This study leverages high-quality data from soccer matches to derive a better understanding of the elements contributing to a team's success. Initially, we classically analyzed extensive soccer logs from major European leagues and international tournaments. We have defined a team's technical performance through a vector of features, including goalkeeping, intercepts, tackles, dribbles, and more. The objective of the paper is to classify the state of a match with the labels of win, defeat, and draw. We have not made predictions about any future outcomes, but did focus on understanding the characteristics of the data itself to identify patterns and trends of the match. In doing so, we guessed the match result only after having collected the above feature data for the entire match duration. Thus, our scenario poses a classification problem. We compare different models (SVM, Logit, XGB, and MLP), the last one outperforming the others. Moreover, as a brand-new approach, we analyzed the logs by considering matches of different increasing duration. In particular, the lengths of the matches were the terms of an arithmetic series with a common difference of 5 minutes. In doing so, we have provided a dynamic approach that labels the match outcome every 5 minutes, using an MLP to track the accuracy of the state over the time. The findings have revealed an improved detection of draws, and highlighted that the model accuracy is higher in the early stages but decreases as the match progresses. In both approaches, explainable AI techniques have identified the key predictive features, offering insights into how technical features influence success dynamically throughout a match.

The pseudonymous nature of blockchain transactions poses a significant challenge for identifying fraudulent activity in decentralized financial systems. This study presents a comprehensive framework for classifying Bitcoin wallets as fraudulent or legitimate by integrating multi-source data, graph-based transaction modeling, and machine learning. Our methodology builds upon publicly available datasets–namely Elliptic++, Chainabuse, and a curated sample of recent transactions–and integrates structural, temporal, and monetary features extracted from the Bitcoin transaction graph. Through systematic experiments across three distinct labeling scenarios, we demonstrate that ensemble methods such as Random Forests offer strong performance even under label noise, achieving F1-scores up to 0.92. Moreover, an explainability framework grounded, in SHAP values, is used to systematically analyze feature contributions and elucidate behavioral patterns associated with financial fraud. Our approach bridges empirical robustness with forensic insight, contributing a scalable, transparent toolset for blockchain compliance and risk analysis.

Automatic trading systems cope with the needs of put out emotional biases from the trading operation of public assets. These systems place orders based on a price model that forecasts the future price of an asset. Those systems, developed by edge funds and institutional investors, are not available to the public, and extensive research in this field is worth the effort. In this research, we developed a short-term price model based on a neural network and used it to forecast the near-future price direction. More in depth, we introduced the feature extraction process and parametric labeling strategy to build an ML ready dataset that includes more than 400 cryptocurrencies. The model is then validated by building a trading strategy on the two most capitalized cryptos at the time of writing: Bitcoin and Ethereum. The validation uses a trading simulation that spans six years of historical data for Bitcoin and Ethereum, including both retrospective (backtest) and prospective (forward test) evaluations. The results demonstrate that the neural network-based model exhibits a very good generalization to patterns found in historical data, enabling predictions in future data within the trading simulation. In addition, a comprehensive analysis of the importance of features was conducted to enhance the interpretability and performance of the model. Finally, we test our model in a simulated trading session; it shows that, with a simple buy-only strategy plus a stop loss, the trading system limits the draw dawn during bear markets.

The rapid expansion of crypto-asset markets and the introduction of the Markets in Crypto-Assets Regulation (MiCAR) pose novel supervisory challenges. Existing blockchain intelligence platforms focus predominantly on on-chain surveillance, leaving gaps in off-chain documentary due diligence automation. This paper presents a Multi-Agent System (MAS) integrating Large Language Model (LLM) capabilities with rule-based compliance frameworks. The architecture comprises seven specialized agents: a Coordinator Agent for orchestration; data acquisition agents (Searcher, Crawler); three parallel analytical agents-Heuristic Agent (LLM-powered qualitative risk assessment), Compliance Agent (hybrid-AI MiCAR asset classification and regulatory requirement verification), and On-Chain Agent (machine learning-based fraud detection); and a Reconciliator Agent synthesizing findings into unified alerts. Component-level empirical validation on 150 projects indicates 95% output reproducibility (identical alert tier and score deviation <= 0.05 across five reruns) and 210 s mean latency, providing proof-of-concept evidence for the integrated pipeline. A pilot user evaluation (six researchers/master students and two experts from regulatory authorities) provides preliminary usability evidence and surfaces domain-specific feedback from regulatory-authority experts. The architecture advances proactive regulatory technology by enabling scalable analysis combining off-chain documentary evidence with on-chain forensics.

