Mobile users can open program in new tab for better viewing.

Open program in new tab

Day 1 14/09/2020
Room #1

Welcome Message 09:00 - 09:10

EAI message 09:10 - 09:20

Keynote by Nuno Nunes 09:20 - 10:10

Coffee break 10:10 - 10:25

Session: Main Track #1 10:25 - 12:25

10:25 - 10:40
Monitoring cooker activities using a Grid-EYE infrared array sensor

As much as the population profile is set to age further over the years, one of the challenges of an ageing society is to create a safe environment in which the elderly can live. Although the idea of creating an entirely risk-free society is impossible, it is feasible to monitor the health of elderly people by placing smart sensors in their houses, in order to react as soon as possible if a hazardous situation is taking place. In particular, this project focuses on the kitchen environment, monitoring daily cooking activities and detecting anomalies in the use of the cooker, using some low-cost sensors: a Grid-EYE and a Sharp sensor.
Authors: Sara Comai (Politecnico di Milano), Andrea Masciadri (Politecnico di Milano), Fabio Salice (Politecnico di Milano), Eva Bafaro (Politecnico di Milano), Debora Di Bartolo (Politecnico di Milano),
Hide Authors & Abstract

Show Authors & Abstract
10:40 - 10:55
Bayesian Networks-based personal data synthesis

Often, confidentiality problems and a lack of original data, make it challenging to analyze user data carefully. In such situations, synthetic data can be used that is more suitable for testing and training marketing strategies, personalized assistants, or behavior analysis systems than the original data. In this paper, the approach for generating synthetic social media profiles data based on Bayesian networks was analyzed. The personal data synthesis problem was considered as the inference of a joint probability distribution from the oriented probabilistic models like Bayesian networks. The quality of this approach in generating VKontakte (VK is the Russian analog of Facebook) social network data was demonstrated and assessed. The Bayesian network approach has shown itself well in the tasks of deriving joint and marginal data distributions, which has led to the production of high-quality synthetic personal data.
Authors: Irina Deeva (ITMO University), Petr Andriushchenko (ITMO University), Anna Kalyuzhnaya (ITMO University), Alexander Boukhanovsky (ITMO University),
Hide Authors & Abstract

Show Authors & Abstract
10:55 - 11:10
A Geo-distributed Architectural Approach Favouring Smart Tourism Development in the 5G Era

The fast-paced evolution of ICT technology is revolutionizing our every day life, endowing us with a seamless digital assistant accessible through smart-devices. In this context, even the way we approach tourism and holidays has undergone many changes. In fact, most of us nowadays exploit smart devices to plan, book and manage the experience. This different approach to tourism is often called Smart Tourism and it is acquiring more and more importance for business, public administrations, and tourists themselves. The idea behind our proposal is to further enhance existing structure and services of a city, promoting and encouraging the smart tourism concept while satisfying the ever increasing necessity and dynamicity this scenario embodies. To this end, we propose a conceptual architectural model following a Mobile Edge Computing (MEC) approach and also exploit virtualization and multiple geographically distributed Function as a Service (FaaS) edge clouds equipped with storage capabilities. While preserving the general aspect of our study and without loss of generality, we envision a reference scenario where users consume and produce data that are geographically bound to a location of interest. This modus operandi could help unlock smart tourism potential, focusing on local communal phenomena, harvesting socio-technical data which would otherwise not be possible on a global scale through traditional centralized information systems.
Authors: Armir Bujari (University of Padua), Claudio Bergamini (Imola Informatica), Antonio Corradi (University of Bologna), Luca Foschini (University of Bologna), Claudio Enrico Palazzi (Università di Padova), Andrea Sabbioni (University of Bologna),
Hide Authors & Abstract

Show Authors & Abstract
11:10 - 11:25
Enabling QoS-secured Enhanced Non-Public Network Slices for Health Environments

5G networks are envisioned to provide high Quality of Service (QoS) for several use cases that differ on their network requirements and where they should be deployed. Some use cases are deployed in Public Land Mobile Network (PLMN) infrastructures that are managed by mobile network operators. However, for other use cases, devices connect to the services over private networks or Non-Public Network (NPN). The NPN deployment is mostly envisioned by companies that will benefit from Industry 4.0 and also eHealth to enhance QoS and network security. Network slicing is the 5G concept that comes to address the different service requirements over the same network. In this paper, we present an experimental study on deploying a network slicing solution for an NPN in health environments. This solution aims to provide both performance isolation over WiFi networks and privacy isolating the service traffic over the NPN network backhaul on the way to the application server, thus providing data confidentiality.
Authors: Henrique de Resende (university of antwerp - IMEC), Joao Paulo Gonçalves (university of antwerp - IMEC), Cristiano Both (UNISINOS), Johann Marquez-Barja (University of Antwerpen - imec),
Hide Authors & Abstract

Show Authors & Abstract
11:25 - 11:40
A data visualization exploration to facilitate a sustainable usage of premises in a Smart Campus context

The growing interest in the IoT in everyday scenarios has led to the transition from buildings to smart buildings. Such smart environments are equipped with sensors and IoT-based facilities, able to collect a huge amount of data that can be analyzed and can bring about a more sustainable usage of spaces. In this paper, we present the case study of a smart campus, where heterogeneous data, gathered both from sensors and official open data, have been exploited to facilitate the data visualization exploration of rich information about the occupant counts, towards a more sustainable and efficient use of its premises (including classrooms, labs, and meeting rooms).
Authors: Chiara Ceccarini (University of Bologna), Silvia Mirri (Univeristy of Bologna), Catia Prandi (University of Bologna), Paola Salomoni (Univeristy of Bologna),
Hide Authors & Abstract

Show Authors & Abstract
11:40 - 11:55
Towards a Reference Model of Guidelines for the Elderly Based on Technology Adoption Factors

The number of older people in the EU (65 years and older) will increase to 149 million by 2050 compared to the current 101. A large percentage of this population has not followed the transition to the world of ICT. Even for application specially aimed at the elderly, the adoption is low. This suggests that despite numerous design guidelines published for designing interfaces for elderly, there is still work to be done. In this paper, we look at existing Technology Adoption Models, especially that of Lee et al. that focuses on elderly, and investigate whether current user interface design guidelines cover the adoption factors. For this, we did a literature survey on user interface design guidelines for elderly and found a rather heavy focus on the Usability factor while the others adoption factors were hardly covered. We propose to augment the set of existing user interface guidelines with guidelines that also support the other adoption facts of Lee. For this purpose, we present a first version of a reference model that could be used to organize guidelines, but also as a guide to uncover new ones.
Authors: Renny Lindberg (Vrije Universiteit Brussel), Olga De Troyer (Vrije Universiteit Brussel),
Hide Authors & Abstract

Show Authors & Abstract
11:55 - 12:10
The new classmate: an exploration of how CoVid-19 affected primary schools activities in Italy

Among all the others, one of the groups of persons most affected by the restrictions applied to contrast Corona-Virus spread is surely represented by children. In particular, closing school has been an action applied by several countries (195 at the beginning of April 2020), involving 1,600,000,000 students all over the world. In Italy, distance learning activities have been adopted all over the country, at each educational stage, but with substantial differences (i.e., in terms of modalities and digital platforms). With the aim of investigating the most adopted technologies, didactic methodologies, as well as the impact on schools population, we have involved families of more than 1,000 Italian students, asking them to fill a survey. This paper presents the analysis of the results we have obtained, focusing on a delicate group of students: the ones attending primary schools, where kids learn fundamental knowledge and basic skills.
Authors: Ombretta Gaggi (University of Padua), Agnieszka Kolasinska (University of Padua, department of General Psychology), Silvia Mirri (Univeristy of Bologna), Catia Prandi (University of Bologna),
Hide Authors & Abstract

