Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201616
Yu Zeng, Biyu Wan
Recently, salient object detection has achieved significant development. Unfortunately, existing methods mainly depend on color differences, not effective for textured images. This is because the visual patterns of textures cannot be well measured with existing methods. In this paper, we address this challenge by using windowed inherent variation to capture texture information and meanwhile performing edge-ware superpixel segmentation. Thus, superpixels can be well utilized to distinguish contents from textures for improving saliency detection. We further employ background and foreground priors via graph-based manifold ranking to improve saliency estimation. For evaluating our method, we collected 200 textured images from literature to build a dataset. With both qualitative and quantitative evaluations on our dataset and other two benchmarks, the results show that our approach can significantly promote saliency detection in textured images, compared with the other state-of-the-art methods.
{"title":"Saliency Detection in Textured Images","authors":"Yu Zeng, Biyu Wan","doi":"10.1109/ICCSE49874.2020.9201616","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201616","url":null,"abstract":"Recently, salient object detection has achieved significant development. Unfortunately, existing methods mainly depend on color differences, not effective for textured images. This is because the visual patterns of textures cannot be well measured with existing methods. In this paper, we address this challenge by using windowed inherent variation to capture texture information and meanwhile performing edge-ware superpixel segmentation. Thus, superpixels can be well utilized to distinguish contents from textures for improving saliency detection. We further employ background and foreground priors via graph-based manifold ranking to improve saliency estimation. For evaluating our method, we collected 200 textured images from literature to build a dataset. With both qualitative and quantitative evaluations on our dataset and other two benchmarks, the results show that our approach can significantly promote saliency detection in textured images, compared with the other state-of-the-art methods.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"371 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133735730","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}
Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201872
Min Li, Yun Guo, Hongge Zhao, Peipei Gao, Gang Wang
In this study, an innovative curriculum construction scheme, which combined the application of MOOC and SPOC was introduced in a detailed manner, including the overall planning of the curriculum design, as well as the construction scheme of MOOC+SPOC. A comparison was conducted with the teaching effectiveness before and after utilizing the SPOC+MOOC curriculum design in higher education, taking the Computer Fundamentals course as an example. What’s more, a survey based on questionnaires were conducted to investigate students’ evaluation of this innovative curriculum construction scheme.
{"title":"The Innovative Curriculum Construction of \"Computer Fundamentals\" Course Based on SPOC+MOOC in Higher Education","authors":"Min Li, Yun Guo, Hongge Zhao, Peipei Gao, Gang Wang","doi":"10.1109/ICCSE49874.2020.9201872","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201872","url":null,"abstract":"In this study, an innovative curriculum construction scheme, which combined the application of MOOC and SPOC was introduced in a detailed manner, including the overall planning of the curriculum design, as well as the construction scheme of MOOC+SPOC. A comparison was conducted with the teaching effectiveness before and after utilizing the SPOC+MOOC curriculum design in higher education, taking the Computer Fundamentals course as an example. What’s more, a survey based on questionnaires were conducted to investigate students’ evaluation of this innovative curriculum construction scheme.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"448 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134458834","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}
Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201680
Sena Seneviratne, L. D. Silva, Jie Hu, Wenxing Hong, Judith Beveridge, D. Levy
In this paper, the introduction of the new OS kernel internals for the new metrics for the grid and cloud performance prediction is explained. This new introduction is named as Division of Load (DOL). The DOL method breaks down the CPU load by individual users and then separates the Disk IO load from the CPU load. In the first part, the concepts of the load signals are shown theoretically and experimentally as these metrics are introduced into the kernel for the first time. In the second part, the required code changes which are introduced to the OS kernel are discussed. The separation will help to collect the computer loads separately for individual users as CPU loads and Disk IOs loads. Such a move will open Grid, Cluster and Cloud Performance Predictors to use the divided data archives for better predictability of both CPU and Disk IO loads. Many existing Grid and Cloud resource prediction engines are going to be advantaged by this data purification and specialization.
