Prediction Accuracy Of Model Research Articles

Prediction and optimization framework of shear strength of reinforced concrete flanged shear wall based on machine learning and non-dominated sorting genetic algorithm-II

Reinforced concrete (RC) flanged shear wall has good lateral strength and stiffness, which has been widely used in building structures. Due to the coupling effect of many factors such as wall section shape, shear span ratio, so the shear performance evaluation of flanged wall is still very limited. This paper proposed a prediction framework for the shear capacity of RC flanged shear walls. A database containing 14 input variables, 1 output variable and 153 samples was constructed to evaluate the prediction accuracy of 11 existing design methods. The Pearson coefficient was used to preliminarily analyze the correlation between variables. The grid search was used to optimize the hyperparameters of 4 machine learning models, and six statistical indicators ( R2, R, RMSE, SD, MAE, and MAPE) were used to comprehensively compare the prediction results of the ML models to determine the best model. On this basis, SHapley Additive exPlanations (SHAP) was used to enhance the interpretability of the prediction models, and the mechanism of the input variables on the shear capacity was quantified. A graphical user interface (GUI) was proposed to guide the engineering design. A multi-objective model (MOO) was established to analyze the trade-off between shear performance and cost, thereby determining the best optimal scheme. The results show that the prediction accuracy of the ML models is better than the existing design methods. The XGB model has the best prediction performance, with R2, R, RMSE are 0.99, 0.99, 118.96, respectively. The SHAP method can effectively enhance the interpretability of the ML models, and tw, lw and f ′c are the key parameters affecting the shear capacity of the flanged shear wall.

Chemical-guided screening of top-performing metal–organic frameworks for hydrogen storage: An explainable deep attention convolutional model

Metal-organic framework (MOF)-based adsorptive hydrogen storage holds promise for enhancing the sustainable design of hydrogen storages by enhancing the usable volumetric (UV) and gravimetric (UG) capacities. However, the extensive number of MOFs poses a challenge in the search for optimal materials owing to the lack of an efficient and interpretable high-throughput screening method. This study introduces an explainable artificial intelligence (XAI) framework to expedite the discovery of high-capacity hydrogen adsorbents by predicting the UV and UG capacities using an attention densely connected convolutional (ADCC) network. A new hybrid dataset with various operating conditions and comprising 24 physical–chemical descriptors, such as void fraction (VF) and metal percentage (MP), was utilized to develop the ADCC model. The explainable ADCC model demonstrated superior predictive performance for the UV and UG capacities, with R2 values of 0.9886 and 0.9982, respectively. The inclusion of the chemical descriptors MOFs enhanced the prediction accuracy of the ADCC model. The XAI analysis showed that VF and MP dominated physical and chemical descriptors, respectively, for UV and UG. Consequently, the ADCC model identified EFAYIU—a real MOF—as a promising hydrogen storage material with UV and UG capacities of 51.55 g H2/L and 11.37 wt%, respectively, surpassing the current materials for hydrogen storage. Additionally, the identified EFAYIU was validated based on molecular simulations, confirming the high hydrogen adsorptive capacities obtained by the ADCC model. Thus, the proposed AI-based high-throughput screening method enables the rapid discovery of high-performance MOFs for sustainable hydrogen storage.

Refrigerant charge estimation method based on data-physic hybrid-driven model for the fault diagnosis of transcritical CO2 heat pump system

The transcritical CO2 heat pump system is a promising and excellent heating scheme. However, the operating pressure of the transcritical CO2 heat pump system is high, and refrigerant leakage is a frequent problem. It is worth noting that the operating principle of CO2 heat pump systems is unique. Thus, conventional refrigerant charge estimation methods for subcritical systems cannot be directly applied to transcritical systems. In this study, a novel refrigerant charge estimation method for the transcritical CO2 heat pump system is proposed. Based on the heat and mass transfer characteristics of the transcritical system, the grey box model constrained by physical laws is constructed. Based on the machine learning algorithm, the correction model of the grey box model is built. The hybrid model combines the advantages of the high generalization ability of the physic-driven model and the nonlinear fitting ability of the data-driven model. The results show that the novel estimation method can accurately predict the refrigerant charge, enabling fault diagnosis of refrigerant leakage. The data-driven correction model can improve the prediction accuracy of the grey box model. The Mean Relative Error of the hybrid-driven model can be controlled within 5 %.

