Smart Objects and Technologies for Social Good

This paper presents the research, the preliminary design stages and an early evaluation of a digital wearable product for monitoring and managing the effects of a chronic disease called Raynaud’s phenomenon (RP). The proposed wearable prototype aims at supporting sufferers in their everyday life for managing and preventing RP. The product is composed of three main parts, a physical product of a smart ring, the digital infrastructure of the physical computing subsystem (hardware and software) and an accompanying mobile application.

Following the Cuckoo Sound is a responsive floor application designed to train blind children to walk along a straight path through the use of interactive audio. The system, based on computer vision algorithms, is able to estimate the cartesian coordinates of a user as soon as s/he enters the active area. To provide children with an efficient and playful tool which can help them in the task of walking straight, we designed an interactive audio environment based on a cuckoo sound which is altered if the child veers from a central hallway. To obtain preliminary information about the potential of the application, we organized a pilot study involving 6 blind children. Results show an improvement in the stability of the direction in 5 subjects out of 6. Moreover, the great interest among the children for interactive audio suggests that this is a promising investigation field to help wayfinding and orientation.

Smart homes offer considerable potential to facilitate aging at home and, therefore, to reduce healthcare costs, both in financial and human resources. To implement the smart home dream, an artificial intelligence has to be able to identify, in real-time, the ongoing activity of daily living with a fine-grained granularity. Despite the recent and ongoing improvements, the limitation of the literature on this subject primarily concerns the quality of the information which can be inferred from standard ubiquitous sensors in a smart home. Passive Radio-Frequency Identification is one of the technology that can help improving activity recognition through the tracking of the objects used by the resident in real-time. This paper builds upon the literature on objects tracking to propose a machine learning scheme exploiting statistical features to transform the signal strength into useful qualitative spatial information. The method has an overall accuracy of 95.98%, which is an improvement of 8.26% over previous work.

The purpose of this article is to explore and present the range of commonalities and differences between internal and external contexts that influence elderly and younger users’ intentions to use commercial off-the-shelf (COTS) smartwatches and pedometers as motivational tools for physical activity. Therefore, this article follows the contextual action theory and the usability evaluation approach, in which “testing” and “inquiry” were applied to 21 younger participants and 13 fit, elderly participants who were in either the pre-contemplation, contemplation, action, or maintenance behavior-change stage. The results revealed no differences in internal context between the target groups due to both the effect and the useful-ness of the external context. However, there were distinctions between the younger and elderly participants regarding external context, especially in certain aspects of device usability, such as font size, touchscreen interaction, interaction technique, and applications installed, which were the core factors that affected the use of COTS smartwatches and pedometers by the study groups. In addition, the external and internal contexts had a cause-effect relationship, which significantly influenced the use of COTS smartwatches and pedometers.

Parkinson’s disease (PD) is a neurodegenerative and progressive disorder of the central nervous system that affects mainly the motor system. As a consequence of the disease, PD patients suffer a progressive reduction of their independence and Quality of Life (QoL). Literature research shows that the use of auditory, visual and haptic cueing could significantly benefit the motor performance of PD patients. Likewise, music therapy (MT) has shown notable benefits for PD either in the motor and non-motor dimensions. This work is aimed at designing a mHealth system to deliver a home based rehabilitation programme for PD patients based on external cueing and MT called HOOP, integrated by a set of inertial sensors, an Android application, and a web tool for professionals. This designing process has been performed according to expert’s consultation in order to develop a tool that can cover both patients and professional necessities.

Through recycling textile waste, greenhouse gas emissions can drastically be reduced. Such textile recycling has become a lot easier with clothing retailers now starting to offer recycling checkpoints. Moreover, people today are often challenged by overloaded wardrobes and store many clothing items that they never use. In this paper, we describe an Internet of Things system that creates incentives for the users to recycle their clothes, benefiting the environmental sustainability. We propose a content-based recommendation approach that utilizes semantic web technologies and that leverages a set of context signals obtained from the system’s architecture, to recommend clothing items that might be relevant for the user to recycle. Experiments on a real-world dataset show that our proposed approach outperforms a baseline which does not utilize semantic web technologies.

