Publications

Mining constrained inter-sequence patterns: a novel approach to cope with item constraints

Fuzzy system identification via probabilistic sets

A Case Study on the Impact of Refactoring on Quality and Productivity in an Agile Team

GRANULAR COMPUTING IN SOFTWARE ENGINEERING

Automated Cluster Elimination Guided by High-Density Points

Determining the optimal number of clusters in cluster analysis without prior knowledge remains a critical and challenging task. Existing methods often depend on calculating clustering validity indices (CVIs), which increases complexity and may reduce efficiency. Furthermore, different CVIs frequently suggest varying optimal cluster numbers, complicating the selection process. To address these challenges, we propose a novel clustering algorithm, self-regulating possibilistic C-means (PCM) with high-density points (SR-PCM-HDP), which simplifies cluster number determination while improving clustering efficiency. First, the density-based knowledge extraction (DBKE) method is introduced to estimate an appropriate initial cluster number and identify high-density points. DBKE enhances the density peak clustering (DPC) algorithm by removing the need for a predefined density radius. Second, SR-PCM-HDP refines the clustering process by incorporating a parameter to balance the interactions between high-density points and cluster centers, reducing sensitivity to initial configurations and accelerating convergence. Third, the parameter adjustment mechanism in classical PCM is redefined to enable adaptive updates during SR-PCM-HDP iterations. This mechanism facilitates the gradual elimination of obsolete clusters and iterative cluster formation. The theoretical foundations of the SR-PCM-HDP cluster elimination mechanism are rigorously established. Experimental results validate the accuracy and effectiveness of SR-PCM-HDP in determining cluster numbers and ensuring clustering validity, particularly for datasets with overlapping or imbalanced distributions. Comparisons are conducted against 13 state-of-the-art algorithms, including fuzzy clustering, possibilistic clustering, and CVI-based cluster determination methods.

IEEE Systems, Man, and Cybernetics Society Information

Semi-supervising Interval Type-2 Fuzzy C-Means clustering with spatial information for multi-spectral satellite image classification and change detection

An incremental preference elicitation-based approach to learning potentially non-monotonic preferences in multi-criteria sorting

This paper introduces a novel incremental preference elicitation-based approach to learning potentially non-monotonic preferences in multi-criteria sorting (MCS) problems, enabling decision makers to progressively provide assignment example preference information. Specifically, we first construct a max-margin optimization-based model to model potentially non-monotonic preferences and inconsistent assignment example preference information in each iteration of the incremental preference elicitation process. Using the optimal objective function value of the max-margin optimization-based model, we devise information amount measurement methods and question selection strategies to pinpoint the most informative alternative in each iteration within the framework of uncertainty sampling in active learning. Once the termination criterion is satisfied, the sorting result for non-reference alternatives can be determined through the use of two optimization models, i.e., the max-margin optimization-based model and the complexity controlling optimization model. Subsequently, two incremental preference elicitation-based algorithms are developed to learn potentially non-monotonic preferences, considering different termination criteria. Ultimately, we apply the proposed approach to a credit rating problem to elucidate the detailed implementation steps, and perform computational experiments on both artificial and real-world data sets to compare the proposed question selection strategies with several benchmark strategies.

Study of select items in different data sources by grouping

Efficient strategies for spatial data clustering using topological relations

Nonlinear channel blind equalization using hybrid genetic algorithm with simulated annealing

Estimating incomplete information in group decision making: A framework of granular computing

Prioritizing tasks in software development: A systematic literature review

Task prioritization is one of the most researched areas in software development. Given the huge number of papers written on the topic, it might be challenging for IT practitioners–software developers, and IT project managers–to find the most appropriate tools or methods developed to date to deal with this important issue. The main goal of this work is therefore to review the current state of research and practice on task prioritization in the Software Engineering domain and to individuate the most effective ranking tools and techniques used in the industry. For this purpose, we conducted a systematic literature review guided and inspired by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses, otherwise known as the PRISMA statement. Based on our analysis, we can make a number of important observations for the field. Firstly, we found that most of the task prioritization approaches developed to date involve a specific type of prioritization strategy— bug prioritization . Secondly, the most recent works we review investigate task prioritization in terms of “pull request prioritization” and “issue prioritization,” (and we speculate that the number of such works will significantly increase due to the explosion of version control and issue management software systems). Thirdly, we remark that the most frequently used metrics for measuring the quality of a prioritization model are f-score , precision , recall , and accuracy .