Effective Outlier Detection for Ensuring Data Quality in Flotation Data Modelling Using Machine Learning (ML) Algorithms

Froth flotation, a widely used mineral beneficiation technique, generates substantial volumes of data, offering the opportunity to extract valuable insights from these data for production line analysis. The quality of flotation data is critical to designing accurate prediction models and process optimisation. Unfortunately, industrial flotation data are often compromised by quality issues such as outliers that can produce misleading or erroneous analytical results. A general approach is to preprocess the data by replacing or imputing outliers with data values that have no connection with the real state of the process. However, this does not resolve the effect of outliers, especially those that deviate from normal trends. Outliers often occur across multiple variables, and their values may occur in normal observation ranges, making their detection challenging. An unresolved challenge in outlier detection is determining how far an observation must be to be considered an outlier. Existing methods rely on domain experts’ knowledge, which is difficult to apply when experts encounter large volumes of data with complex relationships. In this paper, we propose an approach to conduct outlier analysis on a flotation dataset and examine the efficacy of multiple machine learning (ML) algorithms—including k-Nearest Neighbour (kNN), Local Outlier Factor (LOF), and Isolation Forest (ISF)—in relation to the statistical 2σ rule for identifying outliers. We introduce the concept of “quasi-outliers” determined by the 2σ threshold as a benchmark for assessing the ML algorithms’ performance. The study also analyses the mutual coverage between quasi-outliers and outliers from the ML algorithms to identify the most effective outlier detection algorithm. We found that the outliers by kNN cover outliers of other methods. We use the experimental results to show that outliers affect model prediction accuracy, and excluding outliers from training data can reduce the average prediction errors.

Predicting Consumer Behaviour from E-Commerce Platform Product Reviews: A Machine Learning Approach to Sentiment Analysis

Given the recent advancements in web technology, users make use of the online services and offer their feedback thereby creating a vast amount of data available on the internet. To enable improved decision-making, it is essential to study, analyze, and organize this vast amount of user opinion, perspectives, feedback, and suggestions available through online resources. Nevertheless, the majority of e-commerce websites encounter challenges in comprehensively analyzing each individual review owing to the sheer volume of user feedback they receive. The aim of this study is to conduct sentiment analysis of product review from e-commerce platforms using machine learning to predict consumer behaviour so as to make informed decision. The methodology used was a sentiment analysis using models developed in Python with machine learning algorithms (Support Vector Machine and Naive Bayes) in order to compare the performance accuracy. The model was trained and tested on a dataset, and the performance of the two supervised machine learning algorithms for sentiment classification was compared. Accordingly, the results of the experiment showed that the Support Vector Machine technique outperformed Naive Bayes, obtaining accuracy levels of 97%. The study also demonstrates the significance of carrying out further research by exploring different machine-learning techniques and evaluating their performance on local market datasets. Additionally, it was observed that utilizing more data might improve the model's classification and prediction accuracy.

Prediction of the fluoride contents of different crop species via the random forest algorithm.

