AI4EIoTs 2020 Abstracts

Full Papers Short Papers
Full Papers
Paper Nr: 1
Title:

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

Muddasar Naeem, Antonio Coronato, Giovanni Paragliola and Giuseppe De Pietro
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.
Download
Paper Nr: 5
Title:

Image-based Malware Family Detection: An Assessment between Feature Extraction and Classification Techniques
Authors:

Giacomo Iadarola, Fabio Martinelli, Francesco Mercaldo and Antonella Santone
Abstract: The increasing number of malware in mobile environment follows the continuous growth of the app stores, which required constant research in new malware detection approaches, considering also the weaknesses of signature-based anti-malware software. Fortunately, most of the malware are composed of well-known pieces of code, thus can be grouped into families sharing the same malicious behaviour. One interesting approach, which makes use of Image Classification techniques, proposes to convert the malware binaries to images, extract feature vectors and classifying them with supervised machine learning models. Realizing that researchers usually evaluate their solutions on private datasets, it is difficult to establish whether a model can be generalized on another dataset, making it difficult to compare the performance of the various models. This paper presents a comparison between different combination of feature vector extraction methods and machine learning models. The methodology aimed to evaluate feature extractors and supervised machine learning algorithms, and it was tested on more than 20 thousand images of malware, grouped into 10 different malware families. The best classifier, a combination of GIST descriptors and Random Forest classifiers, achieved an accuracy of 0.97 on average.
Download
Paper Nr: 8
Title:

Privacy Regulations Challenges on Data-centric and IoT Systems: A Case Study for Smart Vehicles
Authors:

Lelio Campanile, Mauro Iacono, Fiammetta Marulli and Michele Mastroianni
Abstract: Internet of Things (IoTs) services and data-centric systems allow smart and efficient information exchanging. Anyway, even if existing IoTs and cyber security architectures are enforcing, they are still vulnerable to security issues, as unauthorized access, data breaches, intrusions. They can’t provide yet sufficiently robust and secure solutions to be applied in a straightforward way, both for ensuring privacy preservation and trustworthiness of transmitted data, evenly preventing from its fraudulent and unauthorized usage. Such data potentially include critical information about persons’ privacy (locations, visited places, behaviors, goods, anagraphic data and health conditions). So, novel approaches for IoTs and data-centric security are needed. In this work, we address IoTs systems security problem focusing on the privacy preserving issue. Indeed, after the European Union introduced the General Data Protection Regulation (GDPR), privacy data protection is a mandatory requirement for systems producing and managing sensible users’ data. Starting from a case study for the Internet of Vehicles (IoVs), we performed a pilot study and DPIA assessment to analyze possible mitigation strategies for improving the compliance of IoTs based systems to GDPR requirements. Our preliminary results evidenced that the introduction of blockchains in IoTs systems architectures can improve significantly the compliance to privacy regulations.
Download
Short Papers
Paper Nr: 4
Title:

Early Warning System for Landslide Risk and SHM by Means of Reinforced Optic Fiber in Lifetime Strain Analysis
Authors:

Renato Zona, Martina De Cristofaro, Luca Esposito, Paolo Ferla, Simone Palladino, Elena Totaro, Lucio Olivares and Vincenzo Minutolo
Abstract: Nowadays Sensors Networks (SN) are intensively used for environment monitoring and structural health monitoring. Sensors Network can be greatly useful for data collection in hazard sites or sites of cultural heritage. For the latter is meant structure with historical value as masonry ancient construction, while the first one has to be intended as landslide risk zone. Collecting data in terms of strain and displacements is particularly crucial when anticipating the risks of disasters. When integrated into the Internet of Things and a Big Data database, the SN offers an innovative way to have a health state of the monitored site. The paper describes a prototype of a land-sliding risk early warning system hosted that consists of an optical fiber sensor, called S.T.R.A.I.N, that collects values of deformations in soils or structures in time continuous analysis. This offers an online database readable in remote control from a server or a smartphone. The developed prototype collects and displays strain values, soil movement and structure displacements.
Download
Paper Nr: 6
Title:

A WSN Energy-aware Approach for Air Pollution Monitoring in Waste Treatment Facility Site: A Case Study for Landfill Monitoring Odour
Authors:

Lelio Campanile, Mauro Iacono, Roberta Lotito and Michele Mastroianni
Abstract: The gaseous emissions derived from industrial plants are generally subject to a strictly program of monitoring, both continuous or one-spot, in order to comply with the limits imposed by the permitting license. Nowadays the problem of odour emission, and the consequently nuisance generated to the nearest receptors, has acquired importance so that is frequently asked a specific implementation of the air pollution monitoring program. In this paper we studied the case study of a generic landfill for the implementation of the odour monitoring system and time-specific use of air pollution control technology. The off-site monitoring is based on the deployment of electronic nose as part of a specifically built WSN system. The nodes outside the landfill boundary do not act as a continuously monitoring stations but as sensors activated when specific conditions, inside and outside the landfill, are achieved. The WSN is then organized on an energy-aware approach so to prolong the lifetime of the entire system, with significant cost-benefit advancement, and produce a monitoring-structure that can answer to specific input like threshold overshooting.
Download
Paper Nr: 9
Title:

Machine Learning Approaches for Diabetes Classification: Perspectives to Artificial Intelligence Methods Updating
Authors:

Giuseppe Mainenti, Lelio Campanile, Fiammetta Marulli, Carlo Ricciardi and Antonio S. Valente
Abstract: In recent years the application of Machine Learning (ML) and Artificial Intelligence (AI) techniques in healthcare helped clinicians to improve the management of chronic patients. Diabetes is among the most common chronic illness in the world for which often is still challenging do an early detection and a correct classification of type of diabetes to an individual. In fact it often depends on the circumstances present at the time of diagnosis, and many diabetic individuals do not easily fit into a single class. The aim is this paper is the application of ML techniques in order to classify the occurrence of different mellitus diabetes on the base of clinical data obtained from diabetic patients during the daily hospitals activities.
Download