The latest study in Engineering reveals a groundbreaking approach to greener ethylene manufacturing using a novel physically consistent machine learning (PCML)-based hybrid modeling framework for steam thermal cracking, a highly energy-intensive and carbon-emitting process. Conducted by a team from the University of Sheffield and Southeast University, this research has significant implications for global sustainable chemical production.

With the rapid advancements in fifth-generation (5G) and sixth-generation (6G) technologies, along with aerospace innovations, satellite–terrestrial integrated networks (STINs) have garnered widespread attention.  A new comprehensive review in Engineering presents recent research on and developments in STIN technologies in 6G, such as topology maintenance, network routing, and orchestration transmission. Furthermore, it presents the latest developments in satellite networks, including platforms and simulators.

A research paper by scientists at Tianjin University introduces background electroencephalogram (EEG) mixing (BGMix), a novel data augmentation technique grounded in neural principles that enhances training samples by replacing background noise between different classes.

The new research paper, published on Oct. 07, 2025 in the journal Cyborg and Bionic Systems, introduced a novel EEG augmentation method and a new approach to designing deep learning models informed by the neural processes of EEG.

Discover how organoids are revolutionizing neurotrauma treatment. A new review in Engineering explores the construction and potential applications of spinal cord and peripheral nerve organoids for regenerative medicine. Learn about the latest advancements and challenges in this promising field.

A research paper by scientists at the Beijing Institute of Technology proposed a SnS₂-based in-sensor reservoir that offers an effective solution for detecting a variety of motion types at sensory terminals. By leveraging in-sensor reservoir computing, the device excels at classifying different motions across a wide velocity spectrum, providing a novel and promising method for motion recognition.

The new research paper, published on Sep. 30 in the journal Cyborg and Bionic Systems, presented an optoelectronic in-sensor RC device based on monolayer SnS₂ synthesized via the chemical vapor deposition (CVD) technique. This device demonstrates a notable correlation between its optic response and the duration of illumination, exhibiting excellent optical detection performance under short light illumination. Under long illumination, the sustained optic response can be used to simulate synaptic plasticity.