,

Paper Accepted @ Blockchain for Smart Cyber-Physical Systems – UCC’2021

Title: Monitoring System Architecture for the Multi-Scale Blockchain-based Logistic Network

Authors: Vladislav Kashansky, Radu Prodan, Aso Validi, Cristina Olaverri-Monreal, Gleb Radchenko

Abstract: Contemporary control processes and methods in multi-scale, cyber-physical systems require precise data collection at various levels, timely transmission, and analysis involving large number of computing and storage elements connected within high-performance permissioned consensus networks. For example, in transport networks, resources tend to form multi-scale dynamical systems with diverse operational requirements, including data exchange policies and consensus protocols. Apart from designing complete topology, chaincodes and consensus logic, effective monitoring of the applications and infrastructure of such complex systems remains a research challenge. In this paper, we discuss important aspects of the data-intensive applications monitoring investigated in the frames of the ADAPT project.

We present highlights on the tool-sets, architectures and details on possible optimization approaches for monitoring data collection. We introduce a dynamic multi-scale monitoring system architecture with preliminary workflow model. It allows obtaining effective low-latency publish-subscribe matching of the dynamically varying monitoring tasks and executing machines.

Keywords: Logistics, transportation, decentralization, blockchain, monitoring systems, optimization, data-intensive systems, hybrid systems

Dragi Kimovski
,

The final ASPIDE paper has been accepted in the “Frontiers in Big Data” Journal

Title: Autotuning of exascale applications with anomalies detection

Authors: Dragi Kimovski, Roland Mathá, Gabriel Iuhasz, Fabrizio Marozzo, Dana Petcu, Radu Prodan

Abstract: The execution of complex distributed applications in exascale systems faces many challenges, as it involves empirical evaluation of countless code variations and application run-time parameters over a heterogeneous set of resources. To mitigate these challenges, the research field of autotuning has gained momentum. The autotuning automates identifying the most desirable application implementation in terms of code variations and run-time parameters. However, the complexity and size of the exascale systems make the autotuning process very difficult, especially considering the number of parameter variations that have to be identified. Therefore, we introduce a novel approach for autotuning of exascale applications based on a genetic multi-objective optimization algorithm integrated within the ASPIDE exascale computing framework. The approach considers multi-dimensional search space with support for pluggable objectives functions, including execution time and energy requirements. Furthermore, the autotuner employs a machine learning-based event detection approach to detect events and anomalies during application execution, such as hardware failures or communication bottlenecks.

Keywords: Exascale computing, Autotuning, Events and Anomalies Detection, Multi-objective Optimisation

 

Univ.-Prof. DI Dr. Radu Prodan for being discussion leader in licentiate seminar

Univ.-Prof. DI Dr. Radu Prodan was nominated as discussion leader for the defensio of Mrs. Zeinab Bakhshi from Mälardalen University in Stockholm Sweden.

 

 

, ,

Farzad Tashtarian to give a talk at the University of Isfahan, Isfahan, Iran

Farzad Tashtarian is invited to talk on “Network-Assisted Video Streaming” at the University of Isfahan, Isfahan, Iran.

,

ADAPT Meeting Vienna

Dr. Gerhard Burian and Mag. Vladislav Kashansky participated on behalf of ADAPT collaboration in the international conference: Climate protection: state of play, division of labor, steps forward held at OeNB, Vienna on 07.10.2021.

,

DataCloud Meeting in Rome, Italy

The first face-to-face DataCloud Meeting took place in Rome, Italy, from October 04-06, 2021. The consortium discussed the architecture and the business cases in preparation for the first project review.

Natalia Sokolova
,

Pupil Reaction Detection Paper Accepted in PLOS ONE

Congratulations to Natalia Sokolova, who got her journal paper on “Automatic detection of pupil reactions in cataract surgery videos” accepted in the PLOS ONE journal. This work has been (co-)authored by Natalia Sokolova, Klaus Schoeffmann, Mario Taschwer, Stephanie Sarny, Doris Putzgruber-Adamitsch, and Yosuf El-Shabrawi.

, ,

Paper Accepted at ICONIP 2021

Congratulations to Negin Ghamsarian et al., who got their paper “ReCal-Net: Joint Region-Channel-Wise Calibrated Network for Semantic Segmentation in Cataract Surgery Videos” accepted at the International Conference on Neural Information Processing (ICONIP 2021).

Abstract: Semantic segmentation in surgical videos is a prerequisite for a broad range of applications towards improving surgical outcomes and surgical video analysis. However, semantic segmentation in surgical videos involves many challenges. In particular, in cataract surgery, various features of the relevant objects such as blunt edges, color and context variation, reflection, transparency, and motion blur pose a challenge for semantic segmentation. In this paper, we propose a novel convolutional module termed as ReCal module, which can calibrate the feature maps by employing region intra-and-inter-dependencies and channel-region cross-dependencies. This calibration strategy can effectively enhance semantic representation by correlating different representations of the same semantic label, considering a multi-angle local view centering around each pixel. Thus the proposed module can deal with distant visual characteristics of unique objects as well as cross-similarities in the visual characteristics of different objects. Moreover, we propose a novel network architecture based on the proposed module termed as ReCal-Net. Experimental results confirm the superiority of ReCal-Net compared to rival state-of-the-art approaches for all relevant objects in cataract surgery. Moreover, ablation studies reveal the effectiveness of the ReCal module in boosting semantic segmentation accuracy.

,

FaRes-ML paper is Nominated for the Best New Streaming Innovation Award in the Streaming Media Readers’ Choice Awards 2021

The Fast Multi-Resolution and Multi-Rate Encoding for HTTP Adaptive Streaming Using Machine Learning paper from ATHENA lab is nominated for the Best New Streaming Innovation Award in the Streaming Media Readers’ Choice Awards 2021.

Voting can be done on the awards’ website. The voting is open until October 4. You can find the paper under the Best New Streaming Innovation Award section as following:

More information about the paper can be found here.

Andreas Leibetseder completed his PhD!

On August 30th 2021, Andreas Leibetseder successfully defended his thesis on “Extracting and Using Medical Expert Knowledge to Advance Video Analysis for Gynecologic Laparoscopy” under the supervision of Prof. Klaus Schöffmann. The defense was chaired by Prof. Hermann Hellwagner and the examiners were Prof. Oge Marques (Florida Atlantic University) and Prof. Mathias Lux (Klagenfurt University). Congratulations to Dr. Leibetseder for this great achievement!