Filters








4 Hits in 5.8 sec

Network Anomaly Detection using Memory-augmented Deep Autoencoder

Byeongjun Min, JiHoon Yoo, Sangsoo Kim, Dongil Shin, Dongkyoo Shin
2021 IEEE Access  
The MemAE model is trained to reconstruct the input of an abnormal sample that is close to a normal sample, which solves the generalization problem for such abnormal samples.  ...  This approach is based on the assumption that reconstruction errors for samples that are not used for training will be large, but an autoencoder is often over-generalized and this assumption is often broken  ...  There are two types of MemAE models used in the experiment: the non-sparse MemAE model and the sparse MemAE model.  ... 
doi:10.1109/access.2021.3100087 fatcat:ffu2diqdlra2pkxp3o2b3cbmii

A mapping study on the feasibility of method engineering

Marco Kuhrmann, Daniel Méndez Fernández, Michaela Tiessler
2014 Journal of Software: Evolution and Process  
Contribution We contribute a systematic mapping study to elaborate the state-of-the-art in Method Engineering and Situational Method Engineering with a particular focus on reported evidence for the feasibility  ...  This shall allow for a systematic investigation of the broad publication flora in method engineering and to draw a big picture of reported concepts and evidence for their feasibility.  ...  ACKNOWLEDGEMENTS We want to thank Olena Stute for her work on the initial investigation to figure out the key contributions on method engineering.  ... 
doi:10.1002/smr.1642 fatcat:coamszfo3fc7tmmoixdecbsuzq

MARVEL - D3.1: Multimodal and privacy-aware audio-visual intelligence – initial version

Alexandros Iosifidis
2022 Zenodo  
The effectiveness of these methods is compared against recent baselines, towards achieving the AI methodology- related objectives of the MARVEL project.  ...  This document describes the initial version of the methodologies pro- posed by MARVEL partners towards the realisation of the Audio, Visual and Multimodal AI Subsystem of the MARVEL architecture.  ...  The latter has a quadratic impact on both parameter and MAC count.  ... 
doi:10.5281/zenodo.6821317 fatcat:eia7rkk5lfbg7khs3qcat5qd3m

Modellbasierte Meta-Analyse veranschaulicht am Zusammenhang von Religiosität und Lebenszufriedenheit [article]

Marius Reinhold Wuketich, Universität Stuttgart, Universität Stuttgart
2020
Regarding the two methods for moderator analysis, the OSMASEM approach has a clear advantage over subgroup analysis.  ...  On the one hand, a subgroup analysis is performed in the conventional TSSEM approach and on the other hand, the possibilities of the new OSMASEM for the investigation of moderator variables are being used  ... 
doi:10.18419/opus-10794 fatcat:snvex27xlfbqjbunzwbhc3fi7q