Narrow Results

Schizotypy is a latent cluster of personality traits that denote a vulnerability for schizophrenia or a type of spectrum disorder. The aim of the study is to investigate parametric effective brain connectivity features for classifying high versus low schizotypy (LS) status. Electroencephalography (EEG) signals are recorded from 13 high schizotypy (HS) and 11 LS participants during an emotional auditory odd-ball task. The brain connectivity signals for machine learning are taken after the settlement of event-related potentials. A multivariate autoregressive (MVAR)-based connectivity measure is estimated from the EEG signals using the directed transfer functions (DTFs) method. The values of DTF power in five standard frequency bands are used as features. The support vector machines (SVMs) revealed significant differences between HS and LS. The accuracy, specificity, and sensitivity of the results using SVM are as high as 89.21%, 90.3%, and 88.2%, respectively. Our results demonstrate that the effective brain connectivity in prefrontal/parietal and prefrontal/frontal brain regions considerably changes according to schizotypal status. These findings prove that the brain connectivity indices offer valuable biomarkers for detecting schizotypal personality. Further monitoring of the changes in DTF following the diagnosis of schizotypy may lead to the early identification of schizophrenia and other spectrum disorders.

In recent years, some electrophysiological analysis methods of consciousness have been proposed. Most of these studies are based on visual interpretation or statistical analysis, and there is hardly any work classifying the level of consciousness in a deep coma. In this study, we perform an analysis of electroencephalography complexity measures by quantifying features efficiency in differentiating patients in different consciousness levels. Several measures of complexity have been proposed to quantify the complexity of signals. Our aim is to lay the foundation of a system that will objectively define the level of consciousness by performing a complexity analysis of Electroencephalogram (EEG) signals. Therefore, a nonlinear analysis of EEG signals obtained with a recording scheme proposed by us from 39 patients with Glasgow Coma Scale (GCS) between 3 and 8 was performed. Various entropy values (approximate entropy, permutation entropy, etc.) obtained from different algorithms, Hjorth parameters, Lempel–Ziv complexity and Kolmogorov complexity values were extracted from the signals as features. The features were analyzed statistically and the success of features in classifying different levels of consciousness was measured by various classifiers. Consequently, levels of consciousness in deep coma (GCS between 3 and 8) were classified with an accuracy of 90.3%. To the authors’ best knowledge, this is the first demonstration of the discriminative nonlinear features extracted from tactile and auditory stimuli EEG signals in distinguishing different GCSs of comatose patients.

Feature extraction is an essential procedure in the detection and recognition of epilepsy, especially for clinical applications. As a type of multichannel signal, the association between all of the channels in EEG samples can be further utilized. To implement the classification of epileptic seizures from the nonseizures in EEG samples, one graph convolutional neural network (GCNN)-based framework is proposed for capturing the spatial enhanced pattern of multichannel signals to characterize the behavior of EEG activity, which is capable of visualizing the salient regions in each sequence of EEG samples. Meanwhile, the presented GCNN could be exploited to discriminate normal, ictal and interictal EEGs as a novel classifier. To evaluate the proposed approach, comparison experiments were conducted between state-of-the-art techniques and ours. From the experimental results, we found that for ictal and interictal EEG signal discrimination, the presented approach can achieve a sensitivity of 98.33%, specificity of 99.19% and accuracy of 98.38%.

This paper proposes a generative model and transfer learning powered system for classification of Scanning Electron Microscope (SEM) images of defective nanofibers (D-NF) and nondefective nanofibers (ND-NF) produced by electrospinning (ES) process. Specifically, a conditional-Generative Adversarial Network (c-GAN) is developed to generate synthetic D-NF/ND-NF SEM images. A transfer learning-oriented strategy is also proposed. First, a Convolutional Neural Network (CNN) is pre-trained on real images. The transfer-learned CNN is trained on synthetic SEM images and validated on real ones, reporting accuracy rate up to 95.31%. The achieved encouraging results endorse the use of the proposed generative model in industrial applications as it could reduce the number of needed laboratory ES experiments that are costly and time consuming.

