scholarly journals Modeling the Spread of COVID-19 Infection Using a Multilayer Perceptron

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Zlatan Car ◽  
Sandi Baressi Šegota ◽  
Nikola Anđelić ◽  
Ivan Lorencin ◽  
Vedran Mrzljak
Keyword(s):  
Multilayer Perceptron ◽  
Cross Validation ◽  
Search Algorithm ◽  
Activation Function ◽  
Coefficient Of Determination ◽  
Time Series Dataset ◽  
Number Of Patients ◽  
Patient Model ◽  
Artificial Neural Network Ann ◽  
Deceased Patient

Coronavirus (COVID-19) is a highly infectious disease that has captured the attention of the worldwide public. Modeling of such diseases can be extremely important in the prediction of their impact. While classic, statistical, modeling can provide satisfactory models, it can also fail to comprehend the intricacies contained within the data. In this paper, authors use a publicly available dataset, containing information on infected, recovered, and deceased patients in 406 locations over 51 days (22nd January 2020 to 12th March 2020). This dataset, intended to be a time-series dataset, is transformed into a regression dataset and used in training a multilayer perceptron (MLP) artificial neural network (ANN). The aim of training is to achieve a worldwide model of the maximal number of patients across all locations in each time unit. Hyperparameters of the MLP are varied using a grid search algorithm, with a total of 5376 hyperparameter combinations. Using those combinations, a total of 48384 ANNs are trained (16128 for each patient group—deceased, recovered, and infected), and each model is evaluated using the coefficient of determination (R2). Cross-validation is performed using K-fold algorithm with 5-folds. Best models achieved consists of 4 hidden layers with 4 neurons in each of those layers, and use a ReLU activation function, with R2 scores of 0.98599 for confirmed, 0.99429 for deceased, and 0.97941 for recovered patient models. When cross-validation is performed, these scores drop to 0.94 for confirmed, 0.781 for recovered, and 0.986 for deceased patient models, showing high robustness of the deceased patient model, good robustness for confirmed, and low robustness for recovered patient model.

scholarly journals Prediction of Healing Performance of Autogenous Healing Concrete Using Machine Learning

Materials ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4068
Author(s):  
Xu Huang ◽  
Mirna Wasouf ◽  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Machine Learning ◽  
Search Algorithm ◽  
Weather Conditions ◽  
Prediction Performance ◽  
Machine Learning Algorithms ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Support Vector ◽  
Self Healing ◽  
Artificial Neural Network Ann

Cracks typically develop in concrete due to shrinkage, loading actions, and weather conditions; and may occur anytime in its life span. Autogenous healing concrete is a type of self-healing concrete that can automatically heal cracks based on physical or chemical reactions in concrete matrix. It is imperative to investigate the healing performance that autogenous healing concrete possesses, to assess the extent of the cracking and to predict the extent of healing. In the research of self-healing concrete, testing the healing performance of concrete in a laboratory is costly, and a mass of instances may be needed to explore reliable concrete design. This study is thus the world’s first to establish six types of machine learning algorithms, which are capable of predicting the healing performance (HP) of self-healing concrete. These algorithms involve an artificial neural network (ANN), a k-nearest neighbours (kNN), a gradient boosting regression (GBR), a decision tree regression (DTR), a support vector regression (SVR) and a random forest (RF). Parameters of these algorithms are tuned utilising grid search algorithm (GSA) and genetic algorithm (GA). The prediction performance indicated by coefficient of determination (R2) and root mean square error (RMSE) measures of these algorithms are evaluated on the basis of 1417 data sets from the open literature. The results show that GSA-GBR performs higher prediction performance (R2GSA-GBR = 0.958) and stronger robustness (RMSEGSA-GBR = 0.202) than the other five types of algorithms employed to predict the healing performance of autogenous healing concrete. Therefore, reliable prediction accuracy of the healing performance and efficient assistance on the design of autogenous healing concrete can be achieved.

scholarly journals Use of Artificial Neural Network for Estimation of Propeller Torque Values in a CODLAG Propulsion System

2020 ◽  
Vol 58 (1) ◽  
pp. 25-38
Author(s):  
Sandi Baressi Šegota ◽  
Daniel Štifanić ◽  
Kazuhiro Ohkura ◽  
Zlatan Car
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Absolute Error ◽  
Activation Function ◽  
Propulsion System ◽  
Coefficient Of Determination ◽  
Decay State ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Torque Values

