132571 research outputs found
Sort by
Deep Learning-based Segmentation of Cracks within a Photogrammetry Solution: Fully-Supervised Learning, Transfer Learning and Photogrammetric Image Processing
No full textThe city of Amsterdam faces the challenge of monitoring and assessing 200 kilometers of historic quay walls, of which much is deemed to be in poor condition. A key monitoring technique used is photogrammetry resulting in deformation testing. The fundamental data source forming the basis of this deformation analysis is a collection of overlapping images acquired of the masonry quay walls. Solely focusing on deformations overlooks a potential wealth of information which could be retrieved from this imagery, like the existence of cracks in the quay walls, a key sign of potential deformation of the structure.As manual visual inspection of this imagery is very time-consuming, this work proposes a methodology based on fully-supervised deep learning-based segmentation techniques with the goal of detecting and localizing cracks in the masonry quay walls. For this purpose, two neural networks are trained, one for the segmentation of quay walls in images, and one for the segmentation of cracks.The neural network architectures which are considered in this work are DeepLabV3+, FPN, MANet and LinkNet, together with different encoders and loss functions. For quay wall segmentation, we adopt transfer learning on a network trained on masonry walls and fine-tune it for quay walls specifically. Here, DeepLabV3+ with ResNeXt-50 was found to be most effective, achieving a F1-score of 96.3 % on the test set. For crack segmentation, FPN with ResNeSt-50 performed best, resulting in a test set F1-score of 78.8 %.The inference of the crack network is done with a multi-level scheme to detect cracks at different image scales and increase output confidence.The inherent photogrammetric properties of the imagery have proven to be vital for further post-processing steps, like aggregating overlapping predictions, resulting in more prediction confidence. Photogrammetry also enables converting pixel-wise predictions to crack length and crack width in the units of meters and millimeters respectively. The methodology additionally proposes photogrammetric image processing methods to transform neural network predictions to a 3D representation and a true-to-scale orthographic 2D image. Additionally a concise visual evaluation has been conducted to assess the prediction performance on an otherwise unlabelled dataset.This thesis presents an engineering effort for fully-supervised crack localization within the context of photogrammetric processed images, with generalization in mind for automatic assessment.Geoscience and Remote Sensin
Assessing perceived Humanness of Artificial Intelligence in Chess: A Turing Test experiment using Think Aloud and Eye Tracking methods
No full textWith the advancement of Artificial Intelligence leading to increasingly human-like outputs, assessing a machine’s ability to exhibit human-like intelligence has become more essential than ever. This study aims to investigate how human-like chess players perceive four conditions: one human opponent and three different types of algorithms. One of these algorithms, Maia, has been trained on human data and aims to play the most human-like move. In a custom-designed experiment similar to a Turing test, chess players faced off against Maia, Stockfish and a human without knowing their opponent’s nature. After each game, the chess player assessed how human-like the moves of the opponent were and estimated whether they played against an engine or a human opponent. During the game, participants were asked to think aloud about their next move and react towards the moves of the opponent. Additionally, the gaze of the player was captured with the SR EyeLink Portable Duo at 1000Hz, with the goal of finding differences within the player’s gaze while participants tried to discover the nature of their opponent. Results from the experiment revealed that, based on responses to a subjective questionnaire, the perceived humanness of Maia is statistically similar to a human and different from the other two chess engines. From the analysis of the voice recordings, categories of sentences were identified that could suggest recognition of the opponent, specifically: "expected", "unexpected", "human-like" and "engine-like". From the eye-tracking results, the average fixation duration and pupil diameter changes following the opponent’s move were compared for each condition, but showed no statistical differences between conditions. In summary, Maia was perceived more human-like compared with other chess engines. However, differences in underlying cognitive processes on how the human perceived this difference in a Turing Test experiment were not identified.Mechanical Engineering | BioMechanical Desig
From Potential to Practice: Intellectual Humility During Search on Debated Topics
No full textAn essential characteristic for unbiased and diligent information-seeking that can enable informed opinion formation and decision-making is intellectual humility (IH), the awareness of the limitations of one's knowledge and opinions. While researchers have recognized the potential to boost IH in individuals, the effect of such interventions on their search behavior, along with the broader significance of IH in the context of web search on debated topics remains unexplored. In this paper, we present the results of a preregistered user study (N = 299) that we conducted to (1) test the effect of three interventions that boost self-reported IH on opinionated individuals' search behavior and (2) explore the role of IH in the search process of opinionated individuals more broadly. IH-boosting interventions did not affect search behavior; we attribute this to the high familiarity of the search environment, prompting searchers to default to their usual search behavior. Still, explorations of the role of IH in the search process indicate that IH and IH-related search intentions should be considered as relevant factors in the pursuit of supporting unbiased and diligent search on debated topics. Based on our exploratory findings, we argue that future research should investigate interventions that are more directly integrated into the search process, as well as such that combine boosting IH with encouraging searchers to approach the search task in an IH-driven way and promoting transparency for appropriate reliance on the search system and ranking.Web Information System
