首页 > 最新文献

Artificial Intelligence and Cloud Computing Conference最新文献

英文 中文
Naïve Bayes Classifier for Indoor Positioning using Bluetooth Low Energy Naïve基于低功耗蓝牙的室内定位贝叶斯分类器
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299842
Dzata Farahiyah, Rifky Mukti Romadhoni, Setyawan Wahyu Pratomo
Indoor localization becomes more popular along with the rapid growth of technology dan information system. The research has been conducted in many areas, especially in algorithm. Based on the need for knowledge of training data, Fingerprinting algorithm is categorized as the one that works with it. Training data is then computed with the machine learning approach, Naïve Bayes. Naïve Bayes is a simple and efficient classifier to estimate location. This study conducted an experiment with Naïve Bayes in order to classify unknown location of object based on the signal strength of Bluetooth low energy. It required 2 processes, collecting training data and evaluating test data. The result of the analysis with Naïve Bayes showed that the algorithm works well to estimate the right position of an object regarding its class.
随着技术和信息系统的快速发展,室内定位越来越受欢迎。这方面的研究已经在很多领域展开,尤其是在算法方面。基于对训练数据知识的需求,指纹识别算法被分类为与训练数据相关的算法。然后用机器学习方法(Naïve Bayes)计算训练数据。Naïve贝叶斯是一种简单有效的位置估计分类器。本研究利用Naïve Bayes进行实验,基于蓝牙低功耗信号强度对未知物体位置进行分类。它需要2个过程,收集培训数据和评估测试数据。通过Naïve Bayes的分析结果表明,该算法可以很好地估计对象在其类别中的正确位置。
{"title":"Naïve Bayes Classifier for Indoor Positioning using Bluetooth Low Energy","authors":"Dzata Farahiyah, Rifky Mukti Romadhoni, Setyawan Wahyu Pratomo","doi":"10.1145/3299819.3299842","DOIUrl":"https://doi.org/10.1145/3299819.3299842","url":null,"abstract":"Indoor localization becomes more popular along with the rapid growth of technology dan information system. The research has been conducted in many areas, especially in algorithm. Based on the need for knowledge of training data, Fingerprinting algorithm is categorized as the one that works with it. Training data is then computed with the machine learning approach, Naïve Bayes. Naïve Bayes is a simple and efficient classifier to estimate location. This study conducted an experiment with Naïve Bayes in order to classify unknown location of object based on the signal strength of Bluetooth low energy. It required 2 processes, collecting training data and evaluating test data. The result of the analysis with Naïve Bayes showed that the algorithm works well to estimate the right position of an object regarding its class.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127837525","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}
引用次数: 2
Application of Deep Learning Method in Short-term Load Forecasting of Characteristic Enterprises 深度学习方法在特色企业短期负荷预测中的应用
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299849
Yuchen Dou, Xinman Zhang, Zhihui Wu, Hang Zhang
Short-term load forecasting is an important basic work for the normal operation and control of power systems. The results of power load forecasting have a great impact on dispatching operation of the power system and the production operation of the enterprise. Accurate load forecasting would help improve the safety and stability of power system and save the cost of enterprise. In order to extract the effective information contained in the data and improve the accuracy of short-term load forecasting, this paper proposes a long-short term memory neural network model (LSTM) with deep learning ability for short-term load forecasting combined with clustering algorithm. Deep learning is in line with the trend of big data and has a strong ability to learn and summarize large amounts of data. Through the research on the characteristics and influencing factors of the characteristic enterprises, the collected samples are clustered to establish similar day sets. This paper also studies the impact of different types of load data on prediction and the actual problem of input training sample selection. The LSTM prediction model is built with subdividing and clustering the input load sample set. Compared with other traditional methods, the results prove that LSTM proposed has higher accuracy and applicability.
