Due to the limitations of hyperspectral imaging systems, hyperspectral imagery (HSI) often suffers from poor spatial resolution, thus hampering many applications of the imagery. Hyperspectral super ...resolution refers to fusing HSI and MSI to generate an image with both high spatial and high spectral resolutions. Recently, several new methods have been proposed to solve this fusion problem, and most of these methods assume that the prior information of the point spread function (PSF) and spectral response function (SRF) are known. However, in practice, this information is often limited or unavailable. In this work, an unsupervised deep learning-based fusion method-HyCoNet-that can solve the problems in HSI-MSI fusion without the prior PSF and SRF information is proposed. HyCoNet consists of three coupled autoencoder nets in which the HSI and MSI are unmixed into endmembers and abundances based on the linear unmixing model. Two special convolutional layers are designed to act as a bridge that coordinates with the three autoencoder nets, and the PSF and SRF parameters are learned adaptively in the two convolution layers during the training process. Furthermore, driven by the joint loss function, the proposed method is straightforward and easily implemented in an end-to-end training manner. The experiments performed in the study demonstrate that the proposed method performs well and produces robust results for different data sets and arbitrary PSFs and SRFs.
Instance-level object segmentation is an important yet under-explored task. Most of state-of-the-art methods rely on region proposal methods to extract candidate segments and then utilize object ...classification to produce final results. Nonetheless, generating reliable region proposals itself is a quite challenging and unsolved task. In this work, we propose a Proposal-Free Network (PFN) to address the instance-level object segmentation problem, which outputs the numbers of instances of different categories and the pixel-level information on i) the coordinates of the instance bounding box each pixel belongs to, and ii) the confidences of different categories for each pixel, based on pixel-to-pixel deep convolutional neural network. All the outputs together, by using any off-the-shelf clustering method for simple post-processing, can naturally generate the ultimate instance-level object segmentation results. The whole PFN can be easily trained without the requirement of a proposal generation stage. Extensive evaluations on the challenging PASCAL VOC 2012 semantic segmentation benchmark demonstrate the effectiveness of the proposed PFN solution without relying on any proposal generation methods.
An enhanced design for a solar still desalination system which has been proposed in the previously conducted study of the research team is considered here, and the experimental data obtained during a ...year are employed to develop ANN models for that. Different types of artificial neural network (ANN), as one of the most popular machine learning approaches, are developed and compared together to find the best of them to predict the hourly produced distillate and water temperature in the basin, which are two key performance criteria of the system. Feedforward (FF), backpropagation (BP), and radial basis function (RBF) types of ANN are examined. According to the results, by having the coefficients of determination of 0.963111 and 0.977057, FF and RBF types are the best ANN structures for estimation of the hourly water production and water temperature in the basin, respectively. In addition, the annual error analysis done for the data not used to develop ANN models demonstrates that the average error in prediction of the hourly distillate production and water temperature in the basin varies from 9.03 and 5.13% in January (the highest values) to 4.06 and 2.07% in July (the lowest values), respectively. Moreover, the error for prediction of the daily water production is in the range of 2.41 to 5.84% in the year.
The electrocardiogram (ECG) is one of the most commonly used diagnostic tools in medicine and healthcare. Deep learning methods have achieved promising results on predictive healthcare tasks using ...ECG signals.
This paper presents a systematic review of deep learning methods for ECG data from both modeling and application perspectives.
We extracted papers that applied deep learning (deep neural network) models to ECG data that were published between January 1st of 2010 and February 29th of 2020 from Google Scholar, PubMed, and the Digital Bibliography & Library Project. We then analyzed each article according to three factors: tasks, models, and data. Finally, we discuss open challenges and unsolved problems in this area.
The total number of papers extracted was 191. Among these papers, 108 were published after 2019. Different deep learning architectures have been used in various ECG analytics tasks, such as disease detection/classification, annotation/localization, sleep staging, biometric human identification, and denoising.
The number of works on deep learning for ECG data has grown explosively in recent years. Such works have achieved accuracy comparable to that of traditional feature-based approaches and ensembles of multiple approaches can achieve even better results. Specifically, we found that a hybrid architecture of a convolutional neural network and recurrent neural network ensemble using expert features yields the best results. However, there are some new challenges and problems related to interpretability, scalability, and efficiency that must be addressed. Furthermore, it is also worth investigating new applications from the perspectives of datasets and methods.
This paper summarizes existing deep learning research using ECG data from multiple perspectives and highlights existing challenges and problems to identify potential future research directions.
•A systematic review of deep learning methods on Electrocardiogram data.•Including 191 papers from multiple research fields from 2010 to 2020.•Analyzing papers from perspectives of task, model and data.•Discussing 7 aspects of challenges and potential opportunities for future works.
