We consider the problem of planning a set of tours (closed paths) through a network such that every node is at most l-hops away from at least one tour, and all tours are connected. A set of tours is called connected in this work, if there exists a path between any two nodes on the tour that is completely within the set of tours. In other words, in a connected set of of tours, we do not have to leave the tour to travel between any two tour nodes. The problem naturally involves steps related to finding extended dominating sets, travelling salesman tours and forwarding trees such that the cost of data gathering is minimized. We propose a heuristic for this problem that considers the as costs the tour length, and the multi-hop forwarding traffic. We evaluate experimentally the new heuristic for various settings, and also compare against previously proposed approaches for related data gathering problems.
{"title":"Designing Connected Tours That Almost Cover a Network","authors":"Khaled Almiani, Anastasios Viglas","doi":"10.1109/PDCAT.2013.50","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.50","url":null,"abstract":"We consider the problem of planning a set of tours (closed paths) through a network such that every node is at most l-hops away from at least one tour, and all tours are connected. A set of tours is called connected in this work, if there exists a path between any two nodes on the tour that is completely within the set of tours. In other words, in a connected set of of tours, we do not have to leave the tour to travel between any two tour nodes. The problem naturally involves steps related to finding extended dominating sets, travelling salesman tours and forwarding trees such that the cost of data gathering is minimized. We propose a heuristic for this problem that considers the as costs the tour length, and the multi-hop forwarding traffic. We evaluate experimentally the new heuristic for various settings, and also compare against previously proposed approaches for related data gathering problems.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123306042","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}
Clodoaldo Brasilino Leite Neto, Pedro Carvalho Filho, A. Duarte
Background: The large computational infrastructures required to provide the on-demand services that most users are now used to are more prone to failures than any single computational device. Thus, fault management is a essential activity in the realization of the cloud computing model. Aims: This work aims at identifying well-explored topics on fault management in cloud computing as well as pin-pointing gaps in the scientific literature that may represent opportunities for further research and development in this area. Method: We conducted a systematic mapping study to collect, filter and classify scientific works in this area. The 4535 scientific papers found on major search engines were filtered and the remaining 166 papers were classified according to a taxonomy described in this work. Results: We found that IaaS is most explored in the selected studies. The main dependability functions explored were Tolerance and Removal, and the attributes were Reliability and Availability. Most papers had been classified by research type as Solution Proposal. Conclusion: This work summarizes and classifies the research effort conducted on fault management in cloud computing, providing a good starting point for further research in this area.
{"title":"A Systematic Mapping Study on Fault Management in Cloud Computing","authors":"Clodoaldo Brasilino Leite Neto, Pedro Carvalho Filho, A. Duarte","doi":"10.1109/PDCAT.2013.59","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.59","url":null,"abstract":"Background: The large computational infrastructures required to provide the on-demand services that most users are now used to are more prone to failures than any single computational device. Thus, fault management is a essential activity in the realization of the cloud computing model. Aims: This work aims at identifying well-explored topics on fault management in cloud computing as well as pin-pointing gaps in the scientific literature that may represent opportunities for further research and development in this area. Method: We conducted a systematic mapping study to collect, filter and classify scientific works in this area. The 4535 scientific papers found on major search engines were filtered and the remaining 166 papers were classified according to a taxonomy described in this work. Results: We found that IaaS is most explored in the selected studies. The main dependability functions explored were Tolerance and Removal, and the attributes were Reliability and Availability. Most papers had been classified by research type as Solution Proposal. Conclusion: This work summarizes and classifies the research effort conducted on fault management in cloud computing, providing a good starting point for further research in this area.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125406109","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}
We consider a simple imperative language with fork/join parallelism and lexically scoped nested atomic sections from which threads can escape. In this context, our contribution is a formal operational semantics of this language that satisfies a specification on execution traces designed in a companion paper.
