Query：
学者姓名：孙浩
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Microfluidic technology facilitates high-throughput generation of time series data for biological and medical studies. Deep learning enables accurate, predictive analysis and proactive decision-making based on autonomous recognition of intricate pattern hidden in series. In this work, we first devised a paper-based microfluidic system for portable nucleic acid amplification test with economic energy consumption. Then, we employed Graph Neural Network (GNN), distinguished by its non-Euclidean data structure tailored for deep learning, with spatiotemporal attention mechanism to perform near-sensor predictive analysis of the on-chip reaction. Our findings demonstrated that the novel GNN model can provide accurate predictions of positive outcomes at the early stages of the reaction using less than one-third of the total reaction time. Then, the deep learning model trained by onchip data was subsequently applied to more than 900 clinical plots. Generalization of the GNN model was successfully validated across different detection methods, diverse types of datasets and time series with variable length. Accuracy, sensitivity and specificity of the predictive approach were 96.5 %, 94.3 % and 99.0 % by utilizing the early half of reaction information. Finally, we compared the GNN model with various deep learning models. Despite differences in the prediction of negative samples among various models were minute, GNN obviously offered overall superior performance. This work ignites a cutting-edge application of deep learning in point-of-care and near-sensor tests. By harnessing the power of body area networks and edge/fog computing, our approach unlocks promising possibilities in diverse fields like healthcare and instrument science.
Keyword ：
GNN GNN Microfluidics Microfluidics Nucleic acid amplification test Nucleic acid amplification test Predictive analysis Predictive analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Sun, Hao , Pan, Yihan , Dong, Hui et al. Generalized predictive analysis of reactions in paper devices via graph neural networks [J]. | SENSORS AND ACTUATORS B-CHEMICAL , 2024 , 417 . |
| MLA | Sun, Hao et al. "Generalized predictive analysis of reactions in paper devices via graph neural networks" . | SENSORS AND ACTUATORS B-CHEMICAL 417 (2024) . |
| APA | Sun, Hao , Pan, Yihan , Dong, Hui , Liu, Canfeng , Yang, Jintian , Tao, Yihui et al. Generalized predictive analysis of reactions in paper devices via graph neural networks . | SENSORS AND ACTUATORS B-CHEMICAL , 2024 , 417 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Soft robots, inspired by living organisms in nature, are primarily made of soft materials, and can be used to perform delicate tasks due to their high flexibility, such as grasping and locomotion. However, it is a challenge to efficiently manufacture soft robots with complex functions. In recent years, 3D printing technology has greatly improved the efficiency and flexibility of manufacturing soft robots. Unlike traditional subtractive manufacturing technologies, 3D printing, as an additive manufacturing method, can directly produce parts of high quality and complex geometry for soft robots without manual errors or costly post-processing. In this review, we investigate the basic concepts and working principles of current 3D printing technologies, including stereolithography, selective laser sintering, material extrusion, and material jetting. The advantages and disadvantages of fabricating soft robots are discussed. Various 3D printing materials for soft robots are introduced, including elastomers, shape memory polymers, hydrogels, composites, and other materials. Their functions and limitations in soft robots are illustrated. The existing 3D-printed soft robots, including soft grippers, soft locomotion robots, and wearable soft robots, are demonstrated. Their application in industrial, manufacturing, service, and assistive medical fields is discussed. We summarize the challenges of 3D printing at the technical level, material level, and application level. The prospects of 3D printing technology in the field of soft robots are explored.
