Domain-driven KDD for mining functionally novel rules and linking disjoint medical hypotheses

IntroductionAn important quality of association rules is novelty. However, evaluating rule novelty is AI-hard and has been a serious challenge for most data mining systems.ObjectiveIn this paper, we introduce functional novelty, a new non-pairwise approach to evaluating rule novelty. A functionally novel rule is interesting as it suggests previously unknown relations between user hypotheses.MethodsWe developed a novel domain-driven KDD framework for discovering functionally novel association rules. Association rules were mined from cardiovascular data sets. At post-processing, domain knowledge-compliant rules were discovered by applying semantic-based filtering based on UMLS ontology. Their knowledge compliance scores were computed against medical knowledge in Pubmed literature. A cardiologist explored possible relationships between several pairs of unknown hypotheses. The functional novelty of each rule was computed based on its likelihood to mediate these relationships.ResultsHighly interesting rules were successfully discovered. For instance, common rules such as diabetes mellitus?coronary arteriosclerosis was functionally novel as it mediated a rare association between von Willebrand factor and intracardiac thrombus.ConclusionThe proposed post-mining domain-driven rule evaluation technique and measures proved to be useful for estimating candidate functionally novel rules with the results validated by a cardiologist.     

Express Virtual Channels with Capacitively Driven Global Links

Networks on chip must deliver high bandwidth at low latencies while keeping within a tight power envelope. Using express virtual channels for flow control improves energy-delay throughput by letting packets bypass intermediate routers, but EVCs have key limitations. Nochi (NoC with hybrid interconnect) overcomes these limitations by transporting data payloads and control information on separate planes, optimized for bandwidth and latency respectively.     

A Modeling Framework for Troubleshooting Automotive Systems

This article presents a novel framework for modeling the troubleshooting process for automotive systems such as trucks and buses. We describe how a diagnostic model of the troubleshooting process can be created using event-driven, nonstationary, dynamic Bayesian networks. Exact inference in such a model is in general not practically possible. Therefore, we evaluate different approximate methods for inference based on the Boyen–Koller algorithm. We identify relevant model classes that have particular structure such that inference can be made with linear time complexity. We also show how models created using expert knowledge can be tuned using statistical data. The proposed learning mechanism can use data that is collected from a heterogeneous fleet of modular vehicles that can consist of different components. The proposed framework is evaluated both theoretically and experimentally on an application example of a fuel injection system.     

Portfolio Management in Double Unknown Situations: Technological Platforms and the Role of Cross‐Application Managers

This article investigates portfolio management in double unknown situations. Double unknown refers to a situation in which the level of uncertainty is high and both technology and markets are as yet unknown. This situation can be an opportunity for new discoveries, creation of new performance solutions and giving direction to portfolio structuring. The literature highlights that the double unknown situation is a prerequisite to designing generic technologies that are able to address many existing and emerging markets and create value across a broad range of applications. The purpose of this paper is to investigate the initial phases of generic technology governance and associated portfolio structuring in multi‐project firms. We studied three empirical contexts of portfolio structuring at the European semiconductor provider STMicroelectronics. The results demonstrate that (1) portfolio management for generic technologies is highly transversal and comprises creating both modules to address market complementarities and the core element of a technological system – the platform, and (2) the design of generic technologies requires ‘cross‐application’ managers who are able to supervise the interactions among innovative concepts developed in different business and research groups and who are responsible for structuring and managing technological and marketing exploration portfolios within the organizational structures of a company.     

Applications of ontologies in requirements engineering: a systematic review of the literature

There is an increase use of ontology-driven approaches to support requirements engineering (RE) activities, such as elicitation, analysis, specification, validation and management of requirements. However, the RE community still lacks a comprehensive understanding of how ontologies are used in RE process. Thus, the main objective of this work is to investigate and better understand how ontologies support RE as well as identify to what extent they have been applied to this field. In order to meet our goal, we conducted a systematic literature review (SLR) to identify the primary studies on the use of ontologies in RE, following a predefined review protocol. We then identified the main RE phases addressed, the requirements modelling styles that have been used in conjunction with ontologies, the types of requirements that have been supported by the use of ontologies and the ontology languages that have been adopted. We also examined the types of contributions reported and looked for evidences of the benefits of ontology-driven RE. In summary, the main findings of this work are: (1) there are empirical evidences of the benefits of using ontologies in RE activities both in industry and academy, specially for reducing ambiguity, inconsistency and incompleteness of requirements; (2) the majority of studies only partially address the RE process; (3) there is a great diversity of RE modelling styles supported by ontologies; (4) most studies addressed only functional requirements; (5) several studies describe the use/development of tools to support different types of ontology-driven RE approaches; (6) about half of the studies followed W3C recommendations on ontology-related languages; and (7) a great variety of RE ontologies were identified; nevertheless, none of them has been broadly adopted by the community. Finally, we conclude this work by showing several promising research opportunities that are quite important and interesting but underexplored in current research and practice.     

