The increasing complexity of clinical data presents both challenges and opportunities for modern healthcare. This study proposes a robust framework for building a Clinical Knowledge Graph (KG) by leveraging unstructured Electronic Health Records (EHRs) and clinical notes. Using state-of-the-art natural language processing tools such as MetaMap and the Unified Medical Language System (UMLS), the proposed system structures heterogeneous medical data into a unified format. By analyzing demographic, symptomatic, and laboratory data, this framework enables enhanced decision-making and insights into disease correlations. Demonstrated using the MIMIC-III database, the system achieves high granularity, providing actionable intelligence for personalized recommendations and supporting predictive diagnostic models.

Narratives are essential tools through which politicians and public figures construct shared meanings and shape public perception, both locally and globally. This paper introduces a computational approach for systematically identifying and analyzing narrative structures in political speeches, aiming to enhance our understanding of how politicians try to convey their messages. A novel ontology, OntoNarr (Ontology for Narrative Representation), is defined and used to identify narrative schemas within the full text of the speeches. The core contribution is a more interpretable and conceptually coherent method for comparing political speeches based on their underlying narrative structures. This is achieved by converting ontology-based representations into graph embeddings and visualizing them using scatterplots. Unlike traditional NLP pipelines that rely primarily on lexical and syntactic features, this method incorporates a formal semantic structure, addressing key limitations in conventional analysis. A case study involving speeches from four politicians demonstrates how historical context influences the choice of narrative schema while also revealing some cross-temporal and cross-ideological similarities. Lastly, a method from granular computing is used to quantitatively evaluate the ontology-based approach.

Abstract Forests contribute significantly to climate regulation, biodiversity conservation, and the livelihoods of billions of people. The advancement of digital technologies has driven the growing use of Earth observation techniques, involving satellites, drones, and sensors to gather large volumes of heterogeneous environmental data. However, integrating and interpreting these diverse data sources, such as vegetation indices, meteorological records, geospatial information, and sensor measurements, remains a significant challenge. This paper presents a framework that constructs an integrated knowledge base built around a custom ontology, SORSOntology , designed to provide a consistent and accessible representation of environmental information. By combining AI-driven image analysis with semantic technologies, the proposed system enables automated deforestation monitoring and contextual reasoning driven by both OWL class restrictions and SWRL rules. These inference mechanisms support the automatic classification of observations into high-level environmental categories, and are transparently executed in the backend upon image selection within the Web-based user interface. Experimental results on Sentinel-2 imagery of the Amazon region show that the framework achieves accurate segmentation performance and allows enriched interpretation of forest conditions through ontology-based queries.

Glacier melting, due to climate change, is a growing concern with many implications for the planet. Although remote sensing technology offers valuable solutions, the data acquired is often heterogeneous, varying in format and originating from different sensors and sources. Harmonizing this heterogeneous data is essential to ensure compatibility and integration. This paper introduces an integrated model that combines Machine Learning methods for satellite image segmentation with semantic web technologies for knowledge base construction aimed at retrieving relevant data concerning glacier monitoring implications. An ad-hoc ontology was developed to model the knowledge base about the glacier domain. At the same time, semantic segmentation allows the elicitation of relevant features combined with contextual meteorological data to populate the knowledge base. The synergy between ontology-based annotation and Deep Learning techniques for segmenting remote sensing images enables a more comprehensive assessment of glacial health, facilitating the retrieval of specific information via semantic queries. The effectiveness of the proposed system is shown by evaluating the performance of the Deep Learning models and the consistency and robustness of the ontology in processing complex queries.

