Using Machine Learning Algorithms for Accurate Received Optical Power Prediction of an FSO Link over a Maritime Environment

The performance prediction of an optical communications link over maritime environments has been extensively researched over the last two decades. The various atmospheric phenomena and turbulence effects have been thoroughly explored, and long-term measurements have allowed for the construction of simple empirical models. The aim of this work is to demonstrate the prediction accuracy of various machine learning (ML) algorithms for a free-space optical communication (FSO) link performance, with respect to real time, non-linear atmospheric conditions. A large data set of received signal strength indicators (RSSI) for a laser communications link has been collected and analyzed against seven local atmospheric parameters (i.e., wind speed, pressure, temperature, humidity, dew point, solar flux and air-sea temperature difference). The k-nearest-neighbors (KNN), tree-based methods-decision trees, random forest and gradient boosting- and artificial neural networks (ANN) have been employed and compared among each other using the root mean square error (RMSE) and the coefficient of determination (R2) of each model as the primary performance indices. The regression analysis revealed an excellent fit for all ML models, indicative of their ability to offer a significant improvement in FSO performance modeling as compared to traditional regression models. The best-performing R2 model found to be the ANN approach (0.94867), while random forests achieved the most optimal RMSE result (7.37).

Download Full-text

Prediction of Healing Performance of Autogenous Healing Concrete Using Machine Learning

Materials ◽

10.3390/ma14154068 ◽

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.

Download Full-text

Artificial Intelligence Based Approach for Predicting Fatigue Strength Using Composition and Process Parameters

Volume 3: Materials Technology ◽

10.1115/omae2020-18675 ◽

2020 ◽

Author(s):

Arvind Keprate ◽

R. M. Chandima Ratnayake

Keyword(s):

Artificial Intelligence ◽

Fatigue Strength ◽

Process Parameters ◽

Fatigue Testing ◽

Simulated Data ◽

Machine Learning Algorithms ◽

Coefficient Of Determination ◽

Gradient Boosting ◽

Data Set ◽

Strength Based

Abstract Accurate prediction of the fatigue strength of steels is vital, due to the extremely high cost (and time) of fatigue testing and the often fatal consequences of fatigue failures. The work presented in this paper is an extension of the previous paper submitted to OMAE 2019. The main objective of this manuscript is to utilize Artificial Intelligence (AI) to predict fatigue strength, based on composition and process parameters, using the fatigue dataset for carbon and low alloy steel available from the National Institute of Material Science (NIMS) database, MatNavi. A deep learning framework Keras is used to build a Neural Network (NN), which is trained and tested on the data set obtained from MatNavi. The fatigue strength values estimated using NN are compared to the values predicted by the gradient boosting algorithm, which was the most accurate model in the OMAE 2019 paper. The comparison is done using metrics such as root mean square error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2) and Explained Variance Score (EVS). Thereafter, the trained NN model is used to make predictions of fatigue strength for the simulated data (1 million samples) of input parameters, which is then used to generate conditional probability tables for the Bayesian Network (BN). The main advantage of using BN over previously used machine learning algorithms is that BN can be used to make both forward and backward propagation during the Bayesian inference. A case study illustrating the applicability of the proposed approach is also presented. Furthermore, a dashboard is developed using PowerBI, which can be used by practicing engineers to estimate fatigue strength based on composition and process parameters.

Download Full-text

Random forest and extreme gradient boosting algorithms for streamflow modeling using vessel features, and tree-rings

10.21203/rs.3.rs-303081/v1 ◽

2021 ◽

Author(s):

Hossein Sahour ◽

Vahid Gholami ◽

Javad Torkman ◽

Mehdi Vazifedan ◽

Sirwe Saeedi

Keyword(s):

