SciTePress - Affiliation Profile

National Research Council, Italy

Context (please use complete words only)

Field

Sort by

20 Papers

A Reinforcement Learning and IoT based System to Assist Patients with Disabilities

Authors: Muddasar Naeem ¹ , Antonio Coronato ² , Giovanni Paragliola ² and Giuseppe De Pietro ²

Affiliations: ¹ Universita’ Degli Studi di Napoli Parthenope, Napoli, Italy , ² ICAR-CNR, Napoli, Italy

Digital Object Identifier: 10.5220/0009783804910498

Proceedings of AI4EIoTs 2020, ISBN: 978-989-758-426-8

Quick Abstract

One of the important aspect of clinical process is to complete treatment according to given plan. The successful completion of this task is more challenging when a person have some physical or mental disability and requires resources and man power for personalized treatment and care. We can mitigate this problem by an intelligent guidance and monitoring system who can assist elderly persons and patients in their treatment schedule. Reinforcement learning and IoT systems have received considerable credit of significant contribution in healthcare over last few years, could be suitable choice for said objective. We propose a pill reminder system using Bayesian reinforcement learning assisted with IoT devices to help people (having mental and/or physical disability) in their treatment plan. The proposed intelligent system is able to successfully communicate with the person through a suitable audio, visual and textual message. The proposed pill-reminder system has been demonstrated for a specific treatment plan of a hypertension patient.

Leveraging Machine Learning for Fake News Detection

Topics: Data Mining; Social Data Analytics

Authors: Elio Masciari , Vincenzo Moscato , Antonio Picariello and Giancarlo Sperlì

Affiliation: University Federico II, Naples, Italy

Digital Object Identifier: 10.5220/0009767401510157

Proceedings of DATA 2020, ISBN: 978-989-758-440-4

Quick Abstract

The uncontrolled growth of fake news creation and dissemination we observed in recent years causes continuous threats to democracy, justice, and public trust. This problem has significantly driven the effort of both academia and industries for developing more accurate fake news detection strategies. Early detection of fake news is crucial, however the availability of information about news propagation is limited. Moreover, it has been shown that people tend to believe more fake news due to their features (Vosoughi et al., 2018). In this paper, we present our complete framework for fake news detection and we discuss in detail a solution based on machine learning. Our experiments conducted on two well-known and widely used real-world datasets suggest that our settings can outperform the state-of-the-art approaches and allows fake news accurate detection, even in the case of limited content information.

A Machine Learning Approach for Carotid Diseases using Heart Rate Variability Features

Authors: Laura Verde ¹ and Giuseppe De Pietro ²

Affiliations: ¹ University of Naples Parthenope, Italy , ² Institute of High Performance Computing and Networking (ICAR) and National Research Council of Italy (CNR), Italy

Digital Object Identifier: 10.5220/0006730806580664

Proceedings of AI4Health 2018, ISBN: 978-989-758-281-3

Quick Abstract

In the last few years the incidence of carotid diseases has been increasing rapidly. Atherosclerosis constitutes a major cause of morbidities and mortalities worldwide. The early detection of these diseases is considered necessary to avoid tragic consequences and automatic systems and algorithms can be a valid support for their diagnosis. The main objective of this study is to investigate and compare the performances of different machine learning techniques capable of detecting the presence of a carotid disease by analysing the Heart Rate Variability (HRV) parameters of opportune electrocardiographic signals selected from an appropriate database available online on the Physionet website. All the analyses are evaluated in terms of accuracy, precision, recall and F-measure.