Evaluating the actual price of a residential property is a critical issue in the real estate market. Real estate market practitioners gauge a property's price by considering features such as property type and residential area. Subsequently, they evaluate the property's intrinsic features, such as condition, sun exposure, scenic views, and ancillary amenities. Finally, extrinsic features such as the proximity of services and infrastructure are assessed. This paper proposes a new genetic approach for selecting residential properties that meet the purchase offer and the intrinsic and extrinsic characteristics desired by the client. Since the real estate market's changes can influence extrinsic features, the method introduces price fluctuations of properties. Extrinsic features are modelled as fuzzy partitions: each fuzzy set describes a qualitative aspect of the corresponding feature that, expressed in a linguistic term, has a human-like interpretation. Then, a deviation value (fluctuation) from the average price of the property is considered for each fuzzy set in the partition. All the property features, extrinsic and intrinsic, are encoded in the chromosome genes of the genetic algorithm. The fitness function calculates the distance between the unit price of the property and the purchase offer. Some case studies were conducted in various Italian municipalities, using the average price per square meter of residential properties the Osservatorio del Mercato Immobiliare (OMI) assigned. Depending on customer requirements and preferences, different OMI zones were selected using additional characteristics such as type, location, conservation, and proximity to various urban services. The results demonstrated the effectiveness of the proposed approach for all the case studies, showing how the optimal solution represents a good compromise between customer preferences and market offerings.

Abstract Precision agriculture is evolving toward a contemporary approach that involves multiple sensing techniques to monitor and enhance crop quality while minimizing losses and waste of no longer considered inexhaustible resources, such as soil and water supplies. To understand crop status, it is necessary to integrate data from heterogeneous sensors and employ advanced sensing devices that can assess crop and water status. This study presents a smart monitoring approach in agriculture, involving sensors that can be both stationary (such as soil moisture sensors) and mobile (such as sensor-equipped unmanned aerial vehicles). These sensors collect information from visual maps of crop production and water conditions, to comprehensively understand the crop area and spot any potential vegetation problems. A modular fuzzy control scheme has been designed to interpret spectral indices and vegetative parameters and, by applying fuzzy rules, return status maps about vegetation status. The rules are applied incrementally per a hierarchical design to correlate lower-level data (e.g., temperature, vegetation indices) with higher-level data (e.g., vapor pressure deficit) to robustly determine the vegetation status and the main parameters that have led to it. A case study was conducted, involving the collection of satellite images from artichoke crops in Salerno, Italy, to demonstrate the potential of incremental design and information integration in crop health monitoring. Subsequently, tests were conducted on vineyard regions of interest in Teano, Italy, to assess the efficacy of the framework in the assessment of plant status and water stress. Indeed, comparing the outcomes of our maps with those of cutting-edge machine learning (ML) semantic segmentation has indeed revealed a promising level of accuracy. Specifically, classification performance was compared to the output of conventional ML methods, demonstrating that our approach is consistent and achieves an accuracy of over 90% throughout various seasons of the year.

International audience

Among climate effects, fires are reported to be the most catastrophic events both economically and environmentally, in fact, recent statistics report about 340,000 hectares (ha) burnt in countries of the European Community during 2020, corresponding to an area 30% larger than Luxembourg. In worst cases, fire-affected areas will be permanently damaged. Then, there is a need for solutions to help institutions and researchers to keep the environment under monitoring, assess the damage severity and help planning burned area recovery. To this purpose, this paper presents a smart monitoring framework that bridges spectral image clustering with soft computing techniques to describe the effective fire damages in the monitored area. The approach collects images from Sentinel-2 satellite, assesses Spectral Indices (SIs) from them, then by clustering, divides the area into different sub-regions according to their vegetative features. Then these sub-regions are parsed by a fuzzy decision tree, able to interpret the damage of fire severity in each sub-region. Experiences show that by dividing the area into many sub-regions, fire damage can be detected at different levels of granularity, providing a detailed map of the most damaged sub-areas to plan, for example, ad-hoc recovery interventions.

Collecting massive seismic signals is a high-priority task in seismic risk evaluation, especially in densely populated areas, with cases of strong magnitude earthquake occurrence. At the same time, with the advent of the Internet of Things (IoT) paradigm, distributed and real-time environmental monitoring, supported by device interoperability, enhances the ability to collect data and make decisions especially in critical domains such as the seismic one. A crucial role is played by Semantic Web technologies that, in IoT ecosystems, promote syntactic and semantic interoperability, by enhancing the data quality that becomes ontology-annotated. This article introduces an IoT-oriented framework to collect seismic data, process and store them into a knowledge base. An ontology called Volcano Event Ontology (VEO) modeled for the seismic domain aims at gathering seismic signals collected by sensors for seismic event detection. The ontology is built on the well-known SSN/SOSA ontology, modeled to describe the systems of sensors, actuators, and observations. Seismic data have been collected by monitoring networks at Mt. Vesuvius (Naples, Italy) and Colima volcano (Mexico) and consolidated in the ontology. Moreover, the seismic data are also processed by a classification module to detect different seismic events (Volcano-Tectonic and long-period earthquakes, underwater explosions, and quarry blasts) and then stored in the knowledge base. Prompt detection and classification are, indeed, relevant to track any variation in the volcano dynamics, becoming crucial in cases of explosive crises. Finally, the VEO-driven knowledge base can be queried to get time-based seismic data and detected events, by queries.