Machine Learning ◽

Random Forest ◽

Tree Rings ◽

Test Site ◽

Machine Learning Algorithms ◽

Coefficient Of Determination ◽

Gradient Boosting ◽

Growing Seasons ◽

Extreme Gradient Boosting ◽

Streamflow Modeling

Abstract Monitoring temporal variation of streamflow is necessary for many water resources management plans, yet, such practices are constrained by the absence or paucity of data in many rivers around the world. Using a permanent river in the north of Iran as a test site, a machine learning framework was proposed to model the streamflow data in the three periods of growing seasons based on tree-rings and vessel features of the Zelkova carpinifolia species. First, full-disc samples were taken from 30 trees near the river, and the samples went through preprocessing, cross-dating, standardization, and time series analysis. Two machine learning algorithms, namely random forest (RF) and extreme gradient boosting (XGB), were used to model the relationships between dendrochronology variables (tree-rings and vessel features in the three periods of growing seasons) and the corresponding streamflow rates. The performance of each model was evaluated using statistical coefficients (coefficient of determination (R-squared), Nash-Sutcliffe efficiency (NSE), and root-mean-square error (NRMSE)). Findings demonstrate that consideration should be given to the XGB model in streamflow modeling given its apparent enhanced performance (R-squared: 0.87; NSE: 0.81; and NRMSE: 0.43) over the RF model (R-squared: 0.82; NSE: 0.71; and NRMSE: 0.52). Further, the results showed that the models perform better in modeling the normal and low flows compared to extremely high flows. Finally, the tested models were used to reconstruct the temporal streamflow during the past decades (1970–1981).

Download Full-text

Prediction of Water Saturation from Well Log Data by Machine Learning Algorithms: Boosting and Super Learner

Journal of Marine Science and Engineering ◽

10.3390/jmse9060666 ◽

2021 ◽

Vol 9 (6) ◽

pp. 666

Author(s):

Fahimeh Hadavimoghaddam ◽

Mehdi Ostadhassan ◽

Mohammad Ali Sadri ◽

Tatiana Bondarenko ◽

Igor Chebyshev ◽

...

Keyword(s):

Machine Learning ◽

Water Saturation ◽

Machine Learning Algorithms ◽

Rock Properties ◽

Gradient Boosting ◽

Data Set ◽

Log Data ◽

Gamma Density ◽

Super Learner ◽

Resistivity Log

Intelligent predictive methods have the power to reliably estimate water saturation (Sw) compared to conventional experimental methods commonly performed by petrphysicists. However, due to nonlinearity and uncertainty in the data set, the prediction might not be accurate. There exist new machine learning (ML) algorithms such as gradient boosting techniques that have shown significant success in other disciplines yet have not been examined for Sw prediction or other reservoir or rock properties in the petroleum industry. To bridge the literature gap, in this study, for the first time, a total of five ML code programs that belong to the family of Super Learner along with boosting algorithms: XGBoost, LightGBM, CatBoost, AdaBoost, are developed to predict water saturation without relying on the resistivity log data. This is important since conventional methods of water saturation prediction that rely on resistivity log can become problematic in particular formations such as shale or tight carbonates. Thus, to do so, two datasets were constructed by collecting several types of well logs (Gamma, density, neutron, sonic, PEF, and without PEF) to evaluate the robustness and accuracy of the models by comparing the results with laboratory-measured data. It was found that Super Learner and XGBoost produced the highest accurate output (R2: 0.999 and 0.993, respectively), and with considerable distance, Catboost and LightGBM were ranked third and fourth, respectively. Ultimately, both XGBoost and Super Learner produced negligible errors but the latest is considered as the best amongst all.

Download Full-text

Prediction of Geopolymer Concrete Compressive Strength Using Novel Machine Learning Algorithms

Polymers ◽

10.3390/polym13193389 ◽

2021 ◽

Vol 13 (19) ◽

pp. 3389

Author(s):

Ayaz Ahmad ◽

Waqas Ahmad ◽

Krisada Chaiyasarn ◽

Krzysztof Adam Ostrowski ◽

Fahid Aslam ◽

...

