Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454475
M. M. Hassan, M. N. Marsono
Peer-to-peer (P2P) traffic consumes a significant chunk of Internet bandwidth that requires effective control. This work proposes a novel hybrid heuristics-statistical approach to classify P2P traffic. Heuristics approach provides highly accurate P2P detection, although it involves measuring and analyzing of many correlations between packets and flows for certain duration of time, which make it inapplicable for online P2P traffic classification. On the other hand, statistical classification can classify traffic in an online manner although it needs periodical, often manual, retraining. The proposed hybrid solution merges these two approaches: offline heuristics learning corpus generation and online statistical classification. In the first part, heuristics are used to classify traffic flows into three classes, two which are later used for training the online statistical classifier. This work presents an enhancement on the existing heuristics P2P classification by adding a new class for unknown traffic. Analyses on the offline traces using the improved heuristics show that the addition of the third class reduces the class noise from 7% to 2%, hence, providing quality examples to retrain the online statistical classifier. For the second part, machine learning (ML) algorithms are used to classify traffic on the fly based on the flows and packets statistics. Using examples generated by the heuristics classifier, the overall statistical classification accuracy is 99% based on analysis on downloaded and captured traces.
{"title":"A hybrid heuristics-statistical peer-to-peer traffic classifier","authors":"M. M. Hassan, M. N. Marsono","doi":"10.1109/ICCSII.2012.6454475","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454475","url":null,"abstract":"Peer-to-peer (P2P) traffic consumes a significant chunk of Internet bandwidth that requires effective control. This work proposes a novel hybrid heuristics-statistical approach to classify P2P traffic. Heuristics approach provides highly accurate P2P detection, although it involves measuring and analyzing of many correlations between packets and flows for certain duration of time, which make it inapplicable for online P2P traffic classification. On the other hand, statistical classification can classify traffic in an online manner although it needs periodical, often manual, retraining. The proposed hybrid solution merges these two approaches: offline heuristics learning corpus generation and online statistical classification. In the first part, heuristics are used to classify traffic flows into three classes, two which are later used for training the online statistical classifier. This work presents an enhancement on the existing heuristics P2P classification by adding a new class for unknown traffic. Analyses on the offline traces using the improved heuristics show that the addition of the third class reduces the class noise from 7% to 2%, hence, providing quality examples to retrain the online statistical classifier. For the second part, machine learning (ML) algorithms are used to classify traffic on the fly based on the flows and packets statistics. Using examples generated by the heuristics classifier, the overall statistical classification accuracy is 99% based on analysis on downloaded and captured traces.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131426061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454358
A. Alhammad, F. Siewe, A. Al-Bayatti
This paper presents a novel vehicle ad hoc network (VANET) based on an on-street parking system that exploits the concept of InfoStations (ISs) and context-aware systems to locate and reserve a parking space. All parking zones have an assigned IS that provides wireless coverage to that parking zone. Thus, the parking details are available over dedicated short-range communication (DSRC) via the IS. Vehicles can request and reserve a preferred parking space using wireless capabilities while still moving. Because parking zones are generally distributed according to street (area) names, the architecture in this paper recommends centralised IS, which monitors and controls the geographically intermittent area-wise parking zones.
{"title":"An InfoStation-based context-aware on-street parking system","authors":"A. Alhammad, F. Siewe, A. Al-Bayatti","doi":"10.1109/ICCSII.2012.6454358","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454358","url":null,"abstract":"This paper presents a novel vehicle ad hoc network (VANET) based on an on-street parking system that exploits the concept of InfoStations (ISs) and context-aware systems to locate and reserve a parking space. All parking zones have an assigned IS that provides wireless coverage to that parking zone. Thus, the parking details are available over dedicated short-range communication (DSRC) via the IS. Vehicles can request and reserve a preferred parking space using wireless capabilities while still moving. Because parking zones are generally distributed according to street (area) names, the architecture in this paper recommends centralised IS, which monitors and controls the geographically intermittent area-wise parking zones.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131817904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454392
B. Neupane, K. Perera, Z. Aung, W. Woon
A deregulated electricity market is one of the keystones of up-and-coming smart grid deployments. In such a market, forecasting electricity prices is essential to helping stakeholders with the decision making process. Electricity price forecasting is an inherently difficult problem due to its special characteristics of dynamicity and nonstationarity. In our research, we use an Artificial Neural Network (ANN) model on carefully crafted input features for forecasting hourly electricity prices for the next 24 hours. The input features are selected from a pool of features derived from information such as past electricity price data, weather data, and calendar data. A wrapper method for feature selection is used in which the ANN model is continuously trained and updated in order to select the best feature set. The performance of the proposed method is evaluated and compared with the published results of the state-of-the-art Pattern Sequence-based Forecasting (PSF) method on the same data sets and our method is observed to provide superior results.
