Search

Motivation: The scientific literature embeds an enormous amount of relational knowledge, encompassing interactions between biomedical entities, like proteins, drugs, and symptoms. To cope with the ever-increasing number of publications, researchers are experiencing a surge of interest in extracting valuable, structured, concise, and unambiguous information from plain texts. With the development of deep learning, the granularity of information extraction is evolving from entities and pairwise relations to events. Events can model complex interactions involving multiple participants having a specific semantic role, also handling nested and overlapping definitions. After being studied for years, automatic event extraction is on the road to significantly impact biology in a wide range of applications, from knowledge base enrichment to the formulation of new research hypotheses. Results: This paper provides a comprehensive and up-to-date survey on the link between event extraction and natural language understanding, focusing on the biomedical domain. First, we establish a flexible event definition, summarizing the terminological efforts conducted in various areas. Second, we present the event extraction task, the related challenges, and the available annotated corpora. Third, we deeply explore the most representative methods and present an analysis of the current state-of-the-art, accompanied by performance discussion. To help researchers navigate the avalanche of event extraction works, we provide a detailed taxonomy for classifying the contributions proposed by the community. Fourth, we compare solutions applied in biomedicine with those evaluated in other domains, identifying research opportunities and providing insights for strategies not yet explored. Finally, we discuss applications and our envisions about future perspectives, moving the needle on explainability and knowledge injection.

Knowledge modelling techniques based on knowledge graphs can be used in the context of building customized and flexible e-learning systems to provide learning resources that are accessible to anyone, including learners with special needs and accessibility preferences. The paper describes how a personalized educational resource system that considers the needs of learners, especially when it comes to learners with accessibility needs, can benefit from knowledge graph-based technologies used as resource representation formalism. Knowledge graphs can be used to provide learners with suitable learning objects, learning activities, and teaching methods based on their different preferences and needs and to perform domain knowledge reasoning through modelled domain knowledge.

During the COVID-19 pandemic, there has been a significant increase in the use of non-contact infrared devices for screening the body temperatures of people at the entrances of hospitals, airports, train stations, churches, schools, shops, sports centres, offices, and public places in general. The strong correlation between a high body temperature and SARS-CoV-2 infection has motivated the governments of several countries to restrict access to public indoor places simply based on a person’s body temperature. Negating/allowing entrance to a public place can have a strong impact on people. For example, a cancer patient could be refused access to a cancer centre because of an incorrect high temperature measurement. On the other hand, underestimating an individual’s body temperature may allow infected patients to enter indoor public places where it is much easier for the virus to spread to other people. Accordingly, during the COVID-19 pandemic, the reliability of body temperature measurements has become fundamental. In particular, a debated issue is the reliability of remote temperature measurements, especially when these are aimed at identifying in a quick and reliable way infected subjects. Working distance, body–device angle, and light conditions and many other metrological and subjective issues significantly affect the data acquired via common contactless infrared point thermometers, making the acquisition of reliable measurements at the entrance to public places a challenging task. The main objective of this work is to sensitize the community to the typical incorrect uses of infrared point thermometers, as well as the resulting drifts in measurements of body temperature. Using several commercial contactless infrared point thermometers, we performed four different experiments to simulate common scenarios in a triage emergency room. In the first experiment, we acquired several measurements for each thermometer without measuring the working distance or angle of inclination to show that, for some instruments, the values obtained can differ by 1 °C. In the second and third experiments, we analysed the impacts of the working distance and angle of inclination of the thermometers, respectively, to prove that only a few cm/degrees can cause drifts higher than 1 °C. Finally, in the fourth experiment, we showed that the light in the environment can also cause changes in temperature up to 0.5 °C. Ultimately, in this study, we quantitatively demonstrated that the working distance, angle of inclination, and light conditions can strongly impact temperature measurements, which could invalidate the screening results.

The design and construction of personalized and flexible e-learning systems can benefit from the use of sophisticated knowledge modeling and data-analysis techniques to provide learning resources that are accessible by anyone, including learners with special accessibility needs and preferences. The paper describes a personalized educational resources system that considers learner's needs, especially when it comes to learners with accessibility requirements. We use Semantic Web technologies as resource representation formalism to provide learners with suitable learning objects, learning activities, and teaching methods based on their different preferences and needs. The system supports the creation of interactive semantic queries to bring the result sets closer to user research requirements.

