Carmelo Pino

Feeding back learning resources repurposing patterns into the “information loop”: opportunities and challenges

The paper outlines a model for framing the representation and treatment of information gathered from the reuse and repurposing of learning resources from distributed repositories. The model takes into account as sources of information both static user-edited or automatically generated metadata fields and the emerging, dynamic information clouds that surrounds a learning resource when users comment on it, tags it, or explicitly links it to other learning resources. By coordinating these separate information layers, the advantages that can be achieved are reducing the semantic gap occurring when unanticipated contexts of use are to be described by resorting only to predefined vocabularies; and improvements in the relevance of the retrieved resources after a query. To achieve this “coordination” it is proposed that the textual descriptions of the repurposing activity with respect to the intended learning outcomes and pedagogical strategies are fed to a dynamic unsupervised classification method that operates on the above mentioned information spaces, and that supports exploratory search by suggesting associations. It is argued that the proposed analogical retrieval, as opposed to standard query matching, is more fit to tracking the loci of innovation and sustaining the formation of best practices in the community.

Content based recommender system by using eye gaze data

In this work, we present a proactive content based recommender system that employs web document clustering performed by using eye gaze data. Generally, recommender systems are used in commercial applications, where information about the users habits and interests are of crucial importance in order to plan marketing strategies, or in information retrieval systems in order to suggest similar resources a user is interested in. Commonly, these systems use explicit relevance feedback techniques (e.g. mouse or keyboard) to improve their performance and to recommend products. In contrast, the proposed system permits to capture users interest by using implicit relevance feedback, based on data acquired by an eye tracker Tobii T60. The purpose of the system is to collect eye gaze data during web navigation and, by employing clustering techniques, to suggest web documents similar to those that the user, implicitly, expressed greater interest. Performance evaluation was carried out on 30 users and the results show that the proposed system enhanced navigation experience in about 73% of the cases.

A semantic-based and adaptive architecture for automatic multimedia retrieval composition

In this paper we present a domain-independent multimedia retrieval (MMR) platform. Currently, the use of MMR systems for different domains poses several limitations, mainly related to the poor flexibility and adaptability to different domains and user requirements. A semantic-based platform that uses ontologies for describing not only the application domain but also the processing workflow to be followed for the retrieval, according to users requirements and domain characteristics is here proposed. In detail, an ontological model (domain-processing ontology) that integrates domain peculiarities and processing algorithms allows self-adaptation of the retrieval mechanism to the specified application domain. According to the instances generated for each user request, our platform generates the appropriate interface (GUI) for the specified application domain (e.g. music, sport video, medical images, etc…) by a procedure guided by the defined domain-processing ontology. A use case on content based music retrieval is here presented in order to show how the proposed platform also facilitates the process of multimedia retrieval system implementation.

Mobile cyber physical systems for health care: Functions, ambient ontology and e-diagnostics

In recent decades, people, especially the older ones, try to live at home in autonomous way. For this purpose it is useful to monitor their vital signs and the home environment to activate suitable environment regulation and to send alarms to family members, medical, or hospitals, according to the criticality of the subject. The paper aims at proposing a flexible and reliable monitoring system based on embedded systems and wearable devices. The system main feature is that it allows the doctor and family members to monitor the patients at distance using their mobiles. A suitable communication with the first aid center is foreseen for a fast rescue of the patients in case of critical situations. A user model ontology is adopted so that patient and context data may be used by any diagnostic and first aid software, thus envisaging an open and interoperable health monitoring system for elderly people living at home. A diagnostic system based on fuzzy rules is proposed to support the choice of the best course of actions in case of critical health conditions.

Eye tracker based method for quantitative analysis of pathological nystagmus

In this paper we propose a method for quantitative assessment of pathological nystagmus by using eye gaze data recorded with an eye tracker (Tobii T60). In detail, we use data acquired while patients perform two tests, the smooth pursuit and the saccadic movement test (implemented on the Tobii T60 using its API), that may indicate altered ophthalmic functions typical of the pathological nystagmus. Afterwards, data is analyzed by using statistical, spectral and chaotic methods in order to provide the physicians with a useful tool for assessing quantitatively the severity (or the presence) of the pathological nystagmus. A pilot study carried out on a set of 15 patients is here reported for a preliminary investigation of the suitability of the proposed eye tracker method.

