The urgent need for transformation and upgradation of China's shipbuilding industry can be met by intelligent design technology, enabling the implementation of innovative designs. Considering the multi-source, heterogeneous and multi-disciplinary characteristics of the design knowledge involved in these designs, this paper studies the key technology of intelligent outfitting design and knowledge base management system. By constructing the overall framework of intelligent outfitting design and knowledge base system, the Knowledge Based Engineering method is applied to the ship outfitting design for parameter calculation and intelligent selection of the equipment, as well as layout scheme recommendation and intelligent aided design. Designers can save significant design time by reusing the design knowledge and applying knowledge base management system for intelligent outfitting design.
{"title":"Design and Application of Knowledge Base Management System for Intelligent Outfitting Design","authors":"Yongjun Ji, Jianfeng Liu, Linke Wang, Xiaocai Hu, Zhen Yang, Zu-hua Jiang","doi":"10.1145/3341069.3341078","DOIUrl":"https://doi.org/10.1145/3341069.3341078","url":null,"abstract":"The urgent need for transformation and upgradation of China's shipbuilding industry can be met by intelligent design technology, enabling the implementation of innovative designs. Considering the multi-source, heterogeneous and multi-disciplinary characteristics of the design knowledge involved in these designs, this paper studies the key technology of intelligent outfitting design and knowledge base management system. By constructing the overall framework of intelligent outfitting design and knowledge base system, the Knowledge Based Engineering method is applied to the ship outfitting design for parameter calculation and intelligent selection of the equipment, as well as layout scheme recommendation and intelligent aided design. Designers can save significant design time by reusing the design knowledge and applying knowledge base management system for intelligent outfitting design.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132134001","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 sharp growth of security data and equipment resources in the security industry, the traditional management mode caused such problems as low utilization rate, poor flexibility, weak scheduling ability, insufficient scalability and serious waste. And at present, few researchers in the security industry use the idea of big data to analyze and process security data. In this paper, based on the idea of cloud computing and big data, the demand analysis of security industry data cloud management was completed, and by using cloud computing virtualization technology, the security industry big data platform was demonstrated and designed, realized the integration of resources and data within the security industry. The data application and processing cluster of security industry could be constructed by deploying computing nodes quickly, and computing resources could be allocated on demand to reduce redundant deployment of security management and waste of resources. The functions of security incident alarm management, security patrol management, security resource management, decision support, data operation and maintenance were realized. Through functional testing and performance testing, it was proved that the BDaaS cloud platform for security industry had greatly improved the data storage capacity, stability, security data processing efficiency and operation response speed of the original security management platform.
{"title":"Research and Implementation of BDaaS Cloud Platform for Security Industry","authors":"Lianqing Wang, Rong Che, Nie Jing","doi":"10.1145/3341069.3341077","DOIUrl":"https://doi.org/10.1145/3341069.3341077","url":null,"abstract":"with the sharp growth of security data and equipment resources in the security industry, the traditional management mode caused such problems as low utilization rate, poor flexibility, weak scheduling ability, insufficient scalability and serious waste. And at present, few researchers in the security industry use the idea of big data to analyze and process security data. In this paper, based on the idea of cloud computing and big data, the demand analysis of security industry data cloud management was completed, and by using cloud computing virtualization technology, the security industry big data platform was demonstrated and designed, realized the integration of resources and data within the security industry. The data application and processing cluster of security industry could be constructed by deploying computing nodes quickly, and computing resources could be allocated on demand to reduce redundant deployment of security management and waste of resources. The functions of security incident alarm management, security patrol management, security resource management, decision support, data operation and maintenance were realized. Through functional testing and performance testing, it was proved that the BDaaS cloud platform for security industry had greatly improved the data storage capacity, stability, security data processing efficiency and operation response speed of the original security management platform.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132429268","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}
Fayaz Ahmed Malik, Wenbin Ye, Qiaojun Chen, Dong Li
Recommendation systems in today's world are extremely important for any business and users. Matrix Factorization is extensively researched and widely used for recommendation purposes. But it uses the dot product which does not satisfy the inequality property. Therefore, different techniques are proposed to solve the problem such as Metric Factorization. Although the results of Metric Factorization improved, but there is always welcome for new research work. Therefore we use a multi-model ensemble technique called blending. This Technique consists of two steps. First we train several base models and get the predicted rating of movies, then use a linear regression to combine these results as a second-layer model to get a final rating of movies. The metrics RMSE and MAE are used for evaluation for different models. Our experimental results indicate that new blending approach is superior to other used techniques.