Impulsivity is a multidimensional construct often associated with unfavorable outcomes. Previous studies have implicated several electroencephalography (EEG) indices to impulsiveness, but results are heterogeneous and inconsistent. Using a data-driven approach, we identified EEG power features for the prediction of self-reported impulsiveness. To this end, EEG signals of 56 individuals (18 low impulsive, 20 intermediate impulsive, 18 high impulsive) were recorded during a risk-taking task. Extracted EEG power features from 62 electrodes were fed into various machine learning classifiers to identify the most relevant band. Robustness of the classifier was varied by stratified $k$-fold cross validation. Alpha and beta band power showed best performance in the classification of impulsiveness (accuracy = 95.18% and 95.11%, respectively) using a random forest classifier. Subsequently, a sequential bidirectional feature selection algorithm was used to estimate the most relevant electrode sites. Results show that as little as 10 electrodes are sufficient to reliably classify impulsiveness using alpha band power ($f$-measure = 94.50%). Finally, the Shapley Additive exPlanations (SHAP) analysis approach was employed to reveal the individual EEG features that contributed most to the model’s output. Results indicate that frontal as well as posterior midline alpha power seems to be of most importance for the classification of impulsiveness.

Background and Objective: Alzheimer’s disease is nowadays the most common cause of dementia. It is a degenerative neurological pathology affecting the brain, progressively leading the patient to a state of total dependence, thus creating a very complex and difficult situation for the family that has to assist him/her. Early diagnosis is a primary objective and constitutes the hope of being able to intervene in the development phase of the disease. Methods: In this paper, a method to automatically detect the presence of Alzheimer’s disease, by exploiting deep learning, is proposed. Five different convolutional neural networks are considered: ALEX_NET, VGG16, FAB_CONVNET, STANDARD_CNN and FCNN. The first two networks are state-of-the-art models, while the last three are designed by authors. We classify brain images into one of the following classes: non-demented, very mild demented and mild demented. Moreover, we highlight on the image the areas symptomatic of Alzheimer presence, thus providing a visual explanation behind the model diagnosis. Results: The experimental analysis, conducted on more than 6000 magnetic resonance images, demonstrated the effectiveness of the proposed neural networks in the comparison with the state-of-the-art models in Alzheimer’s disease diagnosis and localization. The best results in terms of metrics are the best with STANDARD_CNN and FCNN with accuracy, precision and recall between 98% and 95%. Excellent results also from a qualitative point of view are obtained with the Grad-CAM for localization and visual explainability. Conclusions: The analysis of the heatmaps produced by the Grad-CAM algorithm shows that in almost all cases the heatmaps highlight regions such as ventricles and cerebral cortex. Future work will focus on the realization of a network capable of analyzing the three anatomical views simultaneously.

Artificial intelligence (AI)-based approaches are crucial in computer-aided diagnosis (CAD) for various medical applications. Their ability to quickly and accurately learn from complex data is remarkable. Deep learning (DL) models have shown promising results in accurately classifying Alzheimer’s disease (AD) and its related cognitive states, Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI), along with the healthy conditions known as Cognitively Normal (CN). This offers valuable insights into disease progression and diagnosis. However, certain traditional machine learning (ML) classifiers perform equally well or even better than DL models, requiring less training data. This is particularly valuable in CAD in situations with limited labeled datasets. In this paper, we propose an ensemble classifier based on ML models for magnetic resonance imaging (MRI) data, which achieved an impressive accuracy of 96.52%. This represents a 3–5% improvement over the best individual classifier. We evaluated popular ML classifiers for AD classification under both data-scarce and data-rich conditions using the Alzheimer’s Disease Neuroimaging Initiative and Open Access Series of Imaging Studies datasets. By comparing the results to state-of-the-art CNN-centric DL algorithms, we gain insights into the strengths and weaknesses of each approach. This work will help users to select the most suitable algorithm for AD classification based on data availability.