{"title":"Nested Atomic Sections with Thread Escape: An Operational Semantics","authors":"Frédéric Dabrowski, F. Loulergue, Thomas Pinsard","doi":"10.1109/PDCAT.2013.12","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.12","url":null,"abstract":"We consider a simple imperative language with fork/join parallelism and lexically scoped nested atomic sections from which threads can escape. In this context, our contribution is a formal operational semantics of this language that satisfies a specification on execution traces designed in a companion paper.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122593004","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}
Virtualization technology, which has the characteristic of producing dynamic change, enables the virtual network structure to no longer depend strictly on the underlying hardware environment. With virtualization platform administrators tasked with preventing attacks in order to provide uninterrupted service, existing intrusion detection technologies are continuously challenged. Consequently, this paper proposes a Centralized Administration and Dynamic Monitoring framework (CADM) based on virtualization for network intrusion detection. CADM is able to centrally administrate, and monitor network behavior in the virtual computing environment by automatically deploying and updating intrusion detection processes and rules. In the aspect of monitoring capability, CADM allows the monitoring locations in intrusion detection to be automatically adjusted in real time, thus adapting to the dynamic changes (such as migration) of virtual machines (VMs). Moreover, the monitoring processes involved in intrusion detection could also be automatically updated by dynamically updating security strategies. In the aspect of monitoring granularity, CADM is able to monitor network interfaces of each virtual machine (VM) for fine-grained network intrusion detection and network traffic acquisition. Our experimental results demonstrate that more convenient and efficient monitoring and administrating capabilities are available with CADM for virtualization platform administrators.
{"title":"CADM: A Centralized Administration and Dynamic Monitoring Framework for Network Intrusion Detection Based on Virtualization","authors":"Zhenquan Ding, Zhiyu Hao, Yongzheng Zhang","doi":"10.1109/PDCAT.2013.24","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.24","url":null,"abstract":"Virtualization technology, which has the characteristic of producing dynamic change, enables the virtual network structure to no longer depend strictly on the underlying hardware environment. With virtualization platform administrators tasked with preventing attacks in order to provide uninterrupted service, existing intrusion detection technologies are continuously challenged. Consequently, this paper proposes a Centralized Administration and Dynamic Monitoring framework (CADM) based on virtualization for network intrusion detection. CADM is able to centrally administrate, and monitor network behavior in the virtual computing environment by automatically deploying and updating intrusion detection processes and rules. In the aspect of monitoring capability, CADM allows the monitoring locations in intrusion detection to be automatically adjusted in real time, thus adapting to the dynamic changes (such as migration) of virtual machines (VMs). Moreover, the monitoring processes involved in intrusion detection could also be automatically updated by dynamically updating security strategies. In the aspect of monitoring granularity, CADM is able to monitor network interfaces of each virtual machine (VM) for fine-grained network intrusion detection and network traffic acquisition. Our experimental results demonstrate that more convenient and efficient monitoring and administrating capabilities are available with CADM for virtualization platform administrators.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117200637","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}
The training of SVM can be viewed as a Convex Quadratic Programming (CQP) problem which becomes difficult to be solved when dealing with the large scale data sets. Traditional methods such as Sequential Minimal Optimization (SMO) for SVM training is used to solve a sequence of small scale sub-problems, which costs a large amount of computation time and is hard to be accelerated by utilizing the computation power of GPU. Although Interior Point Method (IPM) such as primal-dual interior point method (PDIPM) can be also addressed SVM training well and has favourable potential for parallelizing on GPU, it contains comparatively high time complexity O(l^3) and space complexity O(l^2), where l is the number of training instances. Fortunately, by invoking low-rank approximation methods such as Incomplete Cholesky Factorization (ICF) and Sherman Morrison Woodbury formula (SMW), the requirements of both storage and computation of PDIPM can be reduced significantly. In this paper, a parallel PDIPM method (P-PDIPM) along with a parallel ICF method (P-ICF) is proposed to accelerate the SVM training on GPU. Experimental results indicate that the training speed of P-PDIPM on GPU is almost 40x faster than that of the serial one (S-PDIPM) on CPU. Besides, without extensive optimization, P-PDIPM can obtain about 8x speedup over the state of the art tool LIBSVM while maintaining high prediction accuracy.