Rare diseases pose particular challenges to patients, families, caregivers, clinicians and researchers. Due to the scarce availability of information and their disintegration, in recent years we are witnessing a strong growth of patient communities on social platforms such as Facebook. Although the data generated in this context are of high value, the currently existing ontologies and resources tend to ignore them. The work presented in this paper studies how to extract knowledge from the large availability of unstructured text generated by the users over time, in order to represent it in an organized way and to make logical reasoning above. Starting from the awareness of the need to integrate different methodologies in complex domains, the research shows a combined use of Text Mining and Semantic Web techniques. In particular, we describe the basis of a novel approach for Knowledge Graph Learning with the aim of introducing a patient-centered vision into the world of Linked Open Data. By identifying and representing correlations between concepts of interest, we show how it is possible to answer patients’ questions and provide them with an additional tool for decision making. The outlined contribute minimizes costs through automatic data retrieval and increases the productivity of investigators.

Currently, several datasets released in a Linked Open Data format are available at a national and international level, but the lack of shared strategies on the representation and meaning of knowledge related to the publishing community makes it difficult to compare and use them. The paper proposes the use of semantic technologies and linked open data in order to ensure standardized frameworks for the representation of concepts in policy-making. The low-level data can thus be transformed into an enriched information model that allows its reuse and a logical reasoning on the knowledge representation.

Leadership has increasingly become a major research focus in the corporate sector as well as in the higher education sector (HES). However, there is a lack of clear understanding of how leadership and potential features and benefits of Information and Communications Technology (ICT) interact together in the HES context and how to lead most effectively within our emerging volatile, uncertain, complex, and ambiguous (VUCA) learning environments. The intrinsic potential of the available educational datasets can be exploited using sophisticated data-analysis techniques such as automatic reasoning to find patterns and extract information and knowledge in order to enhance decision-making and deliver better learning resources to the users. Moreover, education information sharing and analysis in conjunction with non-traditional data sources (e.g., social media, web content, and linked data) can provide an important component to facilitating the development of the next generation of VUCA learning services, in particular, personalisation and inference reasoning. A conceptual chapter is presented for the purpose of analysing HES organization-environment relations. The theoretical umbrella adopted here is the linked data (LD) and semantic web (SW) theories -- a promising solution for the integration and exploitation of HES data about students, resources, courses, syllabi, and institutions. SW describes a new way to make resource content more meaningful to machines, whereas the meaning of data is provided using ontologies.The use of SW technologies as data representation formalism enables the creation of a common model, thus interconnecting a variety of heterogeneous data sources. Volatility, uncertainty, ambiguity, and complexity can be managed using technologies related to the representation of LD and SW.

Mobile platforms have matured to a point where they can provide the infrastructure required to support sophisticated optimization codes. This opens the possibility to envisage new interest for distributed application codes and the opportunity to intensify research on optimization algorithms requiring limited computational resources, as provided by mobile platforms. In this article, we report on some exploratory experience in this area. We illustrate some practical, real-world cases where running optimization programs on mobile or embedded devices can be useful, with particular emphasis on matheuristics approaches. Then, we discuss a practical use case involving the feasibility version of the generalized assignment problem (GAP). We present a JavaScript implementation of a GAP solver that can be executed inside an ordinary browser supporting ECMAScript. We tested the code on different smartphones of varying age and power, as well as on desktop PCs and other embedded devices. Our experiments confirm the viability of mobile devices for computational intensive tasks.

The huge volume of data gathered from wearable fitness devices and wellness appliances, if effectively analysed and integrated, can be exploited to improve clinical decision making and to stimulate promising applications, as they can provide good measures of everyday patient behaviour and lifestyle. However, several obstacles currently limit the true exploitation of these opportunities. In particular, the healthcare landscape is characterised by a pervasive presence of data silos which prevent users and healthcare professionals from obtaining an overall view of the knowledge, mainly due to the lack of device interoperability and data representation format heterogeneity. This work focuses on current, important needs in self-tracked health data modelling, and summarises challenges and opportunities that will characterise the community in the upcoming years. The paper describes a virtually integrated approach using standard Web Semantic technologies and Linked Open Data to cope with heterogeneous health data integration. The proposed approach is verified using data collected from several IoT fitness vendors to form a standard context-aware resource graph, and linking other health ontologies and open projects. We developed a web portal for integrating, sharing and analysing through a customisable dashboard heterogeneous IoT health and fitness data. In this way, we are able to map information onto an integrated domain model by providing support for logical reasoning.

