Research Topics

Research activities of the e-Lite group focus on designing, building and evaluating interactive and intelligent systems, and testing them in realistic settings. Novel user interaction modalities, empowered by ubiquitous devices, enable the discovery of innovative methods to approach new and existing application domains. We adopt an end-to-end research approach, where we aim at exploring the whole spectrum, from devices to users, from intelligence to data representation, to develop a systemic approach.

Currently, the application area in which we are mostly active is Ambient Intelligence.

Ambient Intelligence (AmI) aims at building a digital environment where people are surrounded by intelligent and intuitive interfaces embedded in all kinds of objects. The ultimate goal of such an environment is to support people in their daily lives in a proactive, yet sensible and unobtrusive, way.
In this wide area, we mainly focus on innovative interaction modalities for people and on the intelligent aspects (e.g., Semantic Web) of the environment, typically exploiting off-the-shelf devices and systems from the Internet of Things and Smart Home domains. We are also interested in understanding how to effectively support developers to build such systems.

Moreover, we deserve particular attention to the Ambient Assisted Living field, in which Accessibility and Assistive Technologies meets AmI. In this domain, we experiment with novel interaction modalities and systems for people with disabilities.

Active: since 2019

socialize1Smartphones have become an integral part of our daily lives.Through smartphones, users can nowadays perform many different tasks such as browsing the web, reading emails, and using social networks. As smartphone use increases dramatically, however, so do studies about the negative impact of overusing technology. Smartphones, in particular, have been found to be a source of distraction, and their excessive use can be a problem for mental health and social interaction.

Many different mobile apps for breaking “smartphone addiction” and achieving “digital wellbeing” are available. However, it is still not clear whether and how such solutions work. Which functionality do they have? Are they effective and appreciated? Do they have a relevant impact on users’ behavior? In our research, we aim at providing the first overall perspective of existing mobile apps for changing users’ behavior with smartphone.

Active: since 2018

architectureNowadays, end users who want to personalize their Internet of Things (IoT) ecosystem can take advantage of visual programming platforms such as IFTTT or Zapier. In such End-User Development (EUD) platforms, users can program the joint behavior of their devices and online services by defining trigger-action rules such as “if the Nest camera in the kitchen detects a movement,then send me a Telegram message.”  Trigger-action programming is, however, a complex task for non-programmers, and errors made during the composition of rules may lead to unpredictable behaviors and security issues, e.g., a lamp that is continuously flashing or a door thatis unexpectedly unlocked. As a consequence, one of the most important and urgent challenges in this context is the need to avoid possible conflicts and to assess the correctness of trigger-action rules. For this purpose, we introduce EUDebug, a system that enables end users to debug their trigger-action rules.

 

Active: since 2017

Code RecipesThe co-existence of various kinds of devices, protocols, architectures, and programming languages make Internet of Things (IoT) systems complex to develop, even for experienced programmers. When novice programmers are learning to implement these systems, they are required to deal with areas in which they do not have deep knowledge. Furthermore, besides becoming proficient in these areas separately, they should integrate them and build a system whose components are heterogeneous from both software and hardware perspectives.

Our research focused, at a first stage, on identifying the most challenging issues that novice programmers experience when developing IoT systems. Results suggested that the integration of heterogeneous software components is one of the most painful issues. It commonly implies dealing with several protocols, formats, and authentication mechanisms, that are usually unknown to the novices. Moreover, the lack of clear and complete documentation, or merely, the absence of documentation that can be understood by a novice developer, make this integration issue even more difficult to overcome.

Two proposals emerged from the outcomes of this research; Code Recipes and IoT Notebooks.

Active: since 2018

virtual assistantsThe usage of voice-based virtual assistants (e.g., Siri or Google Assistant) is growing, and their spread was most possible by the increasing capabilities of natural language processing, and generally has a positive impact on device accessibility, e.g., for people with disabilities. However, people with dysarthria or other speech impairments may be unable to use these virtual assistants with proficiency, within their smartphones or in their smart homes. Is this true? To which extent people with dysarthria can be understood and get consistent answers from these virtual assistants?

We answered these questions by analyzing the most common virtual assistants when faced with dysarthric speech in two different languages: English and Italian. Moreover, we adopted separate methodologies for each language.

Active: since 2017

eupont archProgramming environments for end-user development (EUD) in the Internet of Things (IoT) are becoming increasingly common. They allow users to define simple IoT applications, i.e., connections between different IoT devices and services, by mainly employing trigger-action rules. Unfortunately, the adopted representation models are highly technology-dependent, e.g., they often categorize devices and services by manufacturer or brand. Such an approach is not suitable to face the expected growth of the IoT, nor it allows to adapt to yet undiscovered IoT services.

As a consequence, numerous open questions arise: would a "higher level" of abstraction help users creating their IoT applications more effectively and efficiently compared with the contemporary representations? Which representations would users prefer? How high-level IoT applications could be actually executed? To answer these questions, we introduce EUPont, a high-level semantic model for EUD in the IoT.

Active: since 2014

Accessible Games for Single-Switch Interaction

Jumping ladybugs game

Small children with disabilities, especially in the pre-school age, need to develop their skills by using games and game-like environments. The educational effect of "serious games" enables educators and caregivers to involve the kids with fun and formative activities.

Falling Invaders game In the case of serious motor disabilities, when the interaction with a computer is severely hampered and the usage of a keyboard or pointing device is not possible, the choice of available educational games is greatly reduced.

Our research activity in this area focuses on defining new interaction modalities for accessible games in the educational and entertainment contexts, compatible also with severe motor disabilities.

Our research projects used and maintained outside academia, mostly open-sourced.

Explore our past and completed research projects, on various topics.