Environmental factors - such as difference in mutual work recognition between users, developers, and testers, or knowledge differences - can hinder communication, which may lead to faulty development due to erroneous job definition. Since the exact size and scope of the software cannot be calculated, the risk of excessive requirements, such as schedule, cost, and manpower, may increase. This study analyzes the degree of impact of each environmental factor on software reliability assessment in Korean companies. It aims to investigate the effects of environmental factors in Korean companies and to compare with previous studies. This study can supply useful benefits to software developers and managers.
{"title":"An EFA for Software Development Environments","authors":"Kwangyoon Song, I. Chang","doi":"10.1145/3426020.3426153","DOIUrl":"https://doi.org/10.1145/3426020.3426153","url":null,"abstract":"Environmental factors - such as difference in mutual work recognition between users, developers, and testers, or knowledge differences - can hinder communication, which may lead to faulty development due to erroneous job definition. Since the exact size and scope of the software cannot be calculated, the risk of excessive requirements, such as schedule, cost, and manpower, may increase. This study analyzes the degree of impact of each environmental factor on software reliability assessment in Korean companies. It aims to investigate the effects of environmental factors in Korean companies and to compare with previous studies. This study can supply useful benefits to software developers and managers.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134124598","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}
Saqib Ali, O. Rehman, KyungJin Cha, Taisira Al Balushi, Z. Nadir
Power grid systems are considered as critical infrastructure that require smooth and efficient operation in its power generation, transmission and distribution sectors. A performance loss in such systems can lead towards undesired situations including damages and financial losses. Remote, reliable and real-time monitoring of different components within a power grid system are important features for assuring performance, especially in modern smart grid technologies. Internet of Things (IoT)-enabled monitoring systems have the potential to fulfill the said requirements. For that, adopting a suitable communication technology to effectively transfer data of the monitored component is an essential design objective in IoT-enabled monitoring systems. This paper proposes a prototype design suitable for remotely monitoring different components within a power grid while adopting ZigBee as the underlying communication technology. Experimental results show that the devised prototype has the potential to effectively capture and notify in real-time the changes occurring in a power grid system.
{"title":"Performance Analysis of ZigBee-based IoT Prototype for Remote Monitoring in Power Grid Systems","authors":"Saqib Ali, O. Rehman, KyungJin Cha, Taisira Al Balushi, Z. Nadir","doi":"10.1145/3426020.3426140","DOIUrl":"https://doi.org/10.1145/3426020.3426140","url":null,"abstract":"Power grid systems are considered as critical infrastructure that require smooth and efficient operation in its power generation, transmission and distribution sectors. A performance loss in such systems can lead towards undesired situations including damages and financial losses. Remote, reliable and real-time monitoring of different components within a power grid system are important features for assuring performance, especially in modern smart grid technologies. Internet of Things (IoT)-enabled monitoring systems have the potential to fulfill the said requirements. For that, adopting a suitable communication technology to effectively transfer data of the monitored component is an essential design objective in IoT-enabled monitoring systems. This paper proposes a prototype design suitable for remotely monitoring different components within a power grid while adopting ZigBee as the underlying communication technology. Experimental results show that the devised prototype has the potential to effectively capture and notify in real-time the changes occurring in a power grid system.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134382996","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}
This study aims to suggest a new approach that finds important job skill terms using deep learning and eXplainable Artificial Intelligence (XAI) algorithms. A total of 52,190 job advertisements were collected from a job posting website using web crawling technique. The job advertisements were classified into specific job roles using Deep Learning-based Bidirectional LSTM(Long Short Term Memory) and Bidirectional LSTM Attention. Finally, the best performing Bidirectional LSTM Attention model was used to extract important terms from the selected job advertisements by using Local Interpretable Model-agnostic Explanations (LIME), one of the XAI techniques, and compared them with those selected by term frequency. The results show that these two sets are significantly different in some cases, even when one set is more reasonable compared to other set and vice versa. Although this research cannot conclude the LIME is better than the frequency-based approach for identifying important skills, at least we found that LIME could guide researchers to a new path for this task.
