Multimedia Data Objects Research Articles

Automatic Indexing of Digital Objects Through Learning from User Data

Digital data objects increasingly take the form of a non-textual nature, and the effective retrieval of these objects using their intrinsic contents largely depends on the underlying indexing mechanism. Since current multimedia objects are created with ever-increasing speed and ease, they often form the bulk of the data contents in large data repositories. In this study, we provide an effective automatic indexing mechanism based on learning reinforcement by systematically exploiting the big data obtained from different user interactions. Such human interaction with the search system is able to encode the human intelligence in assessing the relevance of a data object against user retrieval intentions and expectations. By methodically exploiting the big data and learning from such interactions, we establish an automatic indexing mechanism that allows multimedia data objects to be gradually indexed in the normal course of their usage. The proposed method is especially efficient for the search of multimedia data objects such as music, photographs and movies, where the use of straightforward string-matching algorithms are not applicable. The method also permits the index to respond to change in relation to user feedback, which at the same time avoids the system landing in a local optimum. Through the use of the proposed method, the accuracy of searching and retrieval of multimedia objects and documents may be significantly enhanced.

A modified hybrid whale optimization algorithm for the scheduling problem in multimedia data objects

SummaryThe scheduling of the Multimedia Data Objects (MDO) is a difficult and extraordinary issue that faces us in the World Wide Web (WWW) to minimize the response time for clients to finish rapidly their tasks. MDO scheduling problem can be modeled as a Two‐Machine Flow Shop Scheduling Problem (T‐MFSSP) that minimizes the makespan. Notwithstanding another objective is to decrease the average lateness time of the clients' jobs. This paper proposes a Modified Hybrid Whale Algorithm (MHWA) to solve a standout among the most imperative applications of flow shop scheduling in the field of MDO. MHWA is hybridized with a local search strategy for solving the scheduling problem of MDO. To cope up with the combinatorial nature of the MDO scheduling, LRV maps the continuous search space into a sequence of jobs. To get better solutions, some operations are applied to the solutions such as swap mutation and reversed block insertion operations. Nawaz‐Enscore‐Ham (NEH) is added to MHWA to upgrade the performance of the algorithm. The solution of Johnson heuristic is added to the initial population of MHWA. It can be inferred that MHWA gives competitive outcomes appeared differently in relation to Johnson and Earliest Due Date (EDD) algorithms. MHWA can obtain the optimal makespan and can minimize the average lateness of the jobs.

Query Expansion for Content-Based Similarity Search Using Local and Global Features

This article presents an efficient and totally unsupervised content-based similarity search method for multimedia data objects represented by high-dimensional feature vectors. The assumption is that the similarity measure is applicable to feature vectors of arbitrary length. During the offline process, different sets of features are selected by a generalized version of the Laplacian Score in an unsupervised way for individual data objects in the database. Online retrieval is performed by ranking the query object in the feature spaces of candidate objects. Those candidates for which the query object is ranked highly are selected as the query results. The ranking scheme is incorporated into an automated query expansion framework to further improve the semantic quality of the search result. Extensive experiments were conducted on several datasets to show the capability of the proposed method in boosting effectiveness without losing efficiency.

ConceptRank for search-based image annotation

Multimedia information is becoming an ubiquitous part of our lives, which brings an equally ubiquitous need for efficient multimedia retrieval. One of the possible solutions to this problem is to attach text descriptions to multimedia data objects, thus allowing users to utilize traditional text search mechanisms. Search-based annotation techniques attempt to determine the descriptive keywords by analyzing the descriptions of similar, already annotated multimedia objects, which are detected by content-based retrieval techniques. One of the main challenges of this approach is the extraction of semantically connected keywords from the possibly noisy descriptions of similar objects. In this paper, we address this challenge by proposing the ConceptRank, a new keyword ranking algorithm that exploits semantic relationships between candidate keywords and utilizes the random walk mechanism to compute the probability of individual candidates. The effectiveness of the ConceptRank algorithm is evaluated in context of web image annotation. We present a complex image annotation system that includes the ConceptRank component, and compare it to other state-of-the–art annotation techniques.

A Multimedia Data Management Approach with GeM-Tree

In this paper, we propose a multimedia data management framework using GeM-Tree. GeM-Tree is a multidimensional tree-based index structure which provides a generalized framework to organize and retrieve images and videos seamlessly. In addition to supporting different multimedia data types and diverse representations, the proposed data management framework supports varied multimedia retrieval strategies like content-based image and video retrieval, mixed multimedia data retrieval where cross-similarity between images and videos is considered, region-based retrieval, etc. The framework embeds a high-level semantic relationship between multimedia data objects with a construct called Hierarchical Markov Model Mediator via a novel affinity promotion technique to improve query result relevance manifold. Extensive experiments were conducted with different multimedia data types possessing varied representations, different retrieval approaches, and different data sizes. The encouraging results demonstrate a potential solution to the important and complex issue of managing a large volume of multimedia data.

