Efficient Prediction Model Research Articles

Development of hybrid computational data-intelligence model for flowing bottom-hole pressure of oil wells: New strategy for oil reservoir management and monitoring

Among several metric parameters concerning the assessment of oil and gas well production, the flowing bottom-hole pressure (FBHP) is considered essential. Accurate prediction of FBHP is crucial for petroleum engineering and management. Several related parameters are associated with the FBHP magnitude influence; thus, proper inspection of those parameters is another vital concern. This research proposes a hybrid modeling framework based on the hybridization of machine learning (ML) models (i.e., Extreme Learning Machine (ELM), Support Vector Machine Regressor (SVR), Extreme Gradient Boosting (XGB), and Multivariate Adaptive Regression Spline (MARS)) and nature-inspired Differential Evolutional (DE) optimization for FBHP prediction. The adjustment of the internal parameters of the ML-based models and the input feature selection is formulated as an incremental learning problem that is solved by the evolutionary algorithm. Problem-specific samples were collected from the open-source literature for this investigation. Modeling results are adaptable, automatically determining the most relevant variables for the context of the ML model. The adaptive polynomial structure of hybridized MARS model attained the best average performance for the FBHP modeling with correlation (R = 0.94) and minimum root mean square (RMSE = 97.88). The proposed modeling framework produces an alternative efficient computer aid model for FBHP prediction, resulting in reliable automated technology to assist oil and gas well management.

An efficient energy prediction model for solar energy power system using Artificial Intelligence technique

Prediction of Solar power generation plays an important role to improve the efficiency ofeconomic dispatch function and reduce the dependence on fossil fuels and help in the energy managementsystem. For time series solar energy prediction multiple models were introduced but these model trains arebased on yearly historical data. A big data collection containing many missing values makes these modeltraining more complicated that’s why In this paper, an efficient energy prediction model is proposed for theprediction of time series solar energy based on short predicted weather training data. Two complimentarymodels are based on linear regression and a knowledge based neural network is exploited to predict futuresolar power, with offline training. The LR is structured under the direction of the proposed input methodparameter selection and used when training data is enough. KBNN is used for existing advantagespredictive models are also very important when training data is not enough. According to test findings usingreal data sets. An LR model can deal effectively with linear data, but a KBNN model can cope effectivelywith nonlinear behavior. Additionally, the results demonstrate the effectiveness of LR showing a correlationcoefficient (R2) is 98% with a root mean square error of 45 and KBNN shows a correlation coefficient (R2)is 99% with a root mean square error of 44 in providing a reliable version, The results additionally showthe functionality of LR and KBNN in imparting a dependable version, especially when the short trainingdataset is available.

Supercritical water gasification of organic solid waste: H2 yield and cold gas efficiency optimization considering modeling uncertainties

Supercritical water gasification (SCWG) is one of the typical hydrothermal treatment technologies for organic solid waste. However, the current SCWG optimization methods perform deterministic optimization without considering the uncertainty of the model for calculating the objective function, which leads to low reliability of the optimization results. Therefore, an optimization framework that considers the prediction uncertainties of SCWG data-driven models is proposed to optimize the H2 yield and cold gas efficiency of organic solid waste SCWG. An ensemble prediction model integrating random forest, gradient boosting regression, and K-nearest neighbor algorithms by the stacking learning method are built to predict SCWG gas yields. The cold gas efficiency prediction model is constructed based on the gas yield prediction models. The SCWG optimization models are constructed by combining the H2 yield and cold gas efficiency prediction models. The uncertainties in the H2 yield and cold gas efficiency prediction models are analyzed and integrated into the optimization models. The case studies were conducted to test the proposed framework. The optimization results were verified by the results of similar experimental conditions. It demonstrates that the proposed framework can obtain the robust results of the organic solid waste SCWG optimization, which can provide a reference for SCWG optimization.