{"title":"Recommendation Algorithm based on Blending Learning","authors":"Fayaz Ahmed Malik, Wenbin Ye, Qiaojun Chen, Dong Li","doi":"10.1145/3341069.3342983","DOIUrl":"https://doi.org/10.1145/3341069.3342983","url":null,"abstract":"Recommendation systems in today's world are extremely important for any business and users. Matrix Factorization is extensively researched and widely used for recommendation purposes. But it uses the dot product which does not satisfy the inequality property. Therefore, different techniques are proposed to solve the problem such as Metric Factorization. Although the results of Metric Factorization improved, but there is always welcome for new research work. Therefore we use a multi-model ensemble technique called blending. This Technique consists of two steps. First we train several base models and get the predicted rating of movies, then use a linear regression to combine these results as a second-layer model to get a final rating of movies. The metrics RMSE and MAE are used for evaluation for different models. Our experimental results indicate that new blending approach is superior to other used techniques.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"734 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116989647","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 paper discusses a method to improve the performance of Chinese OCR by choosing a proper feature vector and synthetic classification. We compare two groups of features which are used to implement Chinese OCR System and demonstrate that the first group of features is more useful for static Chinese OCR System. By now feature extractions have been done either for local features or for global features. Classifications have been done by single classification. We propose synthetic features extraction and classification in this paper. We find that the result is improved by machine learning method. Later we apply the result in the area of off- and on-line signature verification system.
{"title":"A Study on Features for Improving Performance of Chinese OCR by Machine Learning","authors":"C. Kim, Jang Su Kim, U. J. Kim","doi":"10.1145/3341069.3342991","DOIUrl":"https://doi.org/10.1145/3341069.3342991","url":null,"abstract":"This paper discusses a method to improve the performance of Chinese OCR by choosing a proper feature vector and synthetic classification. We compare two groups of features which are used to implement Chinese OCR System and demonstrate that the first group of features is more useful for static Chinese OCR System. By now feature extractions have been done either for local features or for global features. Classifications have been done by single classification. We propose synthetic features extraction and classification in this paper. We find that the result is improved by machine learning method. Later we apply the result in the area of off- and on-line signature verification system.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125517447","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}
As the carrier of national culture, words and pictograms record the unique culture and history of each nation, but the number of existing ancient pictogram is very small, and it is difficult to collect them, which makes it difficult for the academic research of ancient pictogram and the recognition by deep learning. In addition, due to the preservation environment and their own particularities, the traditional data enhancement methods will cause problems such as wrong data label, inability to simulate real scenes, etc. So, it can't effectively expand the large-scale data. To solve these problems, this paper proposes a set of data enhancement methods for small data sets and natural scenes. For the small data set enhancement method, firstly, we use artificial data enhancement to enhance original data, and then a limited random affine transform is used to limit the extent and extent of the enhancement. For natural scenes, we use the DCGAN to fuse the natural scene image and the ancient pictogram to simulate the natural environment. Finally, the paper designs a neural network model to recognize the ancient pictogram. It is proved that the data enhancement method can solve the problem of insufficient data, and finally achieve 99% accuracy.
