An evidential reasoning rule based feature selection for improving trauma outcome prediction

Prediction of the stage of cancer plays an important role in planning the course of treatment and has been largely reliant on imaging tools which do not capture molecular events that cause cancer progression. Gene-expression data-based analyses are able to identify these events, allowing RNA-sequence and microarray cancer data to be used for cancer analyses. Breast cancer is the most common cancer worldwide, and is classified into four stages - stages 1, 2, 3, and 4 [2]. While machine learning models have previously been explored to perform stage classification with limited success, multi-class stage classification has not had significant progress. There is a need for improved multi-class classification models, such as by investigating deep learning models. Gene-expression-based cancer data is characterised by the small size of available datasets, class imbalance, and high dimensionality. Class balancing methods must be applied to the dataset. Since all the genes are not necessary for stage prediction, retaining only the necessary genes can improve classification accuracy. The breast cancer samples are to be classified into 4 classes of stages 1 to 4. Invasive ductal carcinoma breast cancer samples are obtained from The Cancer Genome Atlas (TCGA) and Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) datasets and combined. Two class balancing techniques are explored, synthetic minority oversampling technique (SMOTE) and SMOTE followed by random undersampling. A hybrid feature selection pipeline is proposed, with three pipelines explored involving combinations of filter and embedded feature selection methods: Pipeline 1 - minimum-redundancy maximum-relevancy (mRMR) and correlation feature selection (CFS), Pipeline 2 - mRMR, mutual information (MI) and CFS, and Pipeline 3 - mRMR and support vector machine-recursive feature elimination (SVM-RFE). The classification is done using deep learning models, namely deep neural network, convolutional neural network, recurrent neural network, a modified deep neural network, and an AutoKeras generated model. Classification performance post class-balancing and various feature selection techniques show marked improvement over classification prior to feature selection. The best multiclass classification was found to be by a deep neural network post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with a Cohen-Kappa score of 0.303 and a classification accuracy of 53.1%. For binary classification into early and late-stage cancer, the best performance is obtained by a modified deep neural network (DNN) post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with an accuracy of 81.0% and a Cohen-Kappa score (CKS) of 0.280. This pipeline also showed improved multiclass classification performance on neuroblastoma cancer data, with a best area under the receiver operating characteristic (auROC) curve score of 0.872, as compared to 0.71 obtained in previous work, an improvement of 22.81%. The results and analysis reveal that feature selection techniques play a vital role in gene-expression data-based classification, and the proposed hybrid feature selection pipeline improves classification performance. Multi-class classification is possible using deep learning models, though further improvement particularly in late-stage classification is necessary and should be explored further.

Drug-Protein Interaction (DPI) identification is crucial in drug discovery. The high dimensionality of drug and protein features poses challenges for accurate interaction prediction, necessitating the use of computational techniques. Docking-based methods rely on 3D structures, while ligand-based methods have limitations such as reliance on known ligands and neglecting protein structure. Therefore, the preferred approach is the chemogenomics-based approach using machine learning, which considers both drug and protein characteristics for DPI prediction. In machine learning, feature selection plays a vital role in improving model performance, reducing overfitting, enhancing interpretability, and making the learning process more efficient. It helps extract meaningful patterns from drug and protein data while eliminating irrelevant or redundant information, resulting in more effective machine-learning models. On the other hand, classification is of great importance as it enables pattern recognition, decision-making, predictive modeling, anomaly detection, data exploration, and automation. It empowers machines to make accurate predictions and facilitates efficient decision-making in DPI prediction. For this research work, protein data was sourced from the KEGG database, while drug data was obtained from the DrugBank data machine-learning base. To address the issue of imbalanced Drug Protein Pairs (DPP), different balancing techniques like Random Over Sampling (ROS), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive SMOTE were employed. Given the large number of features associated with drugs and proteins, feature selection becomes necessary. Various feature selection methods were evaluated: Correlation, Information Gain (IG), Chi-Square (CS), and Relief. Multiple classification methods, including Support Vector Machines (SVM), Random Forest (RF), Adaboost, and Logistic Regression (LR), were used to predict DPI. Finally, this research identifies the best balancing, feature selection, and classification methods for accurate DPI prediction. This comprehensive approach aims to overcome the limitations of existing methods and provide more reliable and efficient predictions in drug-protein interaction studies.

