We exploit altered patterns in brain functional connectivity as features for automatic discriminative analysis of neuropsychiatric patients. Deep learning methods have been introduced to functional network classification only very recently for fMRI, and the proposed architectures essentially focused on a single type of connectivity measure. Methods: We propose a deep convolutional neural network (CNN) framework for classification of electroencephalogram (EEG)-derived brain connectome in schizophrenia (SZ). To capture complementary aspects of disrupted connectivity in SZ, we explore combination of various connectivity features consisting of time and frequencydomain metrics of effective connectivity based on vector autoregressive model and partial directed coherence, and complex network measures of network topology. We design a novel multidomain connectome CNN (MDC-CNN) based on a parallel ensemble of 1D and 2D CNNs to integrate the features from various domains and dimensions using different fusion strategies. We also consider an extension to dynamic brain connectivity using the recurrent neural networks. Results: Hierarchical latent representations learned by the multiple convolutional layers from EEG connectivity reveals apparent group differences between SZ and healthy controls (HC). Results on a large restingstate EEG dataset show that the proposed CNNs significantly outperform traditional support vector machine classifier. The MDC-CNN with combined connectivity features further improves performance over single-domain CNNs using individual features, achieving remarkable accuracy of 91.69% with a decision-level fusion. Conclusion: The proposed MDC-CNN by integrating information from diverse brain connectivity descriptors is able to accurately discriminate SZ from HC. Significance: The new framework is potentially useful for developing diagnostic tools for SZ and other disorders.
This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of twodimensional time-frequency feature maps based on Mel-frequency cepstral coefficients (MFCC). We further develop a time-frequency CNN ensemble (TF-ECNN) combining the 1D-CNN and 2D-CNN based on score-level fusion of the class probabilities. On the large PhysioNet CinC challenge 2016 database, the proposed CNN models outperformed traditional classifiers based on support vector machine and hidden Markov models with various hand-crafted time-and frequency-domain features. Best classification scores with 89.22% accuracy and 89.94% sensitivity were achieved by the ECNN, and 91.55% specificity and 88.82% modified accuracy by the 2D-CNN alone on the test set.
Objective: This paper considers challenges in developing algorithms for accurate segmentation and classification of heart sound (HS) signals. Methods: We propose an approach based on Markov switching autoregressive model (MSAR) to segmenting the HS into four fundamental components each with distinct second-order structure. The identified boundaries are then utilized for automated classification of pathological HS using the continuous density hidden Markov model (CD-HMM). The MSAR formulated in a state-space form is able to capture simultaneously both the continuous hidden dynamics in HS, and the regime switching in the dynamics using a discrete Markov chain. This overcomes the limitation of HMM which uses a single-layer of discrete states. We introduce three schemes for model estimation: (1.) switching Kalman filter (SKF); (2.) refined SKF; (3.) fusion of SKF and the duration-dependent Viterbi algorithm (SKF-Viterbi). Results: The proposed methods are evaluated on Physionet/CinC Challenge 2016 database. The SKF-Viterbi significantly outperforms SKF by improvement of segmentation accuracy from 71% to 84.2%. The use of CD-HMM as a classifier and Mel-frequency cepstral coefficients (MFCCs) as features can characterize not only the normal and abnormal morphologies of HS signals but also morphologies considered as unclassifiable (denoted as X-Factor). It gives classification rates with best gross F 1 score of 90.19 (without X-Factor) and 82.7 (with X-Factor) for abnormal beats. Conclusion: The proposed MSAR approach for automatic localization and detection of pathological HS shows a noticeable performance on large HS dataset. Significance: It has potential applications in heart monitoring systems to assist cardiologists for pre-screening of heart pathologies.
