A Bayesian network-based framework for semantic image understanding

Current research in content-based semantic image understanding is largely confined to exemplar-based approaches built on low-level feature extraction and classification. The ability to extract both low-level and semantic features and perform knowledge integration of different types of features is expected to raise semantic image understanding to a new level. Belief networks, or Bayesian networks (BN), have proven to be an effective knowledge representation and inference engine in artificial intelligence and expert systems research. Their effectiveness is due to the ability to explicitly integrate domain knowledge in the network structure and to reduce a joint probability distribution to conditional independence relationships. In this paper, we present a general-purpose knowledge integration framework that employs BN in integrating both low-level and semantic features. The efficacy of this framework is demonstrated via three applications involving semantic understanding of pictorial images. The first application aims at detecting main photographic subjects in an image, the second aims at selecting the most appealing image in an event, and the third aims at classifying images into indoor or outdoor scenes. With these diverse examples, we demonstrate that effective inference engines can be built within this powerful and flexible framework according to specific domain knowledge and available training data to solve inherently uncertain vision problems.     

An algorithm for recognizing linear objects in aerial photos automatically

A new algorithm for detecting linear infrastructural objects in aerial photos is presented. It is assumed that these objects pass through the whole image: beginning at one side and finishing at the opposite one. It is also assumed that the altitude of shooting and the image scale are invariable. The presented algorithm synthesizes the operation of an edge detector, a ridge detector, and the Hough accumulator into an object-of-interest mask excluding lots of spurious responses, and it completes missing information missed by detectors. First of all the image is preprocessed and anisotropically and repeatedly shrunk along the direction of the linear object and synthesis is performed by finding the shortest paths in a graph. The graph is presented in the form of a mesh, where each mesh node corresponds to a pixel of the shrunk image. At each node on the edges and in ridge lines, its energy is calculated, which is the reliability of this pixel. Then, the path that maximizes the sum of energies at the nodes is determined by considering its curvature. The obtained paths form a mask of linear objects. The algorithm is verified by using aerial photos for different seasons, and it demonstrates proper results (accuracy is ~80%).     

A multiple instance learning based framework for semantic image segmentation

Most image segmentation algorithms extract regions satisfying visual uniformity criteria. Unfortunately, because of the semantic gap between low-level features and high-level semantics, such regions usually do not correspond to meaningful parts. This has motivated researchers to develop methods that, by introducing high-level knowledge into the segmentation process, can break through the performance ceiling imposed by the semantic gap. The main disadvantage of those methods is their lack of flexibility due to the assumption that such knowledge is provided in advance. In content-based image retrieval (CBIR), relevance feedback (RF) learning has been successfully applied as a technique aimed at reducing the semantic gap. Inspired by this, we present a RF-based CBIR framework that uses multiple instance learning to perform a semantically-guided context adaptation of segmentation parameters. A partial instantiation of this framework that uses mean shift-based segmentation is presented. Experiments show the effectiveness and flexibility of the proposed framework on real images.     

An overview of the K semantic framework

K is an executable semantic framework in which programming languages, calculi, as well as type systems or formal analysis tools can be defined, making use of configurations, computations and rules. Configurations organize the system/program state in units called cells, which are labeled and can be nested. Computations carry “computational meaning” as special nested list structures sequentializing computational tasks, such as fragments of program; in particular, computations extend the original language or calculus syntax. K (rewrite) rules generalize conventional rewrite rules by making explicit which parts of the term they read, write, or do not care about. This distinction makes K a suitable framework for defining truly concurrent languages or calculi, even in the presence of sharing. Since computations can be handled like any other terms in a rewriting environment, that is, they can be matched, moved from one place to another in the original term, modified, or even deleted, K is particularly suitable for defining control-intensive language features such as abrupt termination, exceptions, or call/cc.This paper gives an overview of the K framework: what it is, how it can be used, and where it has been used so far. It also proposes and discusses the K definition of Challenge, a programming language that aims to challenge and expose the limitations of existing semantic frameworks.     

