检索结果-内蒙古大学图书馆

18th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Basulo-Ribeiro, Juliana Matos, Nádia C. G. Araujo, Sabrina Magalhães Capela, Nuno Bischoff, Francisco Teixeira, Leonor Cruz-Correia, Ricardo University of Aveiro Aveiro Portugal Faculty of Medicine University of Porto Porto Portugal Faculty of Medicine of the University of Porto Health Data Science Ph.D. Program Porto Portugal CINTESIS - Center for Health Technology and Services Research Faculty of Medicine University of Porto Porto Portugal VirtualCare Portugal

With the advance of artificial intelligence and natural language processing technology, a new tool is standing out in the field of understanding and generating natural language in a sophisticated way: the Large Language Model (LLM). According to several authors, LLMs can be used for various types of medical cases, providing access to different sources of information, and have opened up countless opportunities in the healthcare sector. This work aims to share the lessons learned during the process of developing an LLM-based assistant aimed at specific pathologies that are more prevalent in the elderly in order to support caregivers, whether they are private individuals, home care organizations, nursing homes or others. This study has a significant potential impact on the community by providing access to detailed information on developing an LLM-based assistant. © 2025 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

discrete null field equation methods for solving Laplace's equation: Boundary layer computations

引用

Numerical Methods for Partial differential Equations 2024年第4期40卷 e23092-e23092页

作者： Zhang, Li-Ping Li, Zi-Cai Lee, Ming-Gong Huang, Hung-Tsai School of Mathematical Sciences Qufu Normal University Shandong Qufu China Department of Applied Mathematics National Sun Yat-sen University Kaohsiung Taiwan Department of Tourism and Leisure/Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Department of Data Science and Analytics I-Shou University Kaohsiung Taiwan

Consider dirichlet problems of Laplace's equation in a bounded simply-connected domain (Formula presented.), and use the null field equation (NFE) of Green's representation formulation, where the source nodes (Formula presented.) are located on a pseudo-boundary (Formula presented.) outside (Formula presented.) but not close to its boundary (Formula presented.). Simple algorithms are proposed in this article by using the central rule for the NFE, and the normal derivatives (Formula presented.) of the solutions on the boundary (Formula presented.) can be easily obtained. These algorithms are called the discrete null field equation method (dNFEM) because the collocation equations are, indeed, the direct discrete form of the NFE. The bounds of the condition number are like those by the method of fundamental solutions (MFS) yielding the exponential growth as the number of unknowns increases. One trouble of the dNFEM is the near singularity of integrations for the solutions in boundary layers in Green's representation formulation. The traditional BEM also suffers from the same trouble. To deal with the near singularity, quadrature by expansions and the sinh transformation are often used. To handle this trouble, however, we develop two kinds of new techniques: (I) the interpolation techniques by Taylor's formulas with piecewise (Formula presented.) -degree polynomials and the Fourier series, and (II) the mini-rules of integrals, such as the mini-Simpson's and the mini-Gaussian rules. Error analysis is made for technique I to achieve optimal convergence rates. Numerical experiments are carried out for disk domains to support the theoretical analysis made. The numerical performance of the dNFEM is excellent for disk domains to compete with the MFS. The errors with (Formula presented.) can be obtained by combination algorithms, which are satisfactory for most engineering problems. In summary, the new simple dNFEM is based on the NFE, which is different from the boundary elem

关键词： Fourier series

来源：评论

学校读者我要写书评

暂无评论

Enriching Smart Cities by Optimizing Electric Vehicle Ride-Sharing through Game Theory

Enriching Smart Cities by Optimizing Electric Vehicle Ride-S...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： darko Radakovic Anuradha Singh Aparna S. Varde Pankaj Lal Environmental Science and Management Ph.D. Program Montclair State University NJ USA Clean Energy and Sustainability Analytics Center (CESAC) Montclair State University NJ USA Department of Computer Science Montclair State University NJ USA

