Browsing by Author "Kalbermatter, Rebeca B."
Now showing 1 - 9 of 9
Results Per Page
Sort Options
- Automatic Fall Detection with Thermal CameraPublication . Kalbermatter, Rebeca B.; Franco, Tiago; Pereira, Ana I.; Valente, António; Soares, Salviano Pinto; Lima, JoséPeople are living longer, promoting new challenges in healthcare. Many older adults prefer to age in their own homes rather than in healthcare institutions. Portugal has seen a similar trend, and public and private home care solutions have been developed. However, age-related pathologies can affect an elderly person’s ability to perform daily tasks independently. Ambient Assisted Living (AAL) is a domain that uses information and communication technologies to improve the quality of life of older adults. AI-based fall detection systems have been integrated into AAL studies, and posture estimation tools are important for monitoring patients. In this study, the OpenCV and the YOLOv7 machine learning framework are used to develop a fall detection system based on posture analysis. To protect patient privacy, the use of a thermal camera is proposed to prevent facial recognition. The developed system was applied and validated in the real scenario.
- Design and Development of an Omnidirectional Mecanum Platform for the RobotAtFactory 4.0 CompetitionPublication . Braun, João; Baidi, Kaïs; Bonzatto, Luciano; Berger, Guido; Pinto, Milena F.; Kalbermatter, Rebeca B.; Klein, Luan C.; Grilo, Vinicius F.S.B.; Pereira, Ana I.; Costa, Paulo Gomes da; Lima, JoséRobotics competitions are highly strategic tools to engage and motivate students, cultivating their curiosity and enthusiasm for technology and robotics. These competitions encompass various disciplines, such as programming, electronics, control systems, and prototyping, often beginning with developing a mobile platform. This paper focuses on designing and implementing an omnidirectional mecanum platform, encompassing aspects of mechatronics, mechanics, electronics, kinematics models, and control. Additionally, a simulation model is introduced and compared with the physical robot, providing a means to validate the proposed platform.
- Energy Efficiency Analysis of Differential and Omnidirectional Robotic Platforms: A Comparative StudyPublication . Chellal, Arezki Abderrahim; Braun, João; Junior, Luciano Bonzatto; Faria, Milena; Kalbermatter, Rebeca B.; Gonçalves, José; Costa, Paulo Gomes da; Lima, JoséAs robots have limited power sources. Energy optimization is essential to ensure an extension for their operating periods without needing to be recharged, thus maximizing their uptime and minimizing their running costs. This paper compares the energy consumption of different mobile robotic platforms, including differential, omnidirectional 3-wheel, omnidirectional 4-wheel, and Mecanum platforms. The comparison is based on the RobotAtFactory 4.0 competition that typically takes place during the Portuguese Robotics Open. The energy consumption from the batteries for each platform is recorded and compared. The experiments were conducted in a validated simulation environment with dynamic and friction models to ensure that the platforms operated at similar speeds and accelerations and through a 5200 mAh battery simulation. Overall, this study provides valuable information on the energy consumption of different mobile robotic platforms. Among other findings, differential robots are the most energy-efficient robots, while 4-wheel omnidirectional robots may offer a good balance between energy efficiency and maneuverability.
- Monitoring system for smart buildings - apolo building casePublication . Kalbermatter, Rebeca B.; Brito, Thadeu; Braun, João; Pereira, Ana I.; Lima, JoséThe demand for better safety and comfort conditions in social centers served as an incentive to improve the automation of buildings, making them intelligent systems that could be integrated. However, alongside these innovations, there has also arisen a concern for the ecological risks surrounding the smart building. With these factors as a basis, this work aimed to monitor three main systems within each apartment in the Apolo Building (Bragan¸ca, Portugal), namely electricity consumption, water consumption, and waste disposal. These systems are integrated through a common database, where they are being stored. This study intends to create a platform for data analysis, making it accessible to the consumer, raising awareness of the expenses generated, and looking for short and long term efficiency measures.
- A realistic simulation environment as a teaching aid in educational roboticsPublication . Lima, José; Kalbermatter, Rebeca B.; Braun, João; Brito, Thadeu; Berger, Guido; Costa, Paulo Gomes daThe experimental component is an essential method in Engineering education. Sometimes the availability of laboratories and components is compromised, and the COVID-19 pandemic worsened the situation. Resorting to an accurate simulation seems to help this process by allowing students to develop the work, program, test, and validate it. Moreover, it lowers the development time and cost of the prototyping stages of a robotics project. As a multidisciplinary area, robotics requires simulation environments with essential characteristics, such as dynamics, connection to hardware (embedded systems), and other applications. Thus, this paper presents the Simulation environment of SimTwo, emphasizing previous publications with models of sensors, actuators, and simulation scenes. The simulator can be used for free, and the source code is available to the community. Proposed scenes and examples can inspire the development of other simulation scenes to be used in electrical and mechanical Engineering projects. © 2022 IEEE.