Nowadays, healthcare is becoming increasingly connected and increasingly complex. These changes provide opportunities and challenges to the research community. For instance, the enormous volume of data gathered from IoT wearable fitness devices and wellness appliances, if effectively analysed and understood, can be exploited to improve people’s well-being and identify predictive markers of future diseases. However, due to the lack of devices interoperability and heterogeneity of data representation formats, the IoT healthcare landscape is characterised by a pervasive presence of ”data silos” which prevents users and health practitioners from obtaining an overall view of whole knowledge. Semantic web technologies, such as ontologies and inference rules, have been shown as a promising way for the integration and exploitation of data from heterogeneous sources. In this paper, we present a semantic data model useful to: (a) analyse information from unstructured data sources along with generic or domain specific datasets; (b) unify them in an interlinked data processing area. The proposed semantic eHealth system enables automatic inferences and logical reasoning, and can significantly facilitate reuse, exploitation and possible extension of IoT health data sources. . Nowadays, healthcare is becoming increasingly connected and increasingly complex. These changes provide opportunities and challenges to the research community. For instance, the enormous volume of data gathered from IoT wearable fitness devices and wellness appliances, if effectively analysed and understood, can be exploited to improve peo-ple’s well-being and identify predictive markers of future diseases. However, due to the lack of devices interoperability and heterogeneity of data representation formats, the IoT healthcare landscape is characterised by a pervasive presence of “data silos” which prevents users and health practitioners from obtaining an overall view of whole knowledge. Semantic web technologies, such as ontologies and inference rules have been shown as a promising way for the integration and exploitation of data from heterogeneous sources. In this paper, we present a semantic data model useful to: (a) analyse information from unstructured data sources along with generic or domain specific datasets; (b) unify them in an interlinked data processing area. The proposed semantic eHealth system enables automatic inferences and logical reasoning, and can significantly facilitate reuse, exploitation and possible extension of IoT health data sources.

Though the strong evolution of knowledge learning models has characterized the last few years, the explanation of a phenomenon from text documents, called descriptive text mining, is still a difficult and poorly addressed problem. The need to work with unlabeled data, explainable approaches, unsupervised and domain independent solutions further increases the complexity of this task. Currently, existing techniques only partially solve the problem and have several limitations. In this paper, we propose a novel methodology of descriptive text mining, capable of offering accurate explanations in unsupervised settings and of quantifying the results based on their statistical significance. Considering the strong growth of patient communities on social platforms such as Facebook, we demonstrate the effectiveness of the contribution by taking the short social posts related to Esophageal Achalasia as a typical case study. Specifically, the methodology produces useful explanations about the experiences of patients and caregivers. Starting directly from the unlabeled patient’s posts, we derive correct scientific correlations among symptoms, drugs, treatments, foods and so on.

Fitness sensors and health systems are paving the way toward improving the quality of medical care by exploiting the benefits of new technology. For example, the great amount of patient-generated health data available today gives new opportunities to measure life parameters in real time and create a revolution in communication for professionals and patients. In this work, we concentrated on the basic parameter typically measured by fitness applications and devices&mdash, the number of steps taken daily. In particular, the main goal of this study was to compare the accuracy and precision of smartphone applications versus those of wearable devices to give users an idea about what can be expected regarding the relative difference in measurements achieved using different system typologies. In particular, the data obtained showed a difference of approximately 30%, proving that smartphone applications provide inaccurate measurements in long-term analysis, while wearable devices are precise and accurate. Accordingly, we challenge the reliability of previous studies reporting data collected with phone-based applications, and besides discussing the current limitations, we support the use of wearable devices for mHealth.

The huge amounts of self-tracked health data collected by Internet of Things (IoT) fitness devices offer important opportunities to the research community. If properly exploited, IoT health and fitness datasets can help to gain valuable insights into the human health in order to provide better healthcare.However, IoT health data come from a variety of different heterogeneous sources and in proprietary formats, which means that they require an integration process, normally manually done by domain experts, in order to be analysed. This task is not only significantly time consuming but in many cases, error prone.In this study, we designed and developed a web platform for collecting and publishing IoT health and fitness datasets according to Linked Data principles. We leveraged the IFO ontology and the Semantic Web technologies to make the IoT health and fitness datasets freely available to the community in a shared, semantically meaningful, easily discoverable, and reusable manner.The system introduced in this article shows that Semantic Web technologies can be a viable and comprehensive solution for describing, integrating and sharing heterogeneous IoT datasets, thus overcoming the issues of data silos that nowadays dominate the IoT landscape.

