villani Goto Github PK

37scj

Repositório de trabalhos em grupo da turma 37SCJ da pós na FIAP.

37scj_stocks

alice3

Práticas com o Alice 3

angular-http-get-spotify-episodes

Created with StackBlitz ⚡️

aws-quarkus-demo

Quarkus example projects for Amazon ECS with AWS Fargate and AWS Lambda

bitcoin

Generated by code.quarkus.io

bottelegram

O BotTelegram é um chatbot integrado ao Telegram capaz de responder mais do que cinco perguntas sobre os três diferentes tipos de assuntos: coronavírus, trânsito e clima.

calcula_flex_template

cloud-development

Repositório para a disciplina de Cloud Development do curso de MBA da FIAP.

compose

Define and run multi-container applications with Docker

containers-virtualization

Projeto desenvolvimento para a avaliação da disciplina de Containers & Virtualization do curso de MBA em Full Stack Developer - Microservices, Cloud e IOT da FIAP.

cursoquarkus

devopsonawsoff

drone-project

Projeto da disciplina de Integrations and Development tools

exemplos-rabbitmq

experiments01

Evaluates the performance of the medical images classification performed by algorithms Binary Relevance and Multi-Label kNN

experiments02

Evaluates the performance of the medical images classification performed by algorithms Binary Relevance and Multi-Label kNN. The examples of the dataset were characterized with EHD.

experiments03

Evaluates the performance of the medical images classification performed by algorithms Binary Relevance and Multi-Label kNN. The examples of the dataset were characterized with LBP.

experiments04

Subset are constructed from a set with more than 12.000 ray-X medical images from breast region to can processed in low-performance computer. The EHD, SIFT, LBP, Gabor and Zernike techniques are used to feature the samples from formed set. The created sets are used to train and test the created model by multi-label classifiers. Finally, are evaluated the performance from selected algorithms to the task of classify images with multiples labels.

experiments05

Sub-bases were constructed from the bases created in Experiments04. For each ARFF base from Experiments04, more four sub-bases were created, one for each axe of the IRMA code. An evaluating is performed about what extracting features techniques provides features more relevant and for what axis. The performance from the multi-label classification was evaluated too through from problem transform and algorithm adapting approach.

experiments06

Each ARFF base from Experiments04 are used for train and the nine remaining bases for test in the annotation medical images task. The performance from various classifiers are evaluated to this task. The classifiers used are MLkNN, BRkNN, ClassifierChain(kNN), HMC(kNN) and LabelPowerset(kNN). Furthermore, an evaluating is realized about what extraction features techniques provides more relevant features to the classifiers from this task.

experiments07

Each ARFF base from Experiments04 are used for train and the nine remaining bases for test in the annotation medical images task. The difference those experiment to the preview experiment is that on Experiments07 the classification is realized by axis instead of assign the labels to all the axes in a only step like on Experiments06. The performance from various classifiers are evaluated to this task. The classifiers used are MLkNN, BRkNN, ClassifierChain(kNN), HMC(kNN) and LabelPowerset(kNN). Furthermore, an evaluating is realized about what extraction features techniques provides more relevant features to the classifiers from this task.

fiap

Aplicações para os cursos de pós-graduação da FIAP

fiap-2020-scj-javapersistence

(FIAP) Repositório para a disciplina de Java Persistence

fiap-2020-scj-javaplatform

(FIAP) Repositório para a disciplina de Java Platform

fiap-bank

Nova plataforma de crédito da Fiap

fiap-hncloud

finances

In-browser React micro frontend module-ready. Made with single-spa. CI/CD with CircleCI and Firebase.

ia

O projeto IA contém exemplos de códigos usados na disciplina de Inteligência Artificial ministrada na Fatec Praia Grande e neste pacote estão disponíveis todos os exemplos. A maioria dos exemplos é dependente de classes e arquivos disponíveis na biblioteca Weka. Envie um e-mail para [email protected] se desejar obter mais informações.

kotlinpingpong