短期负荷预测是电力系统正常运行和控制的重要基础工作。电力负荷预测的结果对电力系统的调度运行和企业的生产运行都有很大的影响。准确的负荷预测有助于提高电力系统的安全性和稳定性,节约企业成本。为了提取数据中包含的有效信息,提高短期负荷预测的准确性,本文结合聚类算法,提出了一种具有深度学习能力的长短期记忆神经网络模型(LSTM)用于短期负荷预测。深度学习符合大数据的趋势,具有较强的学习能力和对大量数据的总结能力。通过对特色企业特征及其影响因素的研究,对所收集的样本进行聚类,建立相似日集。本文还研究了不同类型的负载数据对预测的影响以及输入训练样本选择的实际问题。通过对输入负荷样本集进行细分和聚类,建立LSTM预测模型。结果表明,与其他传统方法相比,LSTM具有更高的精度和适用性。
{"title":"Application of Deep Learning Method in Short-term Load Forecasting of Characteristic Enterprises","authors":"Yuchen Dou, Xinman Zhang, Zhihui Wu, Hang Zhang","doi":"10.1145/3299819.3299849","DOIUrl":"https://doi.org/10.1145/3299819.3299849","url":null,"abstract":"Short-term load forecasting is an important basic work for the normal operation and control of power systems. The results of power load forecasting have a great impact on dispatching operation of the power system and the production operation of the enterprise. Accurate load forecasting would help improve the safety and stability of power system and save the cost of enterprise. In order to extract the effective information contained in the data and improve the accuracy of short-term load forecasting, this paper proposes a long-short term memory neural network model (LSTM) with deep learning ability for short-term load forecasting combined with clustering algorithm. Deep learning is in line with the trend of big data and has a strong ability to learn and summarize large amounts of data. Through the research on the characteristics and influencing factors of the characteristic enterprises, the collected samples are clustered to establish similar day sets. This paper also studies the impact of different types of load data on prediction and the actual problem of input training sample selection. The LSTM prediction model is built with subdividing and clustering the input load sample set. Compared with other traditional methods, the results prove that LSTM proposed has higher accuracy and applicability.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127365819","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}
引用次数: 2
An Efficient Allocation of Cloud Computing Resources 云计算资源的高效分配
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299828
Sultan Alshamrani
The Cloud computing is a new paradigm for offering computing services via the Internet. Customers can lease infrastructure resources from cloud providers, such as CPU core, memory and disk storage, based on a "pay as you require" model. The approach in this paper is about distributing the resources (storage, processor, memory) of cloud providers to the customers by efficient manner, satisfying parties in terms of providing requirements and guarantee efficient and fair distribution of the resources. The approach system consists of two phases. In the first phase, we will create an interface in order to allow both customers and providers to insert their inputs. The system will allocate customers' demands based on the availability of the provider resources. In the second phase, the system will start to monitor the customers' usage of the resources to determine whether the customers using all the resources that have been allocated to them or did not. Then the system will reallocate the VMs resources that have not been used for a while to other customers. This will lead to reduce the cost and increase the provider profits.
云计算是一种通过互联网提供计算服务的新模式。客户可以根据“按需付费”的模式,从云提供商那里租用基础设施资源,比如CPU核心、内存和磁盘存储。本文的方法是将云提供商的资源(存储、处理器、内存)以高效的方式分配给客户,在提供需求方面满足各方,保证资源的高效、公平分配。接近系统包括两个阶段。在第一阶段,我们将创建一个接口,以便客户和提供者都可以插入他们的输入。系统将根据供应商资源的可用性分配客户的需求。在第二阶段,系统将开始监视客户对资源的使用情况,以确定客户是否使用了分配给他们的所有资源。系统将有一段时间未使用的虚拟机资源重新分配给其他客户使用。这将导致降低成本,增加供应商的利润。
{"title":"An Efficient Allocation of Cloud Computing Resources","authors":"Sultan Alshamrani","doi":"10.1145/3299819.3299828","DOIUrl":"https://doi.org/10.1145/3299819.3299828","url":null,"abstract":"The Cloud computing is a new paradigm for offering computing services via the Internet. Customers can lease infrastructure resources from cloud providers, such as CPU core, memory and disk storage, based on a \"pay as you require\" model. The approach in this paper is about distributing the resources (storage, processor, memory) of cloud providers to the customers by efficient manner, satisfying parties in terms of providing requirements and guarantee efficient and fair distribution of the resources. The approach system consists of two phases. In the first phase, we will create an interface in order to allow both customers and providers to insert their inputs. The system will allocate customers' demands based on the availability of the provider resources. In the second phase, the system will start to monitor the customers' usage of the resources to determine whether the customers using all the resources that have been allocated to them or did not. Then the system will reallocate the VMs resources that have not been used for a while to other customers. This will lead to reduce the cost and increase the provider profits.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121184608","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}
引用次数: 2
AI based intelligent system on the EDISON platform 基于AI的EDISON平台智能系统
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299843
Jin Ma, Sung-Chan Park, Jung-Hun Shin, Nam Gyu Kim, Jerry H. Seo, Jong-Suk Ruth Lee, J. Sa
In recent years, artificial intelligence (AI) has become a trend all over the world. This trend has led to the application and development of intelligent system that apply AI. In this paper, we describe a system architecture that uses AI, on a platform called EDISON, for computer science and engineering research. This architecture can be used to develop intelligent systems and can support applications in various fields by assisting in the development of algorithms and computer code. In this paper, we demonstrate the scalability of the proposed architecture on EDISON using different languages and application examples from various fields.
