Abstract
Despite significant advances in web archive infrastructures, the problem of exploring the historical heritage preserved by web archives is yet to be solved. Timeline generation emerges in this context as one possible solution for automatically producing summaries of news over time. Thanks to this, users can gain a better sense of reported news events, entities, stories or topics over time, such as getting a summary of the most important news about a politician, an organisation or a locality. Web archives play an important role here by providing access to a historical set of preserved information. This particular characteristic of web archives makes them an irreplaceable infrastructure and a valuable source of knowledge that contributes to the process of timeline generation. Accordingly, the authors of this chapter developed "Tell me Stories" (), a news summarisation system, built on top of the infrastructure of Arquivo.pt-the Portuguese web-archive-to automatically generate a timeline summary of a given topic. In this chapter, we begin by providing a brief overview of the most relevant research conducted on the automatic generation of timelines for past-web events. Next, we describe the architecture and some use cases for "Tell me Stories". Our system demonstrates how web archives can be used as infrastructures to develop innovative services. We conclude this chapter by enumerating open challenges in this field and possible future directions in the general area of temporal summarisation in web archives. © Springer Nature Switzerland AG 2021. All rights reserved.

Abstract
Accurate monthly electricity consumption forecasting is indispensable for electricity retailers to mitigate trading risks in the electricity market. Clustering-based forecasting method are commonly used to generate accurate monthly electricity consumption forecasting results. This paper focuses on the problem that the existing clustering-based monthly electricity consumption forecasting methods perform clustering and forecasting independently, causing that the joint optimization of two steps cannot be achieved. The reason for this situation is that the target of current clustering algorithms, maximizing individual similarity in a group, is not consistent with the final target of improving the forecasting accuracy. To solve the above problem, the greedy clustering-based monthly electricity consumption forecasting model (GCMECF) is proposed in this paper. Its clustering step takes improving the overall predictability as the optimization target, which is closely related to the forecasting target. In this way, with matching targets, the joint optimization of clustering and forecasting can be achieved. Meanwhile, the selection of the optimal number of clusters is decided based on the forecasting performance under multiple clustering scenarios. The case study verifies the effectiveness and superiority of the proposed method via a realworld dataset.

Abstract
Geophysical techniques can be successfully applied towards the detection of buried explosive devices, the ground-penetrating radar (GPR) being an example of one such method. This technology works through emission and reception of electromagnetic radio waves being thus able to detect the presence of a subsurface object fundamentally due to reflections from contrasting electromagnetic properties between the object and the surrounding medium (e.g., soil). Many factors can influence the success of a GPR survey (e.g., target type, soil type, environmental conditions, GPR antenna frequency, data processing techniques), being essential to know and understand their likely effects before performing GPR studies, mainly in real cases. In this paper, through the analysis of case studies related to the use of GPR technology towards the detection of buried explosive devices, we intend to arrange and layout the main prior knowledge that a forensic geophysical expert must have when dealing with this type of fieldwork.

Abstract
Collaboration between companies in transportation problems seeks to reduce empty running of vehicles and to increase the use of vehicles' capacity. Motivated by a case study in the food supply chain, this paper examines a lateral collaboration between a leading retailer (LR), a third party logistics provider (3 PL) and different producers. Three collaborative strategies may be implemented simultaneously, namely pickup-delivery, collection and cross-docking. The collaborative pickup-delivery allows an entity to serve customers of another in the backhaul trips of the vehicles. The collaborative collection allows loads to be picked up at the producers in the backhauling routes of the LR and the 3 PL, instead of the traditional outsourcing. The collaborative cross-docking allows the producers to cross-dock their cargo at the depot of another entity, which is then consolidated and shipped with other loads, either in linehaul or backhaul routes. The collaborative problem is formulated with three different objective functions: minimizing total operational costs, minimizing total fuel consumption and minimizing operational and CO2 emissions costs. The synergy value of collaborative solutions is assessed in terms of costs and environmental impact. Three proportional allocation methods from the literature are used to distribute the collaborative gains among the entities, and their limitations and capabilities to attend fairness criteria are analyzed. Collaboration is able to reduce the global fuel consumption in 26% and the global operational costs in 28%, independently of the objective function used to model the problem. The collaborative pickup-delivery strategy outperforms the other two in the majority of instances under different objectives and parameter settings. The collaborative collection is favoured when the ordering loads from producers increase. The collaborative cross-docking tends to be implemented when the producers are located close to the depot of the 3 PL.

Abstract
Crowdsourced data streams are continuous flows of data generated at high rate by users, also known as the crowd. These data streams are popular and extremely valuable in several domains. This is the case of tourism, where crowdsourcing platforms rely on tourist and business inputs to provide tailored recommendations to future tourists in real time. The continuous, open and non-curated nature of the crowd-originated data requires robust data stream mining techniques for on-line profiling, recommendation and evaluation. The sought techniques need, not only, to continuously improve profiles and learn models, but also be transparent, overcome biases, prioritise preferences, and master huge data volumes; all in real time. This article surveys the state-of-art in this field, and identifies future research opportunities.

Abstract
Over the past decades, the use of digital technologies to support participatory urban planning and design has been repeatedly described as a crucial instrument and critical building block for tackling historical problems of participation in such processes. Social media, e-participation platforms, and crowdsourcing applications are examples of technologies that can involve citizens in decision-making processes and thus leverage the benefits of collective intelligence. However, despite the extensive use of social media platforms, old problems related to engagement and participation still occur in digital initiatives. Successful collaboration examples between citizens, policymakers, and strategic stakeholders are still scarce based on online social practices. This study aims to introduce a collective intelligence model, which combines crowdsourcing and social storytelling to support participatory urban planning and design from a bottom-up perspective. The paper concludes by discussing a scenario where citizens can engage in mapping, taking photos, sending ideas, or even creating collective stories about their university issues in a post-pandemic future.