检索结果-内蒙古大学图书馆

Photocatalytic selective oxidation of HMF to DFF based on hollow CdS QDs/MIL-101 composites under visible light

MOLECULAR CATALYSIS 2024年 569卷

作者： Liang, Yuwei Hu, Chunling Chen, Peng Li, Qi Wu, Jianning Liu, Zhiyong Liu, Jichang Tai, Yanlong Shihezi Univ Sch Chem & Chem Engn Key Lab Green Proc Chem Engn Xinjiang Bingtuan Beisi Rd Shihezi 832003 Xinjiang Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Key Lab Human Machine Intelligence Synergy Syst Shenzhen 518055 Peoples R China

5-hydroxymethylfurfural (HMF) can catalyte into 2,5-diformylfuran (DFF) which had received much attention as a potential biomass resource. Here, we used a simple and effective method to construct hollow CdS quantum dot (CdS QDs)/MIL-101 heterostructures with high contact area and multiple active sites. The structure of heterostructures could improve photocatalytic activity by charge transfer, photogenerated carrier separation and the multiple refractions of light supported within the hollow-structured CdS QDs. The detailed catalytic mechanism was illustrated by trap agent experiments and electron paramagnetic resonance (EPR) spectroscopy, in which superoxide radicals (center dot O2- ) play a decisive role in the catalytic oxidation of HMF to DFF. Furthermore, the large specific surface area of MIL-101 adsorbs O2 from the reaction system thereby accelerating the center dot O2- formation process. Under environmental conditions, 70 % CdS QDs/MIL-101 exhibited optimal catalytic performance. Comparing with pure CdS QDs, the photocurrent enhances 1.8 times, HMF conversion is 1.5 times and DFF selectivity is 1.2 times. This work provide a useful way to improve the conversion of biomass by Z-heterostructures under ambient conditions.

关键词： CdS QDs MIL-101(Cr) HMF Photocatalytic Oxiditionl

来源：评论

学校读者我要写书评

暂无评论

A novel spatial feature extraction method based on high-density sEMG for complex hand movement recognition

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 103卷

作者： Peng, Boxing Zhang, Haoshi Li, Xiangxin Li, Guanglin Chinese Acad Sci Shenzhen Inst Adv Technol SIAT CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen 518055 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc SIAT Branch Shenzhen 518055 Peoples R China

Surface electromyography pattern recognition (sEMG-PR) based prostheses control system is beneficial for amputees to restore their upper limb function. However, identifying complex human movements from surface electromyography (sEMG) remains challenging for electromyography pattern recognition system because complex hand and wrist movements involve more subtle muscular regional activities that may not be captured by the classic independent channel extraction method with time-domain (TD) features. In this study, a novel spatial feature extraction method, Multichannel linear descriptors based Block field method (MLD-BFM), was proposed to improve the movement classification performance by extracting the spatial information of high-density sEMG (HD-sEMG) signals. In this method, a 64-channel HD-sEMG system was used, BFM was designed to segment regions from channel grids, and MLD was employed as spatial feature set extracted from each region. The effectiveness of the proposed method was evaluated to identify 28 classes of hand and wrist movements with comparison to six well-known feature extraction methods. The results showed that the proposed spatial feature extraction method achieved the classification error rates (CE) of 3.59%, which is the lowest for identifying 28 classes of movements, and had the lowest CEs across all four classifiers employed in this study. Furthermore, the proposed method showed greatly enhancement in combined movement recognition with a CE of 4.94%, which is the lowest across all feature extraction methods. The work of this study may provide a promising approach to extract the spatial information of HD-sEMG from different muscle regions to classify the complex hand movements.

关键词： High-density electromyography Spatial feature extraction Pattern recognition Myoelectric control

来源：评论

学校读者我要写书评

暂无评论

Loading Recognition for Lumbar Exoskeleton Based on Multi-Channel Surface Electromyography From Low Back Muscles

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2024年第7期71卷 2154-2162页

作者： Jiang, Naifu Wang, Lin Wang, Dashuai Fang, Peng Wu, Xinyu Li, Guanglin Chinese Acad Sci Shenzhen Inst Adv Technol SIAT CAS Key Lab Human Machine Intelligence Synergy Sy Shenzhen 518055 Peoples R China Guangdong HongKong Macao Joint Lab Human Machine Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Sch Microelect Shenzhen Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc SIAT Branch Shenzhen 518055 Peoples R China

