Percorrer por autor "Oliveira, Pedro Filipe"
A mostrar 1 - 10 de 53
Resultados por página
Opções de ordenação
- 3D-Chatbot: A Intelligent Conversational Agent Integrating RAG, NLP, And VR For Commercial StoresPublication . Telmo Sampaio; Oliveira, Pedro Filipe; Matos, PauloThis paper presents a comprehensive 3D chatbot system that combines advanced AI capabilities with practical commercial applications in immersive virtual reality environments. The system integrates natural language processing, retrieval-augmented generation (RAG) architectures, and real-time speech processing to create seamless customer inquiry experiences. The implementation combines four main components: an intelligent data acquisition pipeline that transforms over 1,000 unstructured web documents into AI-ready knowledge bases; an advanced RAG system utilizing OpenAI's text-embedding-3-small model and Pinecone vector database for semantic search; multimodal speech processing with real-time speech-to-text conversion and lip-sync animation; and a Unity-based VR environment with professional avatar interactions. The results demonstrate exceptional performance with a 94.6% success rate across 65 test interactions, achieving response times under 100 milliseconds for knowledge retrieval and completing full voice response cycles in less than 3 seconds. The system maintains conversation context through a six-step interaction flow while accessing external knowledge sources, with 96.9% contextually appropriate responses and 92.3% conversation continuity in multi-turn dialogues. Performance optimizations ensure responsive operation under variable load conditions, demonstrating the viability of intelligent virtual assistants in three-dimensional commercial spaces.
- A prototype to enhance academic attendance using BLE beaconsPublication . Simas, Sily; Oliveira, Pedro Filipe; Matos, PauloThis project addresses the prototyping and application of an attendance control solution in an academic context, using Beacons. The introduction highlights the importance of effectively managing student attendance to ensure active participation in educational activities and provide insights into student engagement. BLE Beacons technology is compared to other RF signaling technologies, highlighting its advantages in terms of range, power consumption, cost, frequency, and data rate. BLE Beacon is chosen as the preferred technology due to its combination of adequate range, low power consumption, affordable cost, compatibility, security, and flexibility. The results section presents Estimote Beacons as devices used, highlighting their advanced features and techniques used, such as proximity and triangulation, to determine student presence. A visual summary of the project is presented in a flowchart that illustrates the operating processes of each stage. This solution promises to significantly improve the efficiency, safety, and quality of the academic environment, while simplifying the attendance recording process and providing valuable insights into student behavior.
- Adaptive environment system to manage comfort preferences and conflictsPublication . Oliveira, Pedro Filipe; Novais, Paulo; Matos, PauloManaging comfort preferences conflicts of the different users and locals on an Internet of Things (IoT) adaptive system is a actual problem. This paper, proposes a protocol and hierarchical rules to develop a multi-agent system to achieve an Adaptive Environment System that supports interaction between persons and physical spaces, where spaces smartly adapt to their preferences in a transparent way. And also a set of security customization’s to secure the actuators and users on space, that has been developed using a multi agent system architecture with different features to achieve a solution that supports the proposed objectives. Supported by a base architecture to achieve the full system implementation.
- Adaptive system to manage everyday user comfort preferencesPublication . Oliveira, Pedro Filipe; Novais, Paulo; Matos, PauloUrban mobility brings many challenges and opportunities, particularly regarding sustainability. It is natural that we want better living conditions, we are naturally given to consuming, even when there is no need, we increasingly want to travel, socialize, enjoy and it is not easy to accept that we will most likely have to change. It is no longer a distant future, but the present that we are living. Even in the face of successful solutions, receptivity is far from being massified and in most cases it imposes compromises in terms of comfort and quality of life, sometimes even imposing new habits and ways of being. In addition, not all of us have the same perception of the situation seriousness, or the same willingness to compromise. And this can happen for numerous reasons, namely physical or health limitations, financial limitations, different beliefs/motivations, or different ways of facing problems. It is even common that the staunchest defender of certain solutions, when faced with other equally plausible solutions, is completely insensitive or even opposed. In fact, the same individual may have different needs/preferences relatively to the place where he is or the activity he is performing, that is, preferences that vary with time and place. In a broader context of mobility, in which individuals in their daily lives move and visit different places, often with the presence of more people, the situation is even more complex, the variability of preferences increases, and it is necessary to combine preferences/needs of different individuals. Emerging technologies, within the Internet of Things (IoT) scope and smart spaces [1], allow us to aspire to capable solutions in line with