Fluoride (F) is a trace element that is essential to the human body and occurs naturally in the environment. However, a deficiency or excess of F in the environment can potentially lead to human health issues. The pseudototal amount of F in soil often does not correlate directly with the F content in plants. Instead, the F content within plants tends to have a greater correlation with the bioavailable F in soils. In large-scale soil surveys, only the pseudototal elemental content of soils is typically measured, which may not be highly reliable for developing agricultural zoning plans. There are significant variations in the ability of different plants to accumulate F from soil. Additionally, due to variations in soil elemental absorption mechanisms among different plant species, when multiple crops are grown in an area, it is typically necessary to study the elemental absorption mechanisms of each crop. To address these issues, in this study, we examined the factors influencing F bioaccumulation coefficients in different crops based on 1:50,000 soil geochemical survey data. Using the random forest algorithm, four indicators-bioavailable P, bioavailable Zn, leachable Pb, and Sr-were selected from among 29 parameters to predict the F content within crops to replace bioavailable F in the soil. Compared with the multivariate linear regression (MLR) model, the random forest (RF) model provided more accurate and reliable predictions of the fluoride content in crops, with the RF model's prediction accuracy improving by approximately 95.23%. Additionally, while the partial least squares regression (PLSR) model also offered improved accuracy over MLR, the RF model still outperformed PLSR in terms of prediction accuracy and robustness. Additionally, it maximized the utilization of existing geochemical survey data, enabling cross-species studies for the first time and avoiding redundant evaluations of different types of agricultural products in the same region. In this investigation, we selected the Xining-Ledu region of Qinghai Province, China, as the study area and employed a random forest model to predict the crop F content in soils, providing a new methodological framework for crop production that effectively enhances agricultural quality and efficiency.

Quantification and prediction of furnace cylinder activity based on LASSO-GWO-CNN hybrid model

Blast furnace smelting environments are complex and characterised by multi-scale, non-linear and strong coupling, and it is often difficult for operators to detect changes in cylinder activity in a timely manner. Quantifying the cylinder activity is the basis for monitoring and improving the cylinder activity. Aiming at the traditional method of quantifying the cylinder activity, which relies heavily on a single empirical formula and is difficult to realise the prediction effect of the cylinder activity, this paper proposes a new method of quantitatively characterising the cylinder activity by combining the core dead material column temperature index and the dead material pile cleanliness index, which comprehensively takes into account the thermodynamic and kinetic characteristics of the cylinder, and is able to more accurately and comprehensively assess the state of the cylinder activity. Firstly, a new quantitative cylinder activity formula is set according to the combined index, in which the weights of the indexes will be gradually adjusted in the iterative process of the model, and the entropy weighting method is adopted for its operation; a hierarchical affiliation function is established, and the calculation of the affiliation is used to judge the degree of contribution of the new indexes to the active state of the furnace cylinder with different weights in order to assist in finalising the final weights of the indexes, and the final weights of the indexes are then validated through the analysis of the calculation examples. Afterwards, the rationality of the final weights and the effectiveness of the proposed quantisation method are verified through case analysis. Finally, the LASSO algorithm is used to filter the feature variables, and the Grey Wolf Optimisation (GWO) optimised Convolutional Neural Network (CNN) based cylinder activity prediction model is proposed. According to the results of the comparative validation between five different prediction models, the prediction accuracy of the GWO-CNN model reaches more than 90%, which indicates that the model has a higher prediction performance in predicting the furnace cylinder activity.

Data‐Driven Modeling and High‐Precision Tracking Control of a Soft Continuum Manipulator: Enabling Robotic Sorting of Multiwire Cables

As a new class of robots, soft continuum manipulators have attracted attention due to their flexibility and compliance. However, these characteristics create challenges for precise modeling and control. This study proposes a hybrid offline and online data‐driven scheme to achieve high‐precision tracking control of a soft continuum manipulator. First, a novel multiscale deep neural network learns the manipulator model offline. Specifically, the feature fusion module extracts highly discriminative features and captures long‐term dependencies from the temporal trajectory data. The self‐attention module strengthens the ability to represent fusion features and enhances the model prediction accuracy. Then, the learnt model is updated using multisensor data online, and the proposed controller further compensates for the updated model and enhances the tracking accuracy in the movement stage. Finally, the experimental results demonstrate a significant improvement in motion accuracy under different trajectory‐tracking scenarios (i.e., deviations of <1 mm in position and <0.8° in orientation). The example of the multiwire cable sorting proves the feasibility of the proposed scheme in high‐precision industrial applications.

