检索结果-内蒙古大学图书馆

Citrus yield prediction using deep learning techniques: A combination of field and satellite data

Journal of Open Innovation: Technology, Market, and Complexity 2023年第2期9卷

作者： Moussaid, Abdellatif El Fkihi, Sanaa Zennayi, Yahya Kassou, Ismail Bourzeix, François Lahlou, Ouiam El Mansouri, Loubna Imani, Yasmina Information Retrieval and Data Analytics Group ADMIR Laboratory Rabat IT Center ENSIAS Mohammed V University in Rabat Rabat 10000 Morocco Embedded Systems and Artificial Intelligence Department Moroccan Foundation for Advanced Science Innovation and Research Rabat 10100 Morocco Hassan II Institute of Agronomy and Veterinary Morocco

The goal of this paper is to develop a deep learning model for predicting citrus yield. The data used consists of two sources: (1) field data that includes information on fertilization and phytosanitary treatment products, water quantities used for irrigation, climatic data (temperature, precipitation, humidity, wind speed, and solar radiation), parcel sizes, and rootstock types for each parcel. (2) The second source comprises images representing the normalized difference vegetation index (NDVI) and the normalized difference water index (NDWI), extracted from Sentinel-2 images taken before the harvest period. The data was collected over a period of 5 years, from 2015 to 2019, and pertains to 50 parcels within a Moroccan orchard. Following data preparation, we constructed a deep learning neural network model with multiple layers and parameters. This model takes the information from each parcel as input for training purposes. Subsequently, we evaluated the model using new data obtained from additional parcels located at various sites within our orchard. The test phase resulted in the following scores: 0.0458 (Mean Squared Error), 0.1450 (Mean Absolute Error), and 0.10 (Percentage Error). These scores reflect the strong predictive capability of our approach. © 2023 The Author(s)

关键词： Citrus yield prediction Deep learning Machine learning Open innovation Precision farming Spectral data

来源：评论

学校读者我要写书评

暂无评论

Uncovering Android Zero-Day Threats: The Zero-Vuln Approach with Deep and Zero-Shot Learning

Uncovering Android Zero-Day Threats: The Zero-Vuln Approach ...

引用

Computing and data analytics (ICCDA), International Conference on

作者： Suresh Palarimath Pyingkodi Maran Wilfred Blessing N. R S. J Kavitha Cibi. A Subitha G. Sutherlin College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Sultanate of Oman Department of Computer Applications Kongu Engineering College Erode India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Sultanate of Oman Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai India Data & Analytics / Visualization - Delivery Virtusa Consulting Services Private Limited Chennai India Department of Computer Science and Engineering Stella Mary's College of Engineering Kanyakumari India

ISBN: (数字)9798331542573

ISBN: (纸本)9798331542580

The growing occurrence of cybersecurity hazards, such as Android zero-day vulnerabilities, poses substantial difficulties because they are unattended and imperceptible. With the increasing popularity of Android smartphones, hackers are taking advantage of these weaknesses to quickly spread advanced malware. Conventional detection approaches frequently prove inadequate due to the absence of shown criteria for emergent threats. In order to address this crucial problem, this article presents the Zero-Vuln method, an advanced technique specifically developed to identify and categorize previously unidentified malware on Android platforms. Zero-Vuln combines sophisticated supervised deep learning methods with zero-shot learning algorithms to accurately detect zero-day threats. Through the utilization of comprehensive datasets, the method attains an average classification metric score of 84.22%, showcasing exceptional accuracy, precision, and recall. This advanced solution significantly improves the ability to identify and handle Android zero-day threats, representing a major progress in cybersecurity research and implementation. The Zero-Vuln strategy provides a strong and adaptable solution for the constantly changing mobile security risks, representing a notable advancement in the sector.

关键词： Measurement Instruments Zero shot learning Malware Mobile security Hazards Reliability Protection Smart phones Research and development

来源：评论

学校读者我要写书评

暂无评论

Automated Pipeline for Regional Epicardial Adipose Tissue Distribution Analysis in the Left Atrium 15th

Automated Pipeline for Regional Epicardial Adipose Tissue Di...