近年来,人工智能(AI)已经成为世界范围内的一种趋势。这一趋势导致了应用人工智能的智能系统的应用和发展。在本文中,我们描述了一个使用人工智能的系统架构,在一个名为EDISON的平台上,用于计算机科学和工程研究。该体系结构可用于开发智能系统,并可通过协助算法和计算机代码的开发来支持各个领域的应用。在本文中,我们使用不同的语言和来自不同领域的应用实例来演示所提出的架构在EDISON上的可扩展性。
{"title":"AI based intelligent system on the EDISON platform","authors":"Jin Ma, Sung-Chan Park, Jung-Hun Shin, Nam Gyu Kim, Jerry H. Seo, Jong-Suk Ruth Lee, J. Sa","doi":"10.1145/3299819.3299843","DOIUrl":"https://doi.org/10.1145/3299819.3299843","url":null,"abstract":"In recent years, artificial intelligence (AI) has become a trend all over the world. This trend has led to the application and development of intelligent system that apply AI. In this paper, we describe a system architecture that uses AI, on a platform called EDISON, for computer science and engineering research. This architecture can be used to develop intelligent systems and can support applications in various fields by assisting in the development of algorithms and computer code. In this paper, we demonstrate the scalability of the proposed architecture on EDISON using different languages and application examples from various fields.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127477648","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}
引用次数: 3
SmartPeak: Peak Shaving and Ambient Analysis For Energy Efficiency in Electrical Smart Grid 智能电网中能源效率的调峰和环境分析
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299833
Sourajit Behera, R. Misra
In modern times, buildings are heavily contributing to the overall energy consumption of the countries and in some countries they account up to 45% of their total energy consumption. Hence a detailed understanding of the dynamics of energy consumption of buildings and mining the typical daily electricity consumption profiles of households in buildings can open up new avenues for smart energy consumption profiling. This can open up newer business opportunities for all stakeholders in energy supply chain thereby supporting the energy management strategies in a smart grid environment and provide opportunities for improvement in building infrastructure with fault detection and diagnostics. In this context, we propose a approach to predict and re-engineer the hourly energy demand in a residential building. A data-driven system is proposed using machine learning techniques like Multi Linear Regression and Support Vector Machine to predict electricity demand in a smart building along with a real-time strategy to enable the users to save energy by recommending optimal scheduling of the appliances at times of peak load demand, given the consumer's constraints.
