Search results for: Neural Processing Element (NPE)
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 7852

Search results for: Neural Processing Element (NPE)

7672 Physics-Informed Neural Network for Predicting Strain Demand in Inelastic Pipes under Ground Movement with Geometric and Soil Resistance Nonlinearities

Authors: Pouya Taraghi, Yong Li, Nader Yoosef-Ghodsi, Muntaseer Kainat, Samer Adeeb

Abstract:

Buried pipelines play a crucial role in the transportation of energy products such as oil, gas, and various chemical fluids, ensuring their efficient and safe distribution. However, these pipelines are often susceptible to ground movements caused by geohazards like landslides, fault movements, lateral spreading, and more. Such ground movements can lead to strain-induced failures in pipes, resulting in leaks or explosions, leading to fires, financial losses, environmental contamination, and even loss of human life. Therefore, it is essential to study how buried pipelines respond when traversing geohazard-prone areas to assess the potential impact of ground movement on pipeline design. As such, this study introduces an approach called the Physics-Informed Neural Network (PINN) to predict the strain demand in inelastic pipes subjected to permanent ground displacement (PGD). This method uses a deep learning framework that does not require training data and makes it feasible to consider more realistic assumptions regarding existing nonlinearities. It leverages the underlying physics described by differential equations to approximate the solution. The study analyzes various scenarios involving different geohazard types, PGD values, and crossing angles, comparing the predictions with results obtained from finite element methods. The findings demonstrate a good agreement between the results of the proposed method and the finite element method, highlighting its potential as a simulation-free, data-free, and meshless alternative. This study paves the way for further advancements, such as the simulation-free reliability assessment of pipes subjected to PGD, as part of ongoing research that leverages the proposed method.

Keywords: strain demand, inelastic pipe, permanent ground displacement, machine learning, physics-informed neural network

Procedia PDF Downloads 39
7671 Improving the Accuracy of Stress Intensity Factors Obtained by Scaled Boundary Finite Element Method on Hybrid Quadtree Meshes

Authors: Adrian W. Egger, Savvas P. Triantafyllou, Eleni N. Chatzi

Abstract:

The scaled boundary finite element method (SBFEM) is a semi-analytical numerical method, which introduces a scaling center in each element’s domain, thus transitioning from a Cartesian reference frame to one resembling polar coordinates. Consequently, an analytical solution is achieved in radial direction, implying that only the boundary need be discretized. The only limitation imposed on the resulting polygonal elements is that they remain star-convex. Further arbitrary p- or h-refinement may be applied locally in a mesh. The polygonal nature of SBFEM elements has been exploited in quadtree meshes to alleviate all issues conventionally associated with hanging nodes. Furthermore, since in 2D this results in only 16 possible cell configurations, these are precomputed in order to accelerate the forward analysis significantly. Any cells, which are clipped to accommodate the domain geometry, must be computed conventionally. However, since SBFEM permits polygonal elements, significantly coarser meshes at comparable accuracy levels are obtained when compared with conventional quadtree analysis, further increasing the computational efficiency of this scheme. The generalized stress intensity factors (gSIFs) are computed by exploiting the semi-analytical solution in radial direction. This is initiated by placing the scaling center of the element containing the crack at the crack tip. Taking an analytical limit of this element’s stress field as it approaches the crack tip, delivers an expression for the singular stress field. By applying the problem specific boundary conditions, the geometry correction factor is obtained, and the gSIFs are then evaluated based on their formal definition. Since the SBFEM solution is constructed as a power series, not unlike mode superposition in FEM, the two modes contributing to the singular response of the element can be easily identified in post-processing. Compared to the extended finite element method (XFEM) this approach is highly convenient, since neither enrichment terms nor a priori knowledge of the singularity is required. Computation of the gSIFs by SBFEM permits exceptional accuracy, however, when combined with hybrid quadtrees employing linear elements, this does not always hold. Nevertheless, it has been shown that crack propagation schemes are highly effective even given very coarse discretization since they only rely on the ratio of mode one to mode two gSIFs. The absolute values of the gSIFs may still be subject to large errors. Hence, we propose a post-processing scheme, which minimizes the error resulting from the approximation space of the cracked element, thus limiting the error in the gSIFs to the discretization error of the quadtree mesh. This is achieved by h- and/or p-refinement of the cracked element, which elevates the amount of modes present in the solution. The resulting numerical description of the element is highly accurate, with the main error source now stemming from its boundary displacement solution. Numerical examples show that this post-processing procedure can significantly improve the accuracy of the computed gSIFs with negligible computational cost even on coarse meshes resulting from hybrid quadtrees.

