Personalized Healthcare (PH) is a new patientoriented healthcare approach which expects to improve the traditional healthcare system. The focus of this new advancement is the patient data collected from patient Electronic health records (EHR), Internet of Things (IoT) sensor devices, wearables and mobile devices, web-based information and social media. PH applies Artificial Intelligence (AI) techniques to the collected dataset to improve disease progression technique, disease prediction, patient selfmanagement and clinical intervention. Machine learning techniques are widely used in this regard to develop analytic models. These models are integrated into different healthcare service applications and clinical decision support systems. These models mainly analyse the collected data from sensor devices and other sources to identify behavioral patterns and clinical conditions of the patient. For example, these models analyse the collected data to identify the patient's improvements, habits and anomaly in daily routine, changes in sleeping and mobility, eating, drinking and digestive pattern. Based on those patterns the healthcare applications and the clinical decision support systems recommend lifestyle advice, special treatment and care plans for the patient. The doctors and caregivers can also be engaged in the care plan process to validate lifestyle advice. However, there are many uncertainties and a grey area when it comes to applying machine learning in this context. Clinical, behaviour and lifestyle data in nature are very sensitive. There could be different types of biased involved in the process of data collection and interpretation. The training data model could have an older version of the dataset. All these could lead to an incorrect decision from the system without the user's knowledge. In this paper, some of the standards of the ML models reported in the recent research trends, identify the reliability issues and propose improvements.

This paper proposes a novel identity management framework for Internet of Things (IoT) and cloud computing-based personalized healthcare systems. The proposed framework uses multimodal encrypted biometric traits to perform authentication. It employs a combination of centralized and federated identity access techniques along with biometric based continuous authentication. The framework uses a fusion of electrocardiogram (ECG) and photoplethysmogram (PPG) signals when performing authentication. In addition to relying on the unique identification characteristics of the users’ biometric traits, the security of the framework is empowered by the use of Homomorphic Encryption (HE). The use of HE allows patients’ data to stay encrypted when being processed or analyzed in the cloud. Thus, providing not only a fast and reliable authentication mechanism, but also closing the door to many traditional security attacks. The framework’s performance was evaluated and validated using a machine learning (ML) model that tested the framework using a dataset of 25 users in seating positions. Compared to using just ECG or PPG signals, the results of using the proposed fused-based biometric framework showed that it was successful in identifying and authenticating all 25 users with 100% accuracy. Hence, offering some significant improvements to the overall security and privacy of personalized healthcare systems.

With the advent of modern technologies, the healthcare industry is moving towards a more personalised smart care model. The enablers of such care models are the Internet of Things (IoT) and Artificial Intelligence (AI). These technologies collect and analyse data from persons in care to alert relevant parties if any anomaly is detected in a patient’s regular pattern. However, such reliance on IoT devices to capture continuous data extends the attack surfaces and demands high-security measures. Both patients and devices need to be authenticated to mitigate a large number of attack vectors. The biometric authentication method has been seen as a promising technique in these scenarios. To this end, this paper proposes an AI-based multimodal biometric authentication model for single and group-based users’ device-level authentication that increases protection against the traditional single modal approach. To test the efficacy of the proposed model, a series of AI models are trained and tested using physiological biometric features such as ECG (Electrocardiogram) and PPG (Photoplethysmography) signals from five public datasets available in Physionet and Mendeley data repositories. The multimodal fusion authentication model shows promising results with 99.8% accuracy and an Equal Error Rate (EER) of 0.16.

With increasing world population the demand of food production has increased exponentially. Internet of Things (IoT) based smart agriculture system can play a vital role in optimising crop yield by managing crop requirements in real-time. Interpretability can be an important factor to make such systems trusted and easily adopted by farmers. In this paper, we propose a novel artificial intelligence-based agriculture system that uses IoT data to monitor the environment and alerts farmers to take the required actions for maintaining ideal conditions for crop production. The strength of the proposed system is in its interpretability which makes it easy for farmers to understand, trust and use it. The use of fuzzy logic makes the system customisable in terms of types/number of sensors, type of crop, and adaptable for any soil types and weather conditions. The proposed system can identify anomalous data due to security breaches or hardware malfunction using machine learning algorithms. To ensure the viability of the system we have conducted thorough research related to agricultural factors such as soil type, soil moisture, soil temperature, plant life cycle, irrigation requirement and water application timing for Maize as our target crop. The experimental results show that our proposed system is interpretable, can detect anomalous data, and triggers actions accurately based on crop requirements.

Identifying the symptoms of the early stages of dementia is a difficult task, particularly for older adults living in residential care. Internet of Things (IoT) and smart environments can assist with the early detection of dementia, by nonintrusive monitoring of the daily activities of the older adults. In this work, we focus on the daily life activities of adults in a smart home setting to discover their potential cognitive anomalies using a public dataset. After analysing the dataset, extracting the features, and selecting distinctive features based on dynamic ranking, a classification model is built. We compare and contrast several machine learning approaches for developing a reliable and efficient model to identify the cognitive status of monitored adults. Using our predictive model and our approach of distinctive feature selection, we have achieved 90.74% accuracy in detecting the onset of dementia.

Cybersecurity risks have become obstinate problems for critical water infrastructure management in Australia and worldwide. Water management in Australia involves a vast complex of smart technical control systems interconnected with several networks, making the infrastructure susceptible to cyber-attacks. Therefore, ensuring the use of security mechanisms in the control system modules and communication networks for sensors and actuators is vital. The statistics show that Australia is facing frequent cyber-attacks, most of which are either undetected or overlooked or require immediate response. To address these cyber risks, Australia has changed from a country with negligible recognition of attacks on critical infrastructure to a country with improved capability to manage cyber warfare. However, little attention is paid to reducing the risk of attacks to the critical water infrastructure. This study aims to evaluate Australia’s current cybersecurity attack landscape and the implemented controls for water infrastructure using a systematic literature review (SLR). This study also compares Australia in the context of global developments and proposes future research directions. The synthesis of the evidence from 271 studies in this review indicates the importance of managing security vulnerabilities and threats in SCADA water control systems, including the need to upgrade the contemporary water security architecture to mitigate emerging risks. Moreover, human resource development with a specific focus on security awareness and training for SCADA employees is found to be lacking, which will be essential for alleviating cyber threats to the water infrastructure in Australia.