Predicting Ozone Concentration in Hangzhou with the Fusion Class Stacking Algorithm

Aiming at the problem that the single machine learning model has low prediction accuracy of daily average ozone concentration, an ozone concentration prediction method based on the fusion class Stacking algorithm （FSOP） was proposed, which combined the statistical method ordinary least squares （OLS） with machine learning algorithms and improved the prediction accuracy of the ozone concentration prediction model by integrating the advantages of different learners. Based on the principle of the Stacking algorithm, the observation data of the daily maximum 8h ozone average concentration and meteorological reanalysis data in Hangzhou from January 2017 to December 2022 were used. Firstly, the specific ozone concentration prediction models based on the light gradient boosting machine （LightGBM） algorithm, long short-term memory model （LSTM）, and Informer model were established, respectively. Then, the prediction results of the above models were used as meta-features, and the OLS algorithm was used to obtain the prediction expression of ozone concentration to fit the observed ozone concentration. The results showed that the prediction accuracy of the model combined with the class Stacking algorithm was improved, and the fitting effect of ozone concentration was better. Among them, R2, RMSE, and MAE were 0.84, 19.65 μg·m-3, and 15.50 μg·m-3, respectively, which improved the prediction accuracy by approximately 8% compared with that of the single machine learning model.

Characteristics of Vegetation and Soil of Degraded Grasslands and Their Relationships in Xizang

To investigate the characteristics of grassland degradation on a regional scale in Xizang, data on grassland degradation from the second grassland survey of Xizang and 12 vegetation and soil indicators from the National Tibetan Plateau Data Center were collected. Using ArcMap, 10 000 random sample points were selected on raster data （excluding non-grassland, desertification, and salinization data, leaving 7 949 valid sample points）. The multi-value extraction to-point method was applied to extract degradation and indicator data for each sample point. The characteristics of degraded grassland vegetation and soil and their relationships were analyzed in Xizang. Moreover, random forest modeling was conducted to predict the trend of grassland ecosystem changes. The results indicated that： ① The grasslands in Xizang were primarily composed of alpine steppe and alpine meadow types, accounting for 45.83% and 41.15% of the valid sample points, respectively. ② With the intensification of grassland degradation, the number of steppe-type species among the 17 grassland types gradually decreased, and the proportion of steppe dominated by species such as Stipa purpurea and Carex moorcroftii decreased, whereas the proportion of miscellaneous grasses and Dasiphora fruticosa increased. ③ As the degree of degradation increased, vegetation indicators generally showed a declining trend, with soil total nitrogen, total phosphorus, total potassium, and organic carbon decreasing, whereas soil pH and bulk density increased, and soil moisture content was not significant. ④ A positive correlation exists between soil moisture content, total nitrogen, total phosphorus, total potassium, organic carbon, vegetation cover, net primary productivity of vegetation, normalized difference vegetation index, aboveground biomass, and habitat quality. However, there was a negative correlation between pH and soil bulk density, and the correlation coefficients among various indicators decreased with the intensification of degradation. ⑤ The random forest simulation results showed that during the degradation process, the contribution rates of soil bulk density and habitat quality both exceeded 12%, with the model prediction accuracy reaching 78%. The study revealed that grassland degradation in Xizang was closely related to soil bulk density and habitat quality, indicating that higher soil bulk density or lower habitat quality may correspond to more severe grassland degradation. This provides a scientific basis for future grassland conservation and management.

Prediction Accuracy of Hyperelastic Material Models for Rubber Bumper under Compressive Load.

Different hyperelastic material models (Mooney-Rivlin, Yeoh, Gent, Arruda-Boyce and Ogden) are able to estimate Treloar's test data series containing uniaxial and biaxial tension and pure shear stress-strain characteristics of rubber. If the rubber behaviour is only determined for the specific load of the product, which, in the case of rubber bumpers, is the compression, the time needed for the laboratory test can be significantly decreased. The stress-strain characteristics of the uniaxial compression test of rubber samples were used to fit hyperelastic material models. Laboratory and numerical tests of a rubber bumper with a given compound and complex geometry were used to determine the accuracy of the material models. Designing rubber products requires special consideration of the numerical discretization process due to the nonlinear behaviours (material nonlinearity, large deformation, connections, etc.). Modelling considerations were presented for the finite element analysis of the rubber bumper. The results showed that if only uniaxial compression test data are available for the curve fitting of the material model, the Yeoh model performs the best in predicting the rubber product material response under compressive load and complex strain state.

