Abstract
Port authorities have the need to manage diverse information within the port area under its responsibility regarding their land and sea infrastructures. Through this innovation, which adds value to the port and its activity, it is made an interconnection of strategic areas, with the provision and sharing of structured data in a georeferenced environment. This work presents an innovative platform, based on various modules and allows effective control and efficient management of operations, processes and requirements associated with any sea port. The developed modules are designed to support the activities of business processes in the following areas of the port administration: Heritage, Hydrography, Port Traffic, Dominial, Studies and Works, Safety and Environment. Most of these modules were pioneers in the integration with business process management of portuguese ports of Leixoes and Viana do Castelo.

Abstract
SDIs allow the gathering of technical and organizational elements needed to enable the usage of territorial based information in an interoperable way. However, the cost of managing an SDI is high and the expertise level required is too specialized which, combined, hamper its maintenance and operation. This work, still in progress, presents a proposal for a manager for a regional level SDI, free software based, following the European INSPIRE (Infrastructure for Spatial Information in the European Community) directive principles and complying with OGC (Open Geospatial Consortium) standards. This CMS (Content Management System) for the SDI will shield the user from the inherent complexity and ease the creation of innovative services and the integration of cross-sectorial applications for a given region, using the geographic information generated by each municipality, as well as provide data for sibling SDIs (inter regional) and parent SDIs (supra regional).

Abstract

Abstract
The complexity of the number of stakeholders, information systems used, and port operations evoke new challenges to port security when it comes to the total knowledge and control of the overall operations of transport and parking of containerized freight, namely hazmat ones. The rising interest and the port authorities' awareness of the relevance of security concerns involved in this complex ecosystem has led to the search for new technological solutions that allow, in an integrated manner, the smart and automatic control of operations of transport and hazardous freight parking in all the areas of its jurisdiction, without third-party dependencies. Despite its importance and criticality, port authorities tend to have limited real-time knowledge of the location of hazmat containers, whether moving within the port (entering and leaving), or in its parking, having a direct impact on the port security. This article presents a Digital Twin platform for 3D and real-time georeferenced visualization of container parks and the location of hazardous containerized freight. This tool combines different modules that further allow to visualize information associated to a container, its movement, as well as its surrounding area, including a realistic and dynamic 3D representation of what is the area encircling the port.

Abstract
Climate change is causing the emergence of new pest species and diseases, threatening economies, public health, and food security. In Europe, olive groves are crucial for producing olive oil and table olives; however, the presence of the olive fruit fly (Bactrocera Oleae) poses a significant threat, causing crop losses and financial hardship. Early disease and pest detection methods are crucial for addressing this issue. This work presents a pioneering comparative performance study between two state-of-the-art object detection models, YOLOv5 and YOLOv8, for the detection of the olive fruit fly from trap images, marking the first-ever application of these models in this context. The dataset was obtained by merging two existing datasets: the DIRT dataset, collected in Greece, and the CIMO-IPB dataset, collected in Portugal. To increase its diversity and size, the dataset was augmented, and then both models were fine-tuned. A set of metrics were calculated, to assess both models performance. Early detection techniques like these can be incorporated in electronic traps, to effectively safeguard crops from the adverse impacts caused by climate change, ultimately ensuring food security and sustainable agriculture. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

Abstract
Several systems that employ machine learning models are subject to strict latency requirements. Fraud detection systems, transportation control systems, network traffic analysis and footwear manufacturing processes are a few examples. These requirements are imposed at inference time, when the model is queried. However, it is not trivial how to adjust model architecture and hyperparameters in order to obtain a good trade-off between predictive ability and inference time. This paper provides a contribution in this direction by presenting a study of how different architectural and hyperparameter choices affect the inference time of a Convolutional Neural Network for network traffic analysis. Our case study focus on a model for traffic correlation attacks to the Tor network, that requires the correlation of a large volume of network flows in a short amount of time. Our findings suggest that hyperparameters related to convolution operations-such as stride, and the number of filters-and the reduction of convolution and max-pooling layers can substantially reduce inference time, often with a relatively small cost in predictive performance.