In this paper, we present a study on the use of serious games in the assessment and rehabilitation of children with Cerebral Visual Impairment (CVI). Moving objects support vision and processing the information conveyed in children with CVI; they also find it easier to deal with more simple images. Our serious games help them keeping focused on the exercise by using touch interface, the game paradigm and cartoon characters. The paper reports lesson learned from data collected in a user study to highlight the high potential of using these games also in the rehabilitation process, which brings us to develop the games also in a mobile platform to allow children train the skill at home, i.e., more intensively and in a familiar environment.

Remote Control Systems (RCSs) are increasingly being installed in homes and offices. Technology evolves very rapidly and sensors and devices are becoming smaller, smarter and more powerful. Mobile and Web apps are commonly used to remotely configure and control devices. Home control is especially valuable for blind people, since they can benefit from technology to control and turn on/off devices autonomously. Remote control can offer meaningful support, especially when devices are not directly accessible (e.g., thermostat to manage heating temperature). Therefore, if RCS interfaces are not accessible via screen reader, blind users may miss a great opportunity to achieve greater autonomy at home. This paper investigates the accessibility of the web user interfaces offered by RCSs for blind people. To do this, the Fibaro, a popular Remote Control System, was tested as a case study by analyzing the interaction via screen reader. Results indicate that accessibility and especially usability need to be improved to make interaction easier and more satisfying for blind people. To this aim, some suggestions are offered to aid developers in designing more accessible RCS user interfaces.

ALMA is an integrated system to support autonomous mobility and orientation for the elderly and, more in general, for the person with cognitive and/or mobility impairments in indoor facilities. It is composed of a set of modules for navigation, localization, planning, and autonomous wheelchair mobility, interfacing with the user. In this paper, we describe in detail the localization and navigation modules that can guide the target user to a selected destination and report our experience in a large care- and assistance-giving facility.

Individuals with Down Syndrome (DS) have delays in the development of motor function associated with impairments including difficulty with precise movements of limbs, poor balance, and poor visual-motor coordination. It has been reported that children and adolescents with DS might present differences in terms of visual-motor coordination skills, task persistence, emotional expressions, among others. Exergames have the potential to support motor coordination as they combine physical exercise with gaming technology. However, little has been said about the game experience of individuals with DS playing exergames. This work presents the results of an exploratory study of 10 individuals with DS playing a commercial exergame. Our results show a significant difference between children and adolescents in terms of task-efficacy, selective attention, and prompts. Finally, we discuss our results and the implications for designing exergames to support motor coordination of people with DS.

The wide diffusion of mobile devices and of digital technologies are dramatically changing the usage scenarios in different contexts. One of them is cultural heritage, where new media are offering huge possibilities for the enhancement and the enrichment of heritage experience, improving the users’ involvement. In particular, tourists equipped with their mobile devices are invading cultural attractions, sharing pictures and comments (together with hashtags and geo-localized positions) on social networks. These represent a source of data, which can be integrated with the official ones provided by GLAM (Galleries, Libraries, Archives, and Museums) and cultural heritage institutions, enriching them. In this paper, we explore how social networks and crowdsourcing activities can be exploited as a source of information for cultural places and pieces of art.

Mapping services and travel planner applications are experiencing a great success in supporting people while they plan a route or while they move across the city, playing a key role in the smart mobility scenario. Nevertheless, they are based on the same algorithms, on the same elements (in terms of time, distance, means of transports, etc.), providing a limited set of personalization. To fill this gap, we propose PUMA, a Personal Urban Mobility Assistant that aims to let the user add different factors of personalization, such as sustainability, street and personal safety, wellness and health, etc. In this paper we focus on the use of smart bikes (equipped with specific sensors) as means of transports and as a mean to collect data about the urban environment. We describe a cloud based architecture, personas and travel scenario to prove the feasibility of our approach.

Serious gaming can represent a key for fostering learning and letting children to acquire new information and skills while doing engaging activities. Among the different types of games, those ones based on interactive 3D environments are widely diffused and appreciated. A key component of the design of these experiences is the choice of the input device that will be used by the players and the mapping of the users’ intentions to the actions in the 3D environment. The choice of the proper device can lead to benefits in terms of user engagement, which often is the prerequisite for learning. There are also additional dimensions to consider, as the usability and the physical fatigue. Their undervaluation, in an educational context, can hamper the successful outcome of the experience. For this reason in this work we compared the use of three different input devices (a mouse-keyboard set, a gamepad and the Leap Motion, a sensor for recognizing hand gestures) for controlling a 3D educational gaming experience focused on environmental sustainability. We organized a comparative study with 30 children of the Primary School, evaluating the interaction in terms of usability, engagement and physical fatigue. The results evidenced the potential of the Leap for engaging the children, but also drawbacks in terms of usability and physical fatigue that should be taken into consideration for the development of this technology and the design of experiences based on it.