A machine learning method based on TPE-XGBoost model for TRIP/TWIP near-β titanium alloy design

The traditional design method for TRIP/TWIP near-β titanium alloys is time-consuming and expensive. This paper proposes a machine-learning design method for a near-β titanium alloy that uses the Tree-structured Parzen Estimator (TPE) algorithm to optimize the hyperparameter space of XGBoost for improved model prediction accuracy in TRIP/TWIP. The model predicts the mechanical properties and plasticity mechanisms of the alloy based on its composition, key empirical parameters derived from the composition, and solution treatment temperature. The test results of the TPE-XGBoost model showed that when predicting the ultimate tensile strength (UTS), the adjusted determination coefficient (Adjusted R2), root mean square error (RMSE), and mean absolute error (MAE) values were 0.9264, 39.63 MPa and 44.83 MPa, respectively. When predicting elongation (El), the Adjusted R2, RMSE, and MAE values are 0.9134, 1.97 %, and 1.89 %, respectively. When predicting the plastic mechanisms of the alloy, the F1-score, Recall, Precision, Accuracy, and Area Under the ROC Curve (AUC) were 0.74, 0.75, 0.80, 0.78, and 0.83, respectively. A near-β titanium alloy, Ti-8V-4Mo-3.5Al-3Cr-2Zr (wt%), along with an associated heat treatment process, has been developed using this model. The experimental results have demonstrated that the model accurately predicts the strength, elongation, and plasticity mechanisms of the alloys. The TRIP/TWIP effects occur due to {332}<113> twinning and secondary α" martensite formation during tensile deformation. This study offers an alternative approach for designing TRIP/TWIP near-β titanium alloys.

Implicit Modality Knowledge Alignment and Uncertainty Estimation for visible-infrared person re-identification

Visible-infrared person re-identification (VI-ReID) is a crucial cross-modal matching task in computer vision. Existing research typically relies on a single auxiliary modality to address the semantic gap in cross-modal data, but this approach fails to fully exploit the information inherent in both modalities. To tackle this issue, we propose a novel framework called Implicit Modality Knowledge Alignment (IMKA) and Uncertainty Estimation (UE). This framework aims to enhance the robustness of the learned common embedding space and improve the prediction accuracy of the VI-ReID model. The IMKA module is designed to extract valuable supplementary information from the original modality data to generate implicit modality data. The SKA module then aligns the distribution of significant knowledge learned from this generated implicit modality data. Meanwhile, the UE strategy is implemented to mitigate the overconfidence in incorrect predictions. The uncertainty of predicted probabilities is evaluated in a Dirichlet space, and the designed evidence loss bolsters the confidence in uncertainty. This uncertain information can enhance retrieval performance. Extensive experimental results on two publicly available VI-ReID datasets demonstrate that our IMKA-UE framework significantly outperforms state-of-the-art methods. The code for our IMKA-UE framework is available at https://github.com/SWU-CS-MediaLab/IMKA-UE.

Simultaneously predicting SPAD and water content in rice leaves using hyperspectral imaging with deep multi-task regression and transfer component analysis.

Water content and chlorophyll content are important indicators for monitoring rice growth status. Simultaneous detection of water content and chlorophyll content is of significance. Different varieties of rice show differences in phenotype, resulting in the difficulties of establishing a universal model. In this study, hyperspectral imaging was used to detect the Soil and Plant Analyzer Development (SPAD) values and water content of fresh rice leaves of three rice varieties (Jiahua 1, Xiushui 121 and Xiushui 134). Both partial least squares regression and convolutional neural networks were used to establish single-task and multi-task models. Transfer component analysis (TCA) was used as transfer learning to learn the common features to achieve an approximate identical distribution between any two varieties. Single-task and multi-task models were also built using the features of the source domain, and these models were applied to the target domain. These results indicated that for models of each rice variety the prediction accuracy of most multi-task models was close to that of single-task models. As for TCA, the results showed that the single-task model achieved good performance for all transfer learning tasks. Compared with the original model, good and differentiated results were obtained for the models using features learned by TCA for both the source domain and target domain. The multi-task models could be constructed to predict SPAD values and water content simultaneously and then transferred to another rice variety, which could improve the efficiency of model construction and realize rapid detection of rice growth indicators. © 2024 Society of Chemical Industry.

