Citizen safety in modern urban environments is an important aspect of life quality. Implementation of a smart city approach to video surveillance depends heavily on the capability of gathering and processing huge amounts of live urban data. Analyzing data from high bandwidth surveillance video streams provided by large size distributed sensor networks is particularly challenging. We propose here an efficient method for automatic violent behavior detection designed for video sensor networks. Known solutions to real-time violence detection are not suitable for implementation in a resource-constrained environment due to the high processing power requirements. Our algorithm achieves real-time processing on a Raspberry PI-embedded architecture. To ensure separation of temporal and spatial information processing we employ a computationally effective cascaded approach. It consists of a deep neural network followed by a time domain classifier. In contrast with current approaches, the deep neural network input is fed exclusively with motion vector features extracted directly from the MPEG encoded video stream. As proven by results, we achieve state-of-the-art performance, while running on a low computational resources embedded architecture.

Despite the ideal of a unified Single Market, a powerful “home bias” pervades EU public procurement, hinting at unseen barriers that conventional analysis fails to capture. This study introduces an interpretable AI framework to investigate these dynamics, pairing a LightGBM model with SHapley Additive exPlanations (SHAP) to examine the vast Tenders Electronic Daily (TED) database (2018–2023). Concretely, we propose a fuzzy linguistic layer that translates SHAP’s complex quantitative outputs into intuitive, human-readable terms. Our model effectively distinguishes local from non-local awards (AUC ≈ 0.855), revealing that while high-value contracts expectedly attract broader competition, the most potent predictors are a country’s own history of local awards and structural factors like the buyer’s type and location. This points not to isolated incidents, but, rather, to deep-seated patterns shaping market fairness. Our combined XAI-Fuzzy approach offers a new instrument for transparent governance, enabling policymakers to diagnose market realities and forge a more genuinely open and equitable European public square.

Traffic congestion and queues made by cars, are now part of our everyday life. Congestion levels have increased significantly in recent years, and this trend continues. Making correct decisions in congestion management is a difficult thing, because the decision factors need to analyze and absorb a large amount of information, which often are not relevant. In this paper, we propose a regression model to determine the quality factor used in road traffic. The model is defined starting from an experimental study aimed at analyzing the traffic quality in an urban network. This study represents a continuation of previous work [3], in which the authors proposed a new analytical model to determine the quality factor used in transport network (QF). The quality factor is measure used to characterize the global traffic in the intersection, but also to optimize traffic in a structure of interconnected intersections. This concept QF allows the use of the classical models of queuing theory to represent the road traffic. The experimental study was initiated in an area of urban transport network. Using the characteristics of the network topology we determined the value of quality factor for each connection represented in the studied network. With this study, we obtained information about the level of traffic congestion (utilization level), we could estimate the waiting time (in a queue) and response time (the elapsed time between the moment a traffic participant initiates an action and the time when he/she is allowed to execute the action).

The last years have seen major transformation in all segments of the power industry, from power generation to energy supply, smart meters having a key role. Smart energy meters are used also in smart homes solutions. Non-intrusive load monitoring using smart meters can be used to disaggregate energy consumption of home appliances. In our work we aim to estimate energy consumption and power profile of the internal components of an electrical device using the electrical energy signature of the running device. Furthermore, we try to determine the operation mode of the device under analysis based on the differences between power consumption signatures.

Key field information extraction from documents is an increasingly covetable task. Previous related work has touched upon the subject through the lens of rule-based systems or through natural language processing methods. In this paper we see the task of information extraction from invoices as an object detection task. To this end, we used three different models YOLOv5, Scaled YOLOv4 and Faster R-CNN to detect key field information in invoices. Additionally, we propose a data preprocessing method that helps to better generalize the learning. All of the experiments were performed on a custom made dataset with a very high variety of invoice layouts. This decision comes in part from the lack of any suitable public dataset and from the need of finding the best procedure for annotating data pertaining to this task. The obtained results were encouraging, leading us to the conclusion that object detection is a viable method for information extraction.

For decades, Computer Vision has aimed at enabling machines to perceive the external world. Initial limitations led to the development of highly specialized niches. As success in each task accrued and research progressed, increasingly complex perception tasks emerged. This survey charts the convergence of these tasks and, in doing so, introduces Open World Detection (OWD), an umbrella term we propose to unify class-agnostic and generally applicable detection models in the vision domain. We start from the history of foundational vision subdomains and cover key concepts, methodologies and datasets making up today's state-of-the-art landscape. This traverses topics starting from early saliency detection, foreground/background separation, out of distribution detection and leading up to open world object detection, zero-shot detection and Vision Large Language Models (VLLMs). We explore the overlap between these subdomains, their increasing convergence, and their potential to unify into a singular domain in the future, perception.