In recent years, Complex Network theory and graph algorithms have been proved to be effective in predicting software bugs. On the other hand, as a widely-used algorithm theory, k-core decomposition has used engineering domain identify key classes. Intuitively, classes are more likely buggy since they participate functions or interactions dependencies. However, there is no existing research uses analyze To fill this gap, we first use on Class Dependency Networks bug distribution from new...

Sentiment analysis mines people's opinions and attitudes regarding a certain issue from source materials. Recently, it has drawn significant attention in number of application areas. The sentiment healthcare general that users' drug experience particular could shed light on how to improve public health make the right decisions. However, one major challenges classification lies very large extracted features. Fuzzy-rough feature selection provides means by which discrete or real-valued noisy...

When a small portion of the decision makers hold correct information and majority opposite, ranking alternatives for group decision-making cannot be obtained with current methods. A novel method is thus developed to tackle this challenge in article. The priori probabilities each alternative can calculated via opinions makers, which are presented as pairwise comparisons form linguistic preference relation. Based on aggregated normalized-prediction selection rate (NPSR) defined accordingly....

Linguistic pairwise comparison matrices are widely used in decision-making procedures. However, the often give conflicting results when there multiple criteria under consideration. Despite intensive research, achieving consistency of such remains a daunting task. In this paper, novel approach based on linguistic discrete region is proposed to address challenge. Unlike existing methods that require single value for each comparison, our allows be expressed by with terms. Such front-end gives...

The consistency of pair-wise comparison matrix is a serious challenge for the multiple-criteria decision-making problem. However, existing methods are either too complicated to be applied in revising process inconsistent or difficult preserve most original information due use new pairwise matrix. In this paper, discrete region-based approach proposed improve When decision makers feel confused uncertain, they could express their evaluation as region containing multiple judgments, instead...

The methods with consensus reaching process can obtain a collective solution which is supported by most of decision makers in larger-scale group making. However, case who could give correct opinions are from the minority, conventional not answer. In this paper, novel method developed to tackle challenge. utilizing pairwise comparisons alternatives positive and negative views based on intuitionistic fuzzy preference relation. obtained translated into numbers, further grouped aggregated...

Crowd intelligence opens up new ways for decision making in open environments, traditional is unable to effectively make correct decisions environments. In this paper, positive and negative comparing method using linguistic scale proposed the environments with crowd intelligence. Firstly, participants compare alternative corresponding assessment points, give their evaluations scales form views. The participants' can be translated into Intuitionistic Fuzzy Numbers (IFNs). methods, given by do...

H. Zhang, Q. Zheng, and T. Liu et al. proposed a discrete region based approach to improve the consistency of pair-wise comparison matrix. The is able significantly matrix without revise decision maker's opinion. In approach, transformed into set-matrix in which elements are real number set. this paper, reciprocal interval A new iterative searching algorithm (NISA) find with approximate optimum from Based on similarly principle, derive weight vector for key character that derived includes...

Intuitionistic Fuzzy Set (IFS) is considered as a nature solution for information fusion. How to transform the with non-uniform distribution into IFS? In this paper, authors proposed an approach deal challenge. First, intensive region (IR) of data searched. Second, evaluation grades are assigned IR and other regions. more grades, because higher rate in it. Finally, translated IFS based on suitable assignment. The experiment conducted study effectiveness advantage approach.

Aggregation operators for intuitionistic fuzzy information, the popular methods in group decision, face challenge this area - counter-intuitive result (the decision is conflict with people's intuition under specific inputs). In paper, Mixed Intuitionistic Fuzzy Operators (MIFAOs) are proposed to relieve problem. Firstly, Bivariate (BMIFAOs) introduced based on extensions of t-conorms and t-norms. Some basic operational laws Archimedean Thus, effects unusual Numbers (IFNs) would be decreased...

