http://repositorio.ufc.br/handle/riufc/472 2026-06-11T04:27:23Z 2026-06-11T04:27:23Z Nascimento, Vanessa Carvalho do http://repositorio.ufc.br/handle/riufc/86626 2026-06-09T16:54:10Z 2026-01-01T00:00:00Z

Título: Graph attention network para reconhecimento de emoções a partir de eletroencefalogramas Autor(es): Nascimento, Vanessa Carvalho do Abstract: The automatic recognition of emotional states is relevant in several areas, such as mental health, brain-computer interfaces, and affective monitoring systems. Electroencephalography (EEG) is a non-invasive technique for recording brain electrical activity that stands out in this context for directly reflecting the neural states associated with emotions, being harder to mask than facial expressions or voice. However, characteristics such as the non-stationary nature of the signals, low signal-to-noise ratio, and inter-subject variability make this task challenging. In this scenario, Graph Neural Networks (GNNs) stand out for directly modeling the relationships between EEG channels. Thus, this work proposes a model based on Graph Attention Network (GAT), a GNN variant that adaptively weights the contribution of each neighboring channel during information aggregation, for the classification of three emotional states (positive, neutral, and negative) present in the SJTU Emotion EEG Dataset (SEED). Each EEG sample is represented as a graph whose nodes correspond to EEG channels and whose edges connect pairs of channels whose cosine similarity between their respective feature vectors exceeds the 70th percentile of the sample similarity distribution. Among the 62 channels and 5 frequency bands conventionally used in the literature, only 4 channels (FT7, FT8, T7, and T8) and 2 bands (delta and theta) were selected, resulting in a compact configuration with potential application in wearable devices with a limited number of electrodes. Experiments were conducted under the Leave-One-Subject-Out (LOSO) protocol, which evaluates generalization across subjects. The model achieves a mean accuracy of 95.38% over 10 independent runs, outperforming many comparable works that use the full channel and band configuration, indicating that graph-based modeling captures relevant discriminative patterns even with a reduced configuration. Tipo: Dissertação

2026-01-01T00:00:00Z Ramos, Alex de Sousa http://repositorio.ufc.br/handle/riufc/86625 2026-06-08T14:06:17Z 2026-01-01T00:00:00Z

Título: NaVISOL: desenvolvimento de um chatbot com sistema de recomendação para o mapa digital da cidade de Sobral Autor(es): Ramos, Alex de Sousa Abstract: The growing public demand for fast, clear, and efficient access to public services and information, especially in urban contexts increasingly dependent on digital technologies, makes the development of solutions that facilitate citizen interaction with complex databases, such as Geographic Information Systems (GIS), essential. The availability of large volumes of information on interactive mapping platforms, although promising, still faces usability limitations, often resulting in navigation difficulties, cognitive overload, and underutilization of available resources. In this context, this work proposes the development of the Navegador Virtual Inteligente de Sobral (NaVISOL), a conversational agent based on Artificial Intelligence (AI) and Natural Language Processing (NLP), implemented using the Rasa framework and integrated into the Sobral em Mapas platform, with the objective of enabling a more accessible interface for querying and exploring geospatial data. The system incorporates a hybrid recommendation engine that combines conversational context, implicit user navigation feedback, and Singular Value Decomposition (SVD) techniques for similarity analysis among map layers, mitigating data sparsity issues and promoting proactive discovery of relevant content. To evaluate the effectiveness of the solution, quantitative analyses were conducted based on the usage incidence metric of the recommendations, as well as a qualitative assessment of user experience through questionnaires addressing usability aspects, response comprehension, and perceived relevance of the provided suggestions. The results indicate that the adoption of the conversational interface associated with the recommendation system contributes to a more intuitive interaction with GIS, increases access to recommended layers, and fosters the discovery of new geographic content, demonstrating the potential of NaVISOL as a tool to democratize access to urban information and strengthen citizen-centered digital government initiatives. Tipo: Dissertação

2026-01-01T00:00:00Z Chaves, Sueline Cavalcante http://repositorio.ufc.br/handle/riufc/86259 2026-05-13T18:58:42Z 2026-02-25T00:00:00Z

