共查询到20条相似文献，搜索用时 73 毫秒
1.
Traditionally, recommender systems for the web deal with applications that have two dimensions, users and items. Based on access data that relate these dimensions, a recommendation model can be built and used to identify a set of N items that will be of interest to a certain user. In this paper we propose a multidimensional approach, called DaVI (Dimensions as Virtual Items), that consists in inserting contextual and background information as new user–item pairs. The main advantage of this approach is that it can be applied in combination with several existing two-dimensional recommendation algorithms. To evaluate its effectiveness, we used the DaVI approach with two different top-N recommender algorithms, Item-based Collaborative Filtering and Association Rules based, and ran an extensive set of experiments in three different real world data sets. In addition, we have also compared our approach to the previously introduced combined reduction and weight post-filtering approaches. The empirical results strongly indicate that our approach enables the application of existing two-dimensional recommendation algorithms in multidimensional data, exploiting the useful information of these data to improve the predictive ability of top-N recommender systems. 相似文献
2.
This paper is concerned with the robust stability of uncertain neutral-type Lur?e system with time-varying delays and sector bounded nonlinearities. By constructing a modified Lyapunov–Krasovskii functional (LKF), some new robust stability criteria are proposed in terms of linear matrix inequalities (LMIs) without using the general free-weighting matrix method. The criteria are less conservative and more efficiently calculative than some previous ones. Four numerical examples are presented to show the effectiveness and merits of the proposed approach. 相似文献
3.
Yuan-Yong Huang 《Journal of The Franklin Institute》2007,344(8):1075-1090
For finite-dimensional linear systems, the Youla-Kucera parameterization (YKP) with a Q parameter over RH∞ is assumed to satisfy the Diophantine identity. However, the stability is guaranteed if the Diophantine equation is the “U(RH∞)“ equality, but not if it is the “identity” equality. However, Vidyasagar's structure with an H parameter over U(RH∞) is an observer-controller configuration that satisfies the Diophantine equation. This study discusses the deficiency of the Diophantine identity; expands the YKP using an H parameter over U(RH∞), and expands the Vidyasagar's structure using a Qv parameter over RH∞ so that both of the expanded parameterizations satisfy the Diophantine equation and are equivalent for all stabilizing compensators. Moreover, an equation that relates to Q, Qv, and H will be introduced to establish relationships among the YKP, Vidyasagar's structure and both expanded parameterizations. 相似文献
4.
《Information processing & management》2016,52(5):923-948
Across the world, millions of users interact with search engines every day to satisfy their information needs. As the Web grows bigger over time, such information needs, manifested through user search queries, also become more complex. However, there has been no systematic study that quantifies the structural complexity of Web search queries. In this research, we make an attempt towards understanding and characterizing the syntactic complexity of search queries using a multi-pronged approach. We use traditional statistical language modeling techniques to quantify and compare the perplexity of queries with natural language (NL). We then use complex network analysis for a comparative analysis of the topological properties of queries issued by real Web users and those generated by statistical models. Finally, we conduct experiments to study whether search engine users are able to identify real queries, when presented along with model-generated ones. The three complementary studies show that the syntactic structure of Web queries is more complex than what n-grams can capture, but simpler than NL. Queries, thus, seem to represent an intermediate stage between syntactic and non-syntactic communication. 相似文献
5.
《Information processing & management》2001,37(2):295-311
A growing body of research is beginning to explore the information-seeking behavior of Web users. The vast majority of these studies have concentrated on the area of textual information retrieval (IR). Little research has examined how people search for non-textual information on the Internet, and few large-scale studies has investigated visual information-seeking behavior with general-purpose Web search engines. This study examined visual information needs as expressed in users’ Web image queries. The data set examined consisted of 1,025,908 sequential queries from 211,058 users of Excite, a major Internet search service. Twenty-eight terms were used to identify queries for both still and moving images, resulting in a subset of 33,149 image queries by 9855 users. We provide data on: (1) image queries – the number of queries and the number of search terms per user, (2) image search sessions – the number of queries per user, modifications made to subsequent queries in a session, and (3) image terms – their rank/frequency distribution and the most highly used search terms. On average, there were 3.36 image queries per user containing an average of 3.74 terms per query. Image queries contained a large number of unique terms. The most frequently occurring image related terms appeared less than 10% of the time, with most terms occurring only once. We contrast this to earlier work by P.G.B. Enser, Journal of Documentation 51 (2) (1995) 126–170, who examined written queries for pictorial information in a non-digital environment. Implications for the development of models for visual information retrieval, and for the design of Web search engines are discussed. 相似文献
6.
