Open Access

The goal of this study was to utilize a state-of-the-art Speech Emotion Recognition (SER) model to explore the dynamics of basic emotions in semi-structured clinical interviews about depression. Segments of N = 217 interviews from the general population were evaluated using the emotion2vec+ large model and compared with the results of a depressive symptom questionnaire. A direct comparison of depressed and non-depressed subgroups revealed significant differences in the frequency of happy and sad emotions, with participants with higher depression scores exhibiting more sad and less happy emotions. A multiple linear regression model including the seven most predicted emotions plus the duration of the interview as predictors explained 23.7 % of variance in depression scores, with happiness, neutrality, and interview duration emerging as significant predictors. Higher depression scores were associated with lesser happiness and neutrality, as well as a longer interview duration. The study demonstrates the potential of SER models in advancing research methodology by providing a novel, objective tool for exploring emotional dynamics in mental health assessment processes. The model’s capacity for depression screening was tested in a realistic sample from the general population, revealing the potential to supplement future screening systems with an objective emotion measurement.

The identification and traceability of assets throughout their lifecycle is an important prerequisite for the efficient management of circular value creation and the reuse of components and products. This is a particular problem in complex and dynamic value chains. This paper examines the challenges of identifiers in circular supply chains and presents current solution approaches for identification systems by the means of the Digital Product Pass and the Asset Administration Shell. Architectures are presented for ensuring consistent identification in a circular economy and effective traceability systems in global supply chains. The paper highlights the need for both the physical identification features and the associated digital identification information to make an object consistently and uniquely identifiable.

Traditional learning environments are ineffective and inefficient and are failing to adequately equip students and employees with the knowledge and skills required in today’s jobs, let alone prepare them for the jobs of tomorrow. Given the rapidly changing landscapes of technologies and business models, organisations need to be flexible and adaptable to respond to, and even pre-empt future demands. One of the primary shortcomings of existing learning environments is their inflexibility and the ‘one size fits all’ approach followed. Serious games and game-based learning are widely recognised for their potential in providing more effective learning environments, especially when designed in a personalised, adaptive manner, and are explored in this dissertation. In addition to adapting to the individual traits and preferences of users, games are also highly context dependent. Whilst there is a great deal of literature and documented case studies of game-based learning, most focus only on the implementation of one particular game in a specific context. Whilst many existing game design models and approaches focus on achieving improved learning outcomes of learners, there is an opportunity to consider the impact of gameplay on other stake- holders and drive the active development of meta-skills in various stakeholders. Bidirectional learning, where learning simultaneously takes place in a two-way direction [295], has great potential and has, to date, not been incorporated in serious game design. By integrating different perspectives and variable scenarios, the dynamic personalisation of learning trajectories may be possible. Serious games offer a potential platform to aggregate learner behaviours and results, and use these to dynamically configure, adjust and tailor the game to individuals and contexts, ultimately providing a learning environment of improved quality, effectiveness and efficiency. In this dissertation, adaptive, bidirectional games are explored as a means to provide more effective and efficient learning environments for multiple stakeholders. Moreover, an architecture is presented to support the creation of such games for specific scenarios in a faster, more effective and more efficient manner. Following a research-by-design approach, the architecture is iteratively developed and simultaneously applied in four case studies. Experiences and learnings from each case study are infused into subsequent design iterations of the architecture. The architecture allows users to explore and exploit the solution space more deliberately and better understand the various functions and the interrelations between them. The flexible and modular structure of the architecture allows users to prioritise functionalities as required in the given scenario. Furthermore, the directional relations between functions can be interpreted and prioritised as needed given the specific context and requirements. The architecture incorporates various stakeholders in the design process, leading to greater transparency and better understanding throughout the process. More importantly, it emphasises bidirectional learning whereby different stakeholders can learn from gameplay and the aggregated results and behaviours of players.

In this study, a method for determining the optimal location and orientation of an implantable piezoelectric accelerometer on the short process of the incus is presented. The accelerometer is intended to be used as a replacement for an external microphone to enable totally implantable auditory prostheses. The optimal orientation of the sensor and the best attachment point are determined based on two criteria—maximum pressure sensitivity sum and minimum loudness level sum. The best location is determined to be near the incudomalleolar joint. We find that the angular orientation of the sensor is critical and provide guidelines on that orientation. The method described in this paper can be used to further optimize the design and performance of the accelerometer.

A simple technique for generating single and multiple beams from antenna arrays is presented. The approach is based on the multistage sequential rotation technique. A new feature in using multistage sequential rotation is provided. It is demonstrated that by applying a controlled second sequential rotation, circularly polarized antenna arrays operating alternately in a single-beam mode M1 and multi-beam mode M2 in the same frequency band can be designed. Proof-of-concept is provided mathematically and through numerical simulations in light of case studies. The approach can not only be applied to large antenna arrays following a modular principle adapted to the array size and needed applications without loss of generality, but it also paves the way for the manufacture of circularly polarized antennas operating alternately or simultaneously in both modes in the same frequency band. In addition, antennas designed using the proposed approach may have a wide range of applications ranging from monopulse radar to antennas for compensation of interference and blockage in dynamic communication environments.