An artificial neural network (ANN) approach is proposed to the problem of estimating the propeller torques of a frigate using combined diesel, electric and gas (CODLAG) propulsion system. The authors use a multilayer perceptron (MLP) feed-forward ANN trained with data from a dataset which describes the decay state coefficients as outputs and system parameters as inputs – with a goal of determining the propeller torques, removing the decay state coefficients and using the torque values of the starboard and port propellers as outputs. A total of 53760 ANNs are trained – 26880 for each of the propellers, with a total 8960 parameter combinations. The results are evaluated using mean absolute error (MAE) and coefficient of determination (R2). Best results for the starboard propeller are MAE of 2.68 [Nm], and MAE of 2.58 [Nm] for the port propeller with following ANN configurations respectively: 2 hidden layers with 32 neurons and identity activation and 3 hidden layers with 16, 32 and 16 neurons and identity activation function. Both configurations achieve R2 value higher than 0.99.

scholarly journals Compact yet efficient hardware architecture for multilayer-perceptron neural networks

2011 ◽  
Vol 22 (6) ◽  
pp. 647-663 ◽  
Author(s):  
Rodrigo Martins da Silva ◽  
Luiza de Macedo Mourelle ◽  
Nadia Nedjah
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Multilayer Perceptron ◽  
Resource Sharing ◽  
Activation Function ◽  
Hardware Architecture ◽  
Weighted Sum ◽  
Combinational Circuits ◽  
Number Of Layers ◽  
Artificial Neural Network Ann

There are several neural network implementations using either software, hardware-based or a hardware/software co-design. This work proposes a hardware architecture to implement an artificial neural network (ANN), whose topology is the multilayer perceptron (MLP). In this paper, we explore the parallelism of neural networks and allow on-thefly changes of the number of inputs, number of layers and number of neurons per layer of the net. This reconfigurability characteristic permits that any application of ANNs may be implemented using the proposed hardware. In order to reduce the processing time that is spent in arithmetic computation, a real number is represented using a fraction of integers. In this way, the arithmetics is limited to integer operations, performed by fast combinational circuits. A simple state machine is required to control sums and products of fractions. Sigmoid is used as the activation function in the proposed implementation. It is approximated by polynomials, whose underlying computation requires only sums and products. A theorem is introduced and proven so as to cover the arithmetic strategy of the computation of the activation function. Thus, the arithmetic circuitry used to implement the neuron weighted sum is reused for computing the sigmoid. this resource sharing decreased drastically the total area of the system. After modeling and simulation for functionality validation, the proposed architecture synthesized using reconfigurable hardware. The results are promising.

Combination of Support Vector Machine and K-Fold cross-validation for prediction of long-term degradation of the compressive strength of marine concrete

2018 ◽  
Vol 1 (1) ◽  
pp. 120-130 ◽  
Author(s):  
Chunxiang Qian ◽  
Wence Kang ◽  
Hao Ling ◽  
Hua Dong ◽  
Chengyao Liang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Environmental Factors ◽  
Cross Validation ◽  
Concrete Strength ◽  
Simulation Method ◽  
Support Vector ◽  
Svm Model ◽  
Artificial Neural Network Ann ◽  
Influence Degree ◽  
Fold Cross Validation

Support Vector Machine (SVM) model optimized by K-Fold cross-validation was built to predict and evaluate the degradation of concrete strength in a complicated marine environment. Meanwhile, several mathematical models, such as Artificial Neural Network (ANN) and Decision Tree (DT), were also built and compared with SVM to determine which one could make the most accurate predictions. The material factors and environmental factors that influence the results were considered. The materials factors mainly involved the original concrete strength, the amount of cement replaced by fly ash and slag. The environmental factors consisted of the concentration of Mg2+, SO42-, Cl-, temperature and exposing time. It was concluded from the prediction results that the optimized SVM model appeared to perform better than other models in predicting the concrete strength. Based on SVM model, a simulation method of variables limitation was used to determine the sensitivity of various factors and the influence degree of these factors on the degradation of concrete strength.

Decolorization of Reactive Black B from wastewater by electro-coagulation: optimization using multivariate RSM and ANN

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Kajal Gautam ◽  
Rishi K. Verma ◽  
Suantak Kamsonlian ◽  
Sushil Kumar
Keyword(s):  
Current Density ◽  
Operating Cost ◽  
Quadratic Model ◽  
Coefficient Of Determination ◽  
Process Time ◽  
Mathematical Tool ◽  
Electrode Gap ◽  
Artificial Neural Network Ann ◽  
Electro Coagulation ◽  
Optimized Conditions

