M. Z. Islam, Daizong Liu, Kewei Wang, Pan Zhou, Li Yu, D. Wu
The medical services in Bangladesh are shortage nowadays; people are suffering from getting the correct treatment from the hospital. With the low proportion of the doctors and the low per capita salary in Bangladesh, patients need to spend more money to get the appropriate treatments. Therefore, it is necessary to apply modern information technologies by which the scaffold between the patients and specialists can be reduced, and the patients can take proper treatment at a lower cost. Fortunately, we can solve this critical problem by utilizing interaction among electrical devices. With the big data collected from these devices, machine learning is a powerful tool for the data analytics because of its high accuracy, lower computational costs, and lower power consumption. This research is based on a case of study by the incorporation of the database, mobile application, web application and develops a novel platform through which the patients and the doctors can interact. In addition, the platform helps to store the patients' health data to make the final prediction using machine learning methods to get the proper healthcare treatment with the help of the machines and the doctors. The experiment result shows the high accuracy over 95% of the disease detection using machine learning methods, with the cost 90% lower than the local hospital in Bangladesh, which provides the strong support to implement of our platform in the remote area of the country.
{"title":"A Case Study of HealthCare Platform using Big Data Analytics and Machine Learning","authors":"M. Z. Islam, Daizong Liu, Kewei Wang, Pan Zhou, Li Yu, D. Wu","doi":"10.1145/3341069.3342980","DOIUrl":"https://doi.org/10.1145/3341069.3342980","url":null,"abstract":"The medical services in Bangladesh are shortage nowadays; people are suffering from getting the correct treatment from the hospital. With the low proportion of the doctors and the low per capita salary in Bangladesh, patients need to spend more money to get the appropriate treatments. Therefore, it is necessary to apply modern information technologies by which the scaffold between the patients and specialists can be reduced, and the patients can take proper treatment at a lower cost. Fortunately, we can solve this critical problem by utilizing interaction among electrical devices. With the big data collected from these devices, machine learning is a powerful tool for the data analytics because of its high accuracy, lower computational costs, and lower power consumption. This research is based on a case of study by the incorporation of the database, mobile application, web application and develops a novel platform through which the patients and the doctors can interact. In addition, the platform helps to store the patients' health data to make the final prediction using machine learning methods to get the proper healthcare treatment with the help of the machines and the doctors. The experiment result shows the high accuracy over 95% of the disease detection using machine learning methods, with the cost 90% lower than the local hospital in Bangladesh, which provides the strong support to implement of our platform in the remote area of the country.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"24 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":"129848498","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}
To solve the problem that OpenStack cloud platforms can not well support the migration of virtual machines across clusters, several cross-cluster migration technologies are proposed. Based on a novel multi-cluster collabrative architecture, a cross-cluster static migration approach and a cross-cluster live migration approach are provided. The experiments of comparing our approachs with the original intra-cluster migration are carried out. The results show that the proposed approaches have nearly the same migration time cost but gain better performance in disaster tolerance.
{"title":"Research on Cross-Cluster Migration Technologies","authors":"Dingkun Song, Dong Li, Xiaobing Huang","doi":"10.1145/3341069.3342986","DOIUrl":"https://doi.org/10.1145/3341069.3342986","url":null,"abstract":"To solve the problem that OpenStack cloud platforms can not well support the migration of virtual machines across clusters, several cross-cluster migration technologies are proposed. Based on a novel multi-cluster collabrative architecture, a cross-cluster static migration approach and a cross-cluster live migration approach are provided. The experiments of comparing our approachs with the original intra-cluster migration are carried out. The results show that the proposed approaches have nearly the same migration time cost but gain better performance in disaster tolerance.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"1 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":"130267059","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}
Pedestrian attribute recognition is important for many subjects such as pedestrian tracking and person re-identification in monitoring scenario. Recently plenty of models address this task with deeply learned feature representations, but there still great potentials to make further progress due to some variations including low resolution, occlusion and so on. In this paper, we propose a new deep network structure for attribute classification, which takes advantage of multi-level features and an attention weighted scheme to combine multiple predictions from different layers. At last, we evaluate our method on PA-100K benchmark and the experimental results show the effectiveness of our proposed approach.
{"title":"Multi-Level Feature Learning for Pedestrian Attribute Recognition","authors":"Mengling Deng, Jianbiao He","doi":"10.1145/3341069.3342967","DOIUrl":"https://doi.org/10.1145/3341069.3342967","url":null,"abstract":"Pedestrian attribute recognition is important for many subjects such as pedestrian tracking and person re-identification in monitoring scenario. Recently plenty of models address this task with deeply learned feature representations, but there still great potentials to make further progress due to some variations including low resolution, occlusion and so on. In this paper, we propose a new deep network structure for attribute classification, which takes advantage of multi-level features and an attention weighted scheme to combine multiple predictions from different layers. At last, we evaluate our method on PA-100K benchmark and the experimental results show the effectiveness of our proposed approach.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"1 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":"129577819","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":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","authors":"","doi":"10.1145/3341069","DOIUrl":"https://doi.org/10.1145/3341069","url":null,"abstract":"","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"16 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":"126453143","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 particularity of the Web application of catering O2O platform makes its testing challenging, but the current research on its testing is relatively weak compared with the research on its design and development.This paper summarizes the research progress of Web platform testing methods in recent years.The Basic test contents and technologies, typical test models and automated testing tools of existing platforms are summarized.The current research hotspots and difficulties are analyzed, including the optimization of test models, the improvement and development of automated testing tools, the guarantee of test comprehensiveness, safety, stability and efficiency.Finally, the future research directions of the testing methods of catering O2O Web platform are discussed from three aspects: testing content, testing methods and testing tools.