Algorithmic trading enables the execution of orders using a set of rules determined by a computer program. Orders are submitted based on an asset's expected price in the future, an approach well suited for high-volatility markets, such as those trading in cryptocurrencies. The goal of this study is to find a reliable and profitable model to predict the future direction of a crypto asset's price based on publicly available historical data. We first develop a novel labeling scheme and map this problem into a Machine Learning classification problem. The model is then validated on three major cryptocurrencies through an extensive backtest over a bull, bear and flat market. Finally, the contribution of each feature to the classification output is analyzed.

Depression has become a serious disease that affects people's mental state and is an important part of the global disease burden. Research in this area began later in 1920 and has steadily increased due to the pandemic. Many studies on depression have been conducted worldwide. Still, obtaining comparable data for physiological and biological detection techniques, existing datasets, acquisition, and data classification methods in one platform is challenging. In addition, clinical methods using screening instruments, questionnaires, and episodic examinations to determine depression severity are time-consuming. Therefore, an alternative approach is to incorporate assessment into a person's daily activities in their environment or clinic, preferably via sensor technologies with smart systems. Recently, much research has been conducted on machine learning methods that can automatically decode mental and cognitive states to improve efficiency, accuracy, and precision. In this proposed review, depression detection methods based on electrical and acoustic signals and verbal and nonverbal communication are described in detail and then organized for practical/commercial applications. This paper also reviews the potential and challenges of various depression detection methods to serve as a suitable reference for upcoming researchers.

In a physical microgrid system, equipment failures, manual misbehavior of equipment, and power quality can be affected by intentional cyberattacks, made more dangerous by the widespread use of established communication networks via sensors. This paper comprehensively reviews smart grid challenges on cyber-physical and cyber security systems, standard protocols, communication, and sensor technology. Existing supervised learning-based Machine Learning (ML) methods for identifying cyberattacks in smart grids mostly rely on instances of both normal and attack events for training. Additionally, for supervised learning to be effective, the training dataset must contain representative examples of various attack situations having different patterns, which is challenging. Therefore, we reviewed a novel Data Mining (DM) approach based on unsupervised rules for identifying False Data Injection Cyber Attacks (FDIA) in smart grids using Phasor Measurement Unit (PMU) data. The unsupervised algorithm is excellent for discovering unidentified assault events since it only uses examples of typical events to train the detection models. The datasets used in our study, which looked at some well-known unsupervised detection methods, helped us assess the performances of different methods. The performance comparison with popular unsupervised algorithms is better at finding attack events if compared with supervised and Deep Learning (DL) algorithms.

The DC microgrid systems include power electronic converters with information and communication technology. The performance of the DC microgrids will be determined by how effectively these converters are controlled. These communication protocols that support microgrids based on cooperative control are highly vulnerable to cyberattacks. False data injection attack (FDIA) is a kind of cyber-attack in which attackers attempt to introduce false data into the targeted DC microgrid in order to shut it down and destabilize it. Furthermore, the inherent characteristics of communication networks in microgrids may result in delays or/and packet drops in data transmissions between Distributed Generation Units (DGU). These network issues can degrade the stability and control loop performance, resulting in microgrid system uncertainty. Limited papers are available in the literature focusing on resilience against cyber-attacks and communication delays for DC microgrids in one platform. Thus, this paper discusses the impact of FDIAs on parallel DC/DC converter-structured DC microgrids that use droop-based control techniques to sustain the required DC voltage level using voltage observer and current regulator techniques. An unconventional delay-dependent stability condition is formulated and the system’s control parameters are adopted using the Lyapunov stability theory and Linear matrix inequality (LMI). The proposed method is tested under various circumstances, physical actions, and cyber-attacks, such as load changing, communication delay, packet loss, time-varying attacks, etc. The outcomes demonstrate the efficacy of the suggested approach in detecting and mitigating the considered attacks in DC microgrids using the MATLAB/Simulink tool.

This paper reports the results of the Inf@nziaDigiTales3.6 project on the design, development and evaluation of an augmented reality application to support situated learning experiences in a smart city. The users of the application are primary school children and the case study refers to recognition of road signs as geometric shapes. The objective is to allow children to comprehend the meaning of road signs of a city and to guide them in the recognition of the geometric shapes and colors connected to these signs. The mobile application is based on the paradigm of games and uses a virtual character with the role of intelligent tutor. The results of the evaluation confirm the expected benefits related to the adoption of augmented reality and mobile technologies, mainly in terms of involvement, pleasantness and willingness to repeat the experience. The results show that the re-mediation of augmented reality and the intelligent tutoring system have influenced the memorization processes of figures and colors, as well as of the contents of most of the signals presented. The application has been also deployed on smart glasses and shown in the context of an international event for children and teenagers, the Giffoni Film Festival(1)2018.