引用

15th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2024, Held in Conjunction with MICCAI 2024

作者： Lluch, Èric Castañeda, Eduardo Weiss, Maximilian E. R. Vizitiu, Anamaria Jacob, Athira Jami, Jitin Audigier, Chloé Meister, Felix Mihalef, Viorel Passerini, Tiziano Siemens Healthineers Digital Technologies and Innovation Erlangen Germany Pattern Recognition Lab Department of Computer Science Friedrich-Alexander University Erlangen-Nürnberg Erlangen Germany Siemens SRL Brasov Romania Siemens Healthineers Digital Technology and Innovation Princeton United States Machine-Learning and Data Analytics Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Advanced Clinical Imaging Technology Siemens Healthineers AG Lausanne Switzerland

ISBN: (纸本)9783031877551

Atrial fibrillation (AF) is the most common cardiac arrhythmia, affecting approximately 3% of the global population and rising to 11% in individuals over 80 years old. The distribution of epicardial adipose tissue (EAT) around the atria plays a significant role in the pathophysiology of AF, yet its regional analysis remains underexplored. This paper introduces an automated pipeline capable of segmenting 14 atrial regions from patient CT angiograms, a notable advancement over previous attempts to automate the creation of synthetic anatomical or physics-based twins. Our fully automatic pipeline requires no human supervision and provides the regional EAT quantification successfully on 91.9% of the analyzed patients for which the LA and its structures were automatically segmented (1797 out of 1954 patients), including the automatic segmentation of the aorta and pericardium to assess EAT volume around the left atrium. By applying principal component analysis of the regional EAT to analyze a separate dataset of 84 individuals who were clinically labeled, we identified a distinct group that contained all the patients with AF. This finding suggests that there is a significant link between the pattern of fat distribution and AF. This novel approach has the potential to enhance our understanding of AF and improve patient outcomes by enabling large-scale, regional fat analysis in an automated manner on all patients with accurate segmentation of left atrial structures. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vehicles: Steering the Future of Transportation with Self-Driving Technology and advanced AI Systems

Autonomous Vehicles: Steering the Future of Transportation w...

引用

Global Conference for Advancement in Technology (GCAT)

作者： Daniel Nareshkumar. M Desidi Narsimha Reddy A. Sowmiya V. Samuthira Pandi Rayala Sateesh N. Hindumathy Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS University Chennai Tamil Nadu India Data Consultant (Data Governance Data Analytics: Enterprise Performance Management AI&ML) Soniks Consulting LLC Texas USA Department of EEE Rajalakshmi Engineering College Chennai Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamil Nadu India Department of ECE MLR Institute of Technology Hyderabad Department of Artificial Intelligence and Machine Learning Vel Tech Rangarajan Dr.Sagunthala R & D Institute of Science and Technology Chennai

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Autonomous vehicles (AVs) are a game-changer in the transportation industry; they will alter cityscapes, cut down on accidents, and reimagine how people experience mobility. This study investigates the complex relationship between autonomous vehicles and high-tech AI systems, looking at how these two technologies can influence transportation in the future. The paper highlights crucial developments in sensor fusion, machine learning algorithms, and real-time data processing that are essential for the development of fully autonomous systems by analyzing the present status of AV technology. In the first part of the study, the basic technologies that support AVs are described. These technologies include LiDAR, radar, cameras, and GPS. When taken together, they allow AVs to perceive their surroundings and locate themselves. After that, it delves into how AI is helping AVs understand sensor data, make judgments in real-time, and carry out complicated maneuvers, showcasing how advancements in deep learning, neural networks, and predictive analytics are powering these capabilities. Integrating AVs into current transportation infrastructures presents both potential and obstacles, which the paper delves into. Critical situation safety, legal frameworks, cybersecurity risks, and AI decision-making ethics are all covered. In addition to the environmental advantages of improved traffic flow and decreased emissions, the study delves into the possible socioeconomic implications, including shifts in urban design, public transit, and the labor market. The research delves into the existing deployment tactics and the path for scaling AV operations through a thorough analysis of case studies, pilot projects, and industry reports. It determines how prepared different groups are to accept this revolutionary technology, including the general public, lawmakers, and manufacturers. To sum up, the study highlights how important it is for academic institutions, business executives, and governm

关键词： Ethics Machine learning algorithms Urban planning Decision making Sensor fusion data processing Real-time systems Safety Computer security Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Contamination, biofilm formation, virulence and molecular characterization of multi–drug resistant Staphylococcus aureus isolated from pork under low temperature in Zhejiang Province, China

