Academic literature on the topic 'Multilayer perceptron (MLP) neural network'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Multilayer perceptron (MLP) neural network.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Multilayer perceptron (MLP) neural network"
1
Akbar Maulana and Enny Itje Sela. "The Implementation of Artificial Neural Networks for Stock Price Prediction." Journal of Engineering, Electrical and Informatics 3, no. 3 (2023): 34–44. http://dx.doi.org/10.55606/jeei.v3i3.2254.
Full textAbstract:
This research is based on a problem that is difficult to predict stock prices, especially for beginners. Stock prices are hard to predict because they are fluctuating. Users will be easier to predict stock prices through artificial neural networks using Multilayer Perceptron. This MLP is a variant of an artificial neural network and is a development of perceptron. The selection of the Multilayer Perceptron method is based on the ability to solve various problems both classification and regression. The research conducted by the author is a regression problem as the MLP is tasked to predict the close price or closing price of stock after seven days. The results of the model built are able to predict stock prices and produce good accuracy because the resulting RMSE value produced 0.042649862994352014, which is close to 0.
 
 Keywords: Machine Learning, Stock Price Prediction, Neural Network, Multilayer Perceptron, MLP.
2
LERNER, B., H. GUTERMAN, I. DINSTEIN, and Y. ROMEM. "HUMAN CHROMOSOME CLASSIFICATION USING MULTILAYER PERCEPTRON NEURAL NETWORK." International Journal of Neural Systems 06, no. 03 (1995): 359–70. http://dx.doi.org/10.1142/s012906579500024x.
Full textAbstract:
A multilayer perceptron (MLP) neural network (NN) has been studied for human chromosome classification. Only 10–20 examples were required for the MLP NN to reach its ultimate performance classifying chromosomes of 5 types. The empirical dependence of the entropic error on the number of examples was found to be highly comparable to the 1/t function. The principal component analysis (PCA) was used, both for network initialization and for feature reduction purposes. The PCA demonstrated the importance of retaining most of the image information whenever small training sets are used. The MLP NN classifier outperformed the Bayes piecewise classifier for all the cases tested. The MLP classifier was found to be almost unsusceptible to the ratio of the number of training vectors to the number of features, whereas the piecewise classifier was highly dependent on this ratio.
3
Verma, Pratibha, Vineet Kumar Awasthi, and Sanat Kumar Sahu. "Classification of Coronary Artery Disease Using Multilayer Perceptron Neural Network." International Journal of Applied Evolutionary Computation 12, no. 3 (2021): 35–43. http://dx.doi.org/10.4018/ijaec.2021070103.
Full textAbstract:
Coronary artery disease (CAD) has been the leading cause of death worldwide over the past 10 years. Researchers have been using several data mining techniques to help healthcare professionals diagnose heart disease. The neural network (NN) can provide an excellent solution to identify and classify different diseases. The artificial neural network (ANN) methods play an essential role in recognizes diseases in the CAD. The authors proposed multilayer perceptron neural network (MLPNN) among one hidden layer neuron (MLP) and four hidden layers neurons (P-MLP)-based highly accurate artificial neural network (ANN) method for the classification of the CAD dataset. Therefore, the ten-fold cross-validation (T-FCV) method, P-MLP algorithms, and base classifiers of MLP were employed. The P-MLP algorithm yielded very high accuracy (86.47% in CAD-56 and 98.35% in CAD-59 datasets) and F1-Score (90.36% in CAD-56 and 98.83% in CAD-59 datasets) rates, which have not been reported simultaneously in the MLP.
4
Kaur, Jatinder, Dr Mandeep Singh, Pardeep Singh Bains, and Gagandeep Singh. "Analysis of Multi layer Perceptron Network." INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY 7, no. 2 (2013): 600–606. http://dx.doi.org/10.24297/ijct.v7i2.3462.
Full textAbstract:
In this paper, we introduce the multilayer Perceptron (feedforward) neural network (MLPs) and used it for a function approximation. For the training of MLP, we have used back propagation algorithm principle. The main purpose of this paper lies in changing the number of hidden layers of MLP for achieving minimum value of mean square error.
5
Lazri, Mourad, Fethi Ouallouche, Karim Labadi, and Soltane Ameur. "Extreme Learning Machine versus Multilayer perceptron for rainfall estimation from MSG Data." E3S Web of Conferences 353 (2022): 01006. http://dx.doi.org/10.1051/e3sconf/202235301006.
Full textAbstract:
The application of artificial neural networks (ANN) in several fields has shown considerable success for classification or regression. Learning algorithms such as artificial neural networks must constantly readjust during the learning phase. This requires a relatively long learning time compared to the size and dimension of the data used. Contrary to these considerations, a new neural network, such as Extreme Learning Machine (ELM) has recently been implemented. The ELM does not care much about the size of the neural network, the hidden layer parameters are randomly generated and remain constant instead of being adjusted during training. In this paper, we will present a comparison between two neural networks, namely ELM and MLP (Multilayer perceptron) implemented for the precipitation estimation from meteorological satellite data. The architecture chosen for the two neural networks consists of an input layer (7 neurons), a hidden layer (8 neurons) and an output layer (7 neurons). The MLP has undergone standard training as soon as the ELM is trained according to the characteristics mentioned above. The results show that MLP prevails over ELM. However, the time cost during learning is too high for MLP compared to ELM.
6
Li, Deying, Faming Huang, Liangxuan Yan, Zhongshan Cao, Jiawu Chen, and Zhou Ye. "Landslide Susceptibility Prediction Using Particle-Swarm-Optimized Multilayer Perceptron: Comparisons with Multilayer-Perceptron-Only, BP Neural Network, and Information Value Models." Applied Sciences 9, no. 18 (2019): 3664. http://dx.doi.org/10.3390/app9183664.
