKG-based seizure detection is feasible and has potential clinical utility given its ease of acquisition, processing, high signal/noise and ergonomic advantages viz-a-viz EEG (electroencephalogram) or ECoG. Its use as an "electronic" seizure diary will remedy in part, the inaccuracies of those generated by patients/care-givers in a cost-effective manner.

The super-turing computational power of plastic recurrent neural networks

Abstract: We study the computational capabilities of a biologically inspired neural model where the synaptic weights, the connectivity pattern, and the number of neurons can evolve over time rather than stay static. Our study focuses on the mere concept of plasticity of the model so that the nature of the updates is assumed to be not constrained. In this context, we show that the so-called plastic recurrent neural networks (RNNs) are capable of the precise super-Turing computational power — as the static analog neural networks — irrespective of whether their synaptic weights are modeled by rational or real numbers, and moreover, irrespective of whether their patterns of plasticity are restricted to bi-valued updates or expressed by any other more general form of updating. Consequently, the incorporation of only bi-valued plastic capabilities in a basic model of RNNs suffices to break the Turing barrier and achieve the super-Turing level of computation. The consideration of more general mechanisms of architectural plasticity or of real synaptic weights does not further increase the capabilities of the networks. These results support the claim that the general mechanism of plasticity is crucially involved in the computational and dynamical capabilities of biological neural networks. They further show that the super-Turing level of computation reflects in a suitable way the capabilities of brain-like models of computation.

Optimal sparse approximation with integrate and fire neurons

Abstract: Sparse approximation is a hypothesized coding strategy where a population of sensory neurons (e.g. V1) encodes a stimulus using as few active neurons as possible. We present the Spiking LCA (locally competitive algorithm), a rate encoded Spiking Neural Network (SNN) of integrate and fire neurons that calculate sparse approximations. The Spiking LCA is designed to be equivalent to the nonspiking LCA, an analog dynamical system that converges on a l(1)-norm sparse approximations exponentially. We show that the firing rate of the Spiking LCA converges on the same solution as the analog LCA, with an error inversely proportional to the sampling time. We simulate in NEURON a network of 128 neuron pairs that encode 8 × 8 pixel image patches, demonstrating that the network converges to nearly optimal encodings within 20 ms of biological time. We also show that when using more biophysically realistic parameters in the neurons, the gain function encourages additional l(0)-norm sparsity in the encoding, relative both to ideal neurons and digital solvers.

Epileptic Eeg Classification Based on Kernel Sparse Representation

Abstract: The automatic identification of epileptic EEG signals is significant in both relieving heavy workload of visual inspection of EEG recordings and treatment of epilepsy. This paper presents a novel method based on the theory of sparse representation to identify epileptic EEGs. At first, the raw EEG epochs are preprocessed via Gaussian low pass filtering and differential operation. Then, in the scheme of sparse representation based classification (SRC), a test EEG sample is sparsely represented on the training set by solving l1-minimization problem, and the represented residuals associated with ictal and interictal training samples are computed. The test EEG sample is categorized as the class that yields the minimum represented residual. So unlike the conventional EEG classification methods, the choice and calculation of EEG features are avoided in the proposed framework. Moreover, the kernel trick is employed to generate a kernel version of the SRC method for improving the separability between ictal and interictal classes. The satisfactory recognition accuracy of 98.63% for ictal and interictal EEG classification and for ictal and normal EEG classification has been achieved by the kernel SRC. In addition, the fast speed makes the kernel SRC suit for the real-time seizure monitoring application in the near future.

Studying the role of synchronized and chaotic spiking neural ensembles in neural information processing.