the urban mobility and sustainability demands and, at the same time, to promote better conditions of comfort and well-being, without imposing sacrifices or changes in habits and considering the specificities of each individual, at different time and place. These solutions whose success depends in part on the autonomy of operation, not requiring any direct and conscious participation of people, for the ability to make the best decisions given the current context and future expectations, the context being defined by the characteristics of the environment. Including the dynamics, namely those resulting from the presence/involvement of people, but also for the transparency of action, not being evasive and, if possible, fulfilling its function without people realizing the existence of the technology/solution simply the most convenient happens. There are other factors that should not be neglected, such as those related to security and privacy. In this paper, the authors propose an architecture that considers these requirements so that, in a non-evasive way, it adapts the different spaces that the user frequents (house, work, leisure, others) to their personal preferences, such as temperature, humidity, sound, environment, etc. The architecture includes the different devices needed, to identify users, as well as the communication technologies to be used to transfer the preferences of each user to the system. The architecture includes a multi-agent system that allows managing conflicts of preferences through a user’s hierarchy and that considers safety values for each preference, to safeguard the different actuators (air conditioning, fan coils, multimedia, etc.) present in space. It was developed, focusing on the definition of each user's preferences in a smartphone application, which allows the user's preferences to be transferred to the space, without the need to perform any interaction, they can also be passed through smartwatches, fitness bracelets and similar devices, which currently have different communication technologies such as Bluetooth Low Energy (BLE), Near Field Communication (NFC) or Wifi-Direct. It also contains a local processing solution, currently supported by a Raspberry Pi, and will be present in each space where we want to adapt to different preferences. Each of these systems constantly receives each present user preferences. Based on the multi-agent system, it calculates the optimal preferences to be applied to each space at a given time. It is also responsible for sending these to the different actuators present in the space. The multi-agent system has different layers (simulation, data acquisition, user information, actuation). Briefly, there is an agent for each user present, containing their preferences, and there is an agent that represents the pace, containing eventual constraints, such as security values and others that may exist, namely in public spaces. Each of these agents aims to represent the interests of the involved parties. For example, the agent representing the space should be focused on an efficient use of equipment, minimizing energy costs, enhancing the durability of the equipment, minimizing maintenance costs. Taking advantage of the different hierarchies, an equation was devised that meets the different preferences to define the optimal solution, which will be sent to the different actuators.
- Adaptive system to manage user comfort preferences and conflicts at everyday environmentsPublication . Oliveira, Pedro Filipe; Novais, Paulo; Matos, PauloNowadays an actual problem on IoT adaptive systems is to manage user preferences and local actuators specifications. This paper uses a multi agent system to achieve a Adaptive Environment System, that supports interaction between persons and physical spaces, where spaces smartly adapt to their user preferences in a transparent way. This work has been developed using a multi agent system architecture with different features to achieve a solution that reach all the proposed objectives.
- An AI-driven Ukrainian history web platformPublication . Kolomiets, Valentyna; Oliveira, Pedro Filipe; Matos, PauloThe AI-driven Ukrainian History web platform offers an innovative way for users to engage with the nation’s rich history. By integrating artificial intelligence, natural language processing (NLP), and geospatial analysis, it presents historical events, significant locations, and notable figures in an interactive and visually engaging format. The platform systematically gathers historical data using tools like Scrapy for web scraping and Tesseract OCR for digitizing scanned documents. While noisy or degraded documents may affect accuracy, the availability of high-quality sources ensures reliable data extraction. Fine-tuned NLP models, including transformers like BERT and RoBERTa, process the data to identify and categorize key entities such as dates, locations, and names of historical figures. Contextual summarization ensures the extracted information is both accurate and easy to understand. Geospatial data is managed with PostGIS, an extension of PostgreSQL, and visualized using Leaflet.js. An interactive map interface enables users to explore events by location and time period, with filters for categories like political milestones or cultural events. The backend, built on PostgreSQL, ensures scalability and performance, while development in Visual Studio Code streamlined integration across components. This platform not only preserves Ukraine’s cultural heritage but also demonstrates the potential of modern technology to transform historical education, offering an intuitive way to connect with the past and explore its influence on Ukraine’s landscape and culture.
