Hi! My name is

Miguel Díaz

I'm

About

Multidisciplinary technical profile with years of experience developing software and applying Machine Learning techniques. I feel a great passion for new technologies and new tools to bring projects into reality. I enjoy learning and teaching in a team, sharing knowledge and passions. I strongly believe that creating synergies between different technical profiles is the most productive (and funny!) way to find the best solution for a particular business logic.

Software Developer & Data Scientist.

I like to consider engineering as a means to transfer great concepts from the world of ideas to the physical world 💭. Ideas that generate a high impact on society and that are implemented through technical solutions that are beautiful in their simplicity.

  • Birthday: 29 June 1996
  • Website: miguel.diazlozano.com
  • City: Córdoba, Spain
  • Languages: English, French, Spanish
  • Degree: Master
  • Email: miguel@diazlozano.com
  • Freelance: Not Available

The confluence of techniques for obtaining valuable information from data and the mayor paradigms for developing quality software is a powerful tool whose capacity to create social impact is not yet fully explored. There is still a lot of work to be done to exploit the many possibilities that this conjunction can offer, and to bring its great potential to everyone.

Give me a place to stand, and I shall move the world.
Archimedes.

Skills

I have focused my professional and academic career on learning in parallel about my two passions: the data science and the software development disciplines.

Data Science

Python 100%
R 90%
Machine Learning Algorithms Supervised & Unsupervised90%
Data Visualization 90%
Metaheuristics 80%
Computer vision 70%
Data Mining 70%

Software Developer

Object-oriented Programming C#, Python, Node100%
SOLID Principles 100%
Data Structures 90%
Git 90%
Docker 90%
API REST 90%
HTML, CSS & Javascript 80%
Design Patterns 80%
Relational DBs 80%
Non-Relational DBs 70%
Cloud systems Azure, AWS, GCP70%

Resume

Sumary 🤚

Miguel Díaz

Multidisciplinary technical profile with years of experience developing software and applying Machine Learning techniques.

  • Córdoba, Spain
  • miguel@diazlozano.com

Education 🎓

Master in Data Science & Computer Engineer

2018 - 2019

University of Granada, Granada, Spain

Final Thesis: Analysis and development of new techniques for time series processing and its application to the analysis of criptocurrency prices • 10/10 with Honors 🎉

BSc in Computer Science & Engineering

2014 - 2018

University of Córdoba, Córdoba, Spain

Final Thesis: Development of a Python library for time series forecasting through Machine Learning algorithms • 10/10 with Honors 🎉

Professional Experience 💼

Expert Engineer

January 2023 - Present

NTT DATA, Seville (Spain) - Remote

What I've done

  • Design and implementation of service-based, agnostic architectures for the creation of digital twins. Integrator in the Area of Expertise (AoE) for Digital Twins, Edge, and IoT. Responsible for implementing decoupled architectures based on microservices. Designer and developer of cloud architectures on AWS and Azure.

Using

  • Node
  • C#
  • Python
  • Docker, K8s
  • Azure
  • AWS
  • Kafka
  • Git
  • Unix

Research Associate

August 2022 - January 2023

Maimonides Institute for Biomedical Research of Córdoba (IMIBIC)

What I've done

  • In charge of a descriptive investigation about COVID-19 impact in several locations of Andalusia, Spain.
    • Development of techniques for characterizing COVID-19 contagion curves.
    • Cluster analysis of Andalusian sanitary districts based on several COVID-19 pandemic indicators.

Using

  • Python
  • Seaborn, matplotlib
  • Jupyter
  • scikit-learn
  • pandas
  • LaTeX
  • Git
  • Unix

Research Associate

June 2021 - August 2022

Fundación Progreso y Salud, Junta de Andalucía

What I've done

  • Responsible for the drafting of periodic reports for the Andalusian government about the incidence of the COVID-19 pandemic.
    • Analysis of the number of infected people in the 34 sanitary districts of Andalusia.
    • Generation of forecasting models for predicting the number of contagions and the occupied hospital and ICU beds.
    • Analysis of weekly statistical differences using several pandemic indicators.
  • Development of time series decomposition techniques for forecasting number of COVID-19 infected people.