Abstract: The brain is characterized by performing many diverse processing tasks ranging from elaborate processes such as pattern recognition, memory or decision making to more simple functionalities such as linear filtering in image processing. Understanding the mechanisms by which the brain is able to produce such a different range of cortical operations remains a fundamental problem in neuroscience. Here we show a study about which processes are related to chaotic and synchronized states based on the study of in-silico implementation of Stochastic Spiking Neural Networks (SSNN). The measurements obtained reveal that chaotic neural ensembles are excellent transmission and convolution systems since mutual information between signals is minimized. At the same time, synchronized cells (that can be understood as ordered states of the brain) can be associated to more complex nonlinear computations. In this sense, we experimentally show that complex and quick pattern recognition processes arise when both synchronized and chaotic states are mixed. These measurements are in accordance with in vivo observations related to the role of neural synchrony in pattern recognition and to the speed of the real biological process. We also suggest that the high-level adaptive mechanisms of the brain that are the Hebbian and non-Hebbian learning rules can be understood as processes devoted to generate the appropriate clustering of both synchronized and chaotic ensembles. The measurements obtained from the hardware implementation of different types of neural systems suggest that the brain processing can be governed by the superposition of these two complementary states with complementary functionalities (nonlinear processing for synchronized states and information convolution and parallelization for chaotic).

Improved adaptive splitting and selection: the hybrid training method of a classifier based on a feature space partitioning.

Abstract: Currently, methods of combined classification are the focus of intense research. A properly designed group of combined classifiers exploiting knowledge gathered in a pool of elementary classifiers can successfully outperform a single classifier. There are two essential issues to consider when creating combined classifiers: how to establish the most comprehensive pool and how to design a fusion model that allows for taking full advantage of the collected knowledge. In this work, we address the issues and propose an AdaSS+, training algorithm dedicated for the compound classifier system that effectively exploits local specialization of the elementary classifiers. An effective training procedure consists of two phases. The first phase detects the classifier competencies and adjusts the respective fusion parameters. The second phase boosts classification accuracy by elevating the degree of local specialization. The quality of the proposed algorithms are evaluated on the basis of a wide range of computer experiments that show that AdaSS+ can outperform the original method and several reference classifiers.

Cortical excitability as a potential clinical marker of epilepsy: a review of the clinical application of transcranial magnetic stimulation

Abstract: Transcranial magnetic stimulation (TMS) can be used for safe, noninvasive probing of cortical excitability (CE). We review 50 studies that measured CE in people with epilepsy. Most showed cortical hyperexcitability, which can be corrected with anti-epileptic drug treatment. Several studies showed that decrease of CE after epilepsy surgery is predictive of good seizure outcome. CE is a potential biomarker for epilepsy. Clinical application may include outcome prediction of drug treatment and epilepsy surgery.

Code-specific learning rules improve action selection by populations of spiking neurons

Abstract: Population coding is widely regarded as a key mechanism for achieving reliable behavioral decisions. We previously introduced reinforcement learning for population-based decision making by spiking neurons. Here we generalize population reinforcement learning to spike-based plasticity rules that take account of the postsynaptic neural code. We consider spike/no-spike, spike count and spike latency codes. The multi-valued and continuous-valued features in the postsynaptic code allow for a generalization of binary decision making to multi-valued decision making and continuous-valued action selection. We show that code-specific learning rules speed up learning both for the discrete classification and the continuous regression tasks. The suggested learning rules also speed up with increasing population size as opposed to standard reinforcement learning rules. Continuous action selection is further shown to explain realistic learning speeds in the Morris water maze. Finally, we introduce the concept of action perturbation as opposed to the classical weight- or node-perturbation as an exploration mechanism underlying reinforcement learning. Exploration in the action space greatly increases the speed of learning as compared to exploration in the neuron or weight space.

A generalized Leaky Integrate-and-Fire neuron model with fast implementation method.

Abstract: This study introduces a new Generalized Leaky Integrate-and-Fire (GLIF) neuron model with variable leaking resistor and bias current in order to reproduce accurately the membrane voltage dynamics of a biological neuron. The accuracy of this model is ensured by adjusting its parameters to the statistical properties of the Hodgkin-Huxley model outputs; while the speed is enhanced by introducing a Generalized Exponential Moving Average method that converts the parameterized kernel functions into pre-calculated lookup tables based on an analytic solution of the dynamic equations of the GLIF model.

Drug polyconsumption is associated with increased synchronization of brain electrical-activity at rest and in a counting task.