Keyword(s):

Machine Learning ◽

Compressive Strength ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Coefficient Of Determination ◽

Gradient Boosting ◽

Geopolymer Concrete ◽

Ann Model ◽

High Calcium ◽

Boosting Technique

The innovation of geopolymer concrete (GPC) plays a vital role not only in reducing the environmental threat but also as an exceptional material for sustainable development. The application of supervised machine learning (ML) algorithms to forecast the mechanical properties of concrete also has a significant role in developing the innovative environment in the field of civil engineering. This study was based on the use of the artificial neural network (ANN), boosting, and AdaBoost ML approaches, based on the python coding to predict the compressive strength (CS) of high calcium fly-ash-based GPC. The performance comparison of both the employed techniques in terms of prediction reveals that the ensemble ML approaches, AdaBoost, and boosting were more effective than the individual ML technique (ANN). The boosting indicates the highest value of R2 equals 0.96, and AdaBoost gives 0.93, while the ANN model was less accurate, indicating the coefficient of determination value equals 0.87. The lesser values of the errors, MAE, MSE, and RMSE of the boosting technique give 1.69 MPa, 4.16 MPa, and 2.04 MPa, respectively, indicating the high accuracy of the boosting algorithm. However, the statistical check of the errors (MAE, MSE, RMSE) and k-fold cross-validation method confirms the high precision of the boosting technique. In addition, the sensitivity analysis was also introduced to evaluate the contribution level of the input parameters towards the prediction of CS of GPC. The better accuracy can be achieved by incorporating other ensemble ML techniques such as AdaBoost, bagging, and gradient boosting.

Download Full-text

Petrofacies classification using machine learning algorithms

Geophysics ◽

10.1190/geo2019-0439.1 ◽

2020 ◽

Vol 85 (4) ◽

pp. WA101-WA113 ◽

Cited By ~ 3

Author(s):

Adrielle A. Silva ◽

Mônica W. Tavares ◽

Abel Carrasquilla ◽

Roseane Misságia ◽

Marco Ceia

Keyword(s):

Machine Learning ◽

Oil And Gas ◽

Water Saturation ◽

Carbonate Reservoir ◽

Machine Learning Algorithms ◽

Carbonate Reservoirs ◽

Training Data ◽

Southeastern Brazil ◽

Gradient Boosting ◽

Data Set

Carbonate reservoirs represent a large portion of the world’s oil and gas reserves, exhibiting specific characteristics that pose complex challenges to the reservoirs’ characterization, production, and management. Therefore, the evaluation of the relationships between the key parameters, such as porosity, permeability, water saturation, and pore size distribution, is a complex task considering only well-log data, due to the geologic heterogeneity. Hence, the petrophysical parameters are the key to assess the original composition and postsedimentological aspects of the carbonate reservoirs. The concept of reservoir petrofacies was proposed as a tool for the characterization and prediction of the reservoir quality as it combines primary textural analysis with laboratory measurements of porosity, permeability, capillary pressure, photomicrograph descriptions, and other techniques, which contributes to understanding the postdiagenetic events. We have adopted a workflow to petrofacies classification of a carbonate reservoir from the Campos Basin in southeastern Brazil, using the following machine learning methods: decision tree, random forest, gradient boosting, K-nearest neighbors, and naïve Bayes. The data set comprised 1477 wireline data from two wells (A3 and A10) that had petrofacies classes already assigned based on core descriptions. It was divided into two subsets, one for training and one for testing the capability of the trained models to assign petrofacies. The supervised-learning models have used labeled training data to learn the relationships between the input measurements and the petrofacies to be assigned. Additionally, we have developed a comparison of the models’ performance using the testing set according to accuracy, precision, recall, and F1-score evaluation metrics. Our approach has proved to be a valuable ally in petrofacies classification, especially for analyzing a well-logging database with no prior petrophysical information.

Download Full-text

Surface Shortwave Net Radiation Estimation from Landsat TM/ETM+ Data Using Four Machine Learning Algorithms

Remote Sensing ◽

10.3390/rs11232847 ◽

2019 ◽

Vol 11 (23) ◽

pp. 2847 ◽

Cited By ~ 3

Author(s):

Yezhe Wang ◽

Bo Jiang ◽

Shunlin Liang ◽

Dongdong Wang ◽

Tao He ◽

...

