Abstract In this paper we perform statistical data analysis of a broad set of state-of-the-art audio features and low-level MPEG-7 audio descriptors. The investigation comprises data analysis to reveal redundancies between state-of-the-art audio features and MPEG-7 audio descriptors. We introduce a novel measure to evaluate the information content of a descriptor in terms of variance. Statistical data analysis reveals the amount... In this paper we perform statistical data analysis of a broad set of state-of-the-art audio features and low-level MPEG-7 audio descriptors. The investigation comprises data analysis to reveal redundancies between state-of-the-art audio features and MPEG-7 audio descriptors. We introduce a novel measure to evaluate the information content of a descriptor in terms of variance. Statistical data analysis reveals the amount of variance contained in a feature. It enables identification of independent and redundant features. This approach assists in efficient selection of orthogonal features for content-based retrieval. We believe that a good feature should provide descriptions with high variance for the underlying data. Combinations of features should consist of decorrelated features in order to increase expressiveness of the descriptions. Although MPEG-7 is a popular and widely used standard for multimedia description, only few investigations do exist that address analysis of the data quality of low-level MPEG-7 descriptions. Read More Read Less

Abstract Authoring of personalized multimedia content can be considered as a process consisting of selecting, composing, and assembling media elements into coherent multimedia presentations that meet the user’s or user group’s preferences, interests, current situation, and environment. In the approaches we find today, media items and semantically rich metadata information are used for the selection and composition task. However, most valuable... Authoring of personalized multimedia content can be considered as a process consisting of selecting, composing, and assembling media elements into coherent multimedia presentations that meet the user’s or user group’s preferences, interests, current situation, and environment. In the approaches we find today, media items and semantically rich metadata information are used for the selection and composition task. However, most valuable semantics for the media elements and the resulting multimedia content that emerge with and in the authoring process are not considered any further. This means that the effort for semantically enriching media content comes to a sudden halt in the created multimedia document – which is very unfortunate. In this paper, we propose with the SemanticMM4U framework an integrated approach for deriving and exploiting multimedia semantics that arise with and from the creation of personalized multimedia content and make it available for further use and applications. In this approach, not only the metadata are considered that are semantically evolving from the media elements of the newly created presentation. Also the actual usage of media elements for the authoring can emerge new semantics of the single media elements employed. In the application domain of authoring of digital photo albums we show where and how semantics emerge in the authoring process and how these contribute to an even richer media content pool, both for single media and also for the composition and its later use. Read More Read Less

Abstract Recent developments of the Internet and the World Wide Web (WWW) have resulted in the proliferation of multi-media resources and learning with existing multimedia web resources on the Web is becoming more prevalent and important. While recent standardization efforts in eLearning such as LOM, SCORM, and IMS Learning Design work towards learning content description, packaging, and delivery; existing eLearning solutions... Recent developments of the Internet and the World Wide Web (WWW) have resulted in the proliferation of multi-media resources and learning with existing multimedia web resources on the Web is becoming more prevalent and important. While recent standardization efforts in eLearning such as LOM, SCORM, and IMS Learning Design work towards learning content description, packaging, and delivery; existing eLearning solutions still lack the ability to adequately use multi-media resources to provide a learner with personalised learning resources. Effective use of multimedia for web-based learning provides quality interactive learning experience, but current techniques does not adequately provide a semantic approach for organising multimedia resources. With evolving trend in learning through the use of web technology, eLearning systems are expected to provide personalised learning resources for effective learning. We have accordingly proposed a way of organising existing multimedia resources based on contexts towards providing a truly personalised eLearning experience. This paper presents a framework for achieving contextbased multimedia semantic annotation and organisation towards personalised learning. Read More Read Less