{"title":"Artificial Neural Network-based electricity price forecasting for smart grid deployment","authors":"B. Neupane, K. Perera, Z. Aung, W. Woon","doi":"10.1109/ICCSII.2012.6454392","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454392","url":null,"abstract":"A deregulated electricity market is one of the keystones of up-and-coming smart grid deployments. In such a market, forecasting electricity prices is essential to helping stakeholders with the decision making process. Electricity price forecasting is an inherently difficult problem due to its special characteristics of dynamicity and nonstationarity. In our research, we use an Artificial Neural Network (ANN) model on carefully crafted input features for forecasting hourly electricity prices for the next 24 hours. The input features are selected from a pool of features derived from information such as past electricity price data, weather data, and calendar data. A wrapper method for feature selection is used in which the ANN model is continuously trained and updated in order to select the best feature set. The performance of the proposed method is evaluated and compared with the published results of the state-of-the-art Pattern Sequence-based Forecasting (PSF) method on the same data sets and our method is observed to provide superior results.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123382194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454505
M. Qasim, W. Woon, Z. Aung, V. Khadkikar
An intelligent edge detection method is proposed. The method is based on the use of pattern recognition and machine learning techniques to combine the outputs of multiple edge detection algorithms. In this way, the limitations of the individual edge detectors can be overcome and performance enhancement is achieved. Two widely used classification algorithms, the Naive Bayes Classifier and the Multi-layer Perceptron, were selected for the learning task. The proposed system was evaluated on artificial and real images. A simple class labeling system based on the output of all edge detectors is suggested to provide controllability between detection sensitivity and noise resistance. Principal Component Analysis was performed to reduce computational burden and improve detection accuracy. The method is shown to achieve a practical compromise between detection sensitivity, computational complexity, and noise immunity.
{"title":"Intelligent edge detector based on multiple edge maps","authors":"M. Qasim, W. Woon, Z. Aung, V. Khadkikar","doi":"10.1109/ICCSII.2012.6454505","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454505","url":null,"abstract":"An intelligent edge detection method is proposed. The method is based on the use of pattern recognition and machine learning techniques to combine the outputs of multiple edge detection algorithms. In this way, the limitations of the individual edge detectors can be overcome and performance enhancement is achieved. Two widely used classification algorithms, the Naive Bayes Classifier and the Multi-layer Perceptron, were selected for the learning task. The proposed system was evaluated on artificial and real images. A simple class labeling system based on the output of all edge detectors is suggested to provide controllability between detection sensitivity and noise resistance. Principal Component Analysis was performed to reduce computational burden and improve detection accuracy. The method is shown to achieve a practical compromise between detection sensitivity, computational complexity, and noise immunity.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130231748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454330
A. Darwish, Emad Bataineh
Understanding the natural human behavior when people interact with Web browsers is essential for building more user-centric interface design that is customized based on user's perception and experience. This paper presents the first empirical study of users' interaction with security indicators in Web browsers in a controlled real life security risk. The work focuses on the natural and spontaneous behavior of the victim's eyes on several predetermined area of interest, and empirically presents users' evaluation of several online logon pages. The experiment and its results provide a quantitative evidence of the usability of visual security indicators in Internet Explorer (IE8). We first categorized a set of Websites and created phishing Web Pages using most known phishing techniques, and then a group of users from different backgrounds and age groups took the controlled experiment on an eye tracking machine. We found that the simplicity approach in Web design causes more damage rather than helping in online security, and that the current sleek design of Web pages helps users find the logon area and overlook the security indicators instead. We also found that the security certificate cue was not used by the participants to determine the legitimacy of the presented Websites.