{"title":"Survey of Testing Methods of O2O Catering Platform","authors":"Hefang Xu, Caihong Su, Shaoyu Wu, D. Tang","doi":"10.1145/3341069.3341070","DOIUrl":"https://doi.org/10.1145/3341069.3341070","url":null,"abstract":"The particularity of the Web application of catering O2O platform makes its testing challenging, but the current research on its testing is relatively weak compared with the research on its design and development.This paper summarizes the research progress of Web platform testing methods in recent years.The Basic test contents and technologies, typical test models and automated testing tools of existing platforms are summarized.The current research hotspots and difficulties are analyzed, including the optimization of test models, the improvement and development of automated testing tools, the guarantee of test comprehensiveness, safety, stability and efficiency.Finally, the future research directions of the testing methods of catering O2O Web platform are discussed from three aspects: testing content, testing methods and testing tools.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"64 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":"132927921","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}
Chinese writing in primary and secondary schools occupies an extremely important position in Chinese education. With the advent of natural language processing, the automatic e ssay review system has gradually matured, which has greatly promoted the development of composition writing. Especially the off-topic detection plays a key role in the automatic essay review system. We propose effective methods for off-topic detection. Firstly, we use Biterm-LDA combined with Doc2vec to inspect the topic and semantics of composition. Secondly, we propose a threshold calculation method based on the topic composition class center under different topic compositions. Finally, the ROC curve is employed to find the optimal threshold for each type of topic composition, then according to the optimal threshold, the off topic essay is judged. Experiments of the five types of topic composition show the average F1-score value of the off-topic detection reach about 65%.
{"title":"Off-topic Detection Model based on Biterm-LDA and Doc2vec","authors":"Pan Liu, Jie Liu, Xiaoli Ma, Jianshe Zhou","doi":"10.1145/3341069.3342989","DOIUrl":"https://doi.org/10.1145/3341069.3342989","url":null,"abstract":"Chinese writing in primary and secondary schools occupies an extremely important position in Chinese education. With the advent of natural language processing, the automatic e ssay review system has gradually matured, which has greatly promoted the development of composition writing. Especially the off-topic detection plays a key role in the automatic essay review system. We propose effective methods for off-topic detection. Firstly, we use Biterm-LDA combined with Doc2vec to inspect the topic and semantics of composition. Secondly, we propose a threshold calculation method based on the topic composition class center under different topic compositions. Finally, the ROC curve is employed to find the optimal threshold for each type of topic composition, then according to the optimal threshold, the off topic essay is judged. Experiments of the five types of topic composition show the average F1-score value of the off-topic detection reach about 65%.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"40 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":"129399560","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}
Shih-Hsiung Lee, Chien-Hui Yeh, Ting-Wei Hou, Chu-Sing Yang
As the theory of deep learning develops, object detection technology has been widely used in all fields. How to find objects accurately and quickly is one of the key technologies. A usage scenario to be solved is proposed here, that is how to facilitate object detection technology in waste sorting. Hence, in this paper, a lightweight deep learning model is proposed. The basic network architecture of SSD(Single Shot MultiBox Detector) is changed to AlexNet. In this way, the capacity on object detection of SSD is remained, and the model parameters are greatly reduced. The experimental results show that the modified model can recognize the categories of waste accurately.
{"title":"A Lightweight Neural Network Based on AlexNet-SSD Model for Garbage Detection","authors":"Shih-Hsiung Lee, Chien-Hui Yeh, Ting-Wei Hou, Chu-Sing Yang","doi":"10.1145/3341069.3341087","DOIUrl":"https://doi.org/10.1145/3341069.3341087","url":null,"abstract":"As the theory of deep learning develops, object detection technology has been widely used in all fields. How to find objects accurately and quickly is one of the key technologies. A usage scenario to be solved is proposed here, that is how to facilitate object detection technology in waste sorting. Hence, in this paper, a lightweight deep learning model is proposed. The basic network architecture of SSD(Single Shot MultiBox Detector) is changed to AlexNet. In this way, the capacity on object detection of SSD is remained, and the model parameters are greatly reduced. The experimental results show that the modified model can recognize the categories of waste accurately.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"1 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":"128486642","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}
Patric Kiel Navarro, Jihan Karla Cadongonan, Michael Reyes, J. D. Goma
Dental caries is one of the most common tooth diseases in the world which affects people of all ages. In this study, we developed a model that detects and locates smooth surface carious regions in frontal teeth images using Support Vector Machine and Decision Tree in MATLAB R2018a Classification Learner. A total of 45 images with smooth surface dental caries were used which consists of 30 training images and 15 images for testing and validation. Images are pre-processed using Histogram Equalization and are segmented further into 10x10 blocks where the set of color and texture features such as Intensity, Gradient, Hue, Saturation, and Entropy were extracted. The study showed significant results with an accuracy of 84% and 78% using Decision Tree and SVM respectively which proved the effectivity of the use of image processing techniques on classification and location of dental caries.
