A recommender system aims to provide users with personalized online product or service recommendations to handle the increasing online information overload problem and improve customer relationship management. Various recommender system techniques have been proposed since the mid-1990s, and many sorts of recommender system software have been developed recently for a variety of applications. Researchers and managers recognize that recommender systems offer great opportunities and challenges for business, government, education, and other domains, with more recent successful developments of recommender systems for real-world applications becoming apparent. It is thus vital that a high quality, instructive review of current trends should be conducted, not only of the theoretical research results but more importantly of the practical developments in recommender systems. This paper therefore reviews up-to-date application developments of recommender systems, clusters their applications into eight main categories: e-government, e-business, e-commerce/e-shopping, e-library, e-learning, e-tourism, e-resource services and e-group activities, and summarizes the related recommendation techniques used in each category. It systematically examines the reported recommender systems through four dimensions: recommendation methods (such as CF), recommender systems software (such as BizSeeker), real-world application domains (such as e-business) and application platforms (such as mobilebased platforms). Some significant new topics are identified and listed as new directions. By providing a stateof-the-art knowledge, this survey will directly support researchers and practical professionals in their understanding of developments in recommender system applications.

No abstract

a b s t r a c t 26 Transfer learning aims to provide a framework to utilize previously-acquired knowledge to solve new 27 but similar problems much more quickly and effectively. In contrast to classical machine learning 28 methods, transfer learning methods exploit the knowledge accumulated from data in auxiliary domains 29 to facilitate predictive modeling consisting of different data patterns in the current domain. To improve 30 the performance of existing transfer learning methods and handle the knowledge transfer process in 31 real-world systems, computational intelligence has recently been applied in transfer learning. This paper 32 systematically examines computational intelligence-based transfer learning techniques and clusters 33 related technique developments into four main categories: (a) neural network-based transfer learning; 34 (b) Bayes-based transfer learning; (c) fuzzy transfer learning, and (d) applications of computational 35 intelligence-based transfer learning. By providing state-of-the-art knowledge, this survey will directly 36 support researchers and practice-based professionals to understand the developments in computational 37 intelligence-based transfer learning research and applications.38

Recently, pancreatic ductal adenocarcinoma (PDAC) has emerged as one of the most aggressive malignant tumors with the worst prognosis. Previous studies have demonstrated that long noncoding RNA metastasis-associated lung adenocarcinoma transcript 1 (MALAT1) is increased in pancreatic cancer and is identified as a diagnostic biomarker. Nonetheless, the molecular mechanism of elevated MALAT1 levels and tumor aggressiveness remains unknown. In this study, MALAT1 was found to be highly expressed in PDAC tissues, and elevated expression was associated with poorer prognoses. In addition, MALAT1 was positively linearly correlated with the expression of LC3B mRNA. Furthermore, several molecules involved in cellular autophagic flux were modulated following the downregulation of MALAT1, including LC3, P62, and LAMP-2. Mechanistically, we found that MALAT1 interacted with RNA binding protein HuR, and silencing of MALAT1 greatly enhanced the posttranscriptional regulation of TIA-1 and had further effects on inhibiting autophagy. MALAT1 was speculated to regulate tumorigenesis via HuR-TIA-1-mediated autophagic activation. Hence, we investigated the biological properties of MALAT1 in terms of tumor proliferation and metastasis by promoting autophagy in vitro In brief, these data demonstrate that MALAT1 could facilitate the advanced progression of tumors in vivo Our study highlights the new roles of MALAT1 on protumorigenic functioning and anticancer therapy via activating autophagy in pancreatic cancer. Mol Cancer Ther; 15(9); 2232-43. ©2016 AACR.

No abstract

No abstract

No abstract

Within the framework of any bilevel decision problem, a leaderÕs decision is influenced by the reaction of his or her follower. When multiple followers who may have had a share in decision variables, objectives and constraints are involved in a bilevel decision problem, the leaderÕs decision will be affected, not only by the reactions of these followers, but also by the relationships among these followers. This paper firstly identifies nine different kinds of relationships (S 1 to S 9 ) amongst followers by establishing a general framework for bilevel multi-follower decision problems. For each of the nine a corresponding bilevel multi-follower decision model is then developed. Also, this paper particularly proposes related theories focusing on an uncooperative decision problem (i.e., S 1 model), as this model is the most basic one for bilevel multi-follower decision problems over the nine kinds of relationships. Moreover, this paper extends the Kuhn-Tucker approach for driving an optimal solution from the uncooperative decision model. Finally, a real case study of a road network problem illustrates the application of the uncooperative bilevel decision model and the proposed extended Kuhn-Tucker approach.