Abstract: Drug abusers typically consume not just one but several types of drugs, starting from alcohol and marijuana consumption, and then dramatically lapsing into addiction to harder drugs, such as cocaine, heroin, or amphetamine. The brain of drug abusers presents various structural and neurophysiological abnormalities, some of which may predate drug consumption onset. However, how these changes translate into modifications in functional brain connectivity is still poorly understood. To characterize functional connectivity patterns, we recorded Electroencephalogram (EEG) activity from 21 detoxified drug abusers and 20 age-matched control subjects performing a simple counting task and at rest activity. To evaluate the cortical brain connectivity network we applied the Synchronization Likelihood algorithm. The results showed that drug abusers had higher synchronization levels at low frequencies, mainly in the θ band (4–8 Hz) between frontal and posterior cortical regions. During the counting task, patients showed increased synchronization in the β (14–35 Hz), and γ (35–45 Hz) frequency bands, in fronto-posterior and interhemispheric temporal regions. Taken together 'slow-down' at rest and task-related 'over-exertion' could indicate that the brain of drug abusers is suffering from a premature form of ageing. Future studies will clarify whether this condition can be reversed following prolonged periods of abstinence.

Multiple oscillatory states in models of collective neuronal dynamics

Abstract: In our previous studies, we showed that the both realistic and analytical computational models of neural dynamics can display multiple sustained states (attractors) for the same values of model parameters. Some of these states can represent normal activity while other, of oscillatory nature, may represent epileptic types of activity. We also showed that a simplified, analytical model can mimic this type of behavior and can be used instead of the realistic model for large scale simulations. The primary objective of the present work is to further explore the phenomenon of multiple stable states, co-existing in the same operational model, or phase space, in systems consisting of large number of interconnected basic units. As a second goal, we aim to specify the optimal method for state control of the system based on inducing state transitions using appropriate external stimulus. We use here interconnected model units that represent the behavior of neuronal populations as an effective dynamic system. The model unit is an analytical model (S. Kalitzin et al., Epilepsy Behav. 22 (2011) S102–S109) and does not correspond directly to realistic neuronal processes (excitatory–inhibitory synaptic interactions, action potential generation). For certain parameter choices however it displays bistable dynamics imitating the behavior of realistic neural mass models. To analyze the collective behavior of the system we applied phase synchronization analysis (PSA), principal component analysis (PCA) and stability analysis using Lyapunov exponent (LE) estimation. We obtained a large variety of stable states with different dynamic characteristics, oscillatory modes and phase relations between the units. These states can be initiated by appropriate initial conditions; transitions between them can be induced stochastically by fluctuating variables (noise) or by specific inputs. We propose a method for optimal reactive control, allowing forced transitions from one state (attractor) into another.

Self-supervised MRI tissue segmentation by discriminative clustering.

Abstract: The study of brain lesions can benefit from a clear identification of transitions between healthy and pathological tissues, through the analysis of brain imaging data. Current signal processing methods, able to address these issues, often rely on strong prior information. In this article, a new method for tissue segmentation is proposed. It is based on a discriminative strategy, in a self-supervised machine learning approach. This method avoids the use of prior information, which makes it very versatile, and able to cope with different tissue types. It also returns tissue probabilities for each voxel, crucial for a good characterization of the evolution of brain lesions. Simulated as well as real benchmark data were used to validate the accuracy of the method and compare it against other segmentation algorithms.

Computational modeling of transcranial direct current stimulation in the child brain: implications for the treatment of refractory childhood focal epilepsy

Abstract: Transcranial direct current stimulation (tDCS) was recently proposed for the treatment of epilepsy. However, the electrode arrangement for this case is debated. This paper analyzes the influence of the position of the anodal electrode on the electric field in the brain. The simulation shows that moving the anode from scalp to shoulder does influence the electric field not only in the cortex, but also in deeper brain regions. The electric field decreases dramatically in the brain area without epileptiform activity.

Multi-instance dictionary learning for detecting abnormal events in surveillance videos.

