Due to limited power onboard, a significant factor for success of distributed teams of robots is energy-awareness. The ability to predict when power will be depleted beyond a certain point is necessary for recharging or returning to a base station. This paper presents a framework for forecasting state of charge (SOC) of a robot's battery for a given mission. A generalized and customizable mission description is formulated as a sequence of parametrized tasks defined for the robot; the missions are then mapped to expected change in SOC by training neural networks on experimental data. We present results from experiments on the Turtlebot 2 to establish the efficacy of this framework. The performance of the proposed framework is demonstrated for three distinct mission representations and compared to an existing method in the literature. Finally, we discuss the strengths and weaknesses of feedforward and recurrent neural network models in the context of this work.
{"title":"Forecasting battery state of charge for robot missions","authors":"Ameer Hamza, Nora Ayanian","doi":"10.1145/3019612.3019705","DOIUrl":"https://doi.org/10.1145/3019612.3019705","url":null,"abstract":"Due to limited power onboard, a significant factor for success of distributed teams of robots is energy-awareness. The ability to predict when power will be depleted beyond a certain point is necessary for recharging or returning to a base station. This paper presents a framework for forecasting state of charge (SOC) of a robot's battery for a given mission. A generalized and customizable mission description is formulated as a sequence of parametrized tasks defined for the robot; the missions are then mapped to expected change in SOC by training neural networks on experimental data. We present results from experiments on the Turtlebot 2 to establish the efficacy of this framework. The performance of the proposed framework is demonstrated for three distinct mission representations and compared to an existing method in the literature. Finally, we discuss the strengths and weaknesses of feedforward and recurrent neural network models in the context of this work.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"44 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86271973","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}
In this paper, we explore the suitability of employing Convolutional Neural Networks (ConvNets) for multi-label movie trailer genre classification. Assigning genres to movies is a particularly challenging task because genre is an immaterial feature that is not physically present in a movie frame, so off-the-shelf image detection models cannot be easily adapted to this context. Moreover, multi-label classification is more challenging than single-label classification considering that one instance can be assigned to multiple classes at once. We propose a novel classification method that encapsulates an ultra-deep ConvNet with residual connections. Our approach extracts temporal information from image-based features prior to performing the mapping of trailers to genres. We compare our novel approach with the current state-of-the-art techniques for movie classification, which make use of well-known image descriptors and low-level handcrafted features. Results show that our method significantly outperforms the state-of-the-art in this task, improving the classification accuracy for all genres.
{"title":"Convolutions through time for multi-label movie genre classification","authors":"Jonatas Wehrmann, Rodrigo C. Barros","doi":"10.1145/3019612.3019641","DOIUrl":"https://doi.org/10.1145/3019612.3019641","url":null,"abstract":"In this paper, we explore the suitability of employing Convolutional Neural Networks (ConvNets) for multi-label movie trailer genre classification. Assigning genres to movies is a particularly challenging task because genre is an immaterial feature that is not physically present in a movie frame, so off-the-shelf image detection models cannot be easily adapted to this context. Moreover, multi-label classification is more challenging than single-label classification considering that one instance can be assigned to multiple classes at once. We propose a novel classification method that encapsulates an ultra-deep ConvNet with residual connections. Our approach extracts temporal information from image-based features prior to performing the mapping of trailers to genres. We compare our novel approach with the current state-of-the-art techniques for movie classification, which make use of well-known image descriptors and low-level handcrafted features. Results show that our method significantly outperforms the state-of-the-art in this task, improving the classification accuracy for all genres.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88515772","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}
Networks using WiFi continue to proliferate which has contributed to increased levels of crowding in the unlicensed bands in which these networks operate. Given the limited number of channels available in these bands, a key problem that arises is how to avoid / minimise conflicting channel assignment among neighbouring networks. This is particularly challenging in uncoordinated, unplanned deployments wherein Access Points (APs) belonging to different administrative entities may be operating in isolation in the vicinity of each other. Given the difficulty of planning conflict free channel allocation in such deployments, it is highly desirable to devise mechanisms such that the APs themselves become radio neighbourhood aware and adapt their operation (channel switching on the fly) so as to mitigate interference issues. In this paper, we propose two distributed channel selection algorithms for accomplishing the above mentioned objective. In particular, we show that these algorithms are practical from an implementation perspective, accomplish their objective without requiring any changes to the hardware, the existing infrastructure and the WLAN standard, and highlight findings from a simulation based study. Findings indicate that the proposed algorithms significantly outperform the typical random selection approach commonly employed by low cost commercial off-the-shelf hardware.
