Abstract
Pulse oximeters measure peripheral arterial oxygen saturation (SpO2) noninvasively, while the gold standard (SaO2) involves arterial blood gas measurement. There are known racial and ethnic disparities in their performance. BOLD is a new comprehensive dataset that aims to underscore the importance of addressing biases in pulse oximetry accuracy, which disproportionately affect darker-skinned patients. The dataset was created by harmonizing three Electronic Health Record databases (MIMIC-III, MIMIC-IV, eICU-CRD) comprising Intensive Care Unit stays of US patients. Paired SpO2 and SaO2 measurements were time-aligned and combined with various other sociodemographic and parameters to provide a detailed representation of each patient. BOLD includes 49,099 paired measurements, within a 5-minute window and with oxygen saturation levels between 70-100%. Minority racial and ethnic groups account for ~25% of the data - a proportion seldom achieved in previous studies. The codebase is publicly available. Given the prevalent use of pulse oximeters in the hospital and at home, we hope that BOLD will be leveraged to develop debiasing algorithms that can result in more equitable healthcare solutions.

Abstract
We present an imperative refinement language for the development of backtracking programs and discuss its semantic foundations. For expressivity, our language includes prospective values and preference - the latter being a variant of Nelson's biased choice that backtracks from infeasibility of a continuation. Our key contribution is to examine feasibility-preserving refinement as a basis for developing backtracking programs, and several key refinement laws that enable compositional refinement in the presence of non -monotonic program combinators.

Abstract
Machine vision systems are widely used in assembly lines for providing sensing abilities to robots to allow them to handle dynamic environments. This paper presents a comparison of 3D sensors for evaluating which one is best suited for usage in a machine vision system for robotic fastening operations within an automotive assembly line. The perception system is necessary for taking into account the position uncertainty that arises from the vehicles being transported in an aerial conveyor. Three sensors with different working principles were compared, namely laser triangulation (SICK TriSpector1030), structured light with sequential stripe patterns (Photoneo PhoXi S) and structured light with infrared speckle pattern (Asus Xtion Pro Live). The accuracy of the sensors was measured by computing the root mean square error (RMSE) of the point cloud registrations between their scans and two types of reference point clouds, namely, CAD files and 3D sensor scans. Overall, the RMSE was lower when using sensor scans, with the SICK TriSpector1030 achieving the best results (0.25 mm +/- 0.03 mm), the Photoneo PhoXi S having the intermediate performance (0.49 mm +/- 0.14 mm) and the Asus Xtion Pro Live obtaining the higher RMSE (1.01 mm +/- 0.11 mm). Considering the use case requirements, the final machine vision system relied on the SICK TriSpector1030 sensor and was integrated with a collaborative robot, which was successfully deployed in an vehicle assembly line, achieving 94% success in 53,400 screwing operations.

Abstract
Cities are complex and dynamic systems in which a network of actors interact, creating value through different activities. Cities can, therefore, be viewed as service ecosystems. Municipalities take advantage of digitalization to implement a service-dominant logic in urban and mobility planning and management, developing strategies with which citizens, local authorities, and other actors can create value together. While citizens are offered a better service experience, local authorities use citizens' input to improve decision-making processes. This research considers that designing an integrated service supported by an integrated information system can respond to current challenges in decision-making and information access for transport and mobility. Through a multidisciplinary methodological approach, this work proposes some guidelines to design an integrated information system to improve citizens' participation in urban planning and mobility services.

Abstract
Is there an initialization for deep networks that requires no learning? ExplainFix adopts two design principles: the fixed filters principle that all spatial filter weights of convolutional neural networks can be fixed at initialization and never learned, and the nimbleness principle that only few network parameters suffice. We contribute (a) visual model-based explanations, (b) speed and accuracy gains, and (c) novel tools for deep convolutional neural networks. ExplainFix gives key insights that spatially fixed networks should have a steered initialization, that spatial convolution layers tend to prioritize low frequencies, and that most network parameters are not necessary in spatially fixed models. ExplainFix models have up to x100 fewer spatial filter kernels than fully learned models and matching or improved accuracy. Our extensive empirical analysis confirms that ExplainFix guarantees nimbler models (train up to 17% faster with channel pruning), matching or improved predictive performance (spanning 13 distinct baseline models, four architectures and two medical image datasets), improved robustness to larger learning rate, and robustness to varying model size. We are first to demonstrate that all spatial filters in state-of-the-art convolutional deep networks can be fixed at initialization, not learned.This article is categorized under:Technologies > Machine LearningFundamental Concepts of Data and Knowledge > Explainable AIFundamental Concepts of Data and Knowledge > Key Design Issues in Data Mining

Abstract
This article examines the impact of digital influencers ' recommendations, especially Instagrammers, on the pur-chase intention of healthy food. In addition to the direct influence of source credibility on behavioral intention, the study also examines the influence of self-brand congruence and consumers' involvement with healthy food on purchase intention. To test research hypotheses, a quantitative study was conducted with 221 Portuguese con-sumers. High and low involvement with healthy food groups were classified by K-Means Clustering, and the analysis of the structure and the measurement models was performed by using Smart-PLS software. The results confirmed that Instagrammers' credibility drives self-brand congruence and purchase intention for healthy food. It was also confirmed that the involvement with healthy food moderates the influence of self-brand congruity and Instagrammers' credibility on consumers' intention to purchase healthy food, and that brand self-congruence partially mediates the influence of Instagrammers' credibility on purchase intention. Overall, this work offers rel-evant insights for both marketing managers and researchers, as it demonstrates the importance of considering the indirect effects of source credibility on purchase intention of healthy food and of comparing consumers with high and low product involvement to effectively evaluate the impact of digital influencers' in healthy food endorsement.