Recommendation systems play a crucial role in modern e-commerce and streaming services. However, the limited availability of public datasets hampers the rapid development of more efficient and accurate recommendation algorithms within the research community. This work introduces a stream-based data generator designed to generate user preferences for a set of items while accommodating progressive changes in user preferences. The underlying principle involves using user/item embeddings to derive preferences by exploring the proximity of these embeddings. Whether randomly generated or learned from a real finite data stream, these embeddings serve as the basis for generating new preferences. We investigate how this fundamental model can adapt to shifts in user behavior over time; in our framework, changes correspond to alterations in the structure of the tripartite graph, reflecting modifications in the underlying embeddings. Through an analysis of real-life data streams, we demonstrate that the proposed model is effective in capturing actual preferences and the changes that they can exhibit over time. Thus, we characterize these changes and develop a generalized method capable of simulating realistic data, thereby generating streams with similar yet controllable drift dynamics.

Energy optimization is crucial for environmental sustainability, as it reduces resource consumption, minimizes greenhouse gas emissions, and promotes the use of renewable energy. Efficient energy use helps combat climate change and preserves natural ecosystems for future generations. In this paper, a system to support the distribution of photovoltaic energy for Emilia Romagna Energy Communities is proposed. The system will manage and integrate large amounts of data and offer innovative services based on them for calculating climate and energy forecasts. To enable more reliable production estimates and efficient energy storage and distribution, the system will use a platform for managing and integrating data from Regional Climate Models. It will incorporate Machine Learning and Deep Learning models for accurate climate forecasts and optimize energy flows by considering consumption profiles, production forecasts, and storage characteristics. The application background, the proposed methodology, and the current challenges related to the domain will be discussed, with a particular focus on data sources and management operations.

Popularity bias is the tendency of recommender systems to further suggest popular items while disregarding niche ones, hence giving no chance for items with low popularity to emerge. Although the literature is rich in debiasing techniques, it still lacks quality measures that effectively enable their analyses and comparisons. In this article, we first introduce a formal, data-driven, and parameter-free strategy for classifying items into low, medium, and high popularity categories. Then we introduce Balanced Quality Score (BQS) , a quality measure that rewards the debiasing techniques that successfully push a recommender system to suggest niche items, without losing points in its predictive capability in terms of global accuracy. We conduct tests of BQS on three distinct baseline collaborative filtering frameworks: one based on history-embedding and two on user/item-embedding modeling. These evaluations are performed on multiple benchmark datasets and against various state-of-the-art competitors, demonstrating the effectiveness of BQS.

This paper introduces a novel deep learning approach for predicting global solar radiation and temperature. We propose an architecture based on Gated Recurrent Unit (GRU) neural networks able to refine weather predictions returned by the MM5 Regional Climate Model. Measured values from a weather station and outputs from the MM5 system are used to train and validate the model. The forecasting capability is assessed for three-day estimations. The results demonstrate that the model, by correcting MM5’s periodic tendencies to underestimate or overestimate the outputs, leads to a more accurate forecasting of the weather variables.These more precise predictions are then adopted for calculating the electrical energy production of a photovoltaic cell. Also in this case, the proposed model allows better results than the traditional MM5 system, enabling adaptive adjustments in intelligent energy systems.

Abstract In real-world applications, audio surveillance is often performed by large models that can detect many types of anomalies. However, typical approaches are based on centralized solutions characterized by significant issues related to privacy and data transport costs. In addition, the large size of these models prevented a shift to contexts with limited resources, such as edge devices computing. In this work we propose conv-SPAD , a method for convolutional SPectral audio-based Anomaly Detection that takes advantage of common tools for spectral analysis and a simple autoencoder to learn the underlying condition of normality of real scenarios. Using audio data collected from real scenarios and artificially corrupted with anomalous sound events, we test the ability of the proposed model to learn normal conditions and detect anomalous events . It shows performances in line with larger models, often outperforming them. Moreover, the model’s small size makes it usable in contexts with limited resources, such as edge devices hardware.

Consistent query answering is a principled approach for querying inconsistent databases. It relies on two basic notions: the notion of a repair, that is, a consistent database that "minimally" differs from the original one, and the notion of a consistent query answer, that is, a query answer that can be derived from every repair. In general, an inconsistent database can admit multiple repairs, each corresponding to a different way of restoring consistency, and the consistent query answering framework does not make any discrimination among them. However, in many applications it is natural and desired to express preferences among the different choices that can be made to resolve inconsistency.

Correct interpretation of images may be crucial for early disease detection. A growing number of medical instruments are image-oriented and produce a large quantity of image data, typically in the DICOM format, which contain spatio-temporal features together with alpha-numeric information regarding patients. Dealing with this high-dimensional datasets is a complex and time-consuming task. In addition the diffusion of smartphones and tablets requires the development of technological features enabling the medical team to check on helthcare processes on-the-go and freely access and send image and data for case analysis and collaborative diagnostic. This paper presents SIMPATICO 3D (Sistema Informativo Medico PATologIe COmplesse) a system supporting scientists and physicians by providing facilities for case studies analysis and diagnostic imaging in a shared virtual environment and details the features of SIMPATICO 3D Mobile (standing for Evolution Imaging System 3D for Mobile), that extends SIMPATICO 3D with dedicated functions for the mobile environment.