7.
George Church receives the 2011 Bower Award and Prize for Achievement in Science for innovative and creative contributions to genomic science, including the development of DNA sequencing technologies, and for his subsequent efforts to promote personal genomics and synthetic biology. 相似文献
8.
9.
Sajad Ahmadian Majid Meghdadi Mohsen Afsharchi 《Information processing & management》2018,54(4):707-725
Recommender systems are techniques to make personalized recommendations of items to users. In e-commerce sites and online sharing communities, providing high quality recommendations is an important issue which can help the users to make effective decisions to select a set of items. Collaborative filtering is an important type of the recommender systems that produces user specific recommendations of the items based on the patterns of ratings or usage (e.g. purchases). However, the quality of predicted ratings and neighbor selection for the users are important problems in the recommender systems. Selecting suitable neighbors set for the users leads to improve the accuracy of ratings prediction in recommendation process. In this paper, a novel social recommendation method is proposed which is based on an adaptive neighbor selection mechanism. In the proposed method first of all, initial neighbors set of the users is calculated using clustering algorithm. In this step, the combination of historical ratings and social information between the users are used to form initial neighbors set for the users. Then, these neighbor sets are used to predict initial ratings of the unseen items. Moreover, the quality of the initial predicted ratings is evaluated using a reliability measure which is based on the historical ratings and social information between the users. Then, a confidence model is proposed to remove useless users from the initial neighbors of the users and form a new adapted neighbors set for the users. Finally, new ratings of the unseen items are predicted using the new adapted neighbors set of the users and the interested items are recommended to the active user. Experimental results on three real-world datasets show that the proposed method significantly outperforms several state-of-the-art recommendation methods. 相似文献
10.
《Information processing & management》2005,41(3):475-487
In this paper, we compile and review several experiments measuring cross-lingual information retrieval (CLIR) performance as a function of the following resources: bilingual term lists, parallel corpora, machine translation (MT), and stemmers. Our CLIR system uses a simple probabilistic language model; the studies used TREC test corpora over Chinese, Spanish and Arabic. Our findings include:
- •One can achieve an acceptable CLIR performance using only a bilingual term list (70–80% on Chinese and Arabic corpora).
- •However, if a bilingual term list and parallel corpora are available, CLIR performance can rival monolingual performance.
- •If no parallel corpus is available, pseudo-parallel texts produced by an MT system can partially overcome the lack of parallel text.
- •While stemming is useful normally, with a very large parallel corpus for Arabic–English, stemming hurt performance in our empirical studies with Arabic, a highly inflected language.
11.
The ECDIN (Environmental Chemicals Data and Information Network) project started in 1973. During the pilot phase of operation the feasibility of the system was demonstrated using a data base of 4000 compounds and the SIMAS information retrieval system. It was quickly realised that for ECDIN data management was as important as information retrieval and in November 1977, after a study of available software, the ADABAS data base management system was installed at JRC Ispra for ECDIN and other JRC data banks. A design exercise for the ECDIN ADABAS data base has been completed and parts of the existing ECDIN data base have been converted to the new system. The problems encountered and the solutions adopted are discussed. The user interface to ECDIN is still under development. When fully operational ECDIN will be available through EURONET to both casual and specialist users and, in consequence, at least two levels of user interface will be required: (a) a user friendly conversational language designed for the casual user and capable of dealing with the more common types of question, (b) a sophisticated query language capable of answering the more difficult questions, producing “one-off” reports and probably requiring both a specialist knowledge of the data base and a programmer oriented background. The first tentative steps in this direction are described. 相似文献
12.
Matrix factorization-based methods become popular in dyadic data analysis, where a fundamental problem, for example, is to perform document clustering or co-clustering words and documents given a term-document matrix. Nonnegative matrix tri-factorization (NMTF) emerges as a promising tool for co-clustering, seeking a 3-factor decomposition X≈USV? with all factor matrices restricted to be nonnegative, i.e., U?0,S?0,V?0. In this paper we develop multiplicative updates for orthogonal NMTF where X≈USV? is pursued with orthogonality constraints, U?U=I, and V?V=I, exploiting true gradients on Stiefel manifolds. Experiments on various document data sets demonstrate that our method works well for document clustering and is useful in revealing polysemous words via co-clustering words and documents. 相似文献
13.
