Search

Accurate, detailed, and high-frequent bathymetry, coupled with complex semantic content, is crucial for the undermapped shallow seabed areas facing intense climatological and anthropogenic pressures. Current methods exploiting remote sensing images to derive bathymetry or seabed classes mainly exploit non-open data. This lack of openly accessible benchmark archives prevents the wider use of deep learning methods in such applications. To address this issue, in this paper we present the MagicBathyNet, which is a benchmark dataset made up of image patches of Sentinel2, SPOT-6 and aerial imagery, bathymetry in raster format and annotations of seabed classes. MagicBathyNet is then exploited to benchmark state-of-the-art methods in learning-based bathymetry and pixel-based classification. Dataset, pre-trained weights, and code are publicly available at www.magicbathy.eu/magicbathynet.html., Comment: 5 pages, 3 figures, 5 tables. Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2024

Federated learning (FL) aims to collaboratively learn deep learning model parameters from decentralized data archives (i.e., clients) without accessing training data on clients. However, the training data across clients might be not independent and identically distributed (non-IID), which may result in difficulty in achieving optimal model convergence. In this work, we investigate the capability of state-of-the-art transformer architectures (which are MLP-Mixer, ConvMixer, PoolFormer) to address the challenges related to non-IID training data across various clients in the context of FL for multi-label classification (MLC) problems in remote sensing (RS). The considered transformer architectures are compared among themselves and with the ResNet-50 architecture in terms of their: 1) robustness to training data heterogeneity; 2) local training complexity; and 3) aggregation complexity under different non-IID levels. The experimental results obtained on the BigEarthNet-S2 benchmark archive demonstrate that the considered architectures increase the generalization ability with the cost of higher local training and aggregation complexities. On the basis of our analysis, some guidelines are derived for a proper selection of transformer architecture in the context of FL for RS MLC. The code of this work is publicly available at https://git.tu-berlin.de/rsim/FL-Transformer., Comment: Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2024. Our code is available at https://git.tu-berlin.de/rsim/FL-Transformer

The development of supervised deep learning-based methods for multi-label scene classification (MLC) is one of the prominent research directions in remote sensing (RS). Yet, collecting annotations for large RS image archives is time-consuming and costly. To address this issue, several data augmentation methods have been introduced in RS. Among others, the data augmentation technique CutMix, which combines parts of two existing training images to generate an augmented image, stands out as a particularly effective approach. However, the direct application of CutMix in RS MLC can lead to the erasure or addition of class labels (i.e., label noise) in the augmented (i.e., combined) training image. To address this problem, we introduce a label propagation (LP) strategy that allows the effective application of CutMix in the context of MLC problems in RS without being affected by label noise. To this end, our proposed LP strategy exploits pixel-level class positional information to update the multi-label of the augmented training image. We propose to access such class positional information from reference maps associated to each training image (e.g., thematic products) or from class explanation masks provided by an explanation method if no reference maps are available. Similarly to pairing two training images, our LP strategy carries out a pairing operation on the associated pixel-level class positional information to derive the updated multi-label for the augmented image. Experimental results show the effectiveness of our LP strategy in general and its robustness in the case of various simulated and real scenarios with noisy class positional information in particular.

The physical layer foundations of cell-free massive MIMO (CF-mMIMO) have been well-established. As a next step, researchers are investigating practical and energy-efficient network implementations. This paper focuses on multiple sets of access points (APs) where user equipments (UEs) are served in each set, termed a federation, without inter-federation interference. The combination of federations and CF-mMIMO shows promise for highly-loaded scenarios. Our aim is to minimize the total energy consumption while adhering to UE downlink data rate constraints. The energy expenditure of the full system is modelled using a detailed hardware model of the APs. We jointly design the AP-UE association variables, determine active APs, and assign APs and UEs to federations. To solve this highly combinatorial problem, we develop a novel alternating optimization algorithm. Simulation results for an indoor factory demonstrate the advantages of considering multiple federations, particularly when facing large data rate requirements. Furthermore, we show that adopting a more distributed CF-mMIMO architecture is necessary to meet the data rate requirements. Conversely, if feasible, using a less distributed system with more antennas at each AP is more advantageous from an energy savings perspective., Comment: EuCNC/6G Summit 2024