Travel planners and mobile applications related to cultural heritage can play an interesting role in the development of smart cities, when they are integrated each other, engaging the user in touristic and entertainment activities, letting him/her be a source of cultural resources. This paper focuses on a microservices-based architecture, defined with the aim of providing support in computing personalized urban paths across cultural heritage places and in sharing multimedia resources about points of interest. A prototype of mobile application has been implemented on the basis of such architecture, showing the feasibility of the proposed approach thanks to personas and related scenarios.

Recently, big data had become central in the analysis of human behavior and the development of innovative services. In particular, a new class of services is emerging, taking advantage of different sources of data, in order to consider the multiple aspects of human beings. Unfortunately, these data can lead to re-identification problems and other privacy leaks, as diffusely reported in both scientific literature and media. The risk is even more pressing if multiple sources of data are linked together since a potential adversary could know information related to each dataset. For this reason, it is necessary to evaluate accurately and mitigate the individual privacy risk before releasing personal data. In this paper, we propose a methodology for the first task, i.e., assessing privacy risk, in a multidimensional scenario, defining some possible privacy attacks and simulating them using real-world datasets.

Fall detection is a well investigated research area, for which different solutions have been designed, based on wearable or ambient sensors. Depth sensors, like Kinect, located in front view with respect to the monitored subject, are able to provide the human skeleton through the automatic identification of body joints, and are typically used for their unobtrusiveness and inherent privacy-preserving capability. This paper aims to analyze depth signals captured from a Kinect used in top view, to extract useful features for the automatic identification of falls, despite the unavailability of joints and skeleton data. This study, based on a set of signals captured over a number of test users performing different types of falls and activities, shows that the speed of falling computed over the blob identifying the person, extracted from the depth images, should be used as a feature to spot fall events in conjunction with other metrics, for a better reliability.

For investigating whether rewarding elements within a persuasive web-application for increasing prosocial behavior are effective, we conducted an experimental field study with a self-developed web-app (N = 42). Two different versions of the persuasive web-app (high/low persuasive) to foster good deeds were implemented and examined during a three-week period. In both versions, the evaluation of the user-interface correlated positively with the execution of the target behavior, i.e. performing good deeds. Also, the availability of a user profile and a ranking was positively associated with performing prosocial behavior. However, there was neither a significant difference regarding the intensity of app usage nor concerning the number of performed good deeds between experimental groups (high/low persuasive). Therefore, the availability of more persuasive features does not necessarily entail more persuasion. In conclusion, we derive design suggestions for developing persuasive mobile applications which provide benefits for (pro-)social life through encouraging people to perform good deeds.

The use of virtual reality as a form of exposure therapy for people who suffer from acrophobia (fear of height) has been proved and tested by multiple studies. In this paper, we initiate gamified virtual reality approach to overcome fear of height by providing a design implementation theory. We call this theory High Engagement and Low Intensity-Low Engagement and High Intensity. This theory adds a gamified element to the virtual environment. The idea here is to have game engagement at its highest and intensity of the acrophobia at its minimum in the virtual environment at the start of the treatment. As the treatment progresses, the engagement in the game starts decreasing and the intensity of the phobia starts increasing. The implementation provides two parameters (engagement and intensity) that could be adjusted independently according to the patient needs. We also evaluate the base of our theory through a pilot study.

Nowadays there is a growing standardization of musical contents. Our finding comes out from a cross-service multi-level dataset analysis where we study how geography affects the music production. The investigation presented in this paper highlights the existence of a “fractal” musical structure that relates the technical characteristics of the music produced at regional, national and world level. Moreover, a similar structure emerges also when we analyze the musicians’ popularity and the polarity of their songs defined as the mood that they are able to convey. Furthermore, the clusters identified are markedly distinct one from another with respect to popularity and sentiment.