- Smart systems for buildingsPublication . Kalbermatter, Rebeca B.; Lima, José; Pereira, Ana I.; Ferreira, Ângela P.; Moritz, Guilherme LuizLife in society has initiated a search for comfort and security in social centers. This quest has generated revolutions within the knowledge about the technologies involved, making the environment automated and integrated. Along with this increase, ecological concerns have also arisen, which have been involved since the conception of intelligent structures, remaining throughout their use. Based on these two pillars, the present study aims to cover three central systems inside the apartments of the Apolo Building (Bragança, Portugal). The monitoring of the energy and water consumption and waste disposal systems are integrated by storing the data in a single database in InfluxDB. The data is collected through the sensors and transmitted via Wi-Fi, allowing real-time monitoring through the Grafana application. This data collection makes it possible to track the resident’s behavior through the applied machine learning algorithm. In addition, the collected data should be visible to the resident, bringing together ecological solutions that minimize the expenditure of the building’s resources. Through continuous observation of the data, it will be possible to analyze whether there have been changes in the resident’s behavior through the data presented. Besides dealing only with technical data, this analysis can bring advantages in the search for better ecological awareness of each resident. There is no point in seeking efficient solutions for the building if each resident does not has own actions do not aim at it.
- Smart systems for monitoring buildings - an IoT applicationPublication . Kalbermatter, Rebeca B.; Brito, Thadeu; Braun, João; Pereira, Ana I.; Ferreira, Ângela P.; Valente, António; Lima, JoséLife in society has initiated a search for comfort and security in social centers. This search generated revolutions within the knowledge about the technologies involved, making the environments automated and integrated. Along with this increase, ecological concerns have also arisen, which have been involved since the design of intelligent buildings, remaining through the years of their use. Based on these two pillars, the present study aims to monitor three central systems inside the apartments of the Apolo Building (Bragan¸cacity, Portugal). The electrical energy consumption, water flow, and waste disposal systems are integrated through a single database. The data is sent remotely via WiFi through the microcontroller. For better visualization and analytics of the data, a web application is also developed, which allows for real-time monitoring. The obtained results demonstrate to the consumer his behavior regarding household expenses. The idea of showing the consumer their expenditure is to create an ecological awareness. Through the data collected and the environmental alternatives found, it is possible to observe whether there was a behavior change when receiving this data, either in the short or long term.
- A ubiquitous learning approach on roboticsPublication . Mota, Fernanda P.; Kalbermatter, Rebeca B.; Oliveira, Lizandro de S.; Lima, JoséUbiquitous learning refers to the integration of learning processes with everyday environments and activities using technology. By leveraging ubiquitous learning principles in the field of robotics, we can foster an immersive and interactive learning environment that promotes continuous learning and knowledge acquisition. This paper presents an in-depth exploration of a ubiquitous learning approach for robotics with the aim to enhance the educational experiences and capabilities of robotic systems. Furthermore, it explores the potential benefits and challenges of ubiquitous learning in the field of robotics, such as increased adaptability, personalized learning experiences, and the development of lifelong learning skills. The results indicate that a ubiquitous learning approach can significantly enhance the learning capabilities of students.
- XAI Framework for Fall Detection in an AAL SystemPublication . Messaoudi, Chaima; Kalbermatter, Rebeca B.; Lima, José; Pereira, Ana I.; Guessoum, Zahia; Kalbermatter, Rebeca B.The Ambient Assisted Living (AAL) systems are humancentered and designed to prioritize the needs of elderly individuals, providing them with assistance in case of emergencies or unexpected situations. These systems involve caregivers or selected individuals who can be alerted and provide the necessary help when needed. To ensure effective assistance, it is crucial for caregivers to understand the reasons behind alarm triggers and the nature of the danger. This is where an explainability module comes into play. In this paper, we introduce an explainability module that offers visual explanations for the fall detection module. Our framework involves generating anchor boxes using the K-means algorithm to optimize object detection and using YOLOv8 for image inference. Additionally, we employ two well-known XAI (Explainable Artificial Intelligence) algorithms, LIME (Local Interpretable Model) and Grad-CAM (Gradient-weighted Class Activation Mapping), to provide visual explanations.