Title: Radio Spectrum Research for Emerging IoT and 5G Networks: Applications to Smart Buildings and Smart Cities

Abstract

The high demand for wireless Internet including emerging Internet of Things (IoT) applications is putting extreme pressure on better utilisation of the available radio spectrum. The expected spectrum “crunch” requires highly efficient radio resource management schemes with low complexity and high responsiveness to the changing network conditions. Spectrum sharing is regarded as an essential approach to regaining access to otherwise unused spectrum and it is considered an essential component in the development of IoT and 5G networks. Spectrum sharing can be conducted at different time scales. As the time scale of the operation of spectrum sharing decreases, the possibility for utilising more available spectrum holes increases. However, the shorter time scale brings with it challenges. Efficient decisions regarding the use of spectrum sharing require accurate knowledge of the spatial and temporal spectrum use in a geographical area of interest. This knowledge can be represented in Radio Environmental Maps which need to be generated efficiently and accurately. In this presentation we give an overview of the spectrum sharing concept and its emergence in standards activities for IoT and 5G networks. We also present our research on spectrum sharing including methods for efficient and accurate generation of Radio Environmental Maps and radio spectrum measurements campaigns on UTS campus in Sydney to enable Smart Building and Smart City IoT applications.

Title: Quantitative Approaches for Road Maintenance

Abstract

Road maintenance operations involve a host of decision-making problems at the strategic, tactical, operational, and real-time levels. This talk presents quantitative approaches developed for the planning and control of three types of maintenance operations: road network surveillance, roadway marking and winter maintenance. The problems addressed fall in the class of arc routing problems. For each problem, the models incorporate the real-life operational constraints. The methods developed are embedded in decision support systems linked with information technology.

Title: Smart CDSS and Authoring Tool

Abstract

Clinical decision support system (CDSS) is tool that helps in making better medical decision thereby reducing clinical errors and improves quality of life. The reliable and accurate recommendations are based on high quality of knowledge of the CDSS. High quality knowledge is achieved using sophisticated knowledge acquisition method. These acquisition methods are required to follow a rigorous validation process to ensure valid knowledge model. Moreover, the validation process is required to be formally verified for internal consistencies. With traditional knowledge acquisition approaches, the final knowledge model is either partially validated or having problem in integration with healthcare workflow. In order to ensure the transformation of quality knowledge into correct executable knowledge which is sharable and interoperable, demands an intelligent authoring environment. The authoring environment shall possess the capabilities to facilitate the domain expert by hiding the inner complexities of the knowledge representation. In traditional knowledge authoring approaches, the domain experts are unnecessarily overburden with the creation of knowledge components which can be otherwise automatically achieved. Knowledge evolution is highly required to keep up with new developments in the domain knowledge. Traditional approaches have lack of integrated access to evidences in the literature thus complicate the process of knowledge evolution. In such disintegrated approaches the knowledge bases are most probably remains stale or leg behind the current advancements in the evolving medical domain. With AI supported intelligent knowledge-based technologies, we can provides a solid ground to resolve the above mentioned problem. In Smart CDSS research, we introduce a machine learning-based prediction model that automatically learns knowledge from a huge patient data with considerably a higher accuracy. To align the machine learned knowledge with clinical practice guidelines, we propose to generate actionable graphs from the clinical practice guidelines through a rigorous inspection method. For the creation of executable knowledge, we propose a smart knowledge authoring tool equipped with semantic reconciliation model (SRM) and Intelli-sense technologies for standardized and easy-to-use creation of knowledge by the non-computer expert physicians. The knowledge shareability achieved using standard knowledge representation of HL7 in form of Medical Logic Module (MLM). Standard MLM generation using SRM model enhances the interoperability of knowledge with clinical workflows. Unlike traditional approaches, in Smart CDSS an integrated approach for knowledge evolution using research evidence acquisition which is supported with automated methods for knowledge-based search query construction and statistical (machine learning) based quality assessments.

Title: Pediatric Mobile Healthcare: Opportunities, Challenges, and Solutions

Abstract

Since its dawn, mobile healthcare (mHealth) has held promises of reducing hospitalization and administrative costs, making healthcare more accessible by enabling continuous and convenient patient monitoring, and increasing healthcare quality with instant emergency responses. While mHealth has gained significant success over the last decade, pediatric mHealth remained disproportionally under explored. In this talk, we begin by discussing several opportunities and challenges in pediatric mobile healthcare. We then take a look at a few results in areas including non-contact and un-obtrusive vital signal monitoring and 24/7 continuous outpatient clinical assistance through wearables. We then take a broader look at the current and future challenges in moving pediatric mHealth results from research labs to practice.