本研究旨在提出一种利用深度学习和可解释人工智能(XAI)算法发现重要工作技能术语的新方法。使用网页抓取技术从招聘网站收集了52190份招聘广告。使用基于深度学习的双向LSTM(长短期记忆)和双向LSTM注意对招聘广告进行分类。最后，利用XAI技术中的局部可解释模型不可知解释(Local Interpretable model -agnostic interpretation, LIME)，利用表现最佳的双向LSTM注意模型从所选的招聘广告中提取重要术语，并将其与按术语频次选择的招聘广告进行比较。结果表明，这两组在某些情况下存在显著差异，即使其中一组比另一组更合理，反之亦然。虽然这项研究不能得出LIME比基于频率的方法更好地识别重要技能的结论，但至少我们发现LIME可以指导研究人员找到这项任务的新途径。
{"title":"A Study of the Classification of IT Jobs Using LSTM and LIME","authors":"I. Choi, Yangsok Kim, Choong Kwon Lee","doi":"10.1145/3426020.3426083","DOIUrl":"https://doi.org/10.1145/3426020.3426083","url":null,"abstract":"This study aims to suggest a new approach that finds important job skill terms using deep learning and eXplainable Artificial Intelligence (XAI) algorithms. A total of 52,190 job advertisements were collected from a job posting website using web crawling technique. The job advertisements were classified into specific job roles using Deep Learning-based Bidirectional LSTM(Long Short Term Memory) and Bidirectional LSTM Attention. Finally, the best performing Bidirectional LSTM Attention model was used to extract important terms from the selected job advertisements by using Local Interpretable Model-agnostic Explanations (LIME), one of the XAI techniques, and compared them with those selected by term frequency. The results show that these two sets are significantly different in some cases, even when one set is more reasonable compared to other set and vice versa. Although this research cannot conclude the LIME is better than the frequency-based approach for identifying important skills, at least we found that LIME could guide researchers to a new path for this task.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134443233","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}
With the high interest in the peer to peer (P2P) energy trading system, blockchain technology has increased attention as a solution to alleviate the current challenges in the centralised energy system. The study set out to discover how blockchain could be used for microgrid while controlling the scalability to encourage peer-to-peer energy trading with the assumption of the average dwelling density at around 20-30 households. The results showed that there is a scalability challenge in the blockchain as the network grows; however, the blockchain technology can be applied in the community which has a similar size with Hobart as there is no significant difference in the execution time up to 100 nodes while accumulating the transactions. Additionally, the study also found mining time, transaction fee and transactions number in the block are also related to the execution time. Therefore, these parameters should be considered to build a scalable blockchain for a microgrid.
{"title":"Blockchain-based renewable energy trading system with smart contract in a small local community","authors":"Riseul Ryu, Soonja Yeom","doi":"10.1145/3426020.3426078","DOIUrl":"https://doi.org/10.1145/3426020.3426078","url":null,"abstract":"With the high interest in the peer to peer (P2P) energy trading system, blockchain technology has increased attention as a solution to alleviate the current challenges in the centralised energy system. The study set out to discover how blockchain could be used for microgrid while controlling the scalability to encourage peer-to-peer energy trading with the assumption of the average dwelling density at around 20-30 households. The results showed that there is a scalability challenge in the blockchain as the network grows; however, the blockchain technology can be applied in the community which has a similar size with Hobart as there is no significant difference in the execution time up to 100 nodes while accumulating the transactions. Additionally, the study also found mining time, transaction fee and transactions number in the block are also related to the execution time. Therefore, these parameters should be considered to build a scalable blockchain for a microgrid.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133106620","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}
Agriculture can save labor and production costs by automatically recognizing and growing fruit. And the technology that can complete this process is in AI. Using AI technology, we designed a Fruit Object Detection and Monitoring to increase the efficiency of fruit cultivation management, an important task in the agricultural industry. For this, Yolo, transfer learning algorithms and ROS were studied. After that, a Fruit Object Detection and Monitoring was designed by linking a Raspberry Pi 4 equipped with a camera and Arduino, a micro cloud storage cluster and a micro cloud AI cluster. Until now, the design has been tested except for real-time object recognition monitoring, and is planned to be completed through future research.
