Leveraging Fragmental Semantic Data to Enhance Services Discovery

Wang, Jian; Zhang, Jia; Hung, Patrick C. K.; Li, Zheng; Liu, Jianxiao; He, Ke

doi:10.1109/hpcc.2011.149

Cited by 16 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KF-IDF-DF is an enhancement of the typical TF-IDF (term frequency-inverse document frequency) that is a numerical statistic which reflects how important a word is to a document in a collection or corpus [15,16]. Compared with TF-IDF, KF-IDF-DF takes the importance of a term in characterizing a domain into consideration to improve the accuracy of the classification [15,16]. Technically, KF-IRF (keyword frequency-inverse repository frequency) calculates the rank of keywords among the vocabulary that was associated to a given classification [16].…”

Section: B Social Ensing Pea Ventsmentioning

confidence: 99%

“…Compared with TF-IDF, KF-IDF-DF takes the importance of a term in characterizing a domain into consideration to improve the accuracy of the classification [15,16]. Technically, KF-IRF (keyword frequency-inverse repository frequency) calculates the rank of keywords among the vocabulary that was associated to a given classification [16]. With KF-IRF, KF-IDF-DF can magnify the TF-IDF value of a keyword of a document if this keyword highly characterizes the classification that the document belongs to.…”

Section: B Social Ensing Pea Ventsmentioning

confidence: 99%

“…The KF-IDF-DF (keyword frequency-inverse document frequency-domain frequency) vector space of event content was also constructed upon TFS4E. KF-IDF-DF is an enhancement of the typical TF-IDF (term frequency-inverse document frequency) that is a numerical statistic which reflects how important a word is to a document in a collection or corpus [15,16]. Compared with TF-IDF, KF-IDF-DF takes the importance of a term in characterizing a domain into consideration to improve the accuracy of the classification [15,16].…”

Section: B Social Ensing Pea Ventsmentioning

confidence: 99%

See 2 more Smart Citations

Social Sensing Enhanced Time Ruler for Real-Time Bus Service

Liu

Gong

et al. 2013

2013 Ninth International Conference on Semantics, Knowledge and Grids

View full text Add to dashboard Cite

Social sensing helps realize the real-time prediction of bus routes by perceiving social events and evaluating their influence on the time when a bus passes through a road section. This paper proposes a social sensing enhanced real-time bus service that integrates sensing ability and social networks to better understand and measure social events that influence vehicle velocity. The establishment of the real-time service revolves around the PT service quality attributions PEAs and the road condition attributions PRCAs. The processes that collect bus relevant events and further categorize them into PEA events or PRCA events were proposed respectively. A method of scoring PEAs for travelers according to social events was discussed. An artificial neural network based prediction model was proposed to estimate the bus arrival time by analyzing PRCA events.

show abstract

Section: B Social Ensing Pea Ventsmentioning

confidence: 99%

Section: B Social Ensing Pea Ventsmentioning

confidence: 99%

Section: B Social Ensing Pea Ventsmentioning

confidence: 99%

See 1 more Smart Citation

Social Sensing Enhanced Time Ruler for Real-Time Bus Service

Liu

Gong

et al. 2013

2013 Ninth International Conference on Semantics, Knowledge and Grids

View full text Add to dashboard Cite

show abstract

“…However, the systematisation of the services is usually preliminary and artificial (Wang, Zhang, et al 2011). A few approaches (Pop et al 2010;Zhou et al 2013;Elgazzar, Hassan, and Martin 2010;Wu et al 2014;Zhang et al 2012) have been proposed to automatically cluster the services into domains.…”

Section: Introductionmentioning

confidence: 99%

Domain-aware reputable service recommendation in heterogeneous manufacturing service ecosystem

Fan

Huang

Tan

et al. 2014

International Journal of Computer Integrated Manufacturing

View full text Add to dashboard Cite

Networked manufacturing becomes an important manufacturing method for modern manufacturing enterprises. With the wide adoption of service-oriented architecture and cloud manufacturing, manufacturing enterprises and organisations publish their manufacturing capability, such as resources, processes and knowledge as manufacturing services. A rapidly growing manufacturing service ecosystem can be observed nowadays, which brings the information overload problem for the service selection. Thus, how to organise these services and how to recommend the reputable services become two important issues for the manufacturing service retrieval and reuse. In this paper, the service cluster method WSTPCluster, which develops the topic model based on Latent Dirichlet Allocation, is employed to cluster services into specific domains. As the service ecosystem can be modelled as a heterogeneous service network, a unified reputation propagation method URPM is proposed to calculate the reputation of services and to distinguish the reputable services in each domain. Combining WSTPCluster and URPM, domain-aware reputable service recommendation method is introduced to recommend the high reputable services in each domain for the consumers. Experiments show that this method brings a better performance both in the recommendation accuracy and in the long tail recommendation.

show abstract

“…For the publicly accessible service registries such as ProgrammableWeb, we have developed a service categorization method enhanced by incrementally enriched domain knowledge [23]. Using this method, the services in the registry can be classified into different domains.…”

Section: Discover Servicesmentioning

confidence: 99%