Ship detection from remote sensing images can provide important information for maritime reconnaissance and surveillance and is also a challenging task. Although previous detection methods including ...some advanced ones based on deep convolutional neural network expertize in detecting horizontal or nearly horizontal targets, they cannot give satisfying detection results for arbitrary-oriented ship detection. In this letter, we introduce a novel ship detection system that can detect arbitrary-oriented ships. In this method, a rotated region proposal networks (R 2 PN) is proposed to generate multiorientated proposals with ship orientation angle information. In R 2 PN, the orientation angles of bounding boxes are also regressed to make the inclined ship region proposals generated more accurately. For ship discrimination, a rotated region of interest pooling layer is adopted in the following classification subnetwork to extract discriminative features from such inclined candidate regions. The proposed whole ship detection system can be trained end to end. Experimental results conducted on our rotated ship data set and HRSD2016 benchmark demonstrate that our proposed method outperforms state-of-the-art approaches for the arbitrary-oriented ship detection task.
Gas Recognition in E-Nose System: A Review Chen, Hong; Huo, Dexuan; Zhang, Jilin
IEEE transactions on biomedical circuits and systems,
04/2022, Letnik:
16, Številka:
2
Journal Article
Recenzirano
Odprti dostop
Gas recognition is essential in an electronic nose (E-nose) system, which is responsible for recognizing multivariate responses obtained by gas sensors in various applications. Over the past decades, ...classical gas recognition approaches such as principal component analysis (PCA) have been widely applied in E-nose systems. In recent years, artificial neural network (ANN) has revolutionized the field of E-nose, especially spiking neural network (SNN). In this paper, we investigate recent gas recognition methods for E-nose, and compare and analyze them in terms of algorithms and hardware implementations. We find each classical gas recognition method has a relatively fixed framework and a few parameters, which makes it easy to be designed and perform well with limited gas samples, but weak in multi-gas recognition under noise. While ANN-based methods obtain better recognition accuracy with flexible architectures and lots of parameters. However, some ANNs are too complex to be implemented in portable E-nose systems, such as deep convolutional neural networks (CNNs). In contrast, SNN-based gas recognition methods achieve satisfying accuracy and recognize more types of gases, and could be implemented with energy-efficient hardware, which makes them a promising candidate in multi-gas identification.
Since December 2019, the novel COVID-19’s spread rate is exponential, and AI-driven tools are used to prevent further spreading
1
. They can help predict, screen, and diagnose COVID-19 positive ...cases. Within this scope, imaging with Computed Tomography (CT) scans and Chest X-rays (CXRs) are widely used in mass triage situations. In the literature, AI-driven tools are limited to one data type either CT scan or CXR to detect COVID-19 positive cases. Integrating multiple data types could possibly provide more information in detecting anomaly patterns due to COVID-19. Therefore, in this paper, we engineered a Convolutional Neural Network (CNN) -tailored Deep Neural Network (DNN) that can collectively train/test both CT scans and CXRs. In our experiments, we achieved an overall accuracy of 96.28% (AUC = 0.9808 and false negative rate = 0.0208). Further, major existing DNNs provided coherent results while integrating CT scans and CXRs to detect COVID-19 positive cases.
•A novel combined model based on deep learning is proposed for wind speed forecasting.•The multifactor spatio-temporal correlation based on 3D matrix is considered in modeling.•The convolutional ...neural network is employed to extract the spatial feature.•The long short-term memory network is utilized to extract the temporal feature.•Comparison experiments are conducted to prove the superiority of the proposed model.
The accurate forecasting of wind speed plays a vital role in the transformation of wind energy and the dispatching of electricity. However, the inherent intermittence of wind makes it a challenge to achieve high-precision wind speed forecasting. Many existing studies consider the spatio-temporal correlation of wind speed but ignore the influence of meteorological factors on wind speed with changes in time and space. Therefore, to obtain a reliable and accurate forecasting result, a novel multifactor spatio-temporal correlation model for wind speed forecasting is proposed in this study by combining a convolutional neural network and a long short-term memory neural network. The convolutional neural network is used to extract the spatial feature relationship between the meteorological factors at various sites. The long short-term memory neural network is used to extract the temporal feature relationship between the historical time points. Meanwhile, a new data reconstruction method based on a three-dimensional matrix is developed to represent the proposed multifactor spatio-temporal correlation model. Finally, the datasets collected from the National Wind Institute in Texas, 14 baseline models, 8 evaluation metrics, a performance improvement percentage, and hypothesis testing are used to evaluate the proposed model and provide further discussion comprehensively and scientifically. The experiment results demonstrate that the proposed model outperforms other baseline models in the accuracy of forecasting and the generalization ability.
