Proceedings of the 3rd International Conference on Computer Science and Application Engineering最新文献_第9页

Workflow-based Knowledge Flow Modeling and Research: Combination of Knowledge and Workflow 基于工作流的知识流建模与研究:知识与工作流的结合

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3362051

Xingzhou Li, Botao Zhang

引用次数: 1

Open-Category Classification of Hyperspectral Images based on Convolutional Neural Networks 基于卷积神经网络的高光谱图像开放分类

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3362049

Tingting Huang, Shuang Wang, Geng Zhang, Xueji Wang, Song Liu

{"title":"Open-Category Classification of Hyperspectral Images based on Convolutional Neural Networks","authors":"Tingting Huang, Shuang Wang, Geng Zhang, Xueji Wang, Song Liu","doi":"10.1145/3331453.3362049","DOIUrl":"https://doi.org/10.1145/3331453.3362049","url":null,"abstract":"The application of the hyperspectral image (HSI) classification has become increasingly important in industry, agriculture and military. In recent years, the accuracy of HIS classification has been greatly improved through deep learning based methods. However, most of the deep learning models tend to classify all the samples into categories that exist in the training data. In real-world classification tasks, it is difficult to obtain samples from all categories that exist in the whole hyperspectral image. In this paper, we design a framework based on convolutional neural networks and probability thresholds(CNPT) in order to deal with the open-category classification(OCC) problem. Instead of classifying samples of categories that do not exist in the training process to be any known class, the proposed method mark them as unseen category. We first get samples of unseen class from labeled data. With a lightweight convolutional network that fully uses the spectral-spatial information of HSI, we obtain the probabilities for each seen class for every sample. By adding a threshold to the maximum probabilities, we classify some samples to unseen category. A balanced score called Fue which considers both the recall rate of unseen class and the overall accuracy of seen classes is proposed in this paper, and we use it to select the threshold and evaluate the performance of CNPT. The experimental results show that our proposed algorithm performs well on hyperspectral data, and has generalizability on different datasets.","PeriodicalId":162067,"journal":{"name":"Proceedings of the 3rd International Conference on Computer Science and Application Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128540744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Building Extraction Using Mask Scoring R-CNN Network 使用掩码评分R-CNN网络的建筑提取

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3361644

Yiwen Hu, Fenglin Guo

引用次数: 5

Design and Implementation of Medium-Range Weather Forecast Operational System 中期天气预报业务系统的设计与实现

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3361674

Lian-qing Yu, Yong Li, Zhiming Kang

{"title":"Design and Implementation of Medium-Range Weather Forecast Operational System","authors":"Lian-qing Yu, Yong Li, Zhiming Kang","doi":"10.1145/3331453.3361674","DOIUrl":"https://doi.org/10.1145/3331453.3361674","url":null,"abstract":"Medium-range weather forecast has been playing an important role in the decision making process of nationwide disaster prevention and mitigation, and assurance of major social activities. Therefore the construction of a medium-range weather forecast platform is the key to improve operation capability and important for decision makers. In response to the demanding requirements of real-time availability and interactive customization of prediction products in current forecast operations, both a desktop client system and web client system have been developed. The two systems share common backend services that offer features including real-time data collection, processing and database management, automatic creation of graphics products, and data statistics calculation. The clients provide a variety of functionalities such as interactive analysis and visualization of atmospheric circulation and observation data, search of history statistical data, etc. Some innovative technologies including organization of ensemble forecast data, concurrent calculation of forecast products, and a united two- and three-dimensional graphics rendering engine are discussed as well. With the application of the platform in daily operations, the abilities of live monitoring, forecast analysis and model output post-processing for disastrous and extreme synoptic processes have been greatly improved thanks to the introduction of brand-new ensemble products and comprehensive customization for data visualization.","PeriodicalId":162067,"journal":{"name":"Proceedings of the 3rd International Conference on Computer Science and Application Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117053247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fine Granular Multilevel Parallel Algorithm for HEVC Decoding Based on Tilera-GX36 Multi-core Platform 基于Tilera-GX36多核平台的HEVC解码细粒度多级并行算法

