Publications

FUZZY TRANSFER LEARNING IN DATA-SHORTAGE AND RAPIDLY CHANGING ENVIRONMENTS

IEEE Transactions on Systems, Man, and Cybernetics publication information

Resource allocation among multiple targets for a defender-attacker game with false targets consideration

An integrated neural network with nonlinear output structure for interval-valued data

In this paper, an integrated model combining interval deep belief network (IDBN) and neural network with nonlinear weights, called IDBN-NN, is proposed for interval-valued data modeling. Firstly, the IDBN with variable learning rate is designed to initialize parameters of each sub-model. Based on a modified contrastive divergence algorithm the least square method is adopted to identify the coefficients of nonlinear weights in the output layer. Then, to improve the modeling accuracy, the Fuzzy C-Means (FCM) method and the Particle Swarm Optimization (PSO) algorithm are applied to tune the weights of sub-models. Though each sub-model can capture the nonlinear feature of the original system, by intersecting cut sets the synthesizing modeling scheme can further improve the performance of the proposed model. Some numerical examples show that the IDBN-NN with nonlinear output structure can achieve higher accuracy than some interval-valued data modeling methods.

IEEE Transactions on Systems, Man, and Cybernetics publication information

Adaptive Deep Learning from Crowds

In the data-driven era, collecting high-quality labeled data requiring human labor is a common approach for training data-hungry models, called crowdsourcing. Recently, end-to-end learning from crowds has shown its flexibility and practicality. However, existing works in an end-to-end manner focus on learning after collecting labels, which results in noisy annotations and also requires cost. Inspired by computerized adaptive testing, we argue that the characteristics of workers should be mined as soon as possible to make the best use of talents. To this end, we propose an adaptive learning from crowds method, AdaCrowd, as a cost-effective solution. Specifically, we propose a probabilistic model to capture the informativeness of possible instances for each worker. The informativeness is considered to be the uncertainty of the annotation prediction model output in its current status. The adaptive learning procedure is optimized by maximizing data likelihood and can be used with existing crowdsourcing models. Extensive experiments are conducted on real-world datasets, LabelMe and CIFAR-10H. The experimental results, e.g., the reduction of annotations without performance degradation, demonstrate the effectiveness.

Soft-Sensing of Burn-Through Point Based on Weighted Kernel Just-in-Time Learning and Fuzzy Broad-Learning System in Sintering Process

Burn-through point (BTP) is an essential thermal state parameter in a sintering process, which is a direct reflection of the stability of this process. However, it cannot be measured online. Soft-sensing technology offers a reliable method for estimating unmeasurable variables in industrial processes. Here, a soft-sensing model for BTP based on weighted kernel just-in-time learning (WKJITL) and fuzzy broad-learning system (FBLS) is built. First, an abnormal production data detection and correction strategy is employed to process the production data, and the mechanism analysis and mutual information analysis are utilized to specify the detectable process variables that are directly related to BTP. Then, the WKJITL method is proposed to obtain historical production data similar to the query data of BTP for local learning modeling, and the FBLS is utilized as an efficient modeling method for the soft-sensing prediction of BTP. Finally, the results of simulation experiments based on actual sintering production data reveal that the developed soft-sensing model of BTP exhibits better prediction accuracy and efficiency compared with some advanced modeling methods. Furthermore, the proposed method is of general nature and can also be easily applied to other industrial processes.

An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems

Recent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context of HIN. In order to address these challenges, in this article, we propose a novel approach of semantic-aware HIN embedding-based recommendation, called SemHE4Rec. In our proposed SemHE4Rec model, we define two embedding techniques for efficiently learning the representations of both users and items in the context of HIN. These rich-structural user and item representations are then used to facilitate the matrix factorization (MF) process. The first embedding technique is a traditional co-occurrence representation learning (CoRL) approach which aims to learn the co-occurrence of structural features of users and items. These structural features are represented for their interconnections in terms of meta-paths. In order to do that, we adopt the well-known meta-path-based random walk strategy and heterogeneous Skip-gram architecture. The second embedding approach is a semantic-aware representation learning (SRL) method. The SRL embedding technique is designed to focus on capturing the unstructured semantic relations between users and item content for the recommendation task. Finally, all the learned representations of users and items are then jointly combined and optimized while integrating with the extended MF for the recommendation task. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed SemHE4Rec in comparison with the recent state-of-the-art HIN embedding-based recommendation techniques, and reveal that the joint text-based and co-occurrence-based representation learning can help to improve the recommendation performance.