Despite several automated strategies for identification/segmentation of Multiple Sclerosis (MS) lesions in Magnetic Resonance Imaging (MRI) being developed, they consistently fall short when compared to the performance of human experts. This emphasizes the unique skills and expertise of human professionals in dealing with the uncertainty resulting from the vagueness and variability of MS, the lack of specificity of MRI concerning MS, and the inherent instabilities of MRI. Physicians manage this uncertainty in part by relying on their radiological, clinical, and anatomical experience. We have developed an automated framework for identifying and segmenting MS lesions in MRI scans by introducing a novel approach to replicating human diagnosis, a significant advancement in the field. This framework has the potential to revolutionize the way MS lesions are identified and segmented, being based on three main concepts: (1) Modeling the uncertainty; (2) Use of separately trained Convolutional Neural Networks (CNNs) optimized for detecting lesions, also considering their context in the brain, and to ensure spatial continuity; (3) Implementing an ensemble classifier to combine information from these CNNs. The proposed framework has been trained, validated, and tested on a single MRI modality, the FLuid-Attenuated Inversion Recovery (FLAIR) of the MSSEG benchmark public data set containing annotated data from seven expert radiologists and one ground truth. The comparison with the ground truth and each of the seven human raters demonstrates that it operates similarly to human raters. At the same time, the proposed model demonstrates more stability, effectiveness and robustness to biases than any other state-of-the-art model though using just the FLAIR modality.

Conventional munitions emit intense radiation upon detonation which spans much of the electromagnetic spectrum. The phenomenology of time-resolved visible, near- and mid-IR spectra from these fast transient events is poorly understood. The observed spectrum is driven by many factors including the type, size and age of the chemical explosive, method of detonation, interaction with the environment, and the casing used to enclose the explosive. Midwave infrared emissions (1800–6000 cm^-1, 1.67–5.56 μm) from a variety of conventional military munitions were collected with a Fourier transform spectrometer (16 cm^-1, 21 Hz) to assess the possibility of event classification via remotely sensed spectra. Conventional munitions fireballs appear to be graybodies in the midwave. Modeling the spectra as a single-temperature Planckian (appropriately modified by atmospheric transmittance) provided key features for classification and substantially reduced the dimensionality of the data. The temperature cools from ~1800 K to ambient conditions in 3–5 s, often following an exponential decay with a rate near 1 s^-1 second. A systematic, large residual spanning 2050–2250 cm^-1 was consistently observed shortly after detonation and may be attributable to hot CO₂ emission at the periphery of the fireball. For two different explosive types detonated under similar conditions, features based on the temperature, area and fit residuals could be used to distinguish between them. This paper will present the phenomenology of detonation fireballs and explore the utility of physics-based features for explosive classification.

Threats associated with bioaerosol weapons have been around for several decades. However, with the recent political developments that changed the image and dynamics of the international order and security, the visibility and importance of these bioaerosol threats have considerably increased. Over the last few years, Defence Research and Development Canada has investigated the spectrometric LIDAR-based standoff bioaerosol detection technique to address this menace. This technique has the advantages of rapidly monitoring the atmosphere over wide areas without physical intrusions and reporting an approaching threat before it reaches sensitive sites. However, it has the disadvantages of providing a quality of information that degrades as a function of range and bioaerosol concentration. In order to determine the importance of these disadvantages, Canada initiated in 1999 the SINBAHD (Standoff Integrated Bioaerosol Active Hyperspectral Detection) project investigating the standoff detection and characterization of threatening biological clouds by Laser-Induced Fluorescence (LIF) and intensified range-gated spectrometric detection techniques. This article reports an overview of the different lessons learned with this program. Finally, the BioSense project, a Technology Demonstration Program aiming at the next generation of wide area standoff bioaerosol sensing, mapping, tracking and classifying systems, is introduced.

We prove a classification result for properly outer actions σ of discrete amenable groups G on strongly amenable subfactors of type II, N ⊂ M, a class of subfactors that were shown to be completely classified by their standard invariant , in [27]. The result shows that the action σ is completely classified in terms of the action it induces on . As an application of this, we obtain that inclusions of type III_λ factors, 0 < λ < 1, having discrete decomposition and strongly amenable graph, are completely classified by their standard invariant.