AbstractThe present study is aimed to model and optimize the electrocoagulation (EC) process with five important parameters for the decolorization of Reactive Black B (RBB) from simulated wastewater. A multivariate approach, response surface methodology (RSM) together with central composite design (CCD) is used to optimize process parameters such as pH (5–9), electrode gap (0.5–2.5 cm), current density (2.08–10.41 mA/cm2), process time (10–30 min), and initial dye concentration (100–500 mg/l). The predicted percentage decolorization of dye is obtained as 97.21% at optimized conditions: pH (6.8), gapping (1.3 cm), current density (8.32 mA/cm2), time (23 min), and initial dye concentration (200 mg/L), which is very close to experimental percent decolorization (98.41%). The statistical analysis of variance (ANOVA) is performed to evaluate the quadratic model (RSM), and shows good fit of experimental data with coefficient of determination R2 >0.93. An Artificial Neural Network (ANN) is also used to predict the percentage decolorization and gives overall 94.96% which shows performance accuracy between the predicted and actual value of decolorization. The additional considerations of operating cost and current efficiency are also taken care to show the efficacy of EC process with mathematical tool. The sludge characteristics are determined by FE-SEM/EDX.

A comparative study and combined application of RSM and ANN in adsorptive removal of diuron using biomass ashes

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Sunil K. Deokar ◽  
Nachiket A. Gokhale ◽  
Sachin A. Mandavgane
Keyword(s):  
Three Dimensional ◽  
Current Approach ◽  
Coefficient Of Determination ◽  
Ann Model ◽  
Operational Parameters ◽  
Initial Concentration ◽  
Combined Application ◽  
Artificial Neural Network Ann ◽  
Relationship Of ◽  
Biomass Ashes

Abstract Biomass ashes like rice husk ash (RHA), bagasse fly ash (BFA), were used for aqueous phase removal of a pesticide, diuron. Response surface methodology (RSM) and artificial neural network (ANN) were successfully applied to estimate and optimize the conditions for the maximum diuron adsorption using biomass ashes. The effect of operational parameters such as initial concentration (10–30 mg/L); contact time (0.93–16.07 h) and adsorbent dosage (20–308 mg) on adsorption were studied using central composite design (CCD) matrix. Same design was also employed to gain a training set for ANN. The maximum diuron removal of 88.95 and 99.78% was obtained at initial concentration of 15 mg/L, time of 12 h, RHA dosage of 250 mg and at initial concentration of 14 mg/L, time of 13 h, BFA dosage of 60 mg respectively. Estimation of coefficient of determination (R 2) and mean errors obtained for ANN and RSM (R 2 RHA = 0.976, R 2 BFA = 0.943) proved ANN (R 2 RHA = 0.997, R 2 BFA = 0.982) fits better. By employing RSM coupled with ANN model, the qualitative and quantitative activity relationship of experimental data was visualized in three dimensional spaces. The current approach will be instrumental in providing quick preliminary estimations in process and product development.

scholarly journals Hourly Ground-Level PM2.5 Estimation Using Geostationary Satellite and Reanalysis Data via Deep Learning

2021 ◽  
Vol 13 (11) ◽  
pp. 2121
Author(s):  
Changsuk Lee ◽  
Kyunghwa Lee ◽  
Sangmin Kim ◽  
Jinhyeok Yu ◽  
Seungtaek Jeong ◽  
...  
Keyword(s):  
Cross Validation ◽  
Ground Level ◽  
Reanalysis Data ◽  
Training Dataset ◽  
Coefficient Of Determination ◽  
Mean Bias Error ◽  
Bias Error ◽  
Air Quality Model ◽  
Quality Model ◽  
Near Surface

This study proposes an improved approach for monitoring the spatial concentrations of hourly particulate matter less than 2.5 μm in diameter (PM2.5) via a deep neural network (DNN) using geostationary ocean color imager (GOCI) images and unified model (UM) reanalysis data over the Korean Peninsula. The DNN performance was optimized to determine the appropriate training model structures, incorporating hyperparameter tuning, regularization, early stopping, and input and output variable normalization to prevent training dataset overfitting. Near-surface atmospheric information from the UM was also used as an input variable to spatially generalize the DNN model. The retrieved PM2.5 from the DNN was compared with estimates from random forest, multiple linear regression, and the Community Multiscale Air Quality model. The DNN demonstrated the highest accuracy compared to that of the conventional methods for the hold-out validation (root mean square error (RMSE) = 7.042 μg/m3, mean bias error (MBE) = −0.340 μg/m3, and coefficient of determination (R2) = 0.698) and the cross-validation (RMSE = 9.166 μg/m3, MBE = 0.293 μg/m3, and R2 = 0.49). Although the R2 was low due to underestimated high PM2.5 concentration patterns, the RMSE and MBE demonstrated reliable accuracy values (<10 μg/m3 and 1 μg/m3, respectively) for the hold-out validation and cross-validation.