The children’s use of technology is increasing year by year and recent statistics show that children receive their first smartphone and autonomously navigate the Web when they are 10.3 years old (on average). Nevertheless, while the number of tourism packages for families with children grows, the number of websites that can be directly visited by children is small; more relevant, is the number of tourism applications developed for children. This paper discusses the design of usable and accessible websites for children, and proposes, as a case study, our experience on a dedicated section of the tourism website of a Naturalistic Oasis located close to Treviso, in Italy.

Application of deep learning tends to outperform hand-crafted features in many domains. This study uses convolutional neural networks to explore effectiveness of various segments of a speech signal, – text-dependent pronunciation of a short sentence, – in Parkinson’s disease detection task. Besides the common Mel-frequency spectrogram and its first and second derivatives, inclusion of various other input feature maps is also considered. Image interpolation is investigated as a solution to obtain a spectrogram of fixed length. The equal error rate (EER) for sentence segments varied from 20.3% to 29.5%. Fusion of decisions from sentence segments achieved EER of 14.1%, whereas the best result when using the full sentence exhibited EER of 16.8%. Therefore, splitting speech into segments could be recommended for Parkinson’s disease detection.

This paper outlines how a computer game can be used within transmedia storytelling to engage boys in the Danish gymnasium to read the epic poem “The Odyssey” by Homer. The study is based on a formative evaluation with questionnaires, observations, data logging, and interviews. Interviews with classical civilization teachers were further conducted, both in the initial design stage and after participant tests. Through all stages of the transmedia storytelling, it was revealed that curiosity was the main reason behind the engagement. The aesthetics worked out well in the game, and the story was presented in a format that the boys could comprehend and had the potential to increase their engagement in reading the poem. Different elements were implemented in the program code to maintain match in game flow for the individual player. However, this study can also emphasize how well-designed game mechanics are of ultimate importance, as well as involving teachers throughout all stages in the iterative process, as they are key figures for real implementation and acceptance.

Despite their tremendous popularity, Online Social Networks (OSNs) have several issues related to the privacy of social users. These issues have motivated researchers to develop OSN services that take advantage of the decentralized platforms (such as P2P systems or opportunistic networks). Decentralized Online Social Networks (DOSNs) need specific approaches to manage the decentralization of social data. In particular, data availability is one of the main issues and current proposals exploit properties of the social relationships to manage it. At the best of our knowledge, there are no proposals which exploit similarity between users, expressed with the term homophily. Homophily has been well studied in existing sociology literature, however, it is not easily extensible in Online Social Networks due to the limitations of real datasets. In this paper, we propose a preliminary analysis of similarity of social profiles in term of movie preferences. Results reveal that user’s friends are characterized by a different levels of similarity which can be exploited to propose solutions for the data availability problem.

Although activities of daily living are often difficult for individuals with cognitive impairments, their autonomy and independence can be fostered through interactive technologies. The use of traditional computer interfaces has however proved to be difficult for these users, bringing to the surface the need for novel interaction methods. This paper proposes Let’s Cook, an innovative Augmented Reality game, designed to teach children with cognitive impairments how to prepare simple meals, following a playful approach. Let’s Cook supports multimodal interaction techniques utilizing tangible objects on a table-top surface, as well as multimedia output. Additionally, it can be personalized to accommodate the diverse needs of children with cognitive impairments by employing individual user profiling. The system is currently installed in the kitchen of the Rehabilitation Centre for Children with Disabilities in Heraklion, Crete where it was evaluated by the students.

Online social networks (OSN) have revolutionized many aspects of our daily lives and have become the predominant platform where content is consumed and produced. This trend coupled with recent advances in the field of Artificial Intelligence (AI) have paved the way to many interesting features, enriching user experience in these social platforms. Photo sharing and tagging is an important activity contributing to the social media data ecosystem. These data once labeled constitute a fruitful input for the system which is exploited to better the services of interest to the user. However, these labeling activity is imperfect and user subjective, hence prone to errors inherent to the process. In this paper, we present the design and the analysis of an Android app (namely GHio-Ca), an automatic photo tagging service relying on state-of-the-art image recognition APIs. The application is presented to the user as a camera app used to share pictures on social networks while relying on external services to automatically retrieve tags best representing the picture theme. Along with the system description we present a user evaluation involving 30 subjects.

