检索结果-南通市图书馆

Domain generalization with semi-supervised learning for people-centric activity recognition

Science China(Information Sciences) 2025年第1期68卷 171-188页

作者： Jing liU wei ZHU Di li Xing HU liang SONG Academy for Engineering & Technology Fudan University Shanghai East-bund Research Institute on Networking Systems of AI School of Optoelectronic Information and Computer Engineering University of Shanghai for Science & Technology

People-centric activity recognition is one of the most critical technologies in a wide range of real-world applications,including intelligent transportation systems, healthcare services, and brain-computer interfaces. Large-scale data collection and annotation make the application of machine learning algorithms prohibitively expensive when adapting to new tasks. One way of circumventing this limitation is to train the model in a semi-supervised learning manner that utilizes a percentage of unlabeled data to reduce the labeling burden in prediction tasks. Despite their appeal, these models often assume that labeled and unlabeled data come from similar distributions, which leads to the domain shift problem caused by the presence of distribution gaps. To address these limitations, we propose herein a novel method for people-centric activity recognition,called domain generalization with semi-supervised learning(DGSSL), that effectively enhances the representation learning and domain alignment capabilities of a model. We first design a new autoregressive discriminator for adversarial training between unlabeled and labeled source domains, extracting domain-specific features to reduce the distribution gaps. Second, we introduce two reconstruction tasks to capture the task-specific features to avoid losing information related to representation learning while maintaining task-specific consistency. Finally, benefiting from the collaborative optimization of these two tasks, the model can accurately predict both the domain and category labels of the source domains for the classification task. We conduct extensive experiments on three real-world sensing datasets. The experimental results show that DGSSL surpasses the three state-of-the-art methods with better performance and generalization.

关键词： activity recognition deep learning domain generalization semi-supervised learning adversarial training

来源：

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Aerodynamic Optimization and Flow Mechanism for a Compressor Cascade at Low Reynolds Number

引用

Journal of Thermal Science 2025年第1期34卷 92-109页

作者： li lin ZHANG Jianshe CHEN Caiyan TAN wei ZHANG Yanfeng Key Laboratory of light-Duty Gas-Turbine Institute of Engineering ThermophysicsChinese Academy of Sciences University of Chinese Academy of Sciences National Key Laboratory of Science and Technology on Advanced light-duty Gas-turbine

Low-Reynolds-number effect is an important factor affecting the performance of compressors and other main components of high-altitude long-endurance unmanned aerial *** improve the flow condition and reduce flow loss under the condition of high altitude and low Reynolds number(Re),this paper proposes an optimization process based on a surrogate model,which combines the class-shape transformation method(CST),the Latin hypercube sampling(LHS) method,the light gradient-boosting machine algorithm(lightGBM),and a genetic algorithm(GA) to optimize a high-subsonic compressor *** surrogate model is verified to be accurate and can be used in the optimization *** accuracy of the GA is higher than the other algorithms under common test *** optimization results are verified by numerical simulation,and the flow differences before and after optimization are compared,especially the flow within the boundary *** changing the blade shape,the optimization process adjusts the loading distribution to delay the transition of the optimized blade on the suction surface,which changes the turbulent reattachment in the laminar separation bubble(LSB) into laminar ***,the mixing loss induced by the turbulent reattachment of the LSB and the wake loss of turbulent separation at the trailing edge are significantly reduced,and the performance of the compressor profile is finally *** addition,turbulent separation of the optimized profile is delayed reducing the range of the wake region on the suction *** this optimization process,the reduction of total pressure loss coefficient at Re of 2.5×10～5,3.5×10～5,and 4.5×10～5 are 16.32%,20.76%,and 22.16%,respectively.

关键词： Reynolds number

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

A Rapid Adaptation Approach for Dynamic Air‑Writing Recognition Using Wearable Wristbands with Self‑Supervised Contrastive Learning

引用

Nano-Micro Letters 2025年第2期17卷 417-431页

作者： Yunjian Guo Kunpeng li wei Yue Nam‑Young Kim Yang li Guozhen Shen Jong‑Chul Lee Department of Electronic Convergence Engineering Kwangwoon UniversitySeoul 01897South Korea Radio Frequency Integrated Circuit(RFIC)Bio Centre Kwangwoon UniversitySeoul 01897South Korea Department of Electronic Engineering Kwangwoon UniversitySeoul 01897South Korea School of Microelectronics Shandong UniversityJinan 250101People’s Republic of China State Key Laboratory of Integrated Chips and Systems Fudan UniversityShanghai 200433People’s Republic of China School of Integrated Circuits and Electronics Beijing Institute of TechnologyBeijing 100081People’s Republic of China