Show Authors & Abstract
12:10 - 12:25
Adding voice messages to a low-cost long-range data messaging system

Remote locations in rural areas can benefit from any system that would provide some form of connectivity. In a previous work we described a low cost architecture that, thanks to the use of the LoRa technology, allowed long links using low energy and a cheap infrastructure. In this work we extend those results by adding the possibility to include generic external sources of data using an MQTT based interface. More specifically, we describe a voice mes- saging system that allows users that cannot read or write to send voice based messages. We describe how the system was integrated into the existing platform and present some performance results. We consider that these results are promising and provide a tool that can offer a useful service at a low cost.
Authors: Miguel Kiyoshy Nakamura Pinto (Universitat Politécnica de Valéncia Valencia, Spain), Pietro Manzoni (Universitat Politécnica de Valéncia Valencia, Spain), Marco Zennaro (ICTP Trieste, Italy), Juan-Carlos Cano (Universitat Politécnica de Valéncia Valencia, Spain), Carlos T. Calafate (Universitat Politécnica de Valéncia Valencia, Spain),
Hide Authors & Abstract

Show Authors & Abstract

Lunch break 12:25 - 13:25

Session: Main Track #2 13:25 - 14:55

13:25 - 13:40
Sustainable Infrastructure Monitoring for Security-Oriented Purposes

As computing and communication infrastructures have gained an everincreasing role in everybody’s life, guaranteeing their reliability has become a critical endeavor. In the face of threats that grow more and more sophisticated, we must turn our attention to the techniques that have the potential to match them and scale with the infrastructure complexity. The current trend in the telecommunication industry towards "softwarized infrastructures" by means of new technologies such as Software Defined Networking and Network Function Virtualization may provide a innovative and effective solutions from this point of view. In this work, we outline a network security monitoring architecture aimed at striking the best trade-off between effectiveness and efficiency. This result is achieved by exploiting the possibility, already enabled by state-of-the-art, yet well tested components for infrastructural orchestration, of dynamic instantiation and composition of functions. We conclude that efficient detection of some classes of network-based denial-of-service attacks is possible, and open the path to mitigation strategies that optimize the usage of resources by deploying and re-configuring them as needed in real-time.
Authors: Davide Berardi (University of Bologna), Franco Callegati (DEIS University of Bologna), Andrea Melis (University of Bologna), Marco Prandini (Università  Di Bologna),
Hide Authors & Abstract

Show Authors & Abstract
13:40 - 13:55
Towards an Augmented Reality Cognitive Orthosis to Assist people with Alzheimer’s disease: Preliminary Design

Alzheimer’s disease (AD) is the most common cause of neurocognitive disorder in aging. The main impacted activities are instrumental activities of daily living (IADL). Assistance to perform IADL can help people with AD (PwAD) to stay independent longer and live at home. Such assistance can be provided remotely from a caregiver to perform certain tasks using a shared visual representation, where, for instance, audio cues by phone are not sufficient. This paper presents a preliminary design and evaluation of a system to provide a remote assistance from a caregiver to a PwAD who needs assistance, by using a shared visual representation with the caregiver. The PwAD wears an augmented reality head-mounted display and the caregiver can see his environment and add annotations in it through a desktop interface. A preliminary usability and cognitive load study with healthy adults show encouraging results, but several aspects have to be refined.
Authors: Guillaume Spalla (Université de Sherbrooke), Charles Gouin-Vallerand (Université de Sherbrooke), Amel Yaddaden (Université de Montréal), Nathalie Bier (Centre de Recherche de l'Institut Universitaire de Gériatrie de Montréal),
Hide Authors & Abstract

Show Authors & Abstract
13:55 - 14:10
Features Exploration for Grades Prediction using Machine Learning

The province of Quebec in Canada has begun to implement an important plan to bring a digital shift to the educational system. One of the key aspects of this plan is to implement a global electronic student file system. These electronic files encompass a lot of information that can in turn be used to monitor the progress of the students. In this paper, our team was able to obtain a large dataset from this new technological platform and used it to predict the grade of students. We tested up to 328 features and produced different datasets for classification. Moreover, different features selection methods were used. Finally, we were able to predict the end of the year final grade with up to 75% accuracy.
Authors: Kevin Bouchard (UQAC), Lucas Gonzales (UQAC), Julien Maitre (UQAC), Sébastien Gaboury (Université du Québec à Chicoutimi, LIARA),
Hide Authors & Abstract

Show Authors & Abstract
14:10 - 14:25
Aggregating Life Tags for Opportunistic Crowdsensing with Mobile and Smartglasses Users

We discuss in this work the opportunity of employing lifelogging devices, applications, and systems, such as systems that collect, process, and store video using mobile and wearable cameras, in order to run queries about objects and concepts of interest from everyday life. The outcome is an instance of “opportunistic mobile crowdsensing,” which we implement with lifelogging technology, mobile video cameras, and camera glasses. We describe the implementation of our concept that builds on top of Life-Tags, a wearable system for abstracting life in the form of clouds of concepts automatically extracted from videos captured by lifeloggers. We show how Life-Tags can be extended with a mobile application and cloud-based services, the Firebase Realtime Database and Cloud Storage, toward integrated lifelogging and mobile crowdsensing, where the life tags of mobile and wearable users are queries for potential matches regarding specific objects and concepts of interest. We conclude with implications for the future integration of lifelogging technology, mobile and wearable computing, and crowdsensing.
Authors: Adrian Aiordăchioae (University Ștefan cel Mare of Suceava), Daniel Furtună (University Ștefan cel Mare of Suceava), Radu-Daniel Vatavu (University Ștefan cel Mare of Suceava),
Hide Authors & Abstract

Show Authors & Abstract
14:25 - 14:40
Classification models for data fusion in human activity recognition: alternative architectures

In this paper, we present alternative deep learning architectures that perform data fusion, more specifically, feature-level fusion in the context of human activity recognition. The proposed architectures combine statistical features from the time-domain and features extracted automatically with stacked convolutional layers. The power of these architectures relies on the fact that they can be fed by various sources of data (e.g., time series, images). Additionally, we exploited the publicly available Mobile Health dataset to assess the performances of the proposed architectures. The results obtained show that the architectures are suitable for future use.
Authors: Julien Maitre (Université du Québec à Chicoutimi, LIARA), Kevin Bouchard (UQAC), Sébastien Gaboury (Université du Québec à Chicoutimi, LIARA),
Hide Authors & Abstract

Show Authors & Abstract
14:40 - 14:55
Fuzzy Features for Quality Estimation of Activity Instances in a Dataset