- An intelligent environment application case to manage comfort preferences, at an University residencePublication . Oliveira, Pedro Filipe; Matos, PauloThis paper presents a novel application of intelligent environmental management within a university residence, aiming to enhance the overall well-being and satisfaction of residents by dynamically addressing their comfort preferences. The proposed system leverages cutting-edge technologies such as Internet of Things (IoT) sensors, machine learning algorithms, and smart devices to create an adaptive and responsive living environment. Through real-time data collection and analysis, the system learns individual and collective comfort patterns, allowing for personalized adjustments to temperature, and other environmental factors. The study focuses on the development and implementation of the intelligent environment application, emphasizing user-centric design and seamless integration into daily life. Residents are empowered to set and modify their comfort preferences through a user-friendly interface, while the system continuously refines its understanding of these preferences over time. Additionally, the application considers energy e!ciency and sustainability, contributing to a greener and more resource-conscious university residence. The paper discusses the technical architecture of the intelligent environment application, including the deployment of sensors, data processing pipelines, and the communication infrastructure. Furthermore, it addresses privacy concerns by outlining robust security measures and anonymization techniques to protect user data. In conclusion, this paper contributes to the growing body of research on intelligent environments by showcasing a practical application tailored to university residence settings. The presented system not only prioritizes resident comfort but also aligns with the broader goals of sustainability and resource optimization, making it a valuable addition to smart living solutions in educational institutions.
- Aplicação de bluetooth low energy no controlo e monitorização de dispositivos de muito baixo consumoPublication . Oliveira, Pedro Filipe; Matos, PauloThis work was performed in an industrial context, a collaboration between the Polytechnic Institute of Bragança and Techwelf Ltd, a company developing control solutions for energy management. The collaboration aimed to solve a concrete problem of one of the devices that is under development at this company, aiming to strengthen the competitive advantages of the product. The challenge was to analyze the feasibility of using Bluetooth Low Energy as wireless communication solution enabling secure monitoring and control of the device from a smartphone. But ensuring maximum energy autonomy of the device, considered as critical factor, given that communication is the main cause of energy consumption. The work carried out resulted in a technical, fully functional solution, which uses the chip nRF51822 from Nordic and an Apple iPhone. The entire system has been optimized, including the Bluetooth Low Energy GATT services, in order to maximize the autonomy of the device while ensuring the reliability and security of communication. Many of the details of the work performed and the product concerned were purposely omitted as a result of the secrecy and confidentiality agreement signed by the proposer of the dissertation.
- Architecture for efficient food management and waste reductionPublication . Pereira, Hélder; Oliveira, Pedro Filipe; Matos, PauloThis article presents a modular architecture for developing the ZeroWaste mobile application, designed to optimize food management in the home environment and reduce food waste through collaborative and scalable features. Food waste is a global issue with severe environmental, economic, and social repercussions, and ZeroWaste seeks to address this challenge by promoting conscious and sustainable consumption practices. Developed in React Native to support multiple platforms, the application integrates Firebase for authentication, notifications, and real-time data storage, enabling timely alerts on product expiration and facilitating user control over food inventory. Additionally, it incorporates an artificial intelligence module that suggests personalized recipes based on available products, encouraging food usage before spoilage. The proposed architecture also includes an automated product registration system using barcode scanning, supporting the creation of a community database that streamlines food item identification. Other features, such as shared shopping lists and multi-residence inventory management, expand the collaborative scope of the application, fostering the exchange and donation of food between users. With its flexible and expandable design, ZeroWaste is oriented towards continuous development and future improvements, meeting the growing need for technological solutions in sustainable and collaborative food management. This architectural proposal provides a robust foundation for developing an innovative solution.
- Augmented Reality and Mixed Reality in the Factory of the Future: A Bibliometric AnalysisPublication . Monteiro, Redney; Ana Mara Moreira; Moreira, André; Jorge Laranjeira; Barbosa, José; Oliveira, Pedro Filipe; Cunha, Carlos R.; Paulo Leitão; Leitão, PauloMixed Reality (MR) and Augmented Reality (AR) - technologies which are part of the spectrum of Extended Reality (XR) - are considered emerging technologies and have gained increasing attention across multiple sectors, including Tourism and Healthcare, due to their versatility as tools for training, simulation, and education, as well as their potential to serve as innovative Human-Machine Interfaces (HMI). Simultaneously, other emerging technologies such as Internet of Things (IoT), Artificial Intelligence (AI), and Robotics have become central themes in R&D associated with the Fourth Industrial Revolution, commonly referred to as Industry 4.0, which emphasizes the digital transformation of industrial processes, through the integration of the new technologies. Beyond their relevance to Industry 4.0, XR technologies are also potential technologies in the emerging paradigm of Industry 5.0, which shifts the focus toward human-centric solutions and collaboration between humans and machines, this potential being based on the ability to enhance human interaction with complex systems. This paper presents the results of a bibliometric analysis of 634 peer-reviewed journal articles indexed in Web of Science and Scopus, spanning research from the past decade (2015 - 2025), as contribute to support future research and guide relevant stakeholders by identifying prevailing trends, leading contributors, and key publication sources in the domain of XR applied to industrial contexts.