Evidential Decision Tree Based on Belief Entropy

TSTELM: Two-Stage Transfer Extreme Learning Machine for Unsupervised Domain Adaptation

As a single-layer feedforward network (SLFN), extreme learning machine (ELM) has been successfully applied for classification and regression in machine learning due to its faster training speed and better generalization. However, it will perform poorly for domain adaptation in which the distributions between training data and testing data are inconsistent. In this article, we propose a novel ELM called two-stage transfer extreme learning machine (TSTELM) to solve this problem. At the statistical matching stage, we adopt maximum mean discrepancy (MMD) to narrow the distribution difference of the output layer between domains. In addition, at the subspace alignment stage, we align the source and target model parameters, design target cross-domain mean approximation, and add the output weight approximation to further promote the knowledge transferring across domains. Moreover, the prediction of test sample is jointly determined by the ELM parameters generated at the two stages. Finally, we investigate the proposed approach in classification task and conduct experiments on four public domain adaptation datasets. The result indicates that TSTELM could effectively enhance the knowledge transfer ability of ELM with higher accuracy than other existing transfer and non-transfer classifiers.

Belief Entropy Tree and Random Forest: Learning from Data with Continuous Attributes and Evidential Labels

As well-known machine learning methods, decision trees are widely applied in classification and recognition areas. In this paper, with the uncertainty of labels handled by belief functions, a new decision tree method based on belief entropy is proposed and then extended to random forest. With the Gaussian mixture model, this tree method is able to deal with continuous attribute values directly, without pretreatment of discretization. Specifically, the tree method adopts belief entropy, a kind of uncertainty measurement based on the basic belief assignment, as a new attribute selection tool. To improve the classification performance, we constructed a random forest based on the basic trees and discuss different prediction combination strategies. Some numerical experiments on UCI machine learning data set were conducted, which indicate the good classification accuracy of the proposed method in different situations, especially on data with huge uncertainty.

The Characterization of Structure and Prediction for Aquaporin in Tumour Progression by Machine Learning

Recurrence and new cases of cancer constitute a challenging human health problem. Aquaporins (AQPs) can be expressed in many types of tumours, including the brain, breast, pancreas, colon, skin, ovaries, and lungs, and the histological grade of cancer is positively correlated with AQP expression. Therefore, the identification of aquaporins is an area to explore. Computational tools play an important role in aquaporin identification. In this research, we propose reliable, accurate and automated sequence predictor iAQPs-RF to identify AQPs. In this study, the feature extraction method was 188D (global protein sequence descriptor, GPSD). Six common classifiers, including random forest (RF), NaiveBayes (NB), support vector machine (SVM), XGBoost, logistic regression (LR) and decision tree (DT), were used for AQP classification. The classification results show that the random forest (RF) algorithm is the most suitable machine learning algorithm, and the accuracy was 97.689%. Analysis of Variance (ANOVA) was used to analyse these characteristics. Feature rank based on the ANOVA method and IFS strategy was applied to search for the optimal features. The classification results suggest that the 26th feature (neutral/hydrophobic) and 21st feature (hydrophobic) are the two most powerful and informative features that distinguish AQPs from non-AQPs. Previous studies reported that plasma membrane proteins have hydrophobic characteristics. Aquaporin subcellular localization prediction showed that all aquaporins were plasma membrane proteins with highly conserved transmembrane structures. In addition, the 3D structure of aquaporins was consistent with the localization results. Therefore, these studies confirmed that aquaporins possess hydrophobic properties. Although aquaporins are highly conserved transmembrane structures, the phylogenetic tree shows the diversity of aquaporins during evolution. The PCA showed that positive and negative samples were well separated by 54D features, indicating that the 54D feature can effectively classify aquaporins. The online prediction server is accessible at http://lab.malab.cn/∼acy/iAQP.

Target Classification of Similar Spatial Characteristics in Complex Urban Areas by Using Multispectral LiDAR

With the rapid modernization, many remote-sensing sensors were developed for classifying urban land and environmental monitoring. Multispectral LiDAR, which serves as a new technology, has exhibited potential in remote-sensing monitoring due to the synchronous acquisition of three-dimension point cloud and spectral information. This study confirmed the potential of multispectral LiDAR for complex urban land cover classification through three comparative methods. Firstly, the Optech Titan LiDAR point cloud was pre-processed and ground filtered. Then, three methods were analyzed: (1) Channel 1, based on Titan data to simulate the classification of a single-band LiDAR; (2) three-channel information and the digital surface model (DSM); and (3) three-channel information and DSM combined with the calculated three normalized difference vegetation indices (NDVIs) for urban land classification. A decision tree was subsequently used in classification based on the combination of intensity information, elevation information, and spectral information. The overall classification accuracies of the point cloud using the single-channel classification and the multispectral LiDAR were 64.66% and 93.82%, respectively. The results show that multispectral LiDAR has excellent potential for classifying land use in complex urban areas due to the availability of spectral information and that the addition of elevation information to the classification process could boost classification accuracy.

