Membrane technologies are becoming increasingly versatile and helpful today for sustainable development. Machine Learning (ML), an essential branch of artificial intelligence (AI), has substantially ...impacted the research and development norm of new materials for energy and environment. This review provides an overview and perspectives on ML methodologies and their applications in membrane design and discovery. A brief overview of membrane technologies is first provided with the current bottlenecks and potential solutions. Through an applications-based perspective of AI-aided membrane design and discovery, we further show how ML strategies are applied to the membrane discovery cycle (including membrane material design, membrane application, membrane process design, and knowledge extraction), in various membrane systems, ranging from gas, liquid, and fuel cell separation membranes. Furthermore, the best practices of integrating ML methods and specific application targets in membrane design and discovery are presented with an ideal paradigm proposed. The challenges to be addressed and prospects of AI applications in membrane discovery are also highlighted in the end.
Membrane technologies are versatile and helpful for sustainable development. Machine Learning (ML) has substantially impacted the research and development norm of new materials for energy and environment. This review provides an overview and perspectives on ML in membrane design and discovery. Display omitted
•A brief introduction to membrane technology for data scientists is made.•A practical machine learning tutorial for scientists in membrane area is provided.•Recent advances in the interdisciplinary area, AI for membrane, are reviewed and summarized.•A novel research paradigm for AI-accelerated membrane design and discovery is proposed and discussed.
Testing (i.e., retrieval practice) is one of the most powerful strategies to boost learning. A recent study observed an incidental finding that making judgments of learning (JOLs) following retrieval ...practice further enhanced learning of education-related texts to a medium extent (Cohen’s d = 0.44) by comparison with retrieval practice itself, suggesting that making JOLs may serve as an easy-to-implement educational intervention to improve the benefits of testing. Three experiments (one pre-registered) were conducted to test the replicability of Ariel et al.’s incidental finding and to further determine whether making JOLs following retrieval practice reactively enhances the benefits of testing for text learning. The three experiments consistently provided Bayesian evidence supporting no reactivity effect of JOLs following retrieval practice, regardless of whether the replication experiments were conducted in a laboratory (Experiment 1) or online (Experiments 2 and 3), whether the stimuli were presented in the same language (Experiments 2 and 3) or not (Experiment 1), and whether participants were recruited from the sample pool (Experiment 2) or not (Experiments 1 and 3) as in the original study. These null findings imply that making JOLs cannot be utilized as a practical strategy to enhance the benefits of testing for learning of educationally related materials. Possible explanations for the null reactivity effect of JOLs following retrieval practice are discussed.
Abstract This work introduces a silent speech interface (SSI), proposing a few-layer graphene (FLG) strain sensing mechanism based on thorough cracks and AI-based self-adaptation capabilities that ...overcome the limitations of state-of-the-art technologies by simultaneously achieving high accuracy, high computational efficiency, and fast decoding speed while maintaining excellent user comfort. We demonstrate its application in a biocompatible textile-integrated ultrasensitive strain sensor embedded into a smart choker, which conforms to the user’s throat. Thanks to the structure of ordered through cracks in the graphene-coated textile, the proposed strain gauge achieves a gauge factor of 317 with <5% strain, corresponding to a 420% improvement over existing textile strain sensors fabricated by printing and coating technologies reported to date. Its high sensitivity allows it to capture subtle throat movements, simplifying signal processing and enabling the use of a computationally efficient neural network. The resulting neural network, based on a one-dimensional convolutional model, reduces computational load by 90% while maintaining a remarkable 95.25% accuracy in speech decoding. The synergy in sensor design and neural network optimization offers a promising solution for practical, wearable SSI systems, paving the way for seamless, natural silent communication in diverse settings.
