In today's digital landscape, the demand for skilled cybersecurity professionals is higher than ever. However, many educational programs primarily focus on theoretical concepts, leaving students with insufficient practical skills. To address this gap, students need actionable feedback on their hands-on labs and assignments. We present an open-source scoring engine that provides iterative, step-by-step feedback, enabling students to solve complex cybersecurity problems progressively. Integrated into existing courses, this engine can enhance labs with detailed, structured feedback, bridging the gap between theoretical knowledge and practical application. A preliminary study with 11 students showed that all participants could complete complex tasks using the feedback provided by the engine, with limited instruction from the authors. Additionally, about 90% of the students reported high satisfaction with the structured feedback. This approach has the potential to transform cybersecurity education, making it more interactive, practical, and aligned with real-world requirements.

The increasing sophistication of cybersecurity threats necessitates an educational approach that blends theoretical knowledge with practical experience. Many courses focus primarily on theoretical concepts, leaving students with limited hands-on experience with real-world challenges. This paper introduces a cybersecurity course model that integrates Experiential Learning Theory to provide a comprehensive hands-on learning environment. The course covers important cybersecurity topics, including SSH, VPNs, TLS, MFA, OpenID Connect, OAuth2, web server security, high availability, replication, distributed file systems, and orchestration with Docker and Kubernetes. These topics are explored through a mix of lectures, peer presentations, and weekly hands-on team practices. Over three years, the course has been offered at our large public university with 72 students enrolled, consistently receiving high course ratings between 4.8 and 5.0. This paper discusses the course design, methodology, and outcomes, offering insights for educators to replicate and adapt the model for their own institutions.

Oyster farms provide a sustainable and profitable export for New Zealand. Oyster farms are sensitive to changes in salinity that can cause significant crop loss if they persist too long. Recent extreme weather events have been leading to increased periods of low salinity, putting the farms at risk. Machine learning based methods provide a way to predict these low salinity events and provide an early warning system, but this has not been investigated in aquaculture. In this paper, we investigate three different methods to assess the viability of salinity prediction systems. A simple statistical model, a genetic programming (GP) based symbolic regression model and a convolutional neural network (CNN) were compared as ways of solving this problem. The results show that GP based symbolic regression and CNNs are fairly good approaches to predicting salinity. However, as weather events get more extreme, the CNN approach tends to hold up better and can be generalised better, while the G P based symbolic regression models show better potential explainability with the tree based model structure. These results show promise and provide a good stepping off point at creating a generalised approach to predicting salinity in estuaries.

Covid-19 is a novel coronavirus that emerged in 2019 and spread across the globe, establishing a worldwide pandemic. Vaccination was presented as the most effective solution against the virulence of Covid-19. Accelerated vaccination programmes pushed several nucleic acid-based vaccines into production. Global desperation and limited vaccine supply allowed substandard and falsified (SF) Covid-19 vaccines to enter the supply chain. Conventional analytical methods can be cumbersome, costly and sophisticated to operate. Thus, this study presented a comparison of handheld surface-enhanced Raman spectroscopy (SERS) and Raman microscopy with machine learning algorithms (MLAs) for the rapid authentication of Covid-19 vaccines. Measurements were taken using the Metrohm MIRA XTR DS handheld Raman spectrometer and the Horiba XploRA Plus Raman microscope. Raman spectroscopy showed strong potential as a vaccine authentication method, allowing identification of nucleic acid-specific bands in spectra. SERS showed enhancement of up to $498 \%$ when applied to vaccines of sufficient concentration. Clustering based on principal component analysis (PCA) showed some accuracy but indicated poor repeatability for SERS, although, multiple classification models obtained $100 \%$ accuracy and area under the curve (AUC) for vaccine brand prediction based on spectral characteristics. Raman microscopy produced variable results with improved spectral quality over Raman spectroscopy for a number of samples. However, significant fluorescence was observed in numerous vaccine spectra, limiting the identification potential of the method. Clustering based on PCA showed accuracy in distinguishing between vaccine samples, but showed limited performance in vaccine brand identification. Therefore, this paper presents proof of concept for the use of both handheld Raman spectroscopy and confocal Raman microscopy alongside MLAs for the rapid, on-site authentication of Covid-19 vaccines, with further method optimisation required to combat fluorescence interference in vaccine spectra and expansion of sample size to address the potential of overfitting in the MLAs.

The prevalence of cardiovascular diseases (CVDs) and diabetes mellitus (DM) has become a global concern with figures as high as $\mathbf{1 7. 9}$ and $\mathbf{1. 5}$ million lives lost annually [1, 2]. Global figures also suggested that the majority of CVDs and DM are present within low- and middle-income countries (LMICs), where medical equipment, staff and training is limited. As a result, many patients go underdiagnosed or undertreated and instead are left to manifest into further complications such as heart failure or diabetic ketoacidosis, respectively. Therefore, this study aimed to investigate the use of nearinfrared (NIR) spectroscopy paired with machine learning algorithms (MLAs) for detection of CVDs and DM in fingernails. The findings showed key NIR bands related to the glycation of proteins within the fingernails and indicated the presence of disease. Furthermore, binary and multi-class classification models were explored for the classification of healthy, unhealthy, CVD and diabetic fingernails.

