e Informatica Softw. Eng. J.最新文献_第6页

Parallel Strategy to Factorize Fermat Numbers with Implementation in Maple Software 并行策略分解费马数及其在Maple软件中的实现

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.17706/jsw.16.4.167-173

Jianhui Li, Man-shing Liu

引用次数: 1

Research on Key Technologies of Data Service Based on Adaptive Deep Learning 基于自适应深度学习的数据服务关键技术研究

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.17706/jsw.16.3.130-134

Zhigang Zhao, Xinju Zhang

{"title":"Research on Key Technologies of Data Service Based on Adaptive Deep Learning","authors":"Zhigang Zhao, Xinju Zhang","doi":"10.17706/jsw.16.3.130-134","DOIUrl":"https://doi.org/10.17706/jsw.16.3.130-134","url":null,"abstract":"With the widespread adoption of big data technology, the diversity of data sources is continuously evolving. Data service technology is a technology derived from providing effective data interfaces for data applications. Based on the adaptive deep learning algorithm, this study proposes an improved service plan. First, the problem of randomly selecting the sending location of the data packet in the asynchronous random service scheme was analyzed, which leads to the waste of channel resources. Then, combined with the adaptive deep learning algorithm, an adaptive service scheme is specified. For the problem of large delay, the data frame is divided into multiple uniform position intervals. Therefore, the user learns the position interval until the user tends to select a position within the fixed position interval to send the data packet. Furthermore, in the algorithm’s iterative process, adaptive deep learning was used based on the ability of the algorithm to perform intensive learning. A detailed analysis of the various scenarios, the essential mode of the technology, and the computer simulation of the throughput and packet loss rate indicators of the proposed scheme in the three environments are provided to demonstrate the superiority of the proposed scheme.","PeriodicalId":11452,"journal":{"name":"e Informatica Softw. Eng. J.","volume":"29 1","pages":"130-134"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85980775","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

Large Remote Sensing Image Segmentation with Stitching Strategy Based on Dominant Color 基于主色拼接策略的大型遥感图像分割

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.17706/jsw.16.2.67-79

Haizhong Zhang, Ligang Wang, Fei-yang Tong

{"title":"Large Remote Sensing Image Segmentation with Stitching Strategy Based on Dominant Color","authors":"Haizhong Zhang, Ligang Wang, Fei-yang Tong","doi":"10.17706/jsw.16.2.67-79","DOIUrl":"https://doi.org/10.17706/jsw.16.2.67-79","url":null,"abstract":"Large remote sensing image segmentation is a crucial issue in object-based image analysis. It is common sense that a segmentation framework consists of three components: (1) dividing large remote sensing image into blocks for overcoming the constraint of computer memory; (2) executing segmentation algorithm for each block individually; (3) stitching segmentation results of all blocks into a complete result for eliminating artificial borders created by dividing blocks. However, there is a lack of mature technologies to eliminate artificial borders produced by dividing blocks. In this paper, we proposed a new stitching strategy based on the dominant color similarity measure and modified the traditional method of dominant color similarity measure to make it more suitable for measuring the similarity of two segmented regions. A multi-scale segmentation algorithm is adopted for segmenting each block. External memory is used to store intermediate segmentation results and exchange data with internal memory. We tested the algorithm with three different images and validated that the algorithm can implement the segmentation for large remote sensing images in a common computer. Experiments demonstrate that the stitching strategy based on the similarity measure of dominant color can effectively eliminate artificial borders.","PeriodicalId":11452,"journal":{"name":"e Informatica Softw. Eng. J.","volume":"89 1","pages":"67-79"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78372234","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: 2

Mining Non-Functional Requirements using Machine Learning Techniques 使用机器学习技术挖掘非功能需求

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.37190/e-inf210105

Rajni Jindal, R. Malhotra, Abha Jain, A. Bansal

引用次数: 2

Multi-view learning for software defect prediction 软件缺陷预测的多视图学习

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.37190/e-inf210108

Elife Ozturk Kiyak, Derya Birant, K. Birant

引用次数: 0

Applying Statistical Machine Learning Methods to Analysis Differences in the Severity Level of COVID-19 among Countries 应用统计机器学习方法分析各国COVID-19严重程度差异

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.17706/jsw.16.5.219-234

Wen Yin, Chenchen Pan, Nanyi Deng, Dong-lin Ji

引用次数: 0

Feature Extraction with Apparent to Semantic Channels for Object Detection 基于表观到语义通道的特征提取用于目标检测

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.17706/jsw.16.4.157-166

Lei Zhao, Jia Su, Zhiping Shi, Yong Guan

{"title":"Feature Extraction with Apparent to Semantic Channels for Object Detection","authors":"Lei Zhao, Jia Su, Zhiping Shi, Yong Guan","doi":"10.17706/jsw.16.4.157-166","DOIUrl":"https://doi.org/10.17706/jsw.16.4.157-166","url":null,"abstract":"This paper focuses on using traditional image processing algorithms with some apparent-to-semantic features to improve the detection accuracy. Based on the optimization of Faster R-CNN algorithm, a mainstream framework in current object detection scenario, the multi-channel features are achieved by combining traditional image semantic feature algorithms (like Integral Channel Feature (ICF), Histograms of Gradient (HOG), Local Binary Pattern (LBF), etc.) and advanced semantic feature algorithms (like segmentation, heatmap, etc.). In order to realize the joint training of the original image and the above feature extraction algorithms, a unique network for increasing the accuracy of object detection and minimizing system weight called Multi-Channel Feature Network (MCFN) is proposed. The function of MCFN is to provide a multi-channel interface, which is not limited to the RGB component of a single picture, nor to the number of input channels. The experimental result shows the relationship between the number of additional channels, performance of model and accuracy. Compared with the basic Faster R-CNN structure, this result is based on the case of two additional channels. And the universal Mean Average Precision (mAP) can be improved by 2%-3%. When the number of extra channels is increased, the accuracy will not increase linearly. In fact, system performance starts to fluctuate in a range after the number of additional channels reaches six.","PeriodicalId":11452,"journal":{"name":"e Informatica Softw. Eng. J.","volume":"20 1","pages":"157-166"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90832988","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

Creation of Digital Learning Kingdom to Support Online Learning during the COVID-19 Outbreak

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.17706/jsw.16.5.208-218

Thanyawich Vicheanpant

引用次数: 1

Towards Practice and Principle Adoption through Continuous DevOps Leadership 通过持续的DevOps领导实现实践和原则的采用

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.17706/jsw.16.1.1-13

Krikor Maroukian

引用次数: 1

Software Deterioration Control Based on Issue Reports 基于问题报告的软件劣化控制

e Informatica Softw. Eng. J. Pub Date : 2021-01-01 DOI: 10.37190/e-inf210106

O. Bushehrian, M. Sayari, P. Shamsinejad

引用次数: 1