《Information processing & management》2003,39(3):391-402
We will explore various ways to apply query structuring in cross-language information retrieval. In the first test, English queries were translated into Finnish using an electronic dictionary, and were run in a Finnish newspaper database of 55,000 articles. Queries were structured by combining the Finnish translation equivalents of the same English query key using the syn-operator of the InQuery retrieval system. Structured queries performed markedly better than unstructured queries. Second, the effects of compound-based structuring using a proximity operator for the translation equivalents of query language compound components were tested. The method was not useful in syn-based queries but resulted in decrease in retrieval effectiveness. Proper names are often non-identical spelling variants in different languages. This allows n-gram based translation of names not included in a dictionary. In the third test, a query structuring method where the Boolean and-operator was used to assign more weight to keys translated through n-gram matching gave good results. 相似文献
14.
Purpose
The study reported in this paper reviewed the literatures of information science, psychology, sociology, political science, education, and communication science to analyze Compelled Nonuse of Information (CNI). This study of a behavior defined by its absence (i.e., the not using of information) involved the development of a methodology consisting of an iterative performance of a nine-step heuristic leading to a retroductive recognition of absence, here termed RRA.Principal results
The study concluded with a hierarchical taxonomy of the mechanisms that compel a person not to use information. The six primary mechanisms are:- 1.
- Intrinsic somatic (bodily) conditions
- 2.
- Socio-environmental barriers
- 3.
- Authoritarian controls
- 4.
- Threshold knowledge shortfall
- 5.
- Attention shortfall
- 6.
- Information filtering.
Major conclusions
The resultant taxonomy of CNI appears here as a comprehensive checklist with which information workers such as the teacher, librarian, advertiser, politician, or health care professional can respond efficiently and effectively to situations of nonuse of information. For example, a teacher might ask: “Why are students not responding to what I present?” Further, the social implications of any compelled behavior touch the very basis of the social contract, and this paper presents a first step toward understanding the compelled aspects of CNI. 相似文献15.
Vandana Rai 《Indian journal of clinical biochemistry : IJCB》2016,31(4):402-413
The C677T polymorphism of the methylenetetrahydrofolate reductase (MTHFR) gene was implicated to be associated with thrombophilia due to its role in catalyzing the formation of 5-methylenetetrahydrofolate, a co-substrate for the conversion of homocysteine to methionine. Several case–control studies were investigated MTHFR C677T polymorphism as risk for recurrent pregnancy loss (RPL). These studies rendered contradictory results, some indicating that the polymorphism is associated with the risk of RPL whereas others concluded there is no association. To shed light on these inconclusive findings, a meta-analysis of all available studies published from Asian population relating the C677T polymorphism to the risk of RPL was conducted. The following electronic databases were searched without language restrictions: PubMed, Google Scholars, Elsevier and Springer Link up to December, 2015. Meta-analysis was performed using MetaAnalyst and Mix version 1.7. Meta-analysis results suggested that MTHFR C677T polymorphism contributed to the increased RPL risk in Asian population using all five genetic models (for T vs. C: OR 1.35, 95 % CI 1.09–1.68, p = 0.009; for TT + CT vs. CC: OR 1.44, 95 % CI 1.14–1.82, p = 0.006; for CT vs. CC: OR 1.39, 95 % CI 1.07–1.8, p = 0.01; for TT vs. CC: OR 1.79, 95 % CI 1.23.2.6, p = 0.007; for TT vs. CT + CC: OR 1.61, 95 % CI 1.02–2.56, p = 0.04). In conclusion, this meta-analysis demonstrates a strong association between the MTHFR C677T variant and RPL in Asian population and raising the importance of the use of folate in its treatment and prevention. 相似文献
16.