Fusion of Multiple Data Sources for Vehicle Crashworthiness Prediction Using CycleGAN and Temporal Convolutional Networks

Abstract Computer-aided engineering (CAE) models play a pivotal role in predicting crashworthiness of vehicle designs. While CAE models continue to advance in fidelity, an inherent discrepancy between CAE model predictions and the responses of physical tests remains inevitable. Machine learning (ML) models have shown promising potential in improving the prediction accuracy of CAE models. Nevertheless, the scarcity of vehicle crash data poses a significant challenge for the training of such models. This paper overcomes these challenges by fusing multiple data sources from two different types of vehicles. More specifically, the Cycle-Consistent Generative Adversarial Neural networks (CycleGAN) are first employed to translate features of time-series test data from one domain to another using cycle consistency loss. Such a translation allows for the generation of synthetic crash test data for the second vehicle type by leveraging existing tests from both vehicle types. In parallel, an initial temporal convolutional network (TCN) model is trained using CAE simulation data and physical test data of the first vehicle type. This pre-trained TCN model is then fine-tuned using three sources of data from the second vehicle type, namely the CAE data, test data, and the augmented virtual test data generated using CycleGAN. Through these data fusion, the crashworthiness prediction accuracy of the second vehicle type can be improved. The proposed method is demonstrated by a real-world case study with a small-size SUV and a medium-size SUV. Results show enhancements in the predictive performance of the medium-size SUV model.

Road Passenger Load Probability Prediction and Path Optimization Based on Taxi Trajectory Big Data

This paper focuses on predicting road passenger probability and optimizing taxi driving routes based on trajectory big data. By utilizing clustering algorithms to identify key passenger points, a method for calculating and predicting road passenger probability is proposed. This method calculates the passenger probability for each road segment during different time periods and uses a BiLSTM neural network for prediction. A passenger-seeking recommendation model is then constructed with the goal of maximizing passenger probability, and it is solved using the NSGA-II algorithm. Experiments are conducted on the Chengdu taxi trajectory dataset, using MSE as the metric for model prediction accuracy. The results show that the BiLSTM prediction model improves prediction accuracy by 9.67% compared to the BP neural network and by 6.45% compared to the LSTM neural network. The proposed taxi driver passenger-seeking route selection method increases the average passenger probability by 18.95% compared to common methods. The proposed passenger-seeking recommendation framework, which includes passenger probability prediction and route optimization, maximizes road passenger efficiency and holds significant academic and practical value.

Advanced attention-based spatial-temporal neural networks for enhanced CO2 water-alternating-gas performance prediction and history matching

This study combines convolutional neural networks, spatial pyramid pooling, and long short-term memory networks (LSTM) with self-attention (SA) mechanisms (abbreviated as CSAL) to address the problem of production dynamics prediction in tight reservoirs during the CO2 water-alternating-gas (CO2-WAG) injection process. By integrating DenseNet and SPP modules, this method effectively captures and processes complex spatial features in tight reservoirs. Concurrently, the LSTM enhanced with SA mechanisms improves the prediction capability of temporal data during the CO2-WAG process. Experimental results demonstrate that the CSAL model performs excellently in both the training and testing phases, achieving a coefficient of determination (R2) exceeding 0.98, significantly enhancing the model's prediction accuracy. Compared to models without attention mechanisms, the CSAL model increases the R2 value in time series prediction by 10%. Furthermore, employing the Ensemble Smoother with Multiple Data Assimilation algorithm, the CSAL model achieves high-precision history matching, significantly reducing the error between predicted values and actual observations. This study validates the application potential and superiority of the CSAL model in the CO2-WAG process in tight reservoirs.