Keyword ：
3D printing 3D printing additive manufacturing additive manufacturing soft materials soft materials soft robots soft robots
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Dong, Hui , Weng, Tao , Zheng, Kexin et al. Review: Application of 3D Printing Technology in Soft Robots [J]. | 3D PRINTING AND ADDITIVE MANUFACTURING , 2024 , 11 (3) : 954-976 . |
| MLA | Dong, Hui et al. "Review: Application of 3D Printing Technology in Soft Robots" . | 3D PRINTING AND ADDITIVE MANUFACTURING 11 . 3 (2024) : 954-976 . |
| APA | Dong, Hui , Weng, Tao , Zheng, Kexin , Sun, Hao , Chen, Bingxing . Review: Application of 3D Printing Technology in Soft Robots . | 3D PRINTING AND ADDITIVE MANUFACTURING , 2024 , 11 (3) , 954-976 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Automated of gas and liquid classification technologies are of great in multiple fields including food production and human healthcare. Of these, fruit juice contains water, organic acids, minerals and other nutrients which offers a pleasant taste and promotes healthy condition. However, the main challenges faced by conventional components sensing technologies for juice classification are limited to the complexity of experimental preparation, bulky instrument, high consumption and susceptibility to contamination. Moisture Electricity Generation (MEG) technology has made it feasible to acquire energy from trace amounts of water or environmental humidity. This work proposes a novel sensing unit based on MEG technology. The unit mainly comprises non-woven fabric, hydroxylated carbon nanotubes, polyvinyl alcohol, a solution of sea salt and liquid alloy. By this approach, humid air (relative humidity 60%), pure water and juices from three fruits (lemon, kiwifruit, and clementine) have been successfully classified in 15 seconds. The classification accuracy can reach 90%. Electrical signals standard lines highlight the specific response between samples. The relative standard deviation of stable output section is 1.6% and the root-mean-square error between test data and the standard curve is less than 0.08, which indicates the stability, accuracy are fine. Besides, the sensing unit demonstrates an acceptable reusability. The presented approach may provide opportunities to improve sensing paradigms in industrial and medical settings.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Jiawen , Dong, Hui , Yang, Jintian et al. A Novel Fluid Classification Unit Based on Moisture Electricity Generation Mechanism [J]. | NANO SENSORS FOR AI, HEALTHCARE, AND ROBOTICS, NSENS , 2024 : 76-80 . |
| MLA | Lin, Jiawen et al. "A Novel Fluid Classification Unit Based on Moisture Electricity Generation Mechanism" . | NANO SENSORS FOR AI, HEALTHCARE, AND ROBOTICS, NSENS (2024) : 76-80 . |
| APA | Lin, Jiawen , Dong, Hui , Yang, Jintian , Jia, Haichao , Li, Minglin , Yao, Ligang et al. A Novel Fluid Classification Unit Based on Moisture Electricity Generation Mechanism . | NANO SENSORS FOR AI, HEALTHCARE, AND ROBOTICS, NSENS , 2024 , 76-80 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Human beings encompass sophisticated microcirculation and microenvironments, incorporating a broad spectrum of microfluidic systems that adopt fundamental roles in orchestrating physiological mechanisms. In vitro recapitulation of human microenvironments based on lab-on-a-chip technology represents a critical paradigm to better understand the intricate mechanisms. Moreover, the advent of micro/nanorobotics provides brand new perspectives and dynamic tools for elucidating the complex process in microfluidics. Currently, artificial intelligence (AI) has endowed micro/nanorobots (MNRs) with unprecedented benefits, such as material synthesis, optimal design, fabrication, and swarm behavior. Using advanced AI algorithms, the motion control, environment perception, and swarm intelligence of MNRs in microfluidics are significantly enhanced. This emerging interdisciplinary research trend holds great potential to propel biomedical research to the forefront and make valuable contributions to human health. Herein, we initially introduce the AI algorithms integral to the development of MNRs. We briefly revisit the components, designs, and fabrication techniques adopted by robots in microfluidics with an emphasis on the application of AI. Then, we review the latest research pertinent to AI-enhanced MNRs, focusing on their motion control, sensing abilities, and intricate collective behavior in microfluidics. Furthermore, we spotlight biomedical domains that are already witnessing or will undergo game-changing evolution based on AI-enhanced MNRs. Finally, we identify the current challenges that hinder the practical use of the pioneering interdisciplinary technology. Although developed independently at the beginning, AI, micro/nanorobots and microfluidics have become more intertwined in the past few years which has greatly propelled the cutting-edge development in fields of biomedical sciences.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Dong, Hui , Lin, Jiawen , Tao, Yihui et al. AI-enhanced biomedical micro/nanorobots in microfluidics [J]. | LAB ON A CHIP , 2024 , 24 (5) . |
