Abstract
Parkinson's Disease (PD) is a neurological disease that progresses over time and causes severe motor symptoms. Therefore, treating PD requires constant patient monitoring, which may turn clinical practice overwhelming, preventing its practical implementation, and raising the need for patient monitoring outside the clinical setting. The iHandU system described in this paper fulfils this need by providing an objective way to quantify motor symptoms of PD in non-clinical settings. It integrates an innovative real-time assessment of the severity of motor symptoms based on signal processing and Machine Learning models that mimic the clinical severity classification scales used in practice and allows for a more continuous and personalized therapy planning and management by doctors, through the use of a web dashboard user-friendly interface. This system, recently tested at 5 patients' homes, has shown promising results as a PD patient management digital platform, reaching a usability score of 83.9% (A grade) based on the System Usability Scale (SUS). Such a level shows a strong alignment between user needs, expectations and functionalities. This study highlights the potential of the used system as a Patient Management Tool showing a case study from an ongoing clinical study. By giving additional information to the doctors with features beyond the semi-quantitative rating scales currently used, allowing a more optimized and continuous PD symptom management, it will be possible to advance PD management further.

Abstract
This research investigates the use of artificial intelligence algorithms to identify behavioural patterns in computer use, with the aim of detecting trends that help to flag cases of depression by analysing the human-computer interaction records of these users, thereby increasing the quality of the data for early detection of these situations. Following design science methodology, a case study will be conducted using an existing mental health screening questionnaire, integrating an artificial intelligence layer to map mouse and keyboard interactions, followed by machine learning analysis of the records. The results of the machine learning assisted questionnaires will be compared with the results of the questionnaires without the mapping. If there is a significant difference, this model could be useful for making predictions about emotional states, contributing to the field of artificial intelligence and helping to prevent depression, which is the focus of the research, although the aim is to look at mental health in a global way.

Abstract
PurposeIn a society that encourages consumption, attributes such as exclusivity and social recognition are important in what is intended to be restricted to a certain exclusive segment. Luxury is something that is more desirable than necessary. This study develops and tests a model that analyses the brand loyalty-risk relationship in the luxury watch market.Design/methodology/approachTo test the proposed research model, a sample of 306 international consumers and enthusiasts of luxury brand watches was collected. The data were analysed using structural equation modelling.FindingsThe results show that perceived quality has a negative indirect influence on brand risk and brand trust has a strong direct negative effect on brand risk. However, the findings also show that in the luxury market, the greater the affection for the brand, the greater the risk perceived by consumers.Research limitations/implicationsThe study was conducted in a single market, luxury watches and the sample includes both enthusiasts and consumers of the luxury brands.Practical implicationsManagers should be aware of the double-edged role of brand affect on brand risk. The quality of a brand and the trust in its promise decrease the risk to the consumer.Originality/valueThis pioneering study is one of the first to approach an underexplored topic as is the case of the risk associated with a brand in the context of the luxury goods market. Moreover, it relies on an international sample composed of consumers from several countries.

Abstract
Face recognition applications have grown in parallel with the size of datasets, complexity of deep learning models and computational power. However, while deep learning models evolve to become more capable and computational power keeps increasing, the datasets available are being retracted and removed from public access. Privacy and ethical concerns are relevant topics within these domains. Through generative artificial intelligence, researchers have put efforts into the development of completely synthetic datasets that can be used to train face recognition systems. Nonetheless, the recent advances have not been sufficient to achieve performance comparable to the state-of-the-art models trained on real data. To study the drift between the performance of models trained on real and synthetic datasets, we leverage a massive attribute classifier (MAC) to create annotations for four datasets: two real and two synthetic. From these annotations, we conduct studies on the distribution of each attribute within all four datasets. Additionally, we further inspect the differences between real and synthetic datasets on the attribute set. When comparing through the Kullback-Leibler divergence we have found differences between real and synthetic samples. Interestingly enough, we have verified that while real samples suffice to explain the synthetic distribution, the opposite could not be further from being true.

Abstract
We present a pilot study where spectral unmixing is applied to hyperspectral images captured in a controlled environment with a threefold purpose in mind: validation of our experimental setup, of the data processing pipeline, and of the usage of spectral unmixing algorithms for the aforementioned research avenue. Results from this study show that classical techniques such as VCA and FCLS can be used to distinguish between plastic and nonplastic materials, but struggle significantly to distinguish between spectrally similar plastics, even in the presence of multiple pure pixels.

Abstract
This study reports the fabrication of three-dimensional microfluidic channels in fused silica, using femtosecond laser micromachining, to achieve two-dimensional hydrodynamic flow focusing in either the horizontal or the vertical directions. Spatial focusing of 3 µm polystyrene particles was successfully demonstrated, showing the ability of the fabricated devices to confine microparticles within a 6 µm layer over a channel width of 420 µm and within a 5 µm layer over a channel height of 260 µm. Integration of laser-direct written optical waveguides inside a microfluidic chip and orthogonal to the channel also enabled the implementation of a dual-beam optical trap, with trapping of polystyrene microparticles using a 1550 nm beam being demonstrated. © The Authors.