Abstract: In this paper, a novel method termed Multi-Instance Dictionary Learning (MIDL) is presented for detecting abnormal events in crowded video scenes. With respect to multi-instance learning, each event (video clip) in videos is modeled as a bag containing several sub-events (local observations); while each sub-event is regarded as an instance. The MIDL jointly learns a dictionary for sparse representations of sub-events (instances) and multi-instance classifiers for classifying events into normal or abnormal. We further adopt three different multi-instance models, yielding the Max-Pooling-based MIDL (MP-MIDL), Instance-based MIDL (Inst-MIDL) and Bag-based MIDL (Bag-MIDL), for detecting both global and local abnormalities. The MP-MIDL classifies observed events by using bag features extracted via max-pooling over sparse representations. The Inst-MIDL and Bag-MIDL classify observed events by the predicted values of corresponding instances. The proposed MIDL is evaluated and compared with the state-of-the-art methods for abnormal event detection on the UMN (for global abnormalities) and the UCSD (for local abnormalities) datasets and results show that the proposed MP-MIDL and Bag-MIDL achieve either comparable or improved detection performances. The proposed MIDL method is also compared with other multi-instance learning methods on the task and superior results are obtained by the MP-MIDL scheme.

Early prediction of medication refractoriness in children with idiopathic epilepsy based on scalp EEG analysis.

Abstract: Refractory epilepsy often has deleterious effects on an individual's health and quality of life. Early identification of patients whose seizures are refractory to antiepileptic drugs is important in considering the use of alternative treatments. Although idiopathic epilepsy is regarded as having a significantly lower risk factor of developing refractory epilepsy, still a subset of patients with idiopathic epilepsy might be refractory to medical treatment. In this study, we developed an effective method to predict the refractoriness of idiopathic epilepsy. Sixteen EEG segments from 12 well-controlled patients and 14 EEG segments from 11 refractory patients were analyzed at the time of first EEG recordings before antiepileptic drug treatment. Ten crucial EEG feature descriptors were selected for classification. Three of 10 were related to decorrelation time, and four of 10 were related to relative power of delta/gamma. There were significantly higher values in these seven feature descriptors in the well-controlled group as compared to the refractory group. On the contrary, the remaining three feature descriptors related to spectral edge frequency, kurtosis, and energy of wavelet coefficients demonstrated significantly lower values in the well-controlled group as compared to the refractory group. The analyses yielded a weighted precision rate of 94.2%, and a 93.3% recall rate. Therefore, the developed method is a useful tool in identifying the possibility of developing refractory epilepsy in patients with idiopathic epilepsy.

Low-rank approximation based non-negative multi-way array decomposition on event-related potentials.

Abstract: Non-negative tensor factorization (NTF) has been successfully applied to analyze event-related potentials (ERPs), and shown superiority in terms of capturing multi-domain features. However, the time-frequency representation of ERPs by higher-order tensors are usually large-scale, which prevents the popularity of most tensor factorization algorithms. To overcome this issue, we introduce a non-negative canonical polyadic decomposition (NCPD) based on low-rank approximation (LRA) and hierarchical alternating least square (HALS) techniques. We applied NCPD (LRAHALS and benchmark HALS) and CPD to extract multi-domain features of a visual ERP. The features and components extracted by LRAHALS NCPD and HALS NCPD were very similar, but LRAHALS NCPD was 70 times faster than HALS NCPD. Moreover, the desired multi-domain feature of the ERP by NCPD showed a significant group difference (control versus depressed participants) and a difference in emotion processing (fearful versus happy faces). This was more satisfactory than that by CPD, which revealed only a group difference.

SINGULAR SPECTRUM ANALYSIS AND ADAPTIVE FILTERING ENHANCE THE FUNCTIONAL CONNECTIVITY ANALYSIS OF RESTING STATE fMRI DATA

Abstract: Sources of noise in resting-state fMRI experiments include instrumental and physiological noises, which need to be filtered before a functional connectivity analysis of brain regions is performed. These noisy components show autocorrelated and nonstationary properties that limit the efficacy of standard techniques (i.e. time filtering and general linear model). Herein we describe a novel approach based on the combination of singular spectrum analysis and adaptive filtering, which allows a greater noise reduction and yields better connectivity estimates between regions at rest, providing a new feasible procedure to analyze fMRI data.

Simulating vertical and horizontal inhibition with short-term dynamics in a multi-column multi-layer model of neocortex.