Ontologies play an important role in knowledge-intensive contexts such as nutrition, personalised dietary, diet-sensitive disease conditions management and sport activities. Ontologies offer a shared data model for concept integration making possible to actuate automatic data analysis processes such as inference reasoning and allow interoperable communication among heterogeneous systems. In this paper, we propose Food Data Manager, a dietary consultation system which aims to improve the life quality of both healthy people and individuals affected by chronic diet-related diseases. Food Data Manager is an ontology-based system whereby we can automatically reason with food and its properties through inference engines in order to better assist users in making the correct choices for their particular health status, age, lifestyle, preferences, etc. In particular, we developed a set of semantic rules to transfer human dietary and nutrition expertise into machine understandable knowledge.

Transport systems need to represent and analyze data from multiple sources and networks to dynamically respond to demands and operate more efficiently. But deploying ad-hoc platforms could be very expensive and ineffective in the long run. It is preferable to focus on data availability and smart data analysis and to develop interoperability strategies suitable for smart mobility based on open standards and allowing seamless integration of third-party systems and custom applications. This paper highlights the opportunity to take advantage of emerging technologies, like the open-source data platforms and to use services for data linked queries in cities, and especially in the domain of smart mobility systems.

In knowledge intensive nutrition-related contexts, such as personalised dietary, diet-sensitive diseases management and sport supplementation, ontologies play an important role. In this paper, we propose an ontology-based consultation system which aims to improve the life quality of both healthy people and individuals affected by chronic diet-related diseases. We developed a system which is capable of transferring human dietary and nutrition expertise into machine understandable knowledge through a set of semantic rules in order to better assist users in making the correct nutritional choices for their particular health status, age, lifestyle and food preferences. Our system makes use of open data, published ontologies, domain knowledge and IoT data to construct a domain representation consisting of unified concepts and instances suitable for reasoning processes. We described how several knowledge bases in knowledge-intensive contexts can be integrated to provide a unified structured and precise representation of heterogeneous information to provide better diet recommendation to individuals.

Nowadays, the enormous volume of health and fitness data gathered from IoT wearable devices offers favourable opportunities to the research community. For instance, it can be exploited using sophisticated data analysis techniques, such as automatic reasoning, to find patterns and, extract information and new knowledge in order to enhance decision-making and deliver better healthcare. However, due to the high heterogeneity of data representation formats, the IoT healthcare landscape is characterised by an ubiquitous presence of data silos which prevents users and clinicians from obtaining a consistent representation of the whole knowledge. Semantic web technologies, such as ontologies and inference rules, have been shown as a promising way for the integration and exploitation of data from heterogeneous sources. In this paper, we present a semantic data model useful to: (1) consistently represent health and fitness data from heterogeneous IoT sources; (2) integrate and exchange them; and (3) enable automatic reasoning by inference engines.

Currently, several datasets released in a Linked Open Data format are available at a national and international level, but the lack of shared strategies concerning the definition of concepts related to the statistical publishing community makes difficult a comparison among given facts starting from different data sources. In order to guarantee a shared representation framework for what concerns the dissemination of statistical concepts about graduates, we developed SW4AL, an ontology- based system for graduate’s surveys domain. The developed system transforms low-level data into an enriched information model and is based on the AlmaLaurea surveys covering more than 90% of Italian graduates. SW4AL: i) semantically describes the different peculiarities of the graduates; ii) promotes the structured definition of the AlmaLaurea data and the following publication in the Linked Open Data context; iii) provides their reuse in the open data scope; iv) enables logical reasoning about knowledge representation. SW4AL establishes a common semantic for addressing the concept of graduate’s surveys domain by proposing the creation of a SPARQL endpoint and a Web based interface for the query and the visualization of the structured data.

With the blooming of data created for example by IoT devices, the possibility to handle all information coming from healthcare applications is becoming increasingly challenging. Cognitive computing systems can be used to analyse large information volume by providing insights and recommendations to represent, access, integrate, and investigate data in order to improve outcomes across many domains, including healthcare. This paper presents an ontology-based system for the eHealth domain. It provides semantic interoperability among heterogeneous IoT devices and facilitates data integration and sharing. The novelty of the proposed approach lies in exploiting semantic web technologies to explicitly describe the meaning of sensor data and define a common communication strategy for information representation and exchange.

Route following based on visual landmark matching may require many models to cover all different situations. This paper describes a system that is able to adapt template's modelling parameters to environmental conditions (lighting, shadows, etc.) by a genetic learning technique. In addition, the mobile robot self-localisation is obtained by a stereo approach that uses the centres of matching in the two images to solve in a simple way the correspondence problem in the 3D position estimation. The experimental results show that the tracking robustness is improved, while using a small set of templates. © 1998 Elsevier Science B.V. All rights reserved.

