João Pereira

Welcome to my personal webpage!

JP
Download CV

About me


I am a PDEng Trainee in Data Science at Eindhoven University of Technology (TU/e), where I develop data science projects for industry. Most of the time I do machine learning and work on applications involving time series, images, videos, text, and graphs, coming from the most various domains, spanning energy, retail, manufacturing, healthcare, and social good. Meanwhile, I organize tutorials on deep learning and coach professionals and trainees at JADS/TU Eindhoven. I'm specially interested in anomaly detection problems (e.g., fraud) and deep learning (the core of my thesis). Prior to joining TU/e, I developed applied research on deep learning at ISR-Lisbon and completed a M.Sc. degree in Electrical and Computer Engineering at IST (University of Lisbon). Here I show some projects I have been doing recently. Feel free to contact me! ;)

Contacts



From Portugal Portuguese Flag
Live in Eindhoven, The Netherlands Dutch Flag
PT: +351 966 130 155
NL: +31 6 79 20 25
mail@joao-pereira.pt
Download CV

News

Projects

Solar Scan

Solar Potential Image Segmentation CNNs
Python JavaScript C# Google Cloud Platform Microsoft SQL GIS Leaflet

Anti-Money Laundering

Graph Analysis Community Detection
Microsoft Azure PowerBI

Particle Detection

Image Processing Peak Detection
OpenCV Scikit-image

Product Recommendation

Matrix Factorization SVD
Python Plotly & Dash

DeepFake Detection

Video Classification CNNs RNNs
TensorFlow Python JavaScript C# Google Cloud Platform

Occupancy Prediction

Neural Networks Predictive Modelling Regression
TensorFlow Python

Load Forecasting

Neural Networks Power Load
Matlab

Supply Chain

Process Mining
Disco Python & Dash

Experience


Logo JADS

PDEng Trainee in Data Science

January 2019 - Present

Jheronimus Academy of Data Science (JADS)

Developing data science projects for industry. Check out the Projects section!


Logo LXMLS

Lab Monitor

July 2019

Lisbon Machine Learning School (LxMLS)

Part of the organizing team of LxMLS'19 as a monitor. I had responsibilities in the organization of the school and helped the students solving the exercises during the lab sessions, implementing machine learning algorithms such as naive Bayes, hidden Markov models, conditional random fields, recurrent neural networks, and reinforcement learning.

NLP Deep Learning Neural Networks Reinforcement Learning CRFs HMMs RNNs

Logo ISR

Researcher

2018

Institute for Systems and Robotics (ISR-Lisbon)

Developed applied research on deep learning for time series data within the Signal and Image Processing Group. Worked mostly with solar energy generation and electrocardiogram (ECG) data.

Deep Learning Neural Networks Anomaly Detection Time Series Data

Logo EDP

Intern

{Summer 2017, Summer 2016}

EDP Group

Developed a data science project on load forecasting.

Neural Networks Load Forecasting Substations

Publications

Logo Thesis
Unsupervised Anomaly Detection in Time Series Data Using Deep Learning
M.Sc. Thesis
João Pereira
Lisbon, Portugal

Instituto Superior Técnico, University of Lisbon

Deep Learning Anomaly Detection Time Series Data Variational Autoencoders Recurrent Neural Networks Variational Self-Attention Mechanism

Unsupervised Anomaly Detection in Energy Time Series Data using Variational Recurrent Autoencoders
Conference Paper
Oral Presentation
João Pereira
, Margarida Silveira
Orlando, Florida, USA

17th IEEE International Conference on Machine Learning and Applications (ICMLA'18)

Solar Energy Generation Photovoltaic Panels Deep Learning Time Series Data Variational Autoencoders Reconstruction Probability Recurrent Neural Networks Variational Self-Attention Mechanism

Learning Representations from Healthcare Time Series Data for Unsupervised Anomaly Detection
Conference Paper
Oral Presentation
João Pereira
, Margarida Silveira
Kyoto, Japan

2019 IEEE International Conference on Big Data and Smart Computing (BigComp'19)

Electrocardiogram Deep Learning Heartbeats Variational Autoencoders Wasserstein Distance Latent Space Detection

Unsupervised Representation Learning and Anomaly Detection in ECG Sequences
Journal Paper
João Pereira
, Margarida Silveira

International Journal of Data Mining and Bioinformatics (IJDMB)

Electrocardiogram Deep Learning Heartbeats Variational Autoencoders Wasserstein Distance Latent Space Detection

Reviewing

Reviewer

International Conference on Artificial Intelligence, Information Processing and Cloud Computing

Sanya, China
Reviewer

Wireless Communications and Mobile Computing Journal, Wiley-Hindawi

Program Committee Member

ALLDATA 2020

Lisbon, Portugal

Education


Logo TUE

Professional Doctorate in Engineering (PDEng) in Data Science

January 2019 - Present

Eindhoven University of Technology

Eindhoven, The Netherlands
Data Science Machine Learning Business Insights

Logo IST

Integrated Master in Electrical and Computer Engineering

2013-2018

Instituto Superior Técnico, University of Lisbon

Lisbon, Portugal
Artificial Intelligence Machine Learning Digital Signal Processing Image Processing and Computer Vision Robotics

Logo UCdL

Exchange Student within Erasmus+ Program

September 2016 - January 2017

Université catholique de Louvain

Louvain-la-Neuve, Belgium
Machine Learning Image Processing and Vision Instrumentation and Sensors Electric Power Systems

Get in Touch!

mail@joao-pereira.pt