Activity recognition in smart homes is a challenging problem that attracted a lot of attention in the past decades. Most approaches nowadays rely on data-driven methods from artificial intelligence, especially from the field of supervised machine learning. Therefore, those approaches heavily depend on the quality of the datasets they exploit. In this paper, we propose a generalizable method based upon fuzzy logic to estimate and diagnostic the quality of each activity instance of an existing dataset. We then apply it to a labeled dataset of the CASAS laboratory and analyze the results.
Authors: Cédric Demongivert (Université du Québec à Chicoutimi), Kévin Bouchard (Université du Québec à Chicoutimi), Sébastien Gaboury (Université du Québec à Chicoutimi), Maxime Lussier (Centre de Recherche de l'Institut Universitaire de Gériatrie de Montréal), Hubert Ngankam (Université de Sherbrooke), Mélanie Couture (Centre for research and expertise in social gerontology, Integrated Health and Social Services University Network for West-Central Montreal), Nathalie Bier (Centre de Recherche de l'Institut Universitaire de Gériatrie de Montréal), Sylvain Giroux (Université de Sherbrooke),
Hide Authors & Abstract

Show Authors & Abstract

Coffee break 14:55 - 15:10

Special Session: AI for People 15:10 - 15:55

15:10 - 15:25
Active Human Agency in Artificial Intelligence Mediation

Recently, scholars across disciplines raised questions and oncerns about the notion of human intervention [1], control, and oversight over AI systems [2]. This observation becomes particularly important in the age of ubiquitous computing and the increasing adoption of AI in everyday technological infrastructure. This paper proposes a conceptual interpretation and future research agenda for the concept of human agency in times of ubiquitous AI. Building on Nicholas Garnham’s theoretical framework in 2000 [3], this paper explains the concept of mediation through human agents, technological tools and systems of symbolic representation. As AI-enabled mediation becomes ever more prominent in different sectors, this paper reconsiders Garnham’s mediation framework and the role of human agents in 2020, twenty years ahead. This paper proposes distinguishing between passive and active human agency and calls for theoretical and empirical research on individual AI redress. Ultimately, this paper argues to empower active human agency in times of ubiquitous AI.
Authors: Rosanna Fanni (VUB Brussels), Valerie Steinkogler (VUB Brussels), Giulia Zampedri (VUB Brussels), Jo Pierson (VUB Brussels),
Hide Authors & Abstract

Show Authors & Abstract
15:25 - 15:40
Interactive Machine Learning and Explainability in Mobile Classification of Forest-Aesthetics

This paper presents an application that classifies forest's aesthetics using interactive machine learning on mobile devices. Transfer learning is used to be able to build upon deep ANNs (MobileNet) using the limited resources available on smart-phones. We trained and evaluated a model using our application based on a data-set that is plausible to be created by a single user. In order to increase the comprehensibility of our model we explore the potential of incorporating explainable Artificial Intelligence (XAI) into our mobile application. To this end we use deep Taylor decomposition to generate saliency maps that highlight areas of the input that were relevant for the decision of the ANN and conducted a user study to evaluate the usefulness of this approach for end-users.
Authors: Simon Flutura (University of Augsburg Augsburg, Germany), Andreas Seiderer (University of Augsburg Augsburg, Germany), Joachim Rathmann (University of Würzburg Würzburg, Germany), Ruben Schlagowski (University of Augsburg Augsburg, Germany), Michael Dietz (University of Augsburg Augsburg, Germany), Ilhan Aslan (University of Augsburg Augsburg, Germany), Katharina Weitz (University of Augsburg Augsburg, Germany), tobias huber (University of Augsburg), Elisabeth André (Augsburg University, Germany),
Hide Authors & Abstract

Show Authors & Abstract
15:40 - 15:55
Detecting Usage of Mobile Phones using Deep Learning Technique

As the capabilities of mobile phones have increased, the potential of their negative use has also increased tremendously. For example, use of mobile phones while driving or in high security zones can lead to accidents, information leaks and security breaches. In this paper, we use deep-learning algorithms viz., single shot multiBox detector (SSD) and faster recurrent convolution neural network (Faster-RCNN), to detect mobile phone usage. We highlight the importance of mobile phone usage detection and the challenges involved in it. We have used a subset of State Farm Distracted Driver Detection dataset from Kaggle, which we term as KaggleDriver dataset. In addition, we have created a dataset on mobile phone usage, which we term as generic dataset on mobile phone usage (GDMU). Although small, GDMU is more generic than the Kaggle Driver dataset, since it has images with higher amount of variation in foreground and background objects. Ours is possibly the first work to perform mobile-phone detection for a wide range of scenarios. On the KaggleDriver dataset, the AP at 0.5IoU is 98.97% with SSD and 98.84% with Faster-RCNN. On the GDMU dataset, these numbers are 92.6% for SSD and 95.92% for Faster-RCNN. We will release the annotated KaggleDriver and GDMU datasets and the trained CNN models in open-source.
Authors: Poonam Rajput (Indian Institute of Technology(IIT) Hyderabad), Subhrajit Nag (Indian Institute of Technology(IIT) Hyderabad), Sparsh Mittal (Indian Institute of Technology(IIT) Roorkee),
Hide Authors & Abstract

Show Authors & Abstract

Special Session: Ambient Intelligence and Smart Environments 15:55 - 16:40

15:55 - 16:10
Exploring Ambient Air Quality Notifications for Smart Rooms

Many regular meeting participants know the atmosphere of a meeting in a closed room when the air becomes stifling and uncomfortable. With increased concentration of carbon dioxide (CO2), the cognitive performance of participants can also suffer as a result. Therefore, it makes sense to retrofit such meeting rooms with smarthome technology to improve the air quality. However, existing meeting rooms often do not have built-in ventilation systems. Hence, smart technology can be used to measure air quality and communicate that by ambient notifications such as ambient lighting. Actively ventilating a room is then left to the participants of a meeting. This paper reports on a user study demonstrating that the kind of unobtrusive notification from an ambient air quality display has a significant influence on response times of perceiving the information while being concentrated on the course of the meeting.
Authors: Chi Tai Dang (University of Augsburg), Ilhan Aslan (University of Augsburg), Andreas Seiderer (University of Augsburg), Elisabeth Andre (University of Augsburg),
Hide Authors & Abstract

Show Authors & Abstract
16:10 - 16:25
Integrating Alexa in a Rule-based Personalization Platform

Vocal assistants are becoming widely used, but their potentialities have not yet been completely exploited. For instance, while assistants such as Alexa are increasingly boasting compatibility with a large set of third-party services, the possibility for end-users to personalize the joint behaviour of such connected services (including the voice-based ones) in a flexible manner seem not sufficiently explored yet. In this paper, we present how the voice-based support offered by Alexa has been integrated with a rule-based personalization platform to support the creation of trigger-action rules enhanced with voice-based support. This integration opens up the possibility for users without programming knowledge to specify and include in their rules voice-based triggers and voice-based actions, which can be composed with events and commands that can involve a variety of sensors and connected objects. To this aim, a novel solution has been developed, which also aims at overcoming some limitations that have been found in currently available vocal assistants, e.g., the issue of unsupported languages, thus lowering the barriers for their ultimate adoption and everyday use. Indeed, the integrated platform offers the possibility to play the vocal notifications/ reminders contained in relevant personalization rules in any language, including those not currently supported by Alexa.
Authors: Parvaneh Parvin (CNR-ISTI, HIIS Laboratory), Marco Manca (CNR-ISTI, HIIS Laboratory), Fabio Paterno (CNR-ISTI, HIIS Laboratory), Carmen Santoro (CNR-ISTI, HIIS Laboratory),
Hide Authors & Abstract