Keywords: linear elastic fracture mechanics, generalized stress intensity factors, scaled finite element method, hybrid quadtrees

Procedia PDF Downloads 117
7670 Short Term Distribution Load Forecasting Using Wavelet Transform and Artificial Neural Networks

Authors: S. Neelima, P. S. Subramanyam

Abstract:

The major tool for distribution planning is load forecasting, which is the anticipation of the load in advance. Artificial neural networks have found wide applications in load forecasting to obtain an efficient strategy for planning and management. In this paper, the application of neural networks to study the design of short term load forecasting (STLF) Systems was explored. Our work presents a pragmatic methodology for short term load forecasting (STLF) using proposed two-stage model of wavelet transform (WT) and artificial neural network (ANN). It is a two-stage prediction system which involves wavelet decomposition of input data at the first stage and the decomposed data with another input is trained using a separate neural network to forecast the load. The forecasted load is obtained by reconstruction of the decomposed data. The hybrid model has been trained and validated using load data from Telangana State Electricity Board.

Keywords: electrical distribution systems, wavelet transform (WT), short term load forecasting (STLF), artificial neural network (ANN)

Procedia PDF Downloads 403
7669 Diesel Fault Prediction Based on Optimized Gray Neural Network

Authors: Han Bing, Yin Zhenjie

Abstract:

In order to analyze the status of a diesel engine, as well as conduct fault prediction, a new prediction model based on a gray system is proposed in this paper, which takes advantage of the neural network and the genetic algorithm. The proposed GBPGA prediction model builds on the GM (1.5) model and uses a neural network, which is optimized by a genetic algorithm to construct the error compensator. We verify our proposed model on the diesel faulty simulation data and the experimental results show that GBPGA has the potential to employ fault prediction on diesel.

Keywords: fault prediction, neural network, GM(1, 5) genetic algorithm, GBPGA

Procedia PDF Downloads 277
7668 An Evaluation of Neural Network Efficacies for Image Recognition on Edge-AI Computer Vision Platform

Authors: Jie Zhao, Meng Su

Abstract:

Image recognition, as one of the most critical technologies in computer vision, works to help machine-like robotics understand a scene, that is, if deployed appropriately, will trigger the revolution in remote sensing and industry automation. With the developments of AI technologies, there are many prevailing and sophisticated neural networks as technologies developed for image recognition. However, computer vision platforms as hardware, supporting neural networks for image recognition, as crucial as the neural network technologies, need to be more congruently addressed as the research subjects. In contrast, different computer vision platforms are deterministic to leverage the performance of different neural networks for recognition. In this paper, three different computer vision platforms – Jetson Nano(with 4GB), a standalone laptop(with RTX 3000s, using CUDA), and Google Colab (web-based, using GPU) are explored and four prominent neural network architectures (including AlexNet, VGG(16/19), GoogleNet, and ResNet(18/34/50)), are investigated. In the context of pairwise usage between different computer vision platforms and distinctive neural networks, with the merits of recognition accuracy and time efficiency, the performances are evaluated. In the case study using public imageNets, our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.

Keywords: alexNet, VGG, googleNet, resNet, Jetson nano, CUDA, COCO-NET, cifar10, imageNet large scale visual recognition challenge (ILSVRC), google colab

Procedia PDF Downloads 56
7667 Prediction Fluid Properties of Iranian Oil Field with Using of Radial Based Neural Network

Authors: Abdolreza Memari

Abstract:

In this article in order to estimate the viscosity of crude oil,a numerical method has been used. We use this method to measure the crude oil's viscosity for 3 states: Saturated oil's viscosity, viscosity above the bubble point and viscosity under the saturation pressure. Then the crude oil's viscosity is estimated by using KHAN model and roller ball method. After that using these data that include efficient conditions in measuring viscosity, the estimated viscosity by the presented method, a radial based neural method, is taught. This network is a kind of two layered artificial neural network that its stimulation function of hidden layer is Gaussian function and teaching algorithms are used to teach them. After teaching radial based neural network, results of experimental method and artificial intelligence are compared all together. Teaching this network, we are able to estimate crude oil's viscosity without using KHAN model and experimental conditions and under any other condition with acceptable accuracy. Results show that radial neural network has high capability of estimating crude oil saving in time and cost is another advantage of this investigation.