SSRN

引用

SSRN 2025年

作者： Zhai, Ruidong Liang, Yilun Lei, Lei Xu, Xinlu Wu, Qin Han, Yue Deng, Simin Xu, Jiali Xia, Jing Yang, Yongchun Cocolin, Luca Simone Rantsiou, Kalliopi Cheng, Changyong Song, Houhui Key Laboratory of Applied Biotechnology on Animal Science & Veterinary Medicine of Zhejiang Province Zhejiang Engineering Research Center for Veterinary Diagnostics & Advanced Technology Zhejiang International Science and Technology Cooperation Base for Veterinary Medicine and Health Management Belt and Road International Joint Laboratory for One Health and Food Safety China-Australia Joint Laboratory for Animal Health Big Data Analytics College of Veterinary Medicine of Zhejiang Agricultural and Forestry University Zhejiang Province Hangzhou China Department of Agricultural Forest and Food Sciences University of Turin Torino Italy

Staphylococcus aureus is considered to be an increasingly food safety concern. Low temperature is usually used to limit bacterial reproduction on meat. The aim of this study was to investigate the contamination and characterization about S. aureus on pork under low temperature at cold storage warehouses in Zhejiang Province, China. A total of 344 samples were collected to detect S. aureus, and All 52 S. aureus were isolated from 11.6% samples with present in 18 batches from 13 cold storage warehouses, of note, 51.9% isolates was enterotoxigenic, and 71.2% isolates were multi-drug resistant strains with strong biofilm formation, notably, 13 MRSA. Moreover, all 52 isolates were classified into 10 clusters of RAPD with 13 SPA types, especially the new frequently Spa-t20663. And ST398, ST188, ST6 types were ranked among the top three accompanied by close genetic relationships with other food-borne S. aureus in China. In addition, high virulence isolates were observed on Galleria mellonella, and ST188 S. aureus with skin abscesses in rabbits. Findings from this study highlight the contamination, long-term survival, virulence and diverse molecular characteristics of multi-drug resistant S. aureus isolated from frozen pork. Therefore, integrated surveillance and control measures are urgent to mitigate the associated risk. © 2025, The Authors. All rights reserved.

关键词： Meats

来源：评论

学校读者我要写书评

暂无评论

Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis

arXiv

引用

arXiv 2021年

作者： Yang, Linyi Li, Jiazheng Cunningham, Pádraig Zhang, Yue Smyth, Barry Dong, Ruihai The Insight Centre for Data Analytics University College Dublin Ireland School of Computer Science University College Dublin Ireland School of Engineering Westlake University China Institute of Advanced Technology Westlake Institute for Advanced Study China

While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that may exist in their training and test data. Such issues come to be manifest in performance problems when faced with out-of-distribution data in the field. One recent solution has been to use counterfactually augmented datasets in order to reduce any reliance on spurious patterns that may exist in the original data. Producing high-quality augmented data can be costly and time-consuming as it usually needs to involve human feedback and crowdsourcing efforts. In this work, we propose an alternative by describing and evaluating an approach to automatically generating counterfactual data for the purpose of data augmentation and explanation. A comprehensive evaluation on several different datasets and using a variety of state-of-the-art benchmarks demonstrate how our approach can achieve significant improvements in model performance when compared to models training on the original data and even when compared to models trained with the benefit of human-generated augmented data. © 2021, CC BY-NC-SA.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Current and forecasted 10-year prevalence and incidence of inflammatory bowel disease in Hong Kong,Japan,and the United States

引用

World Journal of Gastroenterology 2025年第18期31卷 32-51页

作者： Yin Zhang Hsingwen Chung Qi-Wen Fang You-Ran Xu Yong-Jing Zhang Ko Nakajo Ian Chi-Kei Wong Wai-Keung Leung Hong Qiu Xue Li Department of Medicine School of Clinical MedicineLi Ka Shing Faculty of MedicineThe University of Hong KongHong Kong 999077China Centre for Safe Medication Practice and Research Department of Pharmacology and PharmacyLi Ka Shing Faculty of MedicineThe University of Hong KongHong Kong 999077China Global Epidemiology Janssen Research and DevelopmentLLCTitusvilleNJ 08560United States Global Epidemiology Janssen Research and DevelopmentLLCShanghai 200233China Global Epidemiology Janssen Research and DevelopmentLLCTokyo 103-0014Japan Advanced Data Analytics for Medical Science Limited Hong Kong 999077China Aston Pharmacy School Aston UniversityBirmingham B47ETUnited Kingdom Laboratory of Data Discovery for Health Hong Kong Science ParkHong Kong 999077China