Full textAbstract:
Landslides are one type of serious geological hazard which cause immense losses of local life and property. Landslide susceptibility prediction (LSP) can be used to determine the spatial probability of landslide occurrence in a certain area. It is important to implement LSP for landslide hazard prevention and reduction. This study developed a particle-swarm-optimized multilayer perceptron (PSO-MLP) model for LSP implementation to overcome the drawbacks of the conventional gradient descent algorithm and to determine the optimal structural parameters of MLP. Shicheng County in Jiangxi Province of China was used as the study area. In total, 369 landslides, randomly selected non-landslides, and 14 landslide-related predisposing factors were used to train and test the present PSO-MLP model and three other comparative models (an MLP-only model with the gradient descent algorithm, a back-propagation neural network (BPNN), and an information value (IV) model). The results showed that the PSO-MLP model had the most accurate prediction performance (area under the receiver operating characteristic curve (AUC) of 0.822 and frequency ratio (FR) accuracy of 0.856) compared with the MLP-only (0.791 and 0.829), BPNN (0.800 and 0.840), and IV (0.788 and 0.824) models. It can be concluded that the proposed PSO-MLP model addresses the drawbacks of the MLP-only model well and performs better than conventional artificial neural networks (ANNs) and statistical models. The spatial probability distribution law of landslide occurrence in Shicheng County was well revealed by the landslide susceptibility map produced using the PSO-MLP model. Furthermore, the present PSO-MLP model may have higher prediction and classification performances in some other fields compared with conventional ANNs and statistical models.
7
Lorençone, João Antonio, Pedro Antonio Lorençone, Lucas Eduardo Oliveira Aparecido, Guilherme Botega Torsoni, and Lucas da Rocha Ferreira. "NEURAL NETWORKS IN SIMULATING POTENTIAL CLIMATIC CONDITIONS FOR BAMBOO CULTIVATION IN BRAZIL." Revista Contemporânea 3, no. 10 (2023): 17822–31. http://dx.doi.org/10.56083/rcv3n10-064.
Full textAbstract:
This study aimed to perform the agricultural zoning of climatic risk for bamboo in Brazil by means of artificial neural networks. It was used climatic data of air temperature (TAIR, ºC) and rainfall (P). The Feed Forward Artificial Neural Network, Multilayer Perceptron (MLP) with backpropagation learning algorithm for multilayers was employed. The agroclimatic zoning allowed the classification of regions by climatic suitability and showed that 71% of the national territory was suitable for bamboo cultivation. The use of the neural network allowed an accurate and fast classification of climate suitability.
8
Emedolu, Blessing Obianuju, Godwin Thomas, and Nentawe Y. Gurumdimma. "Phishing Website Detection using Multilayer Perceptron." International Journal of Research and Innovation in Applied Science VIII, no. VII (2023): 260–67. http://dx.doi.org/10.51584/ijrias.2023.8730.
Full textAbstract:
Phishing attacks pose a significant threat in the cyber world, exploiting unsuspecting users through deceptive emails that lead them to malicious websites. To combat this challenge, various deep learning based anti-phishing techniques have been developed. However, these models often suffer from high false positive rates or lower accuracy. In this study, we evaluate the performance of two neural networks, the Autoencoder and Multilayer Perceptron (MLP), using a publicly available dataset to build an efficient phishing detection model. Feature selection was performed through correlation analysis, and the Autoencoder achieved an accuracy of 94.17%, while the MLP achieved 96%. We used hyperparameters for optimization using the Gridsearch CV, resulting in a False Positive Rate (FPR) of 1.3%, outperforming the Autoencoder’s 4.1% FPR. The MLP model was further deployed to determine the legitimacy of websites based on input URLs, demonstrating its usability in real-world scenarios. This research contributes to the development of effective phishing detection models, emphasizing the importance of optimizing neural network architecture for improved accuracy and reduced false positives
9
Li, Yong, Qidan Zhu, and Ahsan Elahi. "Quadcopter Trajectory Tracking Based on Model Predictive Path Integral Control and Neural Network." Drones 9, no. 1 (2024): 9. https://doi.org/10.3390/drones9010009.
Full textAbstract:
This paper aims to address the trajectory tracking problem of quadrotors under complex dynamic environments and significant fluctuations in system states. An adaptive trajectory tracking control method is proposed based on an improved Model Predictive Path Integral (MPPI) controller and a Multilayer Perceptron (MLP) neural network. The technique enhances control accuracy and robustness by adjusting control inputs in real time. The Multilayer Perceptron neural network can learn the dynamics of a quadrotor by its state parameter and then the Multilayer Perceptron sends the model to the Model Predictive Path Integral controller. The Model Predictive Path Integral controller uses the model to control the quadcopter following the desired trajectory. Experimental data show that the improved Model Predictive Path Integral–Multilayer Perceptron method reduces the trajectory tracking error by 10.3%, 9.8%, and 5.7% compared to the traditional Model Predictive Path Integral, MPC with MLP, and a two-layer network, respectively. These results demonstrate the potential application of the method in complex environments.
10
Ismail, M. H., T. R. Razak, R. A. J. M. Gining, S. S. M. Fauzi, and A. Abdul-Aziz. "Predicting vehicle parking space availability using multilayer perceptron neural network." IOP Conference Series: Materials Science and Engineering 1176, no. 1 (2021): 012035. http://dx.doi.org/10.1088/1757-899x/1176/1/012035.
Full textAbstract:
Abstract In this study, we have investigated potential use of Multilayer Perceptron (MLP) to predict parking space availability for use within Field Programmable Gate Array (FPGA) accelerated embedded devices. While previous studies have explored the use of MLP for classification problem in FPGA, very little studies concentrated on the potential use of MLP in regression problem, especially in parking space forecasting. Therefore we formulated five Multi-Layer Perceptron (MLP) models with varying hidden units to perform single-step prediction to forecast parking space availability within the next 15 minutes based on the previous one-hour parking occupancy. The proposed models were trained on the historical data of Kuala Lumpur Convention Center dataset and evaluated against baseline ARIMA models. The results have shown that our proposed MLP model performed relatively well against baseline model with the root mean square error between (RMSE) 78.25 to 78.41 and mean absolute error (MAE) between 37.02 to 39.17.
Dissertations / Theses on the topic "Multilayer perceptron (MLP) neural network"
1
Steinholtz, Tim. "Skip connection in a MLP network for Parkinson’s classification." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-303130.