Keywords: viscosity, Iranian crude oil, radial based, neural network, roller ball method, KHAN model

Procedia PDF Downloads 469
7666 Data Mining of Students' Performance Using Artificial Neural Network: Turkish Students as a Case Study

Authors: Samuel Nii Tackie, Oyebade K. Oyedotun, Ebenezer O. Olaniyi, Adnan Khashman

Abstract:

Artificial neural networks have been used in different fields of artificial intelligence, and more specifically in machine learning. Although, other machine learning options are feasible in most situations, but the ease with which neural networks lend themselves to different problems which include pattern recognition, image compression, classification, computer vision, regression etc. has earned it a remarkable place in the machine learning field. This research exploits neural networks as a data mining tool in predicting the number of times a student repeats a course, considering some attributes relating to the course itself, the teacher, and the particular student. Neural networks were used in this work to map the relationship between some attributes related to students’ course assessment and the number of times a student will possibly repeat a course before he passes. It is the hope that the possibility to predict students’ performance from such complex relationships can help facilitate the fine-tuning of academic systems and policies implemented in learning environments. To validate the power of neural networks in data mining, Turkish students’ performance database has been used; feedforward and radial basis function networks were trained for this task; and the performances obtained from these networks evaluated in consideration of achieved recognition rates and training time.

Keywords: artificial neural network, data mining, classification, students’ evaluation

Procedia PDF Downloads 576
7665 Intelligent System for Diagnosis Heart Attack Using Neural Network

Authors: Oluwaponmile David Alao

Abstract:

Misdiagnosis has been the major problem in health sector. Heart attack has been one of diseases that have high level of misdiagnosis recorded on the part of physicians. In this paper, an intelligent system has been developed for diagnosis of heart attack in the health sector. Dataset of heart attack obtained from UCI repository has been used. This dataset is made up of thirteen attributes which are very vital in diagnosis of heart disease. The system is developed on the multilayer perceptron trained with back propagation neural network then simulated with feed forward neural network and a recognition rate of 87% was obtained which is a good result for diagnosis of heart attack in medical field.

Keywords: heart attack, artificial neural network, diagnosis, intelligent system

Procedia PDF Downloads 626
7664 Comparison of Artificial Neural Networks and Statistical Classifiers in Olive Sorting Using Near-Infrared Spectroscopy

Authors: İsmail Kavdır, M. Burak Büyükcan, Ferhat Kurtulmuş

Abstract:

Table olive is a valuable product especially in Mediterranean countries. It is usually consumed after some fermentation process. Defects happened naturally or as a result of an impact while olives are still fresh may become more distinct after processing period. Defected olives are not desired both in table olive and olive oil industries as it will affect the final product quality and reduce market prices considerably. Therefore it is critical to sort table olives before processing or even after processing according to their quality and surface defects. However, doing manual sorting has many drawbacks such as high expenses, subjectivity, tediousness and inconsistency. Quality criterions for green olives were accepted as color and free of mechanical defects, wrinkling, surface blemishes and rotting. In this study, it was aimed to classify fresh table olives using different classifiers and NIR spectroscopy readings and also to compare the classifiers. For this purpose, green (Ayvalik variety) olives were classified based on their surface feature properties such as defect-free, with bruised defect and with fly defect using FT-NIR spectroscopy and classification algorithms such as artificial neural networks, ident and cluster. Bruker multi-purpose analyzer (MPA) FT-NIR spectrometer (Bruker Optik, GmbH, Ettlingen Germany) was used for spectral measurements. The spectrometer was equipped with InGaAs detectors (TE-InGaAs internal for reflectance and RT-InGaAs external for transmittance) and a 20-watt high intensity tungsten–halogen NIR light source. Reflectance measurements were performed with a fiber optic probe (type IN 261) which covered the wavelengths between 780–2500 nm, while transmittance measurements were performed between 800 and 1725 nm. Thirty-two scans were acquired for each reflectance spectrum in about 15.32 s while 128 scans were obtained for transmittance in about 62 s. Resolution was 8 cm⁻¹ for both spectral measurement modes. Instrument control was done using OPUS software (Bruker Optik, GmbH, Ettlingen Germany). Classification applications were performed using three classifiers; Backpropagation Neural Networks, ident and cluster classification algorithms. For these classification applications, Neural Network tool box in Matlab, ident and cluster modules in OPUS software were used. Classifications were performed considering different scenarios; two quality conditions at once (good vs bruised, good vs fly defect) and three quality conditions at once (good, bruised and fly defect). Two spectrometer readings were used in classification applications; reflectance and transmittance. Classification results obtained using artificial neural networks algorithm in discriminating good olives from bruised olives, from olives with fly defect and from the olive group including both bruised and fly defected olives with success rates respectively changing between 97 and 99%, 61 and 94% and between 58.67 and 92%. On the other hand, classification results obtained for discriminating good olives from bruised ones and also for discriminating good olives from fly defected olives using the ident method ranged between 75-97.5% and 32.5-57.5%, respectfully; results obtained for the same classification applications using the cluster method ranged between 52.5-97.5% and between 22.5-57.5%.

