Analysis and Optimization of Rainfall Prediction in Makassar City Using Artificial Neural Networks Based on Data Augmentation, Regularization, and Bayesian Optimization

In this paper an artificial neural network (ANN) aiming for the efficient modelling of a set of machining conditions for orthogonal cutting of polyetheretherketone (PEEK) composite materials is presented. The supervised learning of the ANN is based on a genetic algorithm (GA) supported by an elitist strategy. Input, hidden and output layers model the topology of the ANN. The weights of the synapses and the biases for hidden and output nodes are used as design variables in the ANN learning process. Considering a set of experimental data, the mean relative error between experimental and numerical results is used to monitor the learning process obtaining the completeness of the machining process modelling. Also a regularization term associated to biases in hidden and output neurons are included in the GA fitness function for learning. Using a different set of experimental results, the optimal ANN obtained after learning is tested. The optimal number of nodes on the hidden layer is searched and the positive influence of the regularization term is demonstrated. This approach of ANN learning based on GA presents low mean relative errors in learning and testing phases.

The article attempts to compare the performance of regression based model and artificial neural network model for the prediction of stochastic – deterministic phenomena like orographic rain in North East Indian hills and valleys using historical thirty eight years data of rainfall over the three hill stations, Majhitar, Shillong and Silchar. Considering the randomness, nonstationary within the time series the suitable model for prediction of rainfall has been carried out. The performance of the prediction model is also calculated in terms of deviation from actual data. Result shows that for long term prediction of rainfall, artificial neural network (ANN) model performs better compared to autoregressive integrated moving average model for the prediction of orographic rainfall of North eastern India.

An evolutionary crow search algorithm equipped with interactive memory mechanism to optimize artificial neural network for disease diagnosis

Algorithms for machine learning have found extensive use in numerous fields and applications. One important aspect of effectively utilizing these algorithms is tuning the hyperparameters to match the specific task at hand. The selection and configuration of hyperparameters directly impact the performance of machine learning models. Achieving optimal hyperparameter settings often requires a deep understanding of the underlying models and the appropriate optimization techniques. While there are many automatic optimization techniques available, each with its own advantages and disadvantages, this article focuses on hyperparameter optimization for well-known machine learning models. It explores cutting-edge optimization methods such as metaheuristic algorithms, deep learning-based optimization, Bayesian optimization, and quantum optimization, and our paper focused mainly on metaheuristic and Bayesian optimization techniques and provides guidance on applying them to different machine learning algorithms. The article also presents real-world applications of hyperparameter optimization by conducting tests on spatial data collections for landslide susceptibility mapping. Based on the experiment's results, both Bayesian optimization and metaheuristic algorithms showed promising performance compared to baseline algorithms. For instance, the metaheuristic algorithm boosted the random forest model's overall accuracy by 5% and 3%, respectively, from baseline optimization methods GS and RS, and by 4% and 2% from baseline optimization methods GA and PSO. Additionally, for models like KNN and SVM, Bayesian methods with Gaussian processes had good results. When compared to the baseline algorithms RS and GS, the accuracy of the KNN model was enhanced by BO-TPE by 1% and 11%, respectively, and by BO-GP by 2% and 12%, respectively. For SVM, BO-TPE outperformed GS and RS by 6% in terms of performance, while BO-GP improved results by 5%. The paper thoroughly discusses the reasons behind the efficiency of these algorithms. By successfully identifying appropriate hyperparameter configurations, this research paper aims to assist researchers, spatial data analysts, and industrial users in developing machine learning models more effectively. The findings and insights provided in this paper can contribute to enhancing the performance and applicability of machine learning algorithms in various domains.

We propose an artificial neural network (ANN) model to predict the CO2 diffusion through the concrete to determine the carbonation depth over time, analyzing the influence of some training algorithm and the network architecture in the ANN learning process. A reliable experimental test database of the non-accelerated test with 278 results of concrete carbonation depth was created from the published literature. It was used to train, test, and validate the model. Altogether, 120 networks had been trained with different characteristics, verifying its performance. In spite of the non-linearity and complexity of the concrete carbonation phenomenon, the proposed ANN model yielded accurate prediction. Results indicate the best training algorithm and the optimum number of neurons in the hidden layer that allows faster ANN training process and generates the most accurate mapping for the concrete carbonation phenomenon. The use of ANN appears as a robust tool easily applied to the study of the concrete carbonation, aiding in decision making in engineering projects focused on durability.

