Julio De Melo Borges

Karlsruhe Institute of Technology (KIT)
Campus Süd
Institute of Telematics
Chair for Pervasive Computing Systems / TECO
Vincenz-Prießnitz-Straße 1
76131 Karlsruhe
Germany
Building 07.07, Room 214

email: borges(at)teco.edu
LinkedIn: http://lnked.in/jborges
phone: +49 721 608-41708
fax: +49 721 608-41702

Short CV

2015-Now: PhD Student at TECO/KIT
2015: Graduation with Master (MSc) of Computer Science from Karlsruhe Institute of Technology (KIT)
2015: Conclusion of Software Campus Executive Training Program in cooperation with Software AG
2012: Graduation with Bachelor (BSc) of Computer Science from Karlsruhe Institute of Technology (KIT)

Projects

2014 – 2017: Data Scientist @ Smart Data Innovation Lab (SDIL) – Promotion of Cutting-Edge Smart Data Research
→ See our projects at: http://www.sdil.de/en/projects/

2014 – 2017: Data Scientist @ Smart Data Solution Center (SDSC) – Smart Data Analytics for Small and Medium Enterprises.
→ See our success stories at: http://sdsc-bw.de/erfolge

2014 – 2015: Project Manager – ESTAData – Data driven decision recommendation for administrative bodies based on collective intelligence

Activities

2017

Speaker at: Information and Networking Days on Horizon 2020 Big Data topics

2016

International Conference on IOT in Urban Space (Urb-IoT’16). Organizing Committee – Social Media Chair
Speaker at ISC High Performance Computing Conference: Industry meets Research: Success-Stories of the Smart Data Solution Center Baden-Wuerttemberg
Speaker at Bitkom Big Data Summit: Industry Meets Science: Erfolge des Smart Data Innovation Lab
Speaker at Small Big Data Value Association Summit: Innovation Spaces (SDIL)

2015

International Conference on Smart Grid Communications (SmartGridComm). Technical Program Committee
Speaker at IHK Karlsruhe: Von Big Data zu Smart Data

Teaching

2017 – Praktikum Smart Data Analytics

2016 – Praktikum Kontextsensitive ubiquitäre Systeme (now: Smart Data Analytics): Techniques, methods and software for context acquisition and processing as the basis of Smart Data Analytics.
- Achievements: Top 1% in a Data Mining Competition on Kaggle

Supervised Theses

Simon Sudrich: Anomaly Detection for Dynamic Heterogeneous Graphs (Praxis der Forschung)

Qianqian Cao: Enhancing Traffic Flow Forecasting with Environmental Models (Master-Thesis)

Daniel Ziehr: Leveraging Spatio-Temporal Features for Improving Predictive Policing (Master-Thesis).

Wei Han: Association Rules Mining for Master Data (Master-Thesis)

Research Interests

Data Mining
Machine Learning
Big Data Technologies
IoT + Smart Cities

Peer-reviewed Publications

2017

Adelson Araujo Junior, Nelio Cacho, Antonio Carlos Thome, Allan Medeiros, Julio Borges (2017) A predictive policing application to support patrol planning in smart cities, 2017 International Smart Cities Conference, ISC2 2017, url, doi:10.1109/ISC2.2017.8090817

Simon Sudrich, Julio Borges, Michael Beigl (2017) Graph-based Anomaly Detection for Smart Cities: A Survey, IEEE International Conference on Smart City Innovations (IEEE SCI 2017), url

Julio Borges, Daniel Ziehr, Michael Beigl, Nelio Cacho, Allan Martins, Simon Sudrich, Samuel Abt, Patrick Frey, Timo Knapp, Michaela Etter, Johannes Popp (2017) Feature Engineering for Crime Hotspot Detection, IEEE International Conference on Smart City Innovations (IEEE SCI 2017), Best Paper Award, url

Julio Borges, Henrik Hain, Simon Sudrich, Michael Beigl (2017) Event Detection for Smarter Cities, IEEE International Conference on Smart City Innovations (IEEE SCI 2017), url

Julio Borges, Peter Bozsoky, Simon Sudrich, Michael Beigl (2017) Advances in Event Detection, The 3rd IEEE International Conference on Smart Data, url

Simon Sudrich, Julio Borges, Michael Beigl (2017) Anomaly Detection in Evolving Heterogeneous Graphs, The 3rd IEEE International Conference on Smart Data, url

Julio Borges, Martin A Neumann, Christian Bauer, Yong Ding, Till Riedel, Michael Beigl (2017) Predicting Target Events In Industrial Domains, Machine Learning and Data Mining in Pattern Recognition, Petra Perner (ed.), p. (To Appear), New York, NY, USA: Springer, url

Wei Han, Julio Borges, Peter Neumayer, Yong Ding, Till Riedel, Michael Beigl (2017) Interestingness Classification of Association Rules for Master Data, 17th Industrial Conference on Data Mining (ICDM), url

2016

Julio Borges, Christian Bauer (2016) Analysis of highly variant, temporal data sets for condition-based maintenance, 1st Smart Data Innovation Conference (SDIC), url

Julio De Melo Borges, Matthias Budde, Oleg Peters, Till Riedel, Michael Beigl (2016) Towards Two-Tier Citizen Sensing, 2nd IEEE International Smart Cities Conference (ISC2-2016), url, doi:10.1109/ISC2.2016.7580771

Julio De Melo Borges, Till Riedel, Michael Beigl (2016) Urban Anomaly Detection: a Use-Case for Participatory Infra-Structure Monitoring, Proceedings of the Second International Conference on IoT in Urban Space - Urb-IoT'16, Best Note Award, url

Julio De Melo Borges, Matthias Budde, Oleg Peters, Till Riedel, Andrea Schankin, Michael Beigl (2016) EstaVis: A Real-World Interactive Platform for Crowdsourced Visual Urban Analytics, Proceedings of the Second International Conference on IoT in Urban Space - Urb-IoT'16, Best Paper Nominee, url

2015

Yong Ding, Julio Borges, Martin A. Neumann, Michael Beigl (2015) Sequential Pattern Mining – a Study to Understand Daily Activity Patterns for Load Forecasting Enhancement, 1st IEEE International Smart Cities Conference (ISC2-2015), Guadalajara, Mexico: IEEE, url

2014

Matthias Budde, Julio De Melo Borges, Stefan Tomov, Till Riedel, Michael Beigl (2014) Leveraging Spatio-Temporal Clustering for Participatory Urban Infrastructure Monitoring, The First International Conference on IoT in Urban Space (UrbIoT'14), Best Paper Award, url

Matthias Budde, Julio De Melo Borges, Stefan Tomov, Till Riedel, Michael Beigl (2014) Improving Participatory Urban Infrastructure Monitoring through Spatio-Temporal Analytics, 3rd ACM SIGKDD International Workshop on Urban Computing (UrbComp’14) - Co-located with the ACM International Conference on Knowledge Discovery and Data Mining (KDD 2014), pdf