检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Kristina Mach shuwen wei Ji Woong Kim Alejandro Martin-Gomez Peiyao Zhang Jin U. Kang M. Ali Nasseri Peter Gehlbach Nassir Navab Iulian Iordachita Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore USA Augenklinik und Poliklinik Klinikum rechts der Isar der Technische Universität Munich Germany Johns Hopkins Hospital Wilmer Eye Institute Baltimore USA Chair for Computer Aided Medical Procedures Technical University of Munich Germany

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Subretinal injection (SI) is an ophthalmic surgical procedure that allows for the direct injection of therapeutic substances into the subretinal space to treat vitreoretinal disorders. Although this treatment has grown in popularity, various factors contribute to its difficulty. These include the retina’s fragile, nonregenerative tissue, as well as hand tremor and poor visual depth perception. In this context, the usage of robotic devices may reduce hand tremors and facilitate gradual and controlled SI. For the robot to successfully move to the target area, it needs to understand the spatial relationship between the attached needle and the tissue. The development of optical coherence tomography (OCT) imaging has resulted in a substantial advancement in visualizing retinal structures at micron resolution. This paper introduces a novel foundation for an OCT-guided robotic steering framework that enables a surgeon to plan and select targets within the OCT volume. At the same time, the robot automatically executes the trajectories necessary to achieve the selected targets. Our contribution consists of a novel combination of existing methods, creating an intraoperative OCT-Robot registration pipeline. We combined straightforward affine transformation computations with robot kinematics and a deep neural network-determined tool-tip location in OCT. We evaluate our framework’s capability in a cadaveric pig eye open-sky procedure and using an aluminum target board. Targeting the subretinal space of the pig eye produced encouraging results with a mean Euclidean error of 23.8μm.

关键词： Visualization Robot kinematics Pipelines Aluminum Surgery Needles Retina

来源：评论

学校读者我要写书评

暂无评论

FireSeg: A weakly supervised fire segmentation framework via pre-trained latent diffusion models

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 275卷

作者： Zhang, wei Zheng, Hongtao Li, weiran Pan, shuwen Liu, Yan Zhejiang Tech Inst Econ Digital Informat Technol Sch Hangzhou 310018 Peoples R China Univ Colorado Dept Comp Sci Boulder CO USA Hangzhou City Univ Sch Informat & Elect Engn Hangzhou 310015 Peoples R China Suzhou Caiju Intelligent Technol Co Ltd Suzhou 215332 Peoples R China Zhejiang Univ Sch Control Sci & Engn Hangzhou 310058 Peoples R China

Accurate fire segmentation is crucial for emergency fire response. However, current deep learning-based fire segmentation methods heavily rely on large-scale annotated data, and the scarcity of high-quality public datasets limits their application in practical, diverse scenarios. To address this, we propose an innovative weakly-supervised fire segmentation framework, FireSeg, which consists of two core modules: 1) a feature extraction module based on a pre-trained latent diffusion model, generating cross-attention maps through diffusion inversion and textual prompts;and 2) a Transformer decoder-based Flame-Decoder module, which progressively decodes the attention maps and outputs segmentation masks by incorporating Dynamic Focus- aware Positional Queries (DFPQ) and a High-Resolution Cross-Attention (HRCA) mechanism. Experimental results demonstrate that FireSeg significantly outperforms other models on three fully supervised datasets covering different fire scenarios. For example, on the BowFire dataset, FireSeg outperforms the secondbest model by 4.10%;on the Corsican dataset, it exceeds the second-best model by 3.83%;and on the FLAME dataset, it surpasses the second-best model by 4.24%. Additionally, FireSeg also shows a significant improvement over the second-best model on the weakly supervised FireDM dataset, which contains diverse scenes but lower-quality annotations. Notably, when only 20% of the weakly supervised data is used, FireSeg achieves a 9.23% increase in IoU. These results indicate that FireSeg not only provides excellent segmentation performance in fully supervised settings but also demonstrates strong adaptability and effectiveness in weakly supervised scenarios with limited labeled data.

关键词： Fire Segmentation Latent diffusion model Textual information Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Substrate-induced hybridization of plasmon modes in the composite nanostructure of nanodisk array/thin film for spectrum modulation

引用

NANOPHOTONICS 2024年第21期13卷 3953-3961页

作者： Liang, Yuzhang Chu, shuwen wei, Xinran wei, Haonan Cheng, Sun Han, Yi Peng, wei Dalian Univ Technol Sch Phys Dalian 116024 Peoples R China Dalian Univ Coll Phys Sci & Technol Dalian 116622 Peoples R China Shanxi Med Univ Hosp 2 Dept Anaesthesia Taiyuan 030001 Peoples R China

