The accurate evaluation of periodontal risk during orthodontic tooth movement remains a major clinical challenge, as excessive lower incisor displacement beyond anatomical limits can result in bone damage and gingival recession. This study proposes a novel artificial intelligence framework, FusionNet-ARC, designed to predict alveolar bone availability directly from standard two-dimensional cephalometric radiographs, enabling data-driven assessment of periodontal risk without the need for high-radiation imaging modalities. A total of 996 anonymized lateral cephalometric radiographs were processed through a dedicated image analysis pipeline to extract six anatomical landmarks and compute two alveolar parameters: ARC1 (lingual bone availability) and ARC2 (vestibular bone availability). The proposed FusionNet-ARC model combines a convolutional neural network (ResNet50) for visual feature extraction with a Graph Attention Network (GAT) for landmark-based spatial reasoning. The fused embeddings were regressed to predict ARC1 and ARC2 values, and model accuracy was assessed using Mean Absolute Error (MAE), coefficient of determination (R2), and prediction match rate within a ±0.5,mm tolerance. The model achieved high predictive precision for both parameters, with 66.1 % of ARC1 and 61.4 % of ARC2 predictions within clinical tolerance, showing strong agreement with manual cephalometric measurements. When applied to periodontal risk classification, it accurately identified the corresponding Normal, Borderline, and At-Risk categories, confirming its reliability for automated estimation of alveolar bone availability and related periodontal risk from standard cephalometric radiographs. The proposed system provides an objective and quantitative method for assessing alveolar bone support within routine orthodontic workflows.

Integrating artificial intelligence into healthcare has been revolutionary, enhancing diagnostic, prognostic, and therapeutic applications. Artificial intelligence has significantly improved accuracy and efficiency in medical imaging, leading to better patient outcomes. In dentistry, particularly in orthodontics, artificial intelligence is essential for automating image-based diagnosis and treatment planning, allowing specialists to evaluate anatomical structures with increased precision. This study suggests an artificial intelligence-based approach to determine the Lower Incisor—Pg, a cephalometric parameter that evaluates the sagittal position of the lower incisor, which is an essential aesthetic and functional factor in orthodontics, affecting facial harmony. Traditional manual methods for identifying this parameter on lateral cephalometric radiographs could be subjected to variability and human error. The proposed artificial intelligence model, called PointIpg, employs deep learning algorithms to automatically identify the Lower Incisor—Pg parameter and assess lower incisor’s potential movement within the lower dental arch, offering orthodontists a tool for accurate treatment planning.PointIpg was trained using a dataset of 996 teleradiographs, from which four cephalometric landmarks (Po, Or, B1, Pg) were extracted using Delta-Dent software and a PointNet++ architecture. The model achieved a Mean Absolute Error of 0.03 mm and an overall accuracy of 97.5%, enhancing precision and consistency in orthodontic planning as a reliable alternative to manual methods.

In this work, we develop and analyze the impact of using a gamified application to encourage users to adopt an eco-sustainable driving style. The proposed solution uses elements of gamification such as rankings, scores, prizes, and levels to encourage and engage the driver in an urban context. The score, in terms of eco-sustainable driving, is calculated by considering vehicle speed, acceleration and braking parameters during the driving session. The application also provides real-time feedback in order to help the driver improve his/her driving style. Whenever the application detects a sudden change in speed, known as an unsustainable behavior, it will warn the user so as to let him/her correct the driving style. Our solution is oriented to assist people in eco-sustainable driving while preventing them from loss of interest and from reverting to his/her former bad driving behaviors.

The evaluation of Dyslexeasy, a reading program for mobile Android devices that is specifically built for people with dyslexia, is presented in this research. Dyslexeasy combines the most effective approach to show text to persons with dyslexia with a unique feature: progressive text reproduction. Our first prototype is for Italian, despite the fact that the novel algorithm employed for this unique feature is language agnostic. We conducted a pilot study with possible stakeholders to evaluate Dyslexeasy. Working with five dyslexic participants, we assessed the effectiveness of the algorithm on the basis of dyslexia, as well as the user experience. Our findings reveal that the participants were satisfied with the quality of the text generated by the algorithm and the overall user experience. As a result, we argue in this paper that a mobile app like Dyslexeasy could have a significant influence on persons with dyslexia.

