Abstract
Modern I/O applications that run on HPC infrastructures are increasingly becoming read and metadata intensive. However, having multiple applications submitting large amounts of metadata operations can easily saturate the shared parallel file system's metadata resources, leading to overall performance degradation and I/O unfairness. We present PADLL, an application and file system agnostic storage middleware that enables QoS control of data and metadata workflows in HPC storage systems. It adopts ideas from Software-Defined Storage, building data plane stages that mediate and rate limit POSIX requests submitted to the shared file system, and a control plane that holistically coordinates how all I/O workflows are handled. We demonstrate its performance and feasibility under multiple QoS policies using synthetic benchmarks, real-world applications, and traces collected from a production file system. Results show that PADLL can enforce complex storage QoS policies over concurrent metadata-aggressive jobs, ensuring fairness and prioritization.

Abstract
The study of data quality in crowdsourcing campaigns is currently a prominent research topic, given the diverse range of participants involved. A potential solution to enhancing data quality processes in crowdsourcing is cognitive personalization, which involves appropriately adapting or assigning tasks based on a crowd worker's cognitive profile. There are two common methods for assessing a crowd worker's cognitive profile: administering online cognitive tests, and inferring behavior from task fingerprinting based on user interaction log events. This article presents the findings of a study that investigated the complementarity of both approaches in a microtask scenario, focusing on personalizing task design. The study involved 134 unique crowd workers recruited from a crowdsourcing marketplace. The main objective was to examine how the administration of cognitive ability tests can be used to allocate crowd workers to microtasks with varying levels of difficulty, including the development of a deep learning model. Another goal was to investigate if task fingerprinting can be used to allocate crowd workers to different microtasks in a personalized manner. The results indicated that both objectives were accomplished, validating the usage of cognitive tests and task fingerprinting as effective mechanisms for microtask personalization, including the development of a deep learning model with 95% accuracy in predicting the accuracy of the microtasks. While we achieved an accuracy of 95%, it is important to note that the small dataset size may have limited the model's performance.

Abstract
The objective of this work was to support the sustainable deployment of immersive learning environments, which face varied obstacles, including the lack of support infrastructures for active learning pedagogies. Sustainability from the perspective of the integration of these environments in educational practice entails situational awareness, workload, and the informed assessment ability of participants, which must be supported for such activities to be employed in a widespread manner. We have approached this wicked problem using the Design Science Research paradigm and produced the Inven!RA software architecture. This novel result constitutes a solution for developing software platforms to enable the sustainable deployment of immersive learning environments. The Inven!RA architecture is presented alongside four demonstration scenarios employed in its evaluation, providing a means for the situational awareness of immersive learning activities in support of pedagogic decision making.

Abstract
E-commerce is a field that changed how consumers purchase and interact with products. Although, inherent limitations such as the difficulty of testing the products first-hand before a purchase can compromise consumers' trust in online purchases. Virtual Reality (VR) has been investigated as a tool to solve limitations in several fields and how we can harness its potential to improve the overall user experience. This study analysed how immersive VR (IVR) could solve these limitations by allowing consumers to test products beforehand. We have studied how the Novelty Factor (evaluated by the users' past VR experience) and Immersive Tendencies correlate with the users' Purchase Intention and Memory (how well they remember the product's characteristics). We have analysed a sample of 38 participants (21 males) from 18 to 28 years old. Participants experienced a refrigerator with an interactive touchscreen in an IVR setup and were guided through its functionalities. Results indicated that memory of the product's characteristics was positively correlated with how recently they experienced VR. No correlations were found in the female sample. A negative correlation between Purchase Intention and Memory of the product's characteristics was found in the male sample. We concluded that IVR applications could become helpful for both consumers and online shops in an e-commerce context regardless of the Novelty Factor and Immersive Tendencies of consumers. However, differences between genders should be further investigated.

Abstract
Currently, it is standard to use tracked handheld controllers for interaction in immersive virtual reality (VR). However, since VR interactions are becoming more natural with hand tracking, it is important to provide hands-free alternatives for selection and system control tasks. As such, this study aims to provide an exploratory evaluation of the effectiveness and efficiency of commonly used hands-free interfaces in selection and system control tasks. Nine interaction methods were evaluated while performing a Fitts' law task with nine advanced users of VR in a within-subject experiment. We evaluated handheld controllers as a baseline, against head gaze, eye gaze, and voice commands for pointing at the targets, and dwell time and voice commands to confirm selections. We found that using eye gaze with a 500 ms dwell time proved to be the hand-free method with the highest performance, matching the handheld controllers and being preferred by users. The evaluation also showed that using a multimodal approach to selection, especially using the voice, decreases performance, but increases effectiveness. Moreover, we verified that Fitts' law can be applied to hands-free methods, but its usage is limited when the methods have very short travel times. We then suggest selections per minute as a more robust comparative performance metric. Further studies should expand the audience and interaction tasks and focus on the confirmatory method of selection.

Abstract
To address metadata with researchers it is important to use models that include familiar domain concepts. In the Social Sciences, the DDI is a well-accepted source of such domain concepts. To create FAIR data and metadata, we need to establish a compact set of DDI elements that fit the requirements in projects and are likely to be adopted by researchers inexperienced with metadata creation. Over time, we have engaged in interviews and data description sessions with research groups in the Social Sciences, identifying a manageable DDI subset. A recent Clinical Psychology project, TOGETHER, dealing with risk assessment for hereditary cancer, considered the inclusion of a DDI subset for the production of metadata that are timely and interoperable with data publication initiatives in the same domain. Taking a DDI subset identified by the data curators, we make a preliminary assessment of its use as a realistic effort on the part of researchers, taking into consideration the metadata created in two data description sessions, the effort involved, and overall metadata quality. A follow-up questionnaire was used to assess the perspectives of researchers regarding data description.