{"title":"Moving away from the crowd: channel selection in uncoordinated unplanned dense wireless LANs","authors":"P. Kulkarni, Zhenzhe Zhong, Fengming Cao","doi":"10.1145/3019612.3019771","DOIUrl":"https://doi.org/10.1145/3019612.3019771","url":null,"abstract":"Networks using WiFi continue to proliferate which has contributed to increased levels of crowding in the unlicensed bands in which these networks operate. Given the limited number of channels available in these bands, a key problem that arises is how to avoid / minimise conflicting channel assignment among neighbouring networks. This is particularly challenging in uncoordinated, unplanned deployments wherein Access Points (APs) belonging to different administrative entities may be operating in isolation in the vicinity of each other. Given the difficulty of planning conflict free channel allocation in such deployments, it is highly desirable to devise mechanisms such that the APs themselves become radio neighbourhood aware and adapt their operation (channel switching on the fly) so as to mitigate interference issues. In this paper, we propose two distributed channel selection algorithms for accomplishing the above mentioned objective. In particular, we show that these algorithms are practical from an implementation perspective, accomplish their objective without requiring any changes to the hardware, the existing infrastructure and the WLAN standard, and highlight findings from a simulation based study. Findings indicate that the proposed algorithms significantly outperform the typical random selection approach commonly employed by low cost commercial off-the-shelf hardware.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88738283","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}
At present, recommendations become an acceptable choice to replace annoying and widespread advertisements. Recommender systems (RS) are mainly used by large scale e-businesses, such as Amazon [1] and Netflix [4], because implementing and deploying RS can involve substantial investments. Many e-commerce businesses prefer to outsource the recommendation services. Therefore, Recommendation as a Service (RaaS) becomes a newly emerging trend for providing a feasible RS alternative. The providers of these services, the RS providers, need to pay the fee of cloud computing services, which is proportional to the amount of time, memory requirement, and computation resources. In addition, the RS providers must support rapidly recommendation services to meet the requests of clients. In this paper, we propose a numerical similarity-aware data partitioning (NSDP) scheme that effectively uses the numeric and similarity of datasets to exactly estimate the memory and the computation requirements for distributing the workloads. The simulation results demonstrate that NSDP significantly improves the speedup performance and achieves high scalability in the RaaS distributed-memory environment.
{"title":"Numerical similarity-aware data partitioning for recommendations as a service","authors":"Ting-Ting Yang, Hsueh-Wen Tseng","doi":"10.1145/3019612.3019676","DOIUrl":"https://doi.org/10.1145/3019612.3019676","url":null,"abstract":"At present, recommendations become an acceptable choice to replace annoying and widespread advertisements. Recommender systems (RS) are mainly used by large scale e-businesses, such as Amazon [1] and Netflix [4], because implementing and deploying RS can involve substantial investments. Many e-commerce businesses prefer to outsource the recommendation services. Therefore, Recommendation as a Service (RaaS) becomes a newly emerging trend for providing a feasible RS alternative. The providers of these services, the RS providers, need to pay the fee of cloud computing services, which is proportional to the amount of time, memory requirement, and computation resources. In addition, the RS providers must support rapidly recommendation services to meet the requests of clients. In this paper, we propose a numerical similarity-aware data partitioning (NSDP) scheme that effectively uses the numeric and similarity of datasets to exactly estimate the memory and the computation requirements for distributing the workloads. The simulation results demonstrate that NSDP significantly improves the speedup performance and achieves high scalability in the RaaS distributed-memory environment.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"376 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77119840","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}
Several studies in the model-driven engineering (MDE) literature report on companies adopting MDE technologies as a result of long collaborations with academics. However, there are more companies than reported that are already using MDE, even without active MDE researchers partners. Therefore we do not have a clear view of how these industries are using MDE and how it is benefiting them. Presche Legacy is a company that already started using MDE even before collaborating with us. To better understand how MDE is used in such industries and to what extent MDE can solve challenges in this business, we conducted a series of interviews with the employees working with MDE. The findings presented in this paper report a successful integration of MDE tools with their in-house software used in production, challenges encountered, and how they surmounted them. We also discuss how this success story can help other companies benefit from MDE.