This paper presents a patient-centered interaction project of Pepper humanoid robotic therapy applications for children with attention deficit. This new therapeutic methodology was created to support and make therapeutic work more attractive. Pepper comes with a tablet and two identical cameras. The tablet is used to make the patients interact with the application, while the cameras are used to capture their emotions in real-time to understand the degree of attention and any difficulties they may have. The interaction with the tablet takes place through some exercises in the form of games. The exercises performed by the patients are analyzed and combined with the data acquired by the cameras. The combination of these data is elaborated to propose adequate levels of therapeutic activity. This process leads to the digitization of the patients' therapeutic path so that any improvement (or worsening) is monitored and makes Pepper a reliable and predictable technological intermediary for the child. The work was developed in collaboration with a diagnostic and therapeutic center, where it is being tested. By interacting with a humanoid robot, children show greater involvement, which can be explained, according to psychologists, by the fact that a robot is emotionally less rich than humans and the patients feel less fearful.

The goal of the present paper is to summarize the content of a “working in progress” position paper produced by the members of the “Women in GI” focus group established within the European Umbrella Organisation for Geographic Information - EUROGI. The paper is collecting data from several sources, namely associations, reports and studies, and presents information about the current situation on the presence and role of women in the GI sector. It can be used to ask more attention from people and institutions directly involved in policy and decision-making activities.

The adoption and deployment of the Internet of Things (IoT) technologies in agroecology raise a challenging research agenda. Agroecology IoT projects feature complex requirements involving: heterogeneous hardware and heterogeneous software systems; data collection architectures, stream and queuing systems as well as data management systems for real-time and batch processing with different data models. On top of that, agroecology IoT applications are characterized by complex spatio-temporal data and low quality communication networks.

In this work, we illustrate an innovative treatment for patients affected by Behavioral Disorders, that relies on the use of Pepper humanoid robot. This new therapeutic methodology was created to support and make the therapist's work more attractive. Pepper is equipped with a tablet and two identical cameras. The tablet is used to let the patient interact with the application, while the cameras are used to capture their real-time emotions to understand the degree of attention and any difficulty that they may have. The interaction with the tablet takes place through some exercises in the form of games. The exercises performed by the subject are analyzed and combined with the data captured by the cameras. The combination of these data is processed to propose appropriate levels of therapeutic activities. This process leads to the digitization of the patient's healing path so that any improvement (or worsening) is monitored and causes Pepper to become a reliable and predictable technological intermediary for the child. The work has been developed in collaboration with a diagnostic and therapeutic center. Interacting with a humanoid robot, children exhibit a higher engagement, which can be explained, according to the psychologists, by the fact that a robot is emotionally less rich than human beings, and the patient feels less scared.

The forest fires represent a social emergency that requires significant economic and organizational commitment. Safety and the lack of reliable and timely localization of firefighters is a big problem. In this paper, we present Karya Advanced Sensor, an automatic, accurate, and reliable IT solution able to locate firefighters in harsh environments and support decision making activities at control rooms. The system consists of sensors perfectly integrated into firefighters' uniforms, which are used to monitor in real-time individual operators' activities as well as the entire fire area. In particular, in case a firefighter gets injured, the system will activate the rescue teams quickly, as there will be a constant link between the firefighters and the medical assistance. The firefighter can also specify the reason for the accident, which is critical information for a more timely and appropriate health intervention. Moreover, the system is able to perform an automatic real-time mapping of forest fires and possibly estimate its propagation rate, providing precious support to control rooms, which are the center of the team coordination.

In Industry 4.0, Human Machine Interfaces are largely used in order to increase the performances of production processes at the same time reducing the number of emergencies and accidents. In manufacturing, the most typical system used to monitor the production is the Andon. It is a graphical system exploited in plants to notify operators who deal with management, maintenance and production performance of the presence of a problem. Of course, the usability of such interfaces is essential to allow an operator to identify and react more effectively to potentially critical situations. Improving the usability of such interfaces is a big challenge due to the increasing complexity of the data that must be processed and understood quickly by operators. In this paper, we present a set of guidelines to help professional developers to design usable interfaces for monitoring industrial production in manufacturing. Such guidelines are based on usability principles and formalized by reviewing existing industrial interfaces. Using a realistic case study prepared with manufacturing experts, we propose an Andon interface that we developed to test the efficacy of these guidelines on a last generation touch-wall device.

