Optimising Multilayer Perceptron weights and biases through a Cellular Genetic Algorithm for medical data classification

Rojas, Matías Gabriel; Olivera, Ana Carolina; Vidal, Pablo Javier

doi:10.1016/j.array.2022.100173

Cited by 17 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The S h notation represents the neuron's output. The whole result may be calculated using equation (10) [44,45]. Based on the estimated loss, which is determined using equation (11), the network modifies the input neuron weights, the hidden node weights in the output layer, and the predicted value ( ) y .…”

Section: Resultsmentioning

confidence: 99%

Highly sensitive Borophene-metal-Si based multilayered Terahertz frequency spectrum based refractive index sensor

Almawgani,

Sorathiya,

Soni

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

We presented the numerical investigation of a multilayered borophne-metal-Si-based refractive index sensor for the wide range of the THz frequency. The proposed structure is worked for the frequency range of 1 to 15 THz. The structure is formed to identify reflectance variation, resonating frequency and other physical parameters over the broad frequency spectrum. The overall structure is simulated using FEM (Finite element method) computational techniques with a periodic boundary condition-based two-port model. The resonance effect of the structure is also investigated for the different shapes of the top metal resonator structure, which significantly influences the overall frequency shift. The proposed structure is investigated for the X and Y polarized input incident condition for the entire frequency band where the oblique angle incident stability is observed up to 80⁰. The proposed structure offers the maximum variation in sensitivity up to 3.5 THz/RIU (~ 11600 nm/RIU) for X-polarized and 5.5 THz/RIU (~ 10600 nm/RIU) for Y-polarized incident wave conditions. We have applied the artificial neural network algorithm (ANN) to predict the overall behaviour of the structure from the data points generated in the simulated results. We used the Relu optimizer to train the model, generating promising results for our collected data. The machine learning model gives RMSE = 0.049422, MAE = 0.018531, MSE = 0.00328 and R2 = 0.93768 for the testing data set. Similarly, the model generated the minimum RMSE values = 0.045955, MAE = 0.017392, MSE = 0.00295, and R2 = 0.97673 for the training data set for 2500 epochs. The proposed results in the manuscript give the future scope to design borophene a wide range of refractive index (RI) sensor designs used in biosensors, gas sensors and other environment sensors where the refractive index range is between 1 and 2.4.

show abstract

Section: Resultsmentioning

confidence: 99%

Highly sensitive Borophene-metal-Si based multilayered Terahertz frequency spectrum based refractive index sensor

Almawgani,

Sorathiya,

Soni

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

show abstract

“…In [26], the automatic tuning of hyperparameters of an MLP is performed with the GWO to identify COVID-19-affected chest X-ray scans. Still for a medical application, in [27], a cellular genetic algorithm is designed with a special crossover operator to optimize weights and biases of the MLP to classify medical data.…”

Section: Background On Metaheuristic Algorithmsmentioning

confidence: 99%

GWO-Based Joint Optimization of Millimeter-Wave System and Multilayer Perceptron for Archaeological Application

Marot,

Zidane,

El-Abed

et al. 2024

Sensors

View full text Add to dashboard Cite

Recently, low THz radar-based measurement and classification for archaeology emerged as a new imaging modality. In this paper, we investigate the classification of pottery shards, a key enabler to understand how the agriculture was introduced from the Fertile Crescent to Europe. Our purpose is to jointly design the measuring radar system and the classification neural network, seeking the maximal compactness and the minimal cost, both directly related to the number of sensors. We aim to select the least possible number of sensors and place them adequately, while minimizing the false recognition rate. For this, we propose a novel version of the Binary Grey Wolf Optimizer, designed to reduce the number of sensors, and a Ternary Grey Wolf Optimizer. Together with the Continuous Grey Wolf Optimizer, they yield the CBTGWO (Continuous Binary Ternary Grey Wolf Optimizer). Working with 7 frequencies and starting with 37 sensors, the CBTGWO selects a single sensor and yields a 0-valued false recognition rate. In a single-frequency scenario, starting with 217 sensors, the CBTGWO selects 2 sensors. The false recognition rate is 2%. The acquisition time is 3.2 s, outperforming the GWO and adaptive mixed GWO, which yield 86.4 and 396.6 s.

show abstract

“…The output O x (m), could be fed as the input for the next corresponding sub-layer of the hidden layer for further processing. The corresponding weight from sub-layers of the hidden layer is identified as ω h1 and the corresponding bias is identified as b hj , then the corresponding outcome of the neuron is identified as S h is determined using Equation ( 13) [47].…”

Section: Multi-layer Perceptron Modelmentioning

confidence: 99%

A Software Framework for Predicting the Maize Yield Using Modified Multi-Layer Perceptron

Ahmed

2023

Sustainability

View full text Add to dashboard Cite

Predicting crop yields is one of agriculture’s most challenging issues. It is crucial in making national, provincial, and regional choices and estimates the government to meet the food demands of its citizens. Crop production is anticipated based on various factors such as soil conditions and meteorological, environmental, and crop variables. This study intends to develop an effective model that can accurately anticipate agricultural production in advance, assisting farmers in better planning. In the current study, the Crop Yield Prediction Dataset is normalized initially, and then feature engineering is performed to determine the significance of the feature in assessing the crop yield. Crop yield forecasting is performed using the Multi-Layer Perceptron model and the Spider Monkey Optimization method. The Multi-Layer Perceptron technique is efficient in dealing with the non-linear relations among the features in the data, and the Spider Monkey Optimization technique would assist in optimizing the corresponding feature weights. The current study uses data from the Food and Agriculture Organization and the World Data Bank to forecast maize yield in the Saudi Arabia region based on factors such as average temperature, average rainfall, and Hg/Ha production in past years. The suggested MLP-SMO model’s prediction effectiveness is being evaluated using several evaluation metrics such as Root-Mean-Square Error, R-Squared, Mean Absolute Error, and Mean Bias Error, where the model has outperformed in the prediction process with a Root-Mean-Square Error value of 0.11, which is lowest among all the techniques that are considered in the statical analysis in the current study.

show abstract

Optimising Multilayer Perceptron weights and biases through a Cellular Genetic Algorithm for medical data classification

Cited by 17 publications

References 53 publications

Highly sensitive Borophene-metal-Si based multilayered Terahertz frequency spectrum based refractive index sensor

Highly sensitive Borophene-metal-Si based multilayered Terahertz frequency spectrum based refractive index sensor

GWO-Based Joint Optimization of Millimeter-Wave System and Multilayer Perceptron for Archaeological Application

A Software Framework for Predicting the Maize Yield Using Modified Multi-Layer Perceptron

Contact Info

Product

Resources

About