The emergence of dynamic, high-volume data streams demands advanced reasoning frameworks to capture complex spatio-temporal relationships that are essential for enabling contextual understanding. However, current approaches often lack scalable and adaptable semantic representations in dynamic and spatio-temporal scenarios. To answer this need, we introduce a novel Spatio-Temporal Knowledge approach based on Graph Neural Networks (STKGNN) for activity recognition. This framework performs graph-based reasoning over semantically enriched Spatio-Temporal Knowledge Graphs (STKGs) constructed from open-source video datasets. By leveraging these custom STKGs, we propose three advanced Graph Neural Network (GNN) based architectures to recognize various activities. Accordingly, we establish a comprehensive approach for spatio-temporal reasoning that adapts to diverse Knowledge Graph structures by addressing adaptability, scalability, and temporal complexities. This framework enhances activity recognition and provides a foundation for wider dynamic or real-time applications in different domains including healthcare, autonomous systems, video surveillance, and various other fields.

Real-time video streams present unique challenges for continual learning systems, demanding models that can incrementally update representations, preserve past knowledge, and reason over complex semantic relationships without sacrificing efficiency. In this paper, we introduce CAST-GNN, the first unified Graph Neural Network architecture expressly designed for continual adaptation on streaming Spatio-Temporal Knowledge Graphs (STKGs) derived from open-source video benchmarks. CAST-GNN integrates dynamic temporal embedding layers, adaptive self-attention, episodic graph pattern memory, and a novel hybrid selective replay buffer with Fisher-based regularization and knowledge distillation to mitigate catastrophic forgetting. Through comprehensive experiments on four diverse STKG benchmarks (UCF-101, HMDB-51, Kinetics-400, and SomethingSomething), our model achieves 96-97% accuracy, between 0.13-0.31 % forgetting, by consistently outperforming re-implemented continual-learning baselines under identical conditions. Ablation studies confirm the critical synergy between temporal embeddings and adaptive attention. We further demonstrate XAI-driven interpretability by aligning global distributional shifts with local node-level attributions. CAST-GNN not only advances robust semantic reasoning and knowledge retention but also provides a scalable, explainable framework applicable to a wide array of real-world streaming scenarios.

Abstract The rapid expansion of decentralized, complex streaming data across diverse domains such as the Internet of Things, healthcare, and smart cities presents significant technical challenges. These challenges–data heterogeneity (integration of diverse formats and sources), dynamicity (handling real-time data evolution), and high-volume throughput (efficient processing of large, rapidly arriving data)–are the central focus of this study and are examined in depth. To address these critical issues necessitates advanced methods capable of seamless integration, effective real-time reasoning, and continuous learning from heterogeneous streaming data, thus enhancing real-time decision-making capabilities. This study provides an extensive review of existing research at the intersection of streaming data, machine learning, and reasoning. The literature review categorizes Stream Reasoning approaches into three key groups: Streaming Machine Learning, Streaming Linked Data, and Streaming Knowledge Graphs. Each category is critically examined in terms of strengths, limitations, ongoing challenges, and future opportunities identified in recent studies. Additionally, potential integrative solutions that leverage Knowledge Graph structures and advanced Stream Reasoning techniques are highlighted, illustrating how state-of-the-art modeling methods can effectively address Stream Reasoning related challenges. The analysis concludes that combining Knowledge Graph and Machine Learning approaches significantly enhances the capability to manage and overcome complex Stream Reasoning challenges.

Personalized healthcare is nowadays driven by the increasing volumes of patient data, observed and produced continuously thanks to medical devices, mobile sensors, patient-reported outcomes, among other data sources. This data is made available as streams, due to their dynamic nature, which represents an important challenge for processing, querying and interpreting the incoming information. In addition, the sensitive nature of healthcare data poses significant restrictions regarding privacy, which has led to the emergence of decentralized personal data management systems. Data semantics play a key role in order to enable both decentralization and integration of personal health data, as they introduce the capability to represent knowledge and information using ontologies and semantic vocabularies. In this paper we describe the SemPryv system, which provides the means to manage personal health data streams enriched with semantic information. SemPryv is designed as a decentralized system, so that users have the possibility of hosting their personal data at different sites, while keeping control of access rights. The semantization of data in SemPryv is implemented through different strategies, ranging from rule-based annotation to machine learning-based suggestions, fed from third-party specialized healthcare metadata providers. The system has been made available as Open Source, and is integrated as part of the Pryv.io platform used and commercialized in the healthcare and personal data management industry.