An OWL-based semantic business process monitoring framework

Process monitoring phase is one of the service-oriented business process (SOBP) lifecycle phases. Traditional process monitoring approaches have been only achieved at the syntactic level of the process monitoring contexts, which causes the communication problems such as ambiguous understandings and divergent interpretations. To solve the problems, the process monitoring should be achieved at the semantic level as well as at the syntax level of the process monitoring context. In order to support semantic monitoring operations, an ontology-based monitoring framework for the SOBP execution is suggested in this paper. The suggested framework combines a BPEL4WS process model with the semantic monitoring context which is expressed with OWL.     

Extracting semantic video objects

We present an accurate and user-interactive semantic video object (SVO) extraction system. Although we also obtain an SVO with an accurate boundary by integrating temporal and spatial information, our way is quite different from others' work. Instead of fusing spatial and temporal segmentations on the first or all the frames of a video sequence, our system adaptively performs spatial and temporal segmentation and fusion when necessary. To achieve this, our system detects the variations between successive frames. We only need to fuse the spatial and temporal segmentation when a large variation occurs. Otherwise, the system tracks the previous SVO's boundary. We find this simple method efficient in both speed and accuracy. Since the temporal segmentation, spatial segmentation, spatio-temporal fusion, and boundary tracking all employ simple algorithms, our system has a low computational complexity     

Confinement framework for encapsulating objects

Confinement is used to prohibit safety-critical objects from unintended access. Approaches for specifying and verifying confinement have been proposed in the last twenty years but their application has been help back. We develop a novel framework for specifying and verifying object confinement in object-oriented (OO) programs. Instead of expressing the confinement requirements within a class for possible future usage, as with ownership types, we specify confinement requirements of the class in its usage class which actually intends to confine the parts, i.e., internal representations. Syntactically, an optional conf clause is introduced in class declarations for annotating the confined attribute-paths. A “same type and confinement” notation is introduced for expressing type and confinement dependence among variables, parameters, and return values of methods. Based on the extension to a Java-like language and existing techniques of alias analysis, we define a sound type-system for checking the well-confinedness of OO programs with respect to the confinement specifications.     

An optimal feedback control framework for grasping objects with position uncertainty

As we move, the relative location between our hands and objects changes in uncertain ways due to noisy motor commands and imprecise and ambiguous sensory information. The impressive capabilities humans display for interacting and manipulating objects with position uncertainty suggest that our brain maintains representations of location uncertainty and builds compensation for uncertainty into its motor control strategies. Our previous work demonstrated that specific control strategies are used to compensate for location uncertainty. However, it is an open question whether compensation for position uncertainty in grasping is consistent with the stochastic optimal feedback control, mainly due to the difficulty of modeling natural tasks within this framework. In this study, we develop a stochastic optimal feedback control model to evaluate the optimality of human grasping strategies. We investigate the properties of the model through a series of simulation experiments and show that it explains key aspects of previously observed compensation strategies. It also provides a basis for individual differences in terms of differential control costs-the controller compensates only to the extent that performance benefits in terms of making stable grasps outweigh the additional control costs of compensation. These results suggest that stochastic optimal feedback control can be used to understand uncertainty compensation in complex natural tasks like grasping.     

Event semantic recognizing based on Markov chain

Owing to the enormous information and complex structure, video semantic processing is a tricky issue all along. Current researches are restricted within recognizing relative simple semantic in some certain domains. This paper brings forward a novel method transiting low-level feature to high-level semantic with Markov chain by stages, which takes object semantic as the core. This method is valid for recognizing complex event semantic. Semantic concept mapping mechanism based on semantic template is presented to realize the automatic recognition of video semantic. In the experiment contrasting with IBM＇s IMAT, our method shows more extensive recognition range and higher accuracy. Experimental results are encouraging, and indicate that the performance of the proposed approach is effective.     

