The effective use of long-range information can yield improved network performance, which is very important for image restoration. Although local window-based models have linear complexity and can be ...feasibly applied to process high-resolution images, a single-scale window has a limited receptive field and is less efficient for encoding long-range context information. To address this issue, this paper presents a single-stage multiscale spatial rearrangement multilayer perceptron (MSSR-MLP) architecture that can obtain information at different scales within a local window. Specifically, we propose a simple and efficient spatial rearrangement module (SRM) that moves information outside the local window to the inside of the local window so that long-range dependencies can be modeled using only a window-based fully connected (FC) layer. The SRM can extend the local receptive field of a window-based FC layer without introducing additional parameters and FLOPs. Utilizing several spatial rearrangement modules with different step sizes, we design an efficient multiscale spatial rearrangement MLP architecture for image restoration. This design aggregates multiscale information to achieve improved restoration quality while maintaining a low computational cost. Extensive experiments conducted on several image restoration tasks demonstrate the efficiency and effectiveness of our method. For example, it requires only ~4.3% of the FLOPs needed by SwinIR for Gaussian gray image denoising, ~13.9% of the FLOPs needed by <inline-formula> <tex-math notation="LaTeX">\mathrm {C^{2}} </tex-math></inline-formula>PNet for single-image dehazing and ~18.9% of the FLOPs needed by MAXIM for single-image motion deblurring but achieves better performance on each of these restoration tasks.
Prediction of the COVID-19 incidence rate is a matter of global importance, particularly in the United States. As of 4 June 2020, more than 1.8 million confirmed cases and over 108 thousand deaths ...have been reported in this country. Few studies have examined nationwide modeling of COVID-19 incidence in the United States particularly using machine-learning algorithms. Thus, we collected and prepared a database of 57 candidate explanatory variables to examine the performance of multilayer perceptron (MLP) neural network in predicting the cumulative COVID-19 incidence rates across the continental United States. Our results indicated that a single-hidden-layer MLP could explain almost 65% of the correlation with ground truth for the holdout samples. Sensitivity analysis conducted on this model showed that the age-adjusted mortality rates of ischemic heart disease, pancreatic cancer, and leukemia, together with two socioeconomic and environmental factors (median household income and total precipitation), are among the most substantial factors for predicting COVID-19 incidence rates. Moreover, results of the logistic regression model indicated that these variables could explain the presence/absence of the hotspots of disease incidence that were identified by Getis-Ord Gi* (
< 0.05) in a geographic information system environment. The findings may provide useful insights for public health decision makers regarding the influence of potential risk factors associated with the COVID-19 incidence at the county level.
Purpose
To reconstruct MR images from subsampled data, we propose a fast reconstruction method using the multilayer perceptron (MLP) algorithm.
Methods and materials
We applied MLP to reduce aliasing ...artifacts generated by subsampling in k‐space. The MLP is learned from training data to map aliased input images into desired alias‐free images. The input of the MLP is all voxels in the aliased lines of multichannel real and imaginary images from the subsampled k‐space data, and the desired output is all voxels in the corresponding alias‐free line of the root‐sum‐of‐squares of multichannel images from fully sampled k‐space data. Aliasing artifacts in an image reconstructed from subsampled data were reduced by line‐by‐line processing of the learned MLP architecture.
Results
Reconstructed images from the proposed method are better than those from compared methods in terms of normalized root‐mean‐square error. The proposed method can be applied to image reconstruction for any k‐space subsampling patterns in a phase encoding direction. Moreover, to further reduce the reconstruction time, it is easily implemented by parallel processing.
Conclusion
We have proposed a reconstruction method using machine learning to accelerate imaging time, which reconstructs high‐quality images from subsampled k‐space data. It shows flexibility in the use of k‐space sampling patterns, and can reconstruct images in real time.
Two new hybrid neural architectures combining morphological neurons and perceptrons are introduced in this paper. The first architecture, called Morphological - Linear Neural Network (MLNN) consists ...of a hidden layer of morphological neurons and an output layer of classical perceptrons has the capability of extracting features. The second architecture, called Linear-Morphological Neural Network (LMNN) is composed of one or several perceptron layers as a feature extractor, it is then followed by an output layer of morphological neurons for non-linear classification. Both architectures are trained by stochastic gradient descent. One of the main contributions of this paper is to show that the morphological layer offers a greater capacity to extract features than the perceptron layer. This claim is supported both theoretically and experimentally. We prove that the morphological layer possesses a greater capacity per computation unit to segment the 2D input space than the perceptron layer. In other words, adding more hyper-boxes produces more response regions than adding hyperplanes. From an empirical point of view, we test the two new models on 25 standard datasets at low dimensionality and one big data dataset. The result is that MLNN requires a lesser number of learning parameters than the other tested architectures while achieving better accuracies.
Wheat is one of the most strategically essential crops in the world and one of Iraq's most important crops.The objective of the present study was to analyze energy and examine the application of a ...multilayer perceptron for predicting wheat yield production in the Kirkuk governorate. The research data were collected with a face-to-face inquiry made with the farmers at two fields that include the types of equipment used for the production of wheat, the number of hours worked, fuel, oil, workers, and the style of agricultural processes for the wheat crop production. The research results showed that total energy consumption in wheat was 13315.21 and 29016.27 MJha-1, while the output energy was 24867.5 and 88641 MJha-1 for the first and second fields, respectively. Seed and diesel fuel consumption are considered essential variables in wheat plantation operations, its the highest input energy values being the relative values of 30.2 and 61.97 %. These variables impacted wheat operation from 2021 to 2022 at 4020 and 17982.44 MJha-1 for the first and second fields, respectively. Finally, the results concluded that the neural network model helps predict wheat production-the neural network architecture 7-4-1 and 5-7-1 for the first and second field systems. The research shows that the trained models produced a minimum error, indicating that the test model can predict wheat yield production in the Kirkuk governorate.