The paper presents a web based system that aims to improve Web exploration by enabling users to discover knowledge associated to his need. Indeed, in exploratory search, the user is willing not only to find documents relevant with respect to his query but he is also interested in learning, discovering and understanding knowledge on complex and sometimes unknown topics. We rely on DBpedia to explore the semantics of keywords thus suggesting potentially interesting related topics or keywords to the user and enabling user-friendly and intelligent content discovery.

The Semantic Web offers a generic infrastructure for interchange, integration and creative reuse of structured data, which can help to cross some of the boundaries that Web 2.0 is facing. Currently, Web 2.0 offers poor query possibilities apart from searching by keywords or tags. There has been a great deal of interest in the development of semantic-based systems to facilitate knowledge representation and extraction and content integration [1], [2]. Semantic-based approach to retrieving relevant material can be useful to address issues like trying to determine the type or the quality of the information suggested from a personalized environment. In this context, standard keyword search has a very limited effectiveness. For example, it cannot filter for the type of information, the level of information or the quality of information. Potentially, one of the biggest application areas of content-based exploration might be personalized searching framework (e.g., [3],[4]). Whereas search engines provide nowadays largely anonymous information, new framework might highlight or recommend web pages related to key concepts. We can consider semantic information representation as an important step towards a wide efficient manipulation and retrieval of information [5], [6], [7]. In the digital library community a flat list of attribute/value pairs is often assumed to be available. In the Semantic Web community, annotations are often assumed to be an instance of an ontology. Through the ontologies the system will express key entities and relationships describing resources in a formal machine-processable representation. An ontology-based knowledge representation could be used for content analysis and object recognition, for reasoning processes and for enabling user-friendly and intelligent multimedia content search and retrieval. Text summarization has been an interesting and active research area since the 60’s. The definition and assumption are that a small portion or several keywords of the original long document can represent the whole informatively and/or indicatively. Reading or processing this shorter version of the document would save time and other resources [8]. This property is especially true and urgently needed at present due to the vast availability of information. Concept-based approach to represent dynamic and unstructured information can be useful to address issues like trying to determine the key concepts and to summarize the information exchanged within a personalized environment. In this context, a concept is represented with a Wikipedia article. With millions of articles and thousands of contributors, this online repository of knowledge is the largest and fastest growing encyclopedia in existence. The problem described above can then be divided into three steps: • Mapping of a series of terms with the most appropriate Wikipedia article (disambiguation). • Assigning a score for each item identified on the basis of its importance in the given context. • Extraction of n items with the highest score. Text summarization can be applied to many fields: from information retrieval to text mining processes and text display. Also in personalized searching framework text summarization could be very useful. The chapter is organized as follows: the next Section introduces personalized searching framework as one of the possible application areas of automatic concept extraction systems. Section three describes the summarization process, providing details on system architecture, used methodology and tools. Section four provides an overview about document summarization approaches that have been recently developed. Section five summarizes a number of real-world applications which might benefit from WSD. Section six introduces Wikipedia and WordNet as used in our project. Section seven describes the logical structure of the project, describing software components and databases. Finally, Section eight provides some consideration...

The process of summarizing information is becoming increasingly important in the light of recent advances in resource creation and distribution and the resulting influx of large numbers of information in everyday life. These advances are also challenging educational institutions to adopt the opportunities of distributed knowledge sharing and communication. The chapter presents a summarization system to support tutor in managing student communication and interaction within a learning framework. Results show the adequacy of the system in identifying a good content summarization and then in improving the efficiency and effectiveness of the context in which summarization can be integrated.

The process of summarizing information is becoming increasingly important in the light of recent advances in resource creation and distribution and the resulting influx of large numbers of information in everyday life. These advances are also challenging educational institutions to adopt the opportunities of distributed knowledge sharing and communication. Among the most recent trends, the availability of social communication networks, knowledge representation and of activate learning gives rise for a new landscape of learning as a networked, situated, contextual and life-long activities. In this scenario, new perspectives on learning and teaching processes must be developed and supported, relating learning models, content-based tools, social organization and knowledge sharing.

The paper presents an ontological approach for enabling personalized searching framework facilitating the user access to desired contents. Through the ontologies the system will express key entities and relationships describing resources in a formal machine-processable representation. An ontology-based knowledge representation could be used for content analysis and concept recognition, for reasoning processes and for enabling user-friendly and intelligent content retrieval.

