APPLIED DEEP LEARNING FOR SLENDER MARINE STRUCTURE DYNAMIC ANALYSIS

Abstract Non-linear finite element models (FEM) are commonly used to perform analysis in the time domain to simulate a limited number of stochastic loading scenarios that a slender marine structure may undergo, requiring a high computational time effort. Analytical equations and frequency domain analysis can be used to speed up these simulations, but they are not a convenient choice when high non-linearities are present in the dynamic system. Alternative models can be developed to reduce the simulation time while maintaining a good accuracy level of the system's response. This work proposes different strategies to develop artificial neural networks (ANN) architectures, based on deep learning algorithms, which can predict multiple structural node responses at once, in time and space, significantly reducing the total training time when a great number of structural nodes are considered. A novel classification concept of ANN-based models is introduced for this application: the NodeNet and the LengthNet class types. In the first approach, the model predictor focuses on a single structural node, while in the latter the model focuses on a length (segment) comprising many structural nodes. The work also extends the response predictions of such marine structures from the top region down to the Touchdown Zone (TDZ).

Download Full-text

Time-Domain Approach for Acoustic Scattering of Rotorcraft Noise

Journal of the American Helicopter Society ◽

10.4050/jahs.57.042001 ◽

2012 ◽

Vol 57 (4) ◽

pp. 1-12 ◽

Cited By ~ 18

Author(s):

Seongkyu Lee ◽

Kenneth S. Brentner ◽

Philip J. Morris

Keyword(s):

Frequency Domain ◽

Time Domain ◽

Impulsive Noise ◽

Near Field ◽

Acoustic Scattering ◽

Frequency Domain Analysis ◽

Computational Time ◽

Computationally Efficient ◽

Time Saving ◽

The Time Domain

This paper addresses acoustic scattering of rotorcraft noise in the time domain. A time-domain equivalent source method is used since it is considered to be a computationally efficient method to solve acoustic scattering. In addition, the time-domain method provides a solution for all frequencies of interest in a single computation and is able to predict the acoustic scattering of aperiodic signals. The prediction is validated against exact solutions for a monopole source. The numerical method is then used to predict acoustic scattering of noise from a BO105 tail rotor by a representative fuselage. Complex directivity patterns are seen in the near field, and a large scattering effect is observed in the far field to the side of the fuselage. The time-domain code results of sound pressure level are validated against the results obtained by a frequency-domain analysis. Finally, acoustic scattering for an impulsive noise source is investigated to simulate main rotor blade–vortex interaction noise. The scattered pressure has a comparable amplitude as that of the incident pressure so that the total pressure is dramatically changed compared to the incident pressure. For the impulsive noise, a large computational time saving is achieved compared to the frequency-domain approach, in which the computation must be repeated for each frequency.

Download Full-text

Computational Complexity Reduction of Neural Networks of Brain Tumor Image Segmentation by Introducing Fermi–Dirac Correction Functions

Entropy ◽

10.3390/e23020223 ◽

2021 ◽

Vol 23 (2) ◽

pp. 223

Author(s):

Yen-Ling Tai ◽

Shin-Jhe Huang ◽

Chien-Chang Chen ◽

Henry Horng-Shing Lu

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Computational Complexity ◽

High Performance ◽

Low Cost ◽

Structural Complexity ◽

Correction Function ◽

Computational Time ◽

Learning Methods ◽

Band Theory

Nowadays, deep learning methods with high structural complexity and flexibility inevitably lean on the computational capability of the hardware. A platform with high-performance GPUs and large amounts of memory could support neural networks having large numbers of layers and kernels. However, naively pursuing high-cost hardware would probably drag the technical development of deep learning methods. In the article, we thus establish a new preprocessing method to reduce the computational complexity of the neural networks. Inspired by the band theory of solids in physics, we map the image space into a noninteraction physical system isomorphically and then treat image voxels as particle-like clusters. Then, we reconstruct the Fermi–Dirac distribution to be a correction function for the normalization of the voxel intensity and as a filter of insignificant cluster components. The filtered clusters at the circumstance can delineate the morphological heterogeneity of the image voxels. We used the BraTS 2019 datasets and the dimensional fusion U-net for the algorithmic validation, and the proposed Fermi–Dirac correction function exhibited comparable performance to other employed preprocessing methods. By comparing to the conventional z-score normalization function and the Gamma correction function, the proposed algorithm can save at least 38% of computational time cost under a low-cost hardware architecture. Even though the correction function of global histogram equalization has the lowest computational time among the employed correction functions, the proposed Fermi–Dirac correction function exhibits better capabilities of image augmentation and segmentation.