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3361646

Yi Li, D. Hu, Wenxiang Zhang

{"title":"Fine Granular Multilevel Parallel Algorithm for HEVC Decoding Based on Tilera-GX36 Multi-core Platform","authors":"Yi Li, D. Hu, Wenxiang Zhang","doi":"10.1145/3331453.3361646","DOIUrl":"https://doi.org/10.1145/3331453.3361646","url":null,"abstract":"This paper presents a fine granular multilevel parallel algorithm for HEVC decoding, which is focus on two modules: the pixel reconstruction and the in-loop filter (ILF). Firstly, in the pixel reconstruction module, the problem of unbalanced load among decoding threads may occur in parallel decoding algorithm based on CTU rows, like wavefront parallel processing (WPP), because there may be big differences in the processing complexity of CTUs within various CTU rows. In order to solve this issue, we propose a fine granular parallel algorithm based on WPP. Then, a fast fusion ILF algorithm has been presented in the ILF module, which realizes the deep coupling between DBF and SAO by a new CTU-like process unit. Furthermore, the introduction of pipeline parallel technology makes a latency reduction between the two modules. We implement our method on Tilera-GX36 multi-core platform, each task executed by a thread bound to a separate core, which makes full use of the parallel computing performance. The experimental results show that the speedup of our proposed algorithms are 1.2, 1.13 and 1.8 times higher than that of those previous schemes respectively.","PeriodicalId":162067,"journal":{"name":"Proceedings of the 3rd International Conference on Computer Science and Application Engineering","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116195947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Optimized Password Recovery based on GPUs for SM3 Algorithm 基于gpu的SM3算法优化密码恢复

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3361632

Hao Tian, Yan Li, Yangde Wang, Tang Peng, Shaopei Shi, Weidong Qiu

引用次数: 0

An Improved Algorithm based on KNN and Random Forest 一种基于KNN和随机森林的改进算法

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3360963

Jun Liang, Qin Liu, Nuihua Nie, Biqing Zeng, Zanbo Zhang

引用次数: 5

A Location Privacy Protection Scheme Based on Hybrid Encryption 一种基于混合加密的位置隐私保护方案

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3361312

Li Li, Zhengjuan Lv, Xiaohong Tong, Run-hua Shi

引用次数: 2

Fine-grained Construction of Semantic Technology Network for Technology Evolution Analysis 面向技术演化分析的语义技术网络的细粒度构建

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3361638

Xiaoman Li, Hongyan Song, Xuefu Zhang, Qian Xu

{"title":"Fine-grained Construction of Semantic Technology Network for Technology Evolution Analysis","authors":"Xiaoman Li, Hongyan Song, Xuefu Zhang, Qian Xu","doi":"10.1145/3331453.3361638","DOIUrl":"https://doi.org/10.1145/3331453.3361638","url":null,"abstract":"As a basic tool for technology evolution analysis, technology network can visualize the relationship among technologies in different patents. However, the current constructions of technology network only represent common technical information, and cannot reflect different types of technical information. We propose a new approach to construct a fine-grained technology network and display technical information from multiple perspectives. Based on the Subject-Action-Object (SAO) structures extracted from patent documents, we first classify the technical information, and then investigate the semantic relationship among different types of technical information. Based on that, single-type and multi-type technology networks are constructed, which can demonstrate different types of technical information and make the technology evolution analysis easier and more reliable. Finally, taking the Nano-fertilizer patents as a data source, we construct a fine-grained construction of technology network, which might help identify fundamental and emerging technologies in the Nano-fertilizer field.","PeriodicalId":162067,"journal":{"name":"Proceedings of the 3rd International Conference on Computer Science and Application Engineering","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126991321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Novel Process Mining Algorithm to Discover Non-free Choice Construct from Event Logs 一种从事件日志中发现非自由选择结构的过程挖掘算法

Proceedings of the 3rd International Conference on Computer Science and Application Engineering Pub Date : 2019-10-22 DOI: 10.1145/3331453.3360956

Jinjin Yuan, Chenchen Duan, Qingjie Wei

引用次数: 1