Emotion detection in the natural language text has drawn the attention of several scientific communities as well as commercial/marketing companies: analyzing human feelings expressed in the opinions and feedback of web users helps understand general moods and support market strategies for product advertising and market predictions. This paper proposes a framework for emotion-based classification from social streams, such as Twitter, according to Plutchik's wheel of emotions. An entropy-based weighted version of the fuzzy c-means (FCM) clustering algorithm, called EwFCM, to classify the data collected from streams has been proposed, improved by a fuzzy entropy method for the FCM center cluster initialization. Experimental results show that the proposed framework provides high accuracy in the classification of tweets according to Plutchik's primary emotions; moreover, the framework also allows the detection of secondary emotions, which, as defined by Plutchik, are the combination of the primary emotions. Finally, a comparative analysis with a similar fuzzy clustering-based approach for emotion classification shows that EwFCM converges more quickly with better performance in terms of accuracy, precision, and runtime. Finally, a straightforward mapping between the computed clusters and the emotion-based classes allows the assessment of the classification quality, reporting coherent and consistent results.

Precision agriculture employs IoT devices to smartly monitoring plant vegetation and support food production. Precision agriculture is highly required to improve product quality and better suit the requirements of the market. Among the IoT devices, Unmanned Aerial Vehicles (UAVs), can be equipped with many sensors that allow precise assessments of plant stress by flying over the plots. Notwithstanding the great benefits introduced, IoT devices may suffer from some issues. Many devices provide data in different formats on the same task, therefore they need solutions to integrate data and support a more thorough crop monitoring. This paper introduces a multitier architecture to deal with IoT-based intelligent monitoring, as well as an implementation of the architecture through multiagent modeling of the IoT devices for precision agriculture. The introduced model allows data acquisition from various sources (i.e., IoT devices), an ontology-based integration of data provided by the devices and a knowledge integration process to deal with domain-specific applications.

In recent years, unmanned vehicles (UVs) have been largely employed in many applications. They, enhanced with computer vision and artificial intelligence, can autonomously recognize targets in an environment and detect events occurring in a real-world scenario. The employment of cooperative UVs can provide multiple interpretations supporting a multiperspective view of the scene. However, UV multiple interpretations often diverge, therefore, UVs need to find an agreed interpretation of the scenario. To this purpose, this paper proposes a novel consensus-based approach to lead multi-UV systems to find agreement on what they observe and build a group situation-based description of the scenario. UVs are modeled as experts in a group decision making problem that must decide on which situations best describe the scenario. First, the approach allows each UV to build high-level situations from the detected events through a fuzzy-based event aggregation. The event aggregation is modeled with a fuzzy ontology which allows each UV to express preferences on the situations. Then, a collective interpretation of situations is achieved by consensing each UV interpretation. Finally, consensus and proximity measures support the evaluation of the final group decision reliability. The assessed consensus reflects how much the collective scenario interpretation fits each UV perspective. The proximity measures support the detection of reliable and unreliable UVs to serve many tasks (i.e., mission replanning, damaged UV detection, etc.).

In the Social Web age, the role of the web user has evolved from a simple consumer of web content to the main actor who interacts with other users, shares data and cooperates in social networks, online communities, blogs, wikis, feeds, and chats. His opinions, comments, and suggestions have an amazing influence on the online communities and users that can be inadvertently influenced in decision-making activities such as buying a certain product or trusting the recommendations of the blog, etc. Big corporations, as well as scientific communities, study the user behavior trying to capture human feeling and emotions, aimed at guessing the “client” preferences and then attend his expectations. Emotion extraction using natural language is a complex activity that needs to understand the content and capture the sentiment hidden in the written text. To this end, the work proposes a text analysis based on Deep Learning (DL) to capture the emotions that regulate human feeling in the natural language. The work shows the effectiveness of this approach presenting a comparative analysis of emotion-based text classification by DL neural networks methods, with different datasets and feature settings.