Keywords: artificial neural networks, statistical classifiers, NIR spectroscopy, reflectance, transmittance

Procedia PDF Downloads 226
7663 Data Augmentation for Automatic Graphical User Interface Generation Based on Generative Adversarial Network

Authors: Xulu Yao, Moi Hoon Yap, Yanlong Zhang

Abstract:

As a branch of artificial neural network, deep learning is widely used in the field of image recognition, but the lack of its dataset leads to imperfect model learning. By analysing the data scale requirements of deep learning and aiming at the application in GUI generation, it is found that the collection of GUI dataset is a time-consuming and labor-consuming project, which is difficult to meet the needs of current deep learning network. To solve this problem, this paper proposes a semi-supervised deep learning model that relies on the original small-scale datasets to produce a large number of reliable data sets. By combining the cyclic neural network with the generated countermeasure network, the cyclic neural network can learn the sequence relationship and characteristics of data, make the generated countermeasure network generate reasonable data, and then expand the Rico dataset. Relying on the network structure, the characteristics of collected data can be well analysed, and a large number of reasonable data can be generated according to these characteristics. After data processing, a reliable dataset for model training can be formed, which alleviates the problem of dataset shortage in deep learning.

Keywords: GUI, deep learning, GAN, data augmentation

Procedia PDF Downloads 154
7662 Exploring Deep Neural Network Compression: An Overview

Authors: Ghorab Sara, Meziani Lila, Rubin Harvey Stuart

Abstract:

The rapid growth of deep learning has led to intricate and resource-intensive deep neural networks widely used in computer vision tasks. However, their complexity results in high computational demands and memory usage, hindering real-time application. To address this, research focuses on model compression techniques. The paper provides an overview of recent advancements in compressing neural networks and categorizes the various methods into four main approaches: network pruning, quantization, network decomposition, and knowledge distillation. This paper aims to provide a comprehensive outline of both the advantages and limitations of each method.

Keywords: model compression, deep neural network, pruning, knowledge distillation, quantization, low-rank decomposition

Procedia PDF Downloads 18
7661 Tumor Detection Using Convolutional Neural Networks (CNN) Based Neural Network

Authors: Vinai K. Singh

Abstract:

In Neural Network-based Learning techniques, there are several models of Convolutional Networks. Whenever the methods are deployed with large datasets, only then can their applicability and appropriateness be determined. Clinical and pathological pictures of lobular carcinoma are thought to exhibit a large number of random formations and textures. Working with such pictures is a difficult problem in machine learning. Focusing on wet laboratories and following the outcomes, numerous studies have been published with fresh commentaries in the investigation. In this research, we provide a framework that can operate effectively on raw photos of various resolutions while easing the issues caused by the existence of patterns and texturing. The suggested approach produces very good findings that may be used to make decisions in the diagnosis of cancer.

Keywords: lobular carcinoma, convolutional neural networks (CNN), deep learning, histopathological imagery scans

Procedia PDF Downloads 109
7660 Finite Element Analysis of RC Frames with Retrofitted Infill Walls

Authors: M. Ömer Timurağaoğlu, Adem Doğangün, Ramazan Livaoğlu

Abstract:

The evaluation of performance of infilled reinforced concrete (RC) frames has been a significant challenge for engineers. The strengthening of infill walls has been an important concern to enhance the behavior of RC infilled frames. The aim of this study is to investigate the behaviour of retrofitted infill walls of RC frames using finite element analysis. For this purpose, a one storey, one bay infilled and strengthened infilled RC frame which have the same geometry and material properties with the frames tested in laboratory are modelled using different analytical approaches. A fibrous material is used to strengthen infill walls and frame. As a consequence, the results of the finite element analysis were evaluated of whether these analytical approaches estimate the behavior or not. To model the infilled and strengthened infilled RC frames, a finite element program ABAQUS is used. Finally, data obtained from the nonlinear finite element analysis is compared with the experimental results.