{"title":"Introduction of the new Operating System Kernel Internals for the New Metrics for the Performance Prediction on the Clouds","authors":"Sena Seneviratne, L. D. Silva, Jie Hu, Wenxing Hong, Judith Beveridge, D. Levy","doi":"10.1109/ICCSE49874.2020.9201680","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201680","url":null,"abstract":"In this paper, the introduction of the new OS kernel internals for the new metrics for the grid and cloud performance prediction is explained. This new introduction is named as Division of Load (DOL). The DOL method breaks down the CPU load by individual users and then separates the Disk IO load from the CPU load. In the first part, the concepts of the load signals are shown theoretically and experimentally as these metrics are introduced into the kernel for the first time. In the second part, the required code changes which are introduced to the OS kernel are discussed. The separation will help to collect the computer loads separately for individual users as CPU loads and Disk IOs loads. Such a move will open Grid, Cluster and Cloud Performance Predictors to use the divided data archives for better predictability of both CPU and Disk IO loads. Many existing Grid and Cloud resource prediction engines are going to be advantaged by this data purification and specialization.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"158 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113987016","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}
Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201755
A. Rababaah
This paper presents the development of a new small programming language named SIMPLE, "Simple Imperative-Model Programming Language for Education. The motivations for the development of this new language stems from the lack of literature for practical efforts and guidelines to develop programming languages bottom-up from scratch. We believe that exposing students to the process of creating a programming language carries significant educational benefits and real experience in a serious project. Further, we discuss the language grammar and demonstrate its main elements and features. The new language has been tested extensively using 60+ programs designed to evaluate all elements of the language
{"title":"A New Simple Programming Language for Education","authors":"A. Rababaah","doi":"10.1109/ICCSE49874.2020.9201755","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201755","url":null,"abstract":"This paper presents the development of a new small programming language named SIMPLE, \"Simple Imperative-Model Programming Language for Education. The motivations for the development of this new language stems from the lack of literature for practical efforts and guidelines to develop programming languages bottom-up from scratch. We believe that exposing students to the process of creating a programming language carries significant educational benefits and real experience in a serious project. Further, we discuss the language grammar and demonstrate its main elements and features. The new language has been tested extensively using 60+ programs designed to evaluate all elements of the language","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116108769","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}
Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201656
Ping Zong, J. Jiang, Jun Qin
With the rapid development of big data, the scale, dimensions, diversity and sparsity of high-dimensional data restrict the effectiveness of traditional clustering algorithms. This paper mainly focuses on high-dimensional data clustering. Starting from the traditional K-means clustering algorithm and subspace clustering algorithm based on self-representation model, an improved algorithm is designed and implemented based on the existing clustering algorithm in this paper. The improved algorithm has better clustering quality by combining the "distance optimization method" and the "density method" to determine the initial clustering center. The feasibility and effectiveness of improved algorithm are verified through simulation experiments.
{"title":"Study of High-Dimensional Data Analysis based on Clustering Algorithm","authors":"Ping Zong, J. Jiang, Jun Qin","doi":"10.1109/ICCSE49874.2020.9201656","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201656","url":null,"abstract":"With the rapid development of big data, the scale, dimensions, diversity and sparsity of high-dimensional data restrict the effectiveness of traditional clustering algorithms. This paper mainly focuses on high-dimensional data clustering. Starting from the traditional K-means clustering algorithm and subspace clustering algorithm based on self-representation model, an improved algorithm is designed and implemented based on the existing clustering algorithm in this paper. The improved algorithm has better clustering quality by combining the \"distance optimization method\" and the \"density method\" to determine the initial clustering center. The feasibility and effectiveness of improved algorithm are verified through simulation experiments.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115158013","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}
Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201664
Shuang Li, Ran Li, Y. Lou, Yingnan Yu
Using virtual reality and other techniques, the system can fully and clearly display the anatomical structure under the beating state of the heart, and systematically realize the online students'autonomous simulation training; offline classroom virtual intelligence teaching; surgical operation room simulation; intelligent evaluation, etc., and through multi-modal learning methods, students can fully understand and master the relationship between adjacency and spatial position between anatomical structures, and have a comprehensive and in-depth understanding of myocardial diseases, coronary atherosclerosis, pericarditis treatment and pacemaker installation.