Preliminary Steps towards Efficient Classification in Large Medical Datasets: Structure Optimization for Deep Learning Networks through Parallelized Differential Evolution

Authors: Ivanoe De Falco ¹ , Giuseppe De Pietro ¹ , Antonio Della Cioppa ² , Giovanna Sannino ¹ , Umberto Scafuri ¹ and Ernesto Tarantino ¹

Affiliations: ¹ National Research Council of Italy (CNR), Italy , ² University of Salerno, Italy

Digital Object Identifier: 10.5220/0006730006330640

Proceedings of AI4Health 2018, ISBN: 978-989-758-281-3

Quick Abstract

Deep Neural Networks are being more and more widely used to perform several tasks over highly-sized datasets, one of them being classification. Finding good configurations for Deep Neural Network structures is a very important problem in general, and particularly in the medical domain. Currently, either trial-and-error methodologies or sampling-based ones are considered. This paper describes some preliminary steps towards effectively facing this task. The first step consists in the use of Differential Evolution, a kind of an Evolutionary Algorithm. The second lies in using a parallelized version in order to reduce the turnaround time. The preliminary results obtained here show that this approach can be useful in easily obtaining structures that allow increases in the network accuracy with respect to those provided by humans.

A FHIR-based System for the Generation and Retrieval of Clinical Documents

Topics: Electronic Health Records; Case Studies in e-Health; Diagnostic Support; Interoperability and System Integration

Authors: Crescenzo Diomaiuta , Mario Sicuranza , Mario Ciampi and Giuseppe De Pietro

Affiliation: National Research Council of Italy, Italy

Digital Object Identifier: 10.5220/0006311301350142

Proceedings of ICT4AWE 2017, ISBN: 978-989-758-251-6

Quick Abstract

Clinical information exchange among heterogeneous systems is a complex process. It is necessary to use dictionaries, coding standards (e.g. LOINC and SNOMED), and terminology services, in order to: i) produce machine-interpretable information and coded data, ii) reduce information exchange complexity, and iii) allow the fulfillment of semantic interoperability among several systems. This work presents a system to support healthcare professionals in the creation of clinical documents using appropriate standards and in the information reading and retrieval of interest on clinical documents. The system allows healthcare professionals to use standard codes easily (via terminology server) during the creation of documents. Similarly, it also permits the decoding of health standard codes, during the read documents process, to facilitate the obtaining of information. In summary, it makes use of a simple and intuitive graphical user interface and a Fast Healthcare Interoperability Resources (FHIR) terminology server to support healthcare professionals in diagnosing and treating patients.

An Open Source System for Big Data Warehousing

Authors: Nunziato Cassavia ¹ , Elio Masciari ² and Domenico Saccà ³

Affiliations: ¹ ICAR-CNR and UNICAL, Italy , ² ICAR-CNR, Italy , ³ UNICAL and Centro di Competenza ICT-SUD, Italy

Digital Object Identifier: 10.5220/0006485703060313

Proceedings of KomIS 2017, ISBN: 978-989-758-255-4

Quick Abstract

The pervasive diffusion of new data generation devices has recently caused the generation of massive data flows containing heterogeneous information generated at different rates and having different formats. These data are referred as \emph{Big Data} and require new storage and analysis approaches to be investigated for managing them. In this paper we will describe a system for dealing with massive big data stores. We defined an open source tool that exploits a NoSQL approach for data warehousing in order to offer user am intuitive way to easily query data that could be quite hard to be understood otherwise.

Data-driven Relation Discovery from Unstructured Texts

Authors: Marilena Ditta , Fabrizio Milazzo , Valentina Ravì , Giovanni Pilato and Agnese Augello

Affiliation: ICAR CNR, Italy

Digital Object Identifier: 10.5220/0005614205970602

Proceedings of DART 2015/IC3K, ISBN: 978-989-758-158-8

Quick Abstract

This work proposes a data driven methodology for the extraction of subject-verb-object triplets from a text corpus. Previous works on the field solved the problem by means of complex learning algorithms requiring hand-crafted examples; our proposal completely avoids learning triplets from a dataset and is built on top of a well-known baseline algorithm designed by Delia Rusu et al.. The baseline algorithm uses only syntactic information for generating triplets and is characterized by a very low precision i.e., very few triplets are meaningful. Our idea is to integrate the semantics of the words with the aim of filtering out the wrong triplets, thus increasing the overall precision of the system. The algorithm has been tested over the Reuters Corpus and has it as shown good performance with respect to the baseline algorithm for triplet extraction.