BACKGROUND The rising incidence of inflammatory bowel disease(IBD)globally has increased disease burden and economic *** remain in understanding the IBD burden between Asian and Western *** To estimate the current and following 10-year prevalence and incidence of IBD in Hong Kong,Japan,and the United *** Patients diagnosed with IBD were identified from a territory-wide electronic medical records database in Hong Kong(2003-2022,including all ages)and two large employment-based healthcare claims databases in Japan and the United States(2010-2022,including<65 age).We used Autoregressive Integrated Moving Average models to predict prevalence and incidence from 2023 to 2032,stratified by disease subtype[ulcerative colitis(UC);Crohn’s disease(CD)],sex,and age,with 95%prediction intervals(PIs).The forecasted annual average percentage change(AAPC)with 95%confidence intervals was *** The age-standardized prevalence of IBD for 2032 is forecasted at 105.88 per 100000 in Hong Kong(95%PI:83.01-128.75,AAPC:5.85%),645.79 in Japan(95%PI:562.51-741.39,AAPC:5.78%),and 629.85 in the United States(95%PI:569.09-690.63,AAPC:2.85%).Prevalence is estimated to rise most significantly among those under 18 in Japan and the United *** the next decade,the incidence of IBD is estimated to increase annually by 3.3%in Hong Kong with forecasted increases across all age groups(although the AAPC for each group is not statistically significant);by 2.88%in Japan with a significant rise in those under 18 and stability in 18-65;and remaining stable in the United *** 2032,the prevalence of CD is estimated to surpass UC in Hong Kong and the United States,whereas UC will continue to be more prevalent in Japan.A higher prevalence and incidence of IBD is forecast for males in Hong Kong and Japan,whereas rates will be similar for both males and females in the United *** The prevalence of IBD is forecasted to increase in Hong Kong,Japan,a

关键词： Inflammatory bowel disease Crohn’s disease Ulcerative colitis Epidemiology Forecast modeling

来源：评论

学校读者我要写书评

暂无评论

Dual template using P123-gelatin for synthesized large mesoporous silica for enhanced adsorption of dyes

引用

South African Journal of Chemical Engineering 2023年 43卷 312-326页

作者： Safitri, Widiya Nur Habiddin, Habiddin Ulfa, Maria Trisunaryanti, Wega Bahruji, Hasliza Holilah, Holilah Rohmah, Alya Awinatul Sholeha, Novia Amalia Jalil, Aishah Abdul Santoso, Eko Prasetyoko, Didik Department of Chemistry Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember East Java Keputih Sukolilo Surabaya 60111 Indonesia Chemistry Education Study Program Faculty of Teacher Training and Education Universitas Sebelas Maret Jl. Ir. Sutami 36A Surakarta 57126 Indonesia Department of Chemistry Faculty of Science Universitas Gadjah Mada Sekip Utara Sleman Indonesia Centre for Advanced Material and Energy Sciences Universiti Brunei Darussalam Bandar Seri Begawan BE 1410 Brunei Darussalam Research Center for Biomass and Bioproducts National Research and Innovation Agency of Indonesia (BRIN) Cibinong 16911 Indonesia Department of Food Science and Technology Faculty of Agriculture Halu Oleo University Indonesia College of Vocational Studies Bogor Agricultural University (IPB University) Jalan Kumbang No. 14 Bogor 16151 Indonesia Department of Chemical Engineering Faculty of Chemical and Energy Engineering Universiti Teknologi Malaysia 81310 UTM Johor Skudai Johor Bahru Malaysia

Mesoporous Silica with a large mesopore channel was synthesized using the sol-gel method for dye adsorption. A dual template consisting of P123 and gelatin at different ratios was employed in the sol-gel synthesis to enhance surface area and mesopore diameter. Gelatin is a green pore directing agent that strengthens P123 thermal stability during the calcination of silicate gel. Optimization of P123:gelatin ratio to 1:0.02 increased the surface area of mesoporous silica to 561.9 m²/g and expanded the pore diameter to 10 nm. The large pore diameter and surface area enhanced methylene blue adsorption capacity to 363.63 mg/g. The adsorption of methylene blue on mesoporous silica follows the pseudo second-order kinetic and the Langmuir model. Regeneration studies using thermal and chemical treatments exhibited the potential of mesoporous silica as an adsorbent for multiple adsorption-desorption of dyes. © 2022 The Author(s)

关键词： Dual template Dye Gelatin Mesoporous silica Pluronic P123

来源：评论

学校读者我要写书评

暂无评论

Incipient fault detection based on Just-in-time-learning and wavelet transform for DAB DC-DC converter

Incipient fault detection based on Just-in-time-learning and...

