Learning from outliers and imbalanced data remains one of the major difficulties for machine learning classifiers. Among the numerous techniques dedicated to tackle this problem, data preprocessing solutions are known to be efficient and easy to implement. In this paper, we propose a selective data preprocessing approach that embeds knowledge of the outlier instances into artificially generated subset to achieve an even distribution. The Synthetic Minority Oversampling TEchnique (SMOTE) was used to balance the training data by introducing artificial minority instances. However, this was not before the outliers were identified and oversampled (irrespective of class). The aim is to balance the training dataset while controlling the effect of outliers. The experiments prove that such selective oversampling empowers SMOTE, ultimately leading to improved classification performance.

Separating household waste into categories such as organic and recyclable is a critical part of waste management systems to make sure that valuable materials are recycled and utilised. This is beneficial to human health and the environment because less risky treatments are used at landfill and/or incineration, ultimately leading to improved circular economy. Conventional waste separation relies heavily on manual separation of objects by humans, which is inefficient, expensive, time consuming, and prone to subjective errors caused by limited knowledge of waste classification. However, advances in artificial intelligence research has led to the adoption of machine learning algorithms to improve the $accuracy$ of waste classification from images. In this paper, we used a waste classification dataset to evaluate the performance of a bespoke five-layer convolutional neural network when trained with two different image resolutions. The dataset is publicly available and contains 25,077 images categorised into 13,966 organic and 11,111 recyclable waste. Many researchers have used the same dataset to evaluate their proposed methods with varying $accuracy$ results. However, these results are not directly comparable to our approach due to fundamental issues observed in their method and validation approach, including the lack of transparency in the experimental setup, which makes it impossible to replicate results. Another common issue associated with image classification is high computational cost which often results to high development time and prediction model size. Therefore, a lightweight model with high $accuracy$ and a high level of methodology transparency is of particular importance in this domain. To investigate the computational cost issue, we used two image resolution sizes (i.e., $225\times 264$ and $80\times 45$) to explore the performance of our bespoke five-layer convolutional neural network in terms of development time, model size, predictive $accuracy$, and cross-entropy $loss$. Our intuition is that smaller image resolution will lead to a lightweight model with relatively high and/or comparable $accuracy$ than the model trained with higher image resolution. In the absence of reliable baseline studies to compare our bespoke convolutional network in terms of $accuracy$ and $loss$, we trained a random guess classifier to compare our results. The results show that small image resolution leads to a lighter model with less training time and the $accuracy$ produced (80.88%) is better than the 76.19% yielded by the larger model. Both the small and large models performed better than the baseline which produced 50.05% $accuracy$. To encourage reproducibility of our results, all the experimental artifacts including preprocessed dataset and source code used in our experiments are made available in a public repository.

An exploratory research is presented to gauge the impact of feature selection on heterogeneous ensembles. The task is to predict diabetes onset with healthcare data obtained from UC Irvine (VCI) database. Evidence suggests that accuracy and diversity are the two vital requirements to achieve good ensembles. Therefore, the research presented in this paper exploits diversity from heterogeneous base classifiers; and the optimisation effect of feature subset selection in order to improve accuracy. Five widely used classifiers are employed for the ensembles and a meta-classifier is used to aggregate their outputs. The results are presented and compared with similar studies that used the same dataset within the literature. It is shown that by using the proposed method, diabetes onset prediction can be done with higher accuracy.

