Creativity Award from Oracle and Locatrix Communication, TADHack 2017
Best Paper Award at HICSS50
Beyond Research Conference
New Jersey Institute of Technology
World Forum of Internet of Things
Washington, with Vint Cerf - "the fathers of the Internet"
Teaching is fun!
Big Data Processing and Analysis in particular developing methods to enable large-scale collection of distributed and heterogeneous data sets on Internet connected devices supported by real-time data processing/reasoning in the cloud or similar distributed environment.
Contextualization and in particular developing techniques that exclude irrelevant data form consideration and have the potential to reduce data from several aspects including volume, velocity, and variety in IoT applications and subsequently improve the data processing and knowledge extraction in large-scale IoT applications.
Semantic Web and in particular data formats and exchange protocols on the Web that have the potential to be extended and be more compatible for large-scale Internet of Things applications and platforms.
Mobile computing and Cloud Computing and in particular Techniques and frameworks to store, process, and manage of Internet scale data using Cloud infrastructure
Disclaimer: These documents are made available to ensure timely dissemination of scholarly work. Copyright and all rights therein are retained by the copyright holders. All parties copying this information are expected to adhere to the terms and constraints invoked by each copyright holder. In most cases, these documents may not be reposted without the explicit permission of the copyright holder. Other restrictions to copying individual documents may apply.
The Internet of Things represents a technology revolution transforming the current environment into a ubiquitous world, whereby everything that benefits from being connected will be connected. Despite the benefits, the privacy of these things becomes a great concern and it is imperative to apply privacy preservation techniques to IoT data collection. One such technique is called data obfuscation in which data is deliberately modified to blur the sensitive information. The current obfuscation techniques, however, focus on the privacy of published datasets. The high connectivity and distributed nature of IoT, opens up the possibility of privacy compromise before obfuscation can take effect, and therefore privacy enforcement should be deployed at earlier stages. Classical privacy treatments are too restrictive for IoT, where coarser/finer data details should be revealed. Motivated by these challenges, we propose a framework for privacy preservation in IoT environments that is capable of multi-granular obfuscation by enforcing context-driven disclosure policies. Then, we customize our framework for a smart vehicle system and make use of data stream watermarking to protect privacy. To address possible concerns about additional performance overhead, we show the burden to be very lightweight, thus validating the suitability of ubiquitous use of our framework for IoT settings.
The Internet of Things (IoT) is the latest Internet evolution that interconnects billions of devices, such as cameras, sensors, RFIDs, smart phones, wearable devices, ODBII dongles, etc. Federations of such IoT devices (or things) provides the information needed to solve many important problems that have been too difficult to harness before. Despite these great benefits, privacy in IoT remains a great concern, in particular when the number of things increases. This presses the need for the development of highly scalable and computationally efficient mechanisms to prevent unauthorised access and disclosure of sensitive information generated by things. In this paper, we address this need by proposing a lightweight, yet highly scalable, data obfuscation technique. For this purpose, a digital watermarking technique is used to control perturbation of sensitive data that enables legitimate users to de-obfuscate perturbed data. To enhance the scalability of our solution, we also introduce a contextualisation service that achieve real-time aggregation and filtering of IoT data for large number of designated users. We, then, assess the effectiveness of the proposed technique by considering a health-care scenario that involves data streamed from various wearable and stationary sensors capturing health data, such as heart-rate and blood pressure. An analysis of the experimental results that illustrate the unconstrained scalability of our technique concludes the paper.
The Internet of Things (IoT) is a new internet evolution that involves connecting billions of sensors and other devices to the Internet. Such IoT devices or IoT things can communicate directly. They also allow Internet users and applications to access and distil their data, control their functions, and harness the information and functionality provided by multiple IoT devices to offer novel smart services. IoT devices collectively generate massive amounts of data with an incredible velocity. Processing IoT device data and distilling high-value information from them presents an Internet-scale computational challenge. Contextualisation of IoT data can help improve the value of information extracted from IoT. However, existing contextualisation techniques can only handle small datasets from a modest number of IoT devices. In this paper, we propose a general-purpose architecture and related techniques for the contextualisation of IoT data. In particular, we introduce a Contextualisation-as-a-Service (ConTaaS) architecture that incorporates scalability improving techniques, as well as a proof-of-concept implementation of all these that utilises elastic cloud-based infrastructure to achieve near real-time contextualisation of IoT data. Experimental evaluations validating the efficiency of ConTaaS are also provided in this paper.
