TCC - Bacharelado em Ciência da Computação (UAG)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/2952
Navegar
Item Uma análise de funções Wavelet para a tarefa de reconhecimento facial(2018-08-22) Ferreira, Fabrício Paes; Carvalho, Tiago Buarque Assunção de; http://lattes.cnpq.br/7150833804013500; http://lattes.cnpq.br/5610038616163785Face recognition is an important research topic because of its wide range of applications, such as surveillance, biometrics and control access. Waveletfaces is a feature extraction technique that can improve the accuracy rate of a face recognition system. Nonetheless, its results may deeply vary depending on the wavelet function, decomposition level, classifier, other dimensionality reduction techniques used along with Waveletfaces, as well as the face database. To determine whether there is a subset of such items that can improve Waveletfaces, we performed an extensive comparison. We evaluate 4 dimensionality reduction methods using Waveletfaces, 106 different wavelet functions, 5 decomposition levels, 4 classifiers, and 5 face data sets. The combination of all these elements results in 42,400 scenarios at most. We used the confidence interval hypothesis test to compare the accuracy rate of each scenario with the maximum one within each data set. We determine that a few wavelet functions, such as some from the Reverse Biorthogonal family, can greatly improve classification accuracy. It is also shown that the Nearest Neighbor classifier performs well on all five databases. Moreover, other elements are very related to database issues.Item Análise dos componentes principais supervisionada: uma abordagem não-paramétrica(2019-02-04) Sousa, Raul Pedro de Vasconcelos; Carvalho, Tiago Buarque Assunção de; http://lattes.cnpq.br/7150833804013500; http://lattes.cnpq.br/3362844917050042Problems of classification of data become more commonly used. Classification task has a broader range of applications, ranging from detection of spam emails to classification of malignant and benign tumors. In these problems, the quantity of characteristics plays a fundamental role both in the quality and performance of the classifiers. Data having a high dimensionality tends to have lower accuracy and longer processing time. Feature extraction techniques are excellent solutions to this situation, generating a new set of features and selecting the best ones for classification. Principal Component Analysis (PCA) is one of the most common feature extraction techniques. In general, PCA presents excellent results, but because it is an unsupervised technique there are situations where the method can not extract discriminant features. We developed a supervised version of the PCA using Bayesian classification with the kernel density estimation (KDE) to select features. This method has emerged as an extension of the Minimum Classification Error PCA (MCPCA). MCPCA also uses the Bayesian error as a metric however it presents a series of constraints. Comparing the exposed method with PCA, MCPCA and Supervised PCA (SPCA), another supervised approach to PCA, comparing the accuracy by characteristics in four classifiers to sixteen databases. The proposed method presented the greater accuracy in 72% of the cases. For PCA, MCPCA, and SPCA this number is 31%, 36%, 12%, respectively. When using a single extracted feature, the maximum accuracy if achieved is 89%, 14%, 37%, and 25% of the cases for proposed method, PCA, MCPCA, and SPCA, respectively.Item Aplicativo para sorteio de jogadores na formação de equipes em esportes coletivos(2019) Almeida, Luiz Alberes Bispo de; Carvalho, Tiago Buarque Assunção de; http://lattes.cnpq.br/7150833804013500In this report is presented the Sem Panelinha, an application for adraw of play-sports teams, with anemphasis on football. With Sem Panelinha,the user can choose three types of sweepstakes: Random, which distributes the players to teams without any criteria; By Key Heads, which does not allow the players to defined as Keyheads remain on the same team; and By Stars, where possible to give a note through the amount of stars for each of the players. The from the selection of one of these draws the participating players are registered and the end of the registration process, the teams will be formed. Among the benefits of the system, the following stand out: practicality, agility and power of choice. The application has been deployed using Android Studio,with the local data base made by SQLite. Besides that, techniques of Software and Data bases were used for better project development. During the modeling process, meetings with users and visits to the event sites enabled the creation of requirements, meeting the needs of of users. A unit test was performed that indicated a good functioning of the system. Finally, all the proposed requirements have been met and the system