在现代,建筑对国家的整体能源消耗做出了重大贡献,在一些国家,建筑占其总能源消耗的45%。因此,详细了解建筑物的能源消耗动态并挖掘建筑物中家庭的典型日常电力消耗概况可以为智能能源消耗概况开辟新的途径。这可以为能源供应链中的所有利益相关者开辟新的商业机会,从而支持智能电网环境中的能源管理战略,并为改进具有故障检测和诊断功能的基础设施提供机会。在此背景下,我们提出了一种预测和重新设计住宅建筑每小时能源需求的方法。提出了一种数据驱动系统,使用多元线性回归和支持向量机等机器学习技术来预测智能建筑中的电力需求,并提供实时策略,使用户能够通过在峰值负荷需求时推荐最佳的设备调度来节省能源,同时考虑到消费者的限制。
{"title":"SmartPeak: Peak Shaving and Ambient Analysis For Energy Efficiency in Electrical Smart Grid","authors":"Sourajit Behera, R. Misra","doi":"10.1145/3299819.3299833","DOIUrl":"https://doi.org/10.1145/3299819.3299833","url":null,"abstract":"In modern times, buildings are heavily contributing to the overall energy consumption of the countries and in some countries they account up to 45% of their total energy consumption. Hence a detailed understanding of the dynamics of energy consumption of buildings and mining the typical daily electricity consumption profiles of households in buildings can open up new avenues for smart energy consumption profiling. This can open up newer business opportunities for all stakeholders in energy supply chain thereby supporting the energy management strategies in a smart grid environment and provide opportunities for improvement in building infrastructure with fault detection and diagnostics. In this context, we propose a approach to predict and re-engineer the hourly energy demand in a residential building. A data-driven system is proposed using machine learning techniques like Multi Linear Regression and Support Vector Machine to predict electricity demand in a smart building along with a real-time strategy to enable the users to save energy by recommending optimal scheduling of the appliances at times of peak load demand, given the consumer's constraints.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125362649","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}
引用次数: 4
Cloud Co-Residency Denial of Service Threat Detection Inspired by Artificial Immune System 基于人工免疫系统的云共居拒绝服务威胁检测
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299821
Azuan Ahmad, Wan Shafiuddin Zainudin, M. Kama, N. Idris, M. Saudi
Cloud computing introduces concerns about data protection and intrusion detection mechanism. A review of the literature shows that there is still a lack of works on cloud IDS that focused on implementing real-time hybrid detections using Dendritic Cell algorithm (DCA) as a practical approach. In addition, there is also lack of specific threat detection built to detect intrusions targeting cloud computing environment where current implementations still using traditional open source or enterprise IDS to detect threats targeting cloud computing environment. Cloud implementations also introduce a new term, "co-residency" attack and lack of research focusing on detecting this type of attack. This research aims to provide a hybrid intrusion detection model for Cloud computing environment. For this purpose, a modified DCA is proposed in this research as the main detection algorithm in the new hybrid intrusion detection mechanism which works on Cloud Co-Residency Threat Detection (CCTD) that combines anomaly and misuse detection mechanism. This research also proposed a method in detecting co-residency attacks. In this paper the co-residency attack detection model was proposed and tested until satisfactory results were obtained with the datasets. The experiment was conducted in a controlled environment and conducted using custom generated co-residency denial of service attacks for testing the capability of the proposed model in detecting novel co-residency attacks. The results show that the proposed model was able to detect most of the types of attacks that conducted during the experiment. From the experiment, the CCTD model has been shown to improve DCA previously used to solve similar problem.