Learning Adaptive Genetic Algorithm for Earth Electromagnetic Satellite Scheduling

Earth electromagnetic exploration satellites are widely used in many fields due to their wide detection range and high detection sensitivity. The complex environment and the proliferating number of satellites make management a primary issue. In this article, a learning adaptive genetic algorithm (LAGA) is proposed for the Earth electromagnetic satellite scheduling problem (EESSP). Control parameters are essential to the successful performance of evolutionary algorithms, and their sensitivity to the problem makes tuning parameters very time-consuming. In the LAGA, a gated recurrent unit (GRU) neural network model is used to control the parameters of variation operators. The neural network model is capable of leveraging real-time information to achieve dynamic parameter adjustment during population search. Moreover, a policy gradient-based reinforcement learning method is utilized to update the parameters of GRU. An adaptive evolution mechanism is employed in LAGA for the autonomous selection of crossover operators. Additionally, the heuristic initialization method, elite strategy, and local search method are incorporated into LAGA to enhance overall performance. Simulation experiments demonstrate the effectiveness of LAGA in solving the EESSP. This study highlights the advantages of utilizing reinforcement learning to optimize neural network models for controlling genetic algorithm searches. Learning adaptive planning methods can effectively address complex problem scenarios and enhance satellite scheduling system performance.

Prediction Intervals for Granular Data Streams Based on Evolving Type-2 Fuzzy Granular Neural Network Dynamic Ensemble

Granular data streams (GDSs) are a class of high-level abstract multitime scale description of data streams. Prediction intervals (PIs) for GDSs that provide estimated values as well as their corresponding reliability play an important role for assisting on-site workers to perceive the nonstationary environment in real time. However, constructing reliable PIs for GDSs constitutes a significant challenge. To provide a solution to the problem, an interval type-2 (IT2) fuzzy granular neural network (FGNN) dynamic ensemble approach (IT2FGNNDEnsemble) is proposed in this article. To fully reflect the uncertainty of GDSs, an interval value learning algorithm based IT2FGNN is developed, which can automatically generate, prune, merge, and realize recall in a single-pass learning mode. In addition, an evolving dynamic ensemble method is presented by providing an adaptive structure that considers a tradeoff between coverage and width of PIs, which can dynamically generate and prune the element of an ensemble according to current data tendency. A number of synthetic and industrial data streams experimentally validate the performance of the proposed IT2FGNNDEnsemble by using the state-of-the-art comparative methods. It is demonstrated that the proposed approach exhibits a good performance on PIs for practical applications.

BEND: Bagging Deep Learning Training Based on Efficient Neural Network Diffusion

Bagging has achieved great success in the field of machine learning by integrating multiple base classifiers to build a single strong classifier to reduce model variance. The performance improvement of bagging mainly relies on the number and diversity of base classifiers. However, traditional deep learning model training methods are expensive to train individually and difficult to train multiple models with low similarity in a restricted dataset. Recently, diffusion models, which have been tremendously successful in the fields of imaging and vision, have been found to be effective in generating neural network model weights and biases with diversity. We creatively propose a Bagging deep learning training algorithm based on Efficient Neural network Diffusion (BEND). The originality of BEND comes from the first use of a neural network diffusion model to efficiently build base classifiers for bagging. Our approach is simple but effective, first using multiple trained model weights and biases as inputs to train autoencoder and latent diffusion model to realize a diffusion model from noise to valid neural network parameters. Subsequently, we generate several base classifiers using the trained diffusion model. Finally, we integrate these ba se classifiers for various inference tasks using the Bagging method. Resulting experiments on multiple models and datasets show that our proposed BEND algorithm can consistently outperform the mean and median accuracies of both the original trained model and the diffused model. At the same time, new models diffused using the diffusion model have higher diversity and lower cost than multiple models trained using traditional methods. The BEND approach successfully introduces diffusion models into the new deep learning training domain and provides a new paradigm for future deep learning training and inference.

Concepts and Design Aspects of Granular Models of Type-1 and Type-2

In this study, we pursue a new direction for system modeling by introducing the concept of granular models, which produce results in the form of information granules (such as intervals, fuzzy sets, and rough sets).We present a rationale and several key motivating arguments behind the use of granular models and discuss their underlying design processes.The development of the granular model includes optimal allocation of information granularity through optimizing the criteria of coverage and specificity.The emergence and construction of granular models of type-2 and type-n (in general) is discussed.It is shown that achieving a suitable coverage-specificity tradeoff (compromise) is essential for developing granular models.