scholarly journals Determination of the Factors Affecting King Abdul Aziz University Published Articles in ISI by Multilayer Perceptron Artificial Neural Network

Mathematics ◽  
2020 ◽  
Vol 8 (5) ◽  
pp. 766
Author(s):  
Rashad A. R. Bantan ◽  
Ramadan A. Zeineldin ◽  
Farrukh Jamal ◽  
Christophe Chesneau
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Multilayer Perceptron ◽  
Research Study ◽  
Real Data ◽  
Factors Affecting ◽  
King Abdulaziz University ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Deanship of scientific research established by the King Abdulaziz University provides some research programs for its staff and researchers and encourages them to submit proposals in this regard. Distinct research study (DRS) is one of these programs. It is available all the year and the King Abdulaziz University (KAU) staff can submit more than one proposal at the same time up to three proposals. The rules of the DSR program are simple and easy so it contributes in increasing the international rank of KAU. The authors are offered financial and moral reward after publishing articles from these proposals in Thomson-ISI journals. In this paper, multiplayer perceptron (MLP) artificial neural network (ANN) is employed to determine the factors that have more effect on the number of ISI published articles. The proposed study used real data of the finished projects from 2011 to April 2019.

scholarly journals QSPR study on the gas/particle partition coefficient of PCBs by using molecular distance-edge vector index

2014 ◽  
Vol 79 (8) ◽  
pp. 965-975 ◽  
Author(s):  
Long Jiao ◽  
Xiaofei Wang ◽  
LI. Hua ◽  
Yunxia Wang
Keyword(s):  
Partition Coefficient ◽  
Cross Validation ◽  
External Validation ◽  
Quantitative Relationship ◽  
Structure Property ◽  
Prediction Ability ◽  
Vector Index ◽  
Artificial Neural Network Ann ◽  
Leave One Out ◽  
Edge Vector

The quantitative structure property relationship (QSPR) for gas/particle partition coefficient, Kp, of polychlorinated biphenyls (PCBs) was investigated. Molecular distance-edge vector (MDEV) index was used as the structural descriptor of PCBs. The quantitative relationship between the MDEV index and log Kp was modeled by multivariate linear regression (MLR) and artificial neural network (ANN) respectively. Leave one out cross validation and external validation were carried out to assess the prediction ability of the developed models. When the MLR method is used, the root mean square relative error (RMSRE) of prediction for leave one out cross validation and external validation is 4.72 and 8.62 respectively. When the ANN method is employed, the prediction RMSRE of leave one out cross validation and external validation is 3.87 and 7.47 respectively. It is demonstrated that the developed models are practicable for predicting the Kp of PCBs. The MDEV index is shown to be quantitatively related to the Kp of PCBs.

Comparison of various multivariate models to estimate structural properties by means of non-destructive techniques (NDTs) in Pinus sylvestris L. timber

Holzforschung ◽  
2019 ◽  
Vol 73 (4) ◽  
pp. 331-338
Author(s):  
Antonio Villasante ◽  
Guillermo Íñiguez-González ◽  
Lluis Puigdomenech
Keyword(s):  
Pinus Sylvestris ◽  
Linear Models ◽  
Longitudinal Vibration ◽  
Modulus Of Rupture ◽  
Coefficient Of Determination ◽  
Pullout Resistance ◽  
Density Prediction ◽  
Learning Software ◽  
Artificial Neural Network Ann ◽  
Non Destructive

AbstractThe predictability of modulus of elasticity (MOE), modulus of rupture (MOR) and density of 120 samples of Scots pine (Pinus sylvestrisL.) were investigated using various non-destructive variables (such as time of flight of stress wave, natural frequency of longitudinal vibration, penetration depth, pullout resistance, visual grading and concentrated knot diameter ratio), and based on multivariate algorithms, applying WEKA as machine learning software. The algorithms used were: multivariate linear regression (MLR), Gaussian, Lazy, artificial neural network (ANN), Rules and decision Tree. The models were quantified based on the root-mean-square error (RMSE) and the coefficient of determination (R2). To avoid model overfitting, the modeling was built and the results validated via the so-called 10-fold cross-validation. MLR with the “greedy method” for variable selection based on the Akaike information metric (MLRak) significantly reduced the RMSE of MOR and MOE compared to univariate linear regressions (ULR). However, this reduction was not significant for density prediction. The predictability of MLRak was not improved by any other of the tested algorithms. Specifically, non-linear models, such as multilayer perceptron, did not contribute any significant improvements over linear models. Finally, MLRak models were simplified by discarding the variables that produce the lowest RMSE increment. The resulted models could be even further simplified without significant RMSE increment.

Sign in / Sign up

Export Citation Format

Share Document