Search

Traditional segmentation networks approach anatomical structures as standalone elements, overlooking the intrinsic hierarchical connections among them. This study introduces Softmax for Arbitrary Label Trees (SALT), a novel approach designed to leverage the hierarchical relationships between labels, improving the efficiency and interpretability of the segmentations. This study introduces a novel segmentation technique for CT imaging, which leverages conditional probabilities to map the hierarchical structure of anatomical landmarks, such as the spine's division into lumbar, thoracic, and cervical regions and further into individual vertebrae. The model was developed using the SAROS dataset from The Cancer Imaging Archive (TCIA), comprising 900 body region segmentations from 883 patients. The dataset was further enhanced by generating additional segmentations with the TotalSegmentator, for a total of 113 labels. The model was trained on 600 scans, while validation and testing were conducted on 150 CT scans. Performance was assessed using the Dice score across various datasets, including SAROS, CT-ORG, FLARE22, LCTSC, LUNA16, and WORD. Among the evaluated datasets, SALT achieved its best results on the LUNA16 and SAROS datasets, with Dice scores of 0.93 and 0.929 respectively. The model demonstrated reliable accuracy across other datasets, scoring 0.891 on CT-ORG and 0.849 on FLARE22. The LCTSC dataset showed a score of 0.908 and the WORD dataset also showed good performance with a score of 0.844. SALT used the hierarchical structures inherent in the human body to achieve whole-body segmentations with an average of 35 seconds for 100 slices. This rapid processing underscores its potential for integration into clinical workflows, facilitating the automatic and efficient computation of full-body segmentations with each CT scan, thus enhancing diagnostic processes and patient care.

Mosaic crystals, with their high integrated reflectivities, are widely-employed in spectrometers used to diagnose high energy density systems. X-ray Thomson scattering (XRTS) has emerged as a powerful diagnostic tool of these systems, providing in principle direct access to important properties such as the temperature via detailed balance. However, the measured XRTS spectrum is broadened by the spectrometer instrument function (IF), and without careful consideration of the IF one risks misdiagnosing system conditions. Here, we consider in detail the IF of 40 $\mu$m and 100 $\mu$m mosaic HAPG crystals, and how the broadening varies across the spectrometer in an energy range of 6.7-8.6 keV. Notably, we find a strong asymmetry in the shape of the IF towards higher energies. As an example, we consider the effect of the asymmetry in the IF on the temperature inferred via XRTS for simulated 80 eV CH plasmas, and find that the temperature can be overestimated if an approximate symmetric IF is used. We therefore expect a detailed consideration of the full IF will have an important impact on system properties inferred via XRTS in both forward modelling and model-free approaches., Comment: 19 pages, 13 figures

Automated medical image analysis systems often require large amounts of training data with high quality labels, which are difficult and time consuming to generate. This paper introduces Radiology Object in COntext version 2 (ROCOv2), a multimodal dataset consisting of radiological images and associated medical concepts and captions extracted from the PMC Open Access subset. It is an updated version of the ROCO dataset published in 2018, and adds 35,705 new images added to PMC since 2018. It further provides manually curated concepts for imaging modalities with additional anatomical and directional concepts for X-rays. The dataset consists of 79,789 images and has been used, with minor modifications, in the concept detection and caption prediction tasks of ImageCLEFmedical Caption 2023. The dataset is suitable for training image annotation models based on image-caption pairs, or for multi-label image classification using Unified Medical Language System (UMLS) concepts provided with each image. In addition, it can serve for pre-training of medical domain models, and evaluation of deep learning models for multi-task learning., Comment: Accepted for Scientific Data

Power systems operate under uncertainty originating from multiple factors that are impossible to account for deterministically. Distributional forecasting is used to control and mitigate risks associated with this uncertainty. Recent progress in deep learning has helped to significantly improve the accuracy of point forecasts, while accurate distributional forecasting still presents a significant challenge. In this paper, we propose a novel general approach for distributional forecasting capable of predicting arbitrary quantiles. We show that our general approach can be seamlessly applied to two distinct neural architectures leading to the state-of-the-art distributional forecasting results in the context of short-term electricity demand forecasting task. We empirically validate our method on 35 hourly electricity demand time-series for European countries. Our code is available here: https://github.com/boreshkinai/any-quantile.