Pillars of smart cities include smart environment, mobility and economy. We explore impacts on these to enhance smart cities, heading towards a smart planet. Our motivation emerges from the need to decarbonize transportation. In this context, ride-sharing companies deploy electric vehicles (EVs). These should be managed by various factors: battery demand, EV charging station location, service availability, and charging time. Ride-sharing EV s aim to maximize profits via more rides. Our paper explores game theory in AI here. We propose E-Ride-Minimax, adapting the Minimax algorithm, treating EV ride-sharing companies as players. We hypothesize one player choosing its next move via total passenger-travel distance (longer the distance, larger the profit); and another player via battery usage (ratio of total passenger-travel distance to vehicle-passenger distance: optimizing this ratio enables more travel without recharging). Experimental results reveal that rising passenger numbers yield maximum battery savings (e.g. rush hours / major events); followed by stable and falling numbers. Our findings indicate that E-Ride-Minimax can reduce battery usage in some circumstances by 64%, losing 1 % profit. This is vital, given global emphasis on climate change. It increases cost-effectiveness, consumer participation and passengers per mile; reduces energy use and greenhouse gas emissions; and thus helps decarbonize transportation.

关键词： Climate change Smart cities Artificial intelligence Economics Smart devices Environmental factors Shared transport

来源：评论

学校读者我要写书评

暂无评论

Machine learning approaches for predicting 5-year breast cancer survival: A multicenter study

引用

Cancer science 2023年第10期114卷 4063-4072页

作者： Quynh Thi Nhu Nguyen phung-Anh Nguyen Chun-Jung Wang phan Thanh phuc Ruo-Kai Lin Chin-Sheng Hung Nei-Hui Kuo Yu-Wen Cheng Shwu-Jiuan Lin Zong-You Hsieh Chi-Tsun Cheng Min-Huei Hsu Jason C Hsu School of Pharmacy College of Pharmacy Taipei Medical University Taipei City Taiwan. Clinical Data Center Office of Data Science Taipei Medical University Taipei City Taiwan. Clinical Big Data Research Center Taipei Medical University Hospital Taipei Medical University Taipei City Taiwan. Research Center of Health Care Industry Data Science College of Management Taipei Medical University Taipei City Taiwan. Department of Surgery School of Medicine College of Medicine Taipei Medical University Taipei City Taiwan. Oncology Center Taipei Medical University Hospital Taipei City Taiwan. Graduate Institute of Data Science College of Management Taipei Medical University Taipei City Taiwan. International Ph.D. Program in Biotech and Healthcare Management College of Management Taipei Medical University Taipei City Taiwan.

The study used clinical data to develop a prediction model for breast cancer survival. Breast cancer prognostic factors were explored using machine learning techniques. We conducted a retrospective study using data from the Taipei Medical University Clinical Research database, which contains electronic medical records from three affiliated hospitals in Taiwan. The study included female patients aged over 20 years who were diagnosed with primary breast cancer and had medical records in hospitals between January 1, 2009 and december 31, 2020. The data were divided into training and external testing datasets. Nine different machine learning algorithms were applied to develop the models. The performances of the algorithms were measured using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score. A total of 3914 patients were included in the study. The highest AUC of 0.95 was observed with the artificial neural network model (accuracy, 0.90; sensitivity, 0.71; specificity, 0.73; PPV, 0.28; NPV, 0.94; and F1-score, 0.37). Other models showed relatively high AUC, ranging from 0.75 to 0.83. According to the optimal model results, cancer stage, tumor size, diagnosis age, surgery, and body mass index were the most critical factors for predicting breast cancer survival. The study successfully established accurate 5-year survival predictive models for breast cancer. Furthermore, the study found key factors that could affect breast cancer survival in Taiwanese women. Its results might be used as a reference for the clinical practice of breast cancer treatment.