This paper presents a comparative study of different methods, such as the analytical method, finite element method (FEM), and multilayer perceptron (MLP) for analyzing a frictionless receding contact ...problem. The problem consists of two layers resting on a Winkler foundation. The top layer is functionally graded (FG) along the depth and pressed using a rigid cylindrical stamp, whereas the bottom layer is homogeneous. We assumed that the contact between the two layers, and that between the FG layer and the rigid cylindrical stamp are frictionless; additionally, compressive normal tractions can be transmitted through the interface. First, the problem was solved analytically using the theory of elasticity and integral transform techniques. Second, the finite element solution of the problem was obtained using ANSYS software. Finally, the problem was extended based on the MLP, which an artificial neural network used for different problem parameters. The results of this study showed that the variations in the contact lengths at the interface between the rigid cylindrical stamp and the FG layer, those between the homogeneous layer and the FG layer, and the maximum contact pressures at these interfaces depended on various dimensionless quantities such as the stamp radius, stiffness parameter, shear modulus ratio, and elastic spring constant ratio. We observed that the results obtained with the three different methods, namely the analytical method, FEM, and MLP, are extremely compatible with each other, thus proving the accuracy of these results.
•In engineering mechanics, contact problems have different applications to a variety of structures.•Numerical results obtained for various dimensionless quantities for the contact problem are presented in graphical form.•We study the effect of various parameters on the contact length and pressure.•We compared analytical and numerical solutions for a receding contact problem.
Purpose
To develop a 3D UNET convolutional neural network for rapid extraction of myelin water fraction (MWF) maps from six‐echo fast acquisition with spiral trajectory and T2‐prep data and to ...evaluate its accuracy in comparison with multilayer perceptron (MLP) network.
Methods
The MWF maps were extracted from 138 patients with multiple sclerosis using an iterative three‐pool nonlinear least‐squares algorithm (NLLS) without and with spatial regularization (srNLLS), which were used as ground‐truth labels to train, validate, and test UNET and MLP networks as a means to accelerate data fitting. Network testing was performed in 63 patients with multiple sclerosis and a numerically simulated brain phantom at SNR of 200, 100 and 50.
Results
Simulations showed that UNET reduced the MWF mean absolute error by 30.1% to 56.4% and 16.8% to 53.6% over the whole brain and by 41.2% to 54.4% and 21.4% to 49.4% over the lesions for predicting srNLLS and NLLS MWF, respectively, compared to MLP, with better performance at lower SNRs. UNET also outperformed MLP for predicting srNLLS MWF in the in vivo multiple‐sclerosis brain data, reducing mean absolute error over the whole brain by 61.9% and over the lesions by 67.5%. However, MLP yielded 41.1% and 51.7% lower mean absolute error for predicting in vivo NLLS MWF over the whole brain and the lesions, respectively, compared with UNET. The whole‐brain MWF processing time using a GPU was 0.64 seconds for UNET and 0.74 seconds for MLP.
Conclusion
Subsecond whole‐brain MWF extraction from fast acquisition with spiral trajectory and T2‐prep data using UNET is feasible and provides better accuracy than MLP for predicting MWF output of srNLLS algorithm.
The multilayer perceptron (MLP) neural network is interpreted from the geometrical viewpoint in this work, that is, an MLP partition an input feature space into multiple nonoverlapping subspaces ...using a set of hyperplanes, where the great majority of samples in a subspace belongs to one object class. Based on this high-level idea, we propose a three-layer feedforward MLP (FF-MLP) architecture for its implementation. In the first layer, the input feature space is split into multiple subspaces by a set of partitioning hyperplanes and rectified linear unit (ReLU) activation, which is implemented by the classical two-class linear discriminant analysis (LDA). In the second layer, each neuron activates one of the subspaces formed by the partitioning hyperplanes with specially designed weights. In the third layer, all subspaces of the same class are connected to an output node that represents the object class. The proposed design determines all MLP parameters in a feedforward one-pass fashion analytically without backpropagation. Experiments are conducted to compare the performance of the traditional backpropagation-based MLP (BP-MLP) and the new FF-MLP. It is observed that the FF-MLP outperforms the BP-MLP in terms of design time, training time, and classification performance in several benchmarking datasets. Our source code is available at https://colab.research.google.com/drive/1Gz0L8AnT4ijrUchrhEXXsnaacrFdenn?usp = sharing .
Air-blast overpressure (AOp) is one of the undesirable effects caused by blasting operations in open-pit mines. This side effect of blasting can seriously undermine surrounding residential structures ...and living quality. To control and mitigate this situation, this study using artificial neural networks to predict AOp implemented at Deo Nai open-pit coal mine, Vietnam. A total of 146 events of blasting were recorded, of which 80% (118 observations) was used for training and 20% (28 observations) was used for testing. A resampling technique, namely tenfold cross-validation, was performed with three repeats to increase the accuracy of the predictive models. In this paper, three different types of neural networks were developed to predict AOp including multilayer perceptron neural network (MLP neural nets), Bayesian regularized neural networks (BRNN) and hybrid neural fuzzy inference system (HYFIS). Each type was tested with ten model configurations to discover the best performing ones based on comparing standard metrics, including root-mean-square error (RMSE), coefficient of determination (
R
2
), and a simple ranking method. Eight parameters were considered for these models, including charge per delay, burden, spacing, length of stemming, powder factor, air humidity, and monitoring distance. The results indicated that MLP neural nets model with RMSE = 2.319,
R
2
= 0.961 on testing datasets and a total ranking of 12 yielded the most accurate prediction over BRNN and HYFIS models.