Microstructural evolutions and impact toughness in simulated welding heat affected zones for a high-strength carbide-free bainitic rail steel

Systematic experimental investigations were conducted to study the microstructures and impact toughness of each heat affected zone (HAZ) formed during rail flash-butt welding. A high-strength carbide-free bainitic rail steel was subjected to different thermal simulation cycles to separately reproduce each HAZ subzone by tailoring the peak...

Joint Feature Synthesis and Embedding: Adversarial Cross-Modal Retrieval Revisited

Recently, generative adversarial network (GAN) has shown its strong ability on modeling data distribution via adversarial learning. Cross-modal GAN, which attempts to utilize the power of GAN to model the cross-modal joint distribution and to learn compatible cross-modal features, is becoming the research hotspot. However, the existing cross...

A Wireless Near-Infrared Spectroscopy Device for Flap Monitoring: Proof of Concept in a Porcine Musculocutaneous Flap Model

Background Current near-infrared spectroscopy (NIRS)-based systems for continuous flap monitoring are highly sensitive for detecting malperfusion. However, the clinical utility and user experience are limited by the wired connection between the sensor and bedside console. This wire leads to instability of the flap-sensor interface and may...

Wireless, implantable catheter-type oximeter designed for cardiac oxygen saturation

Accurate, real-time monitoring of intravascular oxygen levels is important in tracking the cardiopulmonary health of patients after cardiothoracic surgery. Existing technologies use intravascular placement of glass fiber-optic catheters that pose risks of blood vessel damage, thrombosis, and infection. In addition, physical tethers to power...

Changjiang Delta in the Anthropocene: Multi-scale hydro-morphodynamics and management challenges

The Changjiang Delta (CD) is one of well-studied large deltas of critical socio-economical and ecological importance regionally and global representativeness. Cumulated field data and numerical modeling has facilitated scientific understanding of its hydro-morphodynamics at multiple spatial and time scales, but the changing boundary forcing...

A generic high-throughput microstructure classification and quantification method for regular SEM images of complex steel microstructures combining EBSD labeling and deep learning

We present an electron backscattered diffraction (EBSD)-trained deep learning (DL) method integrating traditional material characterization informatics and artificial intelligence for a more accurate classification and quantification of complex microstructures using only regular scanning electron microscope (SEM) images. In this method, EBSD...

Unified Binary Generative Adversarial Network for Image Retrieval and Compression

Binary codes have often been deployed to facilitate large-scale retrieval tasks, but not that often for image compression. In this paper, we propose a unified framework, BGAN+, that restricts the input noise variable of generative adversarial networks to be binary and conditioned on the features of each input image, and simultaneously learns...

Matching images and text with multi-modal tensor fusion and re-ranking

A major challenge in matching images and text is that they have intrinsically different data distributions and feature representations. Most existing approaches are based either on embedding or classification, the first one mapping image and text instances into a common embedding space for distance measuring, and the second one regarding...

Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel

With the development of the materials genome philosophy and data mining methodologies, machine learning (ML) has been widely applied for discovering new materials in various systems including high-end steels with improved performance. Although recently, some attempts have been made to incorporate physical features in the ML process, its...

Parity transitions in the superconducting ground state of hybrid InSb-Al Coulomb islands

The number of electrons in small metallic or semiconducting islands is quantised. When tunnelling is enabled via opaque barriers this number can change by an integer. In superconductors the addition is in units of two electron charges (2e), reflecting that the Cooper pair condensate must have an even parity. This ground state (GS) is...

Localised corrosion in aluminium alloy 2024-T3 using in situ TEM

An approach to carry out chemical reactions using aggressive gases in situ in a transmission electron microscope (TEM), at ambient pressures of 1.5 bar using a windowed environmental cell, called a nanoreactor, is presented here. The nanoreactor coupled with a specially developed holder with platinum tubing permits the usage of aggressive...