https://repositorio.ufpb.br/jspui/handle/tede/5439 PPGI Sun, 28 Jun 2026 06:12:42 GMT 2026-06-28T06:12:42Z http://repositorio.ufpb.br:443/jspui/retrieve/30178/ https://repositorio.ufpb.br/jspui/handle/tede/5439 https://repositorio.ufpb.br/jspui/handle/123456789/38240 Título: Diagnóstico em tempo real de falhas em drones através das análises de sinais de vibração baseadas no caos usando densidade e amplitude de máximos Autor(es): Nunes, Alexandre Magno da Silva Orientador: Brito, Alisson Vasconcelos de Abstract: The Unmanned Aerial Vehicle (UAV) has become popular over the years in various ac- tivities, whether commercial or recreational. However, drones still do not have complete confidence when it comes to safety. Therefore, there is a need to create fault identification techniques that fit the limitations found. This work aims to detect and diagnose drone failu- res in real time and proposes an architecture to identify mechanical failures. The approach proposed in the work uses chaos-based signal analysis techniques using maximum density (SAC-DM) and maximum amplitude (SAC-AM). To achieve the results, data were captured from a quadcopter drone and applied classification techniques and algorithms. With SAC- DM, performances of 91% were achieved and with SAC-AM 100%. It was also possible to validate the system by diagnosing faults in real time. Editor: Universidade Federal da Paraíba Tipo: Dissertação Wed, 31 Aug 2022 00:00:00 GMT https://repositorio.ufpb.br/jspui/handle/123456789/38240 2022-08-31T00:00:00Z https://repositorio.ufpb.br/jspui/handle/123456789/37836 Título: Videoconferência Acessível para Deficientes Auditivos com Avatar de Libras Automático Autor(es): Soares Filho, José Leoberto Orientador: Souza Filho, Guido Lemos de Abstract: Given the increased use of synchronous conferences in the daily activities of the Brazilian population, various adversities have arisen or been exacerbated through this new but already established means of communication. The lack of accessibility for individuals with some form of hearing impairment is one of the most notable challenges, because this portion of society, according to the census conducted by the Brazilian Institute of Geography and Statistics (IBGE) in the year 2010, represented approximately 9.7 million people at that time. There are several laws that ensure access to information for deaf individuals, however, professionals qualified for Portuguese to Brazilian Sign Language (Libras) translation are still a scarce group. With this in mind, this work proposes the incorporation of a Libras Avatar for translating spoken Portuguese language into sign language, while also adding the functionality of automatic captions within the Video For Health (V4H) tool. The results obtained from the proposed experiments showed that the understanding of deaf individuals in videoconferences significantly improved when using the developed tool compared to the platforms available on the internet. Editor: Universidade Federal da Paraíba Tipo: Dissertação Thu, 31 Aug 2023 00:00:00 GMT https://repositorio.ufpb.br/jspui/handle/123456789/37836 2023-08-31T00:00:00Z https://repositorio.ufpb.br/jspui/handle/123456789/37643 Título: Gerenciamento de interseções para otimização do tráfego de carros autônomos Autor(es): Silva, Victor Hugo Azevêdo da Orientador: Siebra, Clauirton de Albuquerque Abstract: Intersections have become, due to the rapid growth of the population of the cities, a prone place for auto accidents and also the main cause of traffic congestion. This work presents a virtual system capable of managing and optimizing the traffic of a region in an environment of autonomous cars. This approach introduces constraints that ensure the safety of stand-alone vehicles, so that they can take advantage of the benefits offered by this new technology without losing confidence. We proposed to remove all traffic lights and signboards present at the intersections, giving the system the responsibility to manage traffic. The results using the SUMO simulator demonstrate that the system was able to optimize vehicle traffic in the various regions used as case studies. Editor: Universidade Federal da Paraíba Tipo: Dissertação Fri, 09 Aug 2019 00:00:00 GMT https://repositorio.ufpb.br/jspui/handle/123456789/37643 2019-08-09T00:00:00Z https://repositorio.ufpb.br/jspui/handle/123456789/37387 Título: Aplicação de técnicas sociais de ambientes SIoV para apoiar a disseminação de eventos emergenciais com qualidade de experiência Autor(es): Medeiros, Alisson Yury Dutra de Orientador: Matos, Fernando Menezes Abstract: The support and daily treatment of critical events in cities are among the significant challenges of urban centers. Such events can negatively impact the proper functioning of cities and cause physical and material damage to the population. Because of that, it is necessary to promptly notify the competent authority to take appropriate actions efficiently and thus mitigate the effects of the event. The Vehicular Ad-hoc Networks (VANETs) are an alternative to support the notification of information about emergency events due to the ubiquity of vehicles in cities. The vehicles with embedded cameras and sensors can assist in event detection. Although the dynamicity of the VANETs compromises the communication, the social relationships between vehicle drivers establish local communities, which can support public authorities in the treatment of events by employing social intelligence in the data collected by the VANET. Thus, this dissertation proposes SOCIABLE (SOCial monItoring and disseminateAtion of urBan criticismL Events), a robust data dissemination system for urban critical events that operates in a Social Internet of Vehicles (SIoV) network. The SOCIABLE takes into account the relationships established between vehicles with common interests or routines to create local communities. It also applies social techniques to perform an intelligent selection of relays to carry out targeted dissemination (multicast) in order to expedite data delivery, thus helping the event handling. An evaluation made through the NS-3 simulator showed the effectiveness of the SOCIABLE in carrying out the monitoring, dissemination, and delivery of data from events detected in different traffic contexts in a faster manner and with less computational resources than a system that does not employ social parameters. We also analyzed the quality of experience obtained with the social strategies employed by SOCIABLE, where the strategies with friendship and social activity allowed a video delivery with better resolution in different traffic contexts. Editor: Universidade Federal da Paraíba Tipo: Dissertação Thu, 29 Jul 2021 00:00:00 GMT https://repositorio.ufpb.br/jspui/handle/123456789/37387 2021-07-29T00:00:00Z