Full textAbstract:
In this thesis, two different architecture designs of a Multi-Layer Perceptron network have been implemented. One architecture being an ordinary MLP, and in the other adding DenseNet inspired skip connections to an MLP architecture. The models were used and evaluated on the classification task, where the goal was to classify if subjects were diagnosed with Parkinson’s disease or not based on vocal features. The models were trained on an openly available dataset for Parkinson’s classification and evaluated on a hold-out set from this dataset and on two datasets recorded in another sound recording environment than the training data. The thesis searched for the answer to two questions; How insensitive models for Parkinson’s classification are to the sound recording environment and how the proposed skip connections in an MLP model could help improve performance and generalization capacity. The thesis results show that the sound environment affects the accuracy. Nevertheless, it concludes that one would be able to overcome this with more time and allow for good accuracy when models are exposed to data from a new sound environment than the training data. As for the question, if the skip connections improve accuracy and generalization, the thesis cannot draw any broad conclusions due to the data that were used. The models had, in general, the best performance with shallow networks, and it is with deeper networks that the skip connections are argued to help improve these attributes. However, when evaluating on the data from a different sound recording environment than the training data, the skip connections had the best performance in two out of three tests.<br>I denna avhandling har två olika arkitektur designer för ett artificiellt flerskikts neuralt nätverk implementerats. En arkitektur som följer konventionen för ett vanlig MLP nätverk, samt en ny arkitektur som introducerar DenseNet inspirerade genvägs kopplingar i MLP nätverk. Modellerna användes och utvärderades för klassificering, vars mål var att urskilja försökspersoner som friska eller diagnostiserade med Parkinsons sjukdom baserat på röst attribut. Modellerna tränades på ett öppet tillgänglig dataset för Parkinsons klassificering och utvärderades på en delmängd av denna data som inte hade använts för träningen, samt två dataset som kommer från en annan ljudinspelnings miljö än datan för träningen. Avhandlingen sökte efter svaret på två frågor; Hur okänsliga modeller för Parkinsons klassificering är för ljudinspelnings miljön och hur de föreslagna genvägs kopplingarna i en MLP-modell kan bidra till att förbättra prestanda och generalisering kapacitet. Resultaten av avhandlingen visar att ljudmiljön påverkar noggrannheten, men drar slutsatsen att med mer tid skulle man troligen kunna övervinna detta och möjliggöra god noggrannhet i nya ljudmiljöer. När det kommer till om genvägs kopplingarna förbättrar noggrannhet och generalisering, är avhandlingen inte i stånd att dra några breda slutsatser på grund av den data som användes. Modellerna hade generellt bästa prestanda med grunda nätverk, och det är i djupare nätverk som genvägs kopplingarna argumenteras för att förbättra dessa egenskaper. Med det sagt, om man bara kollade på resultaten på datan som är ifrån en annan ljudinspelnings miljö så hade genvägs arkitekturen bättre resultat i två av de tre testerna som utfördes.
2
Gaspar, Thiago Lombardi. "Reconhecimento de faces humanas usando redes neurais MLP." Universidade de São Paulo, 2006. http://www.teses.usp.br/teses/disponiveis/18/18133/tde-27042006-231620/.
Full textAbstract:
O objetivo deste trabalho foi desenvolver um algoritmo baseado em redes neurais para o reconhecimento facial. O algoritmo contém dois módulos principais, um módulo para a extração de características e um módulo para o reconhecimento facial, sendo aplicado sobre imagens digitais nas quais a face foi previamente detectada. O método utilizado para a extração de características baseia-se na aplicação de assinaturas horizontais e verticais para localizar os componentes faciais (olhos e nariz) e definir a posição desses componentes. Como entrada foram utilizadas imagens faciais de três bancos distintos: PICS, ESSEX e AT&T. Para esse módulo, a média de acerto foi de 86.6%, para os três bancos de dados. No módulo de reconhecimento foi utilizada a arquitetura perceptron multicamadas (MLP), e para o treinamento dessa rede foi utilizado o algoritmo de aprendizagem backpropagation. As características faciais extraídas foram aplicadas nas entradas dessa rede neural, que realizou o reconhecimento da face. A rede conseguiu reconhecer 97% das imagens que foram identificadas como pertencendo ao banco de dados utilizado. Apesar dos resultados satisfatórios obtidos, constatou-se que essa rede não consegue separar adequadamente características faciais com valores muito próximos, e portanto, não é a rede mais eficiente para o reconhecimento facial<br>This research presents a facial recognition algorithm based in neural networks. The algorithm contains two main modules: one for feature extraction and another for face recognition. It was applied in digital images from three database, PICS, ESSEX and AT&T, where the face was previously detected. The method for feature extraction was based on previously knowledge of the facial components location (eyes and nose) and on the application of the horizontal and vertical signature for the identification of these components. The mean result obtained for this module was 86.6% for the three database. For the recognition module it was used the multilayer perceptron architecture (MLP), and for training this network it was used the backpropagation algorithm. The extracted facial features were applied to the input of the neural network, that identified the face as belonging or not to the database with 97% of hit ratio. Despite the good results obtained it was verified that the MLP could not distinguish facial features with very close values. Therefore the MLP is not the most efficient network for this task
3
Ferro, Luciano [UNESP]. "Aplicação da rede neural MLP (Multilayer Perceptron) em indústria de pisos e revestimentos do Pólo Cerâmico de Santa Gertrudes - SP." Universidade Estadual Paulista (UNESP), 2013. http://hdl.handle.net/11449/102925.