Download Full-text

An Efficient DenseNet-Based Deep Learning Model for Malware Detection

Entropy ◽

10.3390/e23030344 ◽

2021 ◽

Vol 23 (3) ◽

pp. 344

Author(s):

Jeyaprakash Hemalatha ◽

S. Abijah Roseline ◽

Subbiah Geetha ◽

Seifedine Kadry ◽

Robertas Damaševičius

Keyword(s):

Deep Learning ◽

Detection System ◽

Malware Detection ◽

Class Imbalance ◽

Learning Model ◽

Computational Time ◽

Learning Approaches ◽

Security Threat ◽

Static And Dynamic Analysis ◽

Deep Learning Model

Recently, there has been a huge rise in malware growth, which creates a significant security threat to organizations and individuals. Despite the incessant efforts of cybersecurity research to defend against malware threats, malware developers discover new ways to evade these defense techniques. Traditional static and dynamic analysis methods are ineffective in identifying new malware and pose high overhead in terms of memory and time. Typical machine learning approaches that train a classifier based on handcrafted features are also not sufficiently potent against these evasive techniques and require more efforts due to feature-engineering. Recent malware detectors indicate performance degradation due to class imbalance in malware datasets. To resolve these challenges, this work adopts a visualization-based method, where malware binaries are depicted as two-dimensional images and classified by a deep learning model. We propose an efficient malware detection system based on deep learning. The system uses a reweighted class-balanced loss function in the final classification layer of the DenseNet model to achieve significant performance improvements in classifying malware by handling imbalanced data issues. Comprehensive experiments performed on four benchmark malware datasets show that the proposed approach can detect new malware samples with higher accuracy (98.23% for the Malimg dataset, 98.46% for the BIG 2015 dataset, 98.21% for the MaleVis dataset, and 89.48% for the unseen Malicia dataset) and reduced false-positive rates when compared with conventional malware mitigation techniques while maintaining low computational time. The proposed malware detection solution is also reliable and effective against obfuscation attacks.

Download Full-text

Computing 3D Phase-Type Holograms Based on Deep Learning Method

Photonics ◽

10.3390/photonics8070280 ◽

2021 ◽

Vol 8 (7) ◽

pp. 280

Author(s):

Huadong Zheng ◽

Jianbin Hu ◽

Chaojun Zhou ◽

Xiaoxi Wang

Keyword(s):

Deep Learning ◽

Signal To Noise Ratio ◽

Contrast Ratio ◽

Angular Spectrum ◽

Structural Similarity ◽

Computational Time ◽

Experimental Investigations ◽

Training Strategy ◽

Holographic Display ◽

Phase Type

Computer holography is a technology that use a mathematical model of optical holography to generate digital holograms. It has wide and promising applications in various areas, especially holographic display. However, traditional computational algorithms for generation of phase-type holograms based on iterative optimization have a built-in tradeoff between the calculating speed and accuracy, which severely limits the performance of computational holograms in advanced applications. Recently, several deep learning based computational methods for generating holograms have gained more and more attention. In this paper, a convolutional neural network for generation of multi-plane holograms and its training strategy is proposed using a multi-plane iterative angular spectrum algorithm (ASM). The well-trained network indicates an excellent ability to generate phase-only holograms for multi-plane input images and to reconstruct correct images in the corresponding depth plane. Numerical simulations and optical reconstructions show that the accuracy of this method is almost the same with traditional iterative methods but the computational time decreases dramatically. The result images show a high quality through analysis of the image performance indicators, e.g., peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and contrast ratio. Finally, the effectiveness of the proposed method is verified through experimental investigations.