理解人们与Web浏览器交互时的自然行为对于构建基于用户感知和经验定制的以用户为中心的界面设计至关重要。本文首次在现实生活安全风险可控的情况下，对Web浏览器中用户与安全指标的交互进行了实证研究。这项工作着重于受害者的眼睛在几个预定的兴趣区域上的自然和自发的行为，并经验地呈现了用户对几个在线登录页面的评价。该实验及其结果为Internet Explorer (IE8)中视觉安全指示器的可用性提供了定量证据。我们首先对一组网站进行了分类，并使用大多数已知的网络钓鱼技术创建了网络钓鱼网页，然后一组来自不同背景和年龄段的用户在眼动仪上进行了对照实验。我们发现，Web设计中的简单方法对在线安全没有帮助，反而造成了更多的损害，而当前Web页面的圆滑设计反而帮助用户找到登录区域，而忽略了安全指标。我们还发现，参与者没有使用安全证书提示来确定所呈现网站的合法性。
{"title":"Eye tracking analysis of browser security indicators","authors":"A. Darwish, Emad Bataineh","doi":"10.1109/ICCSII.2012.6454330","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454330","url":null,"abstract":"Understanding the natural human behavior when people interact with Web browsers is essential for building more user-centric interface design that is customized based on user's perception and experience. This paper presents the first empirical study of users' interaction with security indicators in Web browsers in a controlled real life security risk. The work focuses on the natural and spontaneous behavior of the victim's eyes on several predetermined area of interest, and empirically presents users' evaluation of several online logon pages. The experiment and its results provide a quantitative evidence of the usability of visual security indicators in Internet Explorer (IE8). We first categorized a set of Websites and created phishing Web Pages using most known phishing techniques, and then a group of users from different backgrounds and age groups took the controlled experiment on an eye tracking machine. We found that the simplicity approach in Web design causes more damage rather than helping in online security, and that the current sleek design of Web pages helps users find the logon area and overlook the security indicators instead. We also found that the security certificate cue was not used by the participants to determine the legitimacy of the presented Websites.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133536361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454594
F. S. Ayad, I. Adly, Y. El-Qattan, H. Ghali
The aim of this paper is to present an operating web application for remote experimentation. The main purpose of the development of such platform is to provide remotely accessible and controllable experiments which constitute a complete web-based laboratory. This has been achieved through two steps; 1) use of hardware development platform with a customized hardware experiment, and 2) development of a web-application service to access, control, and get back results from the experiment, and finally display these data. The proposed system has been implemented to build real hardware physics experiment for teaching Faraday's law of induction. The success of this platform enables the full development of an “eLAB” for teaching physics in undergraduate engineering education.
{"title":"Web application for remote experimentation","authors":"F. S. Ayad, I. Adly, Y. El-Qattan, H. Ghali","doi":"10.1109/ICCSII.2012.6454594","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454594","url":null,"abstract":"The aim of this paper is to present an operating web application for remote experimentation. The main purpose of the development of such platform is to provide remotely accessible and controllable experiments which constitute a complete web-based laboratory. This has been achieved through two steps; 1) use of hardware development platform with a customized hardware experiment, and 2) development of a web-application service to access, control, and get back results from the experiment, and finally display these data. The proposed system has been implemented to build real hardware physics experiment for teaching Faraday's law of induction. The success of this platform enables the full development of an “eLAB” for teaching physics in undergraduate engineering education.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123639343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454371
A. M. Sllame, A. Alasar
This paper describes a fat tree based Network-on-Chip (NOC) system. The fat tree includes processing nodes and communication switches. IP node has a message generator unit which randomly generates messages to different destinations with different packet lengths and buffering. Switches use wormhole routing with virtual channel mechanism. The switch consists of the following units: router, input/output link controllers and arbitration units. A simulator has been developed in C++ to analyze the proposed architecture. Moreover, a VHDL model for the employed algorithms has been simulated and prototyped (partially) in FPGA technology.