is in operation, through usability testing.Item Desenvolvimento de sistema web mobile para home care: beira leito(2018-08-23) Sousa, Raul Pedro de Vasconcelos; Carvalho, Tiago Buarque Assunção de; http://lattes.cnpq.br/7150833804013500; http://lattes.cnpq.br/3362844917050042This report presents "Beira Leito", a web-mobile system for home care, which assists in the control of the day and stock for the company "Homecare Garanhuns". Home care is a form of medical care where the patient is hospitalized, receiving periodic visits from the health professionals who accompany him, such as: doctors, nurses, psychologists, social workers and others. The patient also receives the medicines and other products associated with his treatment at home, and these are applied by the professional who makes the visit. Due to its particular characteristics, this type of care presents problems and challenges characteristic of both the ealth area (monitoring and evolution of the patient’s condition) and administrative (stock control and estimation of associated costs). For this reason, it was proposed that Beira Cama consists of a Web-mobile system that assists in the control of the workday of the professionals, monitoring their location and procedures performed by them through an application installed in a tablet that functions as a " digital prescription "containing the schedules, items and description of the medical procedure to be performed, where at the end of the same the professional informs if the same was performed or not. The web front is an administrative part where the professionals, products, patients and procedure are registered, as well as it is possible to carry out the monitoring of the costs associated with the operations as well as the monitoring of the employee and patients. At the end of the stage we were able to elaborate a MVP Minimum Viable Product that contains everything that was requested by the customer and ready to start being validated commercially.Item M Harmony BR: o uso de formalismos para a composição algorítmica baseada em conhecimento(2018-02-23) Silva, Vinícius Santana; Carvalho, Tiago Buarque Assunção de; Costa Junior, Jerônimo Barbosa da; http://lattes.cnpq.br/6050271311748487; http://lattes.cnpq.br/7150833804013500; http://lattes.cnpq.br/8393251786005816Throughout history, several studies have tried to introduce the use of computers in other areas of knowledge, including music, and several researches have been done to show the ability of computers to compose music. The present work had the objective to verify the possibility of the creation of a simple software capable of generating harmonies of a certain musical style, using context-free grammars, based on knowledge. The development of the tool was based on the analysis of the characteristics of two different musical styles: Punk Rock and Sertanejo Universitário, through the collection and analysis of data of 40 songs. Subsequently the database was expanded with the inclusion of 50 Reggae songs and 30 songs to the Sertanejo Universitário style, totaling 120 songs. Based on the information extracted from the music dataset, 3 specific grammars were generated to produce harmonies of each style analyzed by means of a composition algorithm. The study resulted in the production of an application that composes knowledge-based harmonies, which proved useful in aiding musical composition process.Item Previsão de resultados de jogos do campeonato brasileiro de futebol utilizando aprendizagem de máquina(2019-02-05) Almeida, Luiz Alberes Bispo de; Carvalho, Tiago Buarque Assunção de; http://lattes.cnpq.br/7150833804013500Over the past few years, the demand for sports betting has grown, and several people started living off this market. Using Machine Learning with the goal of making game analysis for betting more comfortable as well as measuring profits, a database for the Brazilian Soccer Championship Série A 2017 was created, encompassing features from two opposing teams and the match. For testing in an evaluation model, the Naive Bayes technique was chosen, simulating a Brazilian Championship round, which contains ten matches. The evaluation model was executed both with and without correct probability restrictions, with the goal of reducing errors. Three scenarios were used on the evaluation model, the first having two classes that consider goals by both teams, the second regarding the total match goals (over or below 2.5 goals) and the third considering all three possible match results (a victory for one side, a tie, or a victory for the other side). The results without probability restriction reached its higher value at 5.51% of average and total profit. However, regarding the results with probability restriction, the best average gain was 36.05%, and the best total profit was 39.13%, both using 99% correct probability restriction.