With the explosion of social media, automatic analysis of sentiment and emotion from user-generated content has attracted the attention of many research areas and commercial-marketing domains targeted at studying the social behavior of web users and their public attitudes toward brands, social events, and political actions. Capturing the emotions expressed in the written language could be crucial to support the decision-making processes: the emotion resulting from a tweet or a review about an item could affect the way to advertise or to trade on the web and then to make predictions about future changes in popularity or market behavior. This paper presents an experience with the emotion-based classification of textual data from a social network by using an extended version of the fuzzy C-means algorithm called extension of fuzzy C-means. The algorithm shows interesting results due to its intrinsic fuzzy nature that reflects the human feeling expressed in the text, often composed of a mix of blurred emotions, and at the same time, the benefits of the extended version yield better classification results.

Visual tracking supported by unmanned aerial vehicles (UAVs) has generated a lot of interest in recent years, especially in application domains such as surveillance, search for missing persons and traffic monitoring. The major challenges in visual tracking with small UAVs arise in the form of target representation, target appearance change, target detection and localization in real time computation. Reliable target detection depends on factors such as occlusions, image noise, illumination and pose changes, or image blur that may compromise the object labeling. To mitigate these issues, this paper proposes a hybrid solution: along with the tracked objects, scenes are completely depicted by adding contextual information, i.e., data describing places, natural features, or in general points of interest. Each scenario indeed is semantically described by ontological statements that define the context and then, by inference, support the object tracking task in the object identification and labeling. The synergy between the tracking methods and semantic modeling can bridge the object labeling gap, enhancing the scene understanding and awareness when alarming situations are discovered. Experimental results are promising and confirm the applicability of the proposed framework in supporting drones in object identification and critical situation detection tasks.

Scenario understanding from video stream plays an important role in many safety-critical application domains, especially if it is targeted at the autonomous aerial navigation and surveillance. Our contribution aims at enhancing the capability of unmanned aircraft systems to get a high-level description of the scene evolution from a video stream, by identifying events, thanks to the objects involved in these events. The work proposes a hybrid solution that merges data from the video tracking with additional semantic data: tracked objects are not only described by their typical information provided by tracking algorithms, but they are enhanced with semantic data, such as their geographical position, the interactions with other objects in the scene as well as their involvement in events occurring in a certain time interval. In particular, given a temporal window, a scene is depicted through the occurring events, the participating object tracks and the consequent evolution in terms of track movements.

Visual object tracking with unmanned aerial vehicles (UAVs) plays a central role in the aerial surveillance. Reliable object detection depends on many factors such as large displacements, occlusions, image noise, illumination and pose changes or image blur that may compromise the object labeling. The paper presents a proposal for a hybrid solution that adds semantic information to the video tracking processing: along with the tracked objects, the scene is completely depicted by data from places, natural features, or in general Points of Interest (POIs). Each scene from a video sequence is semantically described by ontological statements which, by inference, support the object identification which often suffers from some weakness in the object tracking methods. The synergy between the tracking methods and semantic technologies seems to bridge the object labeling gap, enhance the understanding of the situation awareness, as well as critical alarming situations.

With the advent of Social Web, the user has become an active consumer which shares information and participates in social networks, online communities, blogs, wikis, feeds and chats. The volunteer person-power is a valuable resource which creates innovative content and helps other users to make right decisions with his own opinions, suggestions, advice. Opinions and suggestions have an amazing impact on the online user community: they may unexpectedly influence decision-making activities starting from simply buying or not a smartphone until to social events, political actions, and even marketing strategies. This paper aims at studying the role played by the sentiments in influencing the user actions. Particularly, it analyzes how sentiments expressed in the text can move the reader to do altruistic actions. The idea is from RAOP community where users write posts asking or offering a free pizza. Our work achieves a comparative analysis of machine learning methods on a ROAP dataset, that collects original posts where users asked for a free pizza. The goal is to extract the sentiments expressed in natural language, in the textual requests, in order to predict which user request will be satisfied (getting a free pizza). Finally, a posteriori “affective” analysis shows the predominant emotions expressed in the satisfied requests, that move the readers to have an altruistic behavior.