Show Authors & Abstract
16:25 - 16:40
Development of a Privacy-By-Design Speech Assistant Providing Nutrient Information for German Seniors

Elderly people could take benefit of speech assistants since they provide the most natural way to interact with assistive technology. Nevertheless, current speech assistants are mainly based on cloud-systems which are non-functional without a stable internet connection or introduce severe privacy-concerns. In this work we provide an overview of state-of-the-art available components for developing a privacy-by-design, open source speech assistant for seniors, as well as a fully functional implementation. We chose the health related task of getting nutrition information of packaged foodstuff for which we rely on an open data database. Our prototype was used in a workshop with two German seniors to gather further insights into the special requirements of elderly people which can be taken into account for future speech assistants.
Authors: Andreas Seiderer (Augsburg University), Hannes Ritschel (Augsburg University), Elisabeth André (Augsburg University),
Hide Authors & Abstract

Show Authors & Abstract
Day 2 15/09/2020
Room #1

Keynote by Lieven De Marez 09:00 - 09:50

Special Session: OASIS 09:50 - 10:35

09:50 - 10:05
Evaluating Posts on the Steemit Blockchain: Analysis on Topics Based on Textual Cues

Online Social Networking platforms (OSNs) are part of the people’s everyday life answering the deep-rooted need for communication among humans. During recent years, a new generation of social me- dia based on blockchain became very popular, bringing the power of the technology to the service of social networks. Steemit is one such and employs the blockchain to implement a rewarding mech- anism, adding a new, economic, layer to the social media service. The reward mechanism grants virtual tokens to the users capable of engaging other users on the platform, which can be either vested in the platform for increased influence or exchanged for fiat currency. The introduction of an economic layer on a social networking plat- form can seriously influence how people socialize. In this work, we tackle the problem of understanding how this new business model conditions the way people create contents. We performed term frequency and topic modelling analyses over the written contents published on the platforms between 2017 and 2019. This analysis lets us understand the most common topics of the contents that appear in the platform. While personal mundane information still appears, along with contents related to arts, food, travels, and sport, we also see emerging a very strong presence of contents about blockchain, cryptocurrency and, more specifically, on Steemit itself and its users.
Authors: Kristina Kapanova (Trinity College Dublin Dublin, Ireland), Barbara Guidi (Department of Computer Science, University of Pisa Pisa, Italy), Andrea Michienzi (Department of Computer Science, University of Pisa Pisa, Italy), Kevin Koidl (Trinity College Dublin Dublin, Ireland),
Hide Authors & Abstract

Show Authors & Abstract
10:05 - 10:20
A Rewarding Model for the next generation Social Media

Decentralization techniques have been radically changed during the last few years thanks to new decentralized technologies, such as the blockchain. Blockchain-based Online Social Media (BOSMs) have been proposed as the future of Social Media where users are rewarded for their valuable content. Even if these platforms are used by millions of users, they are not fully decentralized. The next generation of Social Media requires the decentralization as the primary characteristic. HELIOS is a decentralized social media platform that addresses the dynamic nature of human communications, and it includes techniques such as decentralisation, context detection in IoT environment, real and virtual object networking, peer-to-peer based content streaming and validation. The paper defines a rewarding system that incentives and engages existing and potential users on the use of the HELIOS Platform, by exploiting the main characteristics of current rewarding strategies applied to BOSMs. The paper proposes an analysis of current blockchain technologies, and the main characteristics of a rewarding system for a decentralized Social Media. The framework is based on the Quorum Network.
Authors: Barbara Guidi (Department of Computer Science, University of Pisa), Vanessa Clemente (Worldline Iberia S.A.U), Tomás García (Worldline Iberia S.A.U), Laura Ricci (Professor at the Department of Computer Science, University of Pisa),
Hide Authors & Abstract

Show Authors & Abstract
10:20 - 10:35
Fixing Social Media with the Blockchain

In today’s social media context, many criticalities have emerged, particularly concerning the security of users’ personal data and the unbalanced redistribution of the value generated. This work, analyzing 40 emerging platforms, investigates how Blockchain technology is reshaping the social media scenario through transparency, value redistribution, ownership awareness, decentralization of data, and censorship resistance.
Authors: Pierluigi Freni (LINKS Foundation), Enrico Ferro (LINKS Foundation), Gabriele Ceci (Polytechnic of Turin),
Hide Authors & Abstract

Show Authors & Abstract

Coffee break 10:35 - 10:50

Special Session: Smart Moving 10:50 - 12:35

10:50 - 11:05
On the Usage of Smart Speakers During the Covid-19 Coronavirus Lockdown

The outbreak of the COVID-19 pandemic has dramatically changed our way of living in many ways, lockdown relegated us to stay at home and either suspend working activities or work from home. Technology has played a crucial role during this period: on the one hand it has given us the possibility to continue to carry on some of our everyday activities (e.g., work, school, social interactions...), on the other hand it has posed serous issues when not adequate enough to allow the owners to accomplish all their needs (e.g., poor connection, old equipment, ...). Among the latest released devices, smart speakers become quite popular in the last years and are emerging as tools that are able to support people in daily activity, including categories of people with special need. In this paper we concentrate our attention on smart speakers and we investigate if and how their usage has changed during this stay-at-home period. We analyzed the answers given to a questionnaire in which we asked questions concerning the usage previous and during the lockdown period, also including questions related to privacy issues. Results showed that usage has not drastically changed and that privacy issues might preclude the use of smart speaker to implement useful tools to control people presence and absences at home during lockdown.
Authors: Marco Furini (University of Modena and Reggio Emilia), Silvia Mirri (Univeristy of Bologna), Manuela Montangero (University of Modena and Reggio Emilia), Catia Prandi (University of Bologna),
Hide Authors & Abstract

Show Authors & Abstract
11:05 - 11:20
Making Smart Buildings and Personal Systems Cooperate via Knowledge Base Overlays

Reactive IOT applications often have to deal with the data source Babel arising from their need to operate on context information originated from different data sources. Semantic knowledge bases can be fruitfully deployed to alleviate this problem: they provide a unified access point for context information including both long term (such as the structure of the environment) and transient (such as sensor readings) data thanks to their ability to host elements responding to different schemas within the same container. In past works we introduced an architecture to create reactive IOT systems based on a semantic knowledge base that also hosts the definition of their behavior and on an accompanying reactive machinery. In this paper we introduce the use of knowledge base overlays, i.e. containers providing a live, unified view over (parts of) different underlying knowledge bases, as a mechanism to enable interoperation between multiple IOT semantics-based systems. Specifically we explore the benefits of this approach in a case study in which a semantic IOT system governing a smart building interacts with the personal semantic systems of the people entering the building.
Authors: Ester Giallonardo (University of Sannio), Francesco Poggi (University of Modena and Reggio Emilia), Davide Rossi (University of Bologna), Eugenio Zimeo (University of Sannio),
Hide Authors & Abstract

Show Authors & Abstract
11:20 - 11:35
Graphic Interfaces in ADAS: from requirements to implementation