Download Full-text

fNIRS Signal Classification Based on Deep Learning in Rock-Paper-Scissors Imagery Task

Applied Sciences ◽

10.3390/app11114922 ◽

2021 ◽

Vol 11 (11) ◽

pp. 4922

Author(s):

Tengfei Ma ◽

Wentian Chen ◽

Xin Li ◽

Yuting Xia ◽

Xinhua Zhu ◽

...

Keyword(s):

Deep Learning ◽

Total Duration ◽

Signal Classification ◽

Imagery Task ◽

Neural Activities ◽

Computer Interfaces ◽

Acquisition Device ◽

The Time Domain ◽

The Brain

To explore whether the brain contains pattern differences in the rock–paper–scissors (RPS) imagery task, this paper attempts to classify this task using fNIRS and deep learning. In this study, we designed an RPS task with a total duration of 25 min and 40 s, and recruited 22 volunteers for the experiment. We used the fNIRS acquisition device (FOIRE-3000) to record the cerebral neural activities of these participants in the RPS task. The time series classification (TSC) algorithm was introduced into the time-domain fNIRS signal classification. Experiments show that CNN-based TSC methods can achieve 97% accuracy in RPS classification. CNN-based TSC method is suitable for the classification of fNIRS signals in RPS motor imagery tasks, and may find new application directions for the development of brain–computer interfaces (BCI).

Download Full-text

Nesting Monte Carlo for high-dimensional non-linear PDEs

Monte Carlo Methods and Applications ◽

10.1515/mcma-2018-2020 ◽

2018 ◽

Vol 24 (4) ◽

pp. 225-247 ◽

Cited By ~ 4

Author(s):

Xavier Warin

Keyword(s):

Monte Carlo ◽

Deep Learning ◽

High Dimension ◽

Analytical Solutions ◽

New Method ◽

Computational Time ◽

High Dimensional ◽

Learning Methods ◽

Lipschitz Constants ◽

Linear Pdes

Abstract A new method based on nesting Monte Carlo is developed to solve high-dimensional semi-linear PDEs. Depending on the type of non-linearity, different schemes are proposed and theoretically studied: variance error are given and it is shown that the bias of the schemes can be controlled. The limitation of the method is that the maturity or the Lipschitz constants of the non-linearity should not be too high in order to avoid an explosion of the computational time. Many numerical results are given in high dimension for cases where analytical solutions are available or where some solutions can be computed by deep-learning methods.

Download Full-text

A Multimodal Feature Fusion-Based Deep Learning Method for Online Fault Diagnosis of Rotating Machinery

Sensors ◽

10.3390/s18103521 ◽

2018 ◽

Vol 18 (10) ◽

pp. 3521 ◽

Cited By ~ 6

Author(s):

Funa Zhou ◽

Po Hu ◽

Shuai Yang ◽

Chenglin Wen

Keyword(s):

Deep Learning ◽

Fault Diagnosis ◽

Real Time ◽

Time Domain ◽

Feature Fusion ◽

Rotating Machinery ◽

Time Domain Data ◽

Diagnosis Method ◽

The Time Domain ◽

Potential Frequency

Rotating machinery usually suffers from a type of fault, where the fault feature extracted in the frequency domain is significant, while the fault feature extracted in the time domain is insignificant. For this type of fault, a deep learning-based fault diagnosis method developed in the frequency domain can reach high accuracy performance without real-time performance, whereas a deep learning-based fault diagnosis method developed in the time domain obtains real-time diagnosis with lower diagnosis accuracy. In this paper, a multimodal feature fusion-based deep learning method for accurate and real-time online diagnosis of rotating machinery is proposed. The proposed method can directly extract the potential frequency of abnormal features involved in the time domain data. Firstly, multimodal features corresponding to the original data, the slope data, and the curvature data are firstly extracted by three separate deep neural networks. Then, a multimodal feature fusion is developed to obtain a new fused feature that can characterize the potential frequency feature involved in the time domain data. Lastly, the fused new feature is used as the input of the Softmax classifier to achieve a real-time online diagnosis result from the frequency-type fault data. A simulation experiment and a case study of the bearing fault diagnosis confirm the high efficiency of the method proposed in this paper.