Today, the deaf community represents a population of more than 70 million individuals around the globe. Sign language is recognized as one of the most popular means of communication for the deaf. The Convention on the Rights of Persons with Disabilities recognizes and promotes the use of sign languages and establishes that their use is critical to ensuring access to information and services, both in everyday life and during emergencies. However, most public information and service providers do not comply with the goal of providing information and services through speech-to-sign language interpreters. In this paper we leverage the results of our previous work and propose ProSign+, a cloud-based speech-to- sign language platform conceived as an intermediary service for any legal entity which is expected to provide inclusive access to information and services also for deaf people (e.g., public transportation companies, municipalities, hospitals, schools and higher education institutions). The idea is to foster a cost-effective transformation of public service providers towards the goal of leaving no one behind, which is central to the Agenda 2030 for Sustainable Development, adopted by all United Nations Member States in 2015.

This paper deals with the problem of empowering elderly people through adequate interactive applications. We describe a user-centered iterative design methodology which is oriented towards empowerment goals. We present the results of a preliminary study that has involved the project work activities performed by groups of computer science students from the course of human-computer interaction. The projects cover different areas of elderly people's life and the adopted approach has provided interesting insight into the empowerment goals which prevail in each area. The results of the study suggest that, especially when dealing with categories of disadvantaged users, empowerment goals are paramount to gain true usability of a given application.

Spatial OLAP systems are GeoBusiness Intelligence systems allowing the exploration and analysis of huge volume of spatial data by means of tabular, graphic and cartographic displays. Although map readability is crucial for decision-making processes, readability of SOLAP maps has not been deeply investigated. In this paper, a initial study on readability metrics for SOLAP maps and methods to improve them are presented and discussed. The results are validated by using a real case study concerning farmland biodiversity analysis. Some open issues associated to this topic are also discussed.

Crop production problems are common in Sri Lanka which severely effect rural farmers, agriculture sector and the country's economy as a whole. A deeper analysis revealed that the root cause was farmers and other stakeholders in the domain not receiving right information at the right time in the right format. Inspired by the rapid growth of mobile phone usage among farmers a mobile-based solution is sought to overcome this information gap. Farmers needed published information (quasi static) about crops, pests, diseases, land preparation, growing and harvesting methods and real-time situational information (dynamic) such as current crop production and market prices. This situational information is also needed by agriculture department, agro-chemical companies, buyers and various government agencies to ensure food security through effective supply chain planning whilst minimising waste. We developed a notion of context specific actionable information which enables user to act with least amount of further processing. User centered agriculture ontology was developed to convert published quasi static information to actionable information. We adopted empowerment theory to create empowerment-oriented farming processes to motivate farmers to act on this information and aggregated the transaction data to generate situational information. This created a holistic information flow model for agriculture domain similar to energy flow in biological ecosystems. Consequently, the initial Mobile-based Information System evolved into a Digital Knowledge Ecosystem that can predict current production situation in near real enabling government agencies to dynamically adjust the incentives offered to farmers for growing different types of crops to achieve sustainable agriculture production through crop diversification.

Integration of spatial data into multidimensional models leads to the concept of Spatial OLAP (SOLAP). Usually, SOLAP models exploit discrete spatial data. Few works integrate continuous field data into dimensions and measures. In this paper, we provide a formal multidimensional model that supports measures and dimension as continuous field data, independently of their implementation. We provide also a proposal for a logical model allowing aggregation of field measures in a feasible ROLAP architecture.

Nowadays, spatial data are totally widespread in mobile applications. They are present in games, map applications, web community applications and office automations. However this kind of spatial information potentially needs a large display area and the hardware constraint related to the limited screen dimensions creates many usability challenges. Our investigation in the last few years to find solutions to these challenges has led us to the discovery of general usability principles that a well-designed interface should adopt. In this paper we describe the mental path we have followed to derive those principles from the experience gained in developing mobile interfaces for different application domains. The principles are formalized in terms of two interaction design patterns, specific for mobile interfaces managing spatial data. They extend existing HCI patterns and are completed, as usual, with concrete examples of their applications.

This paper reports the initial results of a research project to investigate how to develop a web based spreadsheet mediated business collaboration system that could notably enhance the business processes presently carried out by Small to Medium sized Enterprises. Using a scenario-based design approach, a set of user's requirements were extracted from an appropriate field study. These requirements were then analysed in the context of well-known usability principles, and a set of design implications were derived based on a selected set of HCI design patterns related to cooperative interaction design. Starting from that knowledge, suitable interactive collaboration scenarios have been drawn, from which a list of user interface requirements for a web based spreadsheet mediated collaboration system has been formulated.