Influenced by breakthroughs in LLMs, single-cell foundation models are emerging. While these models show successful performance in cell type clustering, phenotype classification, and gene perturbation response prediction, it remains to be seen if a simpler model could achieve comparable or better results, especially with limited data. This is important, as the quantity and quality of single-cell data typically fall short of the standards in textual data used for training LLMs. Single-cell sequencing often suffers from technical artifacts, dropout events, and batch effects. These challenges are compounded in a weakly supervised setting, where the labels of cell states can be noisy, further complicating the analysis. To tackle these challenges, we present sc-OTGM, streamlined with less than 500K parameters, making it approximately 100x more compact than the foundation models, offering an efficient alternative. sc-OTGM is an unsupervised model grounded in the inductive bias that the scRNAseq data can be generated from a combination of the finite multivariate Gaussian distributions. The core function of sc-OTGM is to create a probabilistic latent space utilizing a GMM as its prior distribution and distinguish between distinct cell populations by learning their respective marginal PDFs. It uses a Hit-and-Run Markov chain sampler to determine the OT plan across these PDFs within the GMM framework. We evaluated our model against a CRISPR-mediated perturbation dataset, called CROP-seq, consisting of 57 one-gene perturbations. Our results demonstrate that sc-OTGM is effective in cell state classification, aids in the analysis of differential gene expression, and ranks genes for target identification through a recommender system. It also predicts the effects of single-gene perturbations on downstream gene regulation and generates synthetic scRNA-seq data conditioned on specific cell states., Comment: ICLR 2024, Machine Learning for Genomics Explorations Workshop

Exploring novel strategies for the regulation of axon growth, we introduce a periodic event-triggered control (PETC) to enhance the practical implementation of the associated PDE backstepping control law. Neurological injuries may impair neuronal function, but therapies like Chondroitinase ABC (ChABC) have shown promise in improving axon elongation by influencing the extracellular matrix. This matrix, composed of extracellular macromolecules and minerals, regulates tubulin protein concentration, potentially aiding in neuronal recovery. The concentration and spatial distribution of tubulin influence axon elongation dynamics. Recent research explores feedback control strategies for this model, leading to the development of an event-triggering control (CETC) approach. In this approach, the control law updates when the monitored triggering condition is met, reducing actuation resource consumption. Through the meticulous redesign of the triggering mechanism, we introduce a periodic event-triggering control (PETC), updating control inputs at specific intervals, but evaluating the event-trigger only periodically, an ideal tool for standard time-sliced actuators like ChABC. PETC is a step forward to the design of practically feasible feedback laws for the neuron growth process. The PETC strategy establishes an upper bound on event triggers between periodic examinations, ensuring convergence and preventing Zeno behavior. Through Lyapunov analysis, we demonstrate the local exponential convergence of the system with the periodic event-triggering mechanism in the $L^2$-norm sense. Numerical examples are presented to confirm the theoretical findings., Comment: Submitted to 2024 Conference on Decision and Control

The next generation of cellular networks will be characterized by openness, intelligence, virtualization, and distributed computing. The Open Radio Access Network (Open RAN) framework represents a significant leap toward realizing these ideals, with prototype deployments taking place in both academic and industrial domains. While it holds the potential to disrupt the established vendor lock-ins, Open RAN's disaggregated nature raises critical security concerns. Safeguarding data and securing interfaces must be integral to Open RAN's design, demanding meticulous analysis of cost/benefit tradeoffs. In this paper, we embark on the first comprehensive investigation into the impact of encryption on two pivotal Open RAN interfaces: the E2 interface, connecting the base station with a near-real-time RAN Intelligent Controller, and the Open Fronthaul, connecting the Radio Unit to the Distributed Unit. Our study leverages a full-stack O-RAN ALLIANCE compliant implementation within the Colosseum network emulator and a production-ready Open RAN and 5G-compliant private cellular network. This research contributes quantitative insights into the latency introduced and throughput reduction stemming from using various encryption protocols. Furthermore, we present four fundamental principles for constructing security by design within Open RAN systems, offering a roadmap for navigating the intricate landscape of Open RAN security.