A semantic framework for open processes

We propose a general methodology for analysing the behaviour of open systems modelled as coordinators, i.e., open terms of suitable process calculi. A coordinator is understood as a process with holes or placeholders where other coordinators and components (i.e., closed terms) can be plugged in, thus influencing its behaviour. The operational semantics of coordinators is given by means of a symbolic transition system, where states are coordinators and transitions are labeled by spatial/modal formulae expressing the potential interaction that plugged components may enable. Behavioural equivalences for coordinators, like strong and weak bisimilarities, can be straightforwardly defined over such a transition system. Different from other approaches based on universal closures, i.e., where two coordinators are considered equivalent when all their closed instances are equivalent, our semantics preserves the openness of the system during its evolution, thus allowing dynamic instantiation to be accounted for in the semantics. To further support the adequacy of the construction, we show that our symbolic equivalences provide correct approximations of their universally closed counterparts, coinciding with them over closed components. For process calculi in suitable formats, we show how tractable symbolic semantics can be defined constructively using unification.     

A framework for defining semantic metrics

Software metrics are measures of particular characteristics found in the software. Research in this area seeks to identify relationships between software characteristics and software engineering processes. Most software metrics are based on program structure and are determined statically. This article presents a framework by which semantic information can be quantified. By semantic information, we mean information concerning what occurs internally during execution as program states are created.     

A semantic framework for metamodel-based languages

In the model-based development context, metamodel-based languages are increasingly being defined and adopted either for general purposes or for specific domains of interest. However, meta-languages such as the MOF (Meta Object Facility)—combined with the OCL (Object Constraint Language) for expressing constraints—used to specify metamodels focus on structural and static semantics but have no built-in support for specifying behavioral semantics. This paper introduces a formal semantic framework for the definition of the semantics of metamodel-based languages. Using metamodelling principles, we propose several techniques, some based on the translational approach while others based on the weaving approach, all showing how the Abstract State Machine formal method can be integrated with current metamodel engineering environments to endow language metamodels with precise and executable semantics. We exemplify the use of our semantic framework by applying the proposed techniques to the OMG metamodelling framework for the behaviour specification of the Finite State Machines provided in terms of a metamodel.     

An integrated semantic framework supporting universal accessibility to ICT

As we are moving rapidly to a digital economy, accessing and effectively using Information and Communication Technologies (ICT) in everyday life is widely recognized as an important requirement. However, the accessibility technologies that we have up to date are meeting the needs of only some, at a very high cost and, as a consequence, accessible ICT for all people still remains a major research and development goal. This work presents an integrated ontological framework for the semantic representation of terms and concepts (i.e., related to user needs and preferences (N&P) with respect to ICT use, as well as solutions, platforms and devices) that are required for addressing the universal accessibility in the scope of the Cloud4all project and the Global Public Inclusive Infrastructure (GPII). Cloud4all aims at advancing and building upon the concept of GPII through the development of the necessary tools and models for making ICT accessible for all by exploiting the cloud computing paradigm. The main goal of the proposed framework lays in the separation between generalized accessibility concepts, user interaction mechanisms and N&P with the particular details of different ICT artifacts. Thus, the framework aims at integrating concepts related with user N&P, as well as ICT solutions, platforms, devices and their customizable settings along with information concerning their vendors or implementers, in order to (a) offer the necessary expressiveness for defining/representing personal N&P across applications, platforms and devices, (b) link N&P with the conditions/context according to which these shall be applicable for (e.g., considering the user activity and the physical environment), (c) link interaction requirements (originated from user characteristics) with N&P and (d) support the Cloud4all matchmaking process through the mapping between N&P and application-specific settings based on semantic rules and automatic reasoning techniques.     

An ontology-driven framework towards building enterprise semantic information layer

Enterprises Information Systems (EIS) have been applied for decades in Computer-Aided Engineering (CAE) and Computer-Aided Design (CAD), where huge amount of increasing data is stored in the heterogeneous and distributed systems. As systems evaluating, system redesign and reengineering are demanded. A facing challenge is how to interoperate among different systems by overcoming the gap of conceptual heterogeneity. In this article, an enlarged data representation called semantic information layer (SIL) is described for facilitating heterogeneous systems interoperable. SIL plays a role as mediation media and knowledge representation among heterogeneous systems. The SIL building process is based on ontology engineering, including ontology extraction from relational database (RDB), ontology enrichment and ontology alignment. Mapping path will maintain the links between SIL and data source, and query implementation and user interface are for retrieving data and interacting with end users. We described fully a practical ontology-driven framework for building SIL and introduced extensively relevant standards and techniques for implementing the framework. In the core part of ontology development, a dynamic multi-strategies ontology alignment with automatic matcher selection and dynamic similarity aggregation is proposed. A demonstration case study in the scenario of mobile phone industry is used to illustrate the proposed framework.     