| MLA | Dong, Hui et al. "AI-enhanced biomedical micro/nanorobots in microfluidics" . | LAB ON A CHIP 24 . 5 (2024) . |
| APA | Dong, Hui , Lin, Jiawen , Tao, Yihui , Jia, Yuan , Sun, Lining , Li, Wen Jung et al. AI-enhanced biomedical micro/nanorobots in microfluidics . | LAB ON A CHIP , 2024 , 24 (5) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Classifications of fluids using miniaturized sensors are of substantial importance for various fields of application. Modified with functional nanomaterials, a moisture-enabled electricity generation (MEG) device can execute a dual-purpose operation as both a self-powered framework and a fluid detection platform. In this study, a novel intelligent self-sustained sensing approach was implemented by integrating MEG with deep learning in microfluidics. Following a multilayer design, the MEG device including three individual units for power generation/fluid classification was fabricated in this study by using nonwoven fabrics, hydroxylated carbon nanotubes, poly(vinyl alcohol)-mixed gels, and indium tin bismuth liquid alloy. A composite configuration utilizing hydrophobic microfluidic channels and hydrophilic porous substrates was conducive to self-regulation of the on-chip flow. As a generator, the MEG device was capable of maintaining a continuous and stable power output for at least 6 h. As a sensor, the on-chip units synchronously measured the voltage (V), current (C), and resistance (R) signals as functions of time, whose transitions were completed using relays. These signals can serve as straightforward indicators of a fluid presence, such as the distinctive "fingerprint". After normalization and Fourier transform of raw V/C/R signals, a lightweight deep learning model (wide-kernel deep convolutional neural network, WDCNN) was employed for classifying pure water, kiwifruit, clementine, and lemon juices. In particular, the accuracy of the sample distinction using the WDCNN model was 100% within 15 s. The proposed integration of MEG, microfluidics, and deep learning provides a novel paradigm for the development of sustainable intelligent environmental perception, as well as new prospects for innovations in analytical science and smart instruments.
Keyword ：
deep learning deep learning fluid classification fluid classification moisture-enabled electricity generation moisture-enabled electricity generation self-sustainedsensing self-sustainedsensing V/C/R signals V/C/R signals
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Jiawen , Dong, Hui , Cui, Shilong et al. Fluid Classification via the Dual Functionality of Moisture-Enabled Electricity Generation Enhanced by Deep Learning [J]. | ACS APPLIED MATERIALS & INTERFACES , 2024 , 16 (46) : 63723-63734 . |
| MLA | Lin, Jiawen et al. "Fluid Classification via the Dual Functionality of Moisture-Enabled Electricity Generation Enhanced by Deep Learning" . | ACS APPLIED MATERIALS & INTERFACES 16 . 46 (2024) : 63723-63734 . |
| APA | Lin, Jiawen , Dong, Hui , Cui, Shilong , Dong, Wei , Sun, Hao . Fluid Classification via the Dual Functionality of Moisture-Enabled Electricity Generation Enhanced by Deep Learning . | ACS APPLIED MATERIALS & INTERFACES , 2024 , 16 (46) , 63723-63734 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Bioprinting holds the promise of producing biocompatible structures capable of seamlessly integrating with human physiology, improving human health by enabling the precise fabrication of tissue models that closely mimic the architecture and functions of human skin, brain, and bone. Building on the advancements of bioprinting, there has been a corresponding increase in cross-disciplinary innovations in wearable technologies, brain-machine interfaces, and exoskeleton robotics. Given the progress of bioprinting in skin study, wearable electronics are expected to have improved biocompatibility and integration with the human body. For patient-specific neural tissues created using bioprinting, the potential to replicate neural activities through the synergy of bioprinting and brain-machine interfaces presents opportunities to enhance the performance of more advanced neuromorphic systems. Inspired by the advancements of bioprinting in producing patient-specific bone grafts and scaffolds, this technology could bridge the gap between mechanical systems and biomechanics, redefining the limits of skeleton robotics. This review explores the advancements of bioprinting in wearable sensors, brain-machine interfaces, and exoskeleton robots, and briefly addresses the existing and potential challenges in interdisciplinary research.