The paper presents an ontological approach for enabling semantic-aware information retrieval and browsing framework facilitating the user access to its preferred contents. Through the ontologies the system will express key entities and relationships describing learning, material in a formal machine-processable representation. An ontology-based knowledge representation could be used for content analysis and concept recognition, for reasoning processes and for enabling user-friendly and intelligent multimedia content search and retrieval.

Active learning is the ability of learners to carry out learning activities in such a way that they will be able to effectively and efficiently construct knowledge from information sources. Personalized and customizable access on digital materials collected from the Web according to one’s own personal requirements and interests is an example of active learning. Moreover, it is also necessary to provide techniques to locate suitable materials. In this chapter, we introduce a personalized learning environment providing intelligent support to achieve the expectations of active learning. The system exploits collaborative and semantic approaches to extract concepts from documents, and maintaining user and resources profiles based on domain ontologies. In such a way, the retrieval phase takes advantage of the common knowledge base used to extract useful knowledge and produces personalized views of the learning system.

In this paper we introduce an update of our work on developing a distance-learning environment based on a collaborative bookmark management system approach. We introduce EasyInfo, an hybrid recommender architecture extension, which processes resources to extract concepts (not just words) from the documents using semantic capabilities. Then, the classification, recommendation and sharing phases take advantage of the word senses to classify, retrieve and suggest documents with high semantic relevance with respect to the student and resource models.

In the last years Intelligent Tutoring Systems have been a very successful way for improving learning experience. Many issues must be addressed until this technology can be defined mature. One of the main problems within the Intelligent Tutoring Systems is the process of contents authoring: knowledge acquisition and manipulation process is a difficult task because it requires specialized skills on computer programming and knowledge engineering. In this paper we propose a mechanism based on first order data mining to partially automate the process of knowledge acquisition. The knowledge has to be used in the ITS during the tutoring process for personalized instruction. Such a mechanism can be applied in Constraint Based Tutor and in the Pseudo-Cognitive Tutor.

In this chapter, we introduce how to use a Web-based hybrid recommender system developed with a collaborative bookmark management system approach. The system combines content analysis and the development of virtual clusters of students and educational sources. It provides facilitation in the use of a huge amount of digital information stored in a distributed learning environment on the basis of the student’s personal requirements and interests. By adopting a hybrid approach, the system is able to effectively filter relevant resources from a wide heterogeneous environment like the Web, taking advantage of the common interests of the users and also maintaining the benefits provided by content analysis. The basic idea is to appropriately help students classifying domain-specific information found on the Web and saved as bookmarks, to recommend these documents to other students with similar interests, and to notify users periodically about new, potentially interesting documents. Documents are represented using metadata model.

We propose a hybrid recommender system, InLinx, that combines content analysis and the development of virtual clusters of students and of didactical sources providing facilities to use the huge amount of digital information according to the student's personal requirements and interests. Novel methods for information management, with special focus on the development of new algorithms and intelligent applications for personalized information sharing, filtering and retrieval is proposed. InLinx helps the student to classify domain specific information found in the Web and saved as bookmarks, to recommend these documents to other students with similar interests and to periodically notify new potentially interesting documents. © 2003 IEEE.

The paper presents the guidelines of a project of three Italian Universities (Bologna, Siena, Trento) which aim is to investigate the use of mobile computing technologies to support the learning processes in a University context. The project covers three main areas. The first area is concerned with finding effective models for mobile learning. The second regards the evaluation of learning processes in mobile learning environments. The third focuses on the technological aspects of mobile learning, and on their integration with e-Learning systems, and more generally, with the information systems of the academic institutions. The project has its foundations in the availability of significant experience on e-learning real processes, and on the availability of the source code of an e-learning system developed in previous projects and currently used by different faculties, and of the newer platform that gathers the experience obtained in the past.

The paper describes a prototypical system for optimal landmark acquisition and selection. Our landmark-learning approach does not require any type of environment model to be supplied to the robot in advance, and represents a step towards robots interacting with real environments. The approach is fitted and tested for the TMGA system (P. Zingaretti et al., 1998), which the authors developed for landmark tracking by adaptive, stereo template matching. Two complementary strategies, properly managed, are followed to construct a suitable subset of landmarks: the selection of the more discriminant landmarks and the selection of the landmarks that are more invariant in a neighbourhood. The robustness of the TMGA system in analysing the discriminant power of each landmark and the analysis of the disparity map and of the spatial activity maps of the stereo images are used for identifying discriminant and invariant landmarks. The experimental results show that the number of matching failures, and consequent landmark changes during the following of a route is comparable with (not much greater than) those obtained using an a-priori subset.

