Vlad Costin Andrei

Mr. Vlad Costin Andrei


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 September 2019 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
PDF file
CDC. O. Dumitru
C. O. Dumitru
VAVlad Costin Andrei
Vlad Costin Andrei
GSGottfried Schwarz
Gottfried Schwarz
MDM. Datcu
M. Datcu
Today, radar imaging from space allows continuous and wide-area sea ice monitoring under nearly all weather conditions. To this end, we applied modern machine learning techniques to produce ice-describing semantic maps of the polar regions of the Earth. Time series of these maps can then be exploited for local and regional change maps of selected areas. What we expect, however, are fully-automated unsupervised routine classifications of sea ice regions that are needed for the rapid and reliable monitoring of shipping routes, drifting and disintegrating icebergs, snowfall and melting on ice, and other dynamic climate change indicators. Therefore, we designed and implemented an automated processing chain that analyses and interprets the specific ice-related content of high-resolution synthetic aperture radar (SAR) images. We trained this system with selected images covering various use cases allowing us to interpret these images with modern machine learning approaches. In the following, we describe a system comprising representation learning, variational inference, and auto-encoders. Test runs have already demonstrated its usefulness and stability that can pave the way towards future artificial intelligence systems extending, for instance, the current capabilities of traditional image analysis by including content-related image understanding.

14 February 2023 in arXiv
Verified
Preprint
Open access
PDF file
VAVlad Costin Andrei
Vlad Costin Andrei
XLXinyang Li
Xinyang Li
UMUllrich J. Mönich
Ullrich J. Mönich
HBHolger Boche
Holger Boche
We address the resilience of future 6G MIMO communications by considering an uplink scenario where multiple legitimate transmitters try to communicate with a base station in the presence of an adversarial jammer. The jammer possesses full knowledge about the system and the physical parameters of the legitimate link, while the base station only knows the UL-channels and the angle-of-arrival (AoA) of the jamming signals. Furthermore, the legitimate transmitters are oblivious to the fact that jamming takes place, thus the burden of guaranteeing resilience falls on the receiver. For this case we derive one optimal jamming strategy that aims to minimize the rate of the strongest user and multiple receive strategies, one based on a lower bound on the achievable signal-to-interference-to-noise-ratio (SINR), one based on a zero-forcing (ZF) design, and one based on a minimum SINR constraint. Numerical studies show that the proposed anti-jamming approaches ensure that the sum rate of the system is much higher than without protection, even when the jammer has considerably more transmit power and even if the jamming signals come from the same direction as those of the legitimate users.

24 September 2023 in arXiv
Verified
Preprint
Open access
PDF file
Roberto FerraraRoberto Ferrara
Roberto Ferrara
LTLuis Torres-Figueroa
Luis Torres-Figueroa
HBHolger Boche
Holger Boche
Christian DeppeChristian Deppe
Christian Deppe
WLWafa Labidi
Wafa Labidi
VAVlad Costin Andrei
Vlad Costin Andrei
Identification is a communication paradigm that promises exponential advantages over transmission for applications that do not actually require all messages to be reliably transmitted. Notably, the identification capacity theorems prove exponentially larger rates compared to classical transmission. However, there exist additional trade-offs that are not captured by these theorems and which become relevant for the deployment of identification in practical communication settings. In particular, in this paper we evaluate the latency introduced by computations at the encoder and decoder when employing identification codes. For this, we implement them using an explicit code construction based on Reed-Solomon codes and integrate it into a single carrier transmission system using software-defined radios. Our evaluation of the practical aspects of identification codes show that unless care is taken, these trade-offs can compromise the theoretical advantage given by the exponentially large identification rates.

27 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
MBMichael Baur
Michael Baur
MWMichael Würth
Michael Würth
MKMichael Koller
Michael Koller
VAVlad Costin Andrei
Vlad Costin Andrei
WUWolfgang Utschick
Wolfgang Utschick
The model order of a wireless channel plays an important role for a variety of applications in communications engineering, e.g., it represents the number of resolvable incident wavefronts with non-negligible power incident from a transmitter to a receiver. Areas such as direction of arrival estimation leverage the model order to analyze the multipath components of channel state information. In this work, we propose to use a variational autoencoder to group unlabeled channel state information with respect to the model order in the variational autoencoder latent space in an unsupervised manner. We validate our approach with simulated 3GPP channel data. Our results suggest that, in order to learn an appropriate clustering, it is crucial to use a more flexible likelihood model for the variational autoencoder decoder than it is usually the case in standard applications.

25 January 2023 in arXiv
Verified
Preprint
Open access
PDF file
XLXinyang Li
Xinyang Li
VAVlad Costin Andrei
Vlad Costin Andrei
UMUllrich J. Mönich
Ullrich J. Mönich
HBHolger Boche
Holger Boche
Wireless channel sensing is one of the key enablers for integrated sensing and communication (ISAC) which helps communication networks understand the surrounding environment. In this work, we consider MIMO-OFDM systems and aim to design optimal and robust waveforms for accurate channel parameter estimation given allocated OFDM resources. The Fisher information matrix (FIM) is derived first, and the waveform design problem is formulated by maximizing the log determinant of the FIM. We then consider the uncertainty in the parameters and state the stochastic optimization problem for a robust design. We propose the Riemannian Exact Penalty Method via Smoothing (REPMS) and its stochastic version SREPMS to solve the constrained non-convex problems. In simulations, we show that the REPMS yields comparable results to the semidefinite relaxation (SDR) but with a much shorter running time. Finally, the designed robust waveforms using SREMPS are investigated, and are shown to have a good performance under channel perturbations.

5 December 2024 in arXiv
Verified
Preprint
Open access
PDF file
VAVlad Costin Andrei
Vlad Costin Andrei
ADAlexandru P. Drăguţoiu
Alexandru P. Drăguţoiu
GBGabriel Béna
Gabriel Béna
MAMahmoud Akl
Mahmoud Akl
YLYin Li
Yin Li
HBHolger Boche
Holger Boche
This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval (MHR). By casting the MHR problem as a sparse recovery problem, we devise the currently proposed, deep-unrolling-based Structured Learned Iterative Shrinkage and Thresholding (S-LISTA) algorithm to solve it efficiently using complex-valued convolutional neural networks with complex-valued activations, which are trained using a supervised regression objective. Afterward, a novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed. At the heart of this method lies the recently proposed Few Spikes (FS) conversion, which is extended by modifying the neuron model's parameters and internal dynamics to account for the inherent coupling between real and imaginary parts in complex-valued computations. Finally, the converted SNNs are mapped onto the SpiNNaker2 neuromorphic board, and a comparison in terms of estimation accuracy and power efficiency between the original CNNs deployed on an NVIDIA Jetson Xavier and the SNNs is being conducted. The measurement results show that the converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.