Hybrid Deep Learning Model for Sarcasm Detection in Indian Indigenous Language Using Word-Emoji Embeddings

Automated sarcasm detection is deemed as a complex natural language processing task and extending it to a morphologically-rich and free-order dominant indigenous Indian language Hindi is another challenge in itself. The scarcity of resources and tools such as annotated corpora, lexicons, dependency parser, Part-of-Speech tagger, and benchmark datasets engorge the linguistic challenges of sarcasm detection in low-resource languages like Hindi. Furthermore, as context incongruity is imperative to detect sarcasm, various linguistic, aural and visual cues can be used to predict target utterance as sarcastic. While pre-trained word embeddings capture the meanings, semantic relationships and different types of contexts in the form of word representations, emojis can also render useful contextual information, analogous to human facial expressions, for gauging sarcasm. Thus, the goal of this research is to demonstrate the use of a hybrid deep learning model trained using two embeddings, namely word and emoji embeddings to detect sarcasm. The model is validated on a Hindi tweets dataset, Sarc-H, manually annotated with sarcastic and non-sarcastic labels. The preliminary results clearly depict the importance of using emojis for sarcasm detection, with our model attaining an accuracy of 97.35% with an F-score of 0.9708. The research validates that automated feature engineering facilitates efficient and repeatable predictive model for detecting sarcasm in indigenous, low-resource languages.

Deep learning predictions of unsteady aerodynamic loads on an airfoil model pitched over the entire operating range

For the design and certification of wind turbines, it is essential to provide fast and accurate unsteady aerodynamic load prediction models for the whole operational range of angle of attack, up to 180° for vertical-axis and 90° for horizontal-axis wind turbines. This work describes a computationally efficient unsteady forces prediction model based on a deep learning approach, namely the bidirectional long short-term memory (BiLSTM) algorithm, for an airfoil pitched over the full operational range of angles of attack up to 180°. No model has been developed to capture the unsteady forces at high angles of attack. Novel features based on operating conditions and the steady polars of the airfoil are used as inputs for the BiLSTM model. Direct measurements of steady and unsteady forces on a NACA 0021 airfoil model were conducted at reduced frequencies up to 0.075 and a Reynolds number of 120 000 in an open-jet wind tunnel for model learning and testing. The unsteady forces vary significantly from the steady values at high pitching amplitudes and post-stall angles, which, if not accounted for when simulating wind turbine performance, would result in inaccurate predictions. Furthermore, measurements revealed the effect of unsteady vorticity development and shedding on aerodynamic forces under forward and reverse flow conditions. The BiLSTM model is capable of capturing the underlying physics of unsteady aerodynamic forces under extreme operating conditions.

An Efficient Wireless Propagation Loss Prediction Model Based on 3-D Terrain Features Extracted by Deep Learning

This paper proposes a path loss prediction method based on convolutional neural network (CNN) by extracting features such as terrain obstacles and building distribution. 20 prediction tasks are carried out for different configurations of wave propagation mode, the number and height distribution of buildings and whether there is blocking effect, and a good accuracy is achieved. Meanwhile, the prediction time cost of the CNN and that of ray tracing are comprehensively compared, and in general the CNN has stable and higher computing efficiency. It can be seen that the CNN has greater advantages when dealing with complex environments and multiple propagation mechanisms by processing topographic maps attributed to its better feature extraction and generalization capabilities.

From spectra to plant functional traits: Transferable multi-trait models from heterogeneous and sparse data

Large-scale information on several vegetation properties (‘plant traits’) is critical to assess ecosystem functioning, functional diversity and their role in the Earth system. Hyperspectral remote sensing of plant canopies offers a key tool to map multiple plant traits. However, we are still lacking generalized methods to translate hyperspectral reflectance into a suite of relevant plant traits across biomes, land cover and sensor types. The absence of globally representative data sets and the gap between the available reflectance data with corresponding in-situ measurements have hampered such approaches. In recent years, the scientific community acquired multiple data sets encompassing canopy hyperspectral reflectance and plant traits from different plant types and sensors. To combine these heterogeneous data sets, we propose three multi-trait modeling approaches based on Convolutional Neural Networks (CNNs) to simultaneously infer a broad set of 20 structural and chemical traits (e.g. leaf mass per area, leaf area index, pigments, nitrogen). The performance of these multi-trait CNN models predicting these traits was compared against single-trait CNN as well as single-trait partial least squares regression (PLSR). We found that the multi-trait CNNs performances significantly increased from single-trait CNNs (nRMSE = 0.027–19.61%) and the state-of-the-art PLSR models (nRMSE = 1.94–40.07%) across a broad range of vegetation types (crops, forest, tundra, grassland, shrubland) and sensor types. Thus, providing a single model for multiple traits not only proved to be computationally more efficient, but also more accurate, since it enabled the model to incorporate traits' co-variation. Despite the data heterogeneity of the merged data set, our models performances' were comparable or exceeded those of previous studies. Overall, this study highlights the potential of weakly supervised approaches to overcome the scarcity of in-situ measurements and take a step forward in creating efficient predictive models of multiple biochemical and biophysical vegetation properties.