Femtosecond high-intensity laser pulses at intensities surpassing $10^{14} \,\text{W}/\text{cm}^2$ can generate a diverse range of functional surface nanostructures. Achieving precise control over the production of these functional structures necessitates a thorough understanding of the surface morphology dynamics with nanometer-scale spatial resolution and picosecond-scale temporal resolution. In this study, we show that individual XFEL pulses can elucidate structural changes on surfaces induced by laser-generated plasmas, employing grazing-incidence small-angle x-ray scattering (GISAXS). Using aluminum-coated multilayer samples we can differentiate between ultrafast surface morphology dynamics and subsequent subsurface density dynamics, achieving nanometer-depth sensitivity and subpicosecond temporal resolution. The observed subsurface density dynamics serve to validate advanced simulation models depicting matter under extreme conditions. Our findings promise to unveil novel avenues for laser material nanoprocessing and high-energy-density science., Comment: 11 pages, 5 figures. This is the version of the article before peer review

Optimizing grain boundary characteristics in polycrystalline materials can improve their properties. Many processing methods have been developed for grain boundary manipulation, including the use of intense radiation in certain applications. In this work, we used X-ray free electron laser pulses to irradiate single-crystalline bismuth selenide (Bi2Se3) and observed grain boundary formation and subsequent grain rotation in response to the X-ray radiation. Our observations with simultaneous transmission X-ray microscopy and X-ray diffraction demonstrate how intense X- ray radiation can rapidly change size and texture of grains., Comment: 37 pages, 11 figures including 6 supplemental figures

Entanglement, one of the clearest manifestations of non-classical physics, holds significant promise for technological applications such as more secure communications and faster computations. In this paper we explore the use of non-reciprocal transport in a network of continuous-variable systems to route entanglement in one direction through the network. We develop the theory and discuss a potential realization of controllable flow of entanglement in quantum systems; our method employs only Gaussian interactions and engineered dissipation to break the symmetry. We also explore the conditions under which thermal fluctuations limit the distance over which the entanglement propagates and observe a counter-intuitive behavior between this distance, the strength of the entanglement source, and the strength of the hopping through the network., Comment: 8 pages, 4 figures

Equation of state measurements at Jovian or stellar conditions are currently conducted by dynamic shock compression driven by multi-kilojoule multi-beam nanosecond-duration lasers. These experiments require precise design of the target and specific tailoring of the spatial and temporal laser profiles to reach the highest pressures. At the same time, the studies are limited by the low repetition rate of the lasers. Here, we show that by the irradiation of a thin wire with single beam Joule-class short-pulse laser, a converging cylindrical shock is generated compressing the wire material to conditions relevant for the above applications. The shockwave was observed using Phase Contrast Imaging employing a hard X-ray Free Electron Laser with unprecedented temporal and spatial sensitivity. The data collected for Cu wires is in agreement with hydrodynamic simulations of an ablative shock launched by a highly-impulsive and transient resistive heating of the wire surface. The subsequent cylindrical shockwave travels towards the wire axis and is predicted to reach a compression factor of 9 and pressures above 800 Mbar. Simulations for astrophysical relevant materials underline the potential of this compression technique as a new tool for high energy density studies at high repetition rates.

In 2022, energy prices skyrocketed across Europe, with average day-ahead spot market prices in Germany 2.43 times higher than the previous year, hinting at future trends. At the same time, electricity infrastructure is expected to be overutilized in some regions in the future due to the uptake of electric vehicles, heat pumps, PV systems, and other appliances in the residential sector. Dynamic electricity pricing for households is proposed as a solution to alleviate infrastructure strain and reduce costs. The question arises as to what impact dynamic electricity prices as recently seen on the day-ahead spot market in Germany would have on the use of flexibility in households and whether it can compensate for cost increases for households. We analyze the cost-effectiveness of utilizing flexibility through a home energy management system (HEMS) and smart meters against increased self-consumption using a HEMS and static tariffs. We show that with higher electricity prices and price spreads, a higher share of households can offset initial investments in HEMS and metering operation costs by utilizing flexibility from their electric vehicles, heat pumps, and battery storage systems. While increasing self-consumption remains beneficial for households with heat pumps and PV systems, dynamic electricity tariffs are financially more advantageous for those with electric vehicles. The study also determines the maximum additional annual costs for HEMS and metering point operation that still allow cost savings for 75% of households. these costs range from 126 to 145 Euro in the self-consumption scenario depending and from 50 to 111 Euro in the dynamic electricity tariff scenario, highlighting the financial viability of flexibility utilization in response to current pricing trends., Comment: 38 pages, 11 figures, submitted to Advances in Applied Energy