The Internet of Things (IoT) plays an important role in the development of smart cities. In this paper we focus on the development of IoT-based smart services for solving urban problems that involve IoT-enabled Observation, Orientation, Decision, and Action (OODA) loops. We also focus on how to efficiently support such OODA loops in situations where such loops involve internet-scale data. More specifically, IoT supports Observation via the discovery of sensors and the integration of their data. It supports Orientation via a contextualisation process that refines such data to include only those that are relevant to the situation and/or activities of each specific individual or group. As IoT contextualisation potentially involves internet-scale data, performing this process efficiently allows for fast decision making, and this in turn permits carrying out a timely Action. In this paper we propose an approach and related techniques for performing internet-scale data contextualisation. In particular, we propose IoT-based contextualisation techniques that effectively consider the entire range of data that is being collected in smart cities and use such data to provide hyper-personalised information to each user, i.e., information that best suits the context of each user in the Smart City. We exemplify the proposed contextualisation solution in a smart parking space recommender application/service, and provide an experimental evaluation of this service to illustrate the benefits of our solution.
Improving farm productivity is essential for increasing farm profitability and meeting the rapidly growing demand for food that is fuelled by rapid population growth across the world. Farm productivity can be increased by understanding and forecasting crop performance in a variety of environmental conditions. Crop recommendation is currently based on data collected in field-based agricultural studies that capture crop performance under a variety of conditions (e.g., soil quality and environmental conditions). However, crop performance data collection is currently slow, as such crop studies are often undertaken in remote and distributed locations, and such data are typically collected manually. Furthermore, the quality of manually collected crop performance data is very low, because it does not take into account earlier conditions that have not been observed by the human operators but is essential to filter out collected data that will lead to invalid conclusions (e.g., solar radiation readings in the afternoon after even a short rain or overcast in the morning are invalid, and should not be used in assessing crop performance). Emerging Internet of Things (IoT) technologies, such as IoT devices (e.g., wireless sensor networks, network-connected weather stations, cameras, and smart phones) can be used to collate vast amount of environmental and crop performance data, ranging from time series data from sensors, to spatial data from cameras, to human observations collected and recorded via mobile smart phone applications. Such data can then be analysed to filter out invalid data and compute personalised crop recommendations for any specific farm. In this paper, we present the design of SmartFarmNet, an IoT-based platform that can automate the collection of environmental, soil, fertilisation, and irrigation data; automatically correlate such data and filter-out invalid data from the perspective of assessing crop performance; and compute crop forecasts and personalised crop recommendations for any particular farm. SmartFarmNet can integrate virtually any IoT device, including commercially available sensors, cameras, weather stations, etc., and store their data in the cloud for performance analysis and recommendations. An evaluation of the SmartFarmNet platform and our experiences and lessons learnt in developing this system concludes the paper. SmartFarmNet is the first and currently largest system in the world (in terms of the number of sensors attached, crops assessed, and users it supports) that provides crop performance analysis and recommendations.
There is a growing emphasis to find alternative non-traditional ways to manage patients to ease the burden on health care services largely fuelled by a growing demand from sections of population that is ageing. In-home remote patient monitoring applications harnessing technological advancements in the area of Internet of things (IoT), semantic web, data analytics, and cloud computing have emerged as viable alternatives. However, such applications generate large amounts of real-time data in terms of volume, velocity, and variety thus making it a big data problem. Hence, the challenge is how to combine and analyse such data with historical patient data to obtain meaningful diagnoses suggestions within acceptable time frames (considering quality of service (QoS)). Despite the evolution of big data processing technologies (e.g. Hadoop) and scalable infrastructure (e.g. clouds), there remains a significant gap in the areas of heterogeneous data collection, real-time patient monitoring, and automated decision support (semantic reasoning) based on well-defined QoS constraints. In this study, the authors review the state-of-the-art in enabling QoS for remote health care applications. In particular, they investigate the QoS challenges required to meet the analysis and inferencing needs of such applications and to overcome the limitations of existing big data processing tools.