{"title":"An efficient switch for fat tree Network-on-Chip interconnection architecture","authors":"A. M. Sllame, A. Alasar","doi":"10.1109/ICCSII.2012.6454371","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454371","url":null,"abstract":"This paper describes a fat tree based Network-on-Chip (NOC) system. The fat tree includes processing nodes and communication switches. IP node has a message generator unit which randomly generates messages to different destinations with different packet lengths and buffering. Switches use wormhole routing with virtual channel mechanism. The switch consists of the following units: router, input/output link controllers and arbitration units. A simulator has been developed in C++ to analyze the proposed architecture. Moreover, a VHDL model for the employed algorithms has been simulated and prototyped (partially) in FPGA technology.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122332939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454616
Xiaoyun Wang, Jianping Yao, Haochen Wang
With the rapid development of the Internet, many researchers have been focused on ontology knowledge bases updating. Ontology population has played an important role in updating ontology knowledge bases. However, most domestic and foreign scholars focus on the process of ontology population, while neglecting how to detect and eliminate redundant instances and how to detect the results of population. In this paper, we proposed a mechanism based on instance matching algorithm, trying to verify the results of population, we also present an empirical analysis to verify the validity of the method.
{"title":"Redundant instances and incorrect instances detection mechanism in ontology population","authors":"Xiaoyun Wang, Jianping Yao, Haochen Wang","doi":"10.1109/ICCSII.2012.6454616","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454616","url":null,"abstract":"With the rapid development of the Internet, many researchers have been focused on ontology knowledge bases updating. Ontology population has played an important role in updating ontology knowledge bases. However, most domestic and foreign scholars focus on the process of ontology population, while neglecting how to detect and eliminate redundant instances and how to detect the results of population. In this paper, we proposed a mechanism based on instance matching algorithm, trying to verify the results of population, we also present an empirical analysis to verify the validity of the method.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128073551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454533
Fahimeh Salimi, Hadi Farzin, Farzad Ebrahimi
In this work, a novel method for skin detection in color images is proposed. For this purpose, three different types of kernel functions are applied within the framework of the Generalized Discriminant Analysis (GDA) algorithm in the YCbCr color space. The performance of the resulting system is evaluated using the Compaq database. Our experiments show that by adopting the proposed approach, the correct detection rate of the skin detection system will improve.
{"title":"A novel skin detection method using Generalized Discriminant Analysis","authors":"Fahimeh Salimi, Hadi Farzin, Farzad Ebrahimi","doi":"10.1109/ICCSII.2012.6454533","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454533","url":null,"abstract":"In this work, a novel method for skin detection in color images is proposed. For this purpose, three different types of kernel functions are applied within the framework of the Generalized Discriminant Analysis (GDA) algorithm in the YCbCr color space. The performance of the resulting system is evaluated using the Compaq database. Our experiments show that by adopting the proposed approach, the correct detection rate of the skin detection system will improve.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129507005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/ICCSII.2012.6454625
Y. Salih-Alj, F. Gagnon, R. Landry
In this paper, a novel structure of GPS receiver is proposed. The considered GPS acquisition system leverages a systolic-based array structure of regular and simple locally-connected processing-elements (PEs). The new GPS scheme is simulated and its complexity is evaluated for a real-time implementation on a field programmable gate array (FPGA). The suggested systolic-based acquisition system promises high performance for GPS receivers by yielding greatly improved processing latency and estimation precision while offering an efficient and flexible implementation of a significantly reduced complexity of a fully pipelined architecture.
{"title":"A systolic-based architecture for a novel reduced-complexity GPS receiver","authors":"Y. Salih-Alj, F. Gagnon, R. Landry","doi":"10.1109/ICCSII.2012.6454625","DOIUrl":"https://doi.org/10.1109/ICCSII.2012.6454625","url":null,"abstract":"In this paper, a novel structure of GPS receiver is proposed. The considered GPS acquisition system leverages a systolic-based array structure of regular and simple locally-connected processing-elements (PEs). The new GPS scheme is simulated and its complexity is evaluated for a real-time implementation on a field programmable gate array (FPGA). The suggested systolic-based acquisition system promises high performance for GPS receivers by yielding greatly improved processing latency and estimation precision while offering an efficient and flexible implementation of a significantly reduced complexity of a fully pipelined architecture.","PeriodicalId":281140,"journal":{"name":"2012 International Conference on Computer Systems and Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115703912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：