Purpose:There has been burgeoning interest in applying machine learning methods for predicting radiotherapy outcomes. However, the imbalanced ratio of a large number of variables to a limited sample size in radiation oncology constitutes a major challenge. Therefore, dimensionality reduction methods can be a key to success. The study investigates and contrasts the application of traditional machine learning methods and deep learning approaches for outcome modeling in radiotherapy. In particular, new joint architectures based on variational autoencoder (VAE) for dimensionality reduction are presented and their application is demonstrated for the prediction of lung radiation pneumonitis (RP) from a large-scale heterogeneous dataset.Methods:A large-scale heterogeneous dataset containing a pool of 230 variables including clinical factors (e.g., dose, KPS, stage) and biomarkers (e.g., single nucleotide polymorphisms (SNPs), cytokines and micro-RNAs) in a population of 106 non-small cell lung cancer (NSCLC) patients who received radiotherapy was used for modeling RP. 22 patients had grade 2 or higher RP. Four methods were investigated, including feature selection (case A) and feature extraction (case B) with traditional machine learning methods, a VAE-MLP joint architecture (case C) with deep learning and lastly, the combination of feature selection and joint-architecture (case D). For feature selection, Random forest (RF), Support Vector Machine (SVM) and multi-layer perceptron (MLP) were implemented to select relevant features. Specifically, each method was run for multiple times to rank features within several cross-validated (CV) resampled sets. A collection of ranking lists were then aggregated by top 5% and Kemeny graph methods to identify the final ranking for prediction. A synthetic minority oversampling technique (SMOTE) was applied to correct for class imbalance during this process. For deep learning, a VAE-MLP joint architecture where a VAE aimed for dimensionality reduction and an MLP aimed for classification was developed. In this architecture, reconstruction loss and prediction loss were combined into a single loss function to realize simultaneous training and weights were assigned to different classes to mitigate class imbalance. To evaluate the prediction performance and conduct comparisons, the area under receiver operating characteristic (ROC) curves (AUCs) were performed for nested CVs for both handcrafted feature selections and the deep learning approach. The significance of differences in AUCs was assessed using the DeLong test of U-statistics.Results:An MLP-based method using weight pruning (WP) feature selection yielded the best performance among the different hand-crafted feature selection methods (case A), reaching an AUC of 0.804 (95% CI: 0.761–0.823) with 29 top features. A VAE-MLP joint architecture (case C) achieved a comparable but slightly lower AUC of 0.781 (95% CI: 0.737–0.808) with the size of latent dimension being 2. The combination of handcrafted features (case A) and latent representation (case D) achieved a significant AUC improvement of 0.831 (95% CI: 0.805–0.863) with 22 features (p-value = 0.000642 compared with handcrafted features only (Case A) and p-value=0.000453 compared to VAE alone (Case C)) with an MLP classifier.Conclusion:The potential for combination of traditional machine learning methods and deep learning VAE techniques has been demonstrated for dealing with limited datasets in modeling radiotherapy toxicities. Specifically, latent variables from a VAE-MLP joint architecture are able to complement handcrafted features for the prediction of RP and improve prediction over either method alone.

In current research of complex system health assessment with evidential reasoning (ER) rule, the relationship between the indicators reference grades and pre-defined assessment result grades is regarded as a one to one correspondence. However, in engineering practice, this strict mapping relationship is difficult to meet, and it may degrease the accuracy of the assessment. Therefore, a new ER rule-based health assessment model for a complex system with a transformation matrix is adopted. First, on the basis of the rule-based transformation technique, expert knowledge is embedded on the transformation matrix to solve the inconsistent problems between the input and the output, which keeps completeness and consistency of information transformation. Second, a complete health assessment model is established via the calculation and optimization of the model parameters. Finally, the effectiveness of the proposed model can be validated in contrast with other methods.

Performance evaluation of aerospace relay based on evidential reasoning rule with distributed referential points

This paper presents a new approach to dynamic system state estimation under bounded noises via the Evidential Reasoning(£K) rule. This method regards the dynamic system equations and the actual observations of the system states as two information sources. The random set description of evidence and the extension principle of random set are used to recursively generate state evidence and observation evidence respectively from the two information sources and to propagate them in system equations. At each time step, the ER rule is used to fuse the two pieces of evidence in observation domain and then the fused result is transformed to state domain by the extension principles. Pignistic expectation of the fused result is calculated as state estimation value. Compared with the estimation method using interval analysis and evidence theory given by Nassreddine, the proposed approach makes estimation results more accurate by using fusion mechanism of the ER rule considering weight and reliability of evidence. The method is shown to have better performances in an application to liquid level estimation of industrial level apparatus than does the Nassreddine's method.

It is extremely important to monitor the health status of welding robots for the safe and stable operation of a body-in-white (BIW) welding production line. In the actual production process, the robot degradation rate is slow and the effective data are poor, which can reflect a degradation state in the large amount of obtained monitoring data, which causes difficulties in health status evaluation. In order to realize the accurate evaluation of the health status of welding robots, this paper proposes a health status evaluation method based on the evidential reasoning (ER) rule, which reflects the health status of welding robots by using the running state data monitored in actual engineering and through the qualitative knowledge of experts, which makes up for the lack of effective data. In the ER rule evaluation model, the covariance matrix adaptive evolutionary strategy (CMA-ES) algorithm is used to optimize the initial parameters of the evaluation model, which improved the accuracy of health status evaluations. Finally, a BIW welding robot was taken as an example for verification. The results show that the proposed model is able to accurately estimate the health status of the welding robot by using the monitored degradation data.