In this paper we report our experiences in designing and implementing a digital virtual cockpit to be installed as a component within the software stack of an Advanced Driving Assisted System (ADAS). Since in next-generation automotive embedded platforms both autonomous driving related workloads and virtual cockpit rendering tasks will co-run in a hypervisor-mediated environment, they will share computational resources. For this purpose, our work has been developed by following a requirement-driven approach in which regulations, usability and visual attractiveness requirements have to be taken into account by balancing their impact in terms of computational resources of the embedded platform in which such graphics interfaces are deployed. The graphic interfaces we realized consist of a set of 2D frames for the instrument cluster (for displaying the tachometer and the speedometer) and a screen area in which a 3D representation of the vehicle surroundings is rendered alongside driving directions and the point-cloud obtained through a LIDAR. All these components are able to alert the driver of imminent and/or nearby driving hazards.
Authors: Alessio Masola (University of Modena And Reggio Emilia), Cristian Gabbi (University of Modena And Reggio Emilia), Andrea Castellano (RE:Lab s.r.l.), Nicola Capodieci (Università di Modena e Reggio Emiilia), Paolo Burgio (Università di Modena e Reggio Emilia),
Hide Authors & Abstract

Show Authors & Abstract
11:35 - 11:50
Exploiting Traffic Lights to Manage Auction-Based Crossing

Auction-based crossing management approaches are used to design coordination policies for autonomous vehicles and improve smart intersections by providing differentiated latencies. In this paper, we propose and exploit an auction based mechanism for managing the urban traffic light infrastructure in which participant vehicles are either equipped or non-equipped. The difference between these two categories of vehicles is that only the equipped ones can actively participate to auctions through in-vehicle IoT-devices, i.e. they are able to communicate with the surrounding urban infrastructure. In this way, we aim to study the transitional period that will occur before the complete adoption of autonomous or strongly connected vehicles. Through extensive experiments and simulations, by comparing our mechanism to the traditional traffic light fixed-time-control approach, we studied the benefits and limitations, in term of waiting and trip times, when varying the subset of equipped vehicles and the available budget that can be used to participate to auctions.
Authors: Filippo Muzzini (University of Modena and Reggio Emilia), Nicola Capodieci (University of Modena and Reggio Emiilia), Manuela Montangero (University of Modena and Reggio Emilia),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 12:05
On exploiting Gamification for the Crowdsensing of Air Pollution: a Case Study on a Bicycle-based System

Cities all over the world struggle with air pollution. With the ever-increasing concentration of people in urban areas, more and more people suffer from the negative effects of air pollutants. Crowdsensing systems are a unique chance to increase the users' awareness of this problem and to provide more fine-grained data to policymakers so that they can adopt appropriate strategies. In this paper, we present a crowdsensing system to collect air pollution in urban and suburban environments through the use of bicycles. It consists of a Web application, enriched with gamification elements, that communicate with a portable low-cost sensor. The user interface of such a system, as well as the adopted gamification mechanisms, has been designed by involving a group of target users, with the aim of better meeting users' preferences and needs, and, then, better engaging them.
Authors: Michael Bosello (University of Bologna), Giovanni Delnevo (Università di Bologna), Silvia Mirri (Univeristy of Bologna),
Hide Authors & Abstract

Show Authors & Abstract
12:05 - 12:20
Relationships between the number of integrated pressure sensors and step count accuracy using smart insoles

Several studies have demonstrated that instrumented insoles enable the quantification of steps taken in people with or without walking limitations. However, the number and location of imbedded pressure sensors in an insole vary considerably in the literature, resulting in variable step count accuracies. The objective of this study was to determine optimum locations to consider with minimum pressure sensors (fewer than 5), without altering the accuracy of step detection. An insole was equipped with five pressure sensors (FSRs) located under the heel (FSRH), the first (FSRM1), the third (FSRM3) and the fifth (FSRM5) metatarsal heads, and the great toe (FSRT). Step detection was based on single or combined pressure signals using a step count algorithm, in twelve healthy people who walked during six-minutes at self-selected comfortable speeds. Results showed that there was statistically significant difference (F=17.8, p<0.05) between the average step count accuracy of single and combinations from two-to-five pressure signals. The best accuracies per sensor combination were as follows: FSRM1-FSRM5 (99.0±0.9%), FSRM3-FSRM5-FSRT (99.3±0.7%), FSRH-FSRM3-FSRM5-FSRT (99.5±0.4%) and all five FSRs (99.5±0.4%). For single pressure signal, the best accuracy was 98.0±2.3% with FSRH. These results suggest that the combination of at least two pressure sensors in insole can yield an accuracy of 99% for step counting in adult people.
Authors: Armelle M. Ngueleu (Centre for Interdisciplinary Research in Rehabilitation and Social Integration (Cirris), Quebec City, G1M 2S8 Canada), Andréanne K. Blanchette (Centre for Interdisciplinary Research in Rehabilitation and Social Integration (Cirris) and Department of rehabilitation, Faculty of Medicine, Universite Laval, Quebec City, G1M2S8 Canada), Stéphane Mandigout (Laboratory HAVAE EA-6310 University of Limoges, Limoges P.O. Box 87060 France), Charles S. Batcho (Centre for Interdisciplinary Research in Rehabilitation and Social Integration (Cirris) and Department of rehabilitation, Faculty of Medicine, Universite Laval, Quebec City, G1M2S8 Canada),
Hide Authors & Abstract

Show Authors & Abstract
12:20 - 12:35
Potential and Limitations of Designing a Deep Learning Model for Discovering New Archaeological Sites: A Case with the Mesopotamian Floodplain

With this paper, we have tried to provide an answer to the question whether a collection of satellite images, with notable archaeological sites, is informative enough to instruct a deep learning model that discovers new archaeological sites, as well as other potential features of archaeological significance. Convolutional neural networks and satellite images in the visible light range were employed to detect sites in the Iraqi region of Qadisyah. The preliminary results we achieved are interesting yet not still fully convincing. The AUC value we got is near 70%, while more interesting findings have come from the idea to map the numerical predictions into heatmaps, revealing the regions where a site can lie. Several motivations can explain this controversial output. Not least is the fact that our model was instructed to learn archaeological sites of a very different form and size. Our prevailing belief is that to this lack of uniformity of the objects to be learnt can be attributed the main cause of this (partial) failure
Authors: Marco Roccetti (University of Bologna), Luca Casini (University of Bologna), Giovanni Delnevo (Università di Bologna), Valentina Orrù (University of Bologna), Nicolò marchetti (University of Bologna),
Hide Authors & Abstract

Show Authors & Abstract

Lunch break 12:35 - 13:35

Special Session: Serious game 13:35 - 14:50

13:35 - 13:50
Learning how to recycle waste using a game

Proper waste sorting is crucial for both economic and environmental reasons. Yet, its effectiveness can be strongly limited when citizens do not know how to correctly separate waste, sometimes even due to different regulations depending on their municipality. We have hence devoted our efforts to the creation of a serious game able to teach people of all ages how to match the various trash cans with the corresponding type of waste. Although we have considered the city of Padua, Italy, as a case study, our application can be easily adapted to different waste sorting regulations.
Authors: Ombretta Gaggi (University of Padua, Italy), Francesca Meneghello (University of Padua, Italy), Claudio Palazzi (University of Padua, Italy), Giulio Pante (University of Padua, Italy),
Hide Authors & Abstract

Show Authors & Abstract
13:50 - 14:05
Save the Planets: A Multipurpose Serious Game to Raise Environmental Awareness and to Initiate Change