The Internet of Things (IoT) is the latest web evolution that incorporates billions of devices that are owned by different organisations and people who are deploying and using them for their own purposes. IoT-enabled harnessing of the information that is provided by federations of such IoT devices (which are often referred to as IoT things) provides unprecedented opportunities to solve internet-scale problems that have been too big and too difficult to tackle before. Just like other web-based information systems, IoT must also deal with the plethora of Cyber Security and privacy threats that currently disrupt organisations and can potentially hold the data of entire industries and even countries for ransom. To realise its full potential, IoT must deal effectively with such threats and ensure the security and privacy of the information collected and distilled from IoT devices. However, IoT presents several unique challenges that make the application of existing security and privacy techniques difficult. This is because IoT solutions encompass a variety of security and privacy solutions for protecting such IoT data on the move and in store at the device layer, the IoT infrastructure/platform layer, and the IoT application layer. Therefore, ensuring end-to-end privacy across these three IoT layers is a grand challenge in IoT. In this paper, we tackle the IoT privacy preservation problem. In particular, we propose innovative techniques for privacy preservation of IoT data, introduce a privacy preserving IoT Architecture, and also describe the implementation of an efficient proof of concept system that utilises all these to ensure that IoT data remains private. The proposed privacy preservation techniques utilise multiple IoT cloud data stores to protect the privacy of data collected from IoT. The proposed privacy preserving IoT Architecture and proof of concept implementation are based on extensions of OpenIoT - a widely used open source platform for IoT application development. Experimental evaluations are also provided to validate the efficiency and performance outcomes of the proposed privacy preserving techniques and architecture.
The Internet of Things (IoT) is a new internet evolution that involves connecting billions of internet-connected devices that we refer to as IoT things. These devices can communicate directly and intelligently over the Internet, and generate a massive amount of data that needs to be consumed by a variety of IoT applications. This paper focuses on the automatic contextualisation of IoT data, which also involves distilling information and knowledge from the IoT aiming to simplify answering the following fundamental questions that often arises in IoT applications: Which data collected by IoT are relevant to myself and the IoT Things I care for? Related work around context management and contextualisation ranges from database techniques that involve query re-writing, to semantic web and rule-based context management approaches, to machine learning and data science-based solutions in mobile and ambient computing. All such existing approaches have two main aspects in common: They are highly incompatible and horribly inefficient from a scalability and performance perspective. In this paper, we discuss a new RISC Contextualisation Framework (RCF) we have developed, implemented key aspects of, and assess its scalability. RCF provides fundamental contextualisation concepts that can be mapped to all existing contextualisation approaches for IoT data (and in this sense, it provides a common denominator that unifies the contextualisation space). RCF can be easily implemented as a cloud-based service, and provides better scalability and performance that any of the existing content management and contextualisation approaches in the IoT space.
Learning Analytics (LA) has become a prominent paradigm in the context of education lately which adopts the recent advancements of technology such as cloud computing, big data processing, and Internet of Things. LA also requires an intensive amount of processing resources to generate relevant analytical results. However, the traditional approaches have been inefficient at tackling LA challenges such as real-time, high performance, and scalable processing of heterogeneous datasets and streaming data. An Internet of Things (IoT) scalable, distributed and high performance framework has the potential to address mentioned LA challenges by efficient contextualization of data. In this paper, CoALA, a Smart Learning Analytics conceptual model is proposed to improve the effectiveness of LA by utilizing an IoT-based contextualization framework in terms of performance, scalability, and efficiency.
Seminars, Presentations and Invited Talks
Internet-Scale Data in Internet of Things Applications
Rapid application development provides a range of enabling skills for independent development of complete and industry standard software applications. These skills will equip students to be ready for commercial development and to meet the demand of clients of various sizes, especially startups.
The topics covered in this course include: social implications of computing in a digital world; impact of social media; ethical theories and principles within IT context; IT professional ethics; intellectual property; professional communication; computer crime; ethics of sustainability (including global social and environmental impacts of computer use and disposal).
This course aims is to provide the foundation knowledge of contemporary Information Technology areas, software, applications and job skills required to enter the IT market. A major component of the course is the practical application of the knowledge gained from the theoretical content. The material covers a broad range of introductory Information Technology concepts.
The course is an introductory course in technologies to create mobile applications and mobile services. The course taught students efficient methods and practice on how to create native and platform independent (Web) mobile applications, as well as techniques for developing web-based mobile services.
Best paper award: HICSS Conference 2017, ISSIP-IBM Paper Award for Best Industry Studies
First prize at the Unearthed Hackathon
Minister for Energy and Resources and Premier of Victoria: Media Release
Unearthed is a 54-hour open innovation event focused on the resources sector. Innovators such as: software developers, engineers, data scientists, designers, and industry insiders will come together to develop prototype solutions to resources sector problems.