Bayesian optimization has been studied in many fields as a technique for global optimization of black-box functions. We applied these techniques for optimizing the formulation and manufacturing methods of pharmaceutical products to eliminate unnecessary experiments and accelerate method development tasks. A simulation dataset was generated by the data augmentation from a design of experiment (DoE) which was executed to optimize the formulation and process parameters of orally disintegrating tablets. We defined a composite score for integrating multiple objective functions, physical properties of tablets, to meet the pharmaceutical criteria simultaneously. Performance measurements were used to compare the influence of the selection of initial training sets, by controlling data size and variation, acquisition functions, and schedules of hyperparameter tuning. Additionally, we investigated performance improvements obtained using Bayesian optimization techniques as opposed to random search strategy. Bayesian optimization efficiently reduces the number of experiments to obtain the optimal formulation and process parameters from about 25 experiments with DoE to 10 experiments. Repeated hyperparameter tuning during the Bayesian optimization process stabilizes variations in performance among different optimization conditions, thus improving average performance. We demonstrated the elimination of unnecessary experiments using Bayesian optimization. Simulations of different conditions depicted their dependencies, which will be useful in many real-world applications. Bayesian optimization is expected to reduce the reliance on individual skills and experiences, increasing the efficiency and efficacy of optimization tasks, expediting formulation and manufacturing research in pharmaceutical development.

Brain tumor is one of the most aggressive diseases nowadays, resulting in a very short life span if it is diagnosed at an advanced stage. The treatment planning phase is thus essential for enhancing the quality of life for patients. The use of Magnetic Resonance Imaging (MRI) in the diagnosis of brain tumors is extremely widespread, but the manual interpretation of large amounts of images requires considerable effort and is prone to human errors. Hence, an automated method is necessary to identify the most common brain tumors. Convolutional Neural Network (CNN) architectures are successful in image classification due to their high layer count, which enables them to conceive the features effectively on their own. The tuning of CNN hyperparameters is critical in every dataset since it has a significant impact on the efficiency of the training model. Given the high dimensionality and complexity of the data, manual hyperparameter tuning would take an inordinate amount of time, with the possibility of failing to identify the optimal hyperparameters. In this paper, we proposed a Bayesian Optimization-based efficient hyperparameter optimization technique for CNN. This method was evaluated by classifying 3064 T-1-weighted CE-MRI images into three types of brain tumors (Glioma, Meningioma, and Pituitary). Based on Transfer Learning, the performance of five well-recognized deep pre-trained models is compared with that of the optimized CNN. After using Bayesian Optimization, our CNN was able to attain 98.70% validation accuracy at best without data augmentation or cropping lesion techniques, while VGG16, VGG19, ResNet50, InceptionV3, and DenseNet201 achieved 97.08%, 96.43%, 89.29%, 92.86%, and 94.81% validation accuracy, respectively. Moreover, the proposed model outperforms state-of-the-art methods on the CE-MRI dataset, demonstrating the feasibility of automating hyperparameter optimization.

Inflow Control Devices (ICDs) help reduce the adverse consequences of uneven inflow issues in a lateral completion system. The most common uneven inflow consequences are early water breakthrough and gas coning in water-driven and saturated reservoirs. These issues lead to the dominance of undesired fluid production and consequently, reduced well productivity. Typically, uneven inflow issues are caused by different drivers, including heterogenous permeability, an uneven water saturation profile, and/or complex well completion in a lateral section of a given well. ICDs are placed in permanent positions along the lateral section of a well in order to control zonal production and improve well productivity. The goal of utilizing ICDs is to delay water or gas production and equalize the inflow production from the reservoir to wellbore. However, the uncertainty of reservoir characteristics and operational constraints add complexity to the ICD design and complicate optimization strategies. An optimum ICD design entails identifying the number and size of compartments, packer locations, ICD type, and number of ICDs in each compartment, and the ICD settings such as orifice diameter or flow restriction rating. Extensive reservoir modeling work can be performed to accurately quantify the impact of each ICD design on well production. The intent of this paper is to demonstrate that Bayesian optimization and machine learning techniques can help identify an optimized ICD design in a minimum number of reservoir simulation evaluations. These techniques are implemented into the reservoir simulation workflow to enhance the speed of the analysis and resulting value proposition for the operating customer.Using Gaussian Process Regression as a surrogate, Bayesian optimization makes use of a small number of initial reservoir simulation runs to quantify the uncertainty of the surrogate model in the parameter space. It makes use of an appropriate acquisition function (as determined by the desired exploration-exploitation tradeoff characteristics) to design the next sample (simulation run) to be evaluated. Unlike the ensemble-based optimization algorithms, Bayesian optimization points to the optimum solution sequentially (one evaluation at a time). The proposed workflow automates the optimization process of ICD design evaluation workflow times by 50% in our case studies. The 50% efficiency takes in the time to perform ICD optimization workflow. For instance, the manual iteration ICD design for case study 1 described in this paper was four weeks, which the proposed workflow shortened this time to two weeks.This paper presents two case studies in which the Bayesian optimization technique was used to identify the best ICD completion design. The space parameter in both case studies involves several variables, including the number and location of compartments, the number of ICDs per compartment, and the ICD settings (one such setting, for example, considers orifice diameter size). The goal in the first case study was to find an ICD design that can maximize the net present value over the well lifetime (set to 5 years), while reducing and delaying water production. In this first case study, an 800ft lateral in a horizontal well, with drastic variation of permeability along its lateral length, was considered. In the second case study, 4000ft horizontal length of a well with variations of permeability was analyzed. In this second case, the objective was to extend the life of the well by minimizing the gas-oil ratio and maximizing the oil recovery. The simulation runs stopped after 3 years of production and the best case was chosen based on the aforementioned criteria. In both case studies, the optimization algorithm setup was able to converge to an optimum ICD design within 20 reservoir simulation runs. This alone represents an improvement over the current manual trial and error process in which an expert uses human intuition.

