• A knowledge based system for construction health and safety competence assessment

      Heesom, David; Proverbs, David G.; Buckley, Kevan; Oloke, David; Yu, Hao (University of Wolverhampton, 2009)
      Organisational and individual Health and Safety (H&S) competence is an essential element to the successful completion of a construction project in a safe way and without hazards to the health of all workforce. Under the Construction (Design and Management) (CDM) Regulations 2007, the client should take reasonable steps to ensure that the appointed duty-holders and engaged people are H&S competent to design, build or co-ordinate the project. Although the CDM Regulations 2007 and its Approved Code of Practice (ACoP) have established ‘Core Criteria’ to guide the client to assess duty-holders’ H&S competence in the outset of a project, it is still difficult for most inexperienced clients to discharge the duty of making the key decisions in H&S competence assessment. In order to help the client implement H&S competence assessment, it is important to develop a tool that can effectively and efficiently support the client to make reasonable decisions in the selection of H&S competent duty-holders. According to the findings of the case study of existing formal H&S competence assessment schemes undertaken as part of this work, H&S competence assessment was characterised as a subjective, qualitative and non-linear regulation-compliance checking process. In addition, the case study helped identify the latent shortcomings in the ‘Core Critiera’ and the operational drawbacks in current practice of implementing H&S competence assessment. Based on a review of Information Technology (I.T.) and Artificial Intelligence (A.I.) applications in construction, Knowledge-Based System (KBS) is identified as being a suitable tool to support decision-making in H&S competence assessment, mainly due to its appropriateness to solve regulation-compliance checking problems and support subjective and qualitative decision-making process. Following a decision-making framework for H&S competence assessment, a KBS decision-support model was developed, applying three mechanisms to support the reasonable decision-making for H&S competence assessment. In order to develop an appropriate and practical KBS for H&S competence assessment, a textual knowledge base was developed, specifying the minimum satisfaction standards and a rating indicator system for ‘Core Criteria’. As a result, an online KBS was developed using Java Server Pages (JSP) technology and MySQL. The online KBS applied the textual knowledge base to support the screen, rating, ranking and reporting decision-supporting mechanisms. Simultaneously, the case inquiry and expert inquiry facilities were also included in the KBS for effective decision-making. Finally, construction experts and practitioners in H&S management evaluated the validity and usability of the KBS through a questionnaire survey. The prototype KBS was borne out to be an effective and efficient decision-support tool for H&S competence assessment and have the potential to be applied in practice.
    • Literature Explorer: effective retrieval of scientific documents through nonparametric thematic topic detection

      Wu, Shaopeng; Zhao, Youbing; Parvinzamir, Farzad; Ersotelos, Nikolaos Th; Wei, Hui; Dong, Feng (Springer Science and Business Media LLC, 2019-08-02)
      Scientific researchers are facing a rapidly growing volume of literatures nowadays. While these publications offer rich and valuable information, the scale of the datasets makes it difficult for the researchers to manage and search for desired information efficiently. Literature Explorer is a new interactive visual analytics suite that facilitates the access to desired scientific literatures through mining and interactive visualisation. We propose a novel topic mining method that is able to uncover “thematic topics” from a scientific corpus. These thematic topics have an explicit semantic association to the research themes that are commonly used by human researchers in scientific fields, and hence are human interpretable. They also contribute to effective document retrieval. The visual analytics suite consists of a set of visual components that are closely coupled with the underlying thematic topic detection to support interactive document retrieval. The visual components are adequately integrated under the design rationale and goals. Evaluation results are given in both objective measurements and subjective terms through expert assessments. Comparisons are also made against the outcomes from the traditional topic modelling methods.