Abstract Multimedia content classification and retrieval are indispensable tools in the current convergence of audiovisual entertainment and information media. Thanks to the development of broadband networks, every consumer will have digital video programmes available on-line as well as through the traditional distribution channels. In this scenario, since the early ‘90s, the most important TV broadcasters in Europe have started projects whose... Multimedia content classification and retrieval are indispensable tools in the current convergence of audiovisual entertainment and information media. Thanks to the development of broadband networks, every consumer will have digital video programmes available on-line as well as through the traditional distribution channels. In this scenario, since the early ‘90s, the most important TV broadcasters in Europe have started projects whose aim was to achieve preservation, restoration and automatic documentation of their audiovisual archives. In particular, the association of low-level multimedia features to knowledge and semantics for the purpose of automatic classification of multimedia archives is currently the target of many researchers in both academic and IT industrial communities. This paper describes our research direction, which is focusing on three points: (a) We first introduce a new taxonomy for classification of broadcast digital archives based on a novel theoretical approach. The advantage of this taxonomy is that it can provide an unambiguous representation of multimedia informative content from the relevant points of view to the broadcasters community. (b) We secondly present a multilayer multimedia database model to represent both structure and content of multimedia objects. (c) We further propose a framework architecture for building a Multimedia Fuzzy Annotation System (MFAS), and a description of our experimental plan. Read More Read Less

Abstract This paper describes an approach for semantic description and retrieval of multimedia data described by means of MPEG-7. This standard uses XML schema to define the descriptions. Therefore, it lacks ability to represent the data semantics in a formal and concise way and it does not allow integration and use of domain specific knowledge. Moreover, inference mechanisms are not provided... This paper describes an approach for semantic description and retrieval of multimedia data described by means of MPEG-7. This standard uses XML schema to define the descriptions. Therefore, it lacks ability to represent the data semantics in a formal and concise way and it does not allow integration and use of domain specific knowledge. Moreover, inference mechanisms are not provided and hence the extraction of implicit information is not (always) possible. To address these issues, we propose to add a conceptual layer on top of MPEG-7 metadata layer, where the domain knowledge is represented using a formal language. A set of mapping rules is proposed. They serve as a bridge between the two layers. Querying MPEG-7 descriptions using XML query languages such as XPath or XQuery requires to know MPEG-7 syntax and documents structure. To provide a flexible query formulation, we exploit the conceptual layer vocabulary to express user queries. A user query, making reference to terms specified at the conceptual level, is rewritten into an XQuery expression over MPEG-7 descriptions. Read More Read Less

Abstract Due to its flexibility and efficiency in transmission of data, XML has become the emerging standard for data transfer and exchange across the Internet. In native XML database, XML documents are usually modeled as trees, and XML queries are typically specified in path expression. The primitive structural relationships are parent-child and ancestor-descendant in the path expression. Thus, finding all occurrences... Due to its flexibility and efficiency in transmission of data, XML has become the emerging standard for data transfer and exchange across the Internet. In native XML database, XML documents are usually modeled as trees, and XML queries are typically specified in path expression. The primitive structural relationships are parent-child and ancestor-descendant in the path expression. Thus, finding all occurrences of these relationships is crucial. We adopt the decomposition-matching-merging approach and propose INLAB, a novel hybrid query processing merging both indexing and labeling technologies. Experimental results show that INLAB can process XML path queries by up to an order of magnitude faster than conventional top-down approach. Read More Read Less

Abstract Collaborative processing among sensors to fulfill given tasks is a promising solution to save significant energy in resource-limited wireless sensor networks (WSN). Quality-of-Service (QoS) such as lifetime and latency is largely affected by how tasks are mapped to sensors in network. Tasks allocation is a well-defined problem in the area of high performance computing and has been extensively studied in... Collaborative processing among sensors to fulfill given tasks is a promising solution to save significant energy in resource-limited wireless sensor networks (WSN). Quality-of-Service (QoS) such as lifetime and latency is largely affected by how tasks are mapped to sensors in network. Tasks allocation is a well-defined problem in the area of high performance computing and has been extensively studied in the past. Due to the limitations of WSN, existing algorithms cannot be directly used. In this paper, a novel nested optimization technique based on genetic algorithm is proposed to assign tasks onto sensors with minimal cost while meeting application’s QoS requirements. Optimal solution can be achieved by incorporating task mapping, routing path allocation, communication scheduling, dynamic voltage scaling. Performance is evaluated through experiments with randomly generated Directed Acyclic Graphs (DAG) and experiments results show better solution compared with existing methods. Read More Read Less