Anion exchange membrane (AEM) fuel cells are promising for efficient and environmentally benign electrochemical energy conversion. However, the development of high-performance fuel cells requires new ...AEMs tailored for high conductivity and alkaline stability. In this work, poly(arylene ether sulfone)s with different branching degrees were synthesized as AEM materials. The effect of the branching degree on the properties of the copolymers was investigated in detail. The bulky rigid three-pronged branched structure introduced into the copolymer backbone increased the free volume in the corresponding AEM. As a result, the branched AEM demonstrated markedly improved ionic conductivity (up to 126 mS cm −1 ) compared with that of the linear copolymer AEM (96 mS cm −1 ) at 80 °C. The highly branched comb-shaped copolymer AEM also exhibited robust alkaline stability and dimensional stability. Furthermore, a platinum-catalyzed fuel cell based on a highly branched comb-shaped copolymer AEM achieved a peak power density of 160 mW cm −2 , which was higher than that of the linear copolymer AEM (111 mW cm −2 ). These results suggest that introduction of a branched structure is an effective strategy to fabricate AEMs with high performance suitable for alkaline fuel cell applications.
Although phosphoric acid-doped polybenzimidazoles (PA-doped PBIs) are widely accepted in high-temperature proton exchange membrane fuel cells, further improvement is desirable to obtain optimal fuel ...cell performance. Block copolymers applied as low-temperature proton exchange membranes have been recently shown to exhibit high proton conductivity and fuel cell properties. However, few block copolymers have been reported as high-temperature proton exchange membranes. In this work, a series of segmented block PA-doped PBIs are synthesized with various molar ratios and similar molecular weights. The block copolymer membranes show obvious nanophase-separated structures due to the combination of rigid and flexible segments in the copolymer. A high proton conductivity of the block membrane is obtained at lower phosphoric acid doping levels (0.1 S cm−1 at 180 °C). The fuel cell performance of the block membranes exhibits a maximum power density of 360 mW/cm2 at 160 °C, which is higher than that of pristine poly2,2′-(p-oxydiphenylene)-5,5′-benzimidazole (OPBI) membranes (268 mw/cm2). The results suggest that block PBI doped with phosphoric acid can potentially be applied as a high-temperature proton exchange membrane.
•A series of block copolymers with various molar ratios were prepared.•The combination of rigid and flexible segments resulted in nanophase separation.•The block membranes exhibited a high proton conductivity at a low ADL.•The power density of the block membrane reached 360 mW/cm2.
A set of highly branched imidazolium-functionalized poly(arylene ether sulfone)s copolymer bearing with flexible alkyl side chains of different lengths are designed and synthesized. The ion exchange ...capacity (IEC), ionic conductivity, water uptake, thermal stability, mechanical property and alkaline resistance of the anion exchange membranes (AEMs) were evaluated in detail. Atomic force microscopy and small-angle X-ray scattering are used to study morphology which reveals that the branched membrane with an alkyl side chain (6 carbons) achieves the highest conductivity (up to 115.8 mS cm−1 at 80 °C) due to the well-developed hydrophilic/hydrophobic phase separation. In addition, the branched co-polymer AEM with a longer alkyl side chain (12 carbons) exhibit the best robust alkaline stability, it decreases only 27% of ionic conductivity after 550 h in 1 M KOH. Therefore, this study provides a comprehensive insight into the tuneable membrane properties of highly branched copolymers as a change in the length of flexible alkyl side chains.
The effect of the length of the alkyl imidazolium side chain on the properties of a branched AEM was systematically investigated. Display omitted
•Four novel branched AEMs with alkyl imidazolium side chains were designed and fabricated.•The effect of the length of the alkyl side chain on the properties of AEM was systematically investigated.•The BPES-6-Im membrane achieved the highest ionic conductivity of 116 mS cm−1 at 80 °C.•The BPES-12-Im membrane demonstrated the best alkaline stability in 1 M KOH at 60 °C for 550 h.
Fueled by the recent proliferation of energy-efficient and energy-autonomous or self-powered nanotechnology-based wearable smart systems, human motion intention prediction (MIP) plays a critical role ...in a wide range of applications, such as rehabilitation and assistive robotics, to enable more natural, biologically inspired, and seamless integrated motion assistance task execution, including for elders and physically impaired patients. With the increasing complexity of human-machine interactions and the need for personalized assistance, there is a growing demand for real-time and accurate MIP systems. This review aims to provide a comprehensive understanding of the interdisciplinary field of MIP, under the logic of its physiological foundations, by discussing state-of-the-art sensing technologies, including brain-computer interfaces (BCI), electromyography (EMG), and motion sensors, alongside the relevant data processing techniques and decoding algorithms. We emphasize the importance of fostering collaboration among scholars from different domains to capture the intricate dependencies between the set of stimuli and responses of the central nervous system and the activation of the complex set of muscles and joints that produce human motion. By offering insights into the recent advancements and future prospects of the field, this review seeks to stimulate further research and innovation in the rapidly evolving area of human motion intention prediction, for a future where technologies understand and respond to complex human intentions patterns, anticipating their needs.