Keywords: finite element analysis, infilled RC frames, infill wall, strengthening

Procedia PDF Downloads 498
7659 A Study on Finite Element Modelling of Earth Retaining Wall Anchored by Deadman Anchor

Authors: K. S. Chai, S. H. Chan

Abstract:

In this paper, the earth retaining wall anchored by discrete deadman anchor to support excavations in sand is modelled and analysed by finite element analysis. A study is conducted to examine how deadman anchorage system helps in reducing the deflection of earth retaining wall. A simplified numerical model is suggested in order to reduce the simulation duration. A comparison between 3-D and 2-D finite element analyses is illustrated.

Keywords: finite element, earth retaining wall, deadman anchor, sand

Procedia PDF Downloads 447
7658 Max-Entropy Feed-Forward Clustering Neural Network

Authors: Xiaohan Bookman, Xiaoyan Zhu

Abstract:

The outputs of non-linear feed-forward neural network are positive, which could be treated as probability when they are normalized to one. If we take Entropy-Based Principle into consideration, the outputs for each sample could be represented as the distribution of this sample for different clusters. Entropy-Based Principle is the principle with which we could estimate the unknown distribution under some limited conditions. As this paper defines two processes in Feed-Forward Neural Network, our limited condition is the abstracted features of samples which are worked out in the abstraction process. And the final outputs are the probability distribution for different clusters in the clustering process. As Entropy-Based Principle is considered into the feed-forward neural network, a clustering method is born. We have conducted some experiments on six open UCI data sets, comparing with a few baselines and applied purity as the measurement. The results illustrate that our method outperforms all the other baselines that are most popular clustering methods.

Keywords: feed-forward neural network, clustering, max-entropy principle, probabilistic models

Procedia PDF Downloads 413
7657 Application of Neural Petri Net to Electric Control System Fault Diagnosis

Authors: Sadiq J. Abou-Loukh

Abstract:

The present work deals with implementation of Petri nets, which own the perfect ability of modeling, are used to establish a fault diagnosis model. Fault diagnosis of a control system received considerable attention in the last decades. The formalism of representing neural networks based on Petri nets has been presented. Neural Petri Net (NPN) reasoning model is investigated and developed for the fault diagnosis process of electric control system. The proposed NPN has the characteristics of easy establishment and high efficiency, and fault status within the system can be described clearly when compared with traditional testing methods. The proposed system is tested and the simulation results are given. The implementation explains the advantages of using NPN method and can be used as a guide for different online applications.

Keywords: petri net, neural petri net, electric control system, fault diagnosis

Procedia PDF Downloads 444
7656 Neural Correlates of Arabic Digits Naming

Authors: Fernando Ojedo, Alejandro Alvarez, Pedro Macizo

Abstract:

In the present study, we explored electrophysiological correlates of Arabic digits naming to determine semantic processing of numbers. Participants named Arabic digits grouped by category or intermixed with exemplars of other semantic categories while the N400 event-related potential was examined. Around 350-450 ms after the presentation of Arabic digits, brain waves were more positive in anterior regions and more negative in posterior regions when stimuli were grouped by category relative to the mixed condition. Contrary to what was found in other studies, electrophysiological results suggested that the production of numerals involved semantic mediation.

Keywords: Arabic digit naming, event-related potentials, semantic processing, number production

Procedia PDF Downloads 553
7655 Analysing Techniques for Fusing Multimodal Data in Predictive Scenarios Using Convolutional Neural Networks

Authors: Philipp Ruf, Massiwa Chabbi, Christoph Reich, Djaffar Ould-Abdeslam

Abstract:

In recent years, convolutional neural networks (CNN) have demonstrated high performance in image analysis, but oftentimes, there is only structured data available regarding a specific problem. By interpreting structured data as images, CNNs can effectively learn and extract valuable insights from tabular data, leading to improved predictive accuracy and uncovering hidden patterns that may not be apparent in traditional structured data analysis. In applying a single neural network for analyzing multimodal data, e.g., both structured and unstructured information, significant advantages in terms of time complexity and energy efficiency can be achieved. Converting structured data into images and merging them with existing visual material offers a promising solution for applying CNN in multimodal datasets, as they often occur in a medical context. By employing suitable preprocessing techniques, structured data is transformed into image representations, where the respective features are expressed as different formations of colors and shapes. In an additional step, these representations are fused with existing images to incorporate both types of information. This final image is finally analyzed using a CNN.