Integrated sensing and communication (ISAC) has already established itself as a promising solution to the spectrum scarcity problem, even more so when paired with a reconfigurable intelligent surface (RIS), as RISs can shape the propagation environment by adjusting their phase-shift coefficients. Albeit the potential performance gain, a RIS is also a potential security threat to the system. In this paper, we explore both the positive and negative sides of having a RIS in a multi-user multiple-input multiple-output (MIMO) ISAC network. We first develop an alternating optimization algorithm, obtaining the active and passive beamforming vectors that maximize the sensing signal-to-noise ratio (SNR) under minimum signal-to-interference-plus-noise ratio (SINR) constraints for the communication users and finite power budget. We also investigate the destructive potential of the RIS by devising a RIS phase-shift optimization algorithm that minimizes the sensing SNR while preserving the same minimum communication SINR previously guaranteed by the system. We further investigate the impact of the RIS's individual element failures on the system performance. The simulation results show that the RIS performance-boosting potential is as good as its destructive one and that both of our optimization strategies are hindered by the investigated impairments., Comment: To be presented at IEEE ICC25

Diluted magnetic semiconductor (DMS) colloidal nanocrystals demonstrate remarkable magneto-optical properties. However, the behavior of circular polarization of their emission in high magnetic fields remains unclear. We measure magneto-optical properties of colloidal CdSe/CdMnS nanoplatelets in high magnetic fields up to 30 T and at cryogenic temperatures. The degree of circular polarization of photoluminescence demonstrates non-monotonous behavior in a magnetic field. In low magnetic fields, the polarization degree is positive, due to an exchange interaction of excitons with localized spins of magnetic Mn ions. The exchange interaction is strong enough to overcome the intrinsic Zeeman splitting, which provides negatively polarized emission in nonmagnetic CdSe/CdS nanoplatelets. After reaching a maximum the polarization degree starts to decrease and reverses the sign to negative in high magnetic fields. The critical magnetic field, in which the sign is reversed, increases when temperature is elevated. We develop a model, which explains this behavior by an interplay of bright and dark exciton recombination.

Following the promising beamforming gains offered by reconfigurable intelligent surfaces (RISs), a new hardware architecture, known as \emph{beyond diagonal RIS (BD-RIS)}, has recently been proposed. This architecture enables controllable signal flows between the RIS elements, thereby providing greater design flexibility. However, the physics-imposed symmetry and orthogonality conditions on the non-diagonal reflection matrix make the design challenging. In this letter, we analyze how a BD-RIS can improve a wideband channel, starting from fundamental principles and deriving the capacity. Our analysis considers the effects of various channel taps and their frequency-domain characteristics. We introduce a new algorithm designed to optimize the configuration of the BD-RIS to maximize wideband capacity. The proposed algorithm has better performance than the benchmarks. A BD-RIS is beneficial compared to a conventional RIS in the absence of static path or when the Rician $\kappa$-factor is smaller than $10$., Comment: 5 pages, 3 figures, submitted as a possible publication

We update the ephemerides of 16 transiting exoplanets using our ground-based observations, new TESS data, and previously published observations including those of amateur astronomers. All these light curves were modeled by making use of a set of quantitative criteria with the EXOFAST code to obtain mid-transit times. We searched for statistically significant secular and/or periodic trends in the mid-transit times. We found that the timing data are well modeled by a linear ephemeris for all systems except for XO-2 b, for which we detect an orbital decay with the rate of -12.95 $\pm$ 1.85 ms/yr that can be confirmed with future observations. We also detect a hint of potential periodic variations in the TTV data of HAT-P-13 b which also requires confirmation with further precise observations., Comment: 23 pages, 17 figures