云计算引入了对数据保护和入侵检测机制的关注。对文献的回顾表明,仍然缺乏云IDS的工作,重点是使用树突状细胞算法(DCA)作为一种实用的方法来实现实时混合检测。此外,还缺乏专门的威胁检测来检测针对云计算环境的入侵,目前的实现仍然使用传统的开源或企业IDS来检测针对云计算环境的威胁。云实现还引入了一个新术语“共同驻留”攻击,并且缺乏对检测此类攻击的研究。本研究旨在为云计算环境提供一种混合入侵检测模型。为此,本研究提出了一种改进的DCA作为混合入侵检测机制的主要检测算法,该机制工作于结合异常和误用检测机制的云共居威胁检测(CCTD)。本研究还提出了一种检测共居攻击的方法。本文提出了共驻留攻击检测模型,并对该模型进行了测试,得到了满意的结果。实验在受控环境中进行,并使用自定义生成的共同驻留拒绝服务攻击来测试所提出模型检测新型共同驻留攻击的能力。实验结果表明,所提出的模型能够检测出实验过程中发生的大多数攻击类型。实验表明,CCTD模型改进了以前用于解决类似问题的DCA。
{"title":"Cloud Co-Residency Denial of Service Threat Detection Inspired by Artificial Immune System","authors":"Azuan Ahmad, Wan Shafiuddin Zainudin, M. Kama, N. Idris, M. Saudi","doi":"10.1145/3299819.3299821","DOIUrl":"https://doi.org/10.1145/3299819.3299821","url":null,"abstract":"Cloud computing introduces concerns about data protection and intrusion detection mechanism. A review of the literature shows that there is still a lack of works on cloud IDS that focused on implementing real-time hybrid detections using Dendritic Cell algorithm (DCA) as a practical approach. In addition, there is also lack of specific threat detection built to detect intrusions targeting cloud computing environment where current implementations still using traditional open source or enterprise IDS to detect threats targeting cloud computing environment. Cloud implementations also introduce a new term, \"co-residency\" attack and lack of research focusing on detecting this type of attack. This research aims to provide a hybrid intrusion detection model for Cloud computing environment. For this purpose, a modified DCA is proposed in this research as the main detection algorithm in the new hybrid intrusion detection mechanism which works on Cloud Co-Residency Threat Detection (CCTD) that combines anomaly and misuse detection mechanism. This research also proposed a method in detecting co-residency attacks. In this paper the co-residency attack detection model was proposed and tested until satisfactory results were obtained with the datasets. The experiment was conducted in a controlled environment and conducted using custom generated co-residency denial of service attacks for testing the capability of the proposed model in detecting novel co-residency attacks. The results show that the proposed model was able to detect most of the types of attacks that conducted during the experiment. From the experiment, the CCTD model has been shown to improve DCA previously used to solve similar problem.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125886930","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}
引用次数: 2
Cluster-Based Destination Prediction in Bike Sharing System 基于集群的共享单车目的地预测
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299826
Pengcheng Dai, Changxiong Song, Huiping Lin, Pei Jia, Zhipeng Xu
Destination prediction not only helps to understand users' behavior, but also provides basic information for destination-related customized service. This paper studies the destination prediction in the public bike sharing system, which is now blooming in many cities as an environment friendly short-distance transportation solution. Due to the large number of bike stations (e.g. more than 800 stations of Citi Bike in New York City), the accuracy and effectiveness of destination prediction becomes a problem, where clustering algorithm is often used to reduce the number of destinations. However, grouping bike stations according to their location is not effective enough. The contribution of the paper lies in two aspects: 1) Proposes a Compound Stations Clustering method that considers not only the geographic location but also the usage pattern; 2) Provide a framework that uses feature models and corresponding labels for machine learning algorithms to predict destination for on-going trips. Experiments are conducted on real-world data sets of Citi Bike in New York City through the year of 2017 and results show that our method outperforms baselines in accuracy.
目的地预测不仅可以帮助了解用户的行为,还可以为与目的地相关的定制服务提供基础信息。作为一种环境友好型的短途交通解决方案,公共自行车共享系统目前在许多城市蓬勃发展,本文对其目的地预测进行了研究。由于自行车站点数量众多(例如纽约市的Citi bike有800多个站点),目的地预测的准确性和有效性成为一个问题,通常使用聚类算法来减少目的地的数量。然而,根据位置对自行车站进行分组是不够有效的。本文的贡献主要体现在两个方面:1)提出了一种既考虑地理位置又考虑使用模式的复合站点聚类方法;2)为机器学习算法提供一个使用特征模型和相应标签来预测正在进行的旅行目的地的框架。在2017年纽约市Citi Bike的真实数据集上进行了实验,结果表明我们的方法在准确性上优于基线。