Wearable wristband systems leverage deep learning to revolutionize hand gesture recognition in daily *** existing approaches that often focus on static gestures and require extensive labeled data,the proposed wearable wristband with selfsupervised contrastive learning excels at dynamic motion tracking and adapts rapidly across multiple *** features a four-channel sensing array composed of an ionic hydrogel with hierarchical microcone structures and ultrathin flexible electrodes,resulting in high-sensitivity capacitance *** wireless transmission from a Wi-Fi module,the proposed algorithm learns latent features from the unlabeled signals of random wrist ***,only few-shot labeled data are sufficient for fine-tuning the model,enabling rapid adaptation to various *** system achieves a high accuracy of 94.9%in different scenarios,including the prediction of eight-direction commands,and air-writing of all numbers and *** proposed method facilitates smooth transitions between multiple tasks without the need for modifying the structure or undergoing extensive task-specific *** utility has been further extended to enhance human–machine interaction over digital platforms,such as game controls,calculators,and three-language login systems,offering users a natural and intuitive way of communication.

关键词： Wearable wristband Self-supervised contrastive learning Dynamic gesture Air-writing Human-machine interaction

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Characterization of a formaldehyde degrading fungus Penicillium chrysogenum DY-F2 isolated from deep sea sediment

Characterization of a formaldehyde degrading fungus Penicill...

引用

福建省海洋学会2014年学术年会暨福建省科协第十四届学术年会

作者： Jing-Jing Luo Jie-Fei Ding guang-wei li Tian-ling Zheng Zhu-Hua Luo Key Laboratory of Marine Biogenetic Resources Third Institute of OceanographyState Oceanic Administration School of life Sciences Xiamen University

A formaldehyde-degrading fungus was isolated from deep sea sediment of East Pacific by enrichment culture technique and was identified as Penicillium chrysogenum DY-F2 based on microscopic spore morphology and 18 S r RNA gene sequence analysis. The fungus showed high formaldehyde resistance and was able to grow in the presence of formaldehyde up to 3000 mg l-1. The optimal temperature and p H for the growth of fungus in the presence of 1000 mg l-1 of formaacknowlegementldehyde was 25 °C and 6.0, respectively. The fungus was able to degrade formaldehyde as the sole source of carbon and energy with the formation of formic acid as the intermediate. Degradation of formaldehyde by the fungus conformed to a first-order kinetic model. This study showed that the deep sea sediment fungi are the potential microbial resources for bioremediation of formaldehyde pollution in marine environment.

关键词： Deep sea fungi Penicillium chrysogenum Formaldehyde Biodegradation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Precise gradient separation of nanoparticles using reduced graphene oxide-polyoxomolybdate membranes

引用

Science China Chemistry 2025年第1期68卷 209-216页

作者： Yixin Yang Wanlei Zhao Ruoxuan Zheng Hongqiang li wei Chen Yu-Fei Song State Key Laboratory of Chemical Resource Engineering Beijing University of Chemical Technology Quzhou Institute for Innovation in Resource Chemical Engineering

The purification and size sieving of nanoparticles （NPs） represents a significant scientific ***,the r GO-polyoxometalates (POMs=PMo12,Mo132and Mo368) membranes were fabricated successfully via a simple and scalable POMsassisted in-situ photoreduction *** the mass ratio of r GO to PMo12was 1:30,the resultant r GO-PMo12membranes with highly ordered and uniform nanochannels of 1.0 nm can be obtained,which showed an accurate carbon quantum dots（CQDs） separation with a cut-off size approximately 1.0 *** increase of the size of the interlayered POMs from PMo12（1.0 nm）,{Mo132}（2.9 nm） to{Mo368}（3.8 nm）,the resultant r GO-PMo12,r GO-Mo132and r GO-Mo368exhibited precise gradient separation of CQDs and Au nanoparticles by size exclusion *** results pave a promising way to construct new twodimensional （2D） membranes for highly efficient size-selective separation.