Lumbar exoskeleton is an assistive robot, which can reduce the risk of injury and pain in low back muscles when lifting heavy objects. An important challenge it faces involves enhancing assistance with minimal muscle energy consumption. One of the viable solutions is to adjust the force or torque of assistance in response to changes in the load on the low back muscles. It requires accurate loading recognition, which has yet to yield satisfactory outcomes due to the limitations of available measurement tools and load classification methods. This study aimed to precisely identify muscle loading using a multi-channel surface electromyographic (sEMG) electrode array on the low back muscles, combined with a participant-specific load classification method. Ten healthy participants performed a stoop lifting task with objects of varying weights, while sEMG data was collected from the low back muscles using a 3x7 electrode array. Nineteen time segments of the lifting phase were identified, and time-domain sEMG features were extracted from each segment. Participant-specific classifiers were built using four classification algorithms to determine the object weight in each time segment, and the classification performance was evaluated using a 5-fold cross-validation method. The artificial neural network classifier achieved an impressive accuracy of up to 96%, consistently improving as the lifting phase progressed, peaking towards the end of the lifting movement. This study successfully achieves accurate recognition of load on low back muscles during the object lifting task. The obtained results hold significant potential in effectively reducing muscle energy consumption when wearing a lumbar exoskeleton.

关键词： Muscles Exoskeletons Electrodes Biomedical measurement Particle measurements Hip Atmospheric measurements Exoskeleton load classification lift assistance surface electromyography low back pain

来源：评论

学校读者我要写书评

暂无评论

Organic-inorganic hybrid hole transport layers with SnS doping boost the performance of perovskite solar cells

引用

Journal of Energy Chemistry 2022年第5期31卷 637-645页

作者： Xiaolu Zheng Haibing Wang Feihong Ye Cong Chen Weijun Ke Wenjing Zhang Chuanxin He Yanlong Tai Guojia Fang College of Chemistry and Environmental Engineering Institute of Microscale OptoelectronicsShenzhen UniversityShenzhen 518060GuangdongChina Shenzhen Institute Wuhan UniversityShenzhen 518057GuangdongChina Key Laboratory of Human-Machine Intelligence-Synergy Systems of Chinese Academy of Sciences and Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055GuangdongChina

Perovskite solar cells(PSCs) have demonstrated excellent photovoltaic performance which currently rival the long-standing silicon solar cells’ efficiency. However, the relatively poor device operational stability of PSCs still limits their future commercialization. Binary sulfide is a category of materials with promising optoelectrical properties, which shows the potential to improve both the efficiency and stability of *** we demonstrate that the inorganic tin monosulfide(Sn S) can be an efficient dopant in 2,2’,7,7’-tet rakis(N,N-di-p-methoxy-phenylamine)-9,9’-spirobifluorene(spiro-OMe TAD) to form a composite hole transport layer(HTL) for PSCs. Sn S nanoparticles(NPs) synthesized through a simple chemical precipitation method exhibit good crystallization and suitable band matching with the perovskites. The introduction of Sn S NPs in Spiro-OMTAD HTLs enhanced charge extraction, reduced trap state density, and shallowed trap state energy level of the devices based on the composite HTLs. Therefore, the resulting solar cells employing Sn S-doped spiro-OMe TAD HTLs delivered an improved stabilized power output efficiency of 21.75% as well as enhanced long-term stability and operational stability. Our results provide a simple method to modify the conventional spiro-OMe TAD and obtain PSCs with both high efficiency and good stability.

关键词： Perovskite solar cells SnS nanoparticles Trap state passivation Stability

来源：评论

学校读者我要写书评

暂无评论

Polyhedron BiVO4 co-doped by Mo and Y for visible light-driven photocatalytic overall water splitting

引用

JOURNAL OF MATERIALS SCIENCE 2024年第20期59卷 8721-8735页

作者： Wang, Yifan Wang, Lele Li, Qi Wu, Jianning Meng, Guihua Yang, Shengchao Liu, Zhiyong Tai, Yanlong Liu, Jichang Shihezi Univ Sch Chem & Chem Engn State Key Lab Incubat Base Green Proc Chem Engn Beisi Rd Shihezi 832003 Xinjiang Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Key Lab Human Machine Intelligence Synergy Syst Shenzhen 518055 Peoples R China

