{"id":360,"date":"2026-05-11T15:32:42","date_gmt":"2026-05-11T18:32:42","guid":{"rendered":"https:\/\/eic.cefet-rj.br\/~jsoares\/?p=360"},"modified":"2026-05-11T15:37:50","modified_gmt":"2026-05-11T18:37:50","slug":"defesa-de-dissertacao-13-05-2026-ana-gabriela-viana-de-araujo","status":"publish","type":"post","link":"https:\/\/eic.cefet-rj.br\/~jsoares\/2026\/05\/11\/defesa-de-dissertacao-13-05-2026-ana-gabriela-viana-de-araujo\/","title":{"rendered":"Defesa de disserta\u00e7\u00e3o (13\/05\/2026): Ana Gabriela Viana de Ara\u00fajo"},"content":{"rendered":"
Divulga\u00e7\u00e3o de defesa de disserta\u00e7\u00e3o e de qualifica\u00e7\u00e3o<\/strong><\/div>\n
<\/div>\n

<\/p>\n

Discente<\/strong>:\u00a0Ana Gabriela Viana de Ara\u00fajo<\/div>\n
<\/div>\n

<\/p>\n

T\u00edtulo<\/strong>:\u00a0Aplica\u00e7\u00e3o de m\u00e9todos baseados em concept drift para previs\u00e3o de gols no futebol profissional<\/div>\n
Application of concept drift-based methods for predicting goals in professional football<\/i><\/div>\n
<\/div>\n

<\/p>\n

Orientador<\/strong>:\u00a0Jorge de Abreu Soares (Cefet\/RJ)<\/div>\n
<\/div>\n

<\/p>\n

Banca<\/strong>: Jorge\u00a0 de Abreu Soares (Cefet\/RJ), Glauco Fiorott Amorim (Cefet\/RJ), Pedro Henrique Gonz\u00e1lez Silva (UFRJ), Carlos Eduardo Ribeiro de Mello (Unirio)<\/div>\n
<\/div>\n

<\/p>\n

Dia\/Hora<\/strong>:\u00a013\/05\/2026 \u00e0s 9h<\/div>\n
<\/div>\n

<\/p>\n

Sala ou Link para apresenta\u00e7\u00e3o remota<\/strong>:\u00a0https:\/\/teams.microsoft.com\/meet\/235075217075845?p=ezgpJ8dNRKnMa8dTfM<\/u><\/a><\/div>\n
<\/div>\n

<\/p>\n

Resumo<\/strong>:<\/div>\n
Este trabalho investiga a aplica\u00e7\u00e3o de t\u00e9cnicas de detec\u00e7\u00e3o de \\textit{concept drift} para a identifica\u00e7\u00e3o antecipada de gols em partidas de futebol, com base em dados de eventos intra-partida. A abordagem trata o problema como monitoramento de mudan\u00e7as na
\ndistribui\u00e7\u00e3o de passes intra-partida, utilizando \\textit{drift} virtual operacionalmente, isto \u00e9, detec\u00e7\u00e3o baseada exclusivamente em P(X) sem r\u00f3tulos em tempo real, com a premissa de que essas mudan\u00e7as precedem altera\u00e7\u00f5es na probabilidade de gol. A robustez dos resultados \u00e9 verificada por divis\u00e3o temporal com 190 partidas de treino e 190 de teste. Foram utilizados dados da temporada 2015\/2016 da La Liga: 380 partidas, agregadas em intervalos de um minuto, com an\u00e1lise tanto do comportamento ofensivo quanto defensivo. Tr\u00eas detectores de \\textit{drift} foram avaliados (Page-Hinkley, KSWIN e ADWIN) em compara\u00e7\u00e3o com baselines determin\u00edstico e estoc\u00e1stico, utilizando como sinal de entrada m\u00e9dias m\u00f3veis da frequ\u00eancia de passes. A avalia\u00e7\u00e3o adota uma variante assim\u00e9trica do \\textit{SoftED evaluation}, que penaliza alarmes tardios por meio de uma fun\u00e7\u00e3o de pontua\u00e7\u00e3o linear decrescente na janela [t-K,t], com K=10\u00a0minutos. Os resultados indicam que o Page-Hinkley obteve o maior MCC entre os detectores avaliados, superando ambos os \\textit{baselines}; Page-Hinkley e KSWIN apresentaram F1 equivalentes, com vantagem marginal do KSWIN. A compara\u00e7\u00e3o com abordagem supervisionada da literatura evidencia que o m\u00e9todo proposto, embora mais simples e sem necessidade de dados rotulados, atinge desempenho competitivo a partir da primeira partida. Discutem-se limita\u00e7\u00f5es da abordagem, incluindo o uso de passes como \u00fanico sinal \\textit{proxy} e a restri\u00e7\u00e3o a uma \u00fanica temporada, al\u00e9m de perspectivas para trabalhos futuros com vari\u00e1veis multivariadas e an\u00e1lise longitudinal.<\/div>\n
<\/div>\n

<\/p>\n

Abstract<\/strong><\/div>\n
This work investigates the application of concept drift detection techniques for the early identification of goals in soccer matches, based on intra-match event data. The approach treats the problem as monitoring changes in the intra-match pass distribution, using operationally virtual drift, that is, detection based exclusively on P(X) without labels in real time, with the premise that these changes precede changes in the probability of a goal. The robustness of the results is verified by temporal division with 190 training matches and 190 test matches. Data from the 2015\/2016 La Liga season were used: 380 matches, aggregated in one-minute intervals, with analysis of both offensive and defensive behavior. Three drift detectors were evaluated (Page-Hinkley, KSWIN, and ADWIN) in comparison with deterministic and stochastic baselines, using moving averages of pass frequency as input signal. The evaluation adopts an asymmetric variant of the SoftED evaluation, which penalizes late alarms through a decreasing linear scoring function in the [t-K,t] window, with K=10 minutes. The results indicate that Page-Hinkley obtained the highest MCC among the detectors evaluated, surpassing both baselines; Page-Hinkley and KSWIN presented equivalent F1 values, with a marginal advantage for KSWIN. Comparison with supervised approaches from the literature shows that the proposed method, although simpler and without the need for labeled data, achieves competitive performance from the first match. Limitations of the approach are discussed, including the use of passes as the only proxy signal and the restriction to a single season, as well as perspectives for future work with multivariate variables and longitudinal analysis.<\/div>\n","protected":false},"excerpt":{"rendered":"

Divulga\u00e7\u00e3o de defesa de disserta\u00e7\u00e3o e de qualifica\u00e7\u00e3o Discente:\u00a0Ana Gabriela Viana de Ara\u00fajo T\u00edtulo:\u00a0Aplica\u00e7\u00e3o de m\u00e9todos baseados em concept drift para previs\u00e3o de gols no futebol profissional Application of concept drift-based methods for predicting goals in professional football Orientador:\u00a0Jorge de Abreu Soares (Cefet\/RJ) Banca: Jorge\u00a0 de Abreu Soares (Cefet\/RJ), Glauco Fiorott Amorim (Cefet\/RJ), Pedro Henrique […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-360","post","type-post","status-publish","format-standard","hentry","category-defesas-orientandos"],"_links":{"self":[{"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/posts\/360","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/comments?post=360"}],"version-history":[{"count":8,"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/posts\/360\/revisions"}],"predecessor-version":[{"id":368,"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/posts\/360\/revisions\/368"}],"wp:attachment":[{"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/media?parent=360"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/categories?post=360"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/eic.cefet-rj.br\/~jsoares\/wp-json\/wp\/v2\/tags?post=360"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}