Foreground Detection by Competitive Learning for Varying Input Distributions

One of the most important challenges in computer vision applications is the background modeling, especially when the background is dynamic and the input distribution might not be stationary, i.e. the distribution of the input data could change with time (e.g. changing illuminations, waving trees, water, etc.). In this work, an unsupervised learning neural network is proposed which is able to cope with progressive changes in the input distribution. It is based on a dual learning mechanism which manages the changes of the input distribution separately from the cluster detection. The proposal is adequate for scenes where the background varies slowly. The performance of the method is tested against several state-of-the-art foreground detectors both quantitatively and qualitatively, with favorable results.

Imaging and machine learning techniques for diagnosis of Alzheimer's disease

Alzheimer's disease (AD) is a common health problem in elderly people. There has been considerable research toward the diagnosis and early detection of this disease in the past decade. The sensitivity of biomarkers and the accuracy of the detection techniques have been defined to be the key to an accurate diagnosis. This paper presents a state-of-the-art review of the research performed on the diagnosis of AD based on imaging and machine learning techniques. Different segmentation and machine learning techniques used for the diagnosis of AD are reviewed including thresholding, supervised and unsupervised learning, probabilistic techniques, Atlas-based approaches, and fusion of different image modalities. More recent and powerful classification techniques such as the enhanced probabilistic neural network of Ahmadlou and Adeli should be investigated with the goal of improving the diagnosis accuracy. A combination of different image modalities can help improve the diagnosis accuracy rate. Research is needed on the combination of modalities to discover multi-modal biomarkers.

Nonlinear Semi-Supervised Metric Learning Via Multiple Kernels and Local Topology

Changing the metric on the data may change the data distribution, hence a good distance metric can promote the performance of learning algorithm. In this paper, we address the semi-supervised distance metric learning (ML) problem to obtain the best nonlinear metric for the data. First, we describe the nonlinear metric by the multiple kernel representation. By this approach, we project the data into a high dimensional space, where the data can be well represented by linear ML. Then, we reformulate the linear ML by a minimization problem on the positive definite matrix group. Finally, we develop a two-step algorithm for solving this model and design an intrinsic steepest descent algorithm to learn the positive definite metric matrix. Experimental results validate that our proposed method is effective and outperforms several state-of-the-art ML methods.

Beta Hebbian Learning as a New Method for Exploratory Projection Pursuit

In this research, a novel family of learning rules called Beta Hebbian Learning (BHL) is thoroughly investigated to extract information from high-dimensional datasets by projecting the data onto low-dimensional (typically two dimensional) subspaces, improving the existing exploratory methods by providing a clear representation of data's internal structure. BHL applies a family of learning rules derived from the Probability Density Function (PDF) of the residual based on the beta distribution. This family of rules may be called Hebbian in that all use a simple multiplication of the output of the neural network with some function of the residuals after feedback. The derived learning rules can be linked to an adaptive form of Exploratory Projection Pursuit and with artificial distributions, the networks perform as the theory suggests they should: the use of different learning rules derived from different PDFs allows the identification of "interesting" dimensions (as far from the Gaussian distribution as possible) in high-dimensional datasets. This novel algorithm, BHL, has been tested over seven artificial datasets to study the behavior of BHL parameters, and was later applied successfully over four real datasets, comparing its results, in terms of performance, with other well-known Exploratory and projection models such as Maximum Likelihood Hebbian Learning (MLHL), Locally-Linear Embedding (LLE), Curvilinear Component Analysis (CCA), Isomap and Neural Principal Component Analysis (Neural PCA).

High-Density Liquid-State Machine Circuitry for Time-Series Forecasting

Spiking neural networks (SNN) are the last neural network generation that try to mimic the real behavior of biological neurons. Although most research in this area is done through software applications, it is in hardware implementations in which the intrinsic parallelism of these computing systems are more efficiently exploited. Liquid state machines (LSM) have arisen as a strategic technique to implement recurrent designs of SNN with a simple learning methodology. In this work, we show a new low-cost methodology to implement high-density LSM by using Boolean gates. The proposed method is based on the use of probabilistic computing concepts to reduce hardware requirements, thus considerably increasing the neuron count per chip. The result is a highly functional system that is applied to high-speed time series forecasting.