引用

第33届中国控制与决策会议

作者： Yu Zhang Xianghua Wang Rui Yang College of Electrical Engineering and Automation Shandong University of Science and Technology School of Advanced Technology Xi'an Jiaotong-Liverpool University Research Institute of Big Data Analytics Xi'an Jiaotong-Liverpool University

In this paper,a novel fault detection method for incipient fault occurring in Dual-active-bridge(DAB) DCDC converter is *** incipient fault has the characteristics of small amplitude,weak influence on system performances and easily being covered by noise,hence it is difficult to detect incipient fault for DAB DC-DC *** work proposes to use wavelet transform to process data,which can amplify the fault feature and simultaneously weak the *** then Just-in-time-learning(JITL) algorithm is utilized to model the system dynamic process online,followed by singular-value-decomposition(SVD) and covariance *** threshold is obtained when applying the proposed method to the normal data,and then to the test data in order to get its covariance,which when is larger than the threshold,an alarm will be triggered to imply the fault ***,establish a simulation model in the Matlab environment,and analyze the experimental results to verify the effectiveness of the proposed method.

关键词： Dual-Active-Bridge DC-DC Converter Incipient Fault Just-In-Time-Learning Singular-Value-Decomposition Covariance

来源：评论

学校读者我要写书评

暂无评论

Selenium nanoparticles alleviates cadmium induced hepatotoxicity by inhibiting ferroptosis and oxidative stress in vivo and in vitro

引用

Chemosphere 2024年 364卷 143004页

作者： Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui College of Veterinary Medicine Zhejiang A&F University Zhejiang Hangzhou311300 China Key Laboratory of Applied Technology on Green-Eco-Healthy Animal Husbandry of Zhejiang Province Zhejiang Hangzhou311300 China Zhejiang Provincial Engineering Research Center for Animal Health Diagnostics & Advanced Technology Zhejiang Hangzhou311300 China Zhejiang International Science and Technology Cooperation Base for Veterinary Medicine and Health Management Zhejiang Hangzhou311300 China China-Australia Joint Laboratory for Animal Health Big Data Analytics Zhejiang Hangzhou311300 China

Cadmium (Cd) is an important environmental toxicant that could cause serious damage to various organs including severe hepatotoxicity in intoxicated animals. Selenium has been reported to possess the protective effects against Cd toxicity, but the specific mechanism is still unclear. The purpose of this study was to explore the effects and mechanism of chitosan coated selenium nanoparticles (CS-SeNPs) against Cd-induced hepatotoxicity in animal and cellular models. ICR mice and rat hepatocyte BRL-3A cells were exposed to cadmium chloride (CdCl2) to evaluate the therapeutic efficiency of CS-SeNPs. Analysis of histopathological images, mitochondrial membrane potential (MMP) and ultramicrostructure, serum liver enzyme activities, ferroptosis-related indicators contents, and further molecular biology experiments were performed to investigate the underlying mechanisms. In vivo experiment results showed that CdCl2 caused significant pathological damage involving significant increase of liver index, contents of tissue MDA and serum ALT and AST, and significant decrease of serum GSH-Px activity. Moreover, CdCl2 exposure upregulated ACSL4 and HO-1 protein levels, downregulated GPX4, TfR1, ferritin protein levels in the liver. Notably, CS-SeNPs increased the expression level of GPX4 and ameliorated CdCl2-induced changes in above-mentioned indicators. In vitro experimental results showed that treatment with CS-SeNPs significantly elevated GSH-Px activity and GPX4 protein level, reversed CdCl2-induced expression of several ferroptosis-related proteins TfR1, FTH1 and HO-1, and repressed ROS production and increased MMP of the cells exposed to CdCl2. Our research indicated that CdCl2 induced hepatocyte injury by inducing ferroptosis, while CS-SeNPs can inhibit ferroptosis and reduce the degree of hepatocyte injury. This study is of great significance for further revealing the mechanism of Cd hepatotoxicity and expanding the clinical application of SeNPs. © 2024

关键词： Chlorine compounds

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：