关键词： TMUCRd breast cancer survival machine learning prediction models real-world data

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Natural-Looking Mammography Lesion Synthesis on Ipsilateral dual-Views Breast Cancer Analysis

arXiv

引用

arXiv 2023年

作者： Nguyen, Thanh-Huy Kha, Quang Hien Truong, Thai Ngoc Toan Lam, Ba Thinh Ngo, Ba Hung dinh, Quang Vinh Le, Nguyen Quoc Khanh Department of Biomedical Engineering National Cheng Kung University Taiwan International Ph.D. Program in Medicine College of Medicine Taipei Medical University Taiwan Viet Nam Ho Chi Minh City International University Viet Nam Graduate School of Data Science Chonnam National University Korea Republic of Vietnamese-German University Viet Nam Research Center for Artificial Intelligence in Medicine Taipei Medical University Taiwan Professional Master Program in Artificial Intelligence in Medicine Taiwan

In recent years, many mammographic image analysis methods have been introduced for improving cancer classification tasks. Two major issues of mammogram classification tasks are leveraging multi-view mammographic information and class-imbalance handling. In the first problem, many multi-view methods have been released for concatenating features of two or more views for the training and inference stage. Having said that, most multi-view existing methods are not explainable in the meaning of feature fusion, and treat many views equally for diagnosing. Our work aims to propose a simple but novel method for enhancing examined view (main view) by leveraging low-level feature information from the auxiliary view (ipsilateral view) before learning the high-level feature that contains the cancerous features. For the second issue, we also propose a simple but novel malignant mammogram synthesis framework for upsampling minor class samples. Our easy-to-implement and no-training framework has eliminated the current limitation of the CutMix algorithm which are unreliable synthesized images with random pasted patches, hard-contour problems, and domain shift problems. Our results on Vindr-Mammo and CMMd datasets show the effectiveness of our two new frameworks for both multi-view training and synthesizing mammographic images, outperforming the previous conventional methods in our experimental settings. © 2023, CC BY-NC-SA.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Managing the transition in cervical screening methods for Taiwan: Policy recommendations and perspectives

引用

Journal of the Formosan Medical Association 2023年第11期122卷 1213-1218页

作者： Chen, Chien-Chin Lai, Chyong-Huey Chang, Chih-Long Cheng, Wen-Fang Pwu, Raoh-Fang Tsai, Jane Wang, Peng-Hui Whang-Peng, Jacqueline Lai, Gi-Ming Department of Pathology Ditmanson Medical Foundation Chia-Yi Christian Hospital Chiayi 600 Taiwan Department of Cosmetic Science Chia Nan University of Pharmacy and Science Tainan 717 Taiwan Ph.D. Program in Translational Medicine Rong Hsing Research Center for Translational Medicine National Chung Hsing University Taichung 402 Taiwan Department of Biotechnology and Bioindustry Sciences College of Bioscience and Biotechnology National Cheng Kung University Tainan 701 Taiwan Department of Obstetrics and Gynecology Chang Gung Memorial Hospital Linkou Branch Taoyuan 333 Taiwan Chang Gung University Taoyuan 333 Taiwan Department of Medicine MacKay Medical College New Taipei City 252 Taiwan Department of Obstetrics and Gynecology MacKay Memorial Hospital Taipei 104 Taiwan Department of Obstetrics and Gynecology College of Medicine National Taiwan University Taipei 100 Taiwan School of Health Care Administration Taipei Medical University Taipei 110 Taiwan Data Science Center Fu Jen Catholic University New Taipei City 242 Taiwan Formosa Cancer Foundation Taipei 105 Taiwan Department of Obstetrics and Gynecology Taipei Veterans General Hospital Taipei 112 Taiwan National Yang Ming Chiao Tung University Taipei 112 Taiwan