关键词： reduced graphene oxide polyoxometalates membranes gradient separation nanoparticles

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Resistance of Cement-based Grouting Materials with Nano- SiO_(2) Emulsion to Chloride Ion Penetration

引用

Journal of Wuhan University of Technology(Materials Science) 2025年第1期40卷 114-119页

作者： li Shuiping CHENG Jian wei Chao YUAN Bin YU Chengxiao College of Architectural Science and Engineering Yangzhou UniversityYangzhou 225127China

The chloride penetration resistance of cement-based grout materials was improved by nano-silica *** of mixtures containing different nano-silica particles or emulsions were exposed in sodium chloride solutions of specific concentrations with different test *** properties of the mixes were assessed in terms of weight loss and compressive strength.X-ray diffraction(XRD)and scanning electron microscopy(SEM)of mixes were performed to analysis the phase evolution and *** results demonstrated that the introduction of nano-SiO_(2) emulsion significantly decreased the compressive strength loss and calcium hydroxide(CH)crystal content of hydration production,and then enhanced the resistance of cement-based grouting materials to chloride ion *** improvement derives from the filling and pozzolanic effects of nano-SiO_(2) particles,which were incorporated via an emulsion and attributed to a well dispersion in grouting matrix.

关键词： grouting materials nano-SiO_(2)emulsion chloride ion penetration,weight loss strength loss

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

工艺参数对电沉积钴镍合金镀层成分及耐磨性能的影响

引用

兵工学报 2018年第4期39卷 753-762页

作者：颜丙辉魏广宁李晨霞李雪松长春工业大学材料科学与工程学院吉林长春130012

利用电沉积技术在碳钢表面制备纳米晶钴镍合金镀层,并辅助超声波分散加机械搅拌,获得具有良好减摩性能的纳米晶、低微摩擦系数的钴镍合金镀层材料。研究了电流密度、温度、p H值等工艺参数对合金镀层成分及耐磨性的影响。利用扫描电镜... 详细信息

利用电沉积技术在碳钢表面制备纳米晶钴镍合金镀层,并辅助超声波分散加机械搅拌,获得具有良好减摩性能的纳米晶、低微摩擦系数的钴镍合金镀层材料。研究了电流密度、温度、p H值等工艺参数对合金镀层成分及耐磨性的影响。利用扫描电镜、场发射扫描电镜、X射线衍射仪分析了镀层表面的显微组织、相结构及成分含量,通过UNMT1微纳米材料力学综合测试系统考察镀层的微磨损性能。结果表明,获得的合金镀层组织细密、结构均匀,工艺参数对合金层的微摩擦系数影响较大,在最佳工艺参数电流密度1.5 A/dm2、温度50℃、p H值为4.0时合金镀层的平均摩擦系数最小为0.18,合金具有较好的耐微摩擦磨损性能。

关键词：钴镍合金电沉积纳米晶微摩擦磨损

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Adaptive-basis decomposition-based low-rank network for efficient non-uniform motion deblurring

引用

Optoelectronics Letters 2025年第1期21卷 43-50页

作者： CHEN Lei XIONG Qingbo ZHANG wei li Runde School of Software Henan University School of Applied Technology China University of Labor Relations

In this study, we present a unified sparsity-driven framework that significantly enhances motion deblurring performance by integrating two key components: a custom-designed dataset and a low-rank module(LRM). This framework leverages the inherent sparsity of per-pixel blur kernels to bolster both deblurring accuracy and model interpretability. Firstly, we propose an adaptive-basis decomposition-based deblurring(ADD) approach, which constructs a tailored training dataset to enhance the generalization capacity of the deblurring network. The ADD framework adaptively decomposes motion blur into sparse basis elements, effectively addressing the intricacies associated with non-uniform blurs. Secondly, an LRM is proposed to improve the interpretability of deblurring models as a plug-and-play module, primarily designed to identify and harness the intrinsic sparse features in sharp images. A series of ablation studies have been conducted to substantiate the synergistic advantages of combining the proposed ADD with the LRM for overall improvement in deblurring efficacy. Subsequently, we empirically demonstrate through rigorous experimentation that incorporating the LRM into an existing Uformer network leads to substantial enhancement in reconstruction performance. This integration yields a sparsity-guided low-rank network(SGLRN). Operating under the overarching principle of sparsity, SGLRN consistently outperforms state-of-the-art methods across multiple standard deblurring benchmarks. Comprehensive experimental results, assessed through quantitative metrics and qualitative visual evaluations, provide compelling evidence of its effectiveness. The overall deblurring results are available at Google Drive.