Despite the significant progress in the understanding of the phenomenon of lightning and the physics behind it, locating and mapping its occurrence remain a challenge. Such localization and mapping of very high frequency (VHF) lightning radiation sources provide a foundation for the subsequent research on predicting lightning, saving lives, and protecting valuable assets. A major technical challenge in attempting to map the sources of lightning is mapping accuracy. The three common electromagnetic radio frequencybased lightning locating techniques are magnetic direction finder, time of arrival, and interferometer (ITF). Understanding these approaches requires critically reviewing previous attempts. The performance and reliability of each method are evaluated on the basis of the mapping accuracy obtained from lightning data from different sources. In this work, we review various methods for lightning mapping. We study the approaches, describe their techniques, analyze their merits and demerits, classify them, and derive few opportunities for further research. We find that the ITF system is the most effective method and that its performance may be improved further. One approach is to improve how lightning signals are preprocessed and how noise is filtered. Signal processing can also be utilized to improve mapping accuracy by introducing methods such as wavelet transform in place of conventional cross-correlation approaches. INDEX TERMS interferometer, lightning mapping, magnetic direction finder, time of arrival.
Lightning mapping systems based on perpendicular crossed baseline interferometer (ITF) technology have been developed rapidly in recent years. Several processing methods have been proposed to estimate the temporal location and spatial map of lightning strikes. In this paper, a single very high frequency (VHF) ITF is used to simulate and augment the lightning maps. We perform a comparative study of using different processing techniques and procedures to enhance the localization and mapping of lightning VHF radiation. The benchmark environment involves the use of different noise reduction and cross-correlation methods. Moreover, interpolation techniques are introduced to smoothen the correlation peaks for more accurate lightning localization. A positive narrow bipolar event (NBE) lightning discharge is analyzed and the mapping procedure is confirmed using both simulated and measured lightning signals. The results indicate that a good estimation of lightning radiation sources is achieved when using wavelet denoising and cross-correlations in wavelet-domain (CCWD) with a minimal error of 3.46°. The investigations carried out in this study confirm that the ITF mapping system could effectively map the lightning VHF radiation source.
In recent years, wind energy has gained extensive attention in the recent years in various countries due to the high energy demand of energy and shortage of traditional electric energy sources. Because wind energy constitutes a cost effective and environmentally friendly source, it can significantly contribute toward the reduction of the ever-increasing carbon emissions. It is one of the fastest growing green technologies worldwide, with a total generation share of 564 GW as of the end of 2018. In Malaysia, wind energy has been a hot topic in both academia and green energy industry. In this paper, the current status of wind energy research in Malaysia is reviewed. Different contributing factors such as potentiality and assessments, wind speed and direction modeling, wind prediction and spatial mapping, and optimal sizing of wind farms are extensively discussed. This paper discusses the progress of all studies related to wind energy and presents conclusions and recommendations for improving wind energy research in Malaysia.
Brain functional connectivity (FC) reveals biomarkers for identification of various neuropsychiatric disorders. Recent application of deep neural networks (DNNs) to connectomebased classification mostly relies on traditional convolutional neural networks using input connectivity matrices on a regular Euclidean grid. We propose a graph deep learning framework to incorporate the non-Euclidean information about graph structure for classifying functional magnetic resonance imaging (fMRI)derived brain networks in major depressive disorder (MDD). We design a novel graph autoencoder (GAE) architecture based on the graph convolutional networks (GCNs) to embed the topological structure and node content of large-sized fMRI networks into low-dimensional latent representations. In network construction, we employ the Ledoit-Wolf (LDW) shrinkage method to estimate the high-dimensional FC metrics efficiently from fMRI data. We consider both supervised and unsupervised approaches for the graph embedded learning. The learned embeddings are then used as feature inputs for a deep fully-connected neural network (FCNN) to discriminate MDD from healthy controls. Evaluated on a resting-state fMRI MDD dataset with 43 subjects, results show that the proposed GAE-FCNN model significantly outperforms several state-of-the-art DNN methods for brain connectome classification, achieving accuracy of 72.50% using the LDW-FC metrics as node features. The graph embeddings of fMRI FC networks learned by the GAE also reveal apparent group differences between MDD and HC. Our new framework demonstrates feasibility of learning graph embeddings on brain networks to provide discriminative information for diagnosis of brain disorders.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.