Emotions govern all the human actions and play a key role in decision-making processes. Capturing sentiments and opinions hidden in the written (natural) language is a key activity which attracts both the scientific community, by leading to many novel challenges, and the business world, by supporting market behavior and prediction. Sentiment analysis and Sentic Computing are two interrelated research trends that, by exploiting the common sense in the natural language, try to distill human feelings in the textual data.

The growing amount of images on the Web, the diffusion of social media sharing web sites demand effective tools for searching targeted images. In general, the performance of Web image search depends on the quality of images annotation, but often the keywords (or tags) associated to an image are given without relevance information, strictly connected to a subjective feeling of the taggers and far from the objective description of the image. In this paper, we propose a simple approach for social media sharing web sites such as Flickr, Zooomr, etc. to support users to retrieve images semantically correlated to a given tagged image. In this paper, we present an application scenario for Flickr: in general Flickr returns all the images that meets the input tags, without no semantic analysis and evaluation of the effectiveness of the search results. Our approach adds a semantic layer on the Flickr output: processes the tags associated to the retuned images to discover the appropriate semantics of them, by arranging the results in a more user friendly view.

In the era of data intensive management and discovery, the volume of images repositories requires effective means for mining and classifying digital image collections. Recent studies have evidenced great interest in image processing by "mining" visual information for objects recognition and retrieval. Particularly, image disambiguation based on the shape produces better results than traditional features such as color or texture. On the other hand, the classification of objects extracted from images appears more intuitively formulated as a shape classification task. This work introduces an approach for 2D shapes classification, based on the combined use of geometrical and moments features extracted by a given collection of images. It achieves a shape based classification exploiting fuzzy clustering techniques, which enable also a query-by-image.

In an era in which organizations increasingly consider the competencies of their employees as a crucial resource, human management becomes a key activity for improving staff and business performances. Important is also knowing who knows what inside the organization, so that project teams are assembled as the right mix of skill, knowledge and workforce abilities. At the same time, trust, an essential component, related to understanding interpersonal and group behavior, is an indisputable prerequisite for organizational effectiveness, in terms of social-cognitive capital, global competency as well as economic exchange and social and political stability. This paper defines an approach to support competency-based management by providing recommendations about the reliability of a worker in terms of trust information and own competencies. The approach lies on an agent-based architecture which supervises the Human Resources Management (HRM). Task-oriented agents monitor the employees' profiles and capabilities by maintaining update the competencies and the trusts in the organizational social network. Particularly an agent endowed by fuzzy reasoning capabilities provides recommendation about workers' competencies in HRM decision-making processes.

Nowadays, in enterprise environments there is a wide and consolidated utilization of software for the human resource management providing functionalities like organizational management, personnel development, training event management, etc. that lay upon a competencies repository mostly populated through expensive and inefficient data entry activities. The new trends in Web 2.0 see a paradigm namely Enterprise 2.0, for supporting business activities within organizations. Web 2.0 is mainly exploited to sustain collaboration, information exchange and knowledge sharing. This work introduces an agent-based framework for the dynamic refinement of employees' competencies profiles by analyzing and monitoring collaborative activities executed through Enterprise 2.0 tools (e.g. corporate blogs, enterprise wikis, etc.). A fuzzy extension of Formal Concept Analysis model supports the elicitation of implicit knowledge and the content structuring into a conceptual representation. The resulting concept-based organization of initial user-generated content will be exploited to provide automatic hints to human resources (HR) managers in order to support them in making safer decisions that involve employees' competencies.