Brain tumor classification is a crucial task to evaluate the tumors and make a treatment decision according to their classes. There are many imaging techniques used to detect brain tumors. However, ...MRI is commonly used due to its superior image quality and the fact of relying on no ionizing radiation. Deep learning (DL) is a subfield of machine learning and recently showed a remarkable performance, especially in classification and segmentation problems. In this paper, a DL model based on a convolutional neural network is proposed to classify different brain tumor types using two publicly available datasets. The former one classifies tumors into (meningioma, glioma, and pituitary tumor). The other one differentiates between the three glioma grades (Grade II, Grade III, and Grade IV). The datasets include 233 and 73 patients with a total of 3064 and 516 images on T1-weighted contrast-enhanced images for the first and second datasets, respectively. The proposed network structure achieves a significant performance with the best overall accuracy of 96.13% and 98.7%, respectively, for the two studies. The results indicate the ability of the model for brain tumor multi-classification purposes.
Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems. Since then, the field has rapidly ...progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildfire science and management. Our overall objective is to improve awareness of ML methods among wildfire researchers and managers, as well as illustrate the diverse and challenging range of problems in wildfire science available to ML data scientists. To that end, we first present an overview of popular ML approaches used in wildfire science to date and then review the use of ML in wildfire science as broadly categorized into six problem domains, including (i) fuels characterization, fire detection, and mapping; (ii) fire weather and climate change; (iii) fire occurrence, susceptibility, and risk; (iv) fire behavior prediction; (v) fire effects; and (vi) fire management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildfires within a data science context. In total, to the end of 2019, we identified 300 relevant publications in which the most frequently used ML methods across problem domains included random forests, MaxEnt, artificial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods—including deep learning and agent-based learning—in the wildfire sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML models to learn on their own, expertise in wildfire science is necessary to ensure realistic modelling of fire processes across multiple scales, while the complexity of some ML methods such as deep learning requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildfire research and management communities play an active role in providing relevant, high-quality, and freely available wildfire data for use by practitioners of ML methods.
L’intelligence artificielle a ete utilisee en science et en gestion des feux de foret depuis les annees 1990, les premieres applications comprenant les reseaux neuronaux et les systemes experts. Depuis lors, le domaine a rapidement progresse parallelement a l’adoption des methodes d’apprentissage machine (AM) en sciences de l’environnement. Les auteurs presentent ici une synthese du cadrage des applications de l’AM en science et en gestion des feux de foret. Leur objectif global consiste a ameliorer la notoriete des methodes d’AM aupres des chercheurs et des gestionnaires des feux de foret, de meme qu’a illustrer l’etendue vaste et complexe des problemes en science des feux de foret dont disposent les scientifiques specialistes de donnees en AM. A cette fin, ils presentent d’abord un survol des approches populaires en AM utilisees en science des feux de foret a ce jour et font ensuite la synthese de l’utilisation de l’AM en science des feux de foret, selon six grands domaines de problemes dont (i) la caracterisation des carburants, la detection et la cartographie de l’incendie; (ii) la temperature de l’incendie et les changements climatiques; (iii) les circonstances, la susceptibilite et le risque d’incendie; (iv) la prediction du comportement de l’incendie; (v) les effets de l’incendie; et (vi) la gestion de l’incendie. Par ailleurs, les auteurs discutent des avantages et des limites de differentes approches d’AM en lien avec la taille des donnees, les exigences de calcul, le potentiel de generalisation et d’interpretation et identifient egalement les possibilites d’avancees futures en science et gestion des feux de foret dans le contexte de la science des donnees. Ils ont identifie au total 300 publications pertinentes jusqu’a la fin de 2019 qui comprennent les methodes d’AM les plus frequemment utilisees a travers les domaines de problemes, dont les forets aleatoires, MaxEnt, les reseaux de neurones artificiels, les arbres de decision, les separateurs a vaste marge et les algorithmes genetiques. Il existe ainsi des possibilites d’appliquer davantage de methodes actuelles d’AM—y compris l’apprentissage profond et l’apprentissage base sur l’agent—en sciences des feux de foret, particulierement dans les cas impliquant de tres grands ensembles de donnees multivariees. Ilsreconnaissent cependant que, malgre la capacite des methodes en AM d’apprendre par elles-memes, l’expertise en science des feux de foret est necessaire pour s’assurer d’une modelisation realiste des processus des incendies a differentes echelles, alors que la complexite de certaines methodes en AM telles que l’apprentissage profond, requiert une connaissance approfondie et specifique de leur application. Finalement, ils soulignent que les communautes qui se consacrent a la recherche et a la gestion des feux de foret jouent un role actif en fournissant des donnees pertinentes, de haute qualite et en libre acces a l’usage des praticiens des methodes en AM.
PDF