The rising auto usage deriving from growth in jobs and residential population is making traffic congestion less tolerable in urban and suburban areas. This results in air pollution, energy waste and unproductive and unpleasant consumption of people’s time. Public transport cannot be the only answer to this increasing transport demand. Car pooling has emerged to be a viable possibility for reducing private car usage in congested areas. Its actual practice requires a suitable information system support and, most important, the capability of effectively solving the underlying combinatorial optimization problem. This paper presents an application of the ANTS approach, one of the approaches which follow the Ant Colony Optimization (ACO) paradigm, to the car pooling optimization problem. Computational results are presented both on datasets derived from the literature about problems similar to car pooling and on real-world car pooling instances.

With the aim to individualise human-computer interaction, an Intelligent Tutoring System (ITS) has to keep track of what and how the student has learned. Hence, it is necessary to maintain a Student Model (SM) dealing with complex knowledge representation, such as incomplete and inconsistent knowledge and belief revision. With this in view, the main objective of this paper is to present and discuss the student modelling approach we have adopted to implement Pitagora 2.0, an ITS based on a co-operative learning model, and designed to support teaching-learning activities in a Euclidean Geometry context. In particular, this approach has led us to develop two distinct modules that cooperate to implement the SM of Pitagora 2.0. The first module resembles a "classical" student model, in the sense that it maintains a representation of the current student knowledge level, which can be used by the teacher in order to tune its teaching strategies to the specific student needs. In addition, our system contains a second module that implements a virtual partner, called companion. This module consists of a computational model of an "average student" which cooperates with the student during the learning process. The above mentioned module calls for the use of machine learning algorithms that allow the companion to improve in parallel with the real student. Computational results obtained when testing this module in simulation experiments are also presented. © 1995 Kluwer Academic Publishers.

The problem considered in this paper consists in assigning frequencies to radio links between base stations and mobile transmitters in order to minimize the global interference over a given region. This problem is NP-hard and few results have been reported on techniques for solving it to optimality. We have applied to this problem an ANTS metaheuristic, that is, an approach following the ant colony optimization paradigm. Computational results, obtained on a number of standard problem instances, testify the effectiveness of the proposed approach.

Ant Colony Optimization (ACO) is a class of constructive meta-heuristic algorithms sharing the common approach of constructing a solution on the basis of information provided both by a standard constructive heuristic and by previously constructed solutions. This tutorial is composed of three parts. The first one frames the ACO approach in current trends of research on metaheuristic algorithms for combinatorial optimization; the second outlines current research within the ACO framework, reporting recent results obtained on different problems, while the third part focuses on a particular research line, the ANTS metaheuristic, providing some details on the algorithm and presenting results recently obtained on the quadratic and on the frequency assignment problems.

The materialization of fragmented views in data warehouses has the objective of improving the system response time for a given workload. It represents a combinatorial optimization problem arising in the logical design of data warehouses which has so far received little attention from the optimization community. This paper describes the application of a metaheuristic approach, namely the ANTS approach, to this problem. In particular, we propose an integer programming formulation of the problem, derive an efficient lower bound and embed it in an ANTS algorithm. Preliminary computational results, obtained on the well-known TPC-D benchmark, are presented.

The paper describes a system to control vehicle accesses in restricted areas. The signalling of vehicles whose license- plates do not belong to a specific database is the aim of the system. The adaptation to different environmental conditions, and the identification of a vehicle by processing the license- plate pattern as a whole, without considering the recognition of the characters, are its two main characteristics. The system implements a recognition engine constituted by two modules. First, the system analyzes the video-recorded sequences to select a frame in which the license-plate satisfies pre-defined constraints, and extracts the license- plate template on which the matching with the model templates stored in the database will be performed. Second, vehicle identification is performed by a genetic template matching that, without requiring a high computational complexity, provides adaptation to normal environmental variations by exploiting learning capabilities. The implemented system, forced to distinguish only between authorized and unauthorized vehicles according to a threshold in the genetic fitness function, shows robust performance on Italian cars, but it is adaptable to different license-plate models, and is independent from outdoor conditions.

We describe an approach to image segmentation based on a two-layer module that is executed until a good segmentation is achieved, providing an evolution of previous segmentation results at each execution. The first layer performs a global segmentation of an image of decreasing area at each evolution by adopting a genetic algorithm learning technique to select segmentation parameters that give better results. The second layer provides the input to the next evolution by selecting the segmented regions that need further optimisation. A main goal of our system is to perform the segmentation without using neither ground-truth information nor human judgement. Thus, edge detection is performed to assess the performance of region segmentation and to guide the evolution of segmentation. Experimental results are consistent with what is observed visually.