Keyword(s):

Machine Learning ◽

Land Surface ◽

Thematic Mapper ◽

Global Model ◽

Machine Learning Algorithms ◽

Multivariate Adaptive Regression Splines ◽

Coefficient Of Determination ◽

Gradient Boosting ◽

Support Vector ◽

Net Radiation

Surface shortwave net radiation (SSNR) flux is essential for the determination of the radiation energy balance between the atmosphere and the Earth’s surface. The satellite-derived intermediate SSNR data are strongly needed to bridge the gap between existing coarse-resolution SSNR products and point-based measurements. In this study, four different machine learning (ML) algorithms were tested to estimate the SSNR from the Landsat Thematic Mapper (TM)/ Enhanced Thematic Mapper Plus (ETM+) top-of-atmosphere (TOA) reflectance and other ancillary information (i.e., clearness index, water vapor) at instantaneous and daily scales under all sky conditions. The four ML algorithms include the multivariate adaptive regression splines (MARS), backpropagation neural network (BPNN), support vector regression (SVR), and gradient boosting regression tree (GBRT). Collected in-situ measurements were used to train the global model (using all data) and the conditional models (in which all data were divided into subsets and the models were fitted separately). The validation results indicated that the GBRT-based global model (GGM) performs the best at both the instantaneous and daily scales. For example, the GGM based on the TM data yielded a coefficient of determination value (R2) of 0.88 and 0.94, an average root mean square error (RMSE) of 73.23 W∙m-2 (15.09%) and 18.76 W·m-2 (11.2%), and a bias of 0.64 W·m-2 and –1.74 W·m-2 for instantaneous and daily SSNR, respectively. Compared to the Global LAnd Surface Satellite (GLASS) daily SSNR product, the daily TM-SSNR showed a very similar spatial distribution but with more details. Further analysis also demonstrated the robustness of the GGM for various land cover types, elevation, general atmospheric conditions, and seasons

Download Full-text

Modeling the Settling Velocity of a Sphere in Newtonian and Non-Newtonian Fluids with Machine-Learning Algorithms

Symmetry ◽

10.3390/sym13010071 ◽

2021 ◽

Vol 13 (1) ◽

pp. 71

Author(s):

Sayeed Rushd ◽

Noor Hafsa ◽

Majdi Al-Faiad ◽

Md Arifuzzaman

Keyword(s):

Machine Learning ◽

Settling Velocity ◽

Learning Algorithms ◽

Newtonian Fluids ◽

Machine Learning Algorithms ◽

Coefficient Of Determination ◽

Polynomial Kernel ◽

Support Vector ◽

Data Set ◽

Traditional Procedure

The traditional procedure of predicting the settling velocity of a spherical particle is inconvenient as it involves iterations, complex correlations, and an unpredictable degree of uncertainty. The limitations can be addressed efficiently with artificial intelligence-based machine-learning algorithms (MLAs). The limited number of isolated studies conducted to date were constricted to specific fluid rheology, a particular MLA, and insufficient data. In the current study, the generalized application of ML was comprehensively investigated for Newtonian and three varieties of non-Newtonian fluids such as Power-law, Bingham, and Herschel Bulkley. A diverse set of nine MLAs were trained and tested using a large dataset of 967 samples. The ranges of generalized particle Reynolds number (ReG) and drag coefficient (CD) for the dataset were 10−3 < ReG (-) < 104 and 10−1 < CD (-) < 105, respectively. The performances of the models were statistically evaluated using an evaluation metric of the coefficient-of-determination (R2), root-mean-square-error (RMSE), mean-squared-error (MSE), and mean-absolute-error (MAE). The support vector regression with polynomial kernel demonstrated the optimum performance with R2 = 0.92, RMSE = 0.066, MSE = 0.0044, and MAE = 0.044. Its generalization capability was validated using the ten-fold-cross-validation technique, leave-one-feature-out experiment, and leave-one-data-set-out validation. The outcome of the current investigation was a generalized approach to modeling the settling velocity.