NmRF: identification of multispecies RNA 2'-O-methylation modification sites from RNA sequences

2'-O-methylation (Nm) is a post-transcriptional modification of RNA that is catalyzed by 2'-O-methyltransferase and involves replacing the H on the 2'-hydroxyl group with a methyl group. The 2'-O-methylation modification site is detected in a variety of RNA types (miRNA, tRNA, mRNA, etc.), plays an important role in biological processes and is associated with different diseases. There are few functional mechanisms developed at present, and traditional high-throughput experiments are time-consuming and expensive to explore functional mechanisms. For a deeper understanding of relevant biological mechanisms, it is necessary to develop efficient and accurate recognition tools based on machine learning. Based on this, we constructed a predictor called NmRF based on optimal mixed features and random forest classifier to identify 2'-O-methylation modification sites. The predictor can identify modification sites of multiple species at the same time. To obtain a better prediction model, a two-step strategy is adopted; that is, the optimal hybrid feature set is obtained by combining the light gradient boosting algorithm and incremental feature selection strategy. In 10-fold cross-validation, the accuracies of Homo sapiens and Saccharomyces cerevisiae were 89.069 and 93.885%, and the AUC were 0.9498 and 0.9832, respectively. The rigorous 10-fold cross-validation and independent tests confirm that the proposed method is significantly better than existing tools. A user-friendly web server is accessible at http://lab.malab.cn/∼acy/NmRF.

CED: A Distance for Complex Mass Functions

Evidence theory is an effective methodology for modeling and processing uncertainty that has been widely applied in various fields. In evidence theory, a number of distance measures have been presented, which play an important role in representing the degree of difference between pieces of evidence. However, the existing evidential distances focus on traditional basic belief assignments (BBAs) modeled in terms of real numbers and are not compatible with complex BBAs (CBBAs) extended to the complex plane. Therefore, in this article, a generalized evidential distance measure called the complex evidential distance (CED) is proposed, which can measure the difference or dissimilarity between CBBAs in complex evidence theory. This is the first work to consider distance measures for CBBAs, and it provides a promising way to measure the differences between pieces of evidence in a more general framework of complex plane space. Furthermore, the CED is a strict distance metric with the properties of nonnegativity, nondegeneracy, symmetry, and triangle inequality that satisfies the axioms of a distance. In particular, when the CBBAs degenerate into classical BBAs, the CED will degenerate into Jousselme et al.'s distance. Therefore, the proposed CED is a generalization of the traditional evidential distance, but it has a greater ability to measure the difference or dissimilarity between pieces of evidence. Finally, a decision-making algorithm for pattern recognition is devised based on the CED and is applied to a medical diagnosis problem to illustrate its practicability.

A SWOT method to evaluate safety risks in life cycle of wind turbine extended by D number theory

Wind power is a typical clean and renewable energy, which has been widely regarded as one of the replaceable energies in many countries. Wind turbine is the key equipment to generate wind power. It is necessary to evaluate the risks of each stage of the wind turbine with regard to occupational health and safety. In this study, the stage of production of life cycle of wind turbine is considered. The aim of this study is to propose a new method to identify and evaluate the risk factors based on strengths-weaknesses-opportunities-threats (SWOT) analysis and D number theory, named D-SWOT method. A wind turbine firm is used to demonstrate the detailed steps of the proposed method. SWOT is conducted to identify the risk factors of production stage of the wind turbine company. Experts are invited to perform the risk assessment, and D number theory is carried out to do the processes of information representation and integration. After that, some suggestions are provided to the company to lower the risks. The D-SWOT method obtains the same results as the previous method of hesitant fuzzy linguistic term set (HFLTS). Compared with HFLTS method, D-SWOT method simplifies the process of information processing, and D-SWOT method is more intuitional and concise. Besides, a property of pignistic probability transformation of D number theory (DPPT) is proposed in the manuscript, which extends D number theory and has been used in the process of decision making of D-SWOT.