Download Full-text

Parallel Algorithms for Spatial Rainfall Distribution

Jurnal INKOM ◽

10.14203/j.inkom.383 ◽

2014 ◽

Vol 8 (1) ◽

pp. 29 ◽

Cited By ~ 1

Author(s):

Arnida Lailatul Latifah ◽

Adi Nurhadiyatna

Keyword(s):

Parallel Algorithms ◽

Computation Time ◽

Computational Time ◽

Rainfall Distribution ◽

Flood Modelling ◽

Computation Efficiency ◽

Distance Weighting ◽

Speed Up ◽

Important Input ◽

Serial Algorithms

This paper proposes parallel algorithms for precipitation of flood modelling, especially applied in spatial rainfall distribution. As an important input in flood modelling, spatial distribution of rainfall is always needed as a pre-conditioned model. In this paper two interpolation methods, Inverse distance weighting (IDW) and Ordinary kriging (OK) are discussed. Both are developed in parallel algorithms in order to reduce the computational time. To measure the computation efficiency, the performance of the parallel algorithms are compared to the serial algorithms for both methods. Findings indicate that: (1) the computation time of OK algorithm is up to 23% longer than IDW; (2) the computation time of OK and IDW algorithms is linearly increasing with the number of cells/ points; (3) the computation time of the parallel algorithms for both methods is exponentially decaying with the number of processors. The parallel algorithm of IDW gives a decay factor of 0.52, while OK gives 0.53; (4) The parallel algorithms perform near ideal speed-up.

Download Full-text

A Systematic Analysis of Big Image Data Methodologies in Various Applications

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.e2307.039520 ◽

2020 ◽

Vol 9 (5) ◽

pp. 483-487

Keyword(s):

Big Data ◽

Deep Learning ◽

Large Scale ◽

Image Data ◽

Computational Time ◽

Process Data ◽

Systematic Analysis ◽

Large Scale Data ◽

Learning Techniques ◽

Effective Performance

Big data is large-scale data collected for knowledge discovery, it has been widely used in various applications. Big data often has image data from the various applications and requires effective technique to process data. In this paper, survey has been done in the big image data researches to analysis the effective performance of the methods. Deep learning techniques provides the effective performance compared to other methods included wavelet based methods. The deep learning techniques has the problem of requiring more computational time, and this can be overcome by lightweight methods.

Download Full-text

Batch Effect Removal via Batch-Free Encoding

10.1101/380816 ◽

2018 ◽

Cited By ~ 1

Author(s):

Uri Shaham

Keyword(s):

Deep Learning ◽

Biological Properties ◽

Batch Effect ◽

Training Data ◽

Rna Seq ◽

Batch Effects ◽

Training Time ◽

Learning Techniques ◽

Downstream Analysis ◽

Biological Patterns

AbstractBiological measurements often contain systematic errors, also known as “batch effects”, which may invalidate downstream analysis when not handled correctly. The problem of removing batch effects is of major importance in the biological community. Despite recent advances in this direction via deep learning techniques, most current methods may not fully preserve the true biological patterns the data contains. In this work we propose a deep learning approach for batch effect removal. The crux of our approach is learning a batch-free encoding of the data, representing its intrinsic biological properties, but not batch effects. In addition, we also encode the systematic factors through a decoding mechanism and require accurate reconstruction of the data. Altogether, this allows us to fully preserve the true biological patterns represented in the data. Experimental results are reported on data obtained from two high throughput technologies, mass cytometry and single-cell RNA-seq. Beyond good performance on training data, we also observe that our system performs well on test data obtained from new patients, which was not available at training time. Our method is easy to handle, a publicly available code can be found at https://github.com/ushaham/BatchEffectRemoval2018.

Download Full-text