Abstract
Since digital media has become increasingly popular, video processing has expanded in recent years. Video processing systems require high levels of processing, which is one of the challenges in this field. Various approaches, such as hardware upgrades, algorithmic optimizations, and removing unnecessary information, have been suggested to solve this problem. This study proposes a video saliency map based method that identifies the critical parts of the video and improves the system's overall performance. Using an image registration algorithm, the proposed method first removes the camera's motion. Subsequently, each video frame's color, edge, and gradient information are used to obtain a spatial saliency map. Combining spatial saliency with motion information derived from optical flow and color-based segmentation can produce a saliency map containing both motion and spatial data. A nonlinear function is suggested to properly combine the temporal and spatial saliency maps, which was optimized using a multi-objective genetic algorithm. The proposed saliency map method was added as a preprocessing step in several Human Action Recognition (HAR) systems based on deep learning, and its performance was evaluated. Furthermore, the proposed method was compared with similar methods based on saliency maps, and the superiority of the proposed method was confirmed. The results show that the proposed method can improve HAR efficiency by up to 6.5% relative to HAR methods with no preprocessing step and 3.9% compared to the HAR method containing a temporal saliency map.

Abstract
In recent years, social media platforms have become an essential source of information. Therefore, with their increasing popularity, there is a growing need for effective methods for detecting and analyzing their content in real time. Deep learning is a machine learning technique that teaches computers to understand complex patterns. Deep learning techniques are promising for analyzing acoustic signals from social media posts. In this article, a novel deep learning approach is proposed for socially contextualized event detection based on acoustic signals. The approach integrates the power of deep learning and meaningful features such as Mel frequency cepstral coefficients. To evaluate the effectiveness of the proposed method, it was applied to a real dataset collected from social protests in Iran. The results show that the proposed system can find a protester's clip with an accuracy of approximately 82.57%. Thus, the proposed approach has the potential to significantly improve the accuracy of systems for filtering social media posts.

Abstract
This paper describes the project based learning experience of a multidisciplinary and multicultural team of students enrolled in the spring of 2023 on the European Project Semester at the Instituto Superior de Engenharia do Porto (EPS@ISEP). Animo is an original blimp based concept that aims to help farmers better manage their livestock. Its development was motivated by the difficulty to effectively monitor cattle herds over vast areas, especially in remote locations where locating animals is challenging. This environmentally friendly solution offers real-time livestock monitoring without thermal engines. Real-time monitoring is achieved through the blimp’s extensive animal data collection. Farmers may discover and handle quickly herd welfare issues by accessing information via a user-friendly App. With an emphasis on accessibility and environmental sustainability, Animo seeks to increase agricultural productivity and profitability. The user controls the blimp motion through the app to obtain a comprehensive farm view. Targeting Australia’s large cattle stations, it aims to enhance productivity while minimising the environmental impact. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Abstract
Sensing at the single cell level can provide insights into its dynamics and heterogeneity, yielding information otherwise unattainable with traditional biological methods where average population behavior is observed. In this context, optical tweezers provide the ability to select, separate, manipulate and identify single cells or other types of microparticles, potentially enabling single cell diagnostics. Forward or backscatter analysis of the light interacting with the trapped cells can provide valuable insights on the cell optical, geometrical and mechanical properties. In particular, the combination of tweezers systems with advanced machine learning algorithms can enable single cell identification capabilities. However, typical processing pipelines require a training stage which often struggles when trying to generalize to new sets of data. In this context, fully automated tweezers system can provide mechanisms to obtain much larger datasets with minimum effort form the users, while eliminating procedural variability. In this work, a pipeline for full automation of optical tweezers systems is discussed. A performance comparison between manually operated and fully automated tweezers systems is presented, clearly showing advantages of the latter. A case study demonstrating the ability of the system to discriminate molecular binding events on microparticles is presented.

Abstract
Energy smart grids and other modern industrial control systems networks impose considerable security management challenges due to several factors: their broad geographic dispersion and capillarity, the constrained nature of many of the devices and network links that integrate them, and the fact that they are often fragmented across multiple domains, owned and managed by different entities which often have non-aligned or even competing interests. Due to this scenario, we propose to improve federated learning-based anomaly detection for smart grids and other industrial control networks, using a federated data-centric methodology that attends to the balance and causality of the data, improving the representation of the different classes of anomalies of the ingested data, which directly impact the classifier's performance. The proposed approach shows up to 33% performance improvements in terms of F1-score for attack classification, compared to the baseline federated approach (not attending to class imbalance and causality) on a broad range of industrial control systems traffic datasets.

Abstract
This study estimates alighting stops and transfers from entry-only Automatic Fare Collection (AFC) data. The methodology adopted includes two main steps: an implementation of the Trip Chaining Method (TCM) to estimate the alighting stops from AFC records and the subsequent application of criteria for the identification of transfers. For each pair of consecutive AFC records on the same smart card, a transfer is identified considering a threshold for the walking distance, a threshold for the time required to perform an activity, and the validation of different boarding routes. This methodology was applied to the case study of Porto, Portugal, considering all trips performed by a set of 19999 smart cards over one year. The results of this methodology allied with visualization techniques allowed to study Origin-Destination (OD) patterns by type of day, seasonally, and by user frequency, each analyzed at the stop level and at the geographic area level.