On the Discovery of Explainable and Accurate Behavioral Models for Complex Lowly-structured Business Processes

Topics: Data Mining; Business Modeling and Business Process Management

Authors: Francesco Folino , Massimo Guarascio and Luigi Pontieri

Affiliation: Institute ICAR and National Research Council (CNR), Italy

Digital Object Identifier: 10.5220/0005470602060217

Proceedings of ICEIS 2015, ISBN: 978-989-758-096-3

Quick Abstract

Process discovery (i.e. the automated induction of a behavioral process model from execution logs) is an important tool for business process analysts/managers, who can exploit the extracted knowledge in key process improvement and (re-)design tasks. Unfortunately, when directly applied to the logs of complex and/or lowly-structured processes, such techniques tend to produce low-quality workflow schemas, featuring both poor readability ("spaghetti-like") and low fitness (i.e. low ability to reproduce log traces). Trace clustering methods alleviate this problem, by helping detect different execution scenarios, for which simpler and more fitting workflow schemas can be eventually discovered. However, most of these methods just focus on the sequence of activities performed in each log trace, without fully exploiting all non-structural data (such as cases data and environmental variables) available in many real logs, which might well help discover more meaningful (context-related) process variants. In order to overcome these limitations, we propose a two-phase clustering-based process discovery approach, where the clusters are inherently defined through logical decision rules over context data, ensuring a satisfactory trade-off is between the readability/explainability of the discovered clusters, and the behavioral fitness of the workflow schemas eventually extracted from them. The approach has been implemented in a system prototype, which supports the discovery, evaluation and reuse of such multi-variant process models. Experimental results on a real-life log confirmed its capability to achieve compelling performances w.r.t. state-of-the-art clustering approaches, in terms of both fitness and explainability.

Related Ontology Subjects/Areas/Topics (7)

Artificial Intelligence	Enterprise Information Systems	Signal Processing
Data Mining	Sensor Networks	Soft Computing
Databases and Information Systems Integration

Surfing Big Data Warehouses for Effective Information Gathering

Authors: Nunziato Cassavia ¹ , Pietro Dicosta ² , Elio Masciari ¹ and Domenico Saccà ³

Affiliations: ¹ ICAR-CNR, Italy , ² NTT DATA, Italy , ³ UNICAL, Italy

Digital Object Identifier: 10.5220/0005579403730377

Proceedings of KomIS 2015/DATA, ISBN: 978-989-758-103-8

Quick Abstract

Due to the emerging Big Data paradigm traditional data management techniques result inadequate in many real life scenarios. In particular, OLAP techniques require substantial changes in order to offer useful analysis due to huge amount of data to be analyzed and their velocity and variety. In this paper, we describe an approach for dynamic Big Data searching that based on data collected by a suitable storage system, enriches data in order to guide users through data exploration in an efficient and effective way.

Self Recommendation in Peer to Peer Systems

Topic: Swarm/Collective Intelligence

Author: Agostino Forestiero

Affiliation: Institute for High Performance Computing and Networking and ICAR-CNR, Italy

Digital Object Identifier: 10.5220/0005157603320336

Proceedings of ECTA 2014/IJCCI, ISBN: 978-989-758-052-9

Quick Abstract

Recommendation system aims to produce a set of significant and useful suggestions that can be meaningful for a particular user. This paper introduces a self-organizing algorithm that by exploiting of a decentralized strategy builds a distributed recommendation system. The available resources are represented by a string of bits namely describer. The describers are obtained by exploiting of a locality preserving hash function that maps similar resources into similar strings of bits. Each pear works independently with the aim to locate the similar describer in neighbor peers. The peer decisions are based on the application of ad-hoc probability functions. The outcome will be a fast recommendation service thanks to the emergent sorted overlay-network. Preliminaries experimental results show as the logical reorganization can improve the recommendation operations.

Related Ontology Subjects/Areas/Topics (5)

Artificial Intelligence		Evolutionary Computing		Swarm/Collective Intelligence
Computational Intelligence		Soft Computing

Context (please use complete words only)

Field

Sort by

Topic(s):

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject:

Affiliation

Filter listed results, by