This paper proposes a logic based framework for data integration and query answering for deductive databases in a P2P environment. It is based on a special interpretation of mapping rules that leads to a declarative semantics for P2P systems defined in terms of preferred weak models. Under this semantics, only facts not making the local databases inconsistent can be imported, and the preferred weak models are the consistent scenarios in which peers import, by means of mapping rules, maximal sets of facts not violating (directly or indirectly) integrity constraints. The preferred weak models can be computed by means of a rewriting technique allowing to model a P2P system as a unique logic program whose stable models correspond to its preferred weak models. In the general case a P2P system may admit many preferred weak models and it has been shown that the complexity of their computation is prohibitive. Therefore, the paper looks for a more pragmatic solution assigning to a P2P system a new and more suitable semantics: the Well Founded Model Semantics. It allows to obtain a deterministic model whose computation is polynomial time. This model is a (partial) stable model obtained by evaluating with a three-value semantics the normal version of the rewriting of the P2P system. Finally, a distributed algorithm for the computation of the well founded model is proposed.

This paper proposes a system prototype for query answering in a Peer-to-Peer (P2P) network. As usual, a query can be posed to any peer in the system and the answer is provided by using locally stored data and all the information that can be consistently imported from its neighbors, i.e. the information satisfying integrity constraints collected using the semantic paths of mappings. The work stems from previous works of the same authors in which a declarative semantics for P2P systems is proposed. Under this semantics only facts not making the local databases inconsistent can be imported and the Preferred Weak Models are the consistent scenarios in which peers import maximal sets of facts not violating integrity constraints. In the general case, as a P2P system may admit many preferred weak models, the computational complexity results to be prohibitive, therefore this paper looks for a more pragmatic solution for assigning semantics to a P2P system. More specifically, it assigns to a P2P system its Well Founded Model, a partial deterministic model that captures the intuition that if an atom is true in a preferred weak model, but it is false in another one, then it is undefined in the well founded model. The paper presents a distributed algorithm for the computation of the well founded model and provides details on the implementation of a system prototype for query answering in P2P network based on the proposed semantics.

This paper aims to provide a contribution to the specific topic related to the integration of information and the computation of queries in an open ended network of distributed peers. Each peer joining a P2P system provides or imports data from its neighbors by using a set of mapping rules, i.e. a set of semantic correspondences to a set of peers belonging to the same environment. By using mapping rules, as soon as it enters the system, a peer can participate and access all data available in its neighborhood, and through its neighborhood it becomes accessible to all the other peers. In this setting two different types of mapping rules are possible: a first type allowing to import maximal sets of atoms and a second type allowing to import minimal sets of atoms from source peers to target peers. In the proposed setting, each peer can be thought of as a resource used either to enrich (integrate) the knowledge or to fix (repair) the knowledge. The declarative semantics of a P2P system is defined in terms of preferred weak models. The specific contributions of the present paper, that extends previous works of the same authors, consists in extending the classical notion of consistent answer by allowing the presence of partially defined atoms, i.e. atoms with "unknown" value due to the presence of tuples in different weak models which disagree on the value of one or more attributes.

This paper proposes a logic framework for modeling the interaction among incomplete and inconsistent deductive databases in a P2P environment. It stems from the work in [9, 13, 14, 16, 17] in which the declarative semantics of a P2P system is defined in terms of maximal weak models and the work in [15] in which the declarative semantics of a P2P system is defined in terms of minimal weak models. The maximal weak models semantics is based on the idea to use the mapping rules to import in each peer as much knowledge as possible without violating local integrity constraints. On the other hand under the Minimal Weak Models Semantics each peer uses its mapping rules to import minimal sets of mapping atoms allowing to satisfy its local integrity constraints. This latter behavior turns out to be useful in real world P2P systems in which peers often use the available import mechanisms to extract knowledge from the rest of the system only if this knowledge is strictly needed to repair an inconsistent local database. Therefore, each peer can be thought of as a resource used either to enrich (integrate) the knowledge (Maximal Weak Model Semantics) or to fix (repair) the knowledge (Minimal Weak Model Semantics). This paper extends previous works in [9, 13, 14, 16, 17] and in [15] by proposing a rewriting technique that allows modeling a P2P system, PS, as a unique logic program whose stable models correspond either to the maximal or minimal weak models of PS.

This paper proposes a logic framework for modeling the interaction among incomplete and inconsistent deductive databases in a P2P environment. Each peer joining a P2P system provides or imports data from its neighbors by using a set of mapping rules, i.e. a set of semantic correspondences to a set of peers belonging to the same environment. By using mapping rules, as soon as it enters the system, a peer can participate and access all data available in its neighborhood, and through its neighborhood it becomes accessible to all the other peers in the system. Two different types of mapping rules are defined: a first type allowing to import maximal sets of atoms and a second type allowing to import minimal sets of atoms from source peers to target peers. In the proposed setting, each peer can be thought of as a resource used either to enrich (integrate) the knowledge or to fix (repair) the knowledge. The declarative semantics of a P2P system is defined in terms of preferred weak models. An equivalent and alternative characterization of preferred weak model semantics, in terms of prioritized logic programs, is also introduced. The paper also presents preliminary results about complexity of P2P logic queries.