Keywords: CNN, image processing, tabular data, mixed dataset, data transformation, multimodal fusion

Procedia PDF Downloads 91
7654 Two Day Ahead Short Term Load Forecasting Neural Network Based

Authors: Firas M. Tuaimah

Abstract:

This paper presents an Artificial Neural Network based approach for short-term load forecasting and exactly for two days ahead. Two seasons have been discussed for Iraqi power system, namely summer and winter; the hourly load demand is the most important input variables for ANN based load forecasting. The recorded daily load profile with a lead time of 1-48 hours for July and December of the year 2012 was obtained from the operation and control center that belongs to the Ministry of Iraqi electricity. The results of the comparison show that the neural network gives a good prediction for the load forecasting and for two days ahead.

Keywords: short-term load forecasting, artificial neural networks, back propagation learning, hourly load demand

Procedia PDF Downloads 432
7653 Alphabet Recognition Using Pixel Probability Distribution

Authors: Vaidehi Murarka, Sneha Mehta, Dishant Upadhyay

Abstract:

Our project topic is “Alphabet Recognition using pixel probability distribution”. The project uses techniques of Image Processing and Machine Learning in Computer Vision. Alphabet recognition is the mechanical or electronic translation of scanned images of handwritten, typewritten or printed text into machine-encoded text. It is widely used to convert books and documents into electronic files etc. Alphabet Recognition based OCR application is sometimes used in signature recognition which is used in bank and other high security buildings. One of the popular mobile applications includes reading a visiting card and directly storing it to the contacts. OCR's are known to be used in radar systems for reading speeders license plates and lots of other things. The implementation of our project has been done using Visual Studio and Open CV (Open Source Computer Vision). Our algorithm is based on Neural Networks (machine learning). The project was implemented in three modules: (1) Training: This module aims “Database Generation”. Database was generated using two methods: (a) Run-time generation included database generation at compilation time using inbuilt fonts of OpenCV library. Human intervention is not necessary for generating this database. (b) Contour–detection: ‘jpeg’ template containing different fonts of an alphabet is converted to the weighted matrix using specialized functions (contour detection and blob detection) of OpenCV. The main advantage of this type of database generation is that the algorithm becomes self-learning and the final database requires little memory to be stored (119kb precisely). (2) Preprocessing: Input image is pre-processed using image processing concepts such as adaptive thresholding, binarizing, dilating etc. and is made ready for segmentation. “Segmentation” includes extraction of lines, words, and letters from the processed text image. (3) Testing and prediction: The extracted letters are classified and predicted using the neural networks algorithm. The algorithm recognizes an alphabet based on certain mathematical parameters calculated using the database and weight matrix of the segmented image.

Keywords: contour-detection, neural networks, pre-processing, recognition coefficient, runtime-template generation, segmentation, weight matrix

Procedia PDF Downloads 363
7652 A Comparison between Artificial Neural Network Prediction Models for Coronal Hole Related High Speed Streams

Authors: Rehab Abdulmajed, Amr Hamada, Ahmed Elsaid, Hisashi Hayakawa, Ayman Mahrous

Abstract:

Solar emissions have a high impact on the Earth’s magnetic field, and the prediction of solar events is of high interest. Various techniques have been used in the prediction of solar wind using mathematical models, MHD models, and neural network (NN) models. This study investigates the coronal hole (CH) derived high-speed streams (HSSs) and their correlation to the CH area and create a neural network model to predict the HSSs. Two different algorithms were used to compare different models to find a model that best simulates the HSSs. A dataset of CH synoptic maps through Carrington rotations 1601 to 2185 along with Omni-data set solar wind speed averaged over the Carrington rotations is used, which covers Solar cycles (sc) 21, 22, 23, and most of 24.

