Showing papers by "Ramez Elmasri published in 2010"

Fusion Techniques for Reliable Information: A Survey

Abstract: Information fused by multi-sensors is an important factor for obtaining reliable contextual information in smart spaces which use the pervasive and ubiquitous computing techniques. Adaptive fusion improves robust operational system performances then makes a reliable decision by reducing uncertain information. However, these fusion techniques suffer from problems regarding the accuracy of estimation or inference. No commonly accepted approaches exist currently. In this survey, we introduce the advantages and disadvantages of fusion techniques which can be used in specific applications. Second, we categorize well-known models, algorithms, systems, and applications depending on the proposed approaches. Finally, we discuss the related issues for fusion techniques within the smart spaces then suggest research directions for improving the decision-making in uncertain situation.

A Static Evidential Network for Context Reasoning in Home-Based Care

Abstract: In home-based care, reliable contextual information of remotely monitored patients should be generated by correctly recognizing the activities to prevent hazardous situations of the patient. It is difficult to achieve a higher confidence level of contextual information for several reasons. First, low-level data from multisensors have different degrees of uncertainty. Second, generated contexts can be conflicting, even though they are acquired by simultaneous operations. We propose the static evidential fusion process (SEFP) as a context-reasoning method. The context-reasoning method processes sensor data with an evidential form based on the Dezert-Smarandache theory (DSmT). The DSmT approach reduces ambiguous or conflicting contextual information in multisensor networks. Moreover, we compare SEFP based on DSmT with traditional fusion processes such as Bayesian networks and the Dempster-Shafer theory to understand the uncertainty analysis in decision making and to show the improvement of the DSmT approach compared to the others.

XCDSearch: An XML Context-Driven Search Engine

Abstract: We present in this paper, a context-driven search engine called XCDSearch for answering XML Keyword-based queries as well as Loosely Structured queries, using a stack-based sort-merge algorithm. Most current research is focused on building relationships between data elements based solely on their labels and proximity to one another, while overlooking the contexts of the elements, which may lead to erroneous results. Since a data element is generally a characteristic of its parent, its context is determined by its parent. We observe that we could treat each set of elements consisting of a parent and its children data elements as one unified entity, and then use a stack-based sort-merge algorithm employing context-driven search techniques for determining the relationships between the different unified entities. We evaluated XCDSearch experimentally and compared it with five other search engines. The results showed marked improvement.

BusSEngine: a business search engine

Abstract: With the emergence of World Wide Web, business' databases are increasingly being queried directly by customers. The customers may not be aware of the underlying data and its structure, and might have never learned a query language that enables them to issue structured queries. Some of the business' employees who query the databases may also not be aware of the structure of the data, but they are likely to be aware of some labels of elements containing data. We propose in this article: (1) an XML Keyword-Based search engine for answering business' customers called BusSEngine-K, and (2) an XML loosely Structured-Based search engine for answering business' employees called BusSEngine-L. The two engines employ novel context-driven search techniques and are built on top of XQuery search engine. The two engines were evaluated experimentally and compared with three recently proposed XML search engines. The results showed marked improvement.

Context reasoning under uncertainty based on evidential fusion networks in home-based care

Abstract: Pervasive computing technologies use embedded intelligent systems to enable various real-time applications. Some of these applications are: continuous healthcare monitoring, autonomous diagnosis and treatment, and remote disease management without spatial-temporal limitations. Additional healthcare applications include home-based care, disaster relief management, medical facility management, and sports health management. Issues related to the pervasive healthcare are generally classified into five categories: Hardware, Software, Regulations, Standardization and Organization. Our focus in this dissertation is on software issues. We propose new methods to generate a reliable context in a pervasive information system that has high rates of new measurements over time using data aggregation and data fusion. Different aggregation and fusion techniques can be applied depending on the types of sensed data and autonomous processing within the fusion step. The goal of this research is to produce a high confidence level in the generated context for remote monitoring of patients. Reliable contextual information of remotely monitored patients can prevent hazardous situations by recognizing emergency situations in home-based care. However, it is difficult to achieve a high confidence level of contextual information for several reasons. First, the pieces of information obtained from multi-sensors have different degrees of uncertainty. Second, generated contexts can be conflicting even though they are acquired by simultaneous operations. And last, context reasoning over time is difficult because of unpredictable temporal changes in sensory information. In particular, some types of contextual information are more important than others in home-based care. The weight of this information may change, due to the aggregation of the various sensors (evidence) and the variation of the values of the various sensors (evidence) over time. This causes difficulty in defining the absolute weight of the evidence in order to obtain the correct decision making. In this dissertation, we propose an evidential fusion process as a context reasoning method based on the defined context classification and state-space based context modeling. First, the context reasoning method processes sensed data with an evidential form based on Dezert-Smarandache Theory (DSmT). The DSmT approach reduces ambiguous or conflicting contextual information in multi-sensor networks. Second, we deal with dynamic metrics such as preference, temporal consistency, and relation-dependency of the context using Autonomous Learning Process (ALP) and Temporal Belief Filtering (TBF) in order to improve the confidence level of contextual information that makes a correct decision about the situation of the patient. And last, we deal with both relative and individual importance of the evidence to obtain an optimal weight of the evidence. We then apply dynamic weights of the evidence into Dynamic Evidential Network (DEN) in order to improve the confidence level of the context and to understand the emergency progress of the patient in home-based care. Finally, we compare the Evidential Fusion Process on DSmT with traditional fusion processes such as Bayesian Networks (BNs), Dempster-Shafer Theory (DST), and Dynamic Bayesian Networks (DBNs). This comparison makes us understand the uncertainty analysis in decision-making by distinguishing sensor reading errors (i.e., false alarm) from new sensor activations or deactivations, and shows the improvement of our proposed method compared to the others. The main contributions of the proposed context reasoning method under uncertainty based on evidential fusion networks are: 1) Reducing the conflicting mass in uncertainty level and improving the confidence level by adapting the DSmT, 2) Distinguishing the sensor reading error from new sensor activations or deactivations by considering the ALP and the TBF algorithm, and 3) Representing optimal weights of the evidence by applying the normalized weighting technique into related context attributes. These advantages help to make correct decisions about the situation of the patient in home-based care.