Deep learning based an efficient hybrid prediction model for Covid-19 cross-country spread among E7 and G7 countries

The COVID-19 pandemic has caused the death of many people around the world and has also caused economic problems for all countries in the world. In the literature, there are many studies to analyze and predict the spread of COVID-19 in cities and countries. However, there is no study to predict and analyze the cross-country spread in the world. In this study, a deep learning based hybrid model was developed to predict and analysis of COVID-19 cross-country spread and a case study was carried out for Emerging Seven (E7) and Group of Seven (G7) countries. It is aimed to reduce the workload of healthcare professionals and to make health plans by predicting the daily number of COVID-19 cases and deaths. Developed model was tested extensively using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and R Squared (R2). The experimental results showed that the developed model was more successful to predict and analysis of COVID-19 cross-country spread in E7 and G7 countries than Linear Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). The developed model has R2 value close to 0.9 in predicting the number of daily cases and deaths in the majority of E7 and G7 countries.

Sales Prediction Optimization via Gradient Boosting Decision Tree

Sales prediction is always a top priority for brands, effectively reducing unnecessary waste under the essential circumstance that all customers’ needs have been met. With an efficient prediction model, brands can make accurate inventory decisions and get a significant increase in profit. This paper provides an efficient sales prediction model for cross-border e-commerce companies with Gradient Boosting Decision Tree. We use the sales volume in the past months, their statistical characteristics, difference characteristics and month on month characteristics as the characteristics we choose. We use the Mean Absolute Percentage Error perimeter to compare the accuracy of our method with the Moving Average Method to assess the performance of our model. The results show that our iterative model has higher accuracy compared to the Moving Average Method. It also has a significant edge in both automation and analyzing big-scale data sets, which means that it solves the low feasibility of existing methods. On this basis, we finally conclude that our machine learning model can make great contributions to sales prediction.

Accuracy enhancement of laser-induced breakdown spectroscopy by polarization spectrum fusion

Laser-induced breakdown spectroscopy (LIBS) has been proven to be an effective way for online analysis of coal properties (such as ash content, volatile content, and calorific value), but the quantitative analysis accuracy still needs to be improved. Herein, a polarization spectral data fusion scheme was proposed to obtain more abundant spectral information and improve the performance of quantitative analysis models. First, the polarization effect of laser-induced coal plasma emission was analyzed using the Stokes parameters of the average spectra. Due to the partially polarized phenomenon of emission, fused data of PRLIBS (0°, 0) (horizontal plasma polarization spectra) and PRLIBS (90°, 0) (vertical plasma polarization spectra) was utilized to establish an efficient prediction model to obtain high prediction accuracy. For fusion models, the root mean square error prediction (RMSEP) of ash content, volatile content and calorific values were 1.497%, 0.595%, and 0.597%, respectively, and the coefficients of determination (R2) were 0.980, 0.968, and 0.978, respectively. Comparison with regression models for individual PRLIBS (0°, 0), PRLIBS (90°, 0), and LIBS data, the data fusion scheme significantly improved the performance of the prediction model. The improvement in model performance is due to the fact that there is no perfect correlation between PRLIBS (0°, 0) and PRLIBS (90°, 0), whilst polarization spectral fusion makes it possible to acquire more number of characteristic spectral lines with high importance score. The results demonstrated the feasibility of PRLIBS spectral fusion to provide better analytical results for ash content, volatile content, and calorific values of coal.