Spreadsheets are intensively used for crucial management activities by several organizations. Collaboration through spreadsheet is recognized to be a powerful means to enhance crucial activities carried out in Small and Medium sized Enterprises (SME). However, the main obstacles to its realization appears to be the small size and the limited human and financial resources, which usually characterize SMEs themselves. We present a collaborative environment for spreadsheet-based activities, that overcomes such limitation allowing a smooth shift from single user to multiple user spreadsheet application deployment.

Abstract In this paper, we describe theit Search Tree visual language. It is a novel methodology able to support users to build up complex queries to be run on given search engines. For using this visual language, neither parentheses nor precedence rules are needed, nor the specific ability to perform advanced search tasks. The language is proven to have the same expressive power as the expressions in Sum Of Product form. In order to prove the appropriateness of our proposal, we measured the usability of the proposed querying approach against the traditional Yahoo TM web search query language. Results show that, even if both the approaches fully support users in terms of efficacy, the Search Tree visual language significantly improves task efficiency, both in terms of the number of actions performed and the time requested with respect to the advanced search interface. Copyright © 2010 John Wiley & Sons, Ltd.

In the present paper, we propose an approach for the development of Web GIS based on WebML, a high-level, formal visual language specifically conceived to design data-intensive Web applications. The proposal is motivated by the observation that Web GIS can be considered as a particular class of data-intensive Web applications. In the paper, we describe the extension of the visual formalism for modeling relevant interaction and navigation operations typical of Web GIS.

In the present paper, we propose a visual language meant to support the design of Web GIS applications. The proposal is based on the observation that Web GIS can be considered as a particular class of data- intensive Web applications, since they are mainly devoted to handle (spatial) information to and from the user. The success of WebML (Web Modeling Language) for designing traditional data-intensive Web applications suggested us to extend this visual formalism to model relevant interaction and navigation operations typical of Web GIS. The proposed extension consists of a set of content units specifically tailored for GIS concepts and tasks.

Recently, much attention has been devoted to the management of continuous fields, which describe geographic phenomena, such as temperature, electromagnetism and pressure. While objects are distinguished by their dimensions, and can be associated with points, lines, or areas, such phenomena can be measurable at any point of their domain by distinguishing what varies, and how smoothly. Thus, when dealing with continuous fields, a basic requirement is represented by users' capability to capture some features of a scenario, by selecting an area of interest and handling the involved phenomena.The aim of our research is to provide GIS users with a visual environment where they can manage both continuous fields and discrete objects, by posing spatial queries which capture the heterogeneous nature of phenomena. In particular, in this paper we propose a visual query language Phenomena, which provides users with a uniform style of interaction with the world, which is conceptually modeled as a composition of continuous fields and discrete objects. The intuitiveness of the underlying operators as well as of the query formulation process is ensured by the choice of suitable metaphors and by the adoption of the paradigm of direct manipulation.A prototype of a visual environment running Phenomena has been realized, which allows users to query experimental data by following a SQL-like SELECT-FROM-WHERE scheme.

International audience

The aim of our research is to provide GIS users with a visual environment where they can formulate spatial queries which implicitly capture the double nature of geographical data. In particular, in this paper we propose an extension to the MGISQL visual environment, where users may pose 3D queries about those phenomena where the third dimension is a relevant feature for data retrieving. The interaction between users and the visual environment is performed by manipulating 3D geometaphors. The underlying algebra for spatial operators is enriched accordingly. Visual queries are composed in a 3D environment, called the Sensitive Cube, characterized by the 3D geometaphors, visualized as 'floating objects'.

Many authoring systems have been realized so far in order to allow users to build advanced presentation of documents. These systems represent the result of a requirement analysis performed in specific application domains and their functionality is meaningful for the domain experts. Consequently, in many cases there exists a barrier between system functionality and users, who have a limited knowledge of the domain: in order to use the application, the content expert end-user has to interact with the application expert. Such a barrier limits the effectiveness and the efficiency of the authoring system, because the development of a multimedia presentation forces the user to acquire experience far from his/her background. In this paper we introduce a new approach to educational authoring, based on a multilevel development methodology. It allows and supports teachers to create their own multimedia learning environment. The proposed approach has been experimented on an initial prototype which allows users to manage multimedia authoring of units of study.

We introduce the virtual image, an iconic index suited for pictorial information access in a pictorial database, and a similarity retrieval approach based on virtual images to perform content-based retrieval. A virtual image represents the spatial information contained in a real image in explicit form by means of a set of spatial relations. This is useful to efficiently compute the similarity between a query and an image in the database. We also show that virtual images support real-world applications that require translation, reflection, and/or rotation invariance of image representation.