A Dynamic Normalized Weighting Based Context Reasoning in Home-Based Care

Abstract: Some types of contextual information are more important than others for inferring a situation of the patient in home-based care. The weight of this information may be changed due to the variations of the sensed values over time. Some researches applied a static weighting based fusion process to their systems to model these variations. However, this fusion process sometimes reduces the reliability of contextual information, since it does not consider a dynamic change of the importance over time. We propose the dynamic weighting based evidential fusion process (DWEFP) as a context reasoning method. DWEFP applies a normalized weighting technique to dynamic evidential networks for improving the confidence level of contextual information. To show the improvement of the proposed method, we compare our DWEFP with previous static weighting based fusion methods such as Bayesian Networks (BNs), Dempster-Shafer Theory (DST), Static Evidential Fusion Process (SEFP), Dynamic Evidential Fusion Process (DEFP), and Dynamic Bayesian Networks (DBNs).

A Framework for Enhancing Non Context-Driven XML Search

Abstract: A data element specifies one of the characteristics of its parent element. Therefore, the context of a data element is determined by its parent. Non context driven search engines build relationships between data nodes based solely on their labels and proximity to one another while overlooking their contexts. Therefore, they may return faulty answers. This paper investigates the pitfalls and limitations of non context-driven XML search engines, which caused by overlooking elements' contexts. We propose a generic context-driven search frame- work, which could be used as a layer on top of the frameworks of non context-driven search systems.

Enhancing personalized search and improving accuracy and performance for keyword-based xml queries

Abstract: This dissertation research focuses on three aspects related to querying of XML data. The three focus areas are: (1) Improving accuracy of XML keyword queries by modeling the contexts of XML elements; (2) Enhancing XML-based personalized search by using group profiling to determine individual preferences; and (3) Improving performance of distributed XML querying by caching of frequently-used query results. For each of these three focus areas, we developed formal concepts and algorithms that lead to the improved accuracy and performance. Our contributions are as follows: (1) Improving the accuracy of XML keyword queries: We improve search accuracy by utilizing nodes’ contexts in an XML tree. Overlooking nodes’ contexts when building relationships between the nodes may lead to erroneous query results. The context of a data node is determined by its parent node. By treating each set of nodes consisting of a parent and its children data nodes as one unified entity and then determining the relationships between the different unified entities, an XML system can build much more accurate relationships between data nodes in less processing time, resulting in more accurate query results. (2) Enhancing XML-based personalized search: By pre-defining and categorizing social groups based on demographic, ethnic, cultural, religious, or other characteristics, a user profile could be inferred from the profiles of the social groups to which the user belongs. This would simplify personalized search and make its process more efficient. We implemented this approach in an XML-based recommender system. The system is able to output ranked lists of content items taking into account not only the initial preferences of the user, but also the preferences of the user’s various social groups. (3) Improving performance of distributed XML querying: Distributed XML documents are too big and complicated to be rapidly queried every time a user submits a query due to the overhead involved in decomposing the queries, sending the decomposed queries to remote site(s), and executing structural join operations to compose the results. We investigated strategies and mechanisms to tackle these problems. We then implemented these mechanisms in a query processor, and compared their performance to standard XML query processors.