Solomon Atnafu

Similarity-based operators and query optimization for multimedia database systems

The many successful research results in the domain of computer vision have made similarity based data retrieval techniques a promising approach. As a result, the integration of similarity based retrieval techniques of multimedia data into DBMSs is currently an active research issue. We first illustrate the importance of similarity based operations. Then, we present our image data repository model that supports similarity based operations conveniently under an object-relational database paradigm. Furthermore, we present novel similarity based operators on image tables and study their properties. Finally, based on the properties of the operators identified, we derive algebraic rules that are useful for similarity based query optimization and we introduce a cost model for an implementation of one of the major similarity based operators.

Integrating similarity-based queries in image DBMSs

Until recently, issues in image retrieval have been handled in DBMSs and in computer vision as separate research works. Nowadays, the trend is towards integrating the two approaches (content- and metadata-based) for multi-criteria image retrieval. However, most existing works and proposals in this domain lack a formal framework to deal with a multi-criteria query. In this paper, we introduce a formal framework to address this subject of image retrieval under an ORDBMS model. We first propose an image data repository model interoperable with current popular standards. Then, we present an algebraic formalism for content-based operators on image database. We study the properties of these operators and discuss query optimization issues. To demonstrate the use of our algebra, we implemented an extension of our prototype called EMIMS. Experimental evaluations on our proposed query optimization techniques used in EMIMS are presented here.

Content-based and metadata retrieval in medical image database

The need for systems that can store, represent and provide efficient retrieval facilities for images of particular interest is becoming very high in medicine. In this respect, a lot of work has been done to integrate image data in standard data processing environments. The two different approaches that are used for the representation of images are the meta-data and the content-based approaches. Users in medicine need queries that use both content-based and meta-data representations of images or salient objects. In this paper, we first present a global image data model that supports both meta-data and low-level descriptions of images and their salient objects. This allows us to make multi-criteria image retrieval (context-, semantic- and content-based queries). Then, we present an image data repository model that captures all the data described in the model and permits the integration of heterogeneous operations in a DBMS. In particular, content-based operations (content-based join and selection) in combination with traditional ones can be carried out using our model.

The use of semantic-based predicates implication to improve horizontal multimedia database fragmentation

Database fragmentation allows reducing irrelevant data accesses by grouping data frequently accessed together in dedicated segments. In this paper, we address multimedia database fragmentation to take into account the rich characteristics of multimedia objects. We particularly discuss multimedia primary horizontal fragmentation and focus on semantic-based textual predicates implication required as a pre-process in current fragmentation algorithms in order to partition multimedia data efficiently. Identifying semantic implication between similar queries (if a user searches for the images containing a car, he would probably mean auto, vehicle, van or sport-car as well) will improve the fragmentation process. Making use of the neighborhood concept in knowledge bases to identify semantic implications constitutes the core of our proposal. A prototype has been implemented to evaluate the performance of our approach.

Image data model for an efficient multi-criteria query: a case in medical databases

Since the last two decades, image database management has been practiced using different image representation methods. In the literature, images are represented using two paradigms: the metadata-based and the content-based representations. Image retrieval using the metadata is done using the traditional database operations. However, image retrieval by its low-level features requires similarity-based operations. Practice has shown that both types of operations are needed for an efficient image database management system. Particularly in medical image databases, such a mixed form of retrieval is very important. We first present a global image data model that supports both metadata and low-level descriptions of images. We illustrate our work with real examples in the medical domain. Then, using an original image data repository model, we show how relational and similarity-based operations can be integrated. Both image and salient object are considered in our model. A prototype called MIMS (medical image management system) has been realized to validate the main aspects of our approach.

Similarity-based algebra for multimedia database systems

In database management systems, the need to integrate content-based image retrieval facilities has become one of the key issues. We first illustrate the importance of such facilities with example queries and give an overview of the work done in similarity-based data retrieval. Then, we propose an image repository model that supports similarity-based operations on feature vector representations of images. Moreover, we introduce a new similarity-based algebra on image tables. Thus, we define novel similarity-based algebraic operators and study their properties. We also investigate the use of the novel operators in combination with the relational operators on image and relational tables. Finally, we study the query optimization issues.

Drought Prediction System for Improved Climate Change Mitigation

Due to climate changes and the uncertainties in future weather conditions, research on drought monitoring information received more attention from politicians and scientists. The objective of this paper is to develop a new intelligent system concept for drought information extraction and predictions from satellite images. For the modeling experiment, this study used 24 years of data sets on selected attributes. By using these data sets, ten models were developed for predicting DroughtObjects with a one- to four-month time lag for the growing season from June to October with an accuracy rate ranging from 0.71 to 0.95. The process of the system that uses the new concept was also demonstrated on an easy-to-use graphical user interface. The output of this new concept can be developed to a full system and is helpful for extracting the freely available satellite images for drought monitoring and climate change mitigation applications at different levels of decision making.

Native XML Document Fragmentation Model

As XML document is distributed across the web, it can be considered like a distributed repository of XML documents and is subjected to distribution design. However, there is no adequate works on XML document distribution design. To address the shortcomings in XML document fragmentation design, in this work, we have focused on the vertical fragmentation design of the XML documents. Two fragmentation models have been proposed: query based fragmentation and structure-and size-based fragmentation. For the query based fragmentation model, vertical fragmentation techniques are proposed using the bond energy algorithm and graphical based algorithm. We have implemented both algorithms and evaluated their performance. The performance of our fragmentation algorithms are compared with centralized and fully replicated XML documents, where better results are obtained. The Structure- and size-based Fragmentation model and its implementation algorithms are also evaluated and encouraging results are achieved.

Mobile money system design for illiterate users in rural Ethiopia

Current mobile money systems provide users with hierarchical user interface and represent money as a positive rational numbers of the form 1, 3, 4.87...N. However, research indicates that rural communities that cannot read and write have a challenge entering such numbers in to mobile money system. Navigating through hierarchical text menu is also difficult to illiterate individuals. The present study uses concepts like memory placeholders, dragging & dropping; swiping, temporary holding space, and frequency counter and proposed a system that consists of three layers. The first layer denotes user interface and uses photos of currency notes, second layer is a placeholder memory that keep record of the frequency of currency bill, and the last layer keeps record of the total digital money in the system. We believe that the proposed system enables illiterate to identify currency notes while making payments and receiving payments, count digital money while making payments and or receiving payments during transaction.

Change-aware legal document retrieval model

Legal documents play a basic role in discharging the law to the public, besides constituting learning material for students, researchers and legal practitioners. Legal documents contain text rich contents that can be structured and marked with description languages such as XML. This basic feature can be exploited by XML based retrieval models to return legal document parts that are more relevant as compared to the query results by the traditional Information Retrieval (IR) systems. Under different paradigms, legal documents are subject to change, as the laws they carry undergo modifications or amendments. The dynamicity of the law is manifested by the change in the legal documents, which may be caused for example by the socio-economic changes of the society that it is serving. This change in turn will have a sever consequence on the retrieval quality of the legal document retrieval systems. However, none of the legal document retrieval systems considered the dynamic feature of legal documents over time in their search and retrieval systems. In this work we propose a generic model for a change-aware legal document retrieval system using XML based IR approaches. Based on the model, we have designed the necessary algorithms to implement the system and developed a prototype system that demonstrates the validity of our proposed model. The experiments we conducted show that the system developed based on our model have a significant precision improvement.