The balancing market as a significant part of the spot market addresses fair transaction settlements to eliminate the system imbalances in real time. However, traditional penalty mechanisms that have been also adopted for renewable generators may incur unintended consequences for such intermittent producers and even drive them out of the market. Therefore, here a flexible penalty mechanism (FPM) is adopted instead of the traditional policies to decrease the undesired impacts of traditional penalty mechanism (TPM) on the WPP’s revenue. Aligning with the FPM, making a contract between the WPP and the insurance provider in which the system operator (SO) is in charge of system balance is proposed as a remedy instrument to control the risks of wind volatilities. The proposed framework is formulated as a bi-level trilateral problem, in which in the upper level, the WPP maximizes its expected profit and in the lower level, the SO determines the market clearing prices (MCP) and maximizes the social welfare. Due to the importance of forecasting wind power generation, three deep learning algorithms are also used. Simulation results show that by applying FPM, the WPP’s profit improves depending on the contract it signed with the insurance provider while the SO preserves social welfare.

This paper presents an optimal bidding strategy for a strategic wind power producer (WPP) in a distribution-level energy market (DLEM). The behavior of the WPP is modelled through a bi-level stochastic optimization problem where the upper-level problem maximizes the profit of the WPP and the lower-level problem describes the clearing processes of the DLEM while considering network constraints. The bi-level problem is a stochastic mathematical program with equilibrium constraints (MPEC) that is formulated as a mixed-integer linear programming (MILP) problem. The main focus of this study is investigating prosumers’ impact on the market power of the strategic WPP in a DLEM structure. In this model, the effect of flexible prosumers from the aspects of demand response (DR) participants and photovoltaic penetration level (PVPL) on the WPP’s offering strategy is investigated. Moreover, the impact of bilateral contract on the market power of the strategic WPP and the cleared prices of the network is addressed. The proposed model is implemented in an IEEE 33-bus and numerical results illustrate how behavior of flexible prosumers and PVPL index affect the decision making of the strategic WPP when network constraints are considered. Numerical results show that by active participation of prosumers in DR programs, the reliance of DLEM on the strategic WPP reduces. Moreover, if the WPP participates in bilateral contracts, its offering to the DELM decreases, and as the result, the cleared prices augment indicating market power of the WPP.

In this paper, a decision-making framework is proposed for a virtual power plant (VPP) to participate in day-ahead (DA) and regulating market (RM) considering internal demand response (IDR) flexibility. In the proposed model, a DR exchange market (DRXM) is also introduced to cover deviations of uncertain resources and decrease VPP's imbalance penalties in the RM. The VPP can optimize its procurement expenditures by providing DR services from both IDR providers and DRXM. A market inefficiency index (MII) is defined to analyze the effect of trading energy in the DRXM on the market power of the VPP. The proposed model is formulated as a bi-level problem, in which at the upper level, the VPP maximizes its profit while at the lower level, the distribution system operator (DSO) strives to clear both DA and RM markets to maximize social welfare. The proposed problem is nonlinear and converted into a linear single-level problem through Karush-Kuhn-Tucker (KKT) optimality conditions and duality theory. The simulation results show that in high external demand response (EDR) participants, the expected profit of the VPP augments about 3% which is a substantial value for the one-day scheduling horizon. Furthermore, by providing EDR services, MII reduces which implies the EDRs preserve their economic surplus.

We present and evaluate a virtual counselling system that is devoted to improving user awareness of emotional situations in computer-mediated communication and making informed decisions on actions to recommend to the users involved in a conversation. Starting from elements such as the moods and emotions of the users involved in a conversation, the system constructs the emotional signatures of individuals and groups that are used to characterize a situation. It then uses an approximate reasoning mechanism based on three-way decisions to classify recognized situations with respect to particular emotional dynamics based on emotional contagion. A prototype of the system has been experimented on in a real context based on collaboration between university students for the realization of project work. The distinctive features of the system have been evaluated with accuracy measures, and the results are promising.