{"title":"Draft Design of Fruit Object Recognition using Transfer Learning in Smart Farm","authors":"Y. Cha, Taehong Kim, Dae-Gue Kim, Byung-Rae Cha","doi":"10.1145/3426020.3426048","DOIUrl":"https://doi.org/10.1145/3426020.3426048","url":null,"abstract":"Agriculture can save labor and production costs by automatically recognizing and growing fruit. And the technology that can complete this process is in AI. Using AI technology, we designed a Fruit Object Detection and Monitoring to increase the efficiency of fruit cultivation management, an important task in the agricultural industry. For this, Yolo, transfer learning algorithms and ROS were studied. After that, a Fruit Object Detection and Monitoring was designed by linking a Raspberry Pi 4 equipped with a camera and Arduino, a micro cloud storage cluster and a micro cloud AI cluster. Until now, the design has been tested except for real-time object recognition monitoring, and is planned to be completed through future research.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"24 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114122051","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}
Tazizur Rahman, Md. Abir Hossain, Yangsok Kim, M. Noh, Choong Kwon Lee
This study aims to examine the key influential factors responsible for social media-based online store adoption in Bangladesh. The research model combines constructs from the unified theory of acceptance and use of technology model. We use structural equation modeling to analyze the data collected through an online survey of 273 participants who are social media-based online store users in Bangladesh. The results indicate that social influence is the most influential factor of use intention, and performance expectancy and effort expectancy have an almost similar impact on use intention. The findings also reveal that facilitating conditions and use intention have significant positive impacts on the actual use behavior of these platforms.
{"title":"Determinants of Social Media-Based Online Store Adoption.","authors":"Tazizur Rahman, Md. Abir Hossain, Yangsok Kim, M. Noh, Choong Kwon Lee","doi":"10.1145/3426020.3426081","DOIUrl":"https://doi.org/10.1145/3426020.3426081","url":null,"abstract":"This study aims to examine the key influential factors responsible for social media-based online store adoption in Bangladesh. The research model combines constructs from the unified theory of acceptance and use of technology model. We use structural equation modeling to analyze the data collected through an online survey of 273 participants who are social media-based online store users in Bangladesh. The results indicate that social influence is the most influential factor of use intention, and performance expectancy and effort expectancy have an almost similar impact on use intention. The findings also reveal that facilitating conditions and use intention have significant positive impacts on the actual use behavior of these platforms.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126376888","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}
With tremendous usage of mobile applications, the demand for high speed and low latency connections of the huge number of mobile users is increasing. Cloud radio access network (C-RAN) is a potential mobile network architecture for the next-generation wireless communication, which can meet the requirements of massively increasing data traffic and user demand. In C-RAN, the data processing unit can be centralized and virtualized in data centers and can be shared among distributed base stations. Deep learning (DL), with the recent breakthrough, appears to be a viable approach for facilitating the data processing capability, resource management in the cloud, and predicting traffic in cellular communication. The convergence of C-RAN and DL is believed to bring new possibilities to both interdisciplinary researches and industrial applications. This article provides a comprehensive survey of the state-of-the-art DL techniques applied in C-RAN. A brief introduction is given in the C-RAN architecture and DL techniques to have insights on these two emerging technologies. The reviewed works are categorized in terms of their optimization objectives mentioning the key ideas of DL applied in the works. Research challenges and open research issues are also highlighted to provide future research direction.