The current “semantic” generation of Web strongly lies in sharing knowledge rather than linkages among digital resources. The Semantic Web represents an effective infrastructure based on ontologies, languages and tools to enhance visibility of knowledge on the net. The imprecise nature of knowledge often requires fuzzy techniques to coherently represent the imprecise and uncertain information of the real world. It is indubitable that many decision making problems within business, industrial and web applications are solved by fuzzy approaches, especially by exploiting fuzzy control. In order to integrate fuzzy knowledge in the Semantic Web, appropriate formal schemas are introduced for describing fuzzy data types and uncertainty information. In particular, this paper presents an OWL-based upper ontology, called OWL-FC (Ontology Web Language for Fuzzy Control) which provides a set of ontological constructs for defining semantic specification of Fuzzy Control. The OWL-FC ontology represents a straightforward contribute to support automation in discovery, usage and interoperability among a large number of fuzzy controls; built-in markups for the fuzzy controls enable the natural integration in description logics-based reasoners and guarantee the specification of fuzzy concepts which do not depend on the application domain.

The huge growth of data on the Web and the requirement of semantic content analysis make the knowledge management and data mining very difficult activities. The knowledge elicitation, codification, and storage need not trivial techniques to improve formal information structuring on the Internet. Ontologies provide conceptualization and processing knowledge, sharing of consolidate understanding, reusing of domain knowledge codification for many Web applications. Manual construction of a domain-specific ontology is an intensive and time-consuming process, which requires an accurate domain expertise, because of structural and logical difficulties in the definition of concepts, as well as conceivable relationships. At the same time, the ontology visualization process requires similar endeavors to support ontology management, exploration, and browsing. This work describes an automatic method for ontology design from the content analysis of Web resources. The approach exploits a fuzzy extension of formal concept analysis model for structuring the elicited knowledge, viz. concepts and relations embedded in the resources content. Final result is an effective ontology visualization through a navigable, facet-based view of the built ontology across the extracted concepts and their own population. Furthermore, the approach proposes a simple labeling of ontology concepts through a sketched and intuitive process. © 2010 Wiley Periodicals, Inc.

In this study, we introduce a certain knowledge-guided scheme of fuzzy clustering in which domain knowledge is represented in the form of so-called viewpoints. Viewpoints capture a way in which the user introduces his/her point of view at the data by identifying some representatives, which, being treated as externally introduced prototypes, have to be included in the clustering process. More formally, the viewpoints (views) augment the original, data-based objective function by including the term that expresses distances between data and the viewpoints. Depending upon the nature of domain knowledge, the viewpoints are represented either in a plain numeric format (considering that there is a high level of specificity with regard to how one establishes perspective from which the data need to be analyzed) or through some information granules (which reflect a more relaxed way in which the views at the data are being expressed). The detailed optimization schemes are presented, and the performance of the method is illustrated through some numeric examples. We also elaborate on a way in which the clustering with viewpoints enhances fuzzy models and mechanisms of decision making in the sense that the resulting constructs reflect the preferences and requirement that are present in the modeling environment.

In recent years, the success of Semantic Web is strongly related to the diffusion of numerous distributed ontologies enabling shared machine readable contents. Ontologies vary in size, semantic, application domain, but often do not foresee the representation and manipulation of uncertain information. Here we describe an approach for automatic fuzzy ontology elicitation by the analysis of web resources collection. The approach exploits a fuzzy extension of Formal Concept Analysis theory and defines a methodological process to generate an OWL-based representation of concepts, properties and individuals. A simple case study in the Web domain validates the applicability and the flexibility of this approach.

Nowadays, the emphasis on Web 2.0 is specially focused on user generated content, data sharing and collaboration activities. Protocols like RSS (Really Simple Syndication) allow users to get structured web information in a simple way, display changes in summary form and stay updated about news headlines of interest. In the e-Learning domain, RSS feeds meet demand for didactic activities from learners and teachers viewpoints, enabling them to become aware of new blog posts in educational blogging scenarios, to keep track of new shared media, etc. This paper presents an approach to enrich personalized e-learning experiences with user-generated content, through the RSS-feeds fruition. The synergic exploitation of Knowledge Modeling and Formal Concept Analysis techniques enables the definition and design of a system for supporting learners in the didactic activities. An agent-based layer supervises the extraction and filtering of RSS feeds whose topics are specific of a given educational domain. Then, during the execution of a specific learning path, the agents suggest the most appropriate feeds with respect to the subjects in which the students are currently engaged in.