Nowadays, the massive use of social media provides useful unstructured knowledge that can be used to enhance the efficacy of online brand marketing campaigns. The unstructured nature of social media content and the relevance of the contextual dimension, like time, stress the requirements for extracting users' interests during the timeline. However, user profiling could have some unpleasant consequences for users' privacy, thus raising the need to define methodologies capable of avoiding privacy leaks despite the exploitation of interactions over social media. This paper presents both an intelligent method of profiling social media users and a privacy protection technique that is designed to match users' profiles and advertisements, and which could be used by advertising agencies. The proposed method performssemantic data analysis for extracting representations of the contents of messages exchanged by users over social media (e.g.,tweets), by exploiting rough set theory. In this way, users' interestis obtained by mining their daily online activity. The proposed framework investigates two-party scenarios, i.e., scenarios composed of a social network owner and an advertising agency willing to promote its client's products through the social network. This paper presents three privacy-preserving matching protocols which enable targeted advertising without compromising the privacy of either the users or the advertisers. Starting from a recently proposed advertisement matching protocol, a private layer was added to ensure that any sensitive information of either party is kept private. In this way, the social network and the advertiser could benefit from a system which allows them to run a matching protocol with the guarantee that sensitive user data (for the social network) and business information (for the advertiser) will not be disclosed. The first two protocols require interaction between the Advertiser and the Online Social Network, while the third one outsources to a semi-trusted service provider some of the computation done during the execution of the advertisement matching. The experimental results are also presented to illustrate the proposed system's good performance to discover potentially interested users given an advertisement as input.

This paper introduces Graded Computation Tree Logic with finite path semantics (GCTLf⁎, for short), a variant of Computation Tree Logic CTL⁎, in which path quantifiers are interpreted over finite paths and can count the number of such paths. State formulas of GCTLf⁎ are interpreted over Kripke structures. The syntax of GCTLf⁎ has path quantifiers of the form E≥gψ which express that there are at least g many distinct finite paths that satisfy ψ. After defining and justifying the logic GCTLf⁎, we solve its model checking problem and establish that its computational complexity is PSPACE-complete. Moreover, we investigate GCTLf⁎ under the imperfect information setting. Precisely, we introduce GCTLKf⁎, an epistemic extension of GCTLf⁎ and prove that the model checking problem also in this case is PSPACE-complete.

This paper presents and evaluates a method to combine time-based granulation and three-way decisions to support decision makers in understanding and reasoning on the learned granular structures conceptualising spatio-temporal events. The method uses an existing approach to discover periodic events in the data, such as periods of intense traffic in a city, and provides an original approach to conceptualize such events to support decision makers in: (i) better comprehending the causes that lead to the repetition of such events and/or (ii) increasing the awareness of their effects and consequences. The formal concept analysis is the central tool of the proposed method. This tool is used as a guide in the phase of time-based granulation, which relies on the principle of justified granularity, and as a support for reasoning and making three-way decisions. The main contribution of the paper is an effective and simple method for time-based granulation of events, their observation, and interpretation to support decision making. The method is described with an illustrative example and evaluated on a real data set on forest fires, showing how to define a spatio-temporal DSS model to support decisions in environmental monitoring problems.

To effectively guarantee a secure and stable operation of a smart substation, it is essential to develop a relay protection system considering the real-time online operation state evaluation and the risk assessment of that substation. In this paper, based on action data, defect data, and network message information of the system protection device (PD), a Markov model-based operation state evaluation method is firstly proposed for each device in the relay protection system (RPS). Then, the risk assessment of RPS in the smart substation is carried out by utilizing the risk transfer network. Finally, to highly verify the usefulness and the effectiveness of the proposed method, a case study of a typical 220 kV substation is provided. It follows from the case study that the developed method can achieve a better improvement for the maintenance plan of the smart substation.

In this paper, an improved hybridization of an evolutionary algorithm, named permutated oppositional differential evolution sine cosine algorithm (PODESCA) and also a sensitivity-based decision-making technique (SBDMT) are proposed to tackle the optimal planning of shunt capacitors (OPSC) problem in different-scale radial distribution systems (RDSs). The evolved PODESCA uniquely utilizes the mechanisms of differential evolution (DE) and an enhanced sine–cosine algorithm (SCA) to constitute the algorithm’s main structure. In addition, quasi-oppositional technique (QOT) is applied at the initialization stage to generate the initial population, and also inside the main loop. PODESCA is implemented to solve the OPSC problem, where the objective is to minimize the system’s total cost with the presence of capacitors subject to different operational constraints. Moreover, SBDMT is developed by using a multi-criteria decision-making (MCDM) approach; namely the technique for the order of preference by similarity to ideal solution (TOPSIS). By applying this approach, four sensitivity-based indices (SBIs) are set as inputs of TOPSIS, whereas the output is the highest potential buses for SC placement. Consequently, the OPSC problem’s search space is extensively and effectively reduced. Hence, based on the reduced search space, PODESCA is reimplemented on the OPSC problem, and the obtained results with and without reducing the search space by the proposed SBDMT are then compared. For further validation of the proposed methods, three RDSs are used, and then the results are compared with different methods from the literature. The performed comparisons demonstrate that the proposed methods overcome several previous methods and they are recommended as effective and robust techniques for solving the OPSC problem.