No abstract

Collaborative filtering (CF) recommenders based on User-Item rating matrix as explicitly obtained from end users have recently appeared promising in recommender systems. However, User-Item rating matrix is not always available or very sparse in some web applications, which has critical impact to the application of CF recommenders. In this article we aim to enhance the online recommender system by fusing virtual ratings as derived from user reviews. Specifically, taking into account of Chinese reviews' characteristics, we propose to fuse the self-supervised emotion-integrated sentiment classification results into CF recommenders, by which the User-Item Rating Matrix can be inferred by decomposing item reviews that users gave to the items. The main advantage of this approach is that it can extend CF recommenders to some web applications without user rating information. In the experiments, we have first identified the self-supervised sentiment classification's higher precision and recall by comparing it with traditional classification methods. Furthermore, the classification results, as behaving as virtual ratings, were incorporated into both user-based and item-based CF algorithms. We have also conducted an experiment to evaluate the proximity between the virtual and real ratings and clarified the effectiveness of the virtual ratings. The experimental results demonstrated the significant impact of virtual ratings on increasing system's recommendation accuracy in different data conditions (i.e., conditions with real ratings and without).

Particle Swarm Optimisation (PSO) algorithm is a stochastic search technique, which has exhibited good performance across a wide range of applications. However, very often for multimodal problems involving high dimensions, the algorithm tends to suffer from premature convergence. Analysis of the behaviour of the particle swarm model reveals that such premature convergence is mainly due to the decrease of velocity of particles in the search space that leads to a total implosion and ultimately fitness stagnation of the swarm. This paper introduces Turbulence in the Particle Swarm Optimisation (TPSO) algorithm to overcome the problem of stagnation. The algorithm uses a minimum velocity threshold to control the velocity of particles. The parameter, minimum velocity threshold of the particles is tuned adaptively by a fuzzy logic controller embedded in the TPSO algorithm, which is further called as Fuzzy Adaptive TPSO (FATPSO). We evaluated the performance of FATPSO and compared it with the Standard PSO (SPSO), Genetic Algorithm (GA) and Simulated Annealing (SA). The comparison was performed on a suite of 10 widely used benchmark problems for 30 and 100 dimensions. Empirical results illustrate that the FATPSO could prevent premature convergence very effectively and it clearly outperforms SPSO and GA. research interestes are in advanced computational intelligence with a focus on hybridising intelligent techniques involving connectionist network learning, fuzzy inference systems, swarm intelligence, evolutionary computation, distributed artificial intelligence, multiagent systems and other heuristics.Weishi Zhang is the Dean of School of Computer Science, Dalian Maritime University, Dalian, China. His research interests are in artificial intelligence, soft computing, nature-inspired computing, swarm intelligence and generic information systems development. He is an Editorial

No abstract

No abstract

Abstract.Credit risk has been a widespread and deep penetrating problem for centuries, but not until various credit derivatives and products were developed and novel technologies began radically changing the human society, have fraud detection, credit scoring and other risk management systems become so important not only to some specific firms, but to industries and governments worldwide. Frauds and unpredictable defaults cost billions of dollars each year, thus, forcing financial institutions to continuously improve their systems for loss reduction. In the past twenty years, amounts of studies have proposed the use of data mining techniques to detect frauds, score credits and manage risks, but issues such as data selection, algorithm design, and hyperparameter optimization affect the perceived ability of the proposed solutions and it is difficult for auditors and researchers to explore and figure out the highest level of general development in this area. In this survey we focus on a state of the art survey of recently developed data mining techniques for fraud detection and credit scoring. Several outstanding experiments are recorded and highlighted, and the corresponding techniques, which are mostly based on supervised learning algorithms, unsupervised learning algorithms, semisupervised algorithms, ensemble learning, transfer learning, or some hybrid ideas are explained and analysed. The goal of this paper is to provide a dense review of up-to-date techniques for fraud detection and credit scoring, a general analysis on the results achieved and upcoming challenges for further researches.

No abstract

Underwater images often show low contrast, blurring, and color distortion due to the absorption and scattering of light. In contrast to existing underwater image restoration methods, we propose an underwater image restoration method with red channel compensation and blue-green channel restoration. First, a proposed approach relies on the hue and attenuation differences between different color channels of the underwater image to estimate the background light. Then, the red channel is enhanced according to a perfect reflection assumption algorithm. Finally, a new median underwater dark channel prior (MUDCP) is proposed to precisely estimate the blue-green channel transmission map. Experimental results show that our method significantly improves contrast, removes color bias, and preserves more detail than other underwater restoration techniques.