Full textAbstract:
Made available in DSpace on 2014-06-11T19:32:18Z (GMT). No. of bitstreams: 0
Previous issue date: 2013-04-25Bitstream added on 2014-06-13T19:21:52Z : No. of bitstreams: 1
ferro_l_dr_rcla.pdf: 507040 bytes, checksum: 8569d113b387622fd192e005a1bbf02b (MD5)<br>As Redes Neurais Artificiais se constituem numa alternativa à computação programada tradicional e foram aplicadas em quase todos os ramos do conhecimento humano. Em Geotecnologia, no entanto, ainda são escassas as aplicações de maneira que, com este trabalho, procura-se mostrar que elas também podem ser aplicadas em indústrias de pisos e revestimentos cerâmicos do Pólo Cerâmico de Santa Gertrudes, Estado de São Paulo. Para isso, foram utilizados corpos-de-prova elaborados, testados e analisados nas indústrias Triunfo Cerâmica e Rochaforte Cerâmica, com argilas oriundas de nove minas da região que constitui o Pólo Cerâmico de Santa Gertrudes, dentre aquelas que representavam toda a coluna estratigráfica da Formação Corumbataí com amostras bem diferenciadas. Os dados obtidos relativos às variáveis físicas foram gentilmente cedidos pelo proprietário das indústrias acima citadas e as variáveis físicas usadas neste estudo são a Densidade de Prensagem (DP), a Densidade Aparente de Corpos-de-Prova Secos (DAS), a Retração Linear de Secagem (RLS), a Retração Linear de Queima (RLQ), a Perda ao Fogo (PF), a Carga de Ruptura (CR), a Absorção de Água (Abs) e o Módulo de Resistência à Flexão (MRF). Para a análise, os corpos-de-prova foram submetidos a quatro temperaturas de queima 1000°C, 1020°C, 1040°C e 1060°C, onde cada um destes valores deu origem a uma rede neural MLP (Multilayer Perceptron) de três camadas, para as quais foi usada a Regra do Aprendizado de Retropropagação do Erro (Backpropagation, do original em inglês)<br>Artificial Neural Networks constitute an alternative to traditional programmed computation and have been applied in almost all branches of human knowledge. However, they are rarely applied in Geotechnology, so this work aims to show that they can be applied in the flooring and ceramic tile industries in the Principial Ceramic Region of Saint Gertrudes, São Paulo State. For this purpose, proof specimens elaborated, tested and analyzed in the industries of Triunfo Cerâmica and Rochaforte Cerâmica were used. These proof specimens were composed of well differentiated clays from nine mines in the Principial Ceramic Region of Saint Gertrudes, and these mines are representative of all the stratigraphic column of the Corumbataí Formation. The data relative to physical variables were graciously provided by the owner of the above mentioned industries, and the physical variables used in this study are Pressing Density (DP), Bulk Density of Dry Specimens (DAS), Linear Shrinkage Drying (RLS), Linear Shrinkage Firing (RLQ), Loss on Ignition (PF), Tensile Strength (CR), Water Absorption (Abs) and Flexural Modulus of Resistance (MRF). For analysis, the proof specimens were subjected to four firing temperatures, 1000° C, 1020° C, 1040° C and 1060°C. Each one of these values gave rise to a neural network MLP (Multilayer Perceptron) of three tiers for which the Backpropagation rule of learning was used
4
Ferro, Luciano. "Aplicação da rede neural MLP (Multilayer Perceptron) em indústria de pisos e revestimentos do Pólo Cerâmico de Santa Gertrudes - SP /." Rio Claro, 2013. http://hdl.handle.net/11449/102925.
Full textAbstract:
Orientador: José Ricardo Sturaro<br>Banca: Paulo Milton Barbosa Landim<br>Banca: Ricardo Egydio de Carvalho<br>Banca: Alessandro Firmiano de Jesus<br>Banca: Alexandre Campane Vidal<br>Resumo: As Redes Neurais Artificiais se constituem numa alternativa à computação programada tradicional e foram aplicadas em quase todos os ramos do conhecimento humano. Em Geotecnologia, no entanto, ainda são escassas as aplicações de maneira que, com este trabalho, procura-se mostrar que elas também podem ser aplicadas em indústrias de pisos e revestimentos cerâmicos do Pólo Cerâmico de Santa Gertrudes, Estado de São Paulo. Para isso, foram utilizados corpos-de-prova elaborados, testados e analisados nas indústrias Triunfo Cerâmica e Rochaforte Cerâmica, com argilas oriundas de nove minas da região que constitui o Pólo Cerâmico de Santa Gertrudes, dentre aquelas que representavam toda a coluna estratigráfica da Formação Corumbataí com amostras bem diferenciadas. Os dados obtidos relativos às variáveis físicas foram gentilmente cedidos pelo proprietário das indústrias acima citadas e as variáveis físicas usadas neste estudo são a Densidade de Prensagem (DP), a Densidade Aparente de Corpos-de-Prova Secos (DAS), a Retração Linear de Secagem (RLS), a Retração Linear de Queima (RLQ), a Perda ao Fogo (PF), a Carga de Ruptura (CR), a Absorção de Água (Abs) e o Módulo de Resistência à Flexão (MRF). Para a análise, os corpos-de-prova foram submetidos a quatro temperaturas de queima 1000°C, 1020°C, 1040°C e 1060°C, onde cada um destes valores deu origem a uma rede neural MLP (Multilayer Perceptron) de três camadas, para as quais foi usada a Regra do Aprendizado de Retropropagação do Erro (Backpropagation, do original em inglês)<br>Abstract: Artificial Neural Networks constitute an alternative to traditional programmed computation and have been applied in almost all branches of human knowledge. However, they are rarely applied in Geotechnology, so this work aims to show that they can be applied in the flooring and ceramic tile industries in the Principial Ceramic Region of Saint Gertrudes, São Paulo State. For this purpose, proof specimens elaborated, tested and analyzed in the industries of Triunfo Cerâmica and Rochaforte Cerâmica were used. These proof specimens were composed of well differentiated clays from nine mines in the Principial Ceramic Region of Saint Gertrudes, and these mines are representative of all the stratigraphic column of the Corumbataí Formation. The data relative to physical variables were graciously provided by the owner of the above mentioned industries, and the physical variables used in this study are Pressing Density (DP), Bulk Density of Dry Specimens (DAS), Linear Shrinkage Drying (RLS), Linear Shrinkage Firing (RLQ), Loss on Ignition (PF), Tensile Strength (CR), Water Absorption (Abs) and Flexural Modulus of Resistance (MRF). For analysis, the proof specimens were subjected to four firing temperatures, 1000° C, 1020° C, 1040° C and 1060°C. Each one of these values gave rise to a neural network MLP (Multilayer Perceptron) of three tiers for which the Backpropagation rule of learning was used<br>Doutor
5
Goosen, Johannes Christiaan. "Comparing generalized additive neural networks with multilayer perceptrons / Johannes Christiaan Goosen." Thesis, North-West University, 2011. http://hdl.handle.net/10394/5552.
Full textAbstract:
In this dissertation, generalized additive neural networks (GANNs) and multilayer perceptrons (MLPs) are studied
and compared as prediction techniques. MLPs are the most widely used type of artificial neural network
(ANN), but are considered black boxes with regard to interpretability. There is currently no simple a priori
method to determine the number of hidden neurons in each of the hidden layers of ANNs. Guidelines exist that
are either heuristic or based on simulations that are derived from limited experiments. A modified version of
the neural network construction with cross–validation samples (N2C2S) algorithm is therefore implemented and
utilized to construct good MLP models. This algorithm enables the comparison with GANN models. GANNs
are a relatively new type of ANN, based on the generalized additive model. The architecture of a GANN is less
complex compared to MLPs and results can be interpreted with a graphical method, called the partial residual
plot. A GANN consists of an input layer where each of the input nodes has its own MLP with one hidden layer.