{"title":"Research on Data Enhanced Ancient Pictogram Recognition Method Based on Convolutional Neural Network","authors":"Lily Tian, Yutong Zheng, Qiao Cui","doi":"10.1145/3341069.3342993","DOIUrl":"https://doi.org/10.1145/3341069.3342993","url":null,"abstract":"As the carrier of national culture, words and pictograms record the unique culture and history of each nation, but the number of existing ancient pictogram is very small, and it is difficult to collect them, which makes it difficult for the academic research of ancient pictogram and the recognition by deep learning. In addition, due to the preservation environment and their own particularities, the traditional data enhancement methods will cause problems such as wrong data label, inability to simulate real scenes, etc. So, it can't effectively expand the large-scale data. To solve these problems, this paper proposes a set of data enhancement methods for small data sets and natural scenes. For the small data set enhancement method, firstly, we use artificial data enhancement to enhance original data, and then a limited random affine transform is used to limit the extent and extent of the enhancement. For natural scenes, we use the DCGAN to fuse the natural scene image and the ancient pictogram to simulate the natural environment. Finally, the paper designs a neural network model to recognize the ancient pictogram. It is proved that the data enhancement method can solve the problem of insufficient data, and finally achieve 99% accuracy.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129320880","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 improvement of the current scientific level, the use of mobile phones has become more and more common, and has become an indispensable tool in the lives of many people. Because the rich functions and use of mobile phones are very simple, while facilitating people's lives, it also provides criminals with a very important tool for committing crimes. In the traditional mobile phone forensics system, only some simple sorting or display of the extracted information of the mobile phone is required. To find out the inherent information, it is necessary to conduct artificial research. With the continuous expansion of mobile phone capacity, the burden of handling a large amount of mobile phone information on criminal investigators is growing. This article introduces a method applying basic word2vec and knowledge of statistics to explore the relationship between close friends and owners. It can help criminal investigation personnel to quickly clarify the relationship between the characters and provide some clue for the detection of the case.
{"title":"Method for Identifying Close Friend Relationship in Mobile Phone","authors":"Daodong Ming, Bin Xi, Shunxiang Wu, Baihua Chen, Chao Yi, Zhendong Liao","doi":"10.1145/3341069.3342984","DOIUrl":"https://doi.org/10.1145/3341069.3342984","url":null,"abstract":"With the improvement of the current scientific level, the use of mobile phones has become more and more common, and has become an indispensable tool in the lives of many people. Because the rich functions and use of mobile phones are very simple, while facilitating people's lives, it also provides criminals with a very important tool for committing crimes. In the traditional mobile phone forensics system, only some simple sorting or display of the extracted information of the mobile phone is required. To find out the inherent information, it is necessary to conduct artificial research. With the continuous expansion of mobile phone capacity, the burden of handling a large amount of mobile phone information on criminal investigators is growing. This article introduces a method applying basic word2vec and knowledge of statistics to explore the relationship between close friends and owners. It can help criminal investigation personnel to quickly clarify the relationship between the characters and provide some clue for the detection of the case.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121570644","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}
Xianbin Hong, Gautam Pal, S. Guan, Prudence W. H. Wong, Dawei Liu, K. Man, Xin Huang
Lifelong machine learning is a novel machine learning paradigm which can continually accumulate knowledge during learning. The knowledge extracting and reusing abilities enable the lifelong machine learning to solve the related problems. The traditional approaches like Naïve Bayes and some neural network based approaches only aim to achieve the best performance upon a single task. Unlike them, the lifelong machine learning in this paper focus on how to accumulate knowledge during learning and leverage them for the further tasks. Meanwhile, the demand for labeled data for training also be significantly decreased with the knowledge reusing. This paper suggests that the aim of the lifelong learning is to use less labeled data and computational cost to achieve the performance as well as or even better than the supervised learning.
{"title":"Semi-Unsupervised Lifelong Learning for Sentiment Classification: Less Manual Data Annotation and More Self-Studying","authors":"Xianbin Hong, Gautam Pal, S. Guan, Prudence W. H. Wong, Dawei Liu, K. Man, Xin Huang","doi":"10.1145/3341069.3342992","DOIUrl":"https://doi.org/10.1145/3341069.3342992","url":null,"abstract":"Lifelong machine learning is a novel machine learning paradigm which can continually accumulate knowledge during learning. The knowledge extracting and reusing abilities enable the lifelong machine learning to solve the related problems. The traditional approaches like Naïve Bayes and some neural network based approaches only aim to achieve the best performance upon a single task. Unlike them, the lifelong machine learning in this paper focus on how to accumulate knowledge during learning and leverage them for the further tasks. Meanwhile, the demand for labeled data for training also be significantly decreased with the knowledge reusing. This paper suggests that the aim of the lifelong learning is to use less labeled data and computational cost to achieve the performance as well as or even better than the supervised learning.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127750728","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：