This paper investigates the data exchange problem among distributed independent sources. It is based on previous works of the authors [11, 12, 14] in which a declarative semantics for P2P systems has been presented and a mechanism to set different degrees of reliability for neighbor peers has been provided. The basic semantics for P2P systems defines the concept of Maximal Weak Models (in [11, 12, 14] these models have been called Preferred Weak Models. In this paper we rename them and use the term Preferred for the subclass of Weak Model defined here) that represent scenarios in which maximal sets of facts not violating integrity constraints are imported into the peers [11, 12]. Previous priority mechanism defined in [14] is rigid in the sense that the preference between conflicting sets of atoms that a peer can import only depends on the priorities associated to the source peers at design time. In this paper we present a different framework that allows to select among different scenarios looking at the properties of data provided by the peers. The framework presented here allows to model concepts like "in the case of conflicting information, it is preferable to import data from the neighbor peer that can provide the maximum number of tuples" or "in the case of conflicting information, it is preferable to import data from the neighbor peer such that the sum of the values of an attribute is minimum" without selecting a-priori preferred peers. To enforce this preference mechanism we enrich the previous P2P framework with aggregate functions and present significant examples showing the flexibility of the new framework.

This paper presents a technique that builds a layer of virtual sensors over a sensor network. The virtual sensors are able to infer and provide data for the physical sensors that do not work. The key assumption of our approach is that the physical quantities sensed by the sensors are related. The relations among sensors are unknown, but during a learning phase the layer of virtual sensors infers an approximation of them by means of fuzzy rules. The inferred fuzzy rules capture these relations in a simple way even when the corresponding mathematical models are complex. The set of fuzzy rules inferred for a node can be used to obtain virtual values when the real ones are not available. In order to develop our technique we improved the Tree Routing Protocol in charge to deliver data from the nodes to the base station and used Snlog, a Datalog-like language that supports the implementation of distributed algorithms for Wireless Sensor Network in a declarative way. We developed a system prototype and performed preliminary experiments that prove the validity of our approach.

Virology research is nowadays a discipline involving a broad number of researchers gathered in different institutes and cooperating on defined issues. An example of such an endeavor is the research tackling anti-HIV treatment problems [7] conducted within the Virolab project. The main objective of the ViroLab project is to develop a Virtual Laboratory for Infectious Diseases that facilitates medical knowledge discovery and decision support for HIV drug resistance. Large, high quality in-vitro and clinical patient databases which can be used to relate genotype to drug-susceptibility phenotype have become available. The core of the ViroLab Virtual Laboratory is a rule-based ranking system. More specifically, using a Grid-based service oriented architecture, Virolab vertically integrates the biomedical information from viruses (proteins and mutations), patients and literature (drug resistance experiments), resulting in a rule-based decision support system for drug ranking. This paper is a contribution to virologists, epidemiologists and clinicians in medical knowledge discovery and decision support. The final aim is reasoning on the properties of algorithm modeling the interaction among drugs and HIV virus and detecting its anomalies such as rules that can never be satisfied and subset of rules that are in contradiction.

This paper introduces active integrity constraints (AICs), an extension of integrity constraints for consistent database maintenance. An active integrity constraint is a special constraint whose body contains a conjunction of literals which must be false and whose head contains a disjunction of update actions representing actions (insertions and deletions of tuples) to be performed if the constraint is not satisfied (that is its body is true). The AICs work in a domino-like manner as the satisfaction of one AIC may trigger the violation and therefore the activation of another one. The paper also introduces founded repairs, which are minimal sets of update actions that make the database consistent, and are specified and ldquosupportedrdquo by active integrity constraints. The paper presents: 1) a formal declarative semantics allowing the computation of founded repairs and 2) a characterization of this semantics obtained by rewriting active integrity constraints into disjunctive logic rules, so that founded repairs can be derived from the answer sets of the derived logic program. Finally, the paper studies the computational complexity of computing founded repairs.

The paper proposes a logic framework for modeling the interaction among deductive databases and computing consistent answers to logic queries in a P2P environment. As usual, data are exchanged among peers by using logical rules, called mapping rules. The novelty of our approach is that only data not violating integrity constraints are exchanged. The (declarative) semantics of a P2P system is defined in terms of weak models. Under this semantics only facts not making the local databases inconsistent can be imported, and the preferred weak models are the consistent scenarios in which peers import maximal sets of facts not violating integrity constraints. A characterization of the preferred weak model semantics, allowing to model a P2P system with a prioritized logic program, is provided. The proposed framework is then extended in order to also take into account P2P system in which each peer may be locally inconsistent, i.e. its data does not satisfy some of its constraints. Finally, the complexity of P2P logic queries is investigated