Machine learning and numerical simulation research on specific energy consumption for gradated coarse particle two-phase flow in inclined pipes

In deep-sea mining engineering, accurately predicting the energy required per unit length of pipeline to transport a unit mass of solids (dimensionless specific energy consumption, DSEC) is crucial for ensuring energy conservation and efficiency in the project. Based on our previous work, we utilized the machine learning (ML) and the computational fluid dynamics (CFD)–discrete element method (DEM) method to study the transport characteristics and flow field variations of gradated coarse particles in inclined pipes (gradated particles refer to solid particles mixed in specific size and quantity ratios). First, we collect 1185 sets of data from 13 experimental literature, and after analyzing and processing them, an ensemble model based on four other ML models is developed. Both for pure substance particles (PS) and mixed particles (MP), the prediction accuracy of this ensemble model is relatively higher (PSs are spherical particles with uniform size and density, and MPs are particles with different shapes, sizes, and densities). Then, the CFD-DEM process and the operating conditions include low flow velocity with low volume concentration (2 m/s and 2.5%), low flow velocity with high volume concentration (2 m/s and 7.5%), and high flow velocity with low volume concentration (4 m/s and 2.5%). Under conditions of low flow velocity and low concentrations, as well as high flow velocity and low concentrations, the DSEC hardly changes with the variation of the pipe inclination angle. Under low flow velocity and high-concentration conditions, as the pipe gradually becomes vertical, the value of DSEC gradually increases.

A novel classification algorithm for customer churn prediction based on hybrid Ensemble-Fusion model

Nowadays, customer churn issues are becoming more and more important, which is one of the most important metrics for evaluating the health of a business it is difficult to measure success without measuring customer churn metrics. However, it has become a challenge for the industry to predict when customers are churning or preparing to churn and to take the necessary action at the critical time before they do. At the same time, how to keep the place of deep research on the 17 machine learning algorithms in 9 major classes of machine learning classics production is the first problem we are facing. Through customer churn deep research, we mentioned the Ensemble-Fusion model based on machine learning and introduced a smart intelligent system to help reduce the actual customer churn about the production. Comparing with most popular predictive models, such as the Support vector machine algorithm, Random Forest algorithm, K-Nearest-Neighbor algorithm, Gradient boosting algorithm, Logistic regression algorithm, Bayesian algorithm, Decision tree algorithm, and Neural network algorithm are applied to check the effect on accuracy, AUC, and F1-score. By comparing with 17 algorithms in 9 categories of machine learning classics, the data prediction accuracy of the Ensemble-Fusion model reaches 95.35%, AUC score reaches 91% and F1-Score reaches 96.96%. The experimental results show that the data prediction accuracy of the Ensemble-Fusion model outperforms that of other benchmark algorithms.

Machine learning can be as good as maximum likelihood when reconstructing phylogenetic trees and determining the best evolutionary model on four taxon alignments

Phylogenetic tree reconstruction with molecular data is important in many fields of life science research. The gold standard in this discipline is the phylogenetic tree reconstruction based on the Maximum Likelihood method. In this study, we present neural networks to predict the best model of sequence evolution and the correct topology for four sequence alignments of nucleotide or amino acid sequence data. We trained neural networks with different architectures using simulated alignments for a wide range of evolutionary models, model parameters and branch lengths. By comparing the accuracy of model and topology prediction of the trained neural networks with Maximum Likelihood and Neighbour Joining methods, we show that for quartet trees, the neural network classifier outperforms the Neighbour Joining method and is in most cases as good as the Maximum Likelihood method to infer the best model of sequence evolution and the best tree topology. These results are consistent for nucleotide and amino acid sequence data. We also show that our method is superior for model selection than previously published methods based on convolutionary networks. Furthermore, we found that neural network classifiers are much faster than the IQ-TREE implementation of the Maximum Likelihood method. Our results show that neural networks could become a true competitor for the Maximum Likelihood method in phylogenetic reconstructions.