<title>Abstract</title> With the rapid development of smart contract technology and continuous expansion blockchain application scenarios, security issues contracts have garnered significant attention. However, traditional fuzz testing typically relies on randomly generated initial seed sets. This random generation method fails to understand semantics contracts, resulting in insufficient coverage. Additionally, often ignores syntax semantic constraints within leading seeds that may not...

Pythagorean Fuzzy Preference Relations (PFPRs) have been considered in recent literature more powerful and flexible than the popular intuitionistic fuzzy preference relation dealing with linguistic imprecision for decision makers large scale group making. Following on this promising trend, a novel approach based PFPRs is proposed support. In particular, work starts acquisition of optimal comparison matrices, which essentially record pairwise alternatives from positive negative opinions. The...

The scale of software applications has increased dramatically. Hierarchical clustering is a good method for modular recovery architecture. Because the different evaluation criteria types and results, single hierarchical algorithm cannot integrate number clusters, arbitrary decision-making, quality other indicators on standards, there no comprehensive selection method. We propose combination use principal component analysis to combine results multiple combined result retain basic information...

A scenario that often encounters in the event of aggregating options different experts for acquisition a robust overall consensus is possible existence extremely large or small values termed as outliers this paper, which easily lead to counter-intuitive results decision aggregation. This paper attempts devise novel approach tackle especially non-uniform data, filling gap existing literature. In particular, concentrate region set data first computed with proposed searching algorithm such...

With the large-scale application of lithium-ion batteries (LIB), using deep neural networks to predict remaining useful life (RUL) LIB has gradually become a hotshot in recent years. RUL prediction method based on network can avoid studying electrochemical phenomena and manual extracting features battery. But single different accuracy extraction dataset. In this study, an ensemble for heterogeneous is proposed, which integrates results multiple with adaptive weight. The weight higher closer...

Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is critical for accelerating technology development. The neural network via data driven can avoid manual feature extraction and release difficulty model construction. However, diverse aging mechanisms, significant device variability dynamic operating conditions have remained major challenges. single cannot tackle these challenges efficiently. In this paper, RUL prediction lithium battery ensemble developed to...

Lithium-ion batteries are widely used in industrial and domestic applications because of their high energy ratio low self-discharge rate. It is important to accurately predict the State Health (SoH) lithium-ion as they degrade during use, which can lead serious safety hazards. We propose a support-based neural network ensemble method, incorporates prediction results several basic models. First, set better initial integration weights calculated result obtained, then support degree between...

The software maintainability which is an important part of quality and trustworthiness has always been a hot topic in engineering domain. measurements the are multi-source heterogeneous data, result big challenges on data aggregation for evaluation. In this paper, Intuitionistic Fuzzy Set-based Data Aggregation (IFSDA) approach developed to evaluate maintainability. order unify measurements, Grade Mapping method proposed transform them membership function non-membership based Set (IFS)....

Methods on the basis of consensus reaching process are prevalent in Group Decision Making (GDM), which typically forces some evaluators to revise initial opinions order reach group without being able precisely reflect original viewpoints. Furthermore, case correct opinion is embedded hand minority, existing methods may not consensus. With aim tackle these observations, a novel approach Positive and Negative Prediction Selection Rate (PNPSR) proposed Pythagorean Fuzzy Preference Relation...

Estimation of bearing remaining useful life (RUL) aims to accurately estimate the RUL using sensor data, it is essential for maintaining safety equipment. However, most existing prognostic methods based on data-driven have following two drawbacks: (1) Knowledge experts are required select multiple features. (2) The complex spatial-temporal sequence relationship between data and difficult captured. To overcome these drawbacks, a hybrid deep learning framework construct health indicator (HI)...

The assembly line balancing problems are significant in mass production systems. In order to solve the uncertainties that practically exist but barely mentioned literature,this paper proposed a mathematical model with an optimization algorithm problem uncertainty operation time. developed is able work variable number of workstations under uncertain environment, aiming reach minimal workstation and minimize idle time for each workstation. particular, approach first introduces concept...