Proceedings of the XV Brazilian Symposium on Information Systems最新文献_第3页

Exploring Deep Features and Transfer Learning for Plant Species Recognition 探索植物物种识别的深度特征和迁移学习

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330264

Marcondes Coelho Feitoza, Wanderson Barcelos da Silva, R. Calumby

{"title":"Exploring Deep Features and Transfer Learning for Plant Species Recognition","authors":"Marcondes Coelho Feitoza, Wanderson Barcelos da Silva, R. Calumby","doi":"10.1145/3330204.3330264","DOIUrl":"https://doi.org/10.1145/3330204.3330264","url":null,"abstract":"In recent years, with the evolution of the Convolutional Neural Networks, the automatic recognition of plant species from images became a very relevant research topic for scientists, researchers, and students in the field of botany. However, some problems related to the selection of features that best represent the characteristics of a particular species are still challenging due to the great variability of these characteristics within images from the same species and also the similarity of some characteristics between different species. In this sense, we propose a comparative study of Deep Convolutional Neural Networks to extract the feature vectors, here called \"Deep Features\", from the images of multi-organ plant observations. Moreover, eight variations of the Support Vector Machine (SVM) classifier were used for the assessment of the impact of three different Deep Features on the automatic image-based recognition of plant species. The evaluation protocol adopted for the classifiers was the Stratified 10-fold Cross Validation. As a result, the experiments demonstrate that higher dimensional Deep Features, in our case based on VGG-16 and VGG-19 networks, when exploited with the polynomial kernel SVM classifier and the One-vs-Rest decomposition method presented better classification effectiveness in the proposed study. Beyond it, this work highlights the fact that even in the context of transfer learning with deep features, the adequate selection of the baseline network is extremely important.","PeriodicalId":348938,"journal":{"name":"Proceedings of the XV Brazilian Symposium on Information Systems","volume":"337 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115889614","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: 3

ICT Governance: A View of Adoption of Best Practices in Enterprises of Sergipe State 信息通信技术治理:对塞尔希佩州企业采用最佳做法的看法

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330268

Claudio Junior Nascimento da Silva, Quelita A. D. S. Ribeiro, M. S. Soares, R. Nascimento

引用次数: 5

Louvre 罗浮宫

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.5040/9781350096462.0141

Marcelo Iury S. Oliveira, Bernadette Farias Lóscio

引用次数: 3

Semantic Enrichment of Web Data for the Provision of an Unified Data Repository of Brazilian Missing Persons 为提供巴西失踪人员统一数据存储库而对Web数据进行语义充实

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330267

Jorão Gomes Jr., Nicolas Ferranti, Jairo Francisco de Souza

引用次数: 0

LaNa2

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330281

Adolfo P. Guimarães, T. Bispo, A. Azevedo, Hendrik T. Macedo

引用次数: 0

A Domain-Sensitive Threshold Derivation Method 一种域敏感阈值推导方法

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330252

Allan Mori, Gustavo Vale, Elder Cirilo, Eduardo Figueiredo

{"title":"A Domain-Sensitive Threshold Derivation Method","authors":"Allan Mori, Gustavo Vale, Elder Cirilo, Eduardo Figueiredo","doi":"10.1145/3330204.3330252","DOIUrl":"https://doi.org/10.1145/3330204.3330252","url":null,"abstract":"Software metrics provide means to quantify several attributes of information systems. The effective measurement is dependent of appropriate metric thresholds as they allow characterizing the quality of information systems. Several methods have been proposed to derive metric thresholds, however, previous methods do not take characteristics of software domains into account, such as the difference between size and complexity of systems from different domains. Instead, they rely on (generic) thresholds that are derived from heterogeneous systems. Although derivation of reliable thresholds has long been a concern, we also lack empirical evidence about threshold variation across distinct mobile software domains. This paper proposes a domain-sensitive method to derive thresholds that respects metric statistics and is based on benchmarks of systems from the same domain. To evaluate our method, we manually mined one hundred mobile systems from Fossdroid, measured them using a set of seven well-known metrics, derived thresholds, and validated them through qualitative and quantitative analyses. As a result, we observed that our method gathered more reliable thresholds considering software domain as a factor when building benchmarks for threshold derivation.","PeriodicalId":348938,"journal":{"name":"Proceedings of the XV Brazilian Symposium on Information Systems","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132512103","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

UFJF-MLTK: a framework for machine learning algorithms UFJF-MLTK:一个机器学习算法框架

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330273

Mateus Coutinho Marim, A. M. Oliveira, Saulo Moraes Villela

引用次数: 0

Level UP: Mapping Hard Skills of IT Practitioners to support the Project Management 升级:映射IT从业者的硬技能，以支持项目管理

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330211

V. Milon, Ricardo Araújo, Osenias Oliveira, Andréia Vieira, Adriano Mendes, Luís Braga, B. Ferreira

{"title":"Level UP: Mapping Hard Skills of IT Practitioners to support the Project Management","authors":"V. Milon, Ricardo Araújo, Osenias Oliveira, Andréia Vieira, Adriano Mendes, Luís Braga, B. Ferreira","doi":"10.1145/3330204.3330211","DOIUrl":"https://doi.org/10.1145/3330204.3330211","url":null,"abstract":"Mapping skills is important for software development organizations. Knowing the skills of the company practitioners helps the managers in making decisions to team building and to know what skills are necessary to development of projects. Identifying the adequate practitioner can contribute to good quality and minimize the time spent on the project. To optimize the process of team formation and management of competences, a software company carried out a process of mapping the skills of professionals in the area of software development. The process of identifying and organizing the competencies was carried out between the members of the development teams and the managers. From the mapping, we developed a tool that helped managers to have an overview of the company's competencies and facilitate the decisions making about which practitioners to allocate in each project, identify training needed to acquire competencies, and if was necessary contracting other practitioners. In addition, practitioners could gain insight into skills they could improve or acquire to fulfill certain roles within the company.","PeriodicalId":348938,"journal":{"name":"Proceedings of the XV Brazilian Symposium on Information Systems","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128623179","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

Sequential Sentiment Pattern Mining to Predict Churn in CRM Systems: A Case Study with Telecom Data 顺序情感模式挖掘预测客户关系管理系统的流失:电信数据的案例研究

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330220

Thiago P. Pimentel, R. Goldschmidt

引用次数: 0

Vulnerability detection techniques and tools and their relationship to agile methods and software quality and service models 漏洞检测技术和工具及其与敏捷方法、软件质量和服务模型的关系

Proceedings of the XV Brazilian Symposium on Information Systems Pub Date : 2019-05-20 DOI: 10.1145/3330204.3330257

Lígia Cássia M. C. Santos, E. Prado, M. Chaim

引用次数: 0