{"title":"Efficient SVM Training Using Parallel Primal-Dual Interior Point Method on GPU","authors":"Jing Jin, Xianggao Cai, X. Lin","doi":"10.1109/PDCAT.2013.9","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.9","url":null,"abstract":"The training of SVM can be viewed as a Convex Quadratic Programming (CQP) problem which becomes difficult to be solved when dealing with the large scale data sets. Traditional methods such as Sequential Minimal Optimization (SMO) for SVM training is used to solve a sequence of small scale sub-problems, which costs a large amount of computation time and is hard to be accelerated by utilizing the computation power of GPU. Although Interior Point Method (IPM) such as primal-dual interior point method (PDIPM) can be also addressed SVM training well and has favourable potential for parallelizing on GPU, it contains comparatively high time complexity O(l^3) and space complexity O(l^2), where l is the number of training instances. Fortunately, by invoking low-rank approximation methods such as Incomplete Cholesky Factorization (ICF) and Sherman Morrison Woodbury formula (SMW), the requirements of both storage and computation of PDIPM can be reduced significantly. In this paper, a parallel PDIPM method (P-PDIPM) along with a parallel ICF method (P-ICF) is proposed to accelerate the SVM training on GPU. Experimental results indicate that the training speed of P-PDIPM on GPU is almost 40x faster than that of the serial one (S-PDIPM) on CPU. Besides, without extensive optimization, P-PDIPM can obtain about 8x speedup over the state of the art tool LIBSVM while maintaining high prediction accuracy.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133164591","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}
The audio watermarking method which it was recently proposed by Fallahpour is one of the methods with highest payload published to date. We tried to evaluate it and found that a weakness in terms of noise robustness is demonstrated when the audio source contains some silence gaps. In this paper we evaluate noise robustness issue for Fallahpour's audio watermarking method. It is achieved by adding some important known noises as white, pink and babble noises to the audio data samples, after applying the embedding algorithm. Experimental results show that the extracted data's BER, varies due to different values of the SNR and Fallahpour's method's parameters.
{"title":"Noise Robustness Evaluation for Fallahpour's Audio Watermarking Method","authors":"F. Pahlavani, A. Pourmohammad","doi":"10.1109/PDCAT.2013.31","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.31","url":null,"abstract":"The audio watermarking method which it was recently proposed by Fallahpour is one of the methods with highest payload published to date. We tried to evaluate it and found that a weakness in terms of noise robustness is demonstrated when the audio source contains some silence gaps. In this paper we evaluate noise robustness issue for Fallahpour's audio watermarking method. It is achieved by adding some important known noises as white, pink and babble noises to the audio data samples, after applying the embedding algorithm. Experimental results show that the extracted data's BER, varies due to different values of the SNR and Fallahpour's method's parameters.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122985538","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}
The Intel Threading Building Blocks (TBB) template library has become a popular tool for programming many-core systems. However, it is not suitable in situations where a large number of potentially blocking calls has to be made to handle long-running operations like disk access or remote data access. We have designed and implemented an add-on for the TBB that allows developers to better integrate long-running operations into their applications. We have extended TBB's task dependencies to also include blocking operations and implemented a run-time that efficiently manages these dependencies.
Intel Threading Building Blocks (TBB)模板库已经成为多核系统编程的流行工具。但是，它不适用于必须进行大量潜在阻塞调用来处理长时间运行的操作(如磁盘访问或远程数据访问)的情况。我们为TBB设计并实现了一个附加组件，它允许开发人员更好地将长时间运行的操作集成到他们的应用程序中。我们扩展了TBB的任务依赖关系，使其包括阻塞操作，并实现了一个有效管理这些依赖关系的运行时。
{"title":"Improving Blocking Operation Support in Intel TBB","authors":"J. Dokulil, S. Benkner, Martin Sandrieser","doi":"10.1109/PDCAT.2013.16","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.16","url":null,"abstract":"The Intel Threading Building Blocks (TBB) template library has become a popular tool for programming many-core systems. However, it is not suitable in situations where a large number of potentially blocking calls has to be made to handle long-running operations like disk access or remote data access. We have designed and implemented an add-on for the TBB that allows developers to better integrate long-running operations into their applications. We have extended TBB's task dependencies to also include blocking operations and implemented a run-time that efficiently manages these dependencies.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116260897","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}
Yu-Hao Huang, Ying-Yu Tseng, Hsien-Kai Kuo, Ta-Kan Yen, B. Lai
Modern GPGPUs implement on-chip shared cache to better exploit the data reuse of various general purpose applications. Given the massive amount of concurrent threads in a GPGPU, striking the balance between Data Locality and Load Balance has become a critical design concern. To achieve the best performance, the trade-off between these two factors needs to be performed concurrently. This paper proposes a dynamic thread scheduler which co-optimizes both the data locality and load balance on a GPGPU. The proposed approach is evaluated using three applications with various input datasets. The results show that the proposed approach reduces the overall execution cycles by up to 16% when compared with other approaches concerning only one objective.