Originally, GANNs were constructed by interpreting partial residual plots. This method is time consuming and
subjective, which may lead to the creation of suboptimal models. Consequently, an automated construction
algorithm for GANNs was created and implemented in the SAS R
statistical language. This system was called
AutoGANN and is used to create good GANN models.
A number of experiments are conducted on five publicly available data sets to gain insight into the similarities
and differences between GANN and MLP models. The data sets include regression and classification tasks.
In–sample model selection with the SBC model selection criterion and out–of–sample model selection with the
average validation error as model selection criterion are performed. The models created are compared in terms
of predictive accuracy, model complexity, comprehensibility, ease of construction and utility.
The results show that the choice of model is highly dependent on the problem, as no single model always
outperforms the other in terms of predictive accuracy. GANNs may be suggested for problems where interpretability
of the results is important. The time taken to construct good MLP models by the modified N2C2S
algorithm may be shorter than the time to build good GANN models by the automated construction algorithm<br>Thesis (M.Sc. (Computer Science))--North-West University, Potchefstroom Campus, 2011.
6
Liberatore, Lorenzo. "Introduction to geometric deep learning and graph neural networks." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2022. http://amslaurea.unibo.it/25339/.
Full textAbstract:
This thesis proposes an introduction to the fundamental concepts of supervised deep learning. Starting from Rosemblatt's Perceptron we will discuss the architectures that, in recent years, have revolutioned the world of deep learning: graph neural networks, which led to the formulation of geometric deep learning. We will then give a simple example of graph neural network, discussing the code that composes it and then test our
architecture on the MNISTSuperpixels dataset, which is a variation of the benchmark dataset MNIST.
7
Gouveia, Wellington da Rocha. "Detecção de faces humanas em imagens coloridas utilizando redes neurais artificiais." Universidade de São Paulo, 2010. http://www.teses.usp.br/teses/disponiveis/18/18152/tde-11032010-160048/.
Full textAbstract:
A tarefa de encontrar faces em imagens é extremamente complexa, pois pode ocorrer variação de luminosidade, fundos extremamente complexos e objetos que podem se sobrepor parcialmente à face que será localizada, entre outros problemas. Com o avanço na área de visão computacional técnicas mais recentes de processamento de imagens e inteligência artificial têm sido combinadas para desenvolver algoritmos mais eficientes para a tarefa de detecção de faces. Este trabalho apresenta uma metodologia de visão computacional que utiliza redes neurais MLP (Perceptron Multicamadas) para segmentar a cor da pele e a textura da face, de outros objetos presentes em uma imagem de fundo complexo. A imagem resultante é dividida em regiões, e para cada região são extraídas características que são aplicadas em outra rede neural MLP para identificar se naquela região contem face ou não. Para avaliação do software implementado foram utilizados dois banco de imagens, um com imagens padronizadas (Banco AR) e outro banco com imagens adquiridas na Internet contendo faces com diferentes tons de pele e fundo complexo. Os resultados finais obtidos foram de 83% de faces detectadas para o banco de imagens da Internet e 88% para o Banco AR, evidenciando melhores resultados para as imagens deste banco, pelo fato de serem padronizadas, não conterem faces inclinadas e fundo complexo. A etapa de segmentação apesar de reduzir a quantidade de informação a ser processada para os demais módulos foi a que contribuiu para o maior número de falsos negativos.<br>The task of finding faces in images is extremely complex, as there is variation in brightness, backgrounds and highly complex objects that may overlap partially in the face to be found, among other problems. With the advancement in the field of computer vision techniques latest image processing and artificial intelligence have been combined to develop more efficient algorithms for the task of face detection. This work presents a methodology for computer vision using neural networks MLP (Multilayer Perceptron) to segment the skin color and texture of the face, from other objects present in a complex background image. The resulting image is divided into regions and from each region are extracted features that are applied in other MLP neural network to identify whether this region contains the face or not. To evaluate the software two sets of images were used, images with a standard database (AR) and another database with images acquired from the Internet, containing faces with different skin tones and complex background. The final results were 83% of faces detected in the internet database of images and 88% for the database AR. These better results for the database AR is due to the fact that they are standardized, are not rotated and do not contain complex background. The segmentation step, despite reducing the amount of information being processed for the other modules contributed to the higher number of false negatives.
8
Ridhagen, Markus, and Petter Lind. "A comparative study of Neural Network Forecasting models on the M4 competition data." Thesis, Uppsala universitet, Statistiska institutionen, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-445568.
Full textAbstract:
The development of machine learning research has provided statistical innovations and further developments within the field of time series analysis. This study seeks to investigate two different approaches on artificial neural network models based on different learning techniques, and answering how well the neural network approach compares with a basic autoregressive approach, as well as how the artificial neural network models compare to each other. The models were compared and analyzed in regards to the univariate forecast accuracy on 20 randomly drawn time series from two different time frequencies from the M4 competition dataset. Forecasting was made dependent on one time lag (t-1) and forecasted three and six steps ahead respectively. The artificial neural network models outperformed the baseline Autoregressive model, showing notably lower mean average percentage error overall. The Multilayered perceptron models performed better than the Long short-term memory model overall, whereas the Long short-term memory model showed improvement on longer prediction time dimensions. As the training were done univariately on a limited set of time steps, it is believed that the one layered-approach gave a good enough approximation on the data, whereas the added layer couldn’t fully utilize its strengths of processing power. Likewise, the Long short-term memory model couldn’t fully demonstrate the advantagements of recurrent learning. Using the same dataset, further studies could be made with another approach to data processing. Implementing an unsupervised approach of clustering the data before analysis, the same models could be tested with multivariate analysis on models trained on multiple time series simultaneously.
9
Gao, Zhenning. "Parallel and Distributed Implementation of A Multilayer Perceptron Neural Network on A Wireless Sensor Network." University of Toledo / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1383764269.
Full text
10
Midhall, Ruben, and Amir Parmbäck. "Utvärdering av Multilayer Perceptron modeller för underlagsdetektering." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-43469.