A Modified Grey Wolf Optimizer algorithm for feature selection to predict heart diseases

Globally, heart disease is a leading cause of illness and mortality. This impacts people from all around the world. Accurate prediction of the risk of heart disease is crucial for early detection and prevention.For this, large amounts of features/attributes need to be stored and analyzed to diagnose a patient. Storing many features can lead to substandard management of data. We need to store only the chief features. In this study, we proposed a modified grey wolf optimizerfor feature selection.The resultant subset of features is then used to predict the risk of having a heart disease using machine learning model, Support Vector Machine (SVM). We compared the proposed algorithm with the existing GWO-SVM algorithm. We evaluated the effectiveness of the proposed algorithm using accuracy, sensitivity, and specificity metrics. Our results show that, using the modified grey wolf algorithm for feature selection and using SVM weobtained an accuracy of 95.82%, specificity of 94.64%, and sensitivity of 96.86%. The results show the proposed algorithm's capability for predicting the risk of heart disease and could contribute to the development of more accurate and efficient predictive models for heart disease risk assessment.

A novel framework combining production evaluation and quantification of development parameters for shale gas wells

Accurate prediction of estimated ultimate recovery (EUR) and quantification of important engineering and geological parameters play a decisive role in production parameter optimization and investment decision of shale gas wells. This study proposes an integrated learning framework for EUR prediction and production parameter quantification in shale gas wells using CatBoost algorithm. CatBoost is designed to identify complex relationships efficiently and accurately between geological and engineering parameters and target values EUR. Furthermore, the EUR prediction model based on CatBoost was used to identify important features. Various machine learning interpretation methods are used to visualize the marginal effects of important and interesting features in an attempt to optimize production parameters by quantifying the features. Experiments are conducted to evaluate the performance of the proposed the integrated learning framework in the deep shale gas well data set of Luzhou block in Sichuan Basin, China. Results demonstrate that compared with other mainstream ensemble learning algorithms, the proposed EUR prediction model based on CatBoost algorithm performs well on small data sets, with a prediction error of only 12.31%. The post-interpretation tool of the model was used to find out four important characteristics affecting EUR in Luzhou block, namely, contents of brittle minerals, fracturing length, porosity and fracturing section. The optimal combination of geological and engineering parameters for the block to maximize EUR is identified by using the established efficient and accurate EUR prediction model as input and the visualization of the marginal effects of the features of interest as output. This work can effectively provide guidance for EUR prediction and production parameter optimization of shale gas wells.

Shear Strength Prediction of Slender Concrete Beams Reinforced with FRP Rebar Using Data-Driven Machine Learning Algorithms

Estimating the shear strength of a fiber-reinforced polymer (FRP)–reinforced-concrete (RC) beam is a complex task that depends on multiple design variables. The use of FRP bars has emerged as a promising alternative to diminish the corrosion problems that are associated with steel reinforcement in adverse environments; however, an accurate and reliable method of shear strength prediction is needed to ensure the economical use of materials and robust designs. Several optimized design equations are available in the literature; however, when utilizing these equations a substantial difference is observed between the predicted outcome (Vpred) and the experimental shear strength (Vexp) result. Therefore, this paper presented a novel approach toward implementing machine learning (ML) algorithms to accurately estimate the shear strength of FRP–RC beams. A large database that consisted of 302 shear test results on FRP-reinforced slender concrete beams without stirrup was collected from the literature to formulate the most efficient prediction model. The performance of each ML algorithm model was compared with the existing design provisions and models. The model interpretation was performed through feature importance analysis to explain the model output compared with a black box. The proposed data-driven ML models demonstrated a high level of accuracy and excellent performance and were superior to the existing shear strength models. In addition, a simple graphical user interface (GUI) was developed to aid practicing engineers when estimating shear strength without the need for complicated design procedures.

An efficient Bayesian network model (BNM) for software risk prediction in design phase development

An efficient Bayesian network model (BNM) for software risk prediction in design phase development

Trustworthy Deep Neural Network for Inferring Anticancer Synergistic Combinations.

