TCC - Bacharelado em Ciência da Computação (Sede)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/415
Navegar
7 resultados
Resultados da Pesquisa
Item Comparison of recommendation algorithms for user groups: a food-based case study(2023-04-24) Vasconcelos, Caio Giovanni Pereira; Silva, Douglas Véras e; http://lattes.cnpq.br/2969243668455081; http://lattes.cnpq.br/4775036700843482Item Formação de grupos de alunos baseada em múltiplos critérios(2021-05-27) Fiorentino Neto, Giuseppe; Miranda, Péricles Barbosa Cunha de; http://lattes.cnpq.br/8649204954287770; http://lattes.cnpq.br/6288849609186849Group formation is one of the main steps of the collaborative learning. This paper proposes an intelligent method to optimize the group formation process considering multiple criteria: inter-homogeneity, intra-heterogeneity and empathy. The method was evaluated regarding the performance, being compared to the exhaustive and random approaches; And regarding the pedagogical aspect, being compared with random and self-selected methods. The results showed the potential of the proposed method from the computational point of view as well as the pedagogical point of view.Item Avaliação de algoritmos de rastreamento no problema de detecção de pessoas no mar(2023-09-13) Nascimento, Ramicés Moisés do; Macário Filho, Valmir; http://lattes.cnpq.br/4346898674852080; http://lattes.cnpq.br/0247140467691140It is known that shark attacks are a constant fear for the population on the beaches of Pernambuco. Many of these attacks are fatal, which calls for some action to be taken, considering that Pernambuco beaches attract thousands of tourists each year. Therefore, researchers from UFRPE initiated a study aiming to develop a system for tracking people in the sea, which would make it possible to alert lifeguards when individuals exceed a designated safe area on the beach, as well as allocate a greater number of these professionals in areas with a higher concentration of people. The system was divided into three stages: image segmentation, detection of beachgoers, and tracking of individuals. This work focuses on the third stage. Tracking people is a complex task with high computational costs. Problems such as changes in lighting conditions, alterations in the direction of targets, and variations in the background are just a few of the difficulties that can be mentioned. Thus, the objective of this research is to evaluate six people tracking algorithms found in the literature using beach images. Firstly, a database of ten videos recorded at Boa Viagem beach in Pernambuco was manually labeled. Then, six algorithms were selected for evaluation. Subsequently, the output of each frame provided by the algorithm was compared with the previously labeled data, and an average was calculated. Overall averages were then obtained to assess the algorithm’s accuracy and execution time. Finally, the best algorithm was chosen for optimization using a genetic algorithm, and any improvements in the results were verified. CSRT was the algorithm that obtained the best result and after optimization with the genetic algorithm, an improvement of 20% in its accuracy was obtained.Item Análise de um sistema de recomendação de restaurantes sensível ao contexto sobre o grau de satisfação dos usuários(2023-09-01) Melo Filho, Carlos Olimpio Rodrigues de; Silva, Douglas Véras e; http://lattes.cnpq.br/2969243668455081; http://lattes.cnpq.br/6986499479035317Popular applications of recommender systems can be found in many areas. In the food business, platforms such as TripAdvisor stand out for suggesting specialized restaurant recommendations based on various types of relevant information, such as reviews from other users for the menu, atmosphere and recommendations for the closest restaurants are some of the specialties of these platforms. With the possibility of using new data sensitive to the user’s context, the main objective of this work is to evaluate the usage of the reason of going to the restaurant to reorganize the final restaurants recommendation through a context-based post-filtering. To achieve the goal, a mobile application was developed, the SR Recife Restaurants, to assess the degree of satisfaction of real users to the recommended restaurants, an online evaluation approach, using questionnaires, was used. When carrying out the experiment with 15 users, it was possible to notice an increase of 26.67% in the degree of satisfaction of the top-5 first recommendations when using the trip type to the restaurant as context data for the post-filtering phase.Item Evaluation of dimensionality reduction and truncation techniques forword embeddings(2021-03-03) Aoun, Paulo Henrique Calado; Nascimento, André Câmara Alves do; Silva, Adenilton José da; http://lattes.cnpq.br/0314035098884256; http://lattes.cnpq.br/0622594061462533; http://lattes.cnpq.br/1048218441267310The use of word embeddings is becoming very common in many Natural Language Processing tasks. Most of the time, these require computacional resources that can not be found in most part of the current mobile devices. In this work, we evaluate a combination of numeric truncation and dimensionality reduction strategies in order to obtain smaller vectorial representations without substancial losses in performance.Item Teacher-Student aplicado a diferentes modelos de recompensa do ambiente Lunar Lander(2021-07-20) Silva, Kenedy Felipe dos Santos da; Sampaio, Pablo Azevedo; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/7479192156880225The techniques studied related to learning by reinforcement are becoming more and more common in real world challenges, but one challenge is to reduce the learning time. Currently, the learning time and/or amount of interactions performed by the reinforcement learning agent can result in high costs in applications, as the training of models can consume a lot of time, requiring many interactions between the agent and the task environment. This work seeks to improve learning using a new combination of techniques, the Teacher-Student technique with Reward Shaping. The Teacher-Student technique aims to choose among a set of similar tasks that train for a main task, according to the student’s learning. The Reward Shaping technique, altering the reward to try to accelerate learning, provides more frequent feedback on appropriate behaviors, that is, reports rewards more often. We adapted Teacher-Student algorithms for this combination of techniques, and used the Lunar Lander environment as a case study, using four reward models designed in (ALBUQUERQUE, 2021) for this environment. Experiments were performed running different trainings to compare this approach with training only on the original Lunar Lander (no rewards change), and with the results obtained in (ALBUQUERQUE, 2021) by adopting each of the rewards models individually. The combination of Teacher-Student techniques with Reward Shaping contributed to a new experience in the reinforcement learning area, managing to accelerate the agent’s learning, considering the duration of 600 thousand training steps, reaching the target performance in 2 out of 5 proposals, in addition to of being able to learn better than the original Lunar Lander approach with PPO algorithm.Item Um currículo de aprendizagem por reforço para recompensas modeladas no Lunar Lander(2021-07-19) Albuquerque, Renilson da Silva; Sampaio, Pablo Azevedo; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/3364503614448061Reinforcement learning is a machine learning paradigm where the agent learns to solve problems interacting with an environment, executing actions in a trial and error sequence. For each action performed, the agent receives a reward from the environment indicating how effective it was in solving the whole problem. The agent’s objective is to maximize the total reward received. However, in some reinforcement learning problems, the agent needs to learn complex tasks receiving uninformative rewards, leading to the credit assignment problem that slows the agent’s training process. Reward shaping and curriculum learning are techniques that can speed up agent training time by separating the problem into smaller tasks to be solved sequentially, applying smaller and informative rewards for each action performed. Lunar Lander is a simplified 2D simulator used as a benchmark for reinforcement learning solutions to the optimization problem on landing control of a lunar module. However, its standard rewards system assigns much more punitive rewards for the use of the engines, not being very constructive for the agent, which can lead to the credit assignment problem. Hence, this work proposes a curriculum using two additional shaped reward models and runs experiments that aim to minimize the Lunar Lander learning time. This work found that both the new models and the curriculum were more effective in training the Lunar Lander agent compared to the standard rewards model.