We introduce a general technique to construct Lagrangian torus fibrations in degenerations of K\"ahler manifolds. We show that such torus fibrations naturally occur at the boundary of the A'Campo space. This space extends a degeneration over a punctured disc to a hybrid space involving its real oriented blowup and the dual complex of the special fiber; equipped with an exact modification of a given K\"ahler form which becomes fiberwise symplectic at the boundary. Therefore, it allows to move Lagrangian tori from the "radius zero" fibers at the boundary to the nearby fibers of the original generation using the symplectic connection. As a consequence, for any maximal Calabi-Yau degeneration we prove that a generic region of each nearby fiber admits a Lagrangian torus fibration with asymptotic properties expected from the (conjectural) Strominger--Yau--Zaslow fibration., Comment: 35 pages, 4 figures; slightly improved exposition

Ultra-intense lasers that ionize and accelerate electrons in solids to near the speed of light can lead to kinetic instabilities that alter the laser absorption and subsequent electron transport, isochoric heating, and ion acceleration. These instabilities can be difficult to characterize, but a novel approach using X-ray scattering at keV energies allows for their visualization with femtosecond temporal resolution on the few nanometer mesoscale. Our experiments on laser-driven flat silicon membranes show the development of structure with a dominant scale of $~60\unit{nm}$ in the plane of the laser axis and laser polarization, and $~95\unit{nm}$ in the vertical direction with a growth rate faster than $0.1/\mathrm{fs}$. Combining the XFEL experiments with simulations provides a complete picture of the structural evolution of ultra-fast laser-induced instability development, indicating the excitation of surface plasmons and the growth of a new type of filamentation instability. These findings provide new insight into the ultra-fast instability processes in solids under extreme conditions at the nanometer level with important implications for inertial confinement fusion and laboratory astrophysics.

In this paper, we present an experiment that explores the plasma dynamics of a 7 micron diameter carbon wire after being irradiated with a near-relativistic-intensity short pulse laser. Using an X-ray Free Electron Laser pulse to measure the small angle X-ray scattering signal, we observe that the scattering surface is bent and prone to instability over tens of picoseconds. The dynamics of this process are consistent with the presence of a sharp, propagating shock front inside the wire, moving at a speed close to the hole boring velocity.

In this paper, we propose a new short-term load forecasting (STLF) model based on contextually enhanced hybrid and hierarchical architecture combining exponential smoothing (ES) and a recurrent neural network (RNN). The model is composed of two simultaneously trained tracks: the context track and the main track. The context track introduces additional information to the main track. It is extracted from representative series and dynamically modulated to adjust to the individual series forecasted by the main track. The RNN architecture consists of multiple recurrent layers stacked with hierarchical dilations and equipped with recently proposed attentive dilated recurrent cells. These cells enable the model to capture short-term, long-term and seasonal dependencies across time series as well as to weight dynamically the input information. The model produces both point forecasts and predictive intervals. The experimental part of the work performed on 35 forecasting problems shows that the proposed model outperforms in terms of accuracy its predecessor as well as standard statistical models and state-of-the-art machine learning models.

The embedded Nash problem for a hypersurface in a smooth algebraic variety, is to characterize geometrically the maximal irreducible families of arcs with fixed order of contact along the hypersurface. We show that divisors on minimal models of the pair contribute with such families. We solve the problem for unibranch plane curve germs, in terms of the resolution graph. These are embedded analogs of known results for the classical Nash problem on singular varieties., Comment: v2: The main change is in the proof of Thm 7.4. To appear in Forum Math. Pi

We show that every family of isolated hypersurface singularity with constant Milnor number has constant multiplicity. To achieve this, we endow the A'Campo model of "radius zero" monodromy with a symplectic structure. This new approach allows to generalize a spectral sequence of McLean converging to fixed point Floer homology of iterates of the monodromy to a more general setting which is well suited to study $\mu$-constant families., Comment: 87 pages, 7 figures, to appear in Annals of Mathematics

This paper compares recurrent neural networks (RNNs) with different types of gated cells for forecasting time series with multiple seasonality. The cells we compare include classical long short term memory (LSTM), gated recurrent unit (GRU), modified LSTM with dilation, and two new cells we proposed recently, which are equipped with dilation and attention mechanisms. To model the temporal dependencies of different scales, our RNN architecture has multiple dilated recurrent layers stacked with hierarchical dilations. The proposed RNN produces both point forecasts and predictive intervals (PIs) for them. An empirical study concerning short-term electrical load forecasting for 35 European countries confirmed that the new gated cells with dilation and attention performed best.