Performance Analysis of Selected Programming Languages in the Context of Supporting Decision-Making Processes for Industry 4.0

This study analyzes the possibility of using Go (Golang) in the context of Java and Python in decision-making processes, with particular emphasis on their use in industry-specific solutions for Industry 4.0. The authors intentionally compared Go with Java and Python, which have been widely used for many years for data analysis in many areas. The research work was based on decision trees data mining algorithms, and especially on classification trees, in which the measure of entropy as a heuristics to choose an attribute was taken into account. The tests were carried out on various parameters describing calculation time, RAM usage, and CPU usage. The source data, which were the basis for the computing of the decision tree algorithm implemented using these three languages, were obtained from a commercial remote prototyping system and were related to the target customers’ choice of methods and means of the full design-creation process.

A GMCDM approach with linguistic Z-numbers based on TOPSIS and Choquet integral considering risk preference

Group multi-criteria decision-making (GMCDM) is an important part of decision theory, which is aimed to assess alternatives according to multiple criteria by collecting the wisdom of experts. However, in the process of evaluating, because of the limitation of human knowledge and the complexity of problems, an efficient GMCDM approach under uncertain environment still need to be further explored. Thus, in this paper, a novel GMCDM approach with linguistic Z-numbers based on TOPSIS and Choquet integral is proposed. Firstly, since linguistic Z-numbers performs better in coping with uncertain information, it is used to express the evaluation information. Secondly, TOPSIS, one of the most useful and systematic multi-criteria decision-making (MCDM) method, is adopted as the framework of the proposed approach. Thirdly, frequently it exists interaction between criteria, so Choquet integral is introduced to capture this kind of influence. What’s more, viewing that decision makers (DMs) show different preferences for uncertainty, the risk preference is regarded as a vital parameter when calculating the score of linguistic Z-numbers. An application in supplier selection is illustrated to demonstrate the effectiveness of the proposed approach. Finally, a further comparison and discussion of the proposed GMCDM method is given.

Improved Base Belief Function-Based Conflict Data Fusion Approach Considering Belief Entropy in the Evidence Theory

Due to the nature of the Dempster combination rule, it may produce results contrary to intuition. Therefore, an improved method for conflict evidence fusion is proposed. In this paper, the belief entropy in D–S theory is used to measure the uncertainty in each evidence. First, the initial belief degree is constructed by using an improved base belief function. Then, the information volume of each evidence group is obtained through calculating the belief entropy which can modify the belief degree to get the final evidence that is more reasonable. Using the Dempster combination rule can get the final result after evidence modification, which is helpful to solve the conflict data fusion problems. The rationality and validity of the proposed method are verified by numerical examples and applications of the proposed method in a classification data set.

A Method for Prediction of Thermophilic Protein Based on Reduced Amino Acids and Mixed Features

The thermostability of proteins is a key factor considered during enzyme engineering, and finding a method that can identify thermophilic and non-thermophilic proteins will be helpful for enzyme design. In this study, we established a novel method combining mixed features and machine learning to achieve this recognition task. In this method, an amino acid reduction scheme was adopted to recode the amino acid sequence. Then, the physicochemical characteristics, auto-cross covariance (ACC), and reduced dipeptides were calculated and integrated to form a mixed feature set, which was processed using correlation analysis, feature selection, and principal component analysis (PCA) to remove redundant information. Finally, four machine learning methods and a dataset containing 500 random observations out of 915 thermophilic proteins and 500 random samples out of 793 non-thermophilic proteins were used to train and predict the data. The experimental results showed that 98.2% of thermophilic and non-thermophilic proteins were correctly identified using 10-fold cross-validation. Moreover, our analysis of the final reserved features and removed features yielded information about the crucial, unimportant and insensitive elements, it also provided essential information for enzyme design.

A New Evaluation Methodology for Quality Goals Extended by D Number Theory and FAHP

Evaluation of quality goals is an important issue in process management, which essentially is a multi-attribute decision-making (MADM) problem. The process of assessment inevitably involves uncertain information. The two crucial points in an MADM problem are to obtain weight of attributes and to handle uncertain information. D number theory is a new mathematical tool to deal with uncertain information, which is an extension of evidence theory. The fuzzy analytic hierarchy process (FAHP) provides a hierarchical way to model MADM problems, and the comparison analysis among attributes is applied to obtain the weight of attributes. FAHP uses a triangle fuzzy number rather than a crisp number to represent the evaluation information, which fully considers the hesitation to give a evaluation. Inspired by the features of D number theory and FAHP, a D-FAHP method is proposed to evaluate quality goals in this paper. Within the proposed method, FAHP is used to obtain the weight of each attribute, and the integration property of D number theory is carried out to fuse information. A numerical example is presented to demonstrate the effectiveness of the proposed method. Some necessary discussions are provided to illustrate the advantages of the proposed method.