{"title":"Detecting Smooth Surface Dental Caries in Frontal Teeth Using Image Processing","authors":"Patric Kiel Navarro, Jihan Karla Cadongonan, Michael Reyes, J. D. Goma","doi":"10.1145/3341069.3341091","DOIUrl":"https://doi.org/10.1145/3341069.3341091","url":null,"abstract":"Dental caries is one of the most common tooth diseases in the world which affects people of all ages. In this study, we developed a model that detects and locates smooth surface carious regions in frontal teeth images using Support Vector Machine and Decision Tree in MATLAB R2018a Classification Learner. A total of 45 images with smooth surface dental caries were used which consists of 30 training images and 15 images for testing and validation. Images are pre-processed using Histogram Equalization and are segmented further into 10x10 blocks where the set of color and texture features such as Intensity, Gradient, Hue, Saturation, and Entropy were extracted. The study showed significant results with an accuracy of 84% and 78% using Decision Tree and SVM respectively which proved the effectivity of the use of image processing techniques on classification and location of dental caries.","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":"129902526","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}
Jacobi iteration based on finite difference and finite element discrete scheme is a kind of typical stencil computation in scientific computing. In this paper, we analyze the parallel optimization of Jacobi iteration in the real CFD codes on the Intel Many Integrated Core architecture, and get high performance. We use loop fusion, data structure transformation, subroutine and loop unrolling, cache blocking and some other optimization techniques in our implementation. We also collect hardware performance indicators through the open source performance analysis tools, in order to guide and verify the performance optimization on the many-core architectures. Experimental results on Intel Xeon Phi working in the native execution mode show that our Jacobi iteration can achieve 83.47% parallel efficiency and 4.73 speed ratio of vectorization with a 128 × 128 × 256 grid.
{"title":"Optimization of Jacobi Iteration on the Intel Xeon Phi","authors":"Wenxiang Yang, Jiming Zou, Liang Deng","doi":"10.1145/3341069.3341071","DOIUrl":"https://doi.org/10.1145/3341069.3341071","url":null,"abstract":"Jacobi iteration based on finite difference and finite element discrete scheme is a kind of typical stencil computation in scientific computing. In this paper, we analyze the parallel optimization of Jacobi iteration in the real CFD codes on the Intel Many Integrated Core architecture, and get high performance. We use loop fusion, data structure transformation, subroutine and loop unrolling, cache blocking and some other optimization techniques in our implementation. We also collect hardware performance indicators through the open source performance analysis tools, in order to guide and verify the performance optimization on the many-core architectures. Experimental results on Intel Xeon Phi working in the native execution mode show that our Jacobi iteration can achieve 83.47% parallel efficiency and 4.73 speed ratio of vectorization with a 128 × 128 × 256 grid.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"5 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":"125976482","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 SAT problem is one of basic issues of artificial intelligence and computer science. Maple solver is an algorithm solver that specializes in solving SAT problems. In order to improve the efficiency of the solver, decision level reward based branching heuristic was proposed. Firstly, this paper introduces its major framework and two excellent branching heuristics: Variable State Independent Decaying Sum(VSIDS) Decision Heuristic and Learning Rate Based(LRB) Branching Heuristic. Then, a new method named DLR is proposed in view of LRB considering the decision level rate. Finally, experimental results of different sets of instances indicate that the Maple solver with DLR strategy outperforms original version with LRB strategy by reducing the number of conflicts and decisions.
{"title":"Decision Level Reward Based Branching Heuristic in Maple Solver","authors":"Jing Sun","doi":"10.1145/3341069.3342971","DOIUrl":"https://doi.org/10.1145/3341069.3342971","url":null,"abstract":"The SAT problem is one of basic issues of artificial intelligence and computer science. Maple solver is an algorithm solver that specializes in solving SAT problems. In order to improve the efficiency of the solver, decision level reward based branching heuristic was proposed. Firstly, this paper introduces its major framework and two excellent branching heuristics: Variable State Independent Decaying Sum(VSIDS) Decision Heuristic and Learning Rate Based(LRB) Branching Heuristic. Then, a new method named DLR is proposed in view of LRB considering the decision level rate. Finally, experimental results of different sets of instances indicate that the Maple solver with DLR strategy outperforms original version with LRB strategy by reducing the number of conflicts and decisions.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"39 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":"125269783","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：