Since government-provided annual cervical cytology testing for all Taiwanese women aged 30 years or older became available in 1995, both cervical cancer incidence and death have decreased significantly. However, with the 2018 introduction of the national immunization program for human papillomavirus (HPV) vaccination in all schoolgirls aged 13–15 years old, the positive predictive value of cytology testing is expected to decrease with rising vaccination rates, and therefore a transition to more sensitive HPV-based testing may be needed. This position paper, derived from discussions by a panel of experts in cervical cancer screening, provides short-, medium-, and long-term policy recommendations to manage the transition between cervical screening methods for Taiwan. The recommendations include concrete suggestions regarding testing procedures, standards, accreditation, monitoring, promotion, and implementation. It is hoped that comprehensive preparation and management of this transition will enable Taiwan to repeat the previous successes of the cervical cytology testing program. © 2023 Formosan Medical Association

关键词： Cervical cancer Cervical cytology HPV-based testing Human papillomavirus Pap smear

来源：评论

学校读者我要写书评

暂无评论

Frailty and Other Factors Associated With Early Outcomes in Middle-to Older Age Trauma Patients: A Prospective Cohort Study

引用

American Journal of Geriatric Psychiatry 2024年第2期32卷 244-255页

作者： Yeh, Tian-Shin Kang, Jiunn-Horng Littlejohns, Thomas J. Wu, Chia-Chieh Chen, Jin-Hua Piravej, Krisna Chiu, Wen-Ta Lam, Carlos Department of Physical Medicine and Rehabilitation School of Medicine College of Medicine Taipei Medical University Taipei Taiwan Department of Physical Medicine and Rehabilitation Wan Fang Hospital Taipei Medical University Taipei Taiwan Department of Epidemiology and Nutrition Harvard T. H. Chan School of Public Health Harvard University Boston MA United States Department of Physical Medicine and Rehabilitation National Taiwan University Hospital Taipei Taiwan Department of Physical Medicine and Rehabilitation College of Medicine National Taiwan University Taipei Taiwan Department of Physical Medicine and Rehabilitation Taipei Medical University Hospital Taipei Taiwan Graduate Institute of Nanomedicine and Medical Engineering College of Biomedical Engineering Taipei Medical University Taipei Taiwan International Ph.D. Program in Medicine College of Medicine Taipei Medical University Taipei Taiwan Professional Master Program in Artificial Intelligence in Medicine College of Medicine Taipei Medical University Taipei Taiwan Nuffield Department of Population Health University of Oxford Oxford United Kingdom Emergency Department Wan Fang Hospital Taipei Medical University Taipei Taiwan Department of Emergency School of Medicine College of Medicine Taipei Medical University Taipei Taiwan Graduate Institute of Data Science College of Management Taipei Medical University Taipei Taiwan Institutional Research Center Office of Data Science Taipei Medical University Taipei Taiwan Biostatistics Center Department of Medical Research Wan Fang Hospital Taipei Medical University Taipei Taiwan Department of Rehabilitation Medicine Faculty of Medicine Chulalongkorn University Bangkok Thailand Department of Chula Neuroscience Center King Chulalongkorn Memorial Hospital Bangkok Thailand Graduate Institute of Injury Prevention and Control College of Public Health Taipei Medical University Taipei Taiwan AHMC Health System Alhambra CA United States

Objectives: To prospectively investigate associations of frailty and other predictor variables with functional recovery and health outcomes in middle-aged and older patients with trauma. design: Single-center prospective cohort study. Setting: Emergency department of Wan Fang Hospital in Taiwan. Participants: Trauma patients aged 45 and older. Measurements: Frailty was assessed with the Clinical Frailty Scale (CFS). Injury mechanisms, pre-existing diseases, and fracture locations were recorded at baseline. The primary outcome was functional recovery assessed using the Barthel Index (BI). Secondary outcomes were new care needs, unscheduled return visits, and falls 3 months postinjury. Results: A total of 588 participants were included in the final analysis. For every one-point increase in the CFS, the multivariable-adjusted odds ratio (OR, 95% confidence interval [CI]) of failure to retain the preinjury BI was 1.34 (1.16–1.55);associations were consistent across levels of age and injury severities. Significant joint associations of frailty and age with poor functional recovery were observed. CFS was also associated with new care needs (OR for every one-point increase, 1.36, 95% CI, 1.17–1.58), unscheduled return visits (OR 1.26, 95% CI, 1.04–1.51), and falls (OR 1.23, 95% CI, 1.01–1.51). Other variables associated with failure to retain preinjury BI included road traffic accident and presence of hip fracture. Conclusion: Frailty was significantly associated with poor functional and health outcomes regardless of injury severity in middle-aged and older patients with trauma. Injury mechanisms and fracture locations were also significant predictors of functional recovery postinjury. © 2023 American Association for Geriatric Psychiatry