The technological developments in the Internet of Things (IoT), data science, artificial intelligence, wearable sensors, remote monitoring, decision support systems, fog, and edge systems have transformed digital healthcare. Especially after the pandemic, there has been a rapid transformation of healthcare infrastructure from a conventional to a digital approach. Now, specifically, technologies such as the Internet of Things play a vital role in the transformation of the healthcare system. In this paper, an effort has been made to encompass the transformation of healthcare with a focus on the Internet of Medical Things (IoMT). In particular, it provides a detailed overview of the Internet of Medical Things whilst discussing the design goals and challenges, the resource constraints and limitations of the complex healthcare systems. The paper also provides a detailed account of the research initiatives as well as off-the-shelf wireless motes, internet-enabled sensors and open-source platforms. A thorough account of the next-generation digital healthcare technologies and future research opportunities is provided. This work not only covers the state-of-the-art but also offers critical insight into the digital healthcare challenges. The work attempts to summarise the extensive literature in the domain and present a new perspective on the internet of medical things, affiliate technologies and their role in healthcare.

Addressing the pressing issue of food waste is vital for environmental sustainability and resource conservation. While computer vision has been widely used in food waste reduction research, existing food image datasets are typically aggregated into broad categories (e.g., fruits, meat, dairy, etc.) rather than the fine-grained singular food items required for this research. The aim of this study is to develop a model capable of identifying individual food items to be integrated into a mobile application that allows users to photograph their food items, identify them, and offer suggestions for recipes. This research bridges the gap in available datasets and contributes to a more fine-grained approach to utilising existing technology for food waste reduction, emphasising both environmental and research significance. This study evaluates various (n = 7) convolutional neural network architectures for multi-class food image classification, emphasising the nuanced impact of parameter tuning to identify the most effective configurations. The experiments were conducted with a custom dataset comprising 41,949 food images categorised into 20 food item classes. Performance evaluation was based on accuracy and loss. DenseNet architecture emerged as the top-performing out of the seven examined, establishing a baseline performance (training accuracy = 0.74, training loss = 1.25, validation accuracy = 0.68, and validation loss = 2.89) on a predetermined set of parameters, including the RMSProp optimiser, ReLU activation function, ‘0.5’ dropout rate, and a $160\times 160$ image size. Subsequent parameter tuning involved a comprehensive exploration, considering six optimisers, four image sizes, two dropout rates, and five activation functions. The results show the superior generalisation capabilities of the optimised DenseNet, showcasing performance improvements over the established baseline across key metrics. Specifically, the optimised model demonstrated a training accuracy of 0.99, a training loss of 0.01, a validation accuracy of 0.79, and a validation loss of 0.92, highlighting its improved performance compared to the baseline configuration. The optimal DenseNet has been integrated into a mobile application called FridgeSnap, designed to recognise food items and suggest possible recipes to users, thus contributing to the broader mission of minimising food waste.

Advancements in wearable sensors and digital technologies/computational tools (e.g., machine learning (ML), general data analytics, mobile and desktop applications) have been explored in existing studies. However, challenges related to sensor efficacy and the application of digital technology/computational approaches for hydration assessment remain under-explored. Key knowledge gaps include applicable devices and sensors for measuring hydration and/or dehydration, the performance of approaches (e.g., ML algorithms) on sensor-based hydration monitoring; the potential of multi-sensor fusion to enhance measurement accuracy and the limitations posed by experimental datasets. This review aims to address the gaps by examining existing research to provide recommendations for future improvements. A systematic review was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Comprehensive searches across PubMed, Scopus, IEEE Xplore and MDPI databases for academic studies published between 2009 and 2024 were performed using predefined inclusion and exclusion criteria. Two reviewers independently screened and assessed studies, with disagreements resolved by a third reviewer. Data was synthesised narratively or through meta-analysis, where applicable. The database search yielded 1029 articles, with 999 unique studies remaining after duplicate removal. After title and abstract screening, 910 irrelevant studies were excluded. Full-text evaluation of 89 articles led to the inclusion of 20 studies for in-depth analysis. Findings highlight significant progress in hydration monitoring through multi-sensor fusion and advanced ML techniques, which improve accuracy and utility. However, challenges persist, including model complexity, sensor variability under different conditions, and a lack of diverse and representative datasets. This review underscores the need for further research to overcome these challenges and support the development of robust, data-driven hydration monitoring solutions.