The lack of a gold standard synergy quantification method for chemotherapeutic drug combinations warrants the consideration of different synergy metrics to develop efficient predictive models. Furthermore, neglecting combination sensitivity may lead to biased synergistic combinations, which are ineffective in cancer treatment. In this paper, we propose a deep learning-based model, SynPredict, which effectively predicts synergy in five synergy metrics together with the combination sensitivity score. SynPredict assesses the impact of multimodal fusion architectures of the input data, including the gene expression data of cancer cells, along with the representative chemical features of drugs in pairwise combinations. Both ONEIL and ALMANAC anticancer combination datasets are employed comparatively. The impact of the training datasets was more significant and consistent across most synergy models than input data fusion architectures. Synpredict outperforms the state-of-the-art predictive models, including DeepSynergy, AuDNN synergy, TranSynergy and DrugComb, with up to 74% decline in the mean square error. We highlight the pivotal need to consider a multiplex of synergy metrics and the combined sensitivity in the predictive models.

Prediction of NO concentration using modular long short-term memory neural network for municipal solid waste incineration

Air pollution control poses a major problem in the implementation of municipal solid waste incineration (MSWI). Accurate prediction of nitrogen oxides (NOx) concentration plays an important role in efficient NOx emission controlling. In this study, a modular long short-term memory (M-LSTM) network is developed to design an efficient prediction model for NOx concentration. First, the fuzzy C means (FCM) algorithm is utilized to divide the task into several sub-tasks, aiming to realize the divide-and-conquer ability for complex task. Second, long short-term memory (LSTM) neural networks are applied to tackle corresponding sub-tasks, which can improve the prediction accuracy of the sub-networks. Third, a cooperative decision strategy is designed to guarantee the generalization performance during the testing or application stage. Finally, after being evaluated by a benchmark simulation, the proposed method is applied to a real MSWI process. And the experimental results demonstrate the considerable prediction ability of the M-LSTM network.

Gaussian process regression-based load-carrying capacity models of corroded prestressed concrete bridge girders for fast-screening and reliability-based evaluation

Fast screening and reliability-based evaluation of corroded prestressed concrete (PC) bridge girders for safety assessment requires efficient capacity prediction models. This paper aims at developing data-based prediction models to quantify corrosion effects on load-carrying capacity of PC girders that are precast and standardized for short-span bridges. The load-carrying capacity of corroded bridge girders depends on their initial design configuration (e.g., those characterized by the standardized PC girders), loading condition (e.g., shear-span-to-effective-depth ratio), and corrosion conditions (e.g., corrosion degree). To develop data-based prediction models, generating sufficient data through physical experimental tests of full-scale corroded PC girders is prohibitively costly. Thus, a virtual experimental database is generated numerically using two-dimensional continuum-based finite element (FE) models for corroded PC girders, after being validated using 9 corroded PC girders tested in the literature with flexure or shear failure. To this end, a total of 4,165 PC girders under point loading are simulated to consider various design, loading, and corrosion conditions to estimate their load-carrying capacities. With this database, probabilistic machine learning, specifically Gaussian process regression or kriging, is used to develop (1) a residual capacity factor model (i.e., the ratio between load-carrying capacities from corroded and uncorroded girders), and (2) a load-carrying capacity prediction model (i.e., to predict the load-carrying capacity of uncorroded/corroded girders). The first model is used to study the load-carrying capacity reduction of PC girders due to corrosion compared to their uncorroded counterparts; this can reveal how the increasing corrosion condition affects the load-carrying capacity of corroded PC girders together with other design and loading parameters. The second model is developed to predict the load-carrying capacity of corroded PC girders as a function of design, loading, and corrosion parameters; its application to conditional reliability analysis provides insights into corrosion effect on the probability of failure of corroded PC girders at given load levels when the capacity is affected by corrosion. The application results of the two models enable engineers to quantify the corrosion effect on PC girders in terms of (1) reduction in load-carrying capacity for fast screening and (2) increase in probability of failure for reliability-based evaluation.