关键词： Clinical Frailty Scale Frailty functional recovery injury middle-to older age

来源：评论

学校读者我要写书评

暂无评论

Correction to: Multiplexed inhibition of immunosuppressive genes with Cas13d for combinatorial cancer immunotherapy (Nature Biotechnology, (2025), 10.1038/s41587-024-02535-2)

引用

Nature Biotechnology 2025年

作者： Zhang, Feifei Chow, Ryan d. He, Emily dong, Chuanpeng Xin, Shan Mirza, daniyal Feng, Yanzhi Tian, Xiaolong Verma, Nipun Majety, Medha Zhang, Yueqi Wang, Guangchuan Chen, Sidi Department of Genetics Yale University School of Medicine New HavenCT United States System Biology Institute Yale University West HavenCT United States Center for Cancer Systems Biology Yale University West HavenCT United States M.D.–Ph.D. Program Yale University West HavenCT United States Molecular Cell Biology Genetics and Development Program Yale University New HavenCT United States Yale College New HavenCT United States Immunobiology Program Yale University New HavenCT United States Department of Therapeutic Radiology Yale University School of Medicine New HavenCT United States Department of Neurosurgery Yale University School of Medicine New HavenCT United States Yale Comprehensive Cancer Center Yale University School of Medicine New HavenCT United States Yale Stem Cell Center Yale University School of Medicine New HavenCT United States Yale Center for Biomedical Data Science Yale University School of Medicine New HavenCT United States Key Laboratory of Multi-Cell Systems Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Shanghai China

Correction to: Nature Biotechnologyhttps://***/10.1038/s41587-024-02535-2, published online 16 January 2025. In the version of the article initially published, Sidi Chen was incorrectly associated with a present address. This has now been corrected in the HTML and PdF versions of the article. © The Author(s), under exclusive licence to Springer Nature America, Inc. 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Categorization and analysis of 14 computational methods for estimating cell potency from single-cell RNA-seq data

arXiv

引用

arXiv 2023年

作者： Wang, Qingyang Zhai, Zhiqian Lian, Qiuyu Song, dongyuan Li, Jingyi Jessica Department of Statistics and Data Science University of California Los AngelesCA90095-1554 United States Wellcome Trust Cancer Research UK Gurdon Institute University of Cambridge Cambridgeshire CambridgeCB2 1QN United Kingdom Bioinformatics Interdepartmental Ph.D. Program University of California Los AngelesCA90095-7246 United States Department of Human Genetics University of California Los AngelesCA90095-7088 United States Department of Computational Medicine University of California Los AngelesCA90095-1766 United States Department of Biostatistics University of California Los AngelesCA90095-1772 United States Radcliffe Institute for Advanced Study Harvard University CambridgeMA02138 United States

In single-cell RNA sequencing (scRNA-seq) data analysis, a critical challenge is to infer hidden cellular dynamic processes from measured static cell snapshots. To tackle this challenge, many computational methods have been developed from distinct perspectives. Besides the common perspectives of inferring pseudotime trajectories and RNA velocities, another important perspective is to estimate the differentiation potential of cells, which is commonly referred to as the "cell potency." In this review, we provide a comprehensive summary of 14 computational methods that define cell potency from scRNA-seq data under different assumptions, some of which are even conceptually contradictory. We divide these methods into three categories: average-based, entropy-based, and correlation-based methods, depending on how a method summarizes gene expression levels of a cell or cell type into a potency measure. Our review focuses on the key similarities and differences of the methods within each category and between the categories, providing a high-level intuition for each method. Moreover, we use a unified set of mathematical notations to detail the 14 methods’ methodologies and summarize their usage complexities, including the number of parameters, the number of required inputs, and the changes from the method description in publications to the method implementation in software packages. In conclusion, we regard cell potency estimation as an open question that lacks a consensus on the optimal approach, calling for benchmark datasets and studies. Through categorization and detailed description of existing methods, we aim to provide a solid foundation for future benchmark studies of cell potency estimation methods. A broader open challenge is to understand the comparative advantages of methods that infer cellular dynamics from scRNA-seq data using diverse perspectives, including pseudotime trajectories, RNA velocities, and cell potency. © 2023, CC BY-NC-Nd.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Peptide-Coated Bacteriorhodopsin-Based photoelectric Biosensor for detecting Rheumatoid Arthritis

Biosensors

引用

Biosensors 2023年第10期13卷 929-929页

作者： Chen, Hsiu-Mei Tsai, Yi-Hsuan Hsu, Chien-Yi Wang, Yong-Yi Hsieh, Cheng-En Chen, Jin-Hua Chang, Yu-Sheng Lin, Ching-Yu Department of Chemical Engineering National Taiwan University of Science and Technology Taipei10607 Taiwan Department of Family Medicine Wan Fang Hospital Taipei Medical University Taipei11696 Taiwan Division of Cardiology and Cardiovascular Research Center Department of Internal Medicine Taipei Medical University Hospital Taipei11031 Taiwan Division of Cardiology Department of Internal Medicine School of Medicine College of Medicine Taipei Medical University Taipei11031 Taiwan Taipei Heart Institute Taipei Medical University Taipei11031 Taiwan Graduate Institute of Data Science College of Management Taipei Medical University Taipei11031 Taiwan Office of Data Science Taipei Medical University Taipei11031 Taiwan Division of Allergy Immunology and Rheumatology Department of Internal Medicine Shuang Ho Hospital Taipei Medical University New Taipei City23561 Taiwan Division of Allergy Immunology and Rheumatology Department of Internal Medicine School of Medicine College of Medicine Taipei Medical University Taipei11031 Taiwan School of Medical Laboratory Science and Biotechnology College of Medical Science and Technology Taipei Medical University Taipei11031 Taiwan Ph.D. Program in Medical Biotechnology College of Medical Science and Technology Taipei Medical University Taipei11031 Taiwan

An effective early diagnosis is important for rheumatoid arthritis (RA) management. This study reveals a novel RA detection method using bacteriorhodopsin as a photoelectric transducer, a light-driven proton pump in purple membranes (PMs). It was devised by covalently conjugating a PM monolayer-coated electrode with a citrullinated-inter-alpha-trypsin inhibitor heavy chain 3 (ITIH3)542–556 peptide that recognizes the serum RA-associated autoantibodies. The direct serum coating decreased the photocurrents in the biosensor, with the reduction in the photocurrent caused by coating with an RA-patient serum that is significantly larger than that with a healthy-control serum (38.1% vs. 20.2%). The difference in the reduction in the photocurrent between those two serum groups widened after the serum-coated biosensor was further labeled with gold nanoparticle (AuNP)-conjugated anti-IgA (anti-IgA-AuNP) (53.6% vs. 30.6%). Both atomic force microscopic (AFM) and Raman analyses confirmed the sequential peptide, serum, and anti-IgA-AuNP coatings on the PM-coated substrates. The reductions in the photocurrent measured in both the serum and anti-IgA-AuNPs coating steps correlated well with the results using commercial enzyme-linked immunosorbent assay kits (Spearman rho = 0.805 and 0.787, respectively), with both a sensitivity and specificity close to 100% in both steps. It was shown that an RA diagnosis can be performed in either a single- or two-step mode using the developed biosensor. © 2023 by the authors.

关键词： Peptides

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：