Serious games address not only entertainment purposes but also the transformations on the behaviors of their players. Serious games have recently been used in several domains, such as education, training, rehabilitation, and defense. The positive impacts of the serious games have been highly emphasized in the literature given their strong elements in motivation, a sense of progress, and a sense of purpose. Thus, this study aims to transfer these well-known strengths of serious games to environmental awareness. To do so, a life simulation-like serious game, Save the Planets, has been developed to nurture, care about, and learn from the Solar system. The game also lets the users create their own customized systems so that the aspirations and priorities of the players could be detected. To measure the immediate impact of the Save the Planets serious game, three different scales —Environmental Identity Scale, Pro Environmental Behavior Scale, and Environmental Action Scale— were applied in the pre-test and post-test evaluations of the 22 participants. The results show that the Save the Planets serious game significantly changes the pro-environmental awareness, and this serious game may be used to better inform and motivate the participants to take long-term actions.
Authors: Dilay Seda Özgen (Department of Interior Architecture and Environmental Design, Bilkent University), Yasemin Afacan (Assoc. Prof.), Elif Surer (MIddle East Technical University),
Hide Authors & Abstract

Show Authors & Abstract
14:05 - 14:20
Learning Sign Language from a Sanbot Robot

In modern society, people with communication impairments, e.g., those with hearing loss or non-verbal autistic people, are a non-negligible number, so promoting their inclusion is a very important issue. Different approaches can be used to achieve this, and in this paper we consider the use of sign language as a bridge to connect them with the rest of the world. To this aim, we propose an enjoy- able and playful approach based on the use of an Elf Sanbot robot. We thus introduce two new applications that we have developed to interface with the robot. They can be installed in a smartphone or in a tablet, and can be used to remotely control the robot via Bluetooth or WiFI connection. The first application, called Sanbot Manager, is used to regulate the movements of the robot in the space and of his head. The second one, called Sanbot Server application, al- lows for interfacing the robot with a human, that proposes vocal or textual words or sentences in a chosen language, and the robot reacts by showing the corresponding video in sign language on the robot’s screen. We think that these two applications could be used to stimulate not only a person with a communication impairment, but also therapists, relatives, friends, to learn a sign language in an enjoyable way.
Authors: Flaminia Luccio (Università Ca' Foscari), Diego Gaspari (Università Ca' Foscari),
Hide Authors & Abstract

Show Authors & Abstract
14:20 - 14:35
Integrating gamification into a system to improve diet compliance for elderly users

Nowadays, gamification is applied in many areas, including healthy lifestyle promotion. In earlier work, a system has been proposed to stimulate diet compliance and adherence of participants of a trial within the PROMISS-project. In this paper, we describe the design of a gamified version of this system. The goal of the gamification is to further stimulate diet compliance and adherence to the system, but also to increase the knowledge about the diet and make the use of the system more fun. To do so, we implemented gamification elements (profile page, achievements, mini-games, and a reward garden) to address multiple behaviour change techniques. Based on a small evaluation, the system has been improved so that it can be used by participants of the PROMISS trial. At the end of this paper, future improvements are suggested in the future work section.
Authors: Laura van der Lubbe (Vrije Universiteit Amsterdam), Michel Klein (Vrije Universiteit Amsterdam),
Hide Authors & Abstract

Show Authors & Abstract
14:35 - 14:50
How to design and evaluate a serious game aiming at awareness of therapy skills associated with social anxiety disorder

This study’s aim was to design and evaluate a serious game to raise awareness of cognitive behavioral therapy (CBT) skills associated with social anxiety disorder. The target group was university students, as 10-25% within this group have impaired functioning due to social anxiety. The game was designed in Unity with implementation of different CBT skills within three different scenarios. The scenarios were designed based on psychophysio-logical pilots testing, and external psychiatrist expertise. There were two evaluation stages. Using self-reports (questionnaires and interviews), evaluation 1 identified how engaging the game was. Evaluation 2 took place one week after the first evaluation, and used an online questionnaire to identify if the intended learning of CBT skills could be recalled by the participants. The game was successful in terms of focused attention, attentional focus, aesthetic appeal, and narrative understanding. The designed elements for emotional engagement could be improved by allowing further in-game personalization. The participants were able to recall information from the game with less than 50% correct answers. This accuracy score could be improved by a better game design with focus on the specific information that should be recalled.
Authors: Imre Báldy (Aalborg University), Nikolaj Hansen (Aalborg University), Thomas Bjørner (Aalborg University),
Hide Authors & Abstract

Show Authors & Abstract

Coffee break 14:50 - 15:05

Special Session: ICT-Enhanced Education with Social Impact 15:05 - 16:20

15:05 - 15:20
Practical teaching of distributed systems: A scalable environment for on-demand remote experimentation

A practical compound of education in computer science and electrical engineering, driven by increased availability and maturity of many emerging technologies, should be enriched by various laboratory resources in order to synchronize the paces between technology advancements and education. In particular, advancements in containerization as a virtualization technique pave the way towards allowing students to deploy their project applications with a lightweight resource footprint on top of the cloud. Being backed by a valuable feedback from 45 Bachelor students, in this paper we present the best practices on how virtualization can be leveraged to create a scalable environment for on-demand remote experimentation with distributed systems.
Authors: Nina Slamnik-Krijestorac (University of Antwerp - imec, IDLab - Faculty of Applied Engineering), Henrique Cesar Carvalho de Resende (University of Antwerp - imec, IDLab - Faculty of Applied Engineering), Johann M. Marquez-Barja (University of Antwerp - imec, IDLab - Faculty of Applied Engineering),
Hide Authors & Abstract

Show Authors & Abstract
15:20 - 15:35
Bringing 4G LTE closer to students: A low-cost testbed forpractical teaching and experimentation

Cellular technologies are widely used in the ICT domain, that paving the way towards new opportunities for education and practical experimentation. It also tackles software-related engineering areas, from Digital Processing (DSP) to Software Defined Networks and Network Virtualization applications. Due to the various constraints such as limited access to hardware components, high costs of such equipment, and spectrum regulations that must not be violated, practical education in telecommunications, electrical engineering, and electronics usually lacks the opportunity to pursue experimentation on the realistic cellular deployments. Therefore, in this paper we present a network testbed that allows students to experiment with a fully functional 4G LTE system with no radio. This testbed system mimics the realistic 4G LTE deployment, supporting students towards acquiring valuable knowledge in the field of cellular networks. It is low-cost due the fact there is no need for radio components or Software Defined Radio (SDR) devices, with no limitation on frequency utilization and regulations. The testbed provides seamless scalability for education classes as it can be deployed on top of any machine with general-purpose processor, installing the whole system within two networked PCs or in a fully virtualized environment.We present the testbed framework, as well as the hands-on practices on incorporating such low-cost realistic testbed into the education within various engineering fields
Authors: Erik De Britto e Silva (University of Antwerp - imec), Nina Slamnik-Kriještorac, (University of Antwerp - imec), Seilendria Hadiwardoyo (University of Antwerp - imec), Johann Marquez-Barja (University of Antwerp - imec),
Hide Authors & Abstract

Show Authors & Abstract
15:35 - 15:50
Benefits, drawbacks and psychological impact of online lectures during quarantine due to Covid-19 pandemic