Predicting ATP-Binding Cassette Transporters Using the Random Forest Method

ATP-binding cassette (ABC) proteins play important roles in a wide variety of species. These proteins are involved in absorbing nutrients, exporting toxic substances, and regulating potassium channels, and they contribute to drug resistance in cancer cells. Therefore, the identification of ABC transporters is an urgent task. The present study used 188D as the feature extraction method, which is based on sequence information and physicochemical properties. We also visualized the feature extracted by t-Distributed Stochastic Neighbor Embedding (t-SNE). The sample based on the features extracted by 188D may be separated. Further, random forest (RF) is an efficient classifier to identify proteins. Under the 10-fold cross-validation of the model proposed here for a training set, the average accuracy rate of 10 training sets was 89.54%. We obtained values of 0.87 for specificity, 0.92 for sensitivity, and 0.79 for MCC. In the testing set, the accuracy achieved was 89%. These results suggest that the model combining 188D with RF is an optimal tool to identify ABC transporters.

Refined Expected Value Decision Rules under Orthopair Fuzzy Environment

Refined expected value decision rules can refine the calculation of the expected value and make decisions by estimating the expected values of different alternatives, which use many theories, such as Choquet integral, PM function, measure and so on. However, the refined expected value decision rules have not been applied to the orthopair fuzzy environment yet. To address this issue, in this paper we propose the refined expected value decision rules under the orthopair fuzzy environment, which can apply the refined expected value decision rules on the issues of decision making that is described in the orthopair fuzzy environment. Numerical examples were applied to verify the availability and flexibility of the new refined expected value decision rules model. The experimental results demonstrate that the proposed model can apply refined expected value decision rules in the orthopair fuzzy environment and solve the decision making issues with the orthopair fuzzy environment successfully.

Negation of Pythagorean Fuzzy Number Based on a New Uncertainty Measure Applied in a Service Supplier Selection System

The Pythagorean fuzzy number (PFN) consists of membership and non-membership as an extension of the intuitionistic fuzzy number. PFN has a larger ambiguity, and it has a stronger ability to express uncertainty. In the multi-criteria decision-making (MCDM) problem, it is also very difficult to measure the ambiguity degree of a set of PFN. A new entropy of PFN is proposed based on a technique for order of preference by similarity to ideal solution (Topsis) method of revised relative closeness index in this paper. To verify the new entropy with a good performance in uncertainty measure, a new Pythagorean fuzzy number negation approach is proposed. We develop the PFN negation and find the correlation of the uncertainty measure. Existing methods can only evaluate the ambiguity of a single PFN. The newly proposed method is suitable to systematically evaluate the uncertainty of PFN in Topsis. Nowadays, there are no uniform criteria for measuring service quality. It brings challenges to the future development of airlines. Therefore, grasping the future market trends leads to winning with advanced and high-quality services. Afterward, the applicability in the service supplier selection system with the new entropy is discussed to evaluate the service quality and measure uncertainty. Finally, the new PFN entropy is verified with a good ability in the last MCDM numerical example.

Determining Weights in Multi-Criteria Decision Making Based on Negation of Probability Distribution under Uncertain Environment

Multi-criteria decision making (MCDM) refers to the decision making in the limited or infinite set of conflicting schemes. At present, the general method is to obtain the weight coefficients of each scheme based on different criteria through the expert questionnaire survey, and then use the Dempster–Shafer Evidence Theory (D-S theory) to model all schemes into a complete identification framework to generate the corresponding basic probability assignment (BPA). The scheme with the highest belief value is then chosen. In the above process, using different methods to determine the weight coefficient will have different effects on the final selection of alternatives. To reduce the uncertainty caused by subjectively determining the weight coefficients of different criteria and further improve the level of multi-criteria decision-making, this paper combines negation of probability distribution with evidence theory and proposes a weights-determining method in MCDM based on negation of probability distribution. Through the quantitative evaluation of the fuzzy degree of the criterion, the uncertainty caused by human subjective factors is reduced, and the subjective error is corrected to a certain extent.