Abstract
We propose a pixel color amplification theory and family of enhancement methods to facilitate segmentation tasks on retinal images. Our novel re-interpretation of the image distortion model underlying dehazing theory shows how three existing priors commonly used by the dehazing community and a novel fourth prior are related. We utilize the theory to develop a family of enhancement methods for retinal images, including novel methods for whole image brightening and darkening. We show a novel derivation of the Unsharp Masking algorithm. We evaluate the enhancement methods as a pre-processing step to a challenging multi-task segmentation problem and show large increases in performance on all tasks, with Dice score increases over a no-enhancement baseline by as much as 0.491. We provide evidence that our enhancement preprocessing is useful for unbalanced and difficult data. We show that the enhancements can perform class balancing by composing them together. © Springer Nature Switzerland AG 2020.

Abstract
Purpose To study how supply chain decision makers gather, process and use the available internal and external information when facing supply chain disruptions. Design/methodology/approach The paper reviews relevant supply chain literature to build an information management model for disruption management. Afterwards, three case studies in the vehicle assembly sector, namely cars, trucks and aircraft wings, bring the empirical insights to the information management model. Findings This research characterises the phases of disruption management and identifies the information companies use to recover from a variety of disruptive events. It presents an information management model to enhance supply chain visibility and support disruption management at the operational level. Moreover, it arrives at two design propositions to help companies in the redesign of their disruption discovery and recovery processes. Originality/value This research studies how companies manage operational disruptions. The proposed information management model allows to provide visibility to support the disruption management process. Also, based on the analysis of the disruptions occurring at the operational level we propose a conceptual model to support decision makers in the recovery from daily disruptive events.

Abstract
Investigating strategies that are able to efficiently deal with multi-label classification tasks is a current research topic in machine learning. Many methods have been proposed, making the selection of the most suitable strategy a challenging issue. From this premise, this paper presents an extensive empirical analysis of the binary transformation strategies and base algorithms for multi-label learning. This subset of strategies uses the one-versus-all approach to transform the original data, generating one binary data set per label, upon which any binary base algorithm can be applied. Considering that the influence of the base algorithm on the predictive performance obtained by the strategies has not been considered in depth by many empirical studies, we investigated the influence of distinct base algorithms on the performance of several strategies. Thus, this study covers a family of multi-label strategies using a diversified range of base algorithms, exploring their relationship over different perspectives. This finding has significant implications concerning the methodology of evaluation adopted in multi-label experiments containing binary transformation strategies, given that multiple base algorithms should be considered. Despite these improvements in strategy and base algorithms, for many data sets, a large number of labels, mainly those less frequent, were either never predicted, or always misclassified. We conclude the experimental analysis by recommending strategies and base algorithms in accordance with different performance criteria.

Abstract

Abstract
The smart cities concept - use of connected services and intelligent systems to support decision making in cities governance - aims to build better sustainability and living conditions for urban spaces, which are more complex every day. This work expects to optimize the waste collection circuits for non-residential customers in a city in Portugal. It is developed through the implementation of a simple, low-cost methodology when compared to commercial-available sensor systems. The main goal is to build a classifier for each client, being able to forecast the presence or absence of containers and, in a second step, predict how many containers of glass, paper or plastic would be available to be collected. Data were acquired during the period of one year, from January to December 2017, from more than 100 customers, resulting in a 26.000+ records dataset. Due to its degree of interpretability, we use Decision trees, implemented with a sliding window, which ran through the months of the year, stacking it one-by-one and/or merging few groups aiming the best correct predictions score. This project results in more efficient waste-collection routes, increasing the operation profits and reducing both costs and fuel-consumption, therefore diminishing it environmental footprint.

Abstract
Civil society, business, and local authorities in Portugal have come together to seek solutions to the challenges posed by COVID-19. This study intends to explore the relevance of these initiatives for the implementation of the Human2Human paradigm through five case studies. This approach allows us to understand how these initiatives are organized, to identify the convergent and divergent points between them, and to explore the role of information and communication technologies in these projects. The results of this study enabled the identification of a set of diversified projects with high impact for professionals who are in the front line in the fight against COVID-19 and for the most vulnerable population, particularly the elderly. This study is especially relevant from a practical point of view by exploring the relevance of these initiatives, by highlighting the need for collaborative work and in multidisciplinary teams, and by encouraging their replication to other countries.