{"title":"A Survey on Deep Learning for Cloud Radio Access Networks","authors":"Rehenuma Tasnim Rodoshi, Seokjoo Shin, Wooyeol Choi","doi":"10.1145/3426020.3426022","DOIUrl":"https://doi.org/10.1145/3426020.3426022","url":null,"abstract":"With tremendous usage of mobile applications, the demand for high speed and low latency connections of the huge number of mobile users is increasing. Cloud radio access network (C-RAN) is a potential mobile network architecture for the next-generation wireless communication, which can meet the requirements of massively increasing data traffic and user demand. In C-RAN, the data processing unit can be centralized and virtualized in data centers and can be shared among distributed base stations. Deep learning (DL), with the recent breakthrough, appears to be a viable approach for facilitating the data processing capability, resource management in the cloud, and predicting traffic in cellular communication. The convergence of C-RAN and DL is believed to bring new possibilities to both interdisciplinary researches and industrial applications. This article provides a comprehensive survey of the state-of-the-art DL techniques applied in C-RAN. A brief introduction is given in the C-RAN architecture and DL techniques to have insights on these two emerging technologies. The reviewed works are categorized in terms of their optimization objectives mentioning the key ideas of DL applied in the works. Research challenges and open research issues are also highlighted to provide future research direction.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127150249","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}
Donghun Yang, Iksoo Shin, Mai Ngoc Kien, Hoyong Kim, Chanhee Yu, Myunggwon Hwang
To design an efficient deep learning model that can be used in the real world, it is important that out-of-distribution (OOD) data are detected well. To solve this OOD problem, various studies have been conducted. The current state-of-the-art approach uses confidence score based on the Mahalanobis distance in a feature space. Although it performed better than the previous approaches, the results are sensitive to the quality of the trained model and the datasets. Herein, we propose a simple and new OOD detection module that is designed separately from the existing classifier. In our approach, to obtain a clumped dispersion by class, the feature space is trained using a network based on distance metric learning. Therefore, OOD data can be efficiently detected by applying a threshold to the trained feature space. To evaluate the proposed method, we applied our method to a combination of MNIST and Fashion MNIST datasets. The results showed that the overall performance of the proposed approach is superior to those of other methods.
{"title":"Out-of-Distribution Detection Based on Distance Metric Learning","authors":"Donghun Yang, Iksoo Shin, Mai Ngoc Kien, Hoyong Kim, Chanhee Yu, Myunggwon Hwang","doi":"10.1145/3426020.3426076","DOIUrl":"https://doi.org/10.1145/3426020.3426076","url":null,"abstract":"To design an efficient deep learning model that can be used in the real world, it is important that out-of-distribution (OOD) data are detected well. To solve this OOD problem, various studies have been conducted. The current state-of-the-art approach uses confidence score based on the Mahalanobis distance in a feature space. Although it performed better than the previous approaches, the results are sensitive to the quality of the trained model and the datasets. Herein, we propose a simple and new OOD detection module that is designed separately from the existing classifier. In our approach, to obtain a clumped dispersion by class, the feature space is trained using a network based on distance metric learning. Therefore, OOD data can be efficiently detected by applying a threshold to the trained feature space. To evaluate the proposed method, we applied our method to a combination of MNIST and Fashion MNIST datasets. The results showed that the overall performance of the proposed approach is superior to those of other methods.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125923957","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}
Representing a word into a continuous space, also known as a word vector, has been successful in various NLP tasks. The word-based embedding has two problems; one is the out-of-vocabulary problem and the other is does not take into account the context of a word, which is homonymy, and polysemy since word vector is represented as a single vector. To against out-of-vocabulary problem, the previous researches handle it as splitting smaller unit than word unit, in particular, mainly morphologically rich language is decomposed into morpheme unit as Korean. However, morpheme embedding has also a problem that doesn't take into account multiple senses of a morpheme although the morpheme mitigates the out-of-vocabulary problem. Therefore, we propose the Korean multi-prototype morpheme embedding method representing multiple senses of a morpheme. Connecting morphemes and POS vectors to handle multi-prototype morpheme. In the experiment, we found that our multi-prototype morpheme embedding makes morpheme in a similar context closer in the vector space than the previous morpheme embedding. Our method outperforms the previous morpheme embedding as well as a baseline.