关键词： Image enhancement

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Circumspinal decompression through a single posterior incision to treat thoracolumbar disc herniation

引用

Chinese Medical Journal 2011年第23期124卷 3852-3857页

作者： QI Qiang CHEN Zhong-qiang liU Ning GUO Zhao-qing SHI Ze-feng liU Zhong-jun liU Xiao-guang li wei-shi ZENG Yan SUN Chui-guo Department of Orthopaedics Peking University Third Hospital Beijing 100191 China

Various surgical approaches have been successfully used in the treatment of thoracolumbar disc herniation （TLDH）. Although the anterior transthoracic approach has a reputation for better visualization than the posterolateral and lateral approaches, it involves the manipulation of the thoracic and pulmonary structures. Thus, this approach is technically demanding and prone to compromising the respiratory system. An ideal approach would involve adequate visualization and be accomplished through the posterior midline approach that is familiar to spine surgeons. The objective of this retrospective preliminary clinical study was to introduce a new surgical procedure, circumspinal decompression through a single posterior incision, for the treatment of TLDH （T10/11-L1/2） and to evaluate the surgical outcome of this procedure by comparing it to the conventional anterior transthoracic approach. Methods In this study, 15 patients （10 males, 5 females; mean age 51 years） with symptomatic TLDH underwent the circumspinal decompression through a single posterior incision procedure between January 2008 and December 2009. Altogether, 17 herniated discs were excised, with 2 discs at T10/11, 4 discs at Tll/12, 5 discs at T12/L1 and 6 discs at L1/2. Of these patients, 13 were followed up with a mean follow-up period of 23.5 months. Clinical outcomes, including operative time, blood loss, perioperative complications, postoperative time of hospitalization, neurologic status improvement, back pain and correction of local kyphosis, were investigated by comparing these data with the results from patients who underwent the anterior transthoracic approach for TLDH during the same period. The patients＇ neurologic status was evaluated by a modified Japanese Orthopedic Association （JOA） scoring system of 11 points. Neurologic status improvement after the surgery was assessed by calculating the recovery rate, which was equal to the （postoperative JOA score-preoperative JOA score）/（11-preoperativ

关键词： thoracolumbar disc herniation circumspinal decompression thoracic spine

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Potential role and therapeutic implications of glutathione peroxidase 4 in the treatment of Alzheimer's disease

引用

Neural Regeneration Research 2025年第3期20卷 613-631页

作者： Yanxin Shen Guimei Zhang Chunxiao wei Panpan Zhao Yongchun Wang Mingxi li li Sun Department of Neurology and Neuroscience Center The First Hospital of Jilin UniversityJilin UniversityChangchunJilin ProvinceChina Cognitive Impairment Center Department of NeurologyThe First Hospital of Jilin UniversityJilin UniversityChangchunJilin ProvinceChina

Alzheimer's disease is an age-related neurodegenerative disorder with a complex and incompletely understood pathogenesis. Despite extensive research, a cure for Alzheimer's disease has not yet been found. Oxidative stress mediates excessive oxidative responses, and its involvement in Alzheimer's disease pathogenesis as a primary or secondary pathological event is widely accepted. As a member of the selenium-containing antioxidant enzyme family, glutathione peroxidase 4 reduces esterified phospholipid hydroperoxides to maintain cellular redox homeostasis. With the discovery of ferroptosis, the central role of glutathione peroxidase 4 in anti-lipid peroxidation in several diseases, including Alzheimer's disease, has received widespread attention. Increasing evidence suggests that glutathione peroxidase 4 expression is inhibited in the Alzheimer's disease brain, resulting in oxidative stress, inflammation, ferroptosis, and apoptosis, which are closely associated with pathological damage in Alzheimer's disease. Several therapeutic approaches, such as small molecule drugs, natural plant products, and non-pharmacological treatments, ameliorate pathological damage and cognitive function in Alzheimer's disease by promoting glutathione peroxidase 4 expression and enhancing glutathione peroxidase 4 activity. Therefore, glutathione peroxidase 4 upregulation may be a promising strategy for the treatment of Alzheimer's disease. This review provides an overview of the gene structure, biological functions, and regulatory mechanisms of glutathione peroxidase 4, a discussion on the important role of glutathione peroxidase 4 in pathological events closely related to Alzheimer's disease, and a summary of the advances in small-molecule drugs, natural plant products, and non-pharmacological therapies targeting glutathione peroxidase 4 for the treatment of Alzheimer's disease. Most prior studies on this subject used animal models, and relevant clinical studies are lacking. Future clinica

关键词： apoptosis ferroptosis inflammation lipid peroxidation natural plant products neurodegenerative disorder neuroprotection oxidative stress small-molecule drugs

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：