TU Delft Repository

Located in Suriname, the village of Ricanau Mofo faces a multitude of environmental challenges. This report delves into a comprehensive study that employed a multidisciplinary approach, leveraging the expertise of students from various backgrounds to address these pressing issues.

The most critical concern identified was the relentless erosion of the riverbank, forming an existential threat to the village. The report explores interventions for both riverbank and soil erosion. Building upon the previous year's sheet pile wall construction by van Dongen et al. (2023), the report evaluates its effectiveness and proposes potential improvements for natural shore protection. It presents an analysis of structural solutions like sheet pile walls and quay walls, alongside nature-based methods that promote vegetation growth. A multi-criteria analysis is employed to objectively evaluate the effectiveness and feasibility of each intervention.

Moving beyond the riverbank, the report investigates soil erosion in Ricanau Mofo's old center. To understand the water flow patterns, a hydrological analysis was conducted. This analysis incorporated field measurements, on-site observations, and existing scientific reports. By considering factors like clay content, vegetation cover, discharge, and slope, the study categorized different flow areas within the village center. This detailed analysis lead to the proposal of a combination of targeted interventions, including roof gutters, strategic vegetation planting, and channel improvements, all aimed at effectively addressing drainage issues and mitigating soil erosion.

Waste management emerged as another critical concern. The report sheds light on the impact of inadequate waste collection systems on hygiene and even the success of other implemented solutions. Recognizing the importance of community involvement, the report proposes a roadmap and implements a physical prototype for establishing a more organized and effective waste management system, promoting a sense of shared responsibility for a cleaner Ricanau Mofo.

This report illustrates the value of a multidisciplinary approach. By combining diverse expertise and conducting thorough analyses, the study provides a comprehensive understanding of Ricanau Mofo's environmental challenges. The proposed solutions for riverbank and soil erosion control, improved drainage, and effective waste management offer a sustainable path forward for the village's future development.

This study addresses the gap for fine-grained emotion recognition in immersive environments utilizing solely data from on-board sensors. Two data representations of users eyes are utilized, including periocular recordings and eye movements (gaze estimation and pupil measurements). A novel multi-representation method integrating feature extractors for each representation alongside an effective feature fusion technique is proposed. The method significantly outperforms baselines that use only a single representation or incorporate content stimuli. It achieves an F1-score of 0.85 with 10\% data, approximately 40 seconds of data from all emotions, for personal adaptation, recognizing emotions while watching unseen parts of the stimuli used for adaptation. In a more practical scenario, the method achieves an F1-score of 0.71 with five seconds of personal adaptation data from each emotion, recognizing emotions while watching completely unseen stimuli. Under the same but more extreme condition, where only one second of data is available, the proposed achieves an F1-score of 0.68.
Furthermore, the study demonstrates that estimated labels can substitute for user-provided labels without sacrificing performance in emotion recognition, thus eliminating the need for users to manually label emotion elicitation segments.
Future work will focus on improving performance by allocating more computational resources and making architectural modifications, conducting deeper investigations into the decision-making process, and developing real-time recognition systems for in-the-wild experiments.
The results of this study suggest that more engaging, adaptive, and personalized experiences in immersive environments can be developed.

Over the last two decades, the machine learning (ML) field has witnessed a dramatic expansion, propelled by burgeoning data volumes and the advancement of computational technologies. Deep learning (DL) in particular has demonstrated remarkable success across a wide range of domains, including healthcare, mobility, life sciences, and energy systems. This success has been further accelerated by the availability and efficiency of open-source ML frameworks like TensorFlow and PyTorch, making ML methodologies more accessible than ever.

However, this rapid growth has brought its own set of challenges. The proliferation of ML models and related artifacts, such as datasets, have brought abundant information during the ML lifecycle. The descriptive and property information of these artifacts is referred as metadata. Yet current practices, such as model cards used in public model zoos and tools to track metadata within scripts, cannot fully captured the metadata of these artifacts, let alone a standardized approach for their management, and access. In addition, the prevailing practice of managing ML/DL scripts via traditional software repositories, while adequate for software engineering, falls short in addressing the unique needs of ML workflows, such as model reuse and comparative analysis. These practices hinder the effective use of structured and comprehensive metadata representation. This disconnect points to a pressing need for improved methodologies and tools in the ML field.

In response to these challenges, this thesis delves into the development and exploitation of structured metadata representations within ML model zoos. In Chapter 2, we first propose a metamodel that represent different types of metadata, thus transforming the metadata from being merely descriptive to being queryable and machine-readable. The structured nature of our metamodel allows for more efficient querying and retrieval of information, which is a substantial improvement over the traditional, text-based descriptions.

Additionally, the thesis explores the use of metadata to optimize various ML processes, particularly in the selection of appropriate models for specific tasks, i.e., model inference and fine-tuning. In Chapter 3, we investigate the optimization of ML inference queries in heterogeneous model zoos using a Mixed-Integer-Programming-based optimizer. This optimizer, which considers multiple objectives such as accuracy and inference speed, provides a robust framework for model selection and execution planning. In Chapter 4, the research extends to model selection for fine-tuning. We investigate on predicting model performance, particularly accuracy, in scenarios where data domains shift, thus negating the need for constant model fine-tuning. By selectively choosing only the most promising candidates, this method substantially lowers the computational burden and associated costs of extensive model fine-tuning.

Overall, this thesis investigates the representation and application of metadata. The insights and methodologies presented not only improve the efficiency and effectiveness of ML workflows but also pave the way for further exploration in the integration of metadata within ML practices, highlighting the continual development and potential for advancements in ML.

Drawing on existing archaeological evidence and visual materials, this paper conducts an analysis of the linguistic evolution and formal development of Xiewu. It further investigates the distinctive characteristics of its forms, structures, and spatial configurations. It reveals that Xiewu experienced a period of flourishing and innovation during Song dynasty, marking a pivotal era for its architectural significance. This paper also represents an endeavor to elucidate Song dynasty architecture through the lens of architectural massing typology, enriching the understanding of this historical architectural paradigm.