PARTIAL BACKORDERING INVENTORY MODEL WITH LIMITED STORAGE CAPACITY UNDER ORDER-SIZE DEPENDENT TRADE CREDIT

This study formulates an inventory model with limited storage capacity under the condition of order-size dependent trade credit. Shortages are allowed and partially backlogged. The objective of this study is to determine the optimal replenishment cycle length, the optimal fraction of no shortage, and whether retailers should choose to rent an extra warehouse to store more items, such that retailers’ total annual profit is maximized. We prove the global optimally of objective functions and derive the closed-form optimal solution. Some numerical examples are presented to illustrate the applicability of the proposed model. Sensitivity analysis is carried out and managerial insights are obtained. We find that if retailers’ own warehouse capacity is relatively small, they always benefit from enlarging order quantity and renting an extra warehouse; meanwhile, suppliers further prolong the credit period is beneficial for both parties. On the contrary, as retailers’ own warehouse capacity increases and exceeds the optimal order quantity under that of without capacity constraints, adopting the same replenishment strategy as that without capacity constraints is profitable for retailers. Our results also reveal that other model parameters (e.g., ordering cost, inventory holding cost, shortages cost, backordering rate, etc.) have a significant impact on retailers’ optimal decisions.

13th International Conference on Theory and Application of Fuzzy Systems and Soft Computing — ICAFS-2018

Design of Fuzzy Relation-Based Polynomial Neural Networks Using Information Granulation and Symbolic Gene Type Genetic Algorithms

Corrigendum to ‘ECA Rule Learning in Dynamic Environments’ [Expert Systems with Applications, 41(17) (2014) 7847–7857]

Genetically Optimized Self-Organizing Neural Networks Based on PNs and FPNs

Special Issue: Guest Editorial: Computational Intelligence in Web-Based Education

Hierarchies of Architectures of Collaborative Computational Intelligence

Computational Intelligence (CI) supports a wealth of methodologies and a plethora of algorithmic developments essential to the construction of intelligent systems. Being faced with inherently distributed data which become evident, the paradigm of CI calls for further enhancements along the line of designing systems that are hierarchical and collaborative in nature. This emerging direction could be referred to as collaborative Computational Intelligence (or C2I for brief). The pervasive phenomenon encountered in architectures of C2I is that collaboration is synonym of knowledge sharing, knowledge reuse and knowledge reconciliation. Knowledge itself comes in different ways: as some structural findings in data and usually formalized in the framework of information granules, locally available models, some action plans, classification schemes, and alike. In such distributed systems sharing data is not feasible given existing technical constraints which are quite often exacerbated by non-technical requirements of privacy or security. In this study, we elaborate on the design of information granules which comes hand in hand with various clustering techniques and fuzzy clustering, in particular.

Paul Wang: Pro Memoria

Identification of Fuzzy Rule-Based Models With Collaborative Fuzzy Clustering

Fuzzy rule-based models (FRBMs) are sound constructs to describe complex systems. However, in reality, we may encounter situations, where the user or owner of a system only owns either the input or output data of that system (the other part could be owned by another user); and due to the consideration of data privacy, he/she could not obtain all the needed data to build the FRBMs. Since this type of situation has not been fully realized (noticed) and studied before, our objective is to come up with some strategy to address this challenge to meet the specific privacy consideration during the modeling process. In this study, the concept and algorithm of the collaborative fuzzy clustering (CFC) are applied to the identification of FRBMs, describing either multiple-input-single-output (MISO) or multiple-input-multiple-output (MIMO) systems. The collaboration between input and output spaces based on their structural information (conveyed in terms of the corresponding partition matrices) makes it possible to build FRBMs when input and output data could not be collected and used in unison. Surprisingly, on top of this primary pursuit, with the collaboration mechanism the input and output spaces of a system are endowed with an innovative way to comprehensively share, exchange, and utilize the structural information between each other, which results in their more relevant structures that guarantee better model performance compared with performance produced by some state-of-the-art modeling strategies. The effectiveness of the proposed approach is demonstrated by experiments on a series of synthetic and publicly available datasets.

IEEE Transactions on Systems, Man, and Cybernetics publication information

is an organization within the framework of the IEEE, with professional interest in the closely interrelated fields of man-machine systems, systems science, systems engineering, and cybernetics.