Jump to main content

Mulugeta Weldezgina Asres

PhD Research Fellow

Research Fellow

A03206 ( Jon Lilletuns vei 9, Grimstad )
Office hours:
10:00 - 13:00

Mulugeta Weldezgina Asres is a Ph.D. researcher on Large-Scale Contextual Time-Aware Anomaly Detection Systems for CERN CMS HCAL detector.

He received his B.Sc. and M.Sc. in Computer Engineering at EiT-M, Mekelle University, Ethiopia, with honors of Gold-Medal Award, in 2012 and 2016, respectively. He conducted his Master's thesis and post-graduate research on machine learning for NILM (Non-intrusive Load Monitoring) of complex systems at Midori Srl, an innovative start-up in energy efficiency incubated in I3P, Italy.

He is a former academic member of Mekelle University (2012-2017) and Polytechnic of Turin, Italy, (2018-2020), who researched and developed various AI-powered industrial data science and monitoring applications.


Research interests

Multivariate Time-Series, Large Datasets, Anomaly Detection, Data Science, Data-Driven Models, Deep Learning, IoT, and Industry 4.0

Work experience

Graduate Research Fellow at Center of Artificial Intelligence Research (CAIR), Norway
2020 -

  • Development of a large scale contextual time-aware AD system for CERN detectors.

Research Fellow at Politecnico di Torino, Turin Area, Italy

2018 - 2020

  • R & D on smart-data automation by applying explorative, descriptive, and predictive data analytics using AI for Industry 4.0.
  • Data analytics and machine learning for telecom monitoring system for Telecom Italia (TIM);
  • Predictive energy modeling in vehicle manufacturing factory (FCA);
  • Data analytics in NILM: anomaly detection, recommender systems

NILM Researcher and Developer at Midori srl, Turin Area, Italy

2016 - 2018

  • Developed Algorithms and Machine Learning Systems for NED (Midori's Commercial Product)
  • Developed robust NILM algorithms for domestic and commercial buildings using unsupervised machine learning and signal processing tools.
  • Developed an efficient event-based load disaggregation system with a robust capability for diverse appliance switching transients especially long transients from ACs and overlapped events which are challenging to capture using conventional detectors;
  • Devised an effective mechanism that solves dynamic frequent switching event overlapping challenges from Washing Machines, Microwave, SASD, etc using unsupervised signal analysis;
  • Researched on Non-Intrusive Energy Disaggregation for complex scenarios such as commercial utilities and low voltage substations

Lecturer and Researcher at Ethiopian Institute of Technology - Mekelle, Ethiopia
2013 - 2017

  • Delivered lectures and supervised interns and undergraduate projects.
  • Assisted postgraduate lab courses and projects.
  • Manage and develop applied machine learning research and projects.
  • Freelance software, web, and embedded system developer.

Academic interests

R & D

Selected publications

Asres, MW, Ardito, L., & Patti, E. (2021). Computational Cost Analysis and Data-Driven Predictive Modeling of Cloud-based Online NILM Algorithm. IEEE Transactions on Cloud Computing, (01), 1-1.

Asres, MW, Mengistu, MA, Castrogiovanni, P., Bottaccioli, L., Macii, E., Patti, E., & Acquaviva, A. (2020). Supporting Telecommunication Alarm Management System With Trouble Ticket Prediction. IEEE Transactions on Industrial Informatics17 (2), 1459-1469.

Asres, MW, Girmay, AA, Camarda, C., & Tesfamariam, GT (2019). Non-intrusive load composition estimation from aggregate ZIP load models using machine learning. International Journal of Electrical Power & Energy Systems105, 191-200.

Mali, D., Weldezgina, M., Birhanu, A., & Gebrehiwot, H. (2014). Simulation of GSM Based Home Security and Control System. Wireless Communication, 6 (1), 7-11.

Last changed: 2.02.2021 13:02