Keywords: artificial neural network, coronal hole area, feed-forward neural network models, solar high speed streams

Procedia PDF Downloads 62
7651 Electrocardiogram-Based Heartbeat Classification Using Convolutional Neural Networks

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 93
7650 Thermo-Mechanical Analysis of Composite Structures Utilizing a Beam Finite Element Based on Global-Local Superposition

Authors: Andre S. de Lima, Alfredo R. de Faria, Jose J. R. Faria

Abstract:

Accurate prediction of thermal stresses is particularly important for laminated composite structures, as large temperature changes may occur during fabrication and field application. The normal transverse deformation plays an important role in the prediction of such stresses, especially for problems involving thick laminated plates subjected to uniform temperature loads. Bearing this in mind, the present study aims to investigate the thermo-mechanical behavior of laminated composite structures using a new beam element based on global-local superposition, accounting for through-the-thickness effects. The element formulation is based on a global-local superposition in the thickness direction, utilizing a cubic global displacement field in combination with a linear layerwise local displacement distribution, which assures zig-zag behavior of the stresses and displacements. By enforcing interlaminar stress (normal and shear) and displacement continuity, as well as free conditions at the upper and lower surfaces, the number of degrees of freedom in the model is maintained independently of the number of layers. Moreover, the proposed formulation allows for the determination of transverse shear and normal stresses directly from the constitutive equations, without the need of post-processing. Numerical results obtained with the beam element were compared to analytical solutions, as well as results obtained with commercial finite elements, rendering satisfactory results for a range of length-to-thickness ratios. The results confirm the need for an element with through-the-thickness capabilities and indicate that the present formulation is a promising alternative to such analysis.

Keywords: composite beam element, global-local superposition, laminated composite structures, thermal stresses

Procedia PDF Downloads 135
7649 Empirical Evaluation of Gradient-Based Training Algorithms for Ordinary Differential Equation Networks

Authors: Martin K. Steiger, Lukas Heisler, Hans-Georg Brachtendorf

Abstract:

Deep neural networks and their variants form the backbone of many AI applications. Based on the so-called residual networks, a continuous formulation of such models as ordinary differential equations (ODEs) has proven advantageous since different techniques may be applied that significantly increase the learning speed and enable controlled trade-offs with the resulting error at the same time. For the evaluation of such models, high-performance numerical differential equation solvers are used, which also provide the gradients required for training. However, whether classical gradient-based methods are even applicable or which one yields the best results has not been discussed yet. This paper aims to redeem this situation by providing empirical results for different applications.

Keywords: deep neural networks, gradient-based learning, image processing, ordinary differential equation networks

Procedia PDF Downloads 132
7648 A Neural Network Approach to Understanding Turbulent Jet Formations

Authors: Nurul Bin Ibrahim

Abstract:

Advancements in neural networks have offered valuable insights into Fluid Dynamics, notably in addressing turbulence-related challenges. In this research, we introduce multiple applications of models of neural networks, namely Feed-Forward and Recurrent Neural Networks, to explore the relationship between jet formations and stratified turbulence within stochastically excited Boussinesq systems. Using machine learning tools like TensorFlow and PyTorch, the study has created models that effectively mimic and show the underlying features of the complex patterns of jet formation and stratified turbulence. These models do more than just help us understand these patterns; they also offer a faster way to solve problems in stochastic systems, improving upon traditional numerical techniques to solve stochastic differential equations such as the Euler-Maruyama method. In addition, the research includes a thorough comparison with the Statistical State Dynamics (SSD) approach, which is a well-established method for studying chaotic systems. This comparison helps evaluate how well neural networks can help us understand the complex relationship between jet formations and stratified turbulence. The results of this study underscore the potential of neural networks in computational physics and fluid dynamics, opening up new possibilities for more efficient and accurate simulations in these fields.

Keywords: neural networks, machine learning, computational fluid dynamics, stochastic systems, simulation, stratified turbulence

Procedia PDF Downloads 47
7647 EMI Radiation Prediction and Final Measurement Process Optimization by Neural Network

Authors: Hussam Elias, Ninovic Perez, Holger Hirsch

Abstract:

The completion of the EMC regulations worldwide is growing steadily as the usage of electronics in our daily lives is increasing more than ever. In this paper, we introduce a novel method to perform the final phase of Electromagnetic compatibility (EMC) measurement and to reduce the required test time according to the norm EN 55032 by using a developed tool and the conventional neural network(CNN). The neural network was trained using real EMC measurements, which were performed in the Semi Anechoic Chamber (SAC) by CETECOM GmbH in Essen, Germany. To implement our proposed method, we wrote software to perform the radiated electromagnetic interference (EMI) measurements and use the CNN to predict and determine the position of the turntable that meets the maximum radiation value.