Asynchronous messaging is leading human-machine interaction due to the boom of mobile devices and social networks. The recent release of dedicated APIs from messaging platforms boosted the development of computer programs able to conduct conversations, (i.e., chatbots), which have been adopted in several domain-specific contexts. This paper proposes SMAG: a chatbot framework supporting a smoking cessation program (JDF) deployed on a social network. In particular, it details the single-agent implementation, the campaign results, a multi-agent design for SMAG enabling the modelization of personalized behavior and user profiling, and highlighting of coupling chatbot technology with and multi-agent systems.

Electronic Data Capture (EDC) software solutions are progressively being adopted for conducting clinical trials and studies, carried out by biomedical, pharmaceutical and health-care research teams. In this paper we present the MedRed Ontology, whose goal is to represent the metadata of these studies, using well-established standards, and reusing related vocabularies to describe essential aspects, such as validation rules, composability, or provenance. The paper describes the design principles behind the ontology and how it relates to existing models and formats used in the industry. We also reuse well-known vocabularies and W3C recommendations. Furthermore, we have validated the ontology with existing clinical studies in the context of the MedRed project, as well as a collection of metadata of well-known studies. Finally, we have made the ontology available publicly following best practices and vocabulary sharing guidelines. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

The dramatic rise of time-series data produced in a variety of contexts, such as stock markets, mobile sensing, sensor networks, data centre monitoring, etc., has fuelled the development of large-scale distributed real-time computation systems (e.g., Apache Storm, Samza, Spark Streaming, S4, etc.). However, it is still unclear how certain time series mining tasks could be performed using such new emerging systems. In this paper, we focus on the task of efficiently discovering statistically significant correlations among a large number of time series via a distributed realtime computation engine. We propose a framework referred to as SigCO. In SigCO, we put forward a novel partition-aware data shuffling, which is able to adaptively shuffle time series data only to the relevant nodes of the distributed real-time computation engine. On the other hand, in SigCO we design a δ-hypercube structure based correlation computation approach which is capable of pruning unnecessary correlation computations. Finally, our extensive experimental evaluations on real and synthetic datasets establish that SigCO outperforms the baseline approaches in terms of diverse performance metrics.

RDF and SPARQL are established standards for data interchange and querying on the Web. While they have been shown to be useful and applicable in many scenarios, they are not sufficiently adequate for dealing with streams of data and their intrinsic continuous nature. In the last years data and query languages have been proposed to extend both RDF and SPARQL for streams and continuous processing, under the name of RDF Stream Processing – RSP. These efforts resulted in several models and implementations that, at a first look, appear to propose alternative syntaxes but equivalent semantics. However, when asked to continuously answer the same queries on the same data streams, they provide different answers at disparate moments due to the heterogeneity of their operational semantics. These discrepancies render the process of understanding and comparing continuous query results complex and misleading. In this work, the authors propose RSP-QL, a comprehensive model that formally defines the semantics of an RSP system. RSP-QL makes explicit the hidden assumptions of currently available RSP systems, allows defining a formal notion of correctness for RSP query results and, thus, explains why available implementations provide different answers at disparate moments.

Sensor networks are increasingly being deployed in the environment for many different purposes. The observations that they produce are made available with heterogeneous schemas, vocabularies and data formats, making it difficult to share and reuse this data, for other purposes than those for which they were originally set up. The authors propose an ontology-based approach for providing data access and query capabilities to streaming data sources, allowing users to express their needs at a conceptual level, independent of implementation and language-specific details. In this article, the authors describe the theoretical foundations and technologies that enable exposing semantically enriched sensor metadata, and querying sensor observations through SPARQL extensions, using query rewriting and data translation techniques according to mapping languages, and managing both pull and push delivery modes.