Using

  • Python
  • Seaborn, matplotlib
  • Jupyter
  • scikit-learn
  • pandas
  • LaTeX
  • Git
  • Unix

Data Scientist & Software Developer

September 2019 - June 2021

Deuser, Córdoba, Spain

What I've done

  • Team lead in the design and development of industry machine software for interconnecting industrial machinery, obtaining, processing and storing information.
    • Development of APIs
    • Connection with relational and non-relationals databases.
    • Connection with Cloud Systems
    • Implementation of OPC servers.
  • Development of specific industrial communication drivers.
  • Maintenance of the operation of solar parks.
  • Development of predictive models.

Using

  • .NET Framework, ASP.NET, C#
  • Design patterns
  • API REST
  • Python
  • Git
  • MVC
  • MVP
  • Relational and non-relational DBs
  • AWS, Aveva, Mindsphere
  • HTML, CSS, JS

Research Associate

April 2018 - July 2018

University of Córdoba, Córdoba, Spain

What I've done

  • Research of new techniques for preprocessing time series.
  • Development of a Python library scikit-learn compatible for time series preprocessing and forecasting through Machine Learning algorithms.

Using

  • Python
  • scikit-learn
  • SOLID principles
  • Git

iOS Developer

October 2017 - April 2018

Redsys Processing Services, Córdoba, Spain

What I've done

  • Writing of internal and external documentation about the use and customization of iOS applications.
  • Preparing presentations for final customers.
  • Development of iOS applications modules using Swift and Xcode.
  • Maintenance of mobile payment soluctions on the iOS ecosystem.

Using

  • Swift
  • Xcode
  • MVC
  • MVP
  • Git

Research Activity

During my career as a researcher I have made some contributions to the scientific community. Feel free to check them out!

COVID-19 contagion forecasting framework based on curve decomposition and evolutionary artificial neural networks: A case study in Andalusia, Spain

Díaz-Lozano, M. et al. (2022)

Expert Systems With Applications

Abstract

Many types of research have been carried out with the aim of combating the COVID-19 pandemic since the first outbreak was detected in Wuhan, China. Anticipating the evolution of an outbreak helps to devise suitable economic, social and health care strategies to mitigate the effects of the virus. For this reason, predicting the SARS-CoV-2 transmission rate has become one of the most important and challenging problems of the past months. In this paper, we apply a two-stage mid and long-term forecasting framework to the epidemic situation in eight districts of Andalusia, Spain. First, an analytical procedure is performed iteratively to fit polynomial curves to the cumulative curve of contagions. Then, the extracted information is used for estimating the parameters and structure of an evolutionary artificial neural network with hybrid architectures (i.e., with different basis functions for the hidden nodes) while considering single and simultaneous time horizon estimations. The results obtained demonstrate that including polynomial information extracted during the training stage significantly improves the mid- and long-term estimations in seven of the eight considered districts. The increase in average accuracy (for the joint mid- and long-term horizon forecasts) is 37.61% and 35.53% when considering the single and simultaneous forecast approaches, respectively.

Clustering of COVID-19 Time Series Incidence Intensity in Andalusia, Spain

Díaz-Lozano, M. et al. (2022)

International Work-Conference on the Interplay Between Natural and Artificial Computation

Abstract

In this paper, an approach based on a time series clustering technique is presented by extracting relevant features from the original temporal data. A curve characterization is applied to the daily contagion rates of the 34 sanitary districts of Andalusia, Spain. By determining the maximum incidence instant and two inflection points for each wave, an outbreak curve can be described by six intensity features, defining its initial and final phases. These features are used to derive different groups using state-of-the-art clustering techniques. The experimentation carried out indicates that k=3 is the optimum number of descriptive groups of intensities. According to the resulting clusters for each wave, the pandemic behavior in Andalusia can be visualised over time, showing the most affected districts in the pandemic period considered. Additionally, in order to perform a pandemic overview of the whole period, the approach is also applied to joint information of all the considered periods.
Check out the conference poster 🪧!

Contact

Are you working on an interesting project in which I can participate? Are you looking for technical profiles? Do you want to talk about geek things 🤓? Let's meet!

Location:

Córdoba, Spain

Loading
Your message has been sent. Thank you!