Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)最新文献_第2页

Classification of Newborns with Congenital Syndrome Associated with Zika Virus Infection Using Machine Learning 使用机器学习对与寨卡病毒感染相关的先天性综合征新生儿进行分类

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17461

É. Assis, Luis E. Zárate, C. Nobre

引用次数: 0

Using Named Entities for Recognizing Family Relationships 使用命名实体来识别家族关系

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17457

E. Oliveira, G. Dias, J. Lima, Juliana Pinheiro Campos Pirovani

{"title":"Using Named Entities for Recognizing Family Relationships","authors":"E. Oliveira, G. Dias, J. Lima, Juliana Pinheiro Campos Pirovani","doi":"10.5753/kdmile.2021.17457","DOIUrl":"https://doi.org/10.5753/kdmile.2021.17457","url":null,"abