Search

In this study, a few-shot transfer learning approach was introduced to decode movement intention from electroencephalographic (EEG) signals, allowing to recognize new tasks with minimal adaptation. To this end, a dataset of EEG signals recorded during the preparation of complex sub-movements was created from a publicly available data collection. The dataset was divided into two parts: the source domain dataset (including 5 classes) and the support (target domain) dataset, (including 2 classes) with no overlap between the two datasets in terms of classes. The proposed methodology consists in projecting EEG signals into the space-frequency-time domain, in processing such projections (rearranged in channels × frequency frames) by means of a custom EEG-based deep neural network (denoted as EEGframeNET5), and then adapting the system to recognize new tasks through a few-shot transfer learning approach. The proposed method achieved an average accuracy of 72.45 ± 4.19% in the 5-way classification of samples from the source domain dataset, outperforming comparable studies in the literature. In the second phase of the study, a few-shot transfer learning approach was proposed to adapt the neural system and make it able to recognize new tasks in the support dataset. The results demonstrated the system's ability to adapt and recognize new tasks with an average accuracy of 80 ± 0.12% in discriminating hand opening/closing preparation and outperforming reported results in the literature. This study suggests the effectiveness of EEG in capturing information related to the motor preparation of complex movements, potentially paving the way for BCI systems based on motion planning decoding. The proposed methodology could be straightforwardly extended to advanced EEG signal processing in other scenarios, such as motor imagery or neural disorder classification. [ABSTRACT FROM AUTHOR]

This document is an editorial introducing a topical collection on "Explainable and Augmented Machine Learning for Biosignals and Biomedical Images." It discusses the challenges of machine learning (ML) algorithms in the biomedical field due to their lack of transparency and the emergence of explainable artificial intelligence (xAI) techniques to address this issue. The collection includes ten papers that explore the latest advancements in xAI applied to various medical applications, such as brain function analysis, cancer biomarker identification, stress detection, emotion classification, and disease diagnosis. The papers present innovative computational methods that have the potential to be deployed in clinical contexts. [Extracted from the article]

The development of reinforced polymer composite materials has had a significant influence on the challenging problem of shielding against high-energy photons, particularly X-rays and γ -rays in industrial and healthcare facilities. Heavy materials' shielding characteristics hold a lot of potential for bolstering concrete chunks. The mass attenuation coefficient is the main physical factor that is utilized to measure the narrow beam γ -ray attenuation of various combinations of magnetite and mineral powders with concrete. Data-driven machine learning approaches can be investigated to assess the gamma-ray shielding behavior of composites as an alternative to theoretical calculations, which are often time- and resource-intensive during workbench testing. We developed a dataset using magnetite and seventeen mineral powder combinations at different densities and water/cement ratios, exposed to photon energy ranging from 1 to 100 6 kiloelectronvolt (KeV). The National Institute of Standards and Technology (NIST) photon cross-section database and software methodology (XCOM) was used to compute the concrete's γ -ray shielding characteristics (LAC). The XCOM-calculated LACs and seventeen mineral powders were exploited using a range of machine learning (ML) regressors. The goal was to investigate whether the available dataset and XCOM-simulated LAC can be replicated using ML techniques in a data-driven approach. The minimum absolute error (MAE), root mean square error (RMSE), and R 2 s c o r e were employed to assess the performance of our proposed ML models, specifically a support vector machine (SVM), 1d-convolutional neural network (CNN), multi-Layer perceptrons (MLP), linear regressor, decision tree, hierarchical extreme machine learning (HELM), extreme learning machine (ELM), and random forest networks. Comparative results showed that our proposed HELM architecture outperformed state-of-the-art SVM, decision tree, polynomial regressor, random forest, MLP, CNN, and conventional ELM models. Stepwise regression and correlation analysis were further used to evaluate the forecasting capability of ML techniques compared to the benchmark XCOM approach. According to the statistical analysis, the HELM model showed strong consistency between XCOM and predicted LAC values. Additionally, the HELM model performed better in terms of accuracy than the other models used in this study, yielding the highest R2score and the lowest MAE and RMSE. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Automatic ship detection from spaceborne systems such as satellites or aircrafts, raises considerable attention in sea surface monitoring because of the several applications in military and civilian field. In this context, processing satellite images on-board would reduce the latency time especially for emergency situations. In this paper, an hardware-oriented (HO) ship detection system based on a customized Convolutional Neural Network (CNN), here referred to as HO-ShipNet , is proposed and tested on a revised version of the "Ships in Satellite Imagery" (SSI) Kaggle dataset, reporting detection accuracy of up to 95%. Furthermore, the explainability of HO-ShipNet is investigated by means of explainable Artificial Intelligence (xAI) techniques (i.e., Local Interpretable Model-Agnostic Explanation (LIME) and Occlusion Sensitivuty Analysis (OSA)), in order to understand the reasoning behind the HO-ShipNet decisions by detecting the most important input features and consequently ensure the trustworthiness of the model itself. Finally, HO-ShipNet is also implemented on the heterogeneous Xilinx xc7z045ffg900-2 SoC Field Programmable Gate Array (FPGA) outperforming state-of-the-art FPGA-based accelerators dealing with high-resolution frames. The promising results encourage the potential deployment of the proposed system for on-board applications. [ABSTRACT FROM AUTHOR]

The Covid-19 pandemic is the defining global health crisis of our time. Chest X-Rays (CXR) have been an important imaging modality for assisting in the diagnosis and management of hospitalised Covid-19 patients. However, their interpretation is time intensive for radiologists. Accurate computer aided systems can facilitate early diagnosis of Covid-19 and effective triaging. In this paper, we propose a fuzzy logic based deep learning (DL) approach to differentiate between CXR images of patients with Covid-19 pneumonia and with interstitial pneumonias not related to Covid-19. The developed model here, referred to as CovNNet , is used to extract some relevant features from CXR images, combined with fuzzy images generated by a fuzzy edge detection algorithm. Experimental results show that using a combination of CXR and fuzzy features, within a deep learning approach by developing a deep network inputed to a Multilayer Perceptron (MLP), results in a higher classification performance (accuracy rate up to 81%), compared to benchmark deep learning approaches. The approach has been validated through additional datasets which are continously generated due to the spread of the virus and would help triage patients in acute settings. A permutation analysis is carried out, and a simple occlusion methodology for explaining decisions is also proposed. The proposed pipeline can be easily embedded into present clinical decision support systems. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid-domain deep learning (DL)-based neural system is proposed to decode hand movement preparation phases from electroencephalographic (EEG) recordings. The system exploits information extracted from the temporal-domain and time-frequency-domain, as part of a hybrid strategy, to discriminate the temporal windows (i.e. EEG epochs) preceding hand sub-movements (open/close) and the resting state. To this end, for each EEG epoch, the associated cortical source signals in the motor cortex and the corresponding time-frequency (TF) maps are estimated via beamforming and Continuous Wavelet Transform (CWT), respectively. Two Convolutional Neural Networks (CNNs) are designed: specifically, the first CNN is trained over a dataset of temporal (T) data (i.e. EEG sources), and is referred to as T-CNN; the second CNN is trained over a dataset of TF data (i.e. TF-maps of EEG sources), and is referred to as TF-CNN. Two sets of features denoted as T-features and TF-features, extracted from T-CNN and TF-CNN, respectively, are concatenated in a single features vector (denoted as TTF-features vector) which is used as input to a standard multi-layer perceptron for classification purposes. Experimental results show a significant performance improvement of our proposed hybrid-domain DL approach as compared to temporal-only and time-frequency-only-based benchmark approaches, achieving an average accuracy of 7 6. 2 1 ± 3. 7 7 %. [ABSTRACT FROM AUTHOR]

In the current digital era, one of the most critical and challenging issues is ensuring cybersecurity in information technology (IT) infrastructures. With significant improvements in technology, hackers have been developing ever more complex and dangerous malware attacks that make intrusion recognition a very difficult task. In this context, traditional analytical tools are facing severe challenges to detect and mitigate these threats. In this work, we introduce a novel statistical analysis and autoencoder (AE) driven intelligent intrusion detection system (IDS). Specifically, the proposed IDS combines data analytics and statistical techniques with recent advances in machine learning theory to extract more optimized, strongly correlated features. The proposed IDS is evaluated using the benchmark NSL-KDD database. Comparative experimental results show that the designed statistical analysis and AE based IDS achieves better classification performance compared to conventional deep and shallow machine learning and other recently proposed state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

A system that can detect the intention to move and decode the planned movement could help all those subjects that can plan motion but are unable to implement it. In this paper, motor planning activity is investigated by using electroencephalographic (EEG) signals with the aim to decode motor preparation phases. A publicly available database of 61-channels EEG signals recorded from 15 healthy subjects during the execution of different movements (elbow flexion/extension, forearm pronation/supination, hand open/close) of the right upper limb was employed to generate a dataset of EEG epochs preceding resting and movement's onset. A novel system is introduced for the classification of premovement vs resting and of premovement vs premovement epochs. For every epoch, the proposed system generates a time–frequency (TF) map of every source signal in the motor cortex, through beamforming and Continuous Wavelet Transform (CWT), then all the maps are embedded in a volume and used as input to a deep CNN. The proposed system succeeded in discriminating premovement from resting with an average accuracy of 90.3% (min 74.6%, max 100%), outperforming comparable methods in the literature, and in discriminating premovement vs premovement with an average accuracy of 62.47%. The achieved results encourage to investigate motor planning at source level in the time–frequency domain through deep learning approaches. [ABSTRACT FROM AUTHOR]

Electroencephalographic (EEG) recordings generate an electrical map of the human brain that are useful for clinical inspection of patients and in biomedical smart Internet-of-Things (IoT) and Brain-Computer Interface (BCI) applications. From a signal processing perspective, EEGs yield a nonlinear and nonstationary, multivariate representation of the underlying neural circuitry interactions. In this paper, a novel multi-modal Machine Learning (ML) based approach is proposed to integrate EEG engineered features for automatic classification of brain states. EEGs are acquired from neurological patients with Mild Cognitive Impairment (MCI) or Alzheimer's disease (AD) and the aim is to discriminate Healthy Control (HC) subjects from patients. Specifically, in order to effectively cope with nonstationarities, 19-channels EEG signals are projected into the time–frequency (TF) domain by means of the Continuous Wavelet Transform (CWT) and a set of appropriate features (denoted as CWT features) are extracted from δ , θ , α 1 , α 2 , β EEG sub-bands. Furthermore, to exploit nonlinear phase-coupling information of EEG signals, higher order statistics (HOS) are extracted from the bispectrum (BiS) representation. BiS generates a second set of features (denoted as BiS features) which are also evaluated in the five EEG sub-bands. The CWT and BiS features are fed into a number of ML classifiers to perform both 2-way (AD vs. HC, AD vs. MCI, MCI vs. HC) and 3-way (AD vs. MCI vs. HC) classifications. As an experimental benchmark, a balanced EEG dataset that includes 63 AD, 63 MCI and 63 HC is analyzed. Comparative results show that when the concatenation of CWT and BiS features (denoted as multi-modal (CWT+BiS) features) is used as input, the Multi-Layer Perceptron (MLP) classifier outperforms all other models, specifically, the Autoencoder (AE), Logistic Regression (LR) and Support Vector Machine (SVM). Consequently, our proposed multi-modal ML scheme can be considered a viable alternative to state-of-the-art computationally intensive deep learning approaches. [ABSTRACT FROM AUTHOR]

Abstract A data-driven machine deep learning approach is proposed for differentiating subjects with Alzheimer's Disease (AD), Mild Cognitive Impairment (MCI) and Healthy Control (HC), by only analyzing noninvasive scalp EEG recordings. The methodology here proposed consists of evaluating the power spectral density (PSD) of the 19-channels EEG traces and representing the related spectral profiles into 2- d gray scale images (PSD-images). A customized Convolutional Neural Network with one processing module of convolution, Rectified Linear Units (ReLu) and pooling layer (CNN 1) is designed to extract from PSD-images some suitable features and to perform the corresponding two and three-ways classification tasks. The resulting CNN is shown to provide better classification performance when compared to more conventional learning machines; indeed, it achieves an average accuracy of 89.8% in binary classification and of 83.3% in three-ways classification. These results encourage the use of deep processing systems (here, an engineered first stage, namely the PSD-image extraction, and a second or multiple CNN stage) in challenging clinical frameworks. [ABSTRACT FROM AUTHOR]

Electroencephalographic (EEG) recordings can be of great help in decoding the open/close hand’s motion preparation. To this end, cortical EEG source signals in the motor cortex (evaluated in the 1-s window preceding movement onset) are extracted by solving inverse problem through beamforming. EEG sources epochs are used as source-time maps input to a custom deep convolutional neural network (CNN) that is trained to perform 2-ways classification tasks: pre-hand close (HC) versus resting state (RE) and pre-hand open (HO) versus RE. The developed deep CNN works well (accuracy rates up to 89.65±5.29%\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$89.65 \pm 5.29\%$$\end{document} for HC versus RE and 90.50±5.35%\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$90.50 \pm 5.35\%$$\end{document} for HO versus RE), but the core of the present study was to explore the interpretability of the deep CNN to provide further insights into the activation mechanism of cortical sources during the preparation of hands’ sub-movements. Specifically, occlusion sensitivity analysis was carried out to investigate which cortical areas are more relevant in the classification procedure. Experimental results show a recurrent trend of spatial cortical activation across subjects. In particular, the central region (close to the longitudinal fissure) and the right temporal zone of the premotor together with the primary motor cortex appear to be primarily involved. Such findings encourage an in-depth study of cortical areas that seem to play a key role in hand’s open/close preparation. [ABSTRACT FROM AUTHOR]

The use of a deep neural network scheme is proposed to help clinicians solve a difficult diagnosis problem in neurology. The proposed multilayer architecture includes a feature engineering step (from time-frequency transformation), a double compressing stage trained by unsupervised learning, and a classification stage trained by supervised learning. After fine-tuning, the deep network is able to discriminate well the class of patients from controls with around 90% sensitivity and specificity. This deep model gives better classification performance than some other standard discriminative learning algorithms. As in clinical problems there is a need for explaining decisions, an effort has been carried out to qualitatively justify the classification results. The main novelty of this paper is indeed to give an entropic interpretation of how the deep scheme works and reach the final decision. [ABSTRACT FROM AUTHOR]

In the study of neurological disorders, Electroencephalographic (EEG) signal processing can provide valuable information because abnormalities in the interaction between neuron circuits may reflect on macroscopic abnormalities in the electrical potentials that can be detected on the scalp. A Mild Cognitive Impairment (MCI) condition, when caused by a disorder degenerating into dementia, affects the brain connectivity. Motivated by the promising results achieved through the recently developed descriptor of coupling strength between EEG signals, the Permutation Disalignment Index (PDI), the present paper introduces a novel PDI-based complex network model to evaluate the longitudinal variations in brain-electrical connectivity. A group of 33 amnestic MCI subjects was enrolled and followed-up with over four months. The results were compared to MoCA (Montreal Cognitive Assessment) tests, which scores the cognitive abilities of the patient. A significant negative correlation could be observed between MoCA variation and the characteristic path length (λ) variation (r = -0.56, p = 0.0006), whereas a significant positive correlation could be observed between MoCA variation and the variation of clustering coefficient (CC, r = 0.58, p = 0.0004), global efficiency (GE, r = 0.57, p = 0.0005) and small worldness (SW, r = 0.57, p = 0.0005). Cognitive decline thus seems to reflect an underlying cortical "disconnection" phenomenon: worsened subjects indeed showed an increased l and decreased CC, GE and SW. The PDI-based connectivity model, proposed in the present work, could be a novel tool for the objective quantification of longitudinal brain-electrical connectivity changes in MCI subjects. [ABSTRACT FROM AUTHOR]

The differential diagnosis of epileptic seizures (ES) and psychogenic non-epileptic seizures (PNES) may be difficult, due to the lack of distinctive clinical features. The interictal electroencephalographic (EEG) signal may also be normal in patients with ES. Innovative diagnostic tools that exploit non-linear EEG analysis and deep learning (DL) could provide important support to physicians for clinical diagnosis. In this work, 18 patients with new-onset ES (12 males, 6 females) and 18 patients with video-recorded PNES (2 males, 16 females) with normal interictal EEG at visual inspection were enrolled. None of them was taking psychotropic drugs. A convolutional neural network (CNN) scheme using DL classification was designed to classify the two categories of subjects (ES vs. PNES). The proposed architecture performs an EEG time-frequency transformation and a classification step with a CNN. The CNN was able to classify the EEG recordings of subjects with ES vs. subjects with PNES with 94.4% accuracy. CNN provided high performance in the assigned binary classification when compared to standard learning algorithms (multi-layer perceptron, support vector machine, linear discriminant analysis and quadratic discriminant analysis). In order to interpret how the CNN achieved this performance, information theoretical analysis was carried out. Specifically, the permutation entropy (PE) of the feature maps was evaluated and compared in the two classes. The achieved results, although preliminary, encourage the use of these innovative techniques to support neurologists in early diagnoses. [ABSTRACT FROM AUTHOR]

Stroke is a critical event that causes the disruption of neural connections. There is increasing evidence that the brain tries to reorganize itself and to replace the damaged circuits, by establishing compensatory pathways. Intra- and extra-cellular currents are involved in the communication between neurons and the macroscopic effects of such currents can be detected at the scalp through electroencephalographic (EEG) sensors. EEG can be used to study the lesions in the brain indirectly, by studying their effects on the brain electrical activity. The primary goal of the present work was to investigate possible asymmetries in the activity of the two hemispheres, in the case one of them is affected by a lesion due to stroke. In particular, the compressibility of High-Density-EEG (HD-EEG) recorded at the two hemispheres was investigated since the presence of the lesion is expected to impact on the regularity of EEG signals. The secondary objective was to evaluate if standard low density EEG is able to provide such information. Eighteen patients with unilateral stroke were recruited and underwent HD-EEG recording. Each EEG signal was compressively sensed, using Block Sparse Bayesian Learning, at increasing compression rate. The two hemispheres showed significant differences in the compressibility of EEG. Signals acquired at the electrode locations of the affected hemisphere showed a better reconstruction quality, quantified by the Structural SIMilarity index (SSIM), than the EEG signals recorded at the healthy hemisphere (p < 0.05), for each compression rate value. The presence of the lesion seems to induce an increased regularity in the electrical activity of the brain, thus an increased compressibility. [ABSTRACT FROM AUTHOR]

Until now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-state EEGs, to evaluate the abnormalities in PNES affected brains. Additionally, we have used functional connectivity tools, such as phase lag index (PLI), and graph-derived metrics to better observe the integration of distributed information of regular and synchronized multi-scale communication within and across inter-regional brain areas. We proved the utility of our method after enrolling a cohort study of 20 age- and gender-matched PNES and 19 healthy control (HC) subjects. In this work, three classification models, namely support vector machine (SVM), linear discriminant analysis (LDA), and Multilayer perceptron (MLP), have been employed to model the relationship between the functional connectivity features (rest-HC versus rest-PNES). The best performance for the discrimination of participants was obtained using the MLP classifier, reporting a precision of 85.73%, a recall of 86.57%, an F1-score of 78.98%, and, finally, an accuracy of 91.02%. In conclusion, our results hypothesized two main aspects. The first is an intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES. The second is that functional connectivity features and MLP could be a promising method to classify rest-EEG data of PNES form healthy controls subjects. [ABSTRACT FROM AUTHOR]

The economic and personal consequences that a car accident generates for society have been increasing in recent years. One of the causes that can generate a car accident is the stress level the driver has; consequently, the detection of stress events is a highly desirable task. In this article, the efficacy that statistical time features (STFs), such as root mean square, mean, variance, and standard deviation, among others, can reach in detecting stress events using electromyographical signals in drivers is investigated, since they can measure subtle changes that a signal can have. The obtained results show that the variance and standard deviation coupled with a support vector machine classifier with a cubic kernel are effective for detecting stress events where an AUC of 0.97 is reached. In this sense, since SVM has different kernels that can be trained, they are used to find out which one has the best efficacy using the STFs as feature inputs and a training strategy; thus, information about model explain ability can be determined. The explainability of the machine learning algorithm allows generating a deeper comprehension about the model efficacy and what model should be selected depending on the features used to its development. [ABSTRACT FROM AUTHOR]

Machine learning (ML)-based algorithms are playing an important role in cancer diagnosis and are increasingly being used to aid clinical decision-making. However, these commonly operate as 'black boxes' and it is unclear how decisions are derived. Recently, techniques have been applied to help us understand how specific ML models work and explain the rational for outputs. This study aims to determine why a given type of cancer has a certain phenotypic characteristic. Cancer results in cellular dysregulation and a thorough consideration of cancer regulators is required. This would increase our understanding of the nature of the disease and help discover more effective diagnostic, prognostic, and treatment methods for a variety of cancer types and stages. Our study proposes a novel explainable analysis of potential biomarkers denoting tumorigenesis in non-small cell lung cancer. A number of these biomarkers are known to appear following various treatment pathways. An enhanced analysis is enabled through a novel mathematical formulation for the regulators of mRNA, the regulators of ncRNA, and the coupled mRNA–ncRNA regulators. Temporal gene expression profiles are approximated in a two-dimensional spatial domain for the transition states before converging to the stationary state, using a system comprised of coupled-reaction partial differential equations. Simulation experiments demonstrate that the proposed mathematical gene-expression profile represents a best fit for the population abundance of these oncogenes. In future, our proposed solution can lead to the development of alternative interpretable approaches, through the application of ML models to discover unknown dynamics in gene regulatory systems. [ABSTRACT FROM AUTHOR]