Knowledge management (KM) in information technology outsourcing (ITO) is important to the organizations which pursue long-term strategic benefits and innovation. Effective KM mechanism in outsourcing enables both parties to continuously exchange knowledge and promotes collective learning. This paper investigates the role of Lean principles in supporting KM in ITO relationships. Drawn from the knowledge-based view of the firm, knowledge accessing and knowledge integration and utilization are identified as two key KM processes in outsourcing. Three case studies conducted in different service industries with 18 interviews indicate that the two KM processes were supported by four Lean principles: respect for people, continuous improvement, systems thinking, and proactive behavior. Those principles can be implemented with different tools at different organizational levels. This study reveals the relevance between Lean and KM in ITO relationships, which has not been reported by the KM literature. It also provides implications to ITO practitioners for the implementation of Lean principles. 相似文献
17.
18.
Archana Verma Rakesh Kapoor Rama Devi Mittal 《Indian journal of clinical biochemistry : IJCB》2017,32(3):292-300
Adhesion molecules play a key role in cancer progression and tumorigenesis. Genetic polymorphism of adhesion molecules may alter the normal functioning thereby leading to bladder cancer susceptibility. Hence we aimed to evaluate three SNPs of CD166 gene (CD166rs6437585 C/T, CD166rs10511244 C/T, and CD166rs1157 A/G) in bladder cancer patients and normal controls of North Indian population. A total of 270 healthy controls and 240 confirmed bladder cancer patients were recruited for this study. Three SNPs of CD166 gene viz. CD166rs6437585 C/T, CD166rs10511244 C/T, and CD166rs1157 A/G were selected for this study. CD166rs6437585 C/T and CD166rs10511244 C/T were genotyped by Taqman allelic discrimination assay and CD166rs1157 A/G was genotyped by PCR–RFLP. The statistical analysis was done using the SPSS software, version 16.0 (SPSS, Chicago, IL), and p < 0.05 was considered statistically significant. Haplotypic analysis was done by using SNP analyzer version 1.2A. CD166rs6437585 C/T and CD166rs10511244 C/T showed significant association with reduced risk in bladder cancer while CD166rs1157 A/G showed significant high risk along with association at genotypic and allelic levels. Haplotypic analysis showed 1.8-folds risk in CCG combination, whereas CTA and TCG showed significant association with reduced risk. Further stratification on the basis of smoking, tumor grade/stage and BGC therapy revealed no association of these three polymorphic sites of CD166. Our study suggests that CD166rs6437585 C/T and CD166rs10511244 C/T are predictive for the reduced risk of bladder cancer, whereas CD166rs1157 A/G had shown significant association with high risk of bladder cancer in North Indians. This somehow suggests that CD166rs1157 A/G can be used as a marker for risk prediction of bladder cancer. 相似文献
19.
Knowledge is created through discourse in ba that is the physical, mental and/or virtual arena of knowledge creation. This article studies ba in international humanist (H-group), technical (T-group) and scientific (S-group) research groups. These international groups consist of members originating from many countries. The empirical evidence is derived from interviews and discourse analysis of three research groups from the University of Oulu which, by staff, is the most international large university in Finland. The article advances understanding of ba by considering the theory of ba in relation to the discourse and exploratory case study. In the case groups, ba is formed in relation to the knowledge type created, suitable characteristics of a group member and structural factors related to administrative responsibilities. Humanist knowledge, with abstract concepts and philosophical discussions, is created with deeper attention to language and social bonds inside the H-group than the more accurate scientific and technical knowledge in the S- and T-groups. 相似文献
20.
With the increasing provenance of hedonic and social information systems, systems are observed to employ other forms of feedback and design than purely informational in order to increase user engagement and motivation. Three principle classes of motivational design pursuing user engagement have become increasingly established; gamification, quantified-self and social networking. This study investigates how the perceived prominence of these three design classes in users’ use of information system facilitate experiences of affective, informational and social feedback as well as user’s perceived benefits from a system and their continued use intentions. We employ survey data (N = 167) gathered from users of HeiaHeia; an exercise encouragement system that employs features belonging to the three design classes. The results indicate that gamification is positively associated with experiences of affective feedback, quantified-self with experiences of both affective and informational feedback and social networking with experiences of social feedback. Experiences of affective feedback are further strongly associated with user perceived benefits and continued use intentions, whereas experiences of informational feedback are only associated with continued use intentions. Experiences of social feedback had no significant relationship with neither. The findings provide practical insights into how systems can be designed to facilitate different types of feedback that increases users’ engagement, benefits and intentions to continue the use of a system. 相似文献