Título: Avaliação dos efeitos do óleo essencial de lippia sidoides na criopreservação de folículos pré-antrais inclusos em córtex ovariano bovino Autor(es): Chaves, Sueline Cavalcante Abstract: Cryopreservation of ovarian tissue is an important strategy for preserving fertility in mammals; however, its efficiency can be compromised by structural, cellular, and biochemical damage resulting from oxidative stress generated during the freezing and thawing processes. In this context, the present study aimed to evaluate the effects of different concentrations of Lippia sidoides essential oil on the viability of bovine cumulus cells, as well as during the vitrification of bovine ovarian tissue. Bovine cumulus cells were cultured in vitro with different concentrations of Lippia sidoides essential oil (4, 40, and 400 µg/mL), and cell viability was evaluated using the calcein-AM and ethidium homodimer-1 fluorescence assay. Bovine ovaries were collected at a local slaughterhouse, and fragments of the ovarian cortex were subjected to vitrification in the absence (vitrified control) or in the presence of L. sidoides essential oil at concentrations of 4, 40, and 400 µg/mL. After warming, the fragments were cultured in vitro for 24 hours at 38.5°C with 5% CO₂. Subsequently, ovarian tissue cell viability, morphological integrity and follicular activation, stromal cell density, extracellular matrix collagen content, and oxidative profile were evaluated through the activities of the antioxidant enzymes superoxide dismutase (SOD), catalase (CAT), glutathione peroxidase (GPX), and reduced thiol levels. The results demonstrated that the effects of L. sidoides essential oil were concentration-dependent. Concentrations of 4 and 40 µg/mL, especially 40 µg/mL, favoured the preservation of cumulus cell and ovarian tissue viability, follicular morphology and activation, ovarian stromal organisation, and redox balance after vitrification and in vitro culture. On the other hand, the concentration of 400 µg/mL did not promote additional benefits and was associated with a lower proportion of morphologically normal follicles and the absence of stimulation of follicular activation when compared to lower concentrations. It is concluded that L. sidoides essential oil, at a concentration of 40 µg/mL, has potential as an adjuvant agent in bovine ovarian tissue vitrification protocols, contributing to the structural and functional preservation of the tissue after warming. Tipo: Dissertação

2026-02-25T00:00:00Z Viana, Priscilla Parente http://repositorio.ufc.br/handle/riufc/86039 2026-04-27T14:17:52Z 2026-03-01T00:00:00Z

Título: Avaliação da fotobiomodulação no controle da disgeusia em pacientes com câncer de cabeça e pescoço submetidos à radioterapia: estudo clínico randomizado Autor(es): Viana, Priscilla Parente Abstract: Radiotherapy for head and neck cancer potentially leads to gustatory dysfunction. Dysgeusia is a distortion in taste perception that may result in nutritional deficiencies and reduced quality of life. Photobiomodulation therapy has been used as a supportive measure in cancer treatment, including for the management of taste disorders.This randomized study aimed to evaluate the influence of photobiomodulation therapy on the prevention of dysgeusia in patients with head and neck cancer undergoing radiotherapy, compared with the use of zinc sulfate. The sample included 16 patients, divided into a Test Group (photobiomodulation therapy) and a Control Group (zinc sulfate use). Objective taste testing was performed in both groups at three time points: before radiotherapy (T0), at the 15th radiotherapy session (T1), and at the 30th radiotherapy session (T2). The sample consisted predominantly of male patients (68.8%), with a mean age of 65.63 years. Fisher’s exact test was used for statistical analysis to compare the Test and Control groups at T0, T1, and T2. Salty taste perception was the most affected in both groups. Sweet taste perception showed greater improvement in the zinc group at T2. Sour, bitter, and salty taste perceptions showed greater improvement in the laser group at T2. Statistically, no comparison between groups at T0, T1, or T2 was significant (p > 0.05). Despite the absence of statistically significant differences between groups, laser therapy demonstrated greater effectiveness in reducing the severity of taste disorders related to sour, bitter, and salty tastes throughout radiotherapy, particularly at the most critical time points (T1,T2). The association of both treatments may be beneficial for the treatment and prevention of dysgeusia in patients irradiated for head and neck cancer. Tipo: Dissertação

2026-03-01T00:00:00Z