{"title":"Multi-prototype Morpheme Embedding for Text Classification","authors":"Hye-Young Won, Hyunyoung Lee, Seungshik Kang","doi":"10.1145/3426020.3426095","DOIUrl":"https://doi.org/10.1145/3426020.3426095","url":null,"abstract":"Representing a word into a continuous space, also known as a word vector, has been successful in various NLP tasks. The word-based embedding has two problems; one is the out-of-vocabulary problem and the other is does not take into account the context of a word, which is homonymy, and polysemy since word vector is represented as a single vector. To against out-of-vocabulary problem, the previous researches handle it as splitting smaller unit than word unit, in particular, mainly morphologically rich language is decomposed into morpheme unit as Korean. However, morpheme embedding has also a problem that doesn't take into account multiple senses of a morpheme although the morpheme mitigates the out-of-vocabulary problem. Therefore, we propose the Korean multi-prototype morpheme embedding method representing multiple senses of a morpheme. Connecting morphemes and POS vectors to handle multi-prototype morpheme. In the experiment, we found that our multi-prototype morpheme embedding makes morpheme in a similar context closer in the vector space than the previous morpheme embedding. Our method outperforms the previous morpheme embedding as well as a baseline.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122963896","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}
Using Regular Path Queries (RPQs) is a common way to explore patterns in graph databases. Traditional automata-based approaches for evaluating RPQs on large graphs are restricted in the graph size and/or highly complex queries, which causes a high evaluation cost. Recently, the threshold rare label based approach applied on large graphs has been proved to be effective. Nevertheless, using rare labels in a graph provides only coarse information which could not always guarantee the minimum searching cost. Hence, the Unit-Subquery Cost Matrix (USCM) based approach has been proposed to reduce the parallel evaluation cost by estimating the searching cost of RPQs. However, the previous approach does not take the joining cost among subqueries into account. In this paper, the method of estimating joining cost of subqueries is proposed in order to accelerate the USCM based parallel evaluation of RPQs. Specifically, the proposed method is realized by estimating the result size of the subqueries. Through our experiments upon real-world datasets, it is depicted that estimating joining cost enhances USCM based approach up to around 20% in terms of response time.
{"title":"Accelerating Parallel Evaluation of Regular Path Queries on Large Graphs by Estimating Joining Cost of Subqueries","authors":"Van-Quyet Nguyen, Van-Hau Nguyen, Huy-The Vu, Minh Q. Nguyen, Quyet-Thang Huynh, Kyungbaek Kim","doi":"10.1145/3426020.3426169","DOIUrl":"https://doi.org/10.1145/3426020.3426169","url":null,"abstract":"Using Regular Path Queries (RPQs) is a common way to explore patterns in graph databases. Traditional automata-based approaches for evaluating RPQs on large graphs are restricted in the graph size and/or highly complex queries, which causes a high evaluation cost. Recently, the threshold rare label based approach applied on large graphs has been proved to be effective. Nevertheless, using rare labels in a graph provides only coarse information which could not always guarantee the minimum searching cost. Hence, the Unit-Subquery Cost Matrix (USCM) based approach has been proposed to reduce the parallel evaluation cost by estimating the searching cost of RPQs. However, the previous approach does not take the joining cost among subqueries into account. In this paper, the method of estimating joining cost of subqueries is proposed in order to accelerate the USCM based parallel evaluation of RPQs. Specifically, the proposed method is realized by estimating the result size of the subqueries. Through our experiments upon real-world datasets, it is depicted that estimating joining cost enhances USCM based approach up to around 20% in terms of response time.","PeriodicalId":305132,"journal":{"name":"The 9th International Conference on Smart Media and Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127698371","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：