Wind energy plays a pivotal role in the global shift toward sustainable energy systems. However, the maintenance of wind turbines remains a significant challenge due to their distributed nature, harsh environmental exposure, and the high cost of unplanned downtime. In this work, a novel architecture for predictive maintenance of wind turbines based on continuous acoustic monitoring is presented, based upon OASEES—a decentralized, intelligent, and programmable edge framework that spans the full computing continuum. The proposed system leverages low-cost recording equipment to capture turbine-generated sound data, which are processed locally at the edge using Federated Learning, thus preserving data privacy and reducing communication overhead. A pre-trained deep learning model based on wav2vec is fine-tuned to classify turbine operational states, using labeled acoustic datasets. The effectiveness of the architecture, which, to the best of the authors' knowledge, is among the first to utilize the said distributed learning paradigm for acoustic-based wind turbine predictive maintenance, is validated in a proof-of-concept experimental setting using a publicly available relevant dataset, where both centralized and federated training methods are evaluated. The results demonstrate promising classification accuracy, with the federated model achieving over 78 % accuracy, closely matching the centralized baseline.

Unmanned Aerial Vehicles (UAVs) are increasingly deployed in inspection and monitoring missions, yet onboard computation and communication impose significant energy burdens that limit flight time and operational scope. In this work, we introduce a novel, blockchain-enabled framework-grounded in the Distributed Autonomous Organization (DAO) paradigm-for orchestrating distributed analytics across a swarm of UAVs. Leveraging the OASEES project's smart-contract architecture, each drone embeds a Metrics Module for real-time power monitoring, a Behavioral Module for adaptive control, and a Blockchain Agent that autonomously proposes, votes on, and executes collective decisions. Three concurrent threads-Proposal Trigger, Voting, and Action Execution-enable fully decentralized governance of swarm behavior: from detecting critical energy thresholds and formulating swarm-wide conservation maneuvers, to executing approved strategies across all members. We validate our framework in a UAV-based infrastructure inspection scenario, employing a YOLOv5 object-detection pipeline to classify four corrosion classes on a telecommunications mast under three video-capture modalities (short-distance, long-distance, and horizontally concatenated streams). Across all configurations, our system achieves near-perfect precision, recall, and mean Average Precision (mAP50-95$\approx 0.995$), demonstrating both the efficacy of distributed workload inference and the feasibility of treating a single drone as a multi-feed processor. These results underscore the potential of DAO-driven UAV swarms for energy-aware, resilient aerial analytics, and pave the way for fully decentralized 5G/6G-enabled airborne networks.

We present a novel self-supervised approach for representation learning, particularly for the task of Visual Relationship Detection (VRD). Motivated by the effectiveness of Masked Image Modeling (MIM), we propose Masked Bounding Box Reconstruction (MBBR), a variation of MIM where a percentage of the entities/objects within a scene are masked and subsequently reconstructed based on the unmasked objects. The core idea is that, through object-level masked modeling, the network learns context-aware representations that capture the interaction of objects within a scene and thus are highly predictive of visual object relationships. We extensively evaluate learned representations, both qualitatively and quantitatively, in a few-shot setting and demonstrate the efficacy of MBBR for learning robust visual representations, particularly tailored for VRD. The proposed method is able to surpass state-of-the-art VRD methods on the Predicate Detection (PredDet) evaluation setting, using only a few annotated samples. We make our code available at https://github.com/deeplabai/SelfSupervisedVRD.

Parkinson’s Disease is the second most prevalent neurodegenerative disorder, currently affecting as high as 3% of the global population. Research suggests that up to 80% of patients manifest phonatory symptoms as early signs of the disease. In this respect, various systems have been developed that identify high risk patients by analyzing their speech using recordings obtained from natural dialogues and reading tasks conducted in clinical settings. However, most of them are centralized models, where training and inference take place on a single machine, raising concerns about data privacy and scalability. To address these issues, the current study migrates an existing, state-of-the-art centralized approach to the concept of federated learning, where the model is trained in multiple independent sessions on different machines, each with its own dataset. Therefore, the main objective is to establish a proof of concept for federated learning in this domain, demonstrating its effectiveness and viability. Moreover, the study aims to overcome challenges associated with centralized machine learning models while promoting collaborative and privacy-preserving model training.

As Monte Carlo Tree Search has been established as one of the most promising algorithms in the field of Game AI, several approaches have been proposed in an attempt to exploit as much information as possible during the tree search, most important of which include Rapid Action Value Estimation and its variants. These techniques estimate for each action in a node an additional value (AMAF), based on statistics of all simulations where the action was selected deeper in the search tree. In this study, a methodology for determining the most suitable node for using its AMAF scores during the selection phase is presented. Two different approaches are proposed under the scope of discovering similar nodes’ states based on the actions selected towards their paths; in the first one, N-grams are employed to detect similar paths, while in the second one a vectorized representation of the actions taken is used. The suggested algorithms are tested in the context of general game playing achieving quite satisfactory results in terms of both win rate and overall score.