Optical signatures of charge- and energy transfer in TMDC/TMDC and TMDC/perovskite heterostructures
No full textHeterostructures (HSs) based on two-dimensional transition metal dichalcogenides (TMDCs) are highly intriguing materials because of the layers’ pronounced excitonic properties and their nontrivial contributions to the HS. These HSs exhibit unique properties that are not observed in either of the constituent components in isolation. Interlayer excitons (IEs), which are electron-hole pairs separated across the HSs, play a central role in determining these HS properties and are of interest both fundamentally and for device applications. In recent years, a major focus has been on understanding and designing HSs composed of two or more TMDC materials. Less attention has been paid to HSs composed of one TMDC layer and a layer of perovskite material. A central challenge in the understanding of HS properties is that basic measurements such as optical spectroscopic analysis can be misinterpreted due to the complexity of the charge transfer dynamics. Addressing these aspects, this review presents an overview of the most common and insightful optical spectroscopic techniques used to study TMDC/TMDC and TMDC/halide perovskite HSs. Emphasis is placed on the interpretation of these measurements in terms of charge transfer and the formation of IEs. Recent advances have started to uncover highly interesting phenomena, and with improved understanding these HSs offer great potential for device applications such as photodetectors and miniaturized optics.ChemE/Opto-electronic Material
The Impact of Charging Electric Vehicles Between Routing Instances: The Modeling of a Combined Electric Vehicle Routing and Charging Model
No full textE-mobility, in particular electric vehicles (EVs), play a crucial role in the energy transition. While businesses are increasingly adopting EVs, there is still a lot of opportunity to grow. One aspect of this growth is the way these vehicles are used by companies, especially when it comes to the logistics of EV charging. To encourage companies to further reduce their carbon footprint by more efficiently utilizing EVs, this project proposes a combined vehicle routing and charging model. These models can be used separately, as well as together, allowing the charging model to be combined with any pre-existing routing engine. The goal of this project is to show the benefits of allowing EVs to be charged between shifts during the day, rather than exclusively overnight, as well as to show how such schedules can be made. Our results show that giving vehicles the opportunity to charge between shifts can significantly reduce the costs associated with fleet operations. If the fleet contains non-electric vehicles as well as electric ones, we also see a significant reduction in the number of kilometers driven using fossil fuels. When sufficient chargers were available, even when the vehicles had little time to charge, a feasible schedule could always be found. Moreover, when more realistic charging intervals were used, most vehicles were even able to fully recharge before the start of their next shift. Finally, we concluded that the set of chargers needed to find such a feasible schedule can be relatively small, meaning that even without extensive additions to the charging infrastructure, companies can still benefit from this policy change.Applied Mathematic
Constructing and storytelling: accommodating different play orientations in learning spatial thinking
No full textSpatial ability is malleable and belongs in the preschool. For preschoolers, many analytical activities with one correct answer such as tangram have been developed. Less is known about employing open-ended design assignments to creatively practice spatial thinking. Little attention has been paid to the mutual qualitative differences between children when engaged in spatial thinking and insight in children’s motivation is lacking. As design and play have much in common, our first study investigated play orientations during free play of 49 Dutch preschoolers during free play in a low and a high SES school. Participative interviews and observations in the construction and home corners of two schools uncovered different play orientations– construction and pretend play - and either a focus on open-ended objects or on defined objects. In a subsequent study, the influence of these play and object orientations on how children design was investigated. This study with 13 children also used generative design research methods grounded in ethnographic research and therapeutic practices. Using an empathic, story-based, open-ended design challenge, results showed that play-orientations of children influence the length and nature of the design activities as well as the design outcomes. Children with a pretend-play orientation are longer engaged and talk more about the character involved. They usually built organic structures with a variety of objects, while construction-oriented children mainly built sturdy and geometrical structures and mainly used open-ended objects. In all play orientations, spatial thinking was practiced and children were spatially challenged. For example, in all orientations difficulties arose around getting the character in out the structure, however, as different structures were build, the nature of these difficulties were also different. Open-ended design activities that contain characters and problems children can empathize with are a valuable addition to the palette of activities to develop spatial thinking in early classrooms. Our study shows that design activities stimulate children to practice spatial thinking in a creative context and have the ability to engage children with a pretend-play orientation who are otherwise less engaged in construction. The play-orientations and object-orientations are informative for research and the development of spatial educational interventions aiming at a diversity of learners.Industrial Design EngineeringScience Education and CommunicationDesign Conceptualization and Communicatio
Ridesourcing platforms thrive on socio-economic inequality