National football teams increasingly issue tradeable blockchain-based fan tokens to strategically enhance fan engagement. This study investigates the impact of 2022 World Cup matches on the dynamic performance of each team's fan token. The event study uncovers fan token returns surged six months before the World Cup, driven by positive anticipation effects. However, intraday analysis reveals a reversal of fan token returns consistently declining and trading volumes rising as matches unfold. To explain findings, we uncover asymmetries whereby defeats in high-stake matches caused a plunge in fan token returns, compared to low-stake matches, intensifying in magnitude for knockout matches. Contrarily, victories enhance trading volumes, reflecting increased market activity without a corresponding positive effect on returns. We align findings with the classic market adage "buy the rumor, sell the news," unveiling cognitive biases and nuances in investor sentiment, cautioning the dichotomy of pre-event optimism and subsequent performance declines., Comment: 31 pages, 5 tables, 1 figure

The application of data augmentation for deep learning (DL) methods plays an important role in achieving state-of-the-art results in supervised, semi-supervised, and self-supervised image classification. In particular, channel transformations (e.g., solarize, grayscale, brightness adjustments) are integrated into data augmentation pipelines for remote sensing (RS) image classification tasks. However, contradicting beliefs exist about their proper applications to RS images. A common point of critique is that the application of channel augmentation techniques may lead to physically inconsistent spectral data (i.e., pixel signatures). To shed light on the open debate, we propose an approach to estimate whether a channel augmentation technique affects the physical information of RS images. To this end, the proposed approach estimates a score that measures the alignment of a pixel signature within a time series that can be naturally subject to deviations caused by factors such as acquisition conditions or phenological states of vegetation. We compare the scores associated with original and augmented pixel signatures to evaluate the physical consistency. Experimental results on a multi-label image classification task show that channel augmentations yielding a score that exceeds the expected deviation of original pixel signatures can not improve the performance of a baseline model trained without augmentation., Comment: Accepted at the IEEE International Geoscience and Remote Sensing Symposium

Deployments of artificial intelligence in medical diagnostics mandate not just accuracy and efficacy but also trust, emphasizing the need for explainability in machine decisions. The recent trend in automated medical image diagnostics leans towards the deployment of Transformer-based architectures, credited to their impressive capabilities. Since the self-attention feature of transformers contributes towards identifying crucial regions during the classification process, they enhance the trustability of the methods. However, the complex intricacies of these attention mechanisms may fall short of effectively pinpointing the regions of interest directly influencing AI decisions. Our research endeavors to innovate a unique attention block that underscores the correlation between 'regions' rather than 'pixels'. To address this challenge, we introduce an innovative system grounded in prototype learning, featuring an advanced self-attention mechanism that goes beyond conventional ad-hoc visual explanation techniques by offering comprehensible visual insights. A combined quantitative and qualitative methodological approach was used to demonstrate the effectiveness of the proposed method on the large-scale NIH chest X-ray dataset. Experimental results showed that our proposed method offers a promising direction for explainability, which can lead to the development of more trustable systems, which can facilitate easier and rapid adoption of such technology into routine clinics. The code is available at www.github.com/NUBagcilab/r2r_proto.

Symmergent gravity is an emergent gravity model with an $R+R^2$ curvature sector and an extended particle sector having new particles beyond the known ones. With constant scalar curvature, asymptotically flat black hole solutions are known to have no sensitivity to the quadratic curvature term (coefficient of $R^2$). With variable scalar curvature, however, asymptotically-flat symmergent black hole solutions turn out to explicitly depend on the quadratic curvature term. In the present work, we construct asymptotically-flat symmergent black holes with variable scalar curvature and use its evaporation, shadow, and deflection angle to constrain the symmergent gravity parameters. Concerning their evaporation, we find that the new particles predicted by symmergent gravity, even if they do not interact with the known particles, can enhance the black hole evaporation rate. Concerning their shadow, we show that statistically significant symmergent effects are reached at the $2\,\sigma$ level for the observational data of the Event Horizon Telescope (EHT) on the Sagittarius A* supermassive black hole. Concerning their weak deflection angle, we reveal discernible features for the boson-fermion number differences, particularly at large impact parameters. These findings hold the potential to serve as theoretical predictions for future observations and investigations on black hole properties., Comment: 20 pages, 10 figures. Accepted for publication in Fortschritte der Physik. Dedicated to Durmu\c{s} Demir (1967-2024), our supervisor, candid friend, and guiding light. His unwavering supports always led our way