Download Full-text

Classification of hazelnut cultivars: comparison of DL4J and ensemble learning algorithms

Notulae Botanicae Horti Agrobotanici Cluj-Napoca ◽

10.15835/nbha48412041 ◽

2020 ◽

Vol 48 (4) ◽

pp. 2316-2327

Author(s):

Caner KOC ◽

Dilara GERDAN ◽

Maksut B. EMİNOĞLU ◽

Uğur YEGÜL ◽

Bulent KOC ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Random Forest ◽

Ensemble Learning ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Performance Criteria ◽

Gradient Boosting ◽

Data Set

Classification of hazelnuts is one of the values adding processes that increase the marketability and profitability of its production. While traditional classification methods are used commonly, machine learning and deep learning can be implemented to enhance the hazelnut classification processes. This paper presents the results of a comparative study of machine learning frameworks to classify hazelnut (Corylus avellana L.) cultivars (‘Sivri’, ‘Kara’, ‘Tombul’) using DL4J and ensemble learning algorithms. For each cultivar, 50 samples were used for evaluations. Maximum length, width, compression strength, and weight of hazelnuts were measured using a caliper and a force transducer. Gradient boosting machine (Boosting), random forest (Bagging), and DL4J feedforward (Deep Learning) algorithms were applied in traditional machine learning algorithms. The data set was partitioned into a 10-fold-cross validation method. The classifier performance criteria of accuracy (%), error percentage (%), F-Measure, Cohen’s Kappa, recall, precision, true positive (TP), false positive (FP), true negative (TN), false negative (FN) values are provided in the results section. The results showed classification accuracies of 94% for Gradient Boosting, 100% for Random Forest, and 94% for DL4J Feedforward algorithms.

Download Full-text

Extreme Gradient Boosting for Parkinson’s Disease Diagnosis from Voice Recordings

10.21203/rs.2.20727/v1 ◽

2020 ◽

Author(s):

Ibrahim Karabayir ◽

Suguna Pappu ◽

Samuel Goldman ◽

Oguz Akbilgic

Keyword(s):

Machine Learning ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Disease Diagnosis ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Acoustic Features ◽

Data Set ◽

Non Invasive ◽

Extreme Gradient Boosting

Abstract Background : Parkinson’s Disease (PD) is a clinically diagnosed neurodegenerative disorder that affects both motor and non-motor neural circuits. Speech deterioration (hypokinetic dysarthria) is a common symptom, which often presents early in the disease course. Machine learning can help movement disorders specialists improve their diagnostic accuracy using non-invasive and inexpensive voice recordings. Method : We used “Parkinson Dataset with Replicated Acoustic Features Data Set” from the UCI-Machine Learning repository. The dataset included 45 features including sex and 44 speech test based acoustic features from 40 patients with Parkinson’s disease and 40 controls. We analyzed the data using various machine learning algorithms including tree-based ensemble approaches such as random forest and extreme gradient boosting. We also implemented a variable importance analysis to identify important variables classifying patients with PD. Results : The cohort included total of 80 subjects; 40 patients with PD (55% men) and 40 controls (67.5% men). PD patients showed at least two of the three symptoms; resting tremor, bradykinesia, or rigidity. All patients were over 50 years old and the mean age for PD subjects and controls were 69.6 (SD 7.8) and 66.4 (SD 8.4), respectively. Our final model provided an AUC of 0.940 with 95% confidence interval 0.935-0.945in 4-folds cross validation using only six acoustic features including Delta3 (Run2), Delta0 (Run 3), MFCC4 (Run 2), Delta10 (Run 2/Run 3), MFCC10 (Run 2) and Jitter_Rap (Run 1/Run 2). Conclusions : Machine learning can accurately detect Parkinson’s disease using an inexpensive and non-invasive voice recording. Such technologies can be deployed into smartphones for screening of large patient populations for Parkinson’s disease.

Download Full-text