Hybridization coupling among plasmon modes is an effective approach to manipulate near-field properties thus optical spectral shapes of plasmonic nanostructures. Generally, mode hybridization coupling is achieved by modifying the topography and dimensions of nanostructures themselves, with few concerns about substrate-induced manipulation. Herein, we propose a composite nanostructure consisting of a gold (Au) nanodisk array and a thin Au film supported by a dielectric substrate. In this configuration, both the refractive index of the dielectric substrate and thin gold film's thickness mediate the interaction of plasmon modes supported by upper and lower interfaces of the composite nanostructure, resulting in two hybridized plasmon modes. We systematically investigate the relationship between optical fields at the top surface of plasmon modes before and after the hybridization coupling. Specifically, the near-field amplitude at the top surface of the unhybridized modes is stronger than that of individual hybridized mode, and lower than the near-field summation of these two hybridized modes. This work not only provides a straightforward strategy for generating two plasmon modes in a nanostructure but also elucidates the variation of the optical field during the hybridization process, which is of crucial significance for applications, such as upconversion enhancement and multi-resonance sensing.

关键词： plasmonic nanostructure hybridization coupling substrate-induced coupling spectral modulation biosensor

来源：评论

学校读者我要写书评

暂无评论

RSODNet: Lightweight Remote Sensing Image Object Detection Combined with BCDNS Compression Algorithm

引用

PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING 2025年第1期91卷 35-51页

作者： Zhu, Xinyu Zhang, Zhihua Wang, wei Hou, Yuhao Yang, shuwen Lanzhou Jiaotong Univ Fac Geomat Natl Local Joint Engn Res Ctr Technol & Applicat N Lanzhou Peoples R China

In recent years, with the gradual increase of neural network Params (the aggregate of trainable elements in a model, including weights, biases, and other adjustable elements) and calculation volume, model compression within an acceptable range of network accuracy variations has emerged as a prominent research focus in the field of deep learning. Model pruning and knowledge distillation have been widely used for reducing the complexity and storage cost of neural networks. This study designs the Remote Sensing Object Detection Network (RSODNet), a lightweight model for remote sensing image object detection, and proposes bridging cross-task distillation network slimming (BCDNS) as a method that integrates model pruning and knowledge distillation. The experiment results indicate that RSODNet outperforms the YOLOv8 model in various metrics while maintaining almost unchanged Params and calculation volume. The BCDNS method eliminates redundant channels while preserving a priori knowledge of the initial model intact. This study offers technical support for compressed models used in object detection from remote sensing images..

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Urban - Rural construction land Transition(URCLT) in Shandong Province of China: Features measurement and mechanism exploration

引用

HABITAT INTERNATIONAL 2019年 86卷 101-115页

作者： Qu Yanbo Jiang Guanghui Tian Yaya Shang Ran wei shuwen Li Yuling Shandong Univ Finance & Econ Sch Publ Management Jinan 250014 Shandong Peoples R China Beijing Normal Univ Fac Geog Sci Sch Nat Resources State Key Lab Earth Surface Proc & Resource Ecol Beijing 100875 Peoples R China Shandong Agr & Engn Univ Coll Environm Sci & Engn Jinan 250100 Shandong Peoples R China

The change in urban construction land (UCL) and rural residential land (RRL) and their coupling relationship are the main manifestation of urban-rural construction land transition (URCLT) and the mapping of urban-rural factor flow. It is of great significance to systematically understand and master its laws for expanding the theory of land use transition (LUT) and adjusting the man-land relationship between urban and rural area. This paper constructs a theoretical model of URCLT, analyses the spatial and temporal characteristics of urban and rural construction land (UARCL) scale, elasticity and structure transition in Shandong Province from 1996 to 2015, reveals the transition process and coupling mechanism of UCL and RRL by using the method of geographic detector. The research shows that the UCL and RRL in Shandong Province have evolved along a coordinated track of increase and decrease as a whole, but with certain periodic fluctuations, resulting in insufficient elasticity and structural transition of URCLT. The rationalization degree of UCL growth was reduced, the low synchronization and non-synchronization of RRL reduction predominates, while the dominant type of urban-rural human-land relationship changed from urban-rural (UR) increase or decrease coordinated to both urban (U) and rural (R) increase uncoordinated. The URCLT had obvious spatial differences. The UARCL in the "blue-yellow" economic zone and the provincial capital urban agglomeration was active, but was dominated by uncoordinated transition, and the non-synchronization reduction of RRL was dominant. The factors influencing the transition of URCL were complex, diverse and unstable, and the transition mechanism was the interaction process of self regulation of population, industry and land elements within the urban and rural system and intervention of external natural environment, science and technology and institutional policies.

关键词： Urban and rural construction land Land use transition Geographic detectors Mechanism Shandong province China

来源：评论

学校读者我要写书评

暂无评论

烟草PPO基因家族鉴定与不同成熟度烟叶烘烤过程中PPO活性分析

引用

中国烟草学报 2023年第3期29卷 47-56页

作者：刘银松林建枫张永毅魏恕文张炳辉顾钢汪睿琪张文伟谢小芳金辽福建省烟草公司南平市公司南平市353000 福建农林大学生命科学学院福州市350002 福建省烟草专卖局烟草科学研究所福州市350003

【背景与目的】多酚氧化酶(PPO)参与的棕色化反应是生产高品质烟草产品的关键环节,为了明确烟草中PPO基因的结构与功能。【方法】通过生物信息学的方法鉴定烟草PPO基因家族成员及其特征;利用qRT-PCR方法分析了翠碧一号上部4种成熟度烟叶... 详细信息

【背景与目的】多酚氧化酶(PPO)参与的棕色化反应是生产高品质烟草产品的关键环节,为了明确烟草中PPO基因的结构与功能。【方法】通过生物信息学的方法鉴定烟草PPO基因家族成员及其特征;利用qRT-PCR方法分析了翠碧一号上部4种成熟度烟叶(M1~M4)PPO基因的表达,并采用多酚氧化酶活性检测试剂盒测定烘烤过程中烟叶PPO酶活性变化。【结果】烟草基因组中共鉴定到12个NtPPO基因,大多数成员具有类似的基因结构、相近的蛋白长度和保守的蛋白结构域。系统进化分析将菠萝、高粱、番茄、马铃薯和烟草的PPO蛋白分为3个亚族,其中Ⅱ,Ⅲ亚族中均为双子叶植物的PPO成员。NtPPOs基因家族成员的表达量随着成熟度提高表现出不同的变化模式,大多数成员在过熟烟叶中表达量最低。烘烤过程中不同成熟度烟叶中PPO活性也存在明显差异,其中M2、M3和M4成熟期烟叶PPO活性呈现先下降后上升再下降的趋势,在45℃达到最大值,且M2>M3>M4。【结论】研究结果可为烟草PPO基因的功能研究、烟叶棕色化的调控和品种遗传改良奠定基础。

关键词：烟草多酚氧化酶基因家族酶活不同成熟度

来源：评论

学校读者我要写书评

暂无评论

Interface Manipulation of Composite Solid Polymer Electrolyte with Polydopamine to Construct Durable and Fast Li plus Conduction Pathways

引用

ACS APPLIED ENERGY MATERIALS 2023年第3期6卷 1989-2000页

作者： Chen, Sheng Wu, Yunping Niu, shuwen wei, Zhengyu Wu, Youshen wei, wei Xi An Jiao Tong Univ Sch Chem Dept Appl Chem Xian Key Lab Sustainable Energy Mat Chem Xian 710049 Peoples R China

Taking advantage of light weight, flexibility, and flame retardancy, solid polymer electrolytes (SPEs) provide a feasible solution to these safety concerns and to the enhancement of energy density for lithium-ion batteries (LIBs). However, the development of SPEs is still restricted by low ionic conductivity. Herein, we develop a type of SPE filler built by flower-like Co3O4 microspheres as a lithiophilic backbone and polydopamine (PDA) as a multifunctional coating for the engineering of the interphase properties of the polyether-based SPEs. The hierarchical structure of Co3O4 affords large interfacial contact area with SPEs and effectively suppresses the regular crystallinity of poly(ethylene oxide) (PEO) segments. Moreover, the PDA coating layers with diverse surface functionalities serve as a versatile mediator to finely tune ionic distribution and transport behavior via multiple Lewis acid-base interactions. We uncover the interphase characterizations and their synergistic effects to enhance Li+ conductivity and mechanical/electrochemical stability. This study provides intriguing alternatives for developing composite solid polymer electrolytes (CPEs), for which we further demonstrate the potential application of Co3O4@PDA-based CPEs in all-solid-state LIBs.

关键词： solid polymer electrolyte composite filler polydopamine interphase lithium-ion battery

来源：评论

学校读者我要写书评

暂无评论

Thermal Runaway Gas Generation of Lithium Iron Phosphate Batteries Triggered by Various Abusive Conditions

引用

JOURNAL OF ENERGY ENGINEERING 2024年第4期150卷 04024017-04024017页

作者： Su, Lei Yang, Fan Hu, wei Chen, shuwen Lyu, Nawei State Grid Hubei Elect Power Res Inst Wuhan 430074 Peoples R China Zhengzhou Univ Sch Elect & Informat Engn Zhengzhou 450001 Henan Peoples R China

Lithium iron phosphate (LFP) batteries are widely utilized in energy storage systems due to their numerous advantages. However, their further development is impeded by the issue of thermal runaway. This paper offers a comparative analysis of gas generation in thermal runaway incidents resulting from two abuse scenarios: thermal abuse and electrical abuse. The study initially focuses on 13-Ah lithium iron phosphate single-cell batteries. Experiments were conducted to induce thermal runaway through both forms of abuse, analyzing the production and dispersion of H2 and CO gases in each case. It was observed that thermal abuse-induced thermal runaway resulted in higher gas concentrations and more pronounced fluctuations, whereas electrical abuse-induced thermal runaway exhibited lower gas concentrations and lower fluctuations. Subsequently, key materials and temperature variations at the positive and negative electrodes were investigated under both types of thermal runaway, revealing distinct differences that are identified as the primary reasons for the significant disparities in H2 and CO gas generation during the two thermal runaway conditions. The conclusions drawn in this paper advance the understanding of the mechanisms underlying H2 and CO gas concentration generation in thermal runaway scenarios.

关键词： Lithium compounds

来源：评论

学校读者我要写书评

暂无评论

Selective retina therapy monitoring by speckle variance optical coherence tomography for dosimetry control

引用

JOURNAL OF BIOMEDICAL OPTICS 2020年第2期25卷 026001-026001页

作者： Lee, Soohyun wei, shuwen Guo, Shoujing Kim, Jongmin Kim, Bongkyun Kim, Gihoon Kang, Jin U. Johns Hopkins Univ Dept Elect & Comp Engn Baltimore MD 21218 USA Lutron Corp Goyang South Korea

Significance: Selective retina therapy (SRT) selectively targets the retinal pigment epithelium (RPE) and reduces negative side effects by avoiding thermal damages of the adjacent photoreceptors, the neural retina, and the choroid. However, the selection of proper laser energy for the SRT is challenging because of ophthalmoscopically invisible lesions in the RPE and different melanin concentrations among patients or even regions within an eye. Aim: We propose and demonstrate SRT monitoring based on speckle variance optical coherence tomography (svOCT) for dosimetry control. Approach: M-scans, time-resolved sequence of A-scans, of ex vivo bovine retina irradiated by 1.7-mu s duration laser pulses were obtained by a swept-source OCT. SvOCT images were calculated as interframe intensity variance of the sequence. Spatial and temporal temperature distributions in the retina were numerically calculated in a 2-D retinal model using COMSOL Multiphysics. Microscopic images of treated spots were obtained before and after removing the upper neural retinal layer to assess the damage in both RPE and neural layers. Results: SvOCT images show abrupt speckle variance changes when the retina is irradiated by laser pulses. The svOCT intensities averaged in RPE and photoreceptor layers along the axial direction show sharp peaks corresponding to each laser pulse, and the peak values were proportional to the laser pulse energy. The calculated temperatures in the neural retina layer and RPE were linearly fitted to the svOCT peak values, and the temperature of each lesion was estimated based on the fitting. The estimated temperatures matched well with previously reported results. Conclusion: We found a reliable correlation between the svOCT peak values and the degree of retinal lesion formation, which can be used for selecting proper laser energy during SRT. (C) The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License.

关键词： biomedical optics speckle variance optical coherence tomography selective retina therapy ophthalmology

来源：评论

学校读者我要写书评

暂无评论

UMPPI: Unveiling Multilevel Protein-Peptide Interaction Prediction via Language Models

引用

JOURNAL OF CHEMICAL INFORMATION AND MODELING 2025年第7期65卷 3789-3799页

作者： Xiong, shuwen Cai, Jiajie Shi, Hua Cui, Feifei Zhang, Zilong wei, Leyi Macao Polytech Univ Fac Appl Sci Macau 999078 Peoples R China Shandong Univ Sch Software Jinan 250101 Peoples R China Xiamen Univ Technol Sch Optoelect & Commun Engn Xiamen 361005 Peoples R China Hainan Univ Sch Comp Sci & Technol Haikou 570228 Peoples R China

Protein-peptide interactions are essential to cellular processes and disease mechanisms. Identifying protein-peptide binding residues is critical for understanding peptide function and advancing drug discovery. However, experimental methods are costly and time-intensive, while existing computational approaches often predict interactions or binding residues separately, lack effective feature integration, or rely heavily on limited high-quality structural data. To address these challenges, we propose UMPPI (Unveiling Multilevel Protein-Peptide Interaction), a multiobjective framework based on the pretrained protein language model ESM2. UMPPI simultaneously predicts binary protein-peptide interactions and binding residues on both peptides and proteins through a multiobjective optimization strategy. By integrating ESM2 to encode sequences and extract latent structural information, UMPPI bridges the gap between sequence-based and structure-based methods. Extensive experiments demonstrated that UMPPI successfully captured binary interactions between peptides and proteins and identified the binding residues on peptides and proteins. UMPPI can serve as a useful tool for protein-peptide interaction prediction and identification of critical binding residues, thereby facilitating the peptide drug discovery process.

关键词： Drug interactions

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：