Abstract:The rapid development of mobile technologies has facilitated users to generate and store files on mobile devices such as mobile phones and PDAs. However, it has become a challenging issue for users to efficiently and effectively search for files of interest in a mobile environment involving a large number of mobile nodes. This paper presents SemFARM framework which facilitates users to publish, annotate and retrieve files which are geographically distributed in a mobile network enabled by Bluetooth. The SemFAR… Show more
“…Our proposed research may also be applied to various domain applications, such as mobile systems 28,29,30,31,32,33,34 , RFID 35,36 , real-time systems 37 , business process 38 , web systems 39,40,41 , and fuzzy data 42 .…”
The negative association between items in databases is as important and interesting as the positive one. But, it has not been studied as much. We consider negative association in a hierarchical setting, in which we are able to generate negative association rules at different hierarchy levels. It allows to impose restrictions when we proceed to the next level and discover only most interesting negative association rules among the vast number of possible negative association rules. In this paper, we propose two algorithms for mining negative association rules by considering that items are organized in a hierarchy, and this hierarchy is reflected on the association rules we produce. In this way, we can mine for both general and specialized rules of negative association between items.
“…Our proposed research may also be applied to various domain applications, such as mobile systems 28,29,30,31,32,33,34 , RFID 35,36 , real-time systems 37 , business process 38 , web systems 39,40,41 , and fuzzy data 42 .…”
The negative association between items in databases is as important and interesting as the positive one. But, it has not been studied as much. We consider negative association in a hierarchical setting, in which we are able to generate negative association rules at different hierarchy levels. It allows to impose restrictions when we proceed to the next level and discover only most interesting negative association rules among the vast number of possible negative association rules. In this paper, we propose two algorithms for mining negative association rules by considering that items are organized in a hierarchy, and this hierarchy is reflected on the association rules we produce. In this way, we can mine for both general and specialized rules of negative association between items.
“…To evaluate the performance of OARS comprehensively, we have formulated several test scenarios using the benchmark data sets and the evaluation criteria defined by (10), (11) and (12). The main purposes of these test scenarios are to assess:…”
Section: Similarity Aggregationmentioning
confidence: 99%
“…The annotation process automatically annotates the files with three basic attributes and two user entered fields. The meta-data is automatically parsed and stored in XML structured document as described in [12], [13] and [59]. Fig.8 shows the overall process of the SemFARM search module in which the input file queries are answered after merging two existing ontologies.…”
Section: Integrating Oars Into Semfarmmentioning
confidence: 99%
“…More importantly, the significance of using Rough sets as an aggregation method is also evaluated in this paper. Furthermore, we have integrated OARS into our previously developed SemFARM [12][13], a framework which provides an efficient search mechanism for file annotation and retrieval on mobile devices connected through Bluetooth. The integration of OARS enables SemFARM to utilize the knowledge of multiple ontologies when searching for a file on resourcelimited devices in a network environment which leads to high accuracy in file retrieval.…”
-Ontology alignment facilitates exchange of knowledge among heterogeneous data sources. Many approaches to ontology alignment use multiple similarity measures for mapping entities between ontologies. However, it remains a key challenge in dealing with uncertain entities for which the employed ontology alignment measures produce conflicting results on similarity of the mapped entities. This paper presents OARS, a Rough sets based approach to ontology alignment which achieves a high degree of accuracy in situations where uncertainty arises because of the conflicting results generated by different similarity measures. OARS employs a combinational approach and considers both lexical and structural similarity measures. OARS is extensively evaluated with the benchmark ontologies of the Ontology Alignment Evaluation Initiative (OAEI) 2010, and performs best in the aspect of recall in comparison with a number of alignment systems while generating a comparable performance in precision.
“…As the number of stored files grows on such devices it becomes a challenging issue for users to search efficiently for files of interest. For this purpose, SemFARM [1] framework was presented which annotates the files and provides semantic based file search capabilities. A generic ontology was developed to define the most comely used keywords which can be used as metadata to annotate the stored files.…”
In this paper, we present a file search mechanism that can utilize the ontology alignments to facilitate file retrieval on resource-limited devices by exploiting the knowledge of more than one ontologies. This enables the device users to take advantage of all ontologies, which might have been developed in the same domain. A semantic-based file retrieval framework was previously presented for resource-limited devices, which annotates files with its basic attributes and provides file retrieval capabilities. A generic ontology was developed to define the most commonly used keywords which can be used as metadata of the stored files. The ontology was employed to exploit the semantic based file retrieval capability. The search mechanism was evaluated by formulating two test cases. In first test case the framework make use of single ontology while in the second test case, the ontology alignments were utilized by aligning two ontologies. The implications of ontology alignment support were analyzed through probabilistic evaluation, which shows the progress in file retrieval efficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.