Abstract: The paper introduces a multi-layer multi-column model of the cortex that uses four different neuron types and short-term plasticity dynamics. It was designed with details of neuronal connectivity available in the literature and meets these conditions: (1) biologically accurate laminar and columnar flows of activity, (2) normal function of low-threshold spiking and fast spiking neurons, and (3) ability to generate different stages of epileptiform activity. With these characteristics the model allows for modeling lesioned or malformed cortex, i.e. examine properties of developmentally malformed cortex in which the balance between inhibitory neuron subtypes is disturbed.

Structurally enhanced incremental neural learning for image classification with subgraph extraction.

Abstract: In this paper, a structurally enhanced incremental neural learning technique is proposed to learn a discriminative codebook representation of images for effective image classification applications. In order to accommodate the relationships such as structures and distributions among visual words into the codebook learning process, we develop an online codebook graph learning method based on a novel structurally enhanced incremental learning technique, called as "visualization-induced self-organized incremental neural network (ViSOINN)". The hidden structural information in the images is embedded into the graph representation evolving dynamically with the adaptive and competitive learning mechanism. Afterwards, image features can be coded using a sub-graph extraction process based on the learned codebook graph, and a classifier is subsequently used to complete the image classification task. Compared with other codebook learning algorithms originated from the classical Bag-of-Features (BoF) model, ViSOINN holds the following advantages: (1) it learns codebook efficiently and effectively from a small training set; (2) it models the relationships among visual words in metric scaling fashion, so preserving high discriminative power; (3) it automatically learns the codebook without a fixed pre-defined size; and (4) it enhances and preserves better the structure of the data. These characteristics help to improve image classification performance and make it more suitable for handling large-scale image classification tasks. Experimental results on the widely used Caltech-101 and Caltech-256 benchmark datasets demonstrate that ViSOINN achieves markedly improved performance and reduces the computational cost considerably.

NEV2lkit: a new open source tool for handling neuronal event files from multi-electrode recordings.

Abstract: The analysis and discrimination of action potentials, or "spikes", is a central issue to systems neuroscience research. Here we introduce a free open source software for the analysis and discrimination of neural spikes based on principal component analysis and different clustering algorithms. The main objective is to supply a friendly user interface that links the experimental data to a basic set of routines for analysis, visualization and classification of spikes in a consistent framework. The tool has been tested on artificial data sets, on multi-electrode extracellular recordings from ganglion cell populations in isolated superfused mouse, rabbit and turtle retinas, and on electrophysiological recordings from mouse visual cortex. Our results show that NEV2lkit is very reliable and able to satisfy the experimental demands in terms of accuracy, efficiency and consistency across experiments. It performs fast unit sorting in single or multiple experiments and allows the extraction of spikes from over large time intervals in continuously recorded data streams. The tool is implemented in C++ and runs cross-platform on Linux, OS X and Windows systems. To facilitate the adaptation and extension as well as the addition of new routines, tools and algorithms for data analysis, the source code, binary distributions for different operating systems and documentation are all freely available at http://nev2lkit.sourceforge.net.

Principal polynomial analysis

Abstract: This paper presents a new framework for manifold learning based on a sequence of principal polynomials that capture the possibly nonlinear nature of the data. The proposed Principal Polynomial Analysis (PPA) generalizes PCA by modeling the directions of maximal variance by means of curves, instead of straight lines. Contrarily to previous approaches, PPA reduces to performing simple univariate regressions, which makes it computationally feasible and robust. Moreover, PPA shows a number of interesting analytical properties. First, PPA is a volume-preserving map, which in turn guarantees the existence of the inverse. Second, such an inverse can be obtained in closed form. Invertibility is an important advantage over other learning methods, because it permits to understand the identified features in the input domain where the data has physical meaning. Moreover, it allows to evaluate the performance of dimensionality reduction in sensible (input-domain) units. Volume preservation also allows an easy computation of information theoretic quantities, such as the reduction in multi-information after the transform. Third, the analytical nature of PPA leads to a clear geometrical interpretation of the manifold: it allows the computation of Frenet-Serret frames (local features) and of generalized curvatures at any point of the space. And fourth, the analytical Jacobian allows the computation of the metric induced by the data, thus generalizing the Mahalanobis distance. These properties are demonstrated theoretically and illustrated experimentally. The performance of PPA is evaluated in dimensionality and redundancy reduction, in both synthetic and real datasets from the UCI repository.