{"title":"Research and Development of Teaching System of 3D Cardiac Anatomy Based on Virtual Reality","authors":"Shuang Li, Ran Li, Y. Lou, Yingnan Yu","doi":"10.1109/ICCSE49874.2020.9201664","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201664","url":null,"abstract":"Using virtual reality and other techniques, the system can fully and clearly display the anatomical structure under the beating state of the heart, and systematically realize the online students'autonomous simulation training; offline classroom virtual intelligence teaching; surgical operation room simulation; intelligent evaluation, etc., and through multi-modal learning methods, students can fully understand and master the relationship between adjacency and spatial position between anatomical structures, and have a comprehensive and in-depth understanding of myocardial diseases, coronary atherosclerosis, pericarditis treatment and pacemaker installation.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123160531","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}
Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201710
Hexiang Tan, Wen‐Jinn Chen, Libing Qin, Jie Zhu, Haiping Huang
We investigate a deadline-constrained task scheduling problem in the fog computing environments where tasks can be offloaded to heterogeneous resources. Three kinds of resources are involved: mobile device, fog device and cloud server. The objective is to schedule all the tasks with minimum energy consumption. We develop an energy-aware strategy and propose a critical path based iterative algorithm which can obtain the optimal solution in polynomial time complexity. We also discuss the cases when no feasible solution exists. Experimental results show that the proposal is robust and effective for the problems under study.
{"title":"Energy-aware and Deadline-constrained Task Scheduling in Fog Computing Systems","authors":"Hexiang Tan, Wen‐Jinn Chen, Libing Qin, Jie Zhu, Haiping Huang","doi":"10.1109/ICCSE49874.2020.9201710","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201710","url":null,"abstract":"We investigate a deadline-constrained task scheduling problem in the fog computing environments where tasks can be offloaded to heterogeneous resources. Three kinds of resources are involved: mobile device, fog device and cloud server. The objective is to schedule all the tasks with minimum energy consumption. We develop an energy-aware strategy and propose a critical path based iterative algorithm which can obtain the optimal solution in polynomial time complexity. We also discuss the cases when no feasible solution exists. Experimental results show that the proposal is robust and effective for the problems under study.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124453605","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}
Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201640
Kohki Nakane, Rentaro Ono, Shota Yamamoto, M. Takada, Fumiya Kinoshita, A. Sugiura, Y. Matsuura, Kazuhiro Fujikake, H. Takada
We have applied this artificial intelligence (AI) system to numerical simulations of the stabilogram whose randomness is remarkably greater than that of the other bio-signal in accordance with the nonlinear analysis. We have succeeded in findings of the mathematical models of the body sway in the elderly with use of the Generative Adversarial Networks (GANs). Trying to visualize internal state of the discriminator layer in our GAN, we can discuss how the AI captures the feature of patterns in the stabilograms recorded during the 3D sickness. Especially in the stabilograms measured during the 3D sickness, cusp patterns could be extracted as a high contribution to the output of the discriminator.