Full textAbstract:
Antalet enheter som är uppkopplade till internet, Internet of Things (IoT), ökar hela tiden. År 2035 beräknas det finnas 1000 miljarder Internet of Things-enheter. Samtidigt som antalet enheter ökar, ökar belastningen på internet-nätverken som enheterna är uppkopplade till. Internet of Things-enheterna som finns i vår omgivning samlar in data som beskriver den fysiska tillvaron och skickas till molnet för beräkning. För att hantera belastningen på internet-nätverket flyttas beräkningarna på datan till IoT-enheten, istället för att skicka datan till molnet. Detta kallas för edge computing. IoT-enheter är ofta resurssnåla enheter med begränsad beräkningskapacitet. Detta innebär att när man designar exempelvis "machine learning"-modeller som ska köras med edge computing måste algoritmerna anpassas utifrån de resurser som finns tillgängliga på enheten. I det här arbetet har vi utvärderat olika multilayer perceptron-modeller för mikrokontrollers utifrån en rad olika experiment. "Machine learning"-modellerna har varit designade att detektera vägunderlag. Målet har varit att identifiera hur olika parametrar påverkar "machine learning"-systemen. Vi har försökt att maximera prestandan och minimera den mängd fysiskt minne som krävs av modellerna. Vi har även behövt förhålla oss till att mikrokontrollern inte haft tillgång till internet. Modellerna har varit ämnade att köras på en mikrokontroller "on the edge". Datainsamlingen skedde med hjälp av en accelerometer integrerad i en mikrokontroller som monterades på en cykel. I studien utvärderas två olika "machine learning"-system, ett som är en kombination av binära klassificerings modeller och ett multiklass klassificerings system som framtogs i ett tidigare arbete. Huvudfokus i arbetet har varit att träna modeller för klassificering av vägunderlag och sedan utvärdera modellerna. Datainsamlingen gjordes med en mikrokontroller utrustad med en accelerometer monterad på en cykel. Ett av systemen lyckas uppnå en träffsäkerhet på 93,1\% för klassificering av 3 vägunderlag. Arbetet undersöker även hur mycket fysiskt minne som krävs av de olika "machine learning"-systemen. Systemen krävde mellan 1,78kB och 5,71kB i fysiskt minne.<br>The number of devices connected to the internet, the Internet of Things (IoT), is constantly increasing. By 2035, it is estimated to be 1,000 billion Internet of Things devices in the world. At the same time as the number of devices increase, the load on the internet networks to which the devices are connected, increases. The Internet of Things devices in our environment collect data that describes our physical environment and is sent to the cloud for computation. To reduce the load on the internet networks, the calculations are done on the IoT devices themselves instead of in the cloud. This way no data needs to be sent over the internet and is called edge computing. In edge computing, however, other challenges arise. IoT devices are often resource-efficient devices with limited computing capacity. This means that when designing, for example, machine learning models that are to be run with edge computing, the models must be designed based on the resources available on the device. In this work, we have evaluated different multilayer perceptron models for microcontrollers based on a number of different experiments. The machine learning models have been designed to detect road surfaces. The goal has been to identify how different parameters affect the machine learning systems. We have tried to maximize the performance and minimize the memory allocation of the models. The models have been designed to run on a microcontroller on the edge. The data was collected using an accelerometer integrated in a microcontroller mounted on a bicycle. The study evaluates two different machine learning systems that were developed in a previous thesis. The main focus of the work has been to create algorithms for detecting road surfaces. The data collection was done with a microcontroller equipped with an accelerometer mounted on a bicycle. One of the systems succeeds in achieving an accuracy of 93.1\% for the classification of 3 road surfaces. The work also evaluates how much physical memory is required by the various machine learning systems. The systems required between 1.78kB and 5,71kB of physical memory.
Book chapters on the topic "Multilayer perceptron (MLP) neural network"
1
Mohammadazadeh, Ardahir, Mohammad Hosein Sabzalian, Oscar Castillo, Rathinasamy Sakthivel, Fayez F. M. El-Sousy, and Saleh Mobayen. "Multilayer Perceptron (MLP) Neural Networks." In Synthesis Lectures on Intelligent Technologies. Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-14571-1_2.
Full text
2
Westby, Isaac, Hakduran Koc, Jiang Lu, and Xiaokun Yang. "A Design on Multilayer Perceptron (MLP) Neural Network for Digit Recognition." In Transactions on Computational Science and Computational Intelligence. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-70296-0_53.
Full text
3
Westby, Isaac, Hakduran Koc, Jiang Lu, and Xiaokun Yang. "A Design on Multilayer Perceptron (MLP) Neural Network for Digit Recognition." In Transactions on Computational Science and Computational Intelligence. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-70296-0_53.
Full text
4
Clark, Jonathan Y., and Kevin Warwick. "Artificial Keys for Botanical Identification using a Multilayer Perceptron Neural Network (MLP)." In Artificial Intelligence for Biology and Agriculture. Springer Netherlands, 1998. http://dx.doi.org/10.1007/978-94-011-5048-4_5.
Full text
5
Shyamsunder, Metuku, and Kakarla Subba Rao. "Classification of LPI Radar Signals Using Multilayer Perceptron (MLP) Neural Networks." In Lecture Notes in Electrical Engineering. Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-5550-1_23.
Full text
6
Tashan, Tariq, and Tony Allen. "Two stage speaker verification using Self Organising Map and Multilayer Perceptron Neural Network." In Research and Development in Intelligent Systems XXVIII. Springer London, 2011. http://dx.doi.org/10.1007/978-1-4471-2318-7_8.
Full text
7
Hao, Jianbin, Shaohua Tan, and Joos Vandewalle. "A Geometric Approach to the Structural Synthesis of Multilayer Perceptron Neural Networks." In International Neural Network Conference. Springer Netherlands, 1990. http://dx.doi.org/10.1007/978-94-009-0643-3_120.
Full text
8
Shivappriya, S. N., Rajaguru Harikumar, Krishnamoorthi Maheswari, and Ramasamy Dhivya Praba. "Heart Disease Classification Using Multi-Layer Perceptron (MLP) Neural Network." In Sustainable Digital Technologies for Smart Cities. CRC Press, 2023. http://dx.doi.org/10.1201/9781003307716-14.
Full text
9
Woo, Dong-Min, and Dong-Chul Park. "Application of MultiLayer Perceptron Type Neural Network to Camera Calibration." In Advances in Intelligent and Soft Computing. Springer Berlin Heidelberg, 2009. http://dx.doi.org/10.1007/978-3-642-03156-4_15.
Full text
10
Shyamala Devi, M., A. Peter Soosai Anandaraj, K. Venkata Thanooj, P. V. Sandeep Guptha, and A. Jayanth Reddy. "Multilayer Perceptron Neural Network Supervised Learning Based Solar Radiation Prediction." In Lecture Notes in Electrical Engineering. Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-2281-7_58.
