Explore the vast range of titles available.

Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms. In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016. Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists' specificity with radiologists' sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists' recall assessment was developed and evaluated. Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists' sensitivity, lower than community-practice radiologists' specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity. While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation.

See the retraction notice BIO Web of Conferences 116 , 00001 (2024), https://doi.org/10.1051/bioconf/202411600001

In this paper, the design of the upper limps exoskeleton on a textile basis is considered as a means of increasing the efficiency of manual labor at industrial facilities and enterprises of the fuel and energy complex. The material presents an analysis of existing exoskeleton solutions, features of the implementation of assistance in the considered exoskeleton, presents a mathematical apparatus that describes the movements of the exoskeleton and the results of numerical simulation. Conclusions are drawn about the applicability of the proposed solutions to facilitate the manual labor of workers in industrial enterprises.

The article presents the importance of creating transport corridors in the New Silk Road project and modernizing sections of existing highways. The use of methods of structurization, analysis, synthesis, systematization, and agent-based modeling allowed us to develop a simulation model of local transport hubs of the highway section in the Republic of Buryatia (Russia) to the border with Mongolia. The concept of such hubs is to justify the design of infrastructure facilities that provide short-term parking of vehicles for their rapid maintenance and recreation of drivers or passengers. All entities involved in traffic flows are identified and their characteristics are defined. Based on the rules of their conduct individually and collectively are established. The resulting rules are used to create models of the behavior of entities in the simulation model and presented its corresponding 3d fragments.

In this work we investigate different avenues of improving the Neural Algorithm of Artistic Style (by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge, arXiv:1508.06576). While showing great results when transferring homogeneous and repetitive patterns, the original style representation often fails to capture more complex properties, like having separate styles of foreground and background. This leads to visual artifacts and undesirable textures appearing in unexpected regions when performing style transfer. We tackle this issue with a variety of approaches, mostly by modifying the style representation in order for it to capture more information and impose a tighter constraint on the style transfer result. In our experiments, we subjectively evaluate our best method as producing from barely noticeable to significant improvements in the quality of style transfer.

We explore the method of style transfer presented in the article \"A Neural Algorithm of Artistic Style\" by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge (arXiv:1508.06576). We first demonstrate the power of the suggested style space on a few examples. We then vary different hyper-parameters and program properties that were not discussed in the original paper, among which are the recognition network used, starting point of the gradient descent and different ways to partition style and content layers. We also give a brief comparison of some of the existing algorithm implementations and deep learning frameworks used. To study the style space further we attempt to generate synthetic images by maximizing a single entry in one of the Gram matrices \\(\\mathcal{G}_l\\) and some interesting results are observed. Next, we try to mimic the sparsity and intensity distribution of Gram matrices obtained from a real painting and generate more complex textures. Finally, we propose two new style representations built on top of network's features and discuss how one could be used to achieve local and potentially content-aware style transfer.

In this work, physical dealloying was explored as a simple and green method to microstructure the surface of commercial brass for pool boiling heat transfer coefficient enhancement. Three samples were dealloyed for 0.5, 1 and 3 hours at 650 C, turning the smooth surface into a porous one with a depth of 175, 200 and 223 um. The boiling experiments carried out in ethanol at 78 C have shown, that the maximum enhancement of heat transfer coefficient between 110 and 150% was achieved for the sample dealloyed for 0.5 h. Longer intervals of dealloying reduce boiling performance, but it is still much higher compared to smooth brass. This simple method can be customized for various thermal management equipment, such as conventional, plate and micro heat exchangers, all types of heat pipes, HVAC equipment etc., where the heat transfer occurs with phase change.

Impregnation of Phase Change Materials (PCMs) into a porous medium is a promising way to stabilize their shape and improve thermal conductivity which are essential for thermal energy storage and thermal management of small-size applications, such as electronic devices or batteries. However, in these composites a general understanding of how leakage is related to the characteristics of the porous material is still lacking. As a result, the energy density and the antileakage capability are often antagonistically coupled. In this work we overcome the current limitations, showing that a high energy density can be reached together with superior anti-leakage performance by using hierarchical macro-nanoporous metals for PCMs impregnation. By analyzing capillary phenomena and synthesizing a new type of material, it was demonstrated that a hierarchical trimodal macro-nanoporous metal (copper) provides superior antileakage capability (due to strong capillary forces of nanopores), high energy density (90vol% of PCM load due to macropores) and improves the charging/discharging kinetics, due to a three-fold enhancement of thermal conductivity. It was further demonstrated by CFD simulations that such a composite can be used for thermal management of a battery pack and unlike pure PCM it is capable of maintaining the maximum temperature below the safety limit. The present results pave the way for the application of hierarchical macro-nanoporous metals for high-energy density, leakage-free, and shape-stabilized PCMs with enhanced thermal conductivity. These innovative composites can significantly facilitate the thermal management of compact systems such as electronic devices or high-power batteries by improving their efficiency, durability and sustainability

A new composite heat transfer fluid consisting of tetralin and fullerene has been proposed for photovoltaic thermal hybrid solar harvesting. It features a unique absorption spectrum that is capable of sharply cutting off solar energy irradiated in the range of wavelength from 300 to 650 nm, making it a perfect candidate for simultaneous harvesting of both photovoltaic and thermal components of solar energy. The proposed composite revealed outstanding stability and facile synthesize root, which are the two main obstacles for applicability of nanofluids. It was shown experimentally that the additives of fullerene to tetralin do not alter significantly it's thermophysical properties apart from viscosity that increases moderately. Besides, tetralin/fullerene solutions show similar thermohydraulics performance to that of pure tetralin in laminar flow regime or insignificantly lower in transient and turbulent flow regimes. A new figure of merit was proposed to analyze the thermohydraulics performance that consider not only exergy losses due to the kinetic energy dissipation, but also exergy losses associated with a finite temperature difference in the heat exchanger. As a result, the proposed figure of merit indicates the decrease of the heat transfer performance of tetralin/fullerene solutions that directly proportional to fullerene concentration. The performed simulation suggests that the total energy efficiency of flat-plate photovoltaic/thermal solar collector goes up to 60.4 % estimated according regulation (EU) No. 811/2013. Finally, life cycle analysis revealed further improvement root in view of environmental impact.

It is widely agreed that phase change materials (PCMs) are of high interest for sustainable energy future. Many of the applications require anti-leakage properties of PCM, that can be accomplished through PCM encapsulation. In this study, scalable and considerably simplified approach based on the microfluidics principles was successfully designed for polyvinylidene fluoride (PVDF) hollow- and for leakage-free paraffin-core/PVDF-sheath fibers production. The required device can be as simple as syringe+tube+glass capillary. The fibers were created by PVDF/N,NDimethylformamide (DMF) solution and PVDF/DMF/paraffin emulsion injection in water followed by solvent extraction process. The proposed approach results in a hollow PVDF or PVDF/paraffin composite fibers with the PCM content between 32-47.5% according to DSC and TGA measurements. SEM study of the fibers morphology has shown that PCM is in the form of slugs along the fibers. Such PCM distribution is maintained until the first melting cycle. Later, molten PCM spreads within the fiber under capillary forces that was captured by infrared camera. Elastic modules and stress vs. strain were measured to characterise mechanical properties of designed fibers. Finally, the composite fibers have shown outstanding retention capacity with only 3.5% of PCM mass loose after 1000 melting/crystallisation cycles.