Learning Topologies with the Growing Neural Forest

In this work, a novel self-organizing model called growing neural forest (GNF) is presented. It is based on the growing neural gas (GNG), which learns a general graph with no special provisions for datasets with separated clusters. On the contrary, the proposed GNF learns a set of trees so that each tree represents a connected cluster of data. High dimensional datasets often contain large empty regions among clusters, so this proposal is better suited to them than other self-organizing models because it represents these separated clusters as connected components made of neurons. Experimental results are reported which show the self-organization capabilities of the model. Moreover, its suitability for unsupervised clustering and foreground detection applications is demonstrated. In particular, the GNF is shown to correctly discover the connected component structure of some datasets. Moreover, it outperforms some well-known foreground detectors both in quantitative and qualitative terms.

Emotion Recognition with Eigen Features of Frequency Band Activities Embedded in Induced Brain Oscillations Mediated by Affective Pictures

In this study, singular spectrum analysis (SSA) has been used for the first time in order to extract emotional features from well-defined electroencephalography (EEG) frequency band activities (BAs) so-called delta (0.5–4[Formula: see text]Hz), theta (4–8[Formula: see text]Hz), alpha (8–16[Formula: see text]Hz), beta (16–32[Formula: see text]Hz), gamma (32–64[Formula: see text]Hz). These five BAs were estimated by applying sixth-level multi-resolution wavelet decomposition (MRWD) with Daubechies wavelets (db-8) to single channel nonaveraged emotional EEG oscillations of 6 s for each scalp location over 16 recording sites (Fp1, Fp2, F3, F4, F7, F8, C3, C4, P3, P4, T3, T4, T5, T6, O1, O2). Every trial was mediated by different emotional stimuli which were selected from international affective picture system (IAPS) to induce emotional states such as pleasant (P), neutral (N), and unpleasant (UP). Largest principal components (PCs) of BAs were considered as emotional features and data mining approaches were used for the first time in order to classify both three different (P, N, UP) and two contrasting (P and UP) emotional states for 30 healthy controls. Emotional features extracted from gamma BAs (GBAs) for 16 recording sites provided the high classification accuracies of 87.1% and 100% for classification of three emotional states and two contrasting emotional states, respectively. In conclusion, we found the followings: (1) Eigenspectra of high frequency BAs in EEG are highly sensitive to emotional hemispheric activations, (2) emotional states are mostly mediated by GBA, (3) pleasant pictures induce the higher cortical activation in contrast to unpleasant pictures, (4) contrasting emotions induce opposite cortical activations, (5) cognitive activities are necessary for an emotion to occur.

A Two-Stage Combining Classifier Model for the Development of Adaptive Dialog Systems

This paper proposes a statistical framework to develop user-adapted spoken dialog systems. The proposed framework integrates two main models. The first model is used to predict the user's intention during the dialog. The second model uses this prediction and the history of dialog up to the current moment to predict the next system response. This prediction is performed with an ensemble-based classifier trained for each of the tasks considered, so that a better selection of the next system can be attained weighting the outputs of these specialized classifiers. The codification of the information and the definition of data structures to store the data supplied by the user throughout the dialog makes the estimation of the models from the training data and practical domains manageable. We describe our proposal and its application and detailed evaluation in a practical spoken dialog system.

Nature Inspired Computing: An Overview and Some Future Directions

This paper presents an overview of significant advances made in the emerging field of nature-inspired computing (NIC) with a focus on the physics- and biology-based approaches and algorithms. A parallel development in the past two decades has been the emergence of the field of computational intelligence (CI) consisting primarily of the three fields of neural networks, evolutionary computing and fuzzy logic. It is observed that NIC and CI intersect. The authors advocate and foresee more cross-fertilisation of the two emerging fields.