Abstract Nowadays, most research conducted in the field of abstractive text summarization focuses on neural-based models alone, without considering their combination with knowledge-based approaches that could further enhance their efficiency. In this direction, this work presents a novel framework that combines sequence-to-sequence neural-based text summarization along with structure and semantic-based methodologies. The proposed framework is capable of dealing with the problem of out-of-vocabulary or rare words, improving the performance of the deep learning models. The overall methodology is based on a well-defined theoretical model of knowledge-based content generalization and deep learning predictions for generating abstractive summaries. The framework is composed of three key elements: (i) a pre-processing task, (ii) a machine learning methodology, and (iii) a post-processing task. The pre-processing task is a knowledge-based approach, based on ontological knowledge resources, word sense disambiguation, and named entity recognition, along with content generalization, that transforms ordinary text into a generalized form. A deep learning model of attentive encoder-decoder architecture, which is expanded to enable a coping and coverage mechanism, as well as reinforcement learning and transformer-based architectures, is trained on a generalized version of text-summary pairs, learning to predict summaries in a generalized form. The post-processing task utilizes knowledge resources, word embeddings, word sense disambiguation, and heuristic algorithms based on text similarity methods in order to transform the generalized version of a predicted summary to a final, human-readable form. An extensive experimental procedure on three popular data sets evaluates key aspects of the proposed framework, while the obtained results exhibit promising performance, validating the robustness of the proposed approach.

The task of sentiment analysis tries to predict the affective state of a document by examining its content and metadata through the application of machine learning techniques. Recent advances in the field consider sentiment to be a multi-dimensional quantity that pertains to different interpretations (or aspects), rather than a single one. Based on earlier research, the current work examines the said task in the framework of a larger architecture that crawls documents from various online sources. Subsequently, the collected data are pre-processed, in order to extract useful features that assist the machine learning algorithms in the sentiment analysis task. More specifically, the words that comprise each text are mapped to a neural embedding space and are provided to a hybrid, bi-directional long short-term memory network, coupled with convolutional layers and an attention mechanism that outputs the final textual features. Additionally, a number of document metadata are extracted, including the number of a document's repetitions in the collected corpus (i.e. number of reposts/retweets), the frequency and type of emoji ideograms and the presence of keywords, either extracted automatically or assigned manually, in the form of hashtags. The novelty of the proposed approach lies in the semantic annotation of the retrieved keywords, since an ontology-based knowledge management system is queried, with the purpose of retrieving the classes the aforementioned keywords belong to. Finally, all features are provided to a fully connected, multi-layered, feed-forward artificial neural network that performs the analysis task. The overall architecture is compared, on a manually collected corpus of documents, with two other state-of-the-art approaches, achieving optimal results in identifying negative sentiment, which is of particular interest to certain parties (like for example, companies) that are interested in measuring their online reputation.

Collectible card games are an interesting testing ground for artificial intelligence algorithms, mainly because of their stochasticity and high branching factor. In this work, the performance of a monte carlo tree search-based agent, enhanced with a gradient boosting tree classifier on the simulation phase, is investigated on Hearthstone. Furthermore, the impact of the combination of random simulations and the classifier's predictions is studied, as well as its correlation with the action space and the tree's depth. The aforementioned approach has been implemented in the Metastone framework and has been tested against the vanilla approach and the state-of-the-art algorithm, both provided by the framework itself. Over a set of evaluation games, it is demonstrated that the examined methodology significantly outperforms the vanilla-MCTS and is even matched with the heuristic-driven minimax algorithm.

This work proposes a novel framework for enhancing abstractive text summarization based on the combination of deep learning techniques along with semantic data transformations.Initially, a theoretical model for semantic-based text generalization is introduced and used in conjunction with a deep encoder-decoder architecture in order to produce a summary in generalized form.Subsequently, a methodology is proposed which transforms the aforementioned generalized summary into human-readable form, retaining at the same time important informational aspects of the original text and addressing the problem of out-of-vocabulary or rare words.The overall approach is evaluated on two popular datasets with encouraging results.

Integrated spiral inductors are a fundamental part of Radio-Frequency (RF) circuits. In certain scenarios, a solution to the inverse spiral inductor design problem is required; given the desired properties of an inductor, locate the most suitable geometric characteristics. This problem does not have a unique solution and current approaches approximate it through a number of differential equations and the subsequent application of optimization techniques that narrow down the set of feasible solutions. In this work, the Neural Network Specialists model is outlined; a preliminary approach to solving the aforementioned problem using fully connected neural network models. The obtained results on a first round of experiments are encouraging, especially in terms of the reduction in time complexity.

In this paper, we focus on Recommender Systems that are enhanced with social information in the form of trust statements between their users. The trust information may be processed in a number of ways, including the random walks in the Social Graph, where every step in the walk is chosen almost uniformly at random from the available choices. Even though this strategy yields satisfactory results, it still does not fully exploit the similarity information among users and items. Our work tries to model user-to-user and user-to-item relation as a probability distribution using a novel approach based on Rejection Sampling in order to decide on its next step (biased random walk). Some initial results on reference datasets reveal the potential of this idea.