No full textLimited available market share data seems to suggest that ridesourcing platforms benefit from, even thrive on, socio-economic inequality. We suspect that this is associated with high levels of socio-economic inequality allowing for cheap labour as well as increasing the share of travellers with a considerably above-average willingness to pay for travel time savings and comfort. We test the relation between inequality and system performance by means of an agent-based simulation model representing within-day and day-to-day supply-demand interaction in the ridesourcing market. The model captures travellers’ mode choice with a heterogeneous perception of relevant time components, as well as job seekers’ participation choice with heterogeneous reservation wage. Our experiments cover scenarios for the entire spectrum ranging from perfect equality to extreme inequality. For several of such scenarios, we explore alternative platform pricing strategies. Our analysis shows a strong, positive relationship between socio-economic inequality and ridesourcing market share. This is the outcome of the combination of cheap labour and time-sensitive ridesourcing users, reinforced by network effects inherent to ridesourcing markets. We find that driver earnings are minimal in urban areas with large socio-economic inequality. In such contexts, drivers are likely to face a high platform commission, and yet, fierce competition for passengers.Transport and Plannin
Architecture of Oxfordian coral buildups along the Atlantic margin of Morocco
No full textOxfordian (Upper Jurassic) coral buildups developed widely in Tethys and Atlantic realms, during a time when paleoclimate potentially swung between greenhouse climate and cold snaps. Buildups were constructed by platy and branching corals, sponges and microbialites. Although their initiation is commonly linked to the Upper Jurassic global transgression, a number of global and local factors may have influenced buildup growth and demise (e.g. climate, shelf geometry, detrital input). Extensive outcrops of Oxfordian buildups in Morocco provide an opportunity to investigate the relationship between external drivers and buildup fauna and architecture. Here we show that the interplay of local accommodation changes, rising sea water temperature, and increasing pCO2 linked to the onset of the Middle Oxfordian global transgression were the main drivers for buildup initiation, which was synchronous across the basin. The demise of the coral buildups in Morocco was linked to a regression, dated no later than Upper Oxfordian, the establishment of partly evaporitic conditions across the basin, and to localized influx of coarse-grained siliciclastics, the latter likely driven by synsedimentary tectonic activity. Serial logged sections, outcrop panoramas and detailed facies analysis show that low-relief deeper-water buildups of Dimorpharaea platy corals evolved into higher-relief diversified buildups where shallower-water reworking produced coral rubble and large clinoforms. Buildup diachronicity is apparent, with younger coral bioherms growing in the depressions created between the initial bioherms. Size of buildups ranges from 2 m wide and 0.5 m thick, to 700 m wide and 80 m thick. The outcrops provide constraints on geobody architecture and heterogeneity in the subsurface of Morocco and North America, where facies-controlled dolomitization of high-energy buildup and clinoform facies is a main driver for porosity development.Applied Geolog
Incompatibility stress at inclined grain boundaries for cubic crystals under hydrostatic stress and uniaxial stress
No full textIn a material under stress, grain boundaries may give rise to stress discontinuities. The stress state at grain boundaries strongly affects microscopic processes, such as diffusion and segregation, as well as failure initiation, such as fatigue, creep, and corrosion. Here the general condition of incompatibility stress at grain boundaries is studied with a bicrystal model for linear elastic materials. In materials with cubic crystal structures, it is proven that hydrostatic stress does not lead to a stress discontinuity at grain boundaries. For bicrystals with inclined grain boundaries under uniaxial stress, the extreme values of the incompatibility stress as a function of the inclination angle are obtained by a simulated annealing method. A simple criterion is proposed to classify cubic materials into three groups. For cubic crystals with at most moderate anisotropy, the highest incompatibility stress occurs when the grain boundary plane is perpendicular to the uniaxial stress. For highly anisotropic materials, such as alkali metals and polymorphic high-temperature phases, the highest incompatibility stress occurs on grain boundaries with an inclination of about 47o.Team Marcel Sluite
Improving Adversarial Attacks on Decision Tree Ensembles: Exploring the impact of starting points on attack performance
No full textMost of the adversarial attacks suitable for attacking decision tree ensembles work by doing multiple local searches from randomly selected starting points, around the to be attacked victim. In this thesis we investigate the impact of these starting points on the performance of the attack, and find that the starting points significantly impact the performance: some do much better than others. However, we do find that this is not the case for all attacked points, as there are large differences between points in how difficult they are to attack and for all datasets some points are always optimally attacked.We compare the baseline randomly selected points to three alternative strategies. First, we try alternate random distributions, playing with both the standard deviation, to create a more narrow cone around the victim point, and mean, creating bimodal distributions further away from the victim point. We find that for some datasets these can give up to - improved performance on subsets of the dataset, but these improvements do not generalize to the remainder of the dataset. In general, as long as the distribution is wide enough to successfully find starting points we do not find a substantial performance change.Secondly, we try to remove the randomness and attack from a fixed direction. For the simpler datasets we find it is possible for a starting direction to perform better than random starting points, but for larger datasets performance becomes much worse. We also try an attack from all main directions around the victim point, which we find performs much worse than - times fewer random points. Lastly, we create an attack strategy where we select the closest points that scored well on previously attacked victims. We find that on smaller test sets this gets outperformed by the baseline, but when we extend the attack and give more possible previously well performing starting points we match or outperform the baseline slightly.Computer Science | Cyber Securit