As a response to COVID-19 quarantine measures, educational institutions suspended their regular activities and started delivering remote lectures to almost 11 million of isolated students in Italy. In the attempt to evaluate the psychological impact of e-learning on the mental health of quarantined students, a web-survey has been designed and administered to a small sample of students. Preliminary results show that the possibility of interaction and relationships with teachers and peers may have a positive impact on perceived levels of anxiety and stress. Also, useful insights on students' perceived benefits and issues of e-learning can help the design of lectures that successfully deliver educational content while taking into account device preferences, common problems and the importance of group interaction.
Authors: Roberta De Michele (University of Bologna Bologna, Italy),
Hide Authors & Abstract

Show Authors & Abstract
15:50 - 16:05
Enhancing Education in the Rural Community through Online Training

Everybody irrespective of status, gender or geographical location is entitled to basic education. However, increasing African population is increasing the strain on existing resources and infrastructure even for education. Nigeria has the highest out of school population in the world as it is finding it hard to provide education to all its youths and adolescents. The available data show that 60% of Nigeria’s out of school population are located in the rural Northern part of the country and 60% of them are girls. Investment in good and equal opportunity education is vital for national development and well-being. The research presented in this paper seeks to address the challenge of out of school youths and adolescents in Nigeria using innovative online learning solutions that would enhance youth and adolescent education in the rural communities and also among the girl child. It is expected that by implementing these solutions, Nigeria can improve its attainment towards some specific SDG goals. The paper also considers possible challenges that the Nation may face in sustaining the proposed solutions (online training) in the rural communities.
Authors: Mary-Jane Sule (ICTP Trieste, Italy), Marco Zennaro (ICTP Trieste, Italy), Joel Gogwim (University of Jos), Clement Onime (ICTP Trieste, Italy),
Hide Authors & Abstract

Show Authors & Abstract
16:05 - 16:20
Thinking on Future Web Laboratory Services Application to the VISIR Remote Laboratory Environment

Educational institutions have to train the next-generation workforce. Unfortunately, it is not easy for educational institutions and educators to adapt to this unpredictable and volatile labor world. Besides, students have become more demanding adopting a role close to a consumer. They also have embraced a lifelong learning strategy in «skills learning» through professional development as a common occupational norm. Remote laboratories have emerged as an educational tool in order to provide flexibility to practical training. However, they are going to turn into core elements in future educational approaches due to students' demands and technological advances.
Authors: Felix Garcia Loro (National Distance Education University (UNED)), Sergio Martin (National Distance Education University (UNED)), Manuel-Gil Castro (Universidad Nacional de Educación a Distancia (UNED)), Johann Marquez-Barja (University of Antwerpen - imec),
Hide Authors & Abstract

Show Authors & Abstract

Awards ceremony 16:20 - 16:30

Day 3 16/09/2020
Room #1

Session: Work in Progress and PhD Track #1 09:00 - 10:30

09:00 - 09:15
Human-Centric Ridesharing on Large Scale by Explaining AI-Generated Assignments

Ridesharing has the potential to contribute to reducing CO2 emissions and congestions but user acceptance is still low. Within ridesharing platforms, the assignment of ride offers to requests and vice versa is an essential process with respect to user satisfaction and user acceptance. The aim of our research is to contribute to increase ridesharing usage by improving this process. In particular, we strive to enhance existing assignment approaches that are based on deep reinforcement learning by including additional factors that influence the satisfaction of users. Furthermore, we present the novel concept of applying explainable AI techniques to make ridesharing assignment decisions more transparent to users. In this paper, we present a five-step research methodology to realize the aforementioned enhancements in the future and present preliminary results.
Authors: Sören Schleibaum (Clausthal University of Technology, Clausthal-Zellerfeld, Germany), Jörg P. Müller (Clausthal University of Technology, Clausthal-Zellerfeld, Germany),
Hide Authors & Abstract

Show Authors & Abstract
09:15 - 09:30
An Intelligent Dashboard for Assisted Tweet Composition in the Cultural Heritage Area (Work-in-progress paper)

Cultural Heritage institutions are nowadays using social media to communicate with citizens and tourists. However, providing actual effective communication is not an easy task, as every day millions of messages are posted through social media. Thus, getting visibility is not trivial. In this paper we present the architecture of a dashboard, accessible by mobile Android devices, to support museum social media managers in composing effective tweets by providing suggestions to improve message drafts. At this aim, the application exploits machine learning techniques over data related to tweets posted by museums in the past.
Authors: Martoglia Riccardo (University of Modena and Reggio Emilia), Manuela Montangero (University of Modena and Reggio Emilia),
Hide Authors & Abstract

Show Authors & Abstract
09:30 - 09:45
At Home With Us

In this paper we present ongoing research on a methodology to assist people with moderate disabilities, in their homes, using off-the-shelf smart home technologies, and open-source software. Clearly, such building blocks can cover a smaller set of scenarios than custom-built alternatives, but we believe they are nonetheless capable of improving the life of several people and her/his caregivers, avoiding or postponing the adoption of more invasive, less affordable solutions. Our methodology includes a body of principles to build assistance solutions out of smart home devices. We have already identified a set of technologies to implement our methodology, and actual assistance actions in real-world scenarios where our methodology is applicable. We have already experimented with the methodology in one scenario.
Authors: Carlo Fantozzi (University of Padua), Lorenzo Grigoletto (Informatici Senza Frontiere), Marco Pasquato (Informatici Senza Frontiere),
Hide Authors & Abstract

Show Authors & Abstract
09:45 - 10:00
A Study on The Limits and Potential of Machine Predictions from a Human-Big Data-Machine Interaction Perspective

Machine learning systems are obtaining outstanding results in several fields and are now used in various applications, products, and services. However, in order to minimize their harms and exploit their benefits, it is fundamental understand the limits and the potentialities of algorithms that learn directly from data. In my PhD thesis, I would like to investigate on how the limits of machine predictions influence the interaction between human, computers, and big data.
Authors: Giovanni Delnevo (Università di Bologna),
Hide Authors & Abstract

Show Authors & Abstract
10:00 - 10:15
Safe Routes

Road traffic injuries are the leading cause of death for people aged 5-29 years old worldwide. They are the third largest cause of death (nearly 38,000 people annually) in the United States and the tenth leading cause of death (approximately 1.35 million people per year) worldwide which translates to 3,700 deaths on average per day worldwide. Further more, 4.4 million Americans are injured seriously enough to require medical attention which results in \$380 million in direct medical costs annually. Yet, given all of that, the various navigation software and GPS products used by motorists on a daily basis do not account for the safety of the routes they suggest and navigate users through. This paper is to report on Safe Routes, a navigation software under research and development at Santa Clara University's Ethical, Pragmatic, and Intelligent Computing (EPIC) Laboratory for the safety scoring of routs in an effort to help reduce the number of road traffic injuries and fatalities. Safe Routes operates on historical accident data as well as real time road and weather conditions for every road segment in all the potential routs between a user designated source and destination in order to calculate the safety rating of each and to rank them for the user with the hope of persuading the user to choose the safest rout for navigation.
Authors: Navid Shaghaghi (Santa Clara Univesity), Aidan Mackey (Santa Clara University), Stephen Mistele (Santa Clara University), Kevin Rooney (Santa Clara University), Nicholas Tallis (Santa Clara University),
Hide Authors & Abstract

Show Authors & Abstract
10:15 - 10:30
On the Use of LoRaWAN Technology for Independent Monitoring of Unreliable Campus WIFI Networks