Distributed boundary coverage with a team of networked miniature robots using a robust market-based algorithm

We study distributed boundary coverage of known environments using a team of miniature robots. Distributed boundary coverage is an instance of the multi-robot task-allocation problem and has applications in inspection, cleaning, and painting among others. The proposed algorithm is robust to sensor and actuator noise, failure of individual robots, and communication loss. We use a market-based algorithm with known lower bounds on the performance to allocate the environmental objects of interest among the team of robots. The coverage time for systems subject to sensor and actuator noise is significantly shortended by on-line task re-allocation. The complexity and convergence properties of the algorithm are formally analyzed. The system performance is systematically analyzed at two different microscopic modeling levels, using agent-based, discrete-event and module-based, realistic simulators. Finally, results obtained in simulation are validated using a team of Alice miniature robots involved in a distributed inspection case study.     

Effective visualization of short routes

In this work we develop a new alternative to conventional maps for visualization of relatively short paths as they are frequently encountered in hotels, resorts or museums. Our approach is based on a warped rendering of a 3D model of the environment such that the visualized path appears to be straight even though it may contain several junctions. This has the advantage that the beholder of the image gains a realistic impression of the surroundings along the way which makes it easy to retrace the route in practice. We give an intuitive method for generation of such images and present results from user studies undertaken to evaluate the benefit of the warped images for orientation in unknown environments.     

Inside the adaptive enterprise: an information technology capabilities perspective on business process agility

Recent innovations in utility computing, web services, and service-oriented architectures, combined with a growing array of IT skills, have improved firms’ ability to be more agile in responding to change. Using the resource-based view of the firm, prior research suggests that IT resources, in isolation, are unlikely to yield superior performance and so as firms try to boost their agility, the question becomes how to configure IT resources to prepare for, or react to, change. In this paper, we posit that managerial IT capabilities based on IT-business partnerships, strategic planning, and ex-post IT project analysis lead to the development of technical IT capabilities associated with a flexible IT infrastructure which in turn drives agility or a firm’s ability to react to change in its products and markets. Using data from matched surveys of IT and business executives in 241 firms, we find that managerial and technical capabilities affect agility. In further testing, we reveal that in a stable setting, technical IT capabilities are more important to agility than managerial IT capabilities, while in a dynamic setting, the opposite is true. Thus, for firms operating in volatile markets, effective models of managerial IT governance are essential for delivering superior agility or adaptiveness.

The aDORe federation architecture: digital repositories at scale

The need to federate repositories emerges in two distinctive scenarios. In one scenario, scalability-related problems in the operation of a repository reach a point beyond which continued service requires parallelization and hence federation of the repository infrastructure. In the other scenario, multiple distributed repositories manage collections of interest to certain communities or applications, and federation is an approach to present a unified perspective across these repositories. The high-level, 3-Tier aDORe federation architecture can be used as a guideline to federate repositories in both cases. This paper describes the architecture, consisting of core interfaces for federated repositories in Tier-1, two shared infrastructure components in Tier-2, and a single-point of access to the federation in Tier-3. The paper also illustrates two large-scale deployments of the aDORe federation architecture: the aDORe Archive repository (over 100,000,000 digital objects) at the Los Alamos National Laboratory and the Ghent University Image Repository federation (multiple terabytes of image files).     

A Secure Grid Medical Data Manager Interfaced to the gLite Middleware

The medical community is producing and manipulating a tremendous volume of digital data for which computerized archiving, processing and analysis is needed. Grid infrastructures are promising for dealing with challenges arising in computerized medicine but the manipulation of medical data on such infrastructures faces both the problem of interconnecting medical information systems to Grid middlewares and of preserving patients’ privacy in a wide and distributed multi-user system. These constraints are often limiting the use of Grids for manipulating sensitive medical data. This paper describes our design of a medical data management system taking advantage of the advanced gLite data management services, developed in the context of the EGEE project, to fulfill the stringent needs of the medical community. It ensures medical data protection through strict data access control, anonymization and encryption. The multi-level access control provides the flexibility needed for implementing complex medical use-cases. Data anonymization prevents the exposure of most sensitive data to unauthorized users, and data encryption guarantees data protection even when it is stored at remote sites. Moreover, the developed prototype provides a Grid storage resource manager (SRM) interface to standard medical DICOM servers thereby enabling transparent access to medical data without interfering with medical practice.