Keywords: conventional neural network, electromagnetic compatibility measurement, mean absolute error, position error

Procedia PDF Downloads 173
7646 Low Light Image Enhancement with Multi-Stage Interconnected Autoencoders Integration in Pix to Pix GAN

Authors: Muhammad Atif, Cang Yan

Abstract:

The enhancement of low-light images is a significant area of study aimed at enhancing the quality of captured images in challenging lighting environments. Recently, methods based on convolutional neural networks (CNN) have gained prominence as they offer state-of-the-art performance. However, many approaches based on CNN rely on increasing the size and complexity of the neural network. In this study, we propose an alternative method for improving low-light images using an autoencoder-based multiscale knowledge transfer model. Our method leverages the power of three autoencoders, where the encoders of the first two autoencoders are directly connected to the decoder of the third autoencoder. Additionally, the decoder of the first two autoencoders is connected to the encoder of the third autoencoder. This architecture enables effective knowledge transfer, allowing the third autoencoder to learn and benefit from the enhanced knowledge extracted by the first two autoencoders. We further integrate the proposed model into the PIX to PIX GAN framework. By integrating our proposed model as the generator in the GAN framework, we aim to produce enhanced images that not only exhibit improved visual quality but also possess a more authentic and realistic appearance. These experimental results, both qualitative and quantitative, show that our method is better than the state-of-the-art methodologies.

Keywords: low light image enhancement, deep learning, convolutional neural network, image processing

Procedia PDF Downloads 38
7645 Parallel Vector Processing Using Multi Level Orbital DATA

Authors: Nagi Mekhiel

Abstract:

Many applications use vector operations by applying single instruction to multiple data that map to different locations in conventional memory. Transferring data from memory is limited by access latency and bandwidth affecting the performance gain of vector processing. We present a memory system that makes all of its content available to processors in time so that processors need not to access the memory, we force each location to be available to all processors at a specific time. The data move in different orbits to become available to other processors in higher orbits at different time. We use this memory to apply parallel vector operations to data streams at first orbit level. Data processed in the first level move to upper orbit one data element at a time, allowing a processor in that orbit to apply another vector operation to deal with serial code limitations inherited in all parallel applications and interleaved it with lower level vector operations.

Keywords: Memory Organization, Parallel Processors, Serial Code, Vector Processing

Procedia PDF Downloads 244
7644 Adversarial Attacks and Defenses on Deep Neural Networks

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 163
7643 Neural Reshaping: The Plasticity of Human Brain and Artificial Intelligence in the Learning Process

Authors: Seyed-Ali Sadegh-Zadeh, Mahboobe Bahrami, Sahar Ahmadi, Seyed-Yaser Mousavi, Hamed Atashbar, Amir M. Hajiyavand

Abstract:

This paper presents an investigation into the concept of neural reshaping, which is crucial for achieving strong artificial intelligence through the development of AI algorithms with very high plasticity. By examining the plasticity of both human and artificial neural networks, the study uncovers groundbreaking insights into how these systems adapt to new experiences and situations, ultimately highlighting the potential for creating advanced AI systems that closely mimic human intelligence. The uniqueness of this paper lies in its comprehensive analysis of the neural reshaping process in both human and artificial intelligence systems. This comparative approach enables a deeper understanding of the fundamental principles of neural plasticity, thus shedding light on the limitations and untapped potential of both human and AI learning capabilities. By emphasizing the importance of neural reshaping in the quest for strong AI, the study underscores the need for developing AI algorithms with exceptional adaptability and plasticity. The paper's findings have significant implications for the future of AI research and development. By identifying the core principles of neural reshaping, this research can guide the design of next-generation AI technologies that can enhance human and artificial intelligence alike. These advancements will be instrumental in creating a new era of AI systems with unparalleled capabilities, paving the way for improved decision-making, problem-solving, and overall cognitive performance. In conclusion, this paper makes a substantial contribution by investigating the concept of neural reshaping and its importance for achieving strong AI. Through its in-depth exploration of neural plasticity in both human and artificial neural networks, the study unveils vital insights that can inform the development of innovative AI technologies with high adaptability and potential for enhancing human and AI capabilities alike.

Keywords: neural plasticity, brain adaptation, artificial intelligence, learning, cognitive reshaping

Procedia PDF Downloads 21