Productivity methodologies and tools are crucial in technology-focused organizations, fostering efficiency and collaboration. Industry practices, such as Scrum and Objectives and Key Results (OKRs), along with tools like Jira and Git, empower individuals and teams. Communication platforms like Zoom, Microsoft Teams, Slack, and Confluence bridge geographical gaps. Despite their significance, a noticeable gap exists in integrating these practices into academic institutions, hindering students' transitions to the professional realm. This research focuses on effectively integrating industry best practices—Scrum, OKRs, Jira, Git, Zoom, Microsoft Teams, Slack, and Confluence—into academic settings to improve students' individual and team performance in the classroom and to elevate their overall readiness for industry. The study presents practical guidelines derived from interviews with industry professionals, establishing parallels between industry and academia. These guidelines encompass supplemental learning, pairing students with experienced individuals, and recommending cost-effective tools like Discord for collaboration. Scrum principles, implemented through Taiga (a free alternative to Jira) and GitHub, along with OKRs, are endorsed for project and task tracking, providing a comprehensive framework for enhanced productivity in academic contexts. An assessment of these guidelines in an intensive cybersecurity course at a large public university reveals positive outcomes. Pairing students and leveraging Discord for communication prove effective. Methodologies like Scrum and OKRs receive positive responses, with Git emerging as a favorite for collaborative work. The role of Taiga in task accountability is acknowledged. Overall, the implementation of our guidelines demonstrates a positive impact on student and team performance, emphasizing the potential for the effective integration of industry-endorsed practices in academic settings.

Building Automation Systems (BASs) are seeing increased usage in modern society due to the plethora of benefits they provide such as automation for climate control, HVAC systems, entry systems, and lighting controls. Many BASs in use are outdated and suffer from numerous vulnerabilities that stem from the design of the underlying BAS protocol. In this paper, we provide a comprehensive, up-to-date survey on BASs and attacks against seven BAS protocols including BACnet, EnOcean, KNX, LonWorks, Modbus, ZigBee, and Z-Wave. Holistic studies of secure BAS protocols are also presented, covering BACnet Secure Connect, KNX Data Secure, KNX/IP Secure, ModBus/TCP Security, EnOcean High Security and Z-Wave Plus. LonWorks and ZigBee do not have security extensions. We point out how these security protocols improve the security of the BAS and what issues remain. A case study is provided which describes a real-world BAS and showcases its vulnerabilities as well as recommendations for improving the security of it. We seek to raise awareness to those in academia and industry as well as highlight open problems within BAS security.

Timely detection of behavioural and psychological symptoms of dementia is important for the prevention and reduction of distress for people with dementia and their loved ones. Wearable computing-based systems can be used to predict such difficulties in a timely manner, but a data collection experiment is needed to collect data to develop such a system. Caregivers can be vital assets in such experiments, however, often face high burden and stress due to their caring obligations. An even greater burden has been experienced by many due to the ongoing COVID-19 pandemic. In this paper, the roles that caregivers played in physiological data collections are reviewed. Three main roles were identified as being performed by caregivers in such data collection experiments: observation of difficulties; consenting for participants and themselves; device set-up and maintenance. Roles such as aiding in recruitment and providing information to participants before and during the study were also performed. Each of these roles can present their own burdens, which can be mitigated in a number of ways. Overall, it is vital that researchers consider the burden that may be placed on the caregiver who isfulfilling any of these roles in an experiment with sufficient mitigations to those burdens being implemented. Furthermore, we propose a pivot in our research towards analysing stress during the pandemic, justifying how this will help towards developing a system to detect dementia-related difficulties.

We present a systematic review of wearable devices used for predicting or identifying dementia-related agitation. In the review, six named and described devices were found in the literature and each was evaluated and reviewed to identify their strengths and weaknesses, with all possessing at least one weakness which made it not ideal for future research on the prediction or detection of dementia-related agitation. Only two of the wearables contained all three of the desired sensing modalities, with one of those devices being prohibitively expensive for use in many applications and studies and the other being untested and unevaluated as well as not being available commercially or for use. Future work should focus on the development of a device which contains the three desired sensing modalities while remaining inexpensive and usable enough to be accessible for use in a wide variety of studies and applications.

Data science is the process of liberating meaning from raw data using scientific methods and algorithms, and is becoming much more commonly used in healthcare with the emergence of personalised healthcare. Alzheimer's disease (AD) is a neurodegenerative disease that has no proven curative treatment, however a new treatment protocol, ReCODE, has been proposed to slow and reverse the progression of the disease. In this paper, an overview of AD is provided, followed by a description of the ReCODE protocol, including the new proposed methods and data to be used in prediction diagnosis and treatment. The ways in which data science can help with prediction and diagnosis are then reviewed, along with the data science techniques that can help with each treatment in the protocol. It is concluded that current data science techniques are useful in aiding the successful treatment of AD patients with he ReCODE protocol, and though there is much promise to the use of data science techniques to predict and diagnose AD, no such technique yet exists that can process all the necessary data. Future research should be conducted to develop such a data science technique. Further research should also be conducted to improve current data science techniques used to support the treatment of AD.