This paper describes a system for supporting the user in the discovery of semantic Web services, taking into account personal requirements. Goal is to model an ad-hoc service request by filtering semantic specifications rather than the exploitation of strict syntax formats. Adaptive agent-based techniques help the user to compose his Web service request, exploiting the semantic annotation of the browsed Web resources. This annotation reflects concepts or ontological terms that are relevant for the user services request formulation. Once the request is formulated, the system returns the list of semantic Web services that match the query input and output concepts.

Internet has become a huge repository of information and knowledge, based on the sharing of the electronic documents. Last trends in knowledge management focus on the knowledge representation based on the document content. In fact, most accustomed approaches achieve the document understanding by analyzing the “portions of information'' in the document which describe the content, through techniques of text parsing and extraction. This paper presents an alternative approach that departs from the consolidated techniques of document management and focuses on the logical structure of a PDF document as a discriminating source of document knowledge. The main idea is based on the fact, when the reader looks at a paper, his first perception is related to the layout of the document. The analysis of layout, typesetting, paginating, and graphical arrangement of a document provides interesting information about its content understanding; in general, the documents that are in the same category present similar page layout, fonts, and figures arrangement. In this sense, this work presents an alternative way to deal with documents recognition and understanding, through the analysis of the layout of electronic PDF documents and their classification. © 2008 Wiley Periodicals, Inc.

The evolution of the Semantic Web promises infrastructures for the semantic interoperability of Web Services. Hindrances in the service discovery, composition and execution are often of syntactic nature: the difficulty in the interpretation of inputs, outputs or other nontrivial statements does not favor to find eligible advertised services which appropriately meet the consumer's demand. This paper deals with the semantic matchmaking focusing on the ontology mismatch problem: concepts appearing in the services description are compared at semantic level in order to profit by the semantic similarity existing among entity classes (i.e. concepts). The approach is based on a multi-agent architecture and exploits fuzzy techniques to represent the multi-granular capabilities of a web service. The semantic similarity among concepts supports the clustering of the advertised services and improves the quality of the retrieved results, given a request.

Web information may currently be acquired by activating search engines. However, our daily experience is not only that web pages are often either redundant or missing but also that there is a mismatch between information needs and the web's responses. If we wish to satisfy more complex requests, we need to extract part of the information and transform it into new interactive knowledge. This transformation may either be performed by hand or automatically. In this article we describe an experimental agent-based framework skilled to help the user both in managing achieved information and in personalizing web searching activity. The first process is supported by a query-formulation facility and by a friendly structured representation of the searching results. On the other hand, the system provides a proactive support to the searching on the web by suggesting pages, which are selected according to the user's behavior shown in his navigation activity. A basic role is played by an extension of a classical fuzzy-clustering algorithm that provides a prototype-based representation of the knowledge extracted from the web. These prototypes lead both the proactive suggestion of new pages, mined through web spidering, and the structured representation of the searching results. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 1101–1122, 2007.

The semantic vision of the Web involves the processing of data by automated tools as well as by people, where the association of meaning with content, facilitates the search, the interoperability and the composition of several services. The Semantic Web forms a new scenario, where advanced methods and techniques are developed for the description, the retrieval and filtering of Web-based content. In the light of existing challenges and open issues concerning the actual cyberspace, this study proposes an approach for binding the "semantic" facet with the usual textual one, that together constitutes a typical web page, or specifically, a semantic web document. Through the use of unsupervised learning, we offer a new alternative of organizing web documents which emphasizes a direct separation between the syntactic and semantic facets of the web information. In this study, we discuss a collaborative proximity-based fuzzy clustering and show how this type of clustering is used to discover a structure of web information by a prudent reliance on the structures in the spaces of semantics and data. The method focuses on the reconciliation between the two separated facets of web information and a combination of results leading to a comprehensive data organization. The information arranged in this manner can provide an integral description of web resources, becoming in this manner an essential technique for the next generation of Web search engines.

