Abstract
The manipulation of deformable objects poses a significant challenge for the automotive industry. In particular, the assembly of flexible cables and wire-harnesses in vehicles is still performed manually as there is yet to be a reliable and general solution for this problem. This paper presents a simple yet efficient motion planning algorithm to mount a flexible wire in an assembly jig, where the wire must traverse a set of forks in order. The algorithm uses a heuristic based on a set of control points to guide the wire's movement. Various controlled assembly scenarios are built in simulation using MuJoCo, a physics engine that can emulate the dynamics of Deformable Linear Objects (DLO). Experimental results in simulation demonstrated that the amount and orientation of the forks has a large impact in the solution's performance and highlighted several key ideas and challenges moving forward. Thus, this work serves as a stepping stone towards the development of more complete solutions, capable of assembling flexible items in vehicles.

Abstract
Virtual reality (VR) has the potential to significantly boost productivity in professional settings, especially those that can benefit from immersive environments that allow a better and more thorough way of visualizing information. However, the physical demands of mid-air movements make it difficult to use VR for extended periods. DeskVR offers a solution that allows users to engage in VR while seated at a desk, minimizing physical exhaustion. However, developing appropriate motion techniques for this context is challenging due to limited mobility and space constraints. This work focuses on object manipulation techniques, exploring touch-based and mid-air-based approaches to design a suitable solution for DeskVR, hypothesizing that touch-based object manipulation techniques could be as effective as mid-air object manipulation in a DeskVR scenario while less physically demanding. Thus, we propose Scaled Indirect Touch 6-DOF (SIT6), an indirect touch-based object manipulation technique incorporating scaled input mapping to address precision and out-of-reach manipulation issues. The implementation of our solution consists of a state machine with error-handling mechanisms and visual indicators to enhance interaction. User experiments were conducted to compare the SIT6 technique with a baseline mid-air approach, revealing comparable effectiveness while demanding less physical exertion. These results validated our hypothesis and established SIT6 as a viable option for object manipulation in DeskVR scenarios. (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

Abstract
Physical models and probabilistic applications often guide the study and characterization of natural phenomena in engineering. Such is the case of the study of air change rates (ACHs) in buildings for their complex mechanisms and high variability. It is not uncommon for the referred applications to be costly and impractical in both time and computation, resulting in the use of simplified methodologies and setups. The incorporation of airtightness limits to quantify adequate ACHs in national transpositions of the Energy Performance Building Directive (EPBD) exemplifies the issue. This research presents a roadmap for developing an alternative instrument, a compliance tool built with a Machine Learning (ML) framework, that overcomes some simplification issues regarding policy implementation while fulfilling practitioners' needs and general societal use. It relies on dwellings' terrain, geometric and airtightness characteristics, and meteorological data. Results from previous work on a region with a mild heating season in southern Europe apply in training and testing the proposed tool. The tool outputs numerical information on the air change rates performance of the building envelope, and a label, accordingly. On the test set, the best regressor showed mean absolute errors (MAE) below 1.02% for all the response variables, while the best classifier presented an average accuracy of 97.32%. These results are promising for the generalization of this methodology, with potential for application at regional, national, and European Union levels. The developed tool could be a complementary asset to energy certification programmes of either public or private initiatives. (c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Abstract
The size of massive knowledge graphs (KGs) and the lack of prior information regarding the schemas, ontologies and vocabularies they use frequently makes them hard to understand and visualize. Graph summarization techniques can help by abstracting details of the original graph to produce a reduced summary that can more easily be explored. Identifiers often carry latent information which could be used for classification of the entities they represent. Particularly, IRI namespaces can be used to classify RDF resources. Namespaces, used in some RDF serialization formats as a shortening mechanism for resource IRIs, have no role in the semantics of RDF. Nevertheless, there is often a hidden meaning behind the decision of grouping resources under a common prefix and assigning an alias to it. We improved on previous work on a namespace-based approach to KG summarization that classifies resources using their namespaces. Producing the summary graph is fast, light on computing resources and requires no previous domain knowledge. The summary graph can be used to analyze the namespace interdependencies of the original graph. We also present chilon, a tool for calculating namespace-based KG summaries. Namespaces are gathered from explicit declarations in the graph serialization, community contributions or resource IRI prefix analysis. We applied chilon to publicly available KGs, used it to generate interactive visualizations of the summaries, and discuss the results obtained.

Abstract
Sales forecasts are an important tool for inventory management, allowing retailers to balance inventory levels with customer demand and market conditions. By using sales forecasts to inform inventory management decisions, companies can optimize their inventory levels and avoid costly stockouts or excess inventory costs. The scale of the forecasting problem in the retail domain is significant and requires ongoing attention and resources to ensure accurate and effective forecasting. Recent advances in machine learning algorithms such as deep learning have made possible to build more sophisticated forecasting models that can learn from large amounts of data. These global models can capture complex patterns and relationships in the data and predict demand across multiple regions and product categories. In this paper, we investigate the cross-learning scenarios, inspired by the product hierarchy frequently utilized in retail planning, which enable global models to better capture interdependencies between different products and regions. Our empirical results obtained using M5 competition dataset indicate that the cross-learning approaches exhibit significantly superior performance compared to local forecasting benchmarks. Our findings also suggest that using partial pooling at the lowest aggregation level of the retail hierarchical allows for a more effective capture of the distinct characteristics of each group.

Abstract