A comprehensive framework based on Bayesian optimization and skip connections artificial neural networks to predict buildings energy performance

The application of artificial neural network (ANN) on dynamic voltage stability analysis is presented. Two ANN models have been utilized, in which the first ANN model is used to classify the power system as to whether it is dynamically stable or unstable. Then the second ANN model is used for the dynamically stable system to predict the voltage magnitudes at load busbars. Both ANN models are based on the multiperceptron model, and the training is done using the error back propagation scheme. The training set patterns are generated by carrying out dynamic simulations, using induction motor and constant P-Q load models. This paper highlights the method for selection of the optimum number of training sets so as to minimise the time taken in the ANN learning process. The performance of the ANN models have been tested and shown to give good results.

Rainfall prediction problem has been one of the major issues of catchment management source water protection. Accurate rainfall prediction can be efficiently put to use by the agro based economy countries in terms of long term prediction. In this research work, a rainfall prediction model has been developed which uses K-Means clustering and artificial neural networks to fulfill the purpose. Artificial Neural Networks has been one of the major soft computing techniques used for the rainfall prediction since they are considered as one of the best function approximators. However, artificial neural networks have two issues which limit its applications, the computation complexity of the network and the learning time. In order to deal with these two issues, K-means clustering has been used in this work. Firstly, the data samples in this work are clustered using K means which cluster the samples according to their features. The number of clusters K has been computed using the Silhouette method. The clustered data samples are then used for training, validation and testing of different radial basis function neural networks. The results obtained from this method were then compared to the results obtained by only using a radial basis function neural network. For the comparison purpose, statistical criteria like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Nash-Sutcliffe model efficient coefficient (E) and Correlation Coefficient (R) were used. It was observed that the results obtained by this method (R= 0.94587, E=0.90148) were better than only using RBFNN (R= 0. 88015, E=0. 82159).

Weather prediction is a very old practice and people are doing predictions about weather much before the discovery of the weather measuring instrument. In ancient times, people give weather predictions by observing the sky for a long time and patterns of the stars at night. Things are a bit different now. People more relay on the past trends and patterns followed by the weather parameters. Data mining and machine leaning is used to analysis the historical weather trends by analyzing weather data using various Data mining techniques. In this paper three rainfall prediction model based on data mining techniques are proposed and compared with the other rainfall prediction model. The comparison has been done on the basis of accuracy, precision, Recall and RMSE. The proposed models are based on ensemble methods such as bagging, boosting, and stacking. Ensemble methods are used to enhance the overall performance and accuracy of the prediction. In both bagging and boosting based proposed rainfall prediction models, artificial neural network is used as a base leaner and daily weather data from the year 1988 to 2022 is used. In stacking based proposed rainfall prediction model, random forest, Logistic regression, and K-Nearest neighbor are used as base leaners or level -0 learners and Artificial neural network is used as Meta model.

A study was conducted to develop a stochastic time series model for prediction of annual rainfall and runoff in Manshara watershed of lower Gomati catchment. This is one of the sub-watersheds of lower Gomati catchment and has anareaofll.18 km2• The developed model is based on 13 years data from 1991 to 2003. Autoregressive (AR) model of order 0, 1 and 2 proposed by Kottegoda and Horder (1980) were tried. The goodness off it and adequacy of models were tested by Box-Pierce Portmonteau test, Akaike Information Criterion (AlC) and various statistical characteristics viz., Mean Forecast Error (MFE), Mean Absolute Error (MAE), Mean Relative Error (MRE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and Integral Square Error (lSE). Based on the results, it was concluded that AR (1) model can be effectively used for prediction of rainfall and runoff in Manshara watershed.

An optimum ANN-based breast cancer diagnosis: Bridging gaps between ANN learning and decision-making goals

The paper presents the use of an artificial neural network in sensors application. The task is to determine the volume of the chamber. The tests were performed on a model of a chamber in a mechanical prosthetic heart. In the considered task the surface of the diaphragm is observed by a near-infrared band camera. The artificial neural network was used to determine the relationship between the real views of the diaphragm and stroke volume. The artificial neural network learning process and research results are presented in the article.