Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Perera et al. developed a machine-learning approach for classifying whole-slide images into binary categories of tumour-infiltrating lymphocytes. They have benchmarked it against two established models and made the entire processing pipeline available as open source.
Sebastian Nilsson and colleagues capture the 3D structure of a gliding arc plasma and simultaneously apply a single shot fluorescence lifetime imaging from which the physical properties linked to the chemistry and molecular collision dynamics can be extracted.
Vovchuk et al. utilized generic algorithms to demonstrate a multi-wire superdirective antenna. The small device not only surpasses common directivity bounds but also demonstrates a superbandwidth, thus making it useful for wireless communications.
Mauricio Velazquez Lopez and colleagues fabricate a neuromorphic node with a response time that spans a range of 7 orders of magnitude. Their technology is compatible with complementary metal-oxide semiconductors, which makes it suitable for a variety of machine learning tasks.
Dr Roland Brunner and colleagues demonstrate how acoustic interferometry can be used to conduct a non-destructive and high-resolution failure analysis of through-silicon vias. They analyse the detection of nanometre-scale cracks and discuss how the opening angle of the acoustic lens impacts on performance.
Bahadır Utku Kesgin and Uğur Teğin propose using a Lorenz attractor as a nonlinear transfer function for neural network nodes. They design a power-efficient electrical circuit and use them for regression and classification test tasks.
Mohammad Askari and colleagues report a strategy for Unmanned Aerial Vehicles to perch on vertical poles and trees upon crash landing. An upturned nose passively reorients the robot, while dual-purpose wings secure the robot using an enveloping grasp, not unlike a hug.
The light patterns in backscattering signals of Optical Fiber Tweezers (OFT) has been demonstrated able to discriminate a wide range of microparticles. Barros and Cunha take this a step further by extracting the phase spectral information from OFT backscattering signals. This approach allows for the detection and identification of tumoral cell and extracellular nanovesicle features in complex biological media.
Kaicong Sun and colleagues design a generative uncertainty-aware AI framework to facilitate brain disease diagnosis using single-modal input. Validated on five datasets comprising thousands of subjects, this approach shows promising results close to using multi-modal input across three types of brain disease.
Chengcheng Zhao and co-authors study the potential of battery electric buses and hydrogen polymer electrolyte membrane fuel cell buses. They analyse their usage in urban transport and quantify the environmental impact.
Drs Papathanasiou & Pini, and colleagues present a model-based approach for efficient design of sorbent-based post-combustion carbon capture. They quantify operability-cost trade-offs and identify suitable candidate designs that satisfy CO2 purity and recovery constraints.
Carver and Zhou demonstrate the potential of state-of polarization sensing when applied to unmodified, terrestrial fiber-optic networks. This type of sensing is shown to detect events of both anthropic and seismic origin.
Liam Cronin and colleagues develop an end-to-end approach for crowdsourcing vibration data from cell phones in vehicles to extract bridge vibration characteristics known to be sensitive to structural damage.
Chul Kim and colleagues show a sensor display which is able to capture biometric data. In one device, they combine fingerprint identification and biomarker estimation while maintaining the same display quality.
Mengjia He and colleagues mitigate unwanted interference between inductive coils in multi-detector nuclear magnetic resonance spectroscopy. Their framework enables a compensation mechanism and enhances the parallelisation capacity.
Shuai Liu, Bin Chen and colleagues improve imaging speed and reduced phototoxicity in confocal microimaging by building a deep compressive confocal microscope. Digital micromirror acts as a coding mask for deep learning-based reconstruction algorithms.
Haosong He and co-authors study the impact of topology on the battery thermal management. They find the straight topology leads to more even distribution of temperature gradients among sub-modules, mitigating the over(dis)charging issue.
Zhenming Liu and colleagues show a SiC microelectromechanical system with both high quality factor and high frequency. They demonstrate the advantage of the device over the traditional Si gyroscopes and batch-fabrication possibility.
Lu et al. demonstrated a bidirectional optical wireless communication system for 5G communications using wavelength-division multiplexing and cascaded reflective semiconductor optical amplifiers. The system achieves an aggregate rate of 36.4 Gb/s over a 100-m optical wireless link, enhancing 5G communication capabilities.
Ce Liu, Baobao Lin and colleagues report a rapid and straightforward nucleic acid screening test requiring no professional training or formal medical setting. The device runs on a novel gamepad-like interface and fully integrates nucleic acid release, amplification, and visualization.