Full textConference papers on the topic "Multilayer perceptron (MLP) neural network"
1
Pradhan, Dr Moumita. "PredParkinson-MLP: Parkinson Disease Prediction using Multi Layer Perceptron Neural Network." In 2025 International Conference on Machine Learning and Autonomous Systems (ICMLAS). IEEE, 2025. https://doi.org/10.1109/icmlas64557.2025.10968652.
Full text
2
Solemani, Mohammad R., and Michel Guillot. "Improving the Performance of Process Controllers Using a New Clustered Neural Network." In ASME 2000 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2000. http://dx.doi.org/10.1115/imece2000-2368.
Full textAbstract:
Abstract This paper presents first a newly developed clustered neural network, which incorporates self-organization capacity into the well-known common multilayer perceptron (MLP) architecture. With this addition, it is possible to reduce significantly overall memory degradation of the neuro-controller during on-line training. In the second part of the paper, this clustered multilayer perceptron (CMLP) network is applied and compared to the MLP through modeling and simulations of machining processes. Simulation results presented using machining data demonstrate that the CMLP possesses more powerful modeling capacity than the standard MLP, offers better adaptability to new operating conditions, and finally performs more reliably. During on-line training with machining data about 65% degradation of previously learned information can be observed in the MLP as opposed to only 11% for the CMLP. Finally, an adaptive control scheme intended for on-line optimization of the machining processes is presented. This scheme uses a feedforward CMLP inverse neuro-controller which learns off-line and on-line the relationships between process inputs and output under simulated perturbations (i.e., tool wear and non-homogeneous workpiece material properties). The first results using the CMLP inverse neuro-controller are promising.
3
Ghorbanian, Kaveh, and Mohammad Gholamrezaei. "Axial Compressor Performance Map Prediction Using Artificial Neural Network." In ASME Turbo Expo 2007: Power for Land, Sea, and Air. ASMEDC, 2007. http://dx.doi.org/10.1115/gt2007-27165.
Full textAbstract:
The application of artificial neural network to compressor performance map prediction is investigated. Different types of artificial neural network such as multilayer perceptron network, radial basis function network, general regression neural network, and a rotated general regression neural network proposed by the authors are considered. Two different models are utilized in simulating the performance map. The results indicate that while the rotated general regression neural network has the least mean error and best agreement to the experimental data, it is however limited to curve fitting application. On the other hand, if one considers a tool for curve fitting as well as for interpolation and extrapolation applications, multilayer perceptron network technique is the most powerful candidate. Further, the compressor efficiency based on the multilayer perceptron network technique is determined. Excellent agreement between the predictions and the experimental data is obtained.
4
Harun, N., S. S. Dlay, and W. L. Woo. "Performance of keystroke biometrics authentication system using Multilayer Perceptron neural network (MLP NN)." In 2010 7th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 2010). IEEE, 2010. http://dx.doi.org/10.1109/csndsp16145.2010.5580334.
Full text
5
Aravind, Aditya, Fahad M. Mujawar, Rajat Kumar Sinha, and Kaustav Bhowmick. "Use of Multilayer Perceptron Classifier for Determination of Single Mode Operation in Rib Waveguides." In Frontiers in Optics. Optica Publishing Group, 2023. http://dx.doi.org/10.1364/fio.2023.jm7a.16.
Full textAbstract:
The present work reports the performance of a MLP neural network architecture, classifying single-mode operation for Rib waveguides with varying refractive indices, wavelengths, and geometrical parameters, with an accuracy of ~ 90% and faster computation.
6
Li, De, Honghai Wang, and Zhengying Li. "Accurate and Fast Wavelength Demodulation for Fbg Reflected Spectrum Using Multilayer Perceptron (Mlp) Neural Network." In 2020 12th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA). IEEE, 2020. http://dx.doi.org/10.1109/icmtma50254.2020.00066.
Full text
7
Li, J. W., Y. C. Manie, P. H. Chiu, A. M. Dehnaw, and P. C. Peng. "Optical Comb Generator-based Microwave Photonic Filter Performance Improvement Using Multilayer Perceptron (MLP) Neural Network." In 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW). IEEE, 2021. http://dx.doi.org/10.1109/icce-tw52618.2021.9603173.
Full text
8
Rywik, Marcin, Axel Zimmermann, Alexander J. Eder, Edoardo Scoletta, and Wolfgang Polifke. "Spatially Resolved Modeling of the Nonlinear Dynamics of a Laminar Premixed Flame With a Multilayer Perceptron - Convolution Autoencoder Network." In ASME Turbo Expo 2023: Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2023. http://dx.doi.org/10.1115/gt2023-102543.
Full textAbstract:
Abstract This work presents a multilayer perceptron-convolutional autoencoder (MLP-CAE) neural network model, which accurately predicts the two-dimensional flame field dynamics of an acoustically excited premixed laminar flame. The obtained architecture maps the acoustic perturbation time series to a spatially distributed heat release rate field, capturing the flame lengths and shapes. This extends to previous neural network models, which predicted only the field-integrated value of the heat release rate. The MLP-CAE comprises two sub-models: a fully connected MLP and a CAE. The key idea behind the CAE network is to find a lower dimensional latent space representation of the heat release rate field. The MLP is responsible for modeling the flame dynamics by transforming the acoustic forcing signal into this latent space, enabling the decoder to produce the flow field distributions. To train the MLP-CAE, computational fluid dynamics (CFD) flame simulations with a broadband acoustic forcing were used. Its normalized amplitude was set to 0.5 and 1.0, resulting in a nonlinear flame response. The network was found to accurately predict the perturbed flame shapes — both under broadband and harmonic forcing. Additionally, it conserved the correct frequency response characteristics as verified by the global and local flame describing functions. The MLP-CAE provides a building block towards a potential shift away from a purely ‘0D’ analysis with the assumption of acoustic compactness of the flame. When combined with an acoustic network, the generated flame fields could provide more physical insight in the thermoacoustic dynamics of combustion chambers. Those capabilities do not come at an additional significant computational cost, as even the previous nonspatial flame models had to train on the CFD data, which readily included field distributions.
9
Chen, Shu, Peng Ding, Shuowen Hu, et al. "Optimization of Core Parameters Based on Artificial Neural Network Surrogate Model." In 2022 29th International Conference on Nuclear Engineering. American Society of Mechanical Engineers, 2022. http://dx.doi.org/10.1115/icone29-90511.