{"title":"Numerical Analysis of Body Sway for Evaluation of 3D Sickness","authors":"Kohki Nakane, Rentaro Ono, Shota Yamamoto, M. Takada, Fumiya Kinoshita, A. Sugiura, Y. Matsuura, Kazuhiro Fujikake, H. Takada","doi":"10.1109/ICCSE49874.2020.9201640","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201640","url":null,"abstract":"We have applied this artificial intelligence (AI) system to numerical simulations of the stabilogram whose randomness is remarkably greater than that of the other bio-signal in accordance with the nonlinear analysis. We have succeeded in findings of the mathematical models of the body sway in the elderly with use of the Generative Adversarial Networks (GANs). Trying to visualize internal state of the discriminator layer in our GAN, we can discuss how the AI captures the feature of patterns in the stabilograms recorded during the 3D sickness. Especially in the stabilograms measured during the 3D sickness, cusp patterns could be extracted as a high contribution to the output of the discriminator.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122626269","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}
Pub Date : 2020-08-01DOI: 10.1109/ICCSE49874.2020.9201713
Lingyun Wang, Caiquan Xiong, Na Deng
The joint extraction of entity and relation is an important task in information extraction. Previously, most models in entity relationship extraction assumed that the relationship was discrete. Unfortunately, this assumption is often violated. In order to solve the problem of overlapping in the entity relationship, considering the relationship between extraction under the premise of have the features of multiple targets, this paper puts forward a multi-objective depend on the relationship between extraction model, which transforms the relationship extraction task into a sequence-tagged task. The model uses Iterated Dilated Convolutional Neural Network (IDCNN) and BiLSTM to encode the words in order to more fully extract the semantics in the text. First, determine the target entity subject (s), and then predict all corresponding object (o) and relationship (r) according to s. Experiments show that our model is significantly better than the baseline methods.
{"title":"A Research on Overlapping Relationship Extraction Based on Multi-objective Dependency","authors":"Lingyun Wang, Caiquan Xiong, Na Deng","doi":"10.1109/ICCSE49874.2020.9201713","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201713","url":null,"abstract":"The joint extraction of entity and relation is an important task in information extraction. Previously, most models in entity relationship extraction assumed that the relationship was discrete. Unfortunately, this assumption is often violated. In order to solve the problem of overlapping in the entity relationship, considering the relationship between extraction under the premise of have the features of multiple targets, this paper puts forward a multi-objective depend on the relationship between extraction model, which transforms the relationship extraction task into a sequence-tagged task. The model uses Iterated Dilated Convolutional Neural Network (IDCNN) and BiLSTM to encode the words in order to more fully extract the semantics in the text. First, determine the target entity subject (s), and then predict all corresponding object (o) and relationship (r) according to s. Experiments show that our model is significantly better than the baseline methods.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126142722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose a stacked model with autoencoder for financial time series prediction. A stacked autoencoder model is used for feature extraction of high-dimensional stock factors. The factors after dimensionality reduction serve as input to the stacked model to predict the next-day returns of the stocks. In this paper, the stacked autoencoder not only has the effect of reducing the dimension, but also eliminates the redundant information in the data to a certain extent, which can effectively improve the predictive capacity of the model. The constituent stocks of CSI300 are used as backtest samples, and the experiment shows that the stacked model with autoencoder can obtain more than 50% of excess return in 2019.
{"title":"Stacked Model with Autoencoder for Financial Time Series Prediction","authors":"Haiying Zhang, Qiaomei Liang, Rongqi Wang, Qingqiang Wu","doi":"10.1109/ICCSE49874.2020.9201745","DOIUrl":"https://doi.org/10.1109/ICCSE49874.2020.9201745","url":null,"abstract":"In this paper, we propose a stacked model with autoencoder for financial time series prediction. A stacked autoencoder model is used for feature extraction of high-dimensional stock factors. The factors after dimensionality reduction serve as input to the stacked model to predict the next-day returns of the stocks. In this paper, the stacked autoencoder not only has the effect of reducing the dimension, but also eliminates the redundant information in the data to a certain extent, which can effectively improve the predictive capacity of the model. The constituent stocks of CSI300 are used as backtest samples, and the experiment shows that the stacked model with autoencoder can obtain more than 50% of excess return in 2019.","PeriodicalId":350703,"journal":{"name":"2020 15th International Conference on Computer Science & Education (ICCSE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126039564","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：