Genetic Algorithms and Classifier Systems are often used in biologic-like and evolutionary behaviors’ simulations. The basic example is Wood7 Wilson’s world. In this environment it is interesting to study some problems: Can evolve the cooperative behaviors of organisms present in the world? How and when do the behaviors evolve? Some preliminary results show the conditions under that cooperative behavior rules are developing rapidly. Particularly we have pointed out the likely of following observations: a. The cooperative behavior develops more easily if the initial population start from the same point. b. It exists some thresholds under that the cooperative behavior can’t evolve; these thresholds depend to the population size.

The paper presents an ontological approach for enabling semantic-aware video retrieval framework facilitating the user access to desired contents. Through the ontologies, the system will express key entities and relationships describing videos in a formal machine-processable representation. An ontology-based knowledge representation could be used for content analysis and concept recognition, for reasoning processes and for enabling user-friendly and intelligent multimedia content retrieval.

The use of knowledge graphs (KGs) in advanced applications is constantly growing, as a consequence of their ability to model large collections of semantically interconnected data. The extraction of relational facts from plain text is currently one of the main approaches for the construction and expansion of KGs. In this paper, we introduce a novel unsupervised and automatic technique of KG learning from corpora of short unstructured and unlabeled texts. Our approach is unique in that it starts from raw textual data and comes to: i) identify a set of relevant domain-dependent terms; ii) extract aggregate and statistically significant semantic relationships between terms, documents and classes; iii) represent the accurate probabilistic knowledge as a KG; iv) extend and integrate the KG according to the Linked Open Data vision. The proposed solution is easily transferable to many domains and languages as long as the data are available. As a case study, we demonstrate how it is possible to automatically learn a KG representing the knowledge contained within the conversational messages shared on social networks such as Facebook by patients with rare diseases, and the impact this can have on creating resources aimed to capture the “voice of patients”.

This paper proposes an ontological approach for enabling semantic-aware video content annotation and retrieval in order to facilitate content video analysis. Semantic Web ontologies express key entities and relationships which describe videos in a formal machine-processable representation. Ontology-based knowledge representation systems can be used for content analysis, concept recognition, reasoning processes and for enabling user-friendly and intelligent multimedia content retrieval, thus meeting the challenges of video analysis.

A system for landmark tracking by a template matching approach is described. Route following based on landmarks may require many models to cover all different situations, so a genetic algorithm learning technique is used to adapt modelling parameters to environmental conditions (lighting, shadows, reflexes, etc.) during the tracking. In addition, the mobile robot self-localisation is obtained by a stereo approach that uses the centres of matching in the two images to solve in a simple way the correspondence analysis in the 3D position estimation. The experimental results show that the tracking robustness is improved when the adaptive template matching is used for landmark tracking.

This paper describes the tracking of an object in a sequence of video-recorded images by a template matching approach based on a genetic algorithm learning technique to generate adaptive templates. The system is intended for real images. Contrary to a controlled environment, where the template may be generated from a noise free image and all successive frames do not show great changes, we hypothesise a set of images acquired at possible different environmental conditions. The varying environmental conditions greatly influence the matching, but they cannot be coded/used because they are not known a priori. In addition, 2D projections of 3D objects may vary during the sequence. Despite these difficulties, the need for robust systems that can locate objects in frame sequences is rapidly increasing due to the explosion in the amount of visual data in the communications systems.

The experience from years of development and use, the advance of technology, and the development of authoring tools for questions and tests has resulted in a sophisticated, computer based assessment system. However, there is still a lot of room for further development. Some of the current ideas for development are discussed in the remainder of this work. A primary aim of assessment, both formative and summative, is provide the necessary information to improve future educational experiences because it provides feedback on whether the course and learning objectives have been achieved to satisfactory level. Yet, it is important that the assessment data be accurate and relevant to effectively make informed decisions about the curriculum. Moreover, formative assessment can also be used to help bridge the gap between assessment and learning. This may be achieved particularly where assessment strategies are combined with useful feedback, and integrated within the learning process. The answers to the described objectives are enhanced if we could integrate adaptive testing techniques; accurate and fitted assessment data may improve both the curriculum and the student ability level. The idea behind a computerized adaptive testing (CAT) is quite forward: to apply to each examinee only those items useful to know his proficiency level. As a consequence of this, CAT is more efficient than conventional (i.e., fixeditem) tests. It provides more precise measurements for same-length tests or shorter tests for same-precision measurements.