Abstract The explosive growth of the Web and the consequent exigency of the Web personalization domain have gained a key position in the direction of customization of the Web information to the needs of specific users, taking advantage of the knowledge acquired from the analysis of the user's navigational behavior (usage data) in correlation with other information collected in the Web context, namely, structure, content, and user profile data. This work presents an agent‐based framework designed to help a user in achieving personalized navigation, by recommending related documents according to the user's responses in similar‐pages searching mode. Our agent‐based approach is grounded in the integration of different techniques and methodologies into a unique platform featuring user profiling, fuzzy multisets, proximity‐oriented fuzzy clustering, and knowledge‐based discovery technologies. Each of these methodologies serves to solve one facet of the general problem (discovering documents relevant to the user by searching the Web) and is treated by specialized agents that ultimately achieve the final functionality through cooperation and task distribution.

The rapid growth of Web resources makes very difficult the task of Web search engines. Nevertheless powerful search crawlers have been developed to aid in locating unfamiliar document (by means of category, contents or subject based approaches), often queries return inconsistent results. The main lack of Web searching is in the deduction capability: nowadays Web searching put much attention in matching user's queries that are too weak to cope with the user's expressiveness. First attempts in extending searching towards deduction capability are essentially based on two-valued logic and standard probability theory. The complexity of the problem (8.4 million of Web sites), the features of the space domain (unstructured data, immature standards) demand a strong deviation from this trend. This work presents some results stemmed from a research projects where different technologies (in particular mobile agents and approximate reasoning) have been merged into an operational architecture suitable for Web searching/Web discovering. This paper discusses a different approach to Web searching where the input to the retrieval process is described through a Web page. The system reacts to this kind of query by returning a set of Web pages that reflect a similar context and deals with related arguments.

As information nowadays represents a key factor in every successful business, and Internet offers literally tons of available data concerning almost every area of human activity, there emerges a real necessity for good search tools that can obtain high quality information in a short time. Nowadays finding useful information can be an overwhelming task. As a result, consumers need effective mechanisms for searching the Web. This paper describes LearnMiner, an open, agent-based platform designed for advanced didactic resource discovery. A central role is played by deductive agents, equipped with a similarity-based inference mechanism. This issue enables to bridge the gap between the requested information and the available information on the net, considering the "similarity" as a weaker relation for undiscernibility.

Although advanced and innovative technologies have been used to retrieve information, the need of advanced, new techniques for Web information retrieval is extant. One of the main difficulties is to return accurate information that fully describes the human request. Standard Web search engines provide two mechanisms to handle a user's query: to input the search keywords or to restrict the searching within a certain topic. These approaches appear too weak to cope with such a vast amount of information and with such a rich human expressiveness. Our approach to Web information retrieval consists in merging different available technologies and paradigms: mobile computation is exploited as effective approach to obtain updated results by dispatching the agents directly on Web resources. Agents are equipped with deductive behavior so to be autonomous in applying inference-based reasoning. A similarity model is embedded into the reasoning engine in order to correctly process the approximation level established at user level side.

This paper presents an extension of SLD resolution towards approximate reasoning. The proposed refutation procedure overcomes failures in the unification process by exploiting similarity relation defined between predicate and constant symbols. This enables to compute approximate solutions, with an associated approximation degree, when failures of the exact inference process occur. In this paper we outline the main ideas of this approach and we present an extended PROLOG interpreter, named SiLog, which implements this inference procedure.

Software agents are programs designed to perform tasks autonomously. Mail agents attempt to provide useful functions about electronic mail (E-mail) services, such as information filtering, gathering, and scheduling. The diffusion of the Internet has multiplied the amount of data and the number of information sources so the qualities that made E-mail so popular are now becoming a problem (e.g. the volume of junk or spam mail). Industrial as well as academic research has faced this problem in terms of automated filtering methods in order to distinguish, at the receiver-side, legitimate E-mail from spamming. We describe an alternative approach: our mail system is able to find, at the sender-side, "appropriate" destinations for a message by triggering a spidering process on (a portion of) the Web. This process performs distributed computation using mobile agents: by applying similarity-based reasoning on information extracted from the Web pages of potential addressees, the agents are able to compute a numeric value in [0, 1] which provides, for any address, a measure of the "interest" in receiving the E-mail.