In this paper, we study the evolution of the most influential users in the microblogging social network platform Twitter. To this aim, we consider the Dynamic Retweet Graph (DRG) proposed in [3] and partially analyzed in [2, 4]. The model of the evolution of the Twitter social network is based on the retweet relationship. In a DRGs, once a tweet has been retweeted the last time all the edges representing this tweet are deleted, to model the decay of tweet life in the social platform.We consider the following measures of centrality: degree, closeness, and pagerank-centrality which have been widely studied in the static case. Here we analyze them on the sequence of DRG temporal graphs with special regard to the distribution of the $$75\%$$75% most central nodes.We derive the following results: (a) in all cases the closeness measure produces many nodes with high centrality, so it is useless to detect influential users; (b) for the other measures almost all nodes have null or very low centrality and (c) the number of vertices with significant centrality are often the same; (d) the above observations hold also for the whole DRG and, (e) central nodes in the sequence of DRG temporal graphs have high centrality in static graphs.

Hidradenitis suppurativa (HS) is an orphan, underdiagnosed and painful disease of the skin that has a considerable negative impact on quality of life and on emotional well-being. As reported by the italian HS patients’ association (Inversa Onlus), this condition brings patients to develop an emotional closure with the consequence that they often don’t talk about their condition with anybody. In this paper we discuss some results obtained by applying automatic emotion detection and social network analysis techniques on the Facebook group of the Inversa Onlus association. In particular, we analyze the patients’ emotional states, as expressed by the post published from 2010 to 2016, and how these emotions are influenced by friendships in the group, during the years.

Many and varied experiences are being reported, about the first introduction to programming for young students and neophytes. However, tools and methodologies are needed also for a more comprehensive learning process, which requires to design the architecture of any small but functioning application. We propose a new environment, based on the use of graphical blocks, for designing some object-oriented applications. It merges the positive features of block-programming with the object-oriented paradigm in a graphical educational environment. It is developed as a tool for supporting the objects-early approach. The whole methodology is targeted at high school students, university freshmen and unemployed people who are motivated to learn to code professionally. In these cases, where we have firstly experimented this approach, the concepts of object-oriented programming (OOP) cannot be relegated to a secondary role, but they have to be introduced early and presented in their most intuitive form.

The work presented here is part of the currently ongoing project “Blexer” (Blender Exergames), which aims at creating a complex exergaming environment for people with physical impairments. The games are thought for daily fitness exercises or rehabilitation and are based on movements captured with the Xbox 360 Kinect® sensor. Via a middleware, the games, currently implemented in the Blender Game Engine, communicate with a web platform called “Blexer-med”, which is the working tool for the health professionals to manage the sessions of their patients. With help of the platform, clinicians can assign different games to their patients, personalize exercises by adjusting their difficulty, and obtain their performance results in real time. The advantage is that the exercises can be adapted by the therapist according to the results without the need to meet the patients, who do the exercise at their homes. This paper presents the architecture and functionalities of the web platform and its belonging database, as well as an example use case. The platform is currently tested by some volunteers suffering from muscular dystrophies, with a newly created adventure game. Although our work focuses on people with disabilities, the platform is generic and could be connected to any kind of exergames aimed at other purposes.

This work presents the “Blexer” (Blender Exergames) environment, which aims at the design and implementation of generic, adaptive and customizable rehabilitation exergames for people with physical disabilities. Currently, it consists in one full play exergame based on the movements captured by the Microsoft Xbox 360 Kinect camera and a medical platform that allows the remote configuration of the game. Opposed to multiple mini-games with specific purposes found in literature, here the focus is set on the design of a full game, which includes a character, a story and advanced game mechanics to achieve the integration of currently four exercises into a 3D adventure videogame. The principle aim is to enhance the patient’s motivation to perform daily exercises with help of the game, therefore we apply the Core Drives defined in the Octalysis framework. Furthermore, the game incorporates a motion amplification functionality to augment the immersive feeling of disabled people in the video games. Last but not least, the configuration possibilities of the exercises included in the game are described.

The knowledge of citizens’ interests and problems is crucial for the smart management of a city. Up to few years ago, the employment of opinion agencies was mandatory to get this knowledge, but since this process is cost and time consuming, many studies are beginning to exploit social media contents to understand citizens. In particular, the attention is usually focused on textual data, and only few studies consider multimedia contents. In this paper, we investigate whether it is possible to know citizens’ interests and problems by using images published in the Instagram platform. In particular, we propose a method that analyzes and measures the importance of hashtags associated to images. The experimental evaluation shows that images could be an important source of information to understand citizens.