Special Issue: Web 2.0, Semantics, Knowledge and Grid

With the massive participations of worldwide developers and users as well as enabling collaboration and social networks, Web 2.0 is significantly influencing the development of the Web, Semantic Web and Grid by aiming at a powerful and harmonious interconnection environment. The study of the future Web concerns the exploration of the laws among large-scale and expanding resources such as the formation of community and effective knowledge sharing, the semantics facilitating various interactions (between human, between machines and between human and machine) the scalable infrastructure and applications. This special issue is to reflect the up-to-date progresses of research on the future Web. It contains eight papers selected mainly from the third International Conference on Semantics, Knowledge and Grid 1, which emphasizes on promoting cross-area research. Web mining and community discovery play an important role in supporting intelligent Web applications. Zhang and Xu 2 introduce a set of Web mining methods based on various available information on the Web, including Web document contents, hyperlink analysis, user access logs and semantic analysis. Several key Web clustering algorithms are studied, including a latent linkage information algorithm for finding relevant pages and a Web page clustering algorithm based on the defined concept of Web page correlation. Pierce et al. 3 introduce the application of Web 2.0 in the following scenarios: client-side JavaScript libraries for building and composing Grid services, integrating server-side portlets with ‘rich client’ AJAX tools and Web services for analyzing a global positioning system's data, building and analyzing folksonomies of scientific user communities through social bookmarking, and applying microformats and GeoRSS to problems in scientific metadata description and delivery. The future Web and Grid need to combine different models and techniques to provide users with more accessible services and resources. Dillon et al. 4 discuss three important computing paradigms including service-oriented computing, Grid computing and Web 2.0. An abstracted distributed computing model is introduced and a Grid architecture GRIDspace is discussed. Semantic Web plays an important role in making the description of Web resources more machine-understandable, which can be used as the basic data model and query model to support heterogeneous resource management on Semantic Grid. Babik and Hluchy present an architecture to support efficient resource description, query processing and logic reasoning based on a subset of Semantic Web language 5. The system combines a tableau algorithm with a resolution-based reasoning method to support scalable queries on large-scale instances with complex schema for resource management on Semantic Grid. Ontology technologies are promising and enabling tools for building an intelligent Web. Ungrangsi et al. propose an ontology retrieval framework for the information sharing on the next-generation Web 6. A similarity ranking method is proposed to evaluate the semantic query on ontology modeled by XML declarative description language. Logic reasoning is an important tool to utilize knowledge information. Li et al. propose a case-based reasoning method with adaptive learning rules 7. Resource Space model and Semantic Link Network model are used for efficient resource management and reuse. By dynamically updating the reasoning rules, the reasoning results are improved. Semantics-rich queries are also important for databases that are to manage heterogeneous data objects. Li et al. 8 presents a semantic model for multimedia database systems. A semantic schema description framework called MediaView is provided for users to describe the data model of a multimedia database with more formal semantics. The MediaView model allows users to design a dynamic and evolving object-oriented schema for multimedia data objects, upon which a multimedia recipe database is developed. The future Web faces many problems from architectural solution to scalable and extensible data model. Sun et al. propose a system architectural framework with a semantic object model for massive information and knowledge sharing on the future Web 9. It incorporates peer-to-peer (P2P) computing techniques into the system platform where an object-oriented semantic model is provided for users to describe resources in a more flexible and extensible way. The basic system architecture and related semantic object model are suggested as the scalable semantic model for the future Web. We trust this special issue will make a significant contribution to the development of the future interconnection environment as described in 10. Finally, we would like to take this opportunity to thank the chief editor, publisher, authors and reviewers whose strong support made this special issue possible.

Empirically discovering dominance relations for scheduling problems using an evolutionary algorithm

Many dominance relations have been established in the literature for scheduling problems where they are mainly used in implicit enumeration techniques to further reduce the search space for finding an optimal solution. In this paper, we propose a novel method for discovering dominance relations for scheduling problems. We discover dominance relations by using an evolutionary algorithm. The proposed method of empirically discovering dominance relations can be used for any scheduling problem. After the description of the method, we apply it to a specific scheduling problem. The specific problem is the multimedia data objects scheduling problem for WWW applications which can be modelled as the two-machine flowshop problem of minimizing maximum lateness with separate setup times. The performances of the dominance relations obtained by the proposed method as well as the existing four dominance relations in literature are analysed. The results of the computational experiments show that the proposed method is quite efficient.