Discovering biological knowledge by integrating high-throughput data and scientific literature on the cloud

In this paper, we present a bioinformatics knowledge discovery tool for extracting and validating associations between biological entities. By mining specialized scientific literature, the tool not only generates biological hypotheses in the form of associations between genes, proteins, miRNA and diseases but also validates the plausibility of such associations against high‐throughput biological data (e.g. microarray) and annotated databases (e.g. Gene Ontology). Both the knowledge discovery system and its validation are carried out by exploiting the advantages and the potentialities of the Cloud, which allowed us to derive and check the validity of thousands of biological associations in a reasonable amount of time. The system was tested on a dataset containing more than 1000 gene–disease associations achieving an average recall of about 71%, outperforming existing approaches. The results also showed that porting a data‐intensive application in an Infrastructure as a Service cloud environment boosts significantly the applications efficiency. Copyright

GeoSentiment: A tool for analyzing geographically distributed event-related sentiments

In this demo paper we present GeoSentiment, a tool for effective assessment and visualization of event-related sentiments in geographically confined populations. GeoSentiment is developed as a web tool application and provides to stakeholders an easy-to-use and powerful means to investigate how events are perceived by people and which factors may influence such perception. GeoSentiment relies on different services for a) retrieving and mining official statistical information as well as the most-common social networks and b) performing sentiment analysis. It is provided with an interactive interface, which enables rendering and deep exploration of all the processed data and results.

Automatic 3D segmentation of mandible for assessment of facial asymmetry

This paper presents an vision-based approach to support orthodontists in assessing facial asymmetry by means of: 1) a fully automatic 3D mandible segmentation method which works on CT (Computer Tomography) scans and 2) surface measurements between user-defined landmarks located on the reconstructed surface. The proposed method shows several advantages with respect to the conventional techniques: it is much faster since manual segmentation of the areas of interest on the CT 2D slices is not needed and perform surface measurements instead of simply computing linear distances as carried out by other 3D methods. The results showed that the measurements obtained by our method are compatible with the ones obtained by two experts using a digital caliper on 10 CT scans.

An Interactive Tool for Customizing Clinical Transacranial Magnetic Stimulation (TMS) Experiments

Transcranial magnetic stimulation (TMS) is a very useful technique for neurophysiological and neuropsychological investigations. In this paper we propose a user-friendly and a fully customizable system that allows experimental control, data recording for all the currently used TMS paradigms (single and paired pulse TMS). This system consists of two parts: 1) a user-interface that allows the medical doctors to customize the settings of their experiments and to include post-processing and statistical tools for analyzing the acquired patients data, and 2) a hardware-interface that communicates with the existing TMS equipment. New algorithms for post-processing and new user settings can be easily added without interfering with the hardware part communication. The proposed system was used for conducting a clinical experiment for estimating patterns of cortical excitability in patients with geriatric depression and subcortical ischemic vascular disease, achieving very interesting results from the medical point of view.

A Semantic-Based Platform for Medical Image Storage and Sharing Using the Grid

Since the introduction of medical imaging techniques such as MRI, X-Ray, SPECT, PET, large amounts of medical images have been produced in the different fields of medicine. Most of this data is usually stored either in paper format (stored in clinical records) or in optical disks (given to the patients) and this information is partially uncorrelated with the clinical history of patients. Furthermore, the image processing carried out by the physicians that perform the exam and used to make the diagnosis is unknown for other researchers that further treat the same image. In this paper we propose a system that allows radiologists to share medical images (and their processing) and the associated metadata both within the same medical institute and with other medical institutes located anywhere in the world by using GRID services for data (LFC) and metadata (AMGA) storage. The system is also provided with a semantic layer for describing the stored images through a novel RDF schema, which integrates existing ontologies and vocabularies such as FOAF, Mesh and GeneOntology with new terms related to the image processing part. This enables the correlation of medical images with other clinical information and makes our system fully compatible with the existing systems compliant to semantic web standards.