We designed and deployed a networking monitoring tool based on LoRaWAN for our University network in Benin. Using affordable LoRaWAN devices and by placing the server in our network, we are now able to analyze network failures in real-time. We can receive SMS alerts when a WiFi access point does not work correctly. This has proven to be an affordable and scalable solution for Campus networks with an unreliable cable network.
Authors: Sidoine ODE (Institute of Mathematics and Physical Sciences(IMSP), Africa Center of Excellence in Mathematical Sciences and Applications, Porto-Novo, Benin), Jules DEGILA (Institute of Mathematics and Physical Sciences(IMSP), Africa Center of Excellence in Mathematical Sciences and Applications, Porto-Novo, Benin), Marco Zennaro (ICTP),
Hide Authors & Abstract

Show Authors & Abstract

Coffee break 10:30 - 10:45

Session: Work in Progress and PhD Track #2 10:45 - 12:15

10:45 - 11:00
Cultural Heritage and Internet of Things

Ancient structures and historical buildings represent invaluable assets for future generations. They need to be preserved as much as possible since, as cultural heritage, provide with irreplaceable cultural, social and historical wealth, not only for the local heir communities, but in many cases for the whole human kind. In the context of today’s technologies, the Internet of Things (IoT) paradigm represents one of the most effective ways for monitoring "things" around us. Cultural Heritage stays as one important application field for IoT, since conservation of cultural heritage sites can be significantly improved by means of an efficient and well-designed monitoring and control system. However, there are many approaches to apply IoT on Cultural Heritage use cases. For this reason, in this paper we discuss IoT architectures currently used for monitoring and preservation of historical buildings, and identify existing challenges IoT applications are still facing to become a fundamental part in the conservation of the everlasting cultural values these buildings represent.
Authors: Elizabeth Astorga González (Universidad de Oriente, Santiago de Cuba), Esteban Municio (University of Antwerpen - imec), Maikel Noriega Alemán (Universidad de Oriente, Santiago de Cuba), Johann Marquez-Barja (University of Antwerpen - imec),
Hide Authors & Abstract

Show Authors & Abstract
11:00 - 11:15
On Time Synchronization of LoRaWAN Based IoT Devices for Enhanced Event Correlation

Low power wide area network (LPWAN) technologies are becoming prominent in the era of the Internet of Things. In this context, LoRa long range technology emerges as a good solution thanks to its property of providing long-range along with low power although with limited bandwidth. In this paper, we focus on the use of a LoRa network for time synchronization among various nodes, to support message transmission and critical data sharing in a correct real-time manner. When providing a reliable collaborative service, clock synchronization is required, for example to apply AI solutions in IoT. In this paper, we evaluate different methodologies based on LoRa network time synchronization using commodity low cost hardware so that our solution could be adopted even in low operating expenditures or rural contexts.
Authors: Prachi Wadatkar (ICTP), Marco Zennaro (ICTP), Pietro Manzoni (Universitat Politècnica de València),
Hide Authors & Abstract

Show Authors & Abstract
11:15 - 11:30
Eudaimonia and behavior change. Incorporating negative feelings into game design elements

Behavior change is presently a central topic in healthcare HCI, and gamification is one of the possible ways to address it. However, for a behavior change adequate gamification process to happen, we have to take into account the occurrence of negative feelings and discomfort, that can affect the outcomes and interfere with reaching out goals. We present a vision of embodying those feelings into the design of the game. In fact, the primary function of games lies not only in fun, but also into positively managing difficulties. This is consistent with the tenets of distributed cognition, which states that external tools and representation afford the perception, the manipulation and the sharing of inner thoughts, just like successful games for behavior change should do.
Authors: Silvia Torsi (University of Trento), Fausto Giunchiglia (Università di Trento), Cristina Rebek (Free University of Bolzano), Benedetta Giunchiglia (University of Milano Bicocca),
Hide Authors & Abstract

Show Authors & Abstract
11:30 - 11:45
Enhancing Healthcare Access through Remote Infant Screening

In many countries, babies are required to visit a healthcare facility periodically from birth until they reach the age of five for growth monitoring. However, many parents in marginalized areas are not able to do so which results in high infant mortality rates. In this paper we present the early results of an affordable remote screening system developed using an IoT device that measures a baby’s temperature, height, weight, and skin condition and sends them to a healthcare provider for decision making. The device captures essential data using sensors, after which an image recognition algorithm is used to access the infant’s skin. Analytics are conducted on the data and alerts generated for timely intervention. The results obtained show that it is possible to develop an affordable and functional remote screening device to enhance healthcare access. We plan to scale it to measure the infants breathing patterns and heart rate.
Authors: Leah Mutanu (United States International University), Khushi Gupta (United States International University - Africa), Jeet Gohil (United States International University - Africa), Dharmik Karania (United States International University - Africa), Abdi Ali (United States International University - Africa),
Hide Authors & Abstract

Show Authors & Abstract
11:45 - 12:00
What do we know about AR Storytelling?

In the last years, there has been an abundance of AR applications developed, across multiple sectors. However, AR still remains in many domains just a buzzword, with very little evaluations carried out to study its impact on users in terms of exploration, navigation, learning and enjoyment. In this paper, we want to reflect on the use of AR on a heritage site related to World War II, to raise awareness around an issue, i.e., our common history, whose implications can still be felt today, in these days of social unrest. We want to show how an emerging technology like AR can do some social good by not loosing the memory of those who fought in the war and liberated Europe, now that many of us consider ‘freedom’ as a given. We will do so by presenting the story of George and Ursula Lévy, two Jewish children confined in Kamp Vught, a deportation camp for children in the South of the Netherlands, and by discussing in which way viewers of this story can be sensitized to ‘not forget’.
Authors: Licia Calvi (Breda University of Applied Sciences),
Hide Authors & Abstract

Show Authors & Abstract
12:00 - 12:15
Building an Italian-Chinese Parallel Corpus for Machine Translation from the Web

In an increasingly globalized world, being able to understand texts in different languages (even more so in different alphabets and charsets) has become a necessity. This can be strategic even while moving and travelling across different countries, characterized by different languages. With this in mind, bilingual corpora become critical resources since they are the basis of every state-of-the-art automatic translation system; moreover, building a parallel corpus is usually a complex and very expensive operation. This paper describes an innovative approach we have defined and adopted to automatically build an Italian-Chinese parallel corpus, with the aim of using it for training an Italian-Chinese Neural Machine Translation. Our main idea is to scrape parallel texts from the Web: we defined a general pipeline, describing each specific step from the selection of the appropriate data sources to the sentence alignment method. A final evaluation was conducted to evaluate the goodness of our approach and its results show that 90\% of the sentences were correctly aligned. The corpus we have obtained consists of more than 6,000 sentence pairs (Italian and Chinese), which are the basis for building a Machine Translation system.
Authors: Rita Tse (School of Applied Sciences - Macao Polytechnic Institute, Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence, Ministry of Education - Macao (China)), Silvia Mirri (Univeristy of Bologna), Su-Kit Tang (School of Applied Sciences - Macao Polytechnic Institute, Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence, Ministry of Education - Macao (China)), Giovanni Pau (University of Bologna), Paola Salomoni (Univeristy of Bologna),
Hide Authors & Abstract

Show Authors & Abstract

Closing remarks 12:15 - 12:30

Lunch break 12:30 - 14:00

Data Protection for Health Care Workshop 14:00 - 16:25

The detailed program can be found at: https://goodtechs.eai-conferences.org/2020/data-protection-workshop/