People watch TV with a second screen nearby and more than 30% of the time is used to perform social activities. This is why broadcasters are trying to exploit hashtags: they want people to talk about TV-shows in the social scenario. In this paper, we investigate how broadcasters use hashtags to promote their TV-shows. Indeed, we focus on 15 different TV-shows and we perform two different types of analyses: one investigates if broadcasters propose official hashtags and analyzes how these hashtags are promoted, the other investigates the characteristics of the Twitter conversations held around the considered TV-shows. Results show that broadcasters do not have a clear strategy in the social scenario: most of them do not exploit the synergy that can be created by linking the TV scenario to social and Web platforms. However, from the analysis of the Twitter conversations, we identified a successful case, whose analysis allowed us to outline some clear guidelines that broadcasters should employ when using hashtags to promote their TV-shows.

Wearables capable of monitoring steps are important elements of behavior change interventions to increase physical activity. For intervention studies, there is currently the choice between smartphone apps and fitness trackers for self-monitoring daily steps. We report results from a pilot study, in which younger and older participants experienced both types of devices, rated usability, and performed usability tasks. The fitness tracker, which was operated with a single touch-sensitive button, proved advantageous in subjective and objective usability. The discussion includes further aspects of the choice between smartphone apps and fitness trackers for use in interventions.

Clustering is the subset of data mining techniques used to agnostically classify entities by looking at their attributes. Clustering algorithms specialized to deal with complex networks are called community discovery. Notwithstanding their common objectives, there are crucial assumptions in community discovery – edge sparsity and only one node type, among others – which makes its mapping to clustering non trivial. In this paper, we propose a community discovery to clustering mapping, by focusing on transactional data clustering. We represent a network as a transactional dataset, and we find communities by grouping nodes with common items (neighbors) in their baskets (neighbor lists). By comparing our results with ground truth communities and state of the art community discovery methods, we show that transactional clustering algorithms are a feasible alternative to community discovery, and that a complete mapping of the two problems is possible.

The huge quantity of personal data stored by service providers registering customers daily life enables the analysis of individual fingerprints characterizing the customers’ behavioral profiles. We propose a methodological framework for recognizing residents, tourists and occasional shoppers among the customers of a retail market chain. We employ our recognition framework on a real massive dataset containing the shopping transactions of more than one million of customers, and we identify representative temporal shopping profiles for residents, tourists and occasional customers. Our experiments show that even though residents are about 33% of the customers they are responsible for more than 90% of the expenditure. We statistically validate the number of residents and tourists with national official statistics enabling in this way the adoption of our recognition framework for the development of novel services and analysis.

This paper describes a web-based system composed of an authoring tool and a cross-platform mobile application, based on augmented reality and Bluetooth Low Energy technology, aimed at improving the visitor experience in a museum through tailored, accessible and engaging content and interaction. The system proposes itself as a low-cost solution for museum organizations, both in terms of required technical devices (visitors’ smartphone is exploited for experiencing the augmented reality solution) and professional skills needed for long-term content maintenance. As to the latter, the authoring tool allows museum curators to create and manage all necessary contents that make up an app instance, including the structure of the museum, artwork descriptions and related materials (photos, videos and speeches) suitable for the different user profiles. A preliminary experimentation of the system demonstrates the feasibility of the proposal.

We describe the design of a game-based Web application aimed to support high-functioning individuals affected by Autism Spectrum Disorder in gaining skills that can help them to understand the concept of money and apply it in practical situations of life. In order to evaluate the effectiveness and usability of the games, a user study involving six medium/high-functioning ASD individuals in their teens and above was carried out. Preliminary results were encouraging and show the potential advantages of such a system for training end users on practical life skills.

Discretization is one of the most efficient mathematical approaches to simplify (optimize) a system by transforming a continuous domain into its discrete counterpart. In this paper, by adopting space discretization, we have modified the previously proposed solution called PdUC (Pollution-driven UAV Control), which is a protocol designed to guide UAVs that monitor air quality in a specific area by focusing on the most polluted areas. The improvement proposed in this paper, called PdUC-D, consists of an optimization whereby UAVs only move between the central tile positions of a discretized space, avoiding to monitor locations separated by small distances, and whose actual differences in terms of air quality are barely noticeable. Experimental results show that PdUC-D drastically reduces convergence time compared to the original PdUC proposal without loss of accuracy.