{"title":"Cluster-Based Destination Prediction in Bike Sharing System","authors":"Pengcheng Dai, Changxiong Song, Huiping Lin, Pei Jia, Zhipeng Xu","doi":"10.1145/3299819.3299826","DOIUrl":"https://doi.org/10.1145/3299819.3299826","url":null,"abstract":"Destination prediction not only helps to understand users' behavior, but also provides basic information for destination-related customized service. This paper studies the destination prediction in the public bike sharing system, which is now blooming in many cities as an environment friendly short-distance transportation solution. Due to the large number of bike stations (e.g. more than 800 stations of Citi Bike in New York City), the accuracy and effectiveness of destination prediction becomes a problem, where clustering algorithm is often used to reduce the number of destinations. However, grouping bike stations according to their location is not effective enough. The contribution of the paper lies in two aspects: 1) Proposes a Compound Stations Clustering method that considers not only the geographic location but also the usage pattern; 2) Provide a framework that uses feature models and corresponding labels for machine learning algorithms to predict destination for on-going trips. Experiments are conducted on real-world data sets of Citi Bike in New York City through the year of 2017 and results show that our method outperforms baselines in accuracy.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123571239","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}
引用次数: 9
Natural Language Processing for Productivity Metrics for Software Development Profiling in Enterprise Applications 企业应用中软件开发分析的生产力度量的自然语言处理
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299830
Steven Delaney, Christopher Chan, Doug Smith
In this paper, we utilize ontology-based information extraction for semantic analysis and terminology linking from a corpus of software requirement specification documents from 400 enterprise-level software development projects. The purpose for this ontology is to perform semi-supervised learning on enterprise-level specification documents towards an automated method of defining productivity metrics for software development profiling. Profiling an enterprise-level software development project in the context of productivity is necessary in order to objectively measure productivity of a software development project and to identify areas of improvement in software development when compared to similar software development profiles or benchmark of these profiles. We developed a semi-novel methodology of applying NLP OBIE techniques towards determining software development productivity metrics, and evaluated this methodology on multiple practical enterprise-level software projects.
在本文中,我们利用基于本体的信息提取,从400个企业级软件开发项目的软件需求规范文档语料库中进行语义分析和术语链接。该本体的目的是在企业级规范文档上执行半监督学习,以实现为软件开发分析定义生产力度量的自动化方法。为了客观地度量软件开发项目的生产力,并在与类似的软件开发概要或这些概要的基准相比较时确定软件开发中的改进领域,在生产力的上下文中对企业级软件开发项目进行概要分析是必要的。我们开发了一种半新颖的方法,将NLP OBIE技术应用于确定软件开发生产力度量,并在多个实际的企业级软件项目中评估了这种方法。
{"title":"Natural Language Processing for Productivity Metrics for Software Development Profiling in Enterprise Applications","authors":"Steven Delaney, Christopher Chan, Doug Smith","doi":"10.1145/3299819.3299830","DOIUrl":"https://doi.org/10.1145/3299819.3299830","url":null,"abstract":"In this paper, we utilize ontology-based information extraction for semantic analysis and terminology linking from a corpus of software requirement specification documents from 400 enterprise-level software development projects. The purpose for this ontology is to perform semi-supervised learning on enterprise-level specification documents towards an automated method of defining productivity metrics for software development profiling. Profiling an enterprise-level software development project in the context of productivity is necessary in order to objectively measure productivity of a software development project and to identify areas of improvement in software development when compared to similar software development profiles or benchmark of these profiles. We developed a semi-novel methodology of applying NLP OBIE techniques towards determining software development productivity metrics, and evaluated this methodology on multiple practical enterprise-level software projects.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115829119","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}
引用次数: 0
Feature Extraction Driven Modeling Attack Against Double Arbiter PUF and Its Evaluation 特征提取驱动的双仲裁者PUF建模攻击及其评价
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299835
Susumu Matsumi, Y. Nozaki, M. Yoshikawa
Many imitations of electronic components exist in the market. The PUF has attracted attention as countermeasures against these imitations. The 2-1 DAPUF is one of the PUFs which is suitable for FPGA implementation. However, it is reported that some PUFs are vulnerable to modeling attacks using feature extraction. Regarding the effectiveness of feature extraction, it has not been evaluated in the modeling attack against 2-1 DAPUF. This study evaluated the effectiveness of feature extraction by simulation and FPGA implementation. The results showed that the feature extraction was effective for modeling attacks against 2-1 DAPUF.