Photocatalytic overall water splitting (POWS) is a promising route for converting solar energy into green and sustainable energy. Herein, we report a facile hydrothermal approach to fabricate polyhedron BiVO4 by Mo and Yco-doping (MYB) photocatalysts with suitable band gap for POWS. The MYB exhibited enhanced visible light-driven POWS activities in comparison with that of as-prepared BiVO4, Y-BiVO4 and M-BiVO4, with the maximum H-2 and O-2 evolution rate of 34.7 and 17.4 mu molh(-1)g(-1), respectively. The optimum activity of the catalyst was controlled by adjusting Mo content of MYB. The photodeposition of Pt shows that there are special separation reduction and oxidation centers on the surface of MYB. Electrochemical experiments further confirmed the enhanced charge separation of MYB. MYB photocatalyst has small particle size, unique polyhedral structure, large specific surface area and high (103) and (200) surface exposure, thus improving POWS performance, high electron transfer efficiency and effective separation of photogenerated electron-hole pairs. Because of the doping of Mo and Y elements, the electronic structure of the catalyst is altered, enhancing light absorption and reducing the recombination of photogenerated electron-hole pair. The current study revealed that the MYB products could serve as cost-effective and stable photocatalysts for POWS.

关键词： Bismuth compounds

来源：评论

学校读者我要写书评

暂无评论

Masked cosine similarity prediction for self-supervised skeleton-based action representation learning

引用

PATTERN ANALYSIS AND APPLICATIONS 2025年第2期28卷 1-17页

作者： Ren, Ziliang Liu, Ronggui Qin, Yong Gao, Xiangyang Zhang, Qieshi Dongguan Univ Technol Sch Comp Sci & Technol Dongguan 523808 Guangdong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen 518055 Guangdong Peoples R China

Skeleton-based human action recognition faces challenges owing to the limited availability of annotated data, which constrains the performance of supervised methods in learning representations of skeleton sequences. To address this issue, researchers have introduced self-supervised learning as a method of reducing the reliance on annotated data. This approach exploits the intrinsic supervisory signals embedded within the data itself. In this study, we demonstrate that considering relative positional relationships between joints, rather than relying on joint coordinates as absolute positional information, yields more effective representations of skeleton sequences. Based on this, we introduce the Masked Cosine Similarity Prediction (MCSP) framework, which takes randomly masked skeleton sequences as input and predicts the corresponding cosine similarity between masked joints. Comprehensive experiments show that the proposed MCSP self-supervised pre-training method effectively learns representations in skeleton sequences, improving model performance while decreasing dependence on extensive labeled datasets. After pre-training with MCSP, a vanilla transformer architecture is employed for fine-tuning in action recognition. The results obtained from six subsets of the NTU-RGB+D 60, NTU-RGB+D 120 and PKU-MMD datasets show that our method achieves significant performance improvements on five subsets. Compared to training from scratch, performance improvements are 9.8%, 4.9%, 13%, 11.5%, and 3.6%, respectively, with top-1 accuracies of 92.9%, 97.3%, 89.8%, 91.2%, and 96.1% being achieved. Furthermore, our method achieves comparable results on the PKU-MMD Phase II dataset, achieving a top-1 accuracy of 51.5%. These results are competitive without the need for intricate designs, such as multi-stream model ensembles or extreme data augmentation. The source code of our MOSP is available at https://***/skyisyourlimit/MCSP.

关键词： Skeleton-based action recognition Self-supervised learning Masked autoencoders

来源：评论

学校读者我要写书评

暂无评论

A Prosthetic Hand System with human-Like Grasping by Combining EMG and Visual Information 30

A Prosthetic Hand System with Human-Like Grasping by Combini...

引用

30th International Conference on Mechatronics and machine Vision in Practice, M2VIP 2024

作者： Zheng, Yue Chen, Xinxing Tian, Lan Li, Xiangxin Zhang, Haoshi Jiang, Xugang Li, Guanglin Fu, Chenglong Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Shenzhen518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen518055 China Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems China

ISBN: (纸本)9798350391916

This paper proposed a novel prosthetic hand system integrated with a designed hybrid control method for achieving human-like grasping. The system design has been elaborated, including the mechanism design of a humanoid prosthetic hand equipped with multimodal sensing capabilities, a multi-channel EMG collector, a sensory feedback device, and a real-time central processing unit. A hybrid control method that combines electromyogram (EMG) and visual information was proposed to recognize the control intention of the system user. Preliminary verification of grasping experiments had been conducted, which proved the effectiveness of the prosthetic hand system and the hybrid control method. The development of this system aims to enhance the control performance and perceptual interaction capabilities of prosthetic hands while addressing limitations encountered in traditional myoelectric prosthetic hands. Besides, it could serve as a validation platform for assessing the control performance of diverse algorithms applied in practical applications. © 2024 IEEE.