Lithium-ion batteries are widely used in energy storage, small electronic devices and other fields due to their advantages of high energy density and long life cycles, as well as causing less damage to the environment than alternatives. For safety, it is essential to propose reasonable methods to assess batteries’ health statuses. Therefore, a health assessment model based on the evidential reasoning (ER) rule is proposed in this article. Firstly, the voltage rise time and the current fall time are taken as observation indicators, which contain information about the health status of lithium-ion batteries. Secondly, the information of various indicators is integrated into a belief structure, and the indicator reliability and indicator weights are adequately considered in the assessment model. Thirdly, there are some perturbations that will affect the operating status of batteries and cause the batteries’ reliability to fluctuate, so we use perturbation analysis to determine the adaptability of batteries to perturbations. We set two bounded parameters, the perturbation coefficient and the maximum perturbation error, to assess the reliability of lithium-ion batteries when experiencing perturbations. Finally, on the basis of the whole-life open data set of lithium-ion batteries from the National Aeronautics and Space Administration’s Prognostics Center of Excellence, the validity of the health assessment model and perturbation analysis is demonstrated.

A data-driven industrial alarm decision method via evidence reasoning rule

Unbalanced datasets are a common problem in supervised machine learning. It leads to a deeper understanding of the majority of classes in machine learning. Therefore, the machine learning model is more effective at recognizing the majority classes than the minority classes. Naturally, imbalanced data, such as disease data and data networking, has emerged in real life. DDOS is one of the network intrusions found to happen more often than R2L. There is an imbalance in the composition of network attacks in Intrusion Detection System (IDS) public datasets such as NSL-KDD and UNSW-NB15. Besides, researchers propose many techniques to transform it into balanced data by duplicating the minority class and producing synthetic data. Synthetic Minority Oversampling Technique (SMOTE) and Adaptive Synthetic (ADASYN) algorithms duplicate the data and construct synthetic data for the minority classes. Meanwhile, machine learning algorithms can capture the labeled data's pattern by considering the input features. Unfortunately, not all the input features have an equal impact on the output (predicted class or value). Some features are interrelated and misleading. Therefore, the important features should be selected to produce a good model. In this research, we implement the recursive feature elimination (RFE) technique to select important features from the available dataset. According to the experiment, SMOTE provides a better synthetic dataset than ADASYN for the UNSW-B15 dataset with a high level of imbalance. RFE feature selection slightly reduces the model's accuracy but improves the training speed. Then, the Decision Tree classifier consistently achieves a better recognition rate than Random Forest and KNN.

Recent studies in scientific paper summarization have explored a new form of structured summary for a reference paper by grouping all cited and citing sentences together by facet. This involves three main tasks: (1) identifying cited text spans for citances (i.e., citing sentences), (2) classifying their discourse facets, and (3) generating a structured summary from the cited text spans and citances. This paper focuses on the first task, and approaches the task as binary classification to distinguish relevant pairs of citances and reference sentences from irrelevant pairs. We propose a new method that integrates feature selection and classification techniques to enhance classification performance. The proposed method investigates combinations of six feature selection methods (χ2-Statistics, Information Gain, Gain Ratio, Relief-F, Significance Attribute Evaluation, and Symmetrical Uncertainty), and five classification algorithms (k-Nearest Neighbors, Decision Tree, Support Vector Machine, Naïve Bayes, and Random Forest). Additionally, to address imbalanced data during training, we apply SMOTE (Synthetic Minority Over-sampling Technique) to introduce synthetic biases towards the minority. Experiments are conducted using the CL-SciSumm corpora to compare the effect of feature selection applied to classification. The results reveal the benefits of feature selection in significantly boosting performance of F1 score metric, and show that our method is competitive to the state-of-the-art methods in the CL-SciSumm evaluations.

With the rapid development of artificial intelligence in recent years, the research on image processing, text mining, and genome informatics has gradually deepened, and the mining of large-scale databases has begun to receive more and more attention. The objects of data mining have also become more complex, and the data dimensions of mining objects have become higher and higher. Compared with the ultra-high data dimensions, the number of samples available for analysis is too small, resulting in the production of high-dimensional small sample data. High-dimensional small sample data will bring serious dimensional disasters to the mining process. Through feature selection, redundancy and noise features in high-dimensional small sample data can be effectively eliminated, avoiding dimensional disasters and improving the actual efficiency of mining algorithms. However, the existing feature selection methods emphasize the classification or clustering performance of the feature selection results and ignore the stability of the feature selection results, which will lead to unstable feature selection results, and it is difficult to obtain real and understandable features. Based on the traditional feature selection method, this paper proposes an ensemble feature selection method, Random Bits Forest Recursive Clustering Eliminate (RBF-RCE) feature selection method, combined with multiple sets of basic classifiers to carry out parallel learning and screen out the best feature classification results, optimizes the classification performance of traditional feature selection methods, and can also improve the stability of feature selection. Then, this paper analyzes the reasons for the instability of feature selection and introduces a feature selection stability measurement method, the Intersection Measurement (IM), to evaluate whether the feature selection process is stable. The effectiveness of the proposed method is verified by experiments on several groups of high-dimensional small sample data sets.