市场上有许多电子元件的仿制品。因此,PUF的对策备受关注。2-1 DAPUF是一种适合FPGA实现的puf。然而,据报道,一些puf很容易受到使用特征提取的建模攻击。关于特征提取的有效性,尚未在针对2-1 DAPUF的建模攻击中进行评估。本研究通过仿真和FPGA实现来评估特征提取的有效性。结果表明,特征提取对2-1 DAPUF攻击建模是有效的。
{"title":"Feature Extraction Driven Modeling Attack Against Double Arbiter PUF and Its Evaluation","authors":"Susumu Matsumi, Y. Nozaki, M. Yoshikawa","doi":"10.1145/3299819.3299835","DOIUrl":"https://doi.org/10.1145/3299819.3299835","url":null,"abstract":"Many imitations of electronic components exist in the market. The PUF has attracted attention as countermeasures against these imitations. The 2-1 DAPUF is one of the PUFs which is suitable for FPGA implementation. However, it is reported that some PUFs are vulnerable to modeling attacks using feature extraction. Regarding the effectiveness of feature extraction, it has not been evaluated in the modeling attack against 2-1 DAPUF. This study evaluated the effectiveness of feature extraction by simulation and FPGA implementation. The results showed that the feature extraction was effective for modeling attacks against 2-1 DAPUF.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115929102","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}
引用次数: 1
Do We Need More Training Samples For Text Classification? 我们需要更多的文本分类训练样本吗?
Pub Date : 2018-12-21 DOI: 10.1145/3299819.3299836
Wanwan Zheng, Mingzhe Jin
In recent years, with the rise of exceptional cloud computing technologies, machine learning approach in solving complex problems has been greatly accelerated. In the field of text classification, machine learning is a technology of providing computers the ability to learn and predict tasks without being explicitly labeled, and it is said that enough data are needed in order to let a machine to learn. However, more data tend to cause overfitting in machine learning algorithms, and there is no object criteria in deciding how many samples are required to achieve a desired level of performance. This article addresses this problem by using feature selection method. In our experiments, feature selection is proved to be able to decrease 66.67% at the largest of the required size of training dataset. Meanwhile, the kappa coefficient as a performance measure of classifiers could increase 11 points at the maximum. Furthermore, feature selection as a technology to remove irrelevant features was found be able to prevent overfitting to a great extent.
近年来,随着卓越的云计算技术的兴起,机器学习解决复杂问题的方法得到了极大的加速。在文本分类领域,机器学习是一种为计算机提供学习和预测任务能力的技术,而无需明确标记,据说需要足够的数据才能让机器学习。然而,在机器学习算法中,更多的数据往往会导致过拟合,并且在决定需要多少样本才能达到期望的性能水平时没有对象标准。本文采用特征选择方法解决了这一问题。在我们的实验中,特征选择在训练数据集所需大小的最大值下可以减少66.67%。同时,作为分类器性能指标的kappa系数最大可提高11点。此外,特征选择作为一种去除不相关特征的技术,可以在很大程度上防止过拟合。
{"title":"Do We Need More Training Samples For Text Classification?","authors":"Wanwan Zheng, Mingzhe Jin","doi":"10.1145/3299819.3299836","DOIUrl":"https://doi.org/10.1145/3299819.3299836","url":null,"abstract":"In recent years, with the rise of exceptional cloud computing technologies, machine learning approach in solving complex problems has been greatly accelerated. In the field of text classification, machine learning is a technology of providing computers the ability to learn and predict tasks without being explicitly labeled, and it is said that enough data are needed in order to let a machine to learn. However, more data tend to cause overfitting in machine learning algorithms, and there is no object criteria in deciding how many samples are required to achieve a desired level of performance. This article addresses this problem by using feature selection method. In our experiments, feature selection is proved to be able to decrease 66.67% at the largest of the required size of training dataset. Meanwhile, the kappa coefficient as a performance measure of classifiers could increase 11 points at the maximum. Furthermore, feature selection as a technology to remove irrelevant features was found be able to prevent overfitting to a great extent.","PeriodicalId":119217,"journal":{"name":"Artificial Intelligence and Cloud Computing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114468016","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}
引用次数: 3
期刊
Artificial Intelligence and Cloud Computing Conference
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1