Short-term load forecasting (STLF) is a challenging problem due to the complex nature of the time series expressing multiple seasonality and varying variance. This paper proposes an extension of a hybrid forecasting model combining exponential smoothing and dilated recurrent neural network (ES-dRNN) with a mechanism for dynamic attention. We propose a new gated recurrent cell -- attentive dilated recurrent cell, which implements an attention mechanism for dynamic weighting of input vector components. The most relevant components are assigned greater weights, which are subsequently dynamically fine-tuned. This attention mechanism helps the model to select input information and, along with other mechanisms implemented in ES-dRNN, such as adaptive time series processing, cross-learning, and multiple dilation, leads to a significant improvement in accuracy when compared to well-established statistical and state-of-the-art machine learning forecasting models. This was confirmed in the extensive experimental study concerning STLF for 35 European countries., Comment: Code and data: https://github.com/slaweks17/ES-adRNN. arXiv admin note: text overlap with arXiv:2112.02663

A comprehensive study of thermodynamic properties of three samples of bimetallic molecular magnets [Co$^{\mathrm{II}}$(pyrazole)$_{4}$]$_{2x}$[Fe$^{\mathrm{II}}$(pyrazole)$_{4}$]$_{2(1-x)}$[Nb$^{\mathrm{IV}}$(CN)$_{8}$]$\cdot$4H$_{2}$O with $x$=0 (Co$_{2}$Nb), 0.5 (CoFeNb), and 1 (Fe$_{2}$Nb) is reported. The three samples display the same crystallographic structure crystallizing in the tetragonal system with space group $I4_1/a$. Their heat capacities are measured in the temperature range 0.36-100 K without applied field as well as in the field of $\mu_0 H$ = 0.1, 0.2, 0.5, 1, 2, 5, and 9 T. The results imply the presence of the second-order phase transitions to magnetically ordered phases at 4.87(8) K, 7.1(2) K, and 8.44(3) K for $x$=0, 0.5, and 1, respectively. The corresponding thermodynamic functions are analyzed to discuss the stability of the mixed compound and the magnetocaloric effect (MCE). The Gibbs energy of mixing is found to be positive but smaller in magnitude than the energy of thermal fluctuations indicating that the mixed sample is marginally stable in the full detected temperature range. The enthalpy of mixing is negative, which points to an ordered arrangement of the Co(II) and Fe(II) ions in the solid solution CoFeNb. The negative values of the entropy of mixing are explained by considering the enhanced rigidity of the crystal lattice of the solid solution sample. To extract the magnetic contribution to the heat capacity an approach based on a reasonable frequency spectrum is adopted. Taking advantage of the in-field heat capacity measurements MCE was described in terms of the isothermal entropy change $\Delta S_\mathrm{M}$ and the adiabatic temperature change $\Delta T_\mathrm{ad}$. The magnitudes of these quantities are typical for the class of molecular magnets., Comment: 34 pages, 19 figures

Short-term load forecasting (STLF) is challenging due to complex time series (TS) which express three seasonal patterns and a nonlinear trend. This paper proposes a novel hybrid hierarchical deep learning model that deals with multiple seasonality and produces both point forecasts and predictive intervals (PIs). It combines exponential smoothing (ES) and a recurrent neural network (RNN). ES extracts dynamically the main components of each individual TS and enables on-the-fly deseasonalization, which is particularly useful when operating on a relatively small data set. A multi-layer RNN is equipped with a new type of dilated recurrent cell designed to efficiently model both short and long-term dependencies in TS. To improve the internal TS representation and thus the model's performance, RNN learns simultaneously both the ES parameters and the main mapping function transforming inputs into forecasts. We compare our approach against several baseline methods, including classical statistical methods and machine learning (ML) approaches, on STLF problems for 35 European countries. The empirical study clearly shows that the proposed model has high expressive power to solve nonlinear stochastic forecasting problems with TS including multiple seasonality and significant random fluctuations. In fact, it outperforms both statistical and state-of-the-art ML models in terms of accuracy.