Keyword ：
Bioprinting Bioprinting Brain-machine interface Brain-machine interface Exoskeleton robot Exoskeleton robot Wearable sensor Wearable sensor
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Xinrui , Dong, Wei , Dong, Hui et al. Bioprinting of wearable sensors, brain-machine interfaces, and exoskeleton robots [J]. | INTERNATIONAL JOURNAL OF BIOPRINTING , 2024 , 10 (6) : 16-37 . |
| MLA | Wang, Xinrui et al. "Bioprinting of wearable sensors, brain-machine interfaces, and exoskeleton robots" . | INTERNATIONAL JOURNAL OF BIOPRINTING 10 . 6 (2024) : 16-37 . |
| APA | Wang, Xinrui , Dong, Wei , Dong, Hui , Gao, Yongzhuo , Lin, Jiawen , Jia, Haichao et al. Bioprinting of wearable sensors, brain-machine interfaces, and exoskeleton robots . | INTERNATIONAL JOURNAL OF BIOPRINTING , 2024 , 10 (6) , 16-37 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The study of crushing characteristics of irregular single ore particles is considered crucial for understanding the secondary fragmentation mechanism, predicting particle gradation, and optimizing the gravity flow of ore particles. This study introduces a numerical simulation approach for single particle compression crushing utilizing the Breakable Voronoi block model (BVBM). The paper examines the influence of various parameters including ball diameter, loading speed, softening tensile strength factor, softening factor, and BVBM size on the crushing behavior of ore particles. It provides a suggested value range for each meso-parameter suitable for single particle modeling and crushing characteristics research. Additionally, the paper describes the evolution of BVBM crushing mode, the total number of cracks, and the number of contact bonds under the influence of different softening factors. Soft rock particles with high softening factors exhibit more significant softening behavior and ductility compared to hard rock particles with low softening factors.
Keyword ：
Breakable Voronoi block model Breakable Voronoi block model Crushing characteristics Crushing characteristics Discrete element modeling Discrete element modeling Single ore particle Single ore particle Soft bond contact model Soft bond contact model
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jin, Aibing , Li, Muya , Sun, Hao et al. Numerical modeling of the crushing characteristics of single ore particle based on breakable Voronoi block model [J]. | POWDER TECHNOLOGY , 2024 , 445 . |
| MLA | Jin, Aibing et al. "Numerical modeling of the crushing characteristics of single ore particle based on breakable Voronoi block model" . | POWDER TECHNOLOGY 445 (2024) . |
| APA | Jin, Aibing , Li, Muya , Sun, Hao , Zhao, Lishan , Jia, Junze , Zhao, Yusong . Numerical modeling of the crushing characteristics of single ore particle based on breakable Voronoi block model . | POWDER TECHNOLOGY , 2024 , 445 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
随着医辽诊断和治疗干预技术的不断进步,医学时间序列数据呈现指数级增长.人工智能(AI),尤其是深度学习在挖掘医学时间序列数据潜在信息方面展现出巨大潜力.为此,首次提出将 Transformer 与Kolmogorov arnold网络(KAN)相结合的方法,用于核酸扩增实验数据的预测分析.通过实验数据分析,证实模型在准确预测扩增趋势和终点值方面的有效性,终点值误差仅为 1.87,R-square系数为 0.98,且模型能准确识别不同样本类型的实验数据.进一步地,通过消融实验和超参数调优,深入探究模型各组成部分及其参数对预测性能的影响.最后,在 911 条临床数据上对 10 种深度学习模型进行泛化能力测试的结果表明,Transformer-KAN模型在预测准确性和泛化能力上均优于其他模型,不仅为改进大流行病常规诊断技术提供了新视角,还为进一步研究KAN模型及相应基础理论提供了实验佐证.