关键词： Sensory feedback

来源：评论

学校读者我要写书评

暂无评论

Effective Probabilistic Neural Networks Model for Model-Based Reinforcement Learning USV

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 11625-11641页

作者： Huang, Wenjun Cui, Yunduan Li, Huiyun Wu, Xinyu Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Guangdong Hong Kong Macao Joint Lab Human Machine Shenzhen 518055 Guangdong Peoples R China

Gaussian process (GP) offers a robust solution for modeling the dynamics of unmanned surface vehicles (USV) in model-based reinforcement learning (MBRL). However, the rapidly increasing computational complexity with a large sample capacity of GP limits its application in complex scenarios that require substantial samples to cover the state space. In this article, a novel probabilistic MBRL approach, probabilistic neural networks model predictive control (PNMPC) is proposed to tackle this issue. With an iterative learning framework, PNMPC properly models the USV dynamics using neural networks from a probabilistic perspective to avoid the computational complexity associated with sample capacity. Employing this model to effectively propagate system uncertainties, a model predictive control (MPC) policy is developed to robustly control the USV against external disturbances. Evaluated by position-keeping and multiple targets-tracking scenarios on a real USV data-driven simulation, the proposed method consistently demonstrates its significant superiority in both model accuracy and control performance compared to not only GP model-based approaches but also the probabilistic neural networks-based MBRL baselines, across various scales of external disturbances.

关键词： Computational modeling Probabilistic logic Neural networks Uncertainty Predictive models Vehicle dynamics Training Stability analysis Computational complexity Adaptation models Reinforcement learning (RL) neural networks predictive models marine vehicles

来源：评论

学校读者我要写书评

暂无评论

A Review of State-of-the-arts Sensing Techniques for the Ultra-early Screening of Cerebral Palsy

A Review of State-of-the-arts Sensing Techniques for the Ult...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Zhuang, Yunji Zhou, Hao Zhang, Huiping Chen, Yanni Wang, Lin Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China Guangdong-Hong Kong-Macau Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Xi'an Jiaotong University Children's Hospital Xi'an710002 China

ISBN: (纸本)9798350327182

Cerebral palsy (CP) is characterized by neuromotor disorders. It remains a huge challenge for ultra-early screening of CP. So far, the diagnosis of CP is mainly based on a combination of neuromotor assessment methods, magnetic resonance imaging (MRI) and clinical history. However, subjective errors are highly likely to be introduced in the process of CP screening due to disparities in clinicians' professional backgrounds, working abilities and academic levels. Cutting-edge sensing techniques have been unveiled in the field of ultra-early CP prediction which provides objective diagnosis with quantified output information by obtaining motion capture, classification, and recognition. It is necessary to contrast the strengths, weaknesses, and potential of these techniques and how to apply them in the ultra-early screening of CP. This study compares and analyzes the latest and advanced sensing methods and discusses their future applications in infantile CP screening. The work could provide technical suggestions and clinical guidance for early intervention in the field of ultra-early CP screening later on. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Limited Information Aggregation for Collaborative Driving in Multi-Agent Autonomous Vehicles

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第7期9卷 6624-6631页

作者： Liang, Qingyi Liu, Jia Jiang, Zhengmin Yin, Jianwen Xu, Kun Li, Huiyun Southern Univ Sci & Technol Shenzhen 518055 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen 518055 Peoples R China Univ Chinese Acad Sci Beijing 101408 Peoples R China

Multi-agent reinforcement learning (MARL) methods have emerged as a promising solution for multi-agent collaborative driving in the intersection and roundabout scenarios. However, these methods need large amounts of training data obtained from the interaction with the driving simulator, and learning from limited interaction remains significantly underdeveloped. In this letter, we propose an efficient MARL method to address this challenge. Our method enables each vehicle to receive limited messages from surrounding vehicles, which are then used to augment the input representation of the local driving policy. By predicting the next-step state based on the current augmented local state and action, our approach enhances the decision-making capability of each vehicle. Specifically, we design a Self-supervised Message Attention Encoding (SMAE) module that utilizes an attention mechanism to aggregate the received messages and local observations, generating a compact representation. Then, this representation is used in a self-supervised module to predict the next-step state. By jointly training the encoder module and the prediction module, each vehicle effectively leverages the most relevant components of the aggregated representation to improve the learning efficiency of driving policy and alleviate issues related to partial observability in making driving decisions. To validate the effectiveness of our approach, we conduct experiments using an open-source autonomous driving simulator. The simulation results demonstrate that our proposed method outperforms the IPPO, MAPPO and CoPO algorithms in terms of success rate, route completion rate, crash rate, and other relevant metrics.

关键词： Collaboration Observability Autonomous vehicles Training Decision making Data mining Uncertainty Multi-agent autonomous vehicles collaborative driving information aggregation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：