{"title":"A Locality-Aware Dynamic Thread Scheduler for GPGPUs","authors":"Yu-Hao Huang, Ying-Yu Tseng, Hsien-Kai Kuo, Ta-Kan Yen, B. Lai","doi":"10.1109/PDCAT.2013.46","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.46","url":null,"abstract":"Modern GPGPUs implement on-chip shared cache to better exploit the data reuse of various general purpose applications. Given the massive amount of concurrent threads in a GPGPU, striking the balance between Data Locality and Load Balance has become a critical design concern. To achieve the best performance, the trade-off between these two factors needs to be performed concurrently. This paper proposes a dynamic thread scheduler which co-optimizes both the data locality and load balance on a GPGPU. The proposed approach is evaluated using three applications with various input datasets. The results show that the proposed approach reduces the overall execution cycles by up to 16% when compared with other approaches concerning only one objective.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121408920","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}
C. R. Valêncio, Rodrigo Dulizio Martins, Matheus Henrique Marioto, P. L. Corrêa, Maurizio Babini
The volume of digital information is growing considerably in the last two decades and there is currently a huge concern about obtaining this content quickly and effectively. In the health sector it is not different, to retrieve medical records that obtain relevant information about treatments and progresses of clinical conditions may speed up new patients' diagnosis. In this work it is described a framework proposed for automatically indexing information based on semantics and on text mining techniques. This task should work in parallel with the insertion of data into electronic records. The original contributions come down to search engine in texts organized so as to potentiate the amount of results obtained, as evidenced by the experiments carried out. The stored information is automatically fragmented into words, which have a semantic dictionary based on a framework that enables the information retrieval through semantics.
{"title":"Automatic Knowledge Extraction Supported by Semantic Enrichment in Medical Records","authors":"C. R. Valêncio, Rodrigo Dulizio Martins, Matheus Henrique Marioto, P. L. Corrêa, Maurizio Babini","doi":"10.1109/PDCAT.2013.19","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.19","url":null,"abstract":"The volume of digital information is growing considerably in the last two decades and there is currently a huge concern about obtaining this content quickly and effectively. In the health sector it is not different, to retrieve medical records that obtain relevant information about treatments and progresses of clinical conditions may speed up new patients' diagnosis. In this work it is described a framework proposed for automatically indexing information based on semantics and on text mining techniques. This task should work in parallel with the insertion of data into electronic records. The original contributions come down to search engine in texts organized so as to potentiate the amount of results obtained, as evidenced by the experiments carried out. The stored information is automatically fragmented into words, which have a semantic dictionary based on a framework that enables the information retrieval through semantics.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122226843","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}
Large-scale interactive applications and real time data-processing are facing problems with traditional disk-based storage solutions. Because of the often irregular access patterns they must keep almost all data in RAM caches, which need to be manually synchronized with secondary storage and need a lot of time to be re-loaded in case of power outages. In this paper we propose a novel key-value storage keeping all data always in RAM by aggregating resources of potentially many nodes in a data center. We aim at supporting management of billions of small data objects (16-64 byte) like for example needed for storing graphs. A scalable low-overhead meta-data management is realized using a novel range-based ID approach combined with a super-overlay network. Furthermore, we provide persistence by a novel SSD-aware logging approach allowing to recover failed nodes very fast.
{"title":"DXRAM: A Persistent In-Memory Storage for Billions of Small Objects","authors":"F. Klein, M. Schöttner","doi":"10.1109/PDCAT.2013.23","DOIUrl":"https://doi.org/10.1109/PDCAT.2013.23","url":null,"abstract":"Large-scale interactive applications and real time data-processing are facing problems with traditional disk-based storage solutions. Because of the often irregular access patterns they must keep almost all data in RAM caches, which need to be manually synchronized with secondary storage and need a lot of time to be re-loaded in case of power outages. In this paper we propose a novel key-value storage keeping all data always in RAM by aggregating resources of potentially many nodes in a data center. We aim at supporting management of billions of small data objects (16-64 byte) like for example needed for storing graphs. A scalable low-overhead meta-data management is realized using a novel range-based ID approach combined with a super-overlay network. Furthermore, we provide persistence by a novel SSD-aware logging approach allowing to recover failed nodes very fast.","PeriodicalId":187974,"journal":{"name":"2013 International Conference on Parallel and Distributed Computing, Applications and Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130796583","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：