Textual data suffers from two main problems, large number of features and class imbalance. Many conventional approaches and their variants exist in literature to solve both these problems. The classic synthetic minority oversampling technique (SMOTE) is the most explored technique for balancing the dataset. We introduced a new algorithm to balance the dataset, named distributed SMOTE (D_SMOTE), which overcomes the problem of lack of density and reducing the formation of small disjuncts. Further, another problem handled is the large number of features or high-dimensionality. To solve high-dimensionality, a novel feature selection technique is introduced known as modified biogeography-based optimization (M_BBO). The proposed model, M_BBO, performs modification in ranking of variables using feature weighting algorithm rather than randomly ranking. We have proposed two new expressions in D_SMOTE and one new expression in M_BBO. The extensive experimental results are computed out on four text classification datasets with four machine learning classifiers. The results are concluded using three performance measures, area under curve, G-mean, and F1-score. Our empirical and statistical observation for four class-imbalanced datasets shows that the proposed D_SMOTE outperforms the other similar oversampling technique. We have also compared our proposed algorithm, M_BBO+D_SMOTE, with other models on 17 imbalanced text classification datasets. Our model outperformed the other models in 14 datasets. We have also compared our model with bidirectional encoder representations from transformers. To validate the experimental analysis, statistical Friedman test is employed.

In this paper, we prove from a new angle that Dempster’s rule is inherently probabilistic, extends Bayes’ rule and reduces to Bayes’ rule when precise probabilities are available, regardless of whether prior is uniform. We use examples to demonstrate this equivalence. Additionally, we explain that the Evidential Reasoning (ER) rule is also probabilistic and includes Bayes’ and Dempster’s rules as special cases. Furthermore, we address some criticisms of the behaviour of Dempster’s rule from a probabilistic perspective and explain the rationality of the behaviour. We also identify instances where such critiques were misapplied. Finally, we clarify vital differences between belief degrees in belief functions and basic probabilities and highlight the critical differences between Shafer’s discounting method and the ER rule. These differences make the latter probabilistic, while the former is not. Our motivation is to show that evidence theory has a probabilistic foundation and is possible to become probabilistic again.

Background: Perioperative management plays a pivotal role in reducing complications and improving patient outcomes. The choice of anesthesia can significantly influence postoperative trajectories; however, current clinical practice lacks data-driven tools to support personalized selection. With the emergence of machine learning (ML) and access to large clinical databases, new opportunities have arisen to optimize anesthesia selection and predict patient outcomes. Methods: This retrospective study utilized the MIMIC-IV database (version 3.1), which comprises data from over 364,000 patients. After feature selection and preprocessing, 28 demographic, clinical, and laboratory variables were used to model four types of anesthesia (general, regional, local, and sedation) in 31,821 patients. Supervised models [random forest, logistic regression, support vector machine (SVM), k-nearest neighbors (KNN), decision tree, gradient boosting, and extreme gradient boosting (XGBoost)] were trained to predict anesthesia type; synthetic minority oversampling technique (SMOTE) was applied within training to address class imbalance. Performance was evaluated on a held-out test set using accuracy and macro-F1. Associations between anesthesia type and short-term outcomes (in-hospital mortality, 30-day readmission, postoperative infection, and length of stay) were examined through observational comparisons. Results: Boosting-based models achieved the highest predictive performance, with XGBoost and gradient boosting reaching approximately 83% accuracy on the test set (macro-F1 for XGBoost ≈ 0.45). Across anesthesia groups, regional anesthesia was associated with more favorable outcomes than general anesthesia — namely lower in-hospital mortality, fewer infections, shorter hospital and intensive care unit (ICU) stays, and reduced 30-day readmission — although estimates for the regional group were less precise due to small sample size and residual confounding is possible. Conclusions: Anesthesia type was associated with short-term clinical outcomes in this large, single-center cohort, and boosting models demonstrated strong predictive performance for anesthesia type. These findings suggest a potential role for predictive analytics in perioperative planning, while underscoring that observed differences are associations rather than causal effects. Prospective multicenter studies and randomized trials, with longer-term patient-reported outcomes, are warranted. Predictive models require external validation and calibration before they can be used clinically.