Dissemination activities will be listed here as they take place.
Journals
1. JunKyu Lee, Lev Mukhanov, Amir Sabbagh Molahosseini, Umar Minhas, Yang Hua, Jesus Martinez del Rincon, Kiril Dichev, Cheol-Ho Hong, Hans Vandierendonck, “Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques“, Submitted to ACM Computing Surveys.
2. N. Llisterri Giménez, M. Monfort Grau, R. Pueyo Centelles, and F. Freitag, “On-device training of machine learning models on microcontrollers with federated learning“, Electronics, vol. 11, no. 4, 2022.
3. Javier Panadero, Mennan Selimi, Laura Calvet, Joan Manuel Marquès, Felix Freitag, “A two-stage Multi-Criteria Optimization method for service placement in decentralized edge micro-clouds“, Volume 121, August 2021, Pages 90-105, Future Generation Computer Systems, 2021
Conferences
1. F. Freitag, P. Vilchez, Ch. Liu, L. Wei, and M. Selimi, “Testbed in Wireless City Mesh Network with Application to Federated Learning Experiments“, ACM/SIGCHI International Conference on the Internet of Things (IoT 2021), Nov 2021, St.Gallen, Switzerland.
2. Llorenç Cerdà-Alabern, Gabriel Iuhasz, “Anomaly Detection in Wireless Community Networks using PCA“, In Jornadas de Concurrencia y Sistemas Distribuidos, 2021.
3. Marc Monfort Grau, Roger Pueyo Centelles, Felix Freitag, “On-Device Training of Machine Learning Models on Microcontrollers With a Look at Federated Learning“, In GoodIT ’21: Proceedings of the Conference on Information Technology for Social Good, 2021.
4. JunKyu Lee, Blesson Varghese, Roger Woods, Hans Vandierendonck, “TOD: Transprecise Object Detection to Maximise Real-Time Accuracy on the Edge”, In: 5th IEEE International Conference on Fog and Edge Computing (ICFEC) 2021. Presentation Link: https://www.youtube.com/watch?v=cESSAH2EsUo&t=540s
5. Calin-George Barburescu, Gabriel Iuhasz, “Optimizing Deep Learning Models for Object Detection“, 22nd IEEE International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), 2020
6. Amir Sabbagh Molahosseini, Hans Vandierendonck. “Half-Precision Floating-Point Formats for PageRank: Opportunities and Challenges”, In: 2020 IEEE High Performance Extreme Computing Conference (HPEC), September, 2020
Workshops
1. Hans Vandierendonck, “Distributed Stream Processing on Fog and Edge Systems using Transprecise Computing”, At the HiPEAC Computing Systems Week in Lyon, 25-27 October 2021
2. JunKyu Lee, “Energy-Efficient Transprecision Computing”, At NI-HPC User Conference, 2021.
3. JunKyu Lee, “Transprecise Object Detection to Maximise Real-Time Accuracy on the Edge”, Poster Presentation in tinyML EMEA Technical Forum 2021. Poster link: https://cms.tinyml.org/wp-content/uploads/emea2021/tinyMLEMEA2021d4_Lee.pdf
Deliverables
GitHub/GitLab Links
1. Event-Detection-Engine (Main Author: Gabriel, UVT)
Event Detection Engine (EDE) for the DIPET Chist-Era project based on the work done during the DICE H2020 project specifically the DICE Anomaly Detection Platform and on the work done during the ASPIDE H2020 project. EDE can be used for detecting anomalies and events. Event and anomaly detection can be split up into several categories based on the methods and the characteristics of the available data. For example, the most simple form of anomalies are point anomalies which can be characterized by only one metric (feature). These types of anomalies are fairly easy to detect by applying simple rules (i.e. CPU is above 70%). Other types of anomalies are more complex but ultimately yield a much deeper understanding about the inner workings of a monitored exascale system or application.
2. DiPET Network Intrusion Detection System (Main Author: Roger, UPC)
Repository for the code developed within DiPET on the traffic anomaly detection use case related to the eXo micro ISP in Guifi.net. The approach targets the analysis of network flows, specifically netflow records. The code in the repository combines the Pmacct suite, anonymisation tools and Apache Kafka.
3. Open Dataset for Anomaly Detection in a Production Wireless Mesh Community Network Uploaded to Zenodo (Main Author: Llorenç Cerdà-Alabern, UPC)
CSV dataset generated gathering data from a production wireless mesh community network. Data is gathered every 5 minutes during the interval 2021-04-13 00:00:00 to 2021-04-16 00:00:00. During the interval 2021-04-14 01:55:00 2021-04-14 18:10:00 there is the failure of a gateway in the mesh (node 24). Mesh network link: http://dsg.ac.upc.edu/qmpsu . For every node the features listed below are gathered (whenever possible). Feature’s suffix is the node number, as in “processes-23”.