Using two-machine flowshop with maximum lateness objective to model multimedia data objects scheduling problem for WWW applications

The multimedia data objects scheduling problem for WWW applications is modeled using the two-machine flowshop problem of minimizing maximum lateness with separate setup times. We establish three dominance relations, and propose four heuristics. Also, we conduct computational experiments to compare the performance of the proposed heuristics and that of existing ones in the literature. The results of the computational experiments show that the proposed heuristics are quite efficient. Scope and purpose A two-machine flowshop scheduling problem involves scheduling a number of jobs on the machines in order to optimize a given criterion. The majority of research assumes that setup times are negligible or can be combined with the processing times. However, the latter assumption is invalid since it may lead to more idle time on the second machine. In the literature, the separate setup times problem has been mainly addressed with the completion-time-related objective functions such as makespan. However, there are many real-life situations in which a due-date-related objective function such as maximum lateness is more appropriate. The problem with maximum lateness objective has received limited attention from researchers as indicated by a recent survey paper. In this paper, we show a real-life situation in the Internet where the two-machine flowshop problem of minimizing maximum lateness with separate setup times can be used to model the multimedia object scheduling problem. We propose new improved heuristics for this problem and compare with existing ones in the literature.

Response time driven multimedia data objects allocation for browsing documents in distributed environments

Distributed information processing, in many WWW applications, requires access to and the transfer and synchronization of large multimedia data objects (MDOs) across the communication network. Moreover, end users expect very fast response times and high QoS. Since the transfer of large MDOs across the communication network contributes to the response time observed by the end users, the problem of allocating these MDOs so as to minimize the response time is challenging. This problem becomes more complex in the context of hypermedia documents, in which the MDOs need to be synchronized during presentation to the end users. The basic problem of data allocation in distributed database environments is NP-complete. Therefore, there is a need to pursue and evaluate solutions based on heuristics which generate near-optimal MDO allocation. We address this problem by: (1) conceptualizing this problem by using a navigational model to represent hypermedia documents and their access behavior by end users, and by capturing the synchronization requirements on MDOs, (2) formulating the problem by developing a base case cost model for response time and generalizing it to incorporate user interaction and buffer memory constraints, (3) designing two algorithms to find near-optimal solutions for allocating MDOs of the hypermedia documents while adhering to the synchronization requirements, and (4) evaluating the trade-off between the time complexity to obtain the solution and the solution quality by comparing the solutions generated by the algorithms with the optimal solutions generated through an exhaustive search.

Design and evaluation of data allocation algorithms for distributed multimedia database systems

A major cost in retrieving multimedia data from multiple sites is the cost incurred in transferring multimedia data objects (MDOs) from different sites to the site where the query is initiated. The objective of a data allocation algorithm is to locate the MDOs at different sites so as to minimize the total data transfer cost incurred in executing a given set of queries. The optimal allocation of MDOs depends on the query execution strategy employed by a distributed multimedia system while the query execution strategy optimizes a query based on this allocation. We fix the query execution strategy and develop a site-independent MDO dependency graph representation to model the dependencies among the MDOs accessed by a query. Given the MDO dependency graphs as well as the set of multimedia database sites, data transfer costs between the sites, the allocation limit on the number of MDOs that can be allocated at a site, and the query execution frequencies from the sites, an allocation scheme is generated. We formulate the data allocation problem as an optimization problem. We solve this problem with a number of techniques that broadly belong to three classes: max-flow min-cut, state-space search, and graph partitioning heuristics. The max-flow min-cut technique formulates the data allocation problem as a network-flow problem, and uses a hill-climbing approach to try to find the optimal solution. For the state-space search approach, the problem is solved using a best-first search algorithm. The graph partitioning approach uses two clustering heuristics, the agglomerative clustering and divisive clustering. We evaluate and compare these approaches, and assess their cost-performance trade-offs. All algorithms are also compared with optimal solutions obtained through exhaustive search. Conclusions are also made on the suitability of these approaches to different scenarios.

TIMS/DADS: A Project to Develop a System of Linking National and International Repositories of Multimedia Information

The Distributed Audio Database System (DADS) is the focus of a project to develop and implement a distributed, mulimedia database linking major media archives in the USA and Europe via national and international networks. DADS is derivative of TIMS (Total Information Management System) which is based on a relational database operating in a distributed mode and which contains multi-media data objects.