Keyword ：
Kolmogorov-Arnold网络 Kolmogorov-Arnold网络 Transformer Transformer 时间序列预测 时间序列预测 核酸扩增检测技术 核酸扩增检测技术 深度学习 深度学习
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘灿锋 , 孙浩 , 东辉 . 结合Transformer与Kolmogorov Arnold网络的分子扩增时序预测研究 [J]. | 图学学报 , 2024 , 45 (6) : 1256-1265 . |
| MLA | 刘灿锋 et al. "结合Transformer与Kolmogorov Arnold网络的分子扩增时序预测研究" . | 图学学报 45 . 6 (2024) : 1256-1265 . |
| APA | 刘灿锋 , 孙浩 , 东辉 . 结合Transformer与Kolmogorov Arnold网络的分子扩增时序预测研究 . | 图学学报 , 2024 , 45 (6) , 1256-1265 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the increasing demand for biomarker detection in wearable electronic devices, flexible biosensors have garnered significant attention. Additionally, graphene field-effect transistors (GFETs) have emerged as key components for constructing biosensors, owing to their high sensitivity, multifunctionality, rapid response, and low cost. Leveraging the advantages of flexible substrates, such as biocompatibility, adaptability to complex environments, and fabrication flexibility, flexible GFET sensors exhibit promising prospects in detecting various biomarkers. This review provides a concise summary of design strategies for flexible GFET biosensors, including non-encapsulated gate without dielectric layer coverage and external gate designs. Furthermore, notable advancements in sensing applications of biomolecules, such as proteins, glucose, and ions, are highlighted. Finally, we discuss the future challenges and prospects in this field, aiming to inspire researchers to address these issues in their further investigations.
Keyword ：
biomarker biomarker biomolecule biomolecule biosensor biosensor flexible flexible graphene field-effect transistor graphene field-effect transistor
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Hu, Bo , Sun, Hao , Tian, Jinpeng et al. Advances in flexible graphene field-effect transistors for biomolecule sensing [J]. | FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY , 2023 , 11 . |
| MLA | Hu, Bo et al. "Advances in flexible graphene field-effect transistors for biomolecule sensing" . | FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY 11 (2023) . |
| APA | Hu, Bo , Sun, Hao , Tian, Jinpeng , Mo, Jin , Xie, Wantao , Song, Qiu Ming et al. Advances in flexible graphene field-effect transistors for biomolecule sensing . | FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY , 2023 , 11 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Hollow nanomaterials have attracted significant interest. However, developing an effective growth mechanism for synthesizing seed-like hollow nanoparticles (SHNPs) with tailored structures still remains challenging. In this study, we developed a dynamic interfacial-tension-controlled polar growth strategy to synthesize SHNPs with a narrow size distribution using a metal-organic coordination compound. The synthesis was performed in an oil-in-water emulsion system comprising disulfiram (DSF) oil nanodroplets and cis-dichlorodiamine platinum-(II) (Cpt) aqueous phases. The DSF nanodroplets exhibited dynamic interfacial tension owing to the gradual consumption of DSF molecules, resulting in the polar growth of DSF nanodroplets from a spherical to anisotropic seed-like morphology. This method produced seed-like hollow nanostructures with tailored morphologies, such as pomegranate, peanut, bean sprout, and pistachio structures and desired lengths. Additionally, we constructed a seed-like nanomotor by loading small platinum (Pt) nanoparticles onto the surface of SHNPs, which exhibit an enhanced diffusion coefficient and exceptional oriented movement in response to the hydrogen peroxide (H2O2) fuel.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Dang, Meng , Yu, Ruifa , Han, Xiaolin et al. Seed-like Hollow Nanoparticles by a Dynamic Interfacial-Tension-Controlled Polar Growth Strategy [J]. | CHEMISTRY OF MATERIALS , 2023 , 35 (24) : 10542-10549 . |
| MLA | Dang, Meng et al. "Seed-like Hollow Nanoparticles by a Dynamic Interfacial-Tension-Controlled Polar Growth Strategy" . | CHEMISTRY OF MATERIALS 35 . 24 (2023) : 10542-10549 . |
| APA | Dang, Meng , Yu, Ruifa , Han, Xiaolin , Shao, Lixin , Zhao, Jiajia , Ding, Zhi et al. Seed-like Hollow Nanoparticles by a Dynamic Interfacial-Tension-Controlled Polar Growth Strategy . | CHEMISTRY OF MATERIALS , 2023 , 35 (24) , 10542-10549 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