面向对象与MVC框架的融合

随着面向对象思想的确立,使得人们认识事物的角度发生了重大变化,用面向对象的思想来分析事物,模拟人们对客观事物认识方式的反应。21世纪软件业的发展是在信息计算机的大背景下不断发展的。人们对软件功能的需求在不断变化,使得原有的软件无法维持业务功能的新需求,这使得软件的重用性和可扩展性受到严重限制,这就必然推动软件开发的革新要有新的认识,这使得面向对象的软件开发思想在软件领域不断发展。在Web软件开发中面向对象的开发思想有了很成熟的发展,特别是以java面向对象的语言为基础的软件开发,以java语言为开发的经典架构MVC的设计框架充分体现了面向对象的思想。本次就java的MVC三大框架与面向对象的思想进行深入探讨。     

An efficient location reporting and indexing framework for urban road moving objects

The tracking of moving objects consists of two critical operations: location reporting, in which moving objects (or clients) send their locations to centralized servers, and index maintenance, through which centralized servers update the locations of moving objects. In existing location reporting techniques, each moving object reports its locations to servers by utilizing long-distance links such as 3G/4G. Corresponding to this location reporting strategy, servers need to respond to all the location updating requests from individual moving objects. Such techniques suffer from very high communication cost (due to the individual reporting using long-distance links) and high index update I/Os (due to the massive amount of location updating requests). In this paper, we present a novel Group-movement based location Reporting and Indexing (GRI) framework for location reporting (at moving object side) and index maintenance (at server side). In the GRI framework, we introduce a novel location reporting strategy which allows moving objects to report their locations to servers in a group (instead of individually) by aggregating the moving objects that share similar movement patterns through wireless local links (such as WiFi). At the server side, we present a dual-index, Hash-GTPR-tree (H-GTPR), to index objects sharing similar movement patterns. Our experimental results on synthetic and real data sets demonstrate the effectiveness and efficiency of our new GRI framework, as well as the location reporting strategy and the H-GTPR tree index technique.     

SETL: A programmable semantic extract-transform-load framework for semantic data warehouses

In order to create better decisions for business analytics, organizations increasingly use external structured, semi-structured, and unstructured data in addition to the (mostly structured) internal data. Current Extract-Transform-Load (ETL) tools are not suitable for this “open world scenario” because they do not consider semantic issues in the integration processing. Current ETL tools neither support processing semantic data nor create a semantic Data Warehouse (DW), a repository of semantically integrated data. This paper describes our programmable Semantic ETL (SETL) framework. SETL builds on Semantic Web (SW) standards and tools and supports developers by offering a number of powerful modules, classes, and methods for (dimensional and semantic) DW constructs and tasks. Thus it supports semantic data sources in addition to traditional data sources, semantic integration, and creating or publishing a semantic (multidimensional) DW in terms of a knowledge base. A comprehensive experimental evaluation comparing SETL to a solution made with traditional tools (requiring much more hand-coding) on a concrete use case, shows that SETL provides better programmer productivity, knowledge base quality, and performance.     

A framework for automatic semantic video annotation

Hypermedia composite templates define generic structures of nodes and links to be added to a document composition, providing spatio-temporal synchronization semantics. This paper presents EDITEC, a graphical editor for hypermedia composite templates. EDITEC templates are based on the XTemplate 3.0 language. The editor was designed for offering a user-friendly visual approach. It presents a new method that provides several options for representing iteration structures graphically, in order to specify a certain behavior to be applied to a set of generic document components. The editor provides a multi-view environment, giving the user a complete control of the composite template during the authoring process. Composite templates can be used in NCL documents for embedding spatio-temporal semantics into NCL contexts. NCL is the standard declarative language used for the production of interactive applications in the Brazilian digital TV system and ITU H.761 IPTV services. Hypermedia composite templates could also be used in other hypermedia authoring languages offering new types of compositions with predefined semantics.