Earthquakes magnitude prediction using deep learning for the Horn of Africa

Earthquakes are vibrations of the Earth's surface that can cause ground shaking, fires, tsunamis, landslides and fissures. These natural phenomena can cause destruction and kill lives. When there is a possibility of an earthquake, an accurate prediction can save lives and avoid infrastructure damage. Due to the probabilistic nature of an earthquake occurring and the challenge of achieving an efficient and dependable model for an earthquake prediction, efforts to predict earthquakes have been met with mixed results. Therefore, new methods are constantly sought. A deep learning-based technique, specifically a transformer algorithm, was applied to predict earthquake magnitudes using available data for the Horn of Africa. The problem was formulated as multi-variant time series regression, and predictions were made for earthquakes magnitudes greater than or equal to 3 for the next three months. A comparison of the results was made with the output obtained from long short-term memory (LSTM), bidirectional long short-term memory (BILSTM), and bidirectional long short-term memory with attention (BILSTM-AT) models. The results showed that the transformer model outperformed the other three models with 0.276, 0.147, 0.383, 28.868% mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE) and mean absolute percentage error (MAPE) respectively in predicting earthquake magnitudes in the Horn of Africa.

Prediction Models for Sleep Quality Among College Students During the COVID-19 Outbreak: Cross-sectional Study Based on the Internet New Media

COVID-19 has been reported to affect the sleep quality of Chinese residents; however, the epidemic's effects on the sleep quality of college students during closed-loop management remain unclear, and a screening tool is lacking. This study aimed to understand the sleep quality of college students in Fujian Province during the epidemic and determine sensitive variables, in order to develop an efficient prediction model for the early screening of sleep problems in college students. From April 5 to 16, 2022, a cross-sectional internet-based survey was conducted. The Pittsburgh Sleep Quality Index (PSQI) scale, a self-designed general data questionnaire, and the sleep quality influencing factor questionnaire were used to understand the sleep quality of respondents in the previous month. A chi-square test and a multivariate unconditioned logistic regression analysis were performed, and influencing factors obtained were applied to develop prediction models. The data were divided into a training-testing set (n=14,451, 70%) and an independent validation set (n=6194, 30%) by stratified sampling. Four models using logistic regression, an artificial neural network, random forest, and naïve Bayes were developed and validated. In total, 20,645 subjects were included in this survey, with a mean global PSQI score of 6.02 (SD 3.112). The sleep disturbance rate was 28.9% (n=5972, defined as a global PSQI score >7 points). A total of 11 variables related to sleep quality were taken as parameters of the prediction models, including age, gender, residence, specialty, respiratory history, coffee consumption, stay up, long hours on the internet, sudden changes, fears of infection, and impatient closed-loop management. Among the generated models, the artificial neural network model proved to be the best, with an area under curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 0.713, 73.52%, 25.51%, 92.58%, 57.71%, and 75.79%, respectively. It is noteworthy that the logistic regression, random forest, and naive Bayes models achieved high specificities of 94.41%, 94.77%, and 86.40%, respectively. The COVID-19 containment measures affected the sleep quality of college students on multiple levels, indicating that it is desiderate to provide targeted university management and social support. The artificial neural network model has presented excellent predictive efficiency and is favorable for implementing measures earlier in order to improve present conditions.

An efficient landmark model for prediction of suicide attempts in multiple clinical settings

Growing evidence has shown that applying machine learning models to large clinical data sources may exceed clinician performance in suicide risk stratification. However, many existing prediction models either suffer from “temporal bias” (a bias that stems from using case-control sampling) or require training on all available patient visit data. Here, we adopt a “landmark model” framework that aligns with clinical practice for prediction of suicide-related behaviors (SRBs) using a large electronic health record database. Using the landmark approach, we developed models for SRB prediction (regularized Cox regression and random survival forest) that establish a time-point (e.g., clinical visit) from which predictions are made over user-specified prediction windows using historical information up to that point. We applied this approach to cohorts from three clinical settings: general outpatient, psychiatric emergency department, and psychiatric inpatients, for varying prediction windows and lengths of historical data. Models achieved high discriminative performance (area under the Receiver Operating Characteristic curve 0.74–0.93 for the Cox model) across different prediction windows and settings, even with relatively short periods of historical data. In short, we developed accurate, dynamic SRB risk prediction models with the landmark approach that reduce bias and enhance the reliability and portability of suicide risk prediction models.