Display omitted
•Wearable sensors and AI data processing for Motion Intention Prediction (MIP).•Multimodal sensing from Brain to human motion task actuation via the CNS and PNS.•Materials and devices for brain-computer interface, electromyography, and IMUs.•Latest breakthroughs in transfer learning and explainable AI for MIP data decoding.•Exploring challenges and applications of biocompatible, efficient, and ethical MIP.
Summary
Sulfonated polyimides (SPIs) are extremely suitable as polymer electrolyte membranes (PEMs) for fuel cell applications, except for their poor water stability. Cross‐linking is a method that ...is commonly used to improve the weak hydrolytic stability of SPI membranes. However, this strategy significantly decreases the proton conductivity of the membrane, which leads to a lower fuel cell power density. In this work, a cross‐linked SPI membrane containing a highly branched polymer main chain was fabricated as a PEM. With a similar ion‐exchange capacity value, the cross‐linked membrane containing branched main chains showed an improved proton conductivity. Also, this membrane remained 92.3% of pristine weight after a hydrolytic stability test about 120 hours. In a single direct methanol fuel cell, the cross‐linked membrane containing a branched structure showed a higher power density (53.4 mW cm−2) than the common cross‐linked membrane (43.0 mW cm−2), indicating that branching is effective for improving the electrochemical properties of PEM‐based cross‐linked SPIs.
A cross‐linked SPI membrane (SPI‐BC) based on branched polymer main chain was fabricated as proton exchange membrane.
By combing the merits of branching and cross‐linking, the SPI‐BC membrane exhibited great chemical stability.
With a similar ion‐exchange capacity value, the SPI‐BC membrane showed an improved proton conductivity because of more free volume in polymer to accommodate water.
The development of information dissemination is associated with significantly increased risk of health anxiety (HA) , imposing a heavy burden on individuals and society. Although there are ...inconsistencies between the evolution and revisions in clinical diagnosis of HA, cognitive-behavioral interventions have been recognized as effective treatments for HA. We reviewed the clinical diagnoses, measurement tools, associated factors and online cognitive-behavioral interventions of HA, then proposed that the concepts and measurement tools of HA need to be further standardized. Main difficulties are the determination of the threshold for intervention and the development of psychological interventions suitable for general practices. Online and face-to-face cognitive-behavioral interventions for HA have similar effects, but the former is more inexpensive and convenient, which deserve to be studied further.
Anion exchange membrane (AEM) fuel cells are promising for efficient and environmentally benign electrochemical energy conversion. However, the development of high-performance fuel cells requires new ...AEMs tailored for high conductivity and alkaline stability. In this work, poly(arylene ether sulfone)s with different branching degrees were synthesized as AEM materials. The effect of the branching degree on the properties of the copolymers was investigated in detail. The bulky rigid three-pronged branched structure introduced into the copolymer backbone increased the free volume in the corresponding AEM. As a result, the branched AEM demonstrated markedly improved ionic conductivity (up to 126 mS cm
−1
) compared with that of the linear copolymer AEM (96 mS cm
−1
) at 80 °C. The highly branched comb-shaped copolymer AEM also exhibited robust alkaline stability and dimensional stability. Furthermore, a platinum-catalyzed fuel cell based on a highly branched comb-shaped copolymer AEM achieved a peak power density of 160 mW cm
−2
, which was higher than that of the linear copolymer AEM (111 mW cm
−2
). These results suggest that introduction of a branched structure is an effective strategy to fabricate AEMs with high performance suitable for alkaline fuel cell applications.
A novel strategy can enhance conductivity and stability of AEMs
via
the introduction of a branched structure in polymers.