{"title":"Feedback on how MDE tools are used prior to academic collaboration","authors":"V. Sousa, Eugene Syriani, Martin Paquin","doi":"10.1145/3019612.3019775","DOIUrl":"https://doi.org/10.1145/3019612.3019775","url":null,"abstract":"Several studies in the model-driven engineering (MDE) literature report on companies adopting MDE technologies as a result of long collaborations with academics. However, there are more companies than reported that are already using MDE, even without active MDE researchers partners. Therefore we do not have a clear view of how these industries are using MDE and how it is benefiting them. Presche Legacy is a company that already started using MDE even before collaborating with us. To better understand how MDE is used in such industries and to what extent MDE can solve challenges in this business, we conducted a series of interviews with the employees working with MDE. The findings presented in this paper report a successful integration of MDE tools with their in-house software used in production, challenges encountered, and how they surmounted them. We also discuss how this success story can help other companies benefit from MDE.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86971688","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}
Baptiste de La Robertie, Y. Pitarch, A. Takasu, O. Teste
Numereous digital library projects mine heterogeneous data from different sources to provide expert finding services. However, a variety of models seek experts as simple sources of information and neglect authority signals. In this paper we address the issue of modelling the authority of researchers in academic networks. A model, RAC, is proposed that merges several graph representations and incorporate external knowledge about the authority of some major scientific conferences to improve the identification of authoritative researchers. Based on the provided structural model a biased label propagation algorithm aimed to strenghten the scores calculation of the labelled entities and their neighbors is developped. Both quantitative and qualitative analyses validate the effectiveness of the proposal. Indeed, RAC outperforms state-of-the-art models on a real-world graph containing more than 5 million nodes constructed using Microsoft Academic Search, AMiner and Core.edu databases.
{"title":"Identifying authoritative researchers in digital libraries using external a priori knowledge","authors":"Baptiste de La Robertie, Y. Pitarch, A. Takasu, O. Teste","doi":"10.1145/3019612.3019809","DOIUrl":"https://doi.org/10.1145/3019612.3019809","url":null,"abstract":"Numereous digital library projects mine heterogeneous data from different sources to provide expert finding services. However, a variety of models seek experts as simple sources of information and neglect authority signals. In this paper we address the issue of modelling the authority of researchers in academic networks. A model, RAC, is proposed that merges several graph representations and incorporate external knowledge about the authority of some major scientific conferences to improve the identification of authoritative researchers. Based on the provided structural model a biased label propagation algorithm aimed to strenghten the scores calculation of the labelled entities and their neighbors is developped. Both quantitative and qualitative analyses validate the effectiveness of the proposal. Indeed, RAC outperforms state-of-the-art models on a real-world graph containing more than 5 million nodes constructed using Microsoft Academic Search, AMiner and Core.edu databases.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88925525","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 loosely coupled interoperability of heterogeneous existing systems, together with the ongoing replacement of monolithic systems design with Off-The-Shelf (OTS) approaches, promotes a new architectural paradigm that is called System of Systems (SoS). In SoSs, independent and autonomous constituent systems (CSs) cooperate to achieve higher-level goals. Some inherent challenges are that boundaries of the SoS may be partially unknown and the components may be governed by different authorities, affecting the ability to observe the system as a whole. Further, novel challenges related to dependability and security are introduced, such as the detection of emerging and possibly unexpected behaviors resulting from the interconnection of previous disconnected CSs. In this paper we explore these challenges questioning if a novel mindset to error, malware or intrusion detection is needed when dealing with SoSs. With the support of a state of the art review, we first identify the design principles and the performance targets of a monitoring and anomaly detection framework. Then we discuss these principles at the light of SoS fundamentals. Ultimately, we propose an approach to design a monitoring and anomaly detection framework for SoSs aggregating i) monitoring approaches ii) SoS properties, and iii) anomaly detection techniques.