Full textAbstract:
Abstract The methodology of artificial intelligence (AI), particularly artificial neural network (ANN), would be in favor of nuclear energy system development. These ANN simulators may provide more efficient means than the traditional nuclear design codes, especially for the design of the key parameters, such as core geometry and layout, material composition. In this paper, a neutronics calculation code SARAX and the corresponding multilayer perceptron (MLP) surrogate model were used as simulators for core parameters optimization of a reference lead based fast reactor. The pellet radius, enrichments and active height are the interested core parameters, and core burnup and power distribution are the target characteristics in the study. The training of structure and weight parameters in MLP network are based on about 5000 calculations of SARAX code. Test results of neural network show a good agreement between MLP surrogate model and SARAX code. The feasibility of the MLP surrogate model to be used in core parameters optimization was also discussed. Results showed that, the core surrogate model based on MLP could be quickly constructed and regulated, and be a more efficient simulators in a innovate reactor optimization. The above work is completed in Sinan Platform, a multidisciplinary intelligent design platform developed by China Nuclear Power Technology Research Institute Co. Ltd.
10
Coelho, Bruno França, and João Viana Fonseca Neto. "Extended Kalman Filter Enhanced by Neural Network to Solve the SLAM Problem." In Congresso Brasileiro de Inteligência Computacional. SBIC, 2021. http://dx.doi.org/10.21528/cbic2021-59.
Full textAbstract:
This work presents a way for online estimation of the location and mapping of a non-holonomic robot by means of an algorithm that uses EKF and in the output of this algorithm, a multilayer perceptron neural network (MLP) has been added that aims to improve the estimation of the robot pose in an unfamiliar environment. The effectiveness was proven through the comparison between the EKF-SLAM and the EKFMLP-SLAM, where it was evidenced a significant improvement in relation to the location of the poses of the robot.
Reports on the topic "Multilayer perceptron (MLP) neural network"
1
Alwan, Iktimal, Dennis D. Spencer, and Rafeed Alkawadri. Comparison of Machine Learning Algorithms in Sensorimotor Functional Mapping. Progress in Neurobiology, 2023. http://dx.doi.org/10.60124/j.pneuro.2023.30.03.
Full textAbstract:
Objective: To compare the performance of popular machine learning algorithms (ML) in mapping the sensorimotor cortex (SM) and identifying the anterior lip of the central sulcus (CS). Methods: We evaluated support vector machines (SVMs), random forest (RF), decision trees (DT), single layer perceptron (SLP), and multilayer perceptron (MLP) against standard logistic regression (LR) to identify the SM cortex employing validated features from six-minute of NREM sleep icEEG data and applying standard common hyperparameters and 10-fold cross-validation. Each algorithm was tested using vetted features based on the statistical significance of classical univariate analysis (p<0.05) and extended () 17 features representing power/coherence of different frequency bands, entropy, and interelectrode-based distance. The analysis was performed before and after weight adjustment for imbalanced data (w). Results: 7 subjects and 376 contacts were included. Before optimization, ML algorithms performed comparably employing conventional features (median CS accuracy: 0.89, IQR [0.88-0.9]). After optimization, neural networks outperformed others in means of accuracy (MLP: 0.86), the area under the curve (AUC) (SLPw, MLPw, MLP: 0.91), recall (SLPw: 0.82, MLPw: 0.81), precision (SLPw: 0.84), and F1-scores (SLPw: 0.82). SVM achieved the best specificity performance. Extending the number of features and adjusting the weights improved recall, precision, and F1-scores by 48.27%, 27.15%, and 39.15%, respectively, with gains or no significant losses in specificity and AUC across CS and Function (correlation r=0.71 between the two clinical scenarios in all performance metrics, p<0.001). Interpretation: Computational passive sensorimotor mapping is feasible and reliable. Feature extension and weight adjustments improve the performance and counterbalance the accuracy paradox. Optimized neural networks outperform other ML algorithms even in binary classification tasks. The best-performing models and the MATLAB® routine employed in signal processing are available to the public at (Link 1).
2
Ramakrishnan, Aravind, Fangyu Liu, Angeli Jayme, and Imad Al-Qadi. Prediction of Pavement Damage under Truck Platoons Utilizing a Combined Finite Element and Artificial Intelligence Model. Illinois Center for Transportation, 2024. https://doi.org/10.36501/0197-9191/24-030.
Full textAbstract:
For robust pavement design, accurate damage computation is essential, especially for loading scenarios such as truck platoons. Studies have developed a framework to compute pavement distresses as function of lateral position, spacing, and market-penetration level of truck platoons. The established framework uses a robust 3D pavement model, along with the AASHTOWare Mechanistic–Empirical Pavement Design Guidelines (MEPDG) transfer functions to compute pavement distresses. However, transfer functions include high variability and lack physical significance. Therefore, as an improvement to effectively predict permanent deformation, this study utilized a conventional Burger’s model, incorporating a nonlinear power-law dashpot, in lieu of a transfer function. Key components, including stress increments and the Jacobian, were derived for implementation in ABAQUS as a user subroutine. Model parameters were determined through asphalt concrete (AC) flow number and dynamic modulus tests. Using a nonlinear power-law dashpot, the model accurately characterized rutting under varying conditions. The Burger’s model was both verified and validated to check the accuracy of implementation and representative of the actual behavior, respectively. Initially developed in 1D domain, the validated Burger’s model was integrated into the robust 3D finite element (FE) pavement model to predict permanent deformation. A new load-pass approach (LPA) enabled reduction in computational domain and cost, along with implementing transient loads more efficiently. The combined integration of the LPA and the Burger’s model into the pavement model effectively captured the rutting progression per loading cycle. Moreover, a graph neural network (GNN) was established to extend the prediction power of the framework, while strategically limiting the FE numerical matrix. The FE model data was transformed into a graph structure, converting FE model components into corresponding graph nodes and edges. The GNN-based pavement simulator (GPS) was developed to model 3D pavement responses, integrating three key components: encoder, processor, and decoder. The GPS model employed two-layer multilayer perceptrons (MLP) for the encoder and decoder, while utilizing graph network (GN) technology for the processor. Validation occurred through two case studies—OneStep and Rollout—with results compared against FE model data as ground truth. Results demonstrated that the GPS model provides an accurate and computationally efficient alternative to traditional 3D pavement FE simulations.