Let X be an infinite compact metric space, α : X → X a minimal homeomorphism, u the unitary that implements α in the transformation group C*-algebra C(X) ⋊_α ℤ, and a class of separable nuclear C*-algebras that contains all unital hereditary C*-subalgebras of C*-algebras in . Motivated by the success of tracial approximation by finite dimensional C*-algebras as an abstract characterization of classifiable C*-algebras and the idea that classification results for C*-algebras tensored with UHF algebras can be used to derive classification results up to tensoring with the Jiang-Su algebra , we prove that (C(X) ⋊_α ℤ) ⊗ M_q^∞ is tracially approximately if there exists a y ∈ X such that the C*-subalgebra (C*(C(X), uC₀(X\{y}))) ⊗ M_q^∞ is tracially approximately . If the class consists of finite dimensional C*-algebras, this can be used to deduce classification up to tensoring with for C*-algebras associated to minimal dynamical systems where projections separate tracial states. This is done without making any assumptions on the real rank or stable rank of either C(X) ⋊_α ℤ or C*(C(X), uC₀(X\{y})), nor on the dimension of X. The result is a key step in the classification of C*-algebras associated to uniquely ergodic minimal dynamical systems by their ordered K-groups. It also sets the stage to provide further classification results for those C*-algebras of minimal dynamical systems where projections do not necessarily separate traces.

We provide an abstract categorical framework that relates the Cuntz semigroups of the C*-algebras A and . This is done through a certain completion of ordered monoids by adding suprema of countable ascending sequences. Our construction is rather explicit and we show it is functorial and unique up to isomorphism. This approach is used in some applications to compute the stabilized Cuntz semigroup of certain C*-algebras.

We classify certain extensions of A𝕋-algebras using the six-term exact sequence in K-theory together with the Elliott invariants of the ideal and quotient. We also give certain necessary and sufficient conditions for such extension algebras being A𝕋-algebras.

Positive Quaternion Kähler Manifolds are Riemannian manifolds with holonomy contained in Sp(n)Sp(1) and with positive scalar curvature. Conjecturally, they are symmetric spaces. We prove this conjecture in dimension 20 under additional assumptions and we provide recognition theorems for the real Grassmannian in almost all dimensions.

The smallest primitive ideal spaces for which there exist counterexamples to the classification of non-simple, purely infinite, nuclear, separable C*-algebras using filtrated K-theory, are four-point spaces. In this article, we therefore restrict to real rank zero C*-algebras with four-point primitive ideal spaces. Up to homeomorphism, there are ten different connected T₀-spaces with exactly four points. We show that filtrated K-theory classifies real rank zero, tight, stable, purely infinite, nuclear, separable C*-algebras that satisfy that all simple subquotients are in the bootstrap class for eight out of ten of these spaces.

Let be the Jiang–Su algebra and let τ be its unique tracial state. We prove that for all , the following statements are equivalent:

(1) a is a finite sum of commutators.

(2) a is a sum of five commutators.

(3) τ(a) = 0.

Let M be a complex projective manifold with the property that for any compact Riemann surface C and holomorphic map f : C → M the pullback of the tangent bundle of M is semistable. We prove that in this case M is a curve or a finite étale quotient of an abelian variety answering a conjecture of Biswas.

Recently by Casas et al. a notion of chain of evolution algebras (CEAs) is introduced. This chain is a dynamical system the state of which at each given time is an evolution algebra. It is known 25 distinct classes of chains of two-dimensional evolution algebras. In our previous paper we gave the classification of two-dimensional real evolution algebras. This classification contains seven (pairwise non-isomorphic) such algebras. For each known CEA we study its dynamics to be an element of a given class.

We study a natural map from representations of a free (respectively, free abelian) group of rank g in GL_r(ℂ), to holomorphic vector bundles of degree zero over a compact Riemann surface X of genus g (respectively, complex torus X of dimension g). This map defines what is called a Schottky functor. Our main result is that this functor induces an equivalence between the category of unipotent representations of Schottky groups and the category of unipotent vector bundles on X. We also show that, over a complex torus, any vector or principal bundle with a flat holomorphic connection is Schottky.