异构现有系统的松散耦合互操作性，以及用现成(Off-The-Shelf, OTS)方法不断替代单片系统设计，促进了一种新的体系结构范例，称为系统的系统(System of systems, SoS)。在社会责任系统中，独立和自治的组成系统(CSs)相互协作以实现更高层次的目标。一些固有的挑战是，SoS的边界可能部分未知，组件可能由不同的权威管理，从而影响观察整个系统的能力。此外，引入了与可靠性和安全性相关的新挑战，例如检测由于先前断开的CSs互连而产生的新行为和可能的意外行为。在本文中，我们探讨了这些挑战，质疑在处理sos时是否需要一种新的错误，恶意软件或入侵检测的心态。在最新技术综述的支持下，我们首先确定了监视和异常检测框架的设计原则和性能目标。然后我们根据SoS的基本原理来讨论这些原则。最后，我们提出了一种方法来设计一个监测和异常检测框架，用于聚合i)监测方法ii) SoS属性和iii)异常检测技术。
{"title":"Exploring anomaly detection in systems of systems","authors":"T. Zoppi, A. Ceccarelli, A. Bondavalli","doi":"10.1145/3019612.3019765","DOIUrl":"https://doi.org/10.1145/3019612.3019765","url":null,"abstract":"The loosely coupled interoperability of heterogeneous existing systems, together with the ongoing replacement of monolithic systems design with Off-The-Shelf (OTS) approaches, promotes a new architectural paradigm that is called System of Systems (SoS). In SoSs, independent and autonomous constituent systems (CSs) cooperate to achieve higher-level goals. Some inherent challenges are that boundaries of the SoS may be partially unknown and the components may be governed by different authorities, affecting the ability to observe the system as a whole. Further, novel challenges related to dependability and security are introduced, such as the detection of emerging and possibly unexpected behaviors resulting from the interconnection of previous disconnected CSs. In this paper we explore these challenges questioning if a novel mindset to error, malware or intrusion detection is needed when dealing with SoSs. With the support of a state of the art review, we first identify the design principles and the performance targets of a monitoring and anomaly detection framework. Then we discuss these principles at the light of SoS fundamentals. Ultimately, we propose an approach to design a monitoring and anomaly detection framework for SoSs aggregating i) monitoring approaches ii) SoS properties, and iii) anomaly detection techniques.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"39 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73773762","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}
In this paper we present an empirical study on patterns of operating system failure causes. We surveyed 566 computers and collected 7,007 real failures of operating systems. We found that 87.97+ of the failures were caused by faults related to software updating. We found strong evidences of autocorrelation among operating system failure causes, i.e., the same failure occurs multiple times successively and due to the same cause; or different failures occur simultaneously due to a common cause. Cross-correlation among different failure causes was also observed and discussed. We discovered 47 genuine patterns of operating system failure causes with 156,866 occurrences in the analyzed dataset.
{"title":"An empirical study on patterns of failure causes in a mass-market operating system","authors":"C. A. R. D. Santos, Rivalino Matias","doi":"10.1145/3019612.3019740","DOIUrl":"https://doi.org/10.1145/3019612.3019740","url":null,"abstract":"In this paper we present an empirical study on patterns of operating system failure causes. We surveyed 566 computers and collected 7,007 real failures of operating systems. We found that 87.97+ of the failures were caused by faults related to software updating. We found strong evidences of autocorrelation among operating system failure causes, i.e., the same failure occurs multiple times successively and due to the same cause; or different failures occur simultaneously due to a common cause. Cross-correlation among different failure causes was also observed and discussed. We discovered 47 genuine patterns of operating system failure causes with 156,866 occurrences in the analyzed dataset.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"95 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74687053","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}
{"title":"Session details: EMBS - embedded systems track","authors":"","doi":"10.1145/3243969","DOIUrl":"https://doi.org/10.1145/3243969","url":null,"abstract":"","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"134 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74702016","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}
M. Danelutto, T. D. Matteis, D. D. Sensi, G. Mencagli, M. Torquati
High-level parallel programming is a de-facto standard approach to develop parallel software with reduced time to development. High-level abstractions are provided by existing frameworks as pragma-based annotations in the source code, or through pre-built parallel patterns that recur frequently in parallel algorithms, and that can be easily instantiated by the programmer to add a structure to the development of parallel software. In this paper we focus on this second approach and we propose P3ARSEC, a benchmark suite for parallel pattern-based frameworks consisting of a representative subset of PARSEC applications. We analyse the programmability advantages and the potential performance penalty of using such high-level methodology with respect to hand-made parallelisations using low-level mechanisms. The results are obtained on the new Intel Knights Landing multicore, and show a significantly reduced code complexity with comparable performance.
{"title":"P3ARSEC: towards parallel patterns benchmarking","authors":"M. Danelutto, T. D. Matteis, D. D. Sensi, G. Mencagli, M. Torquati","doi":"10.1145/3019612.3019745","DOIUrl":"https://doi.org/10.1145/3019612.3019745","url":null,"abstract":"High-level parallel programming is a de-facto standard approach to develop parallel software with reduced time to development. High-level abstractions are provided by existing frameworks as pragma-based annotations in the source code, or through pre-built parallel patterns that recur frequently in parallel algorithms, and that can be easily instantiated by the programmer to add a structure to the development of parallel software. In this paper we focus on this second approach and we propose P3ARSEC, a benchmark suite for parallel pattern-based frameworks consisting of a representative subset of PARSEC applications. We analyse the programmability advantages and the potential performance penalty of using such high-level methodology with respect to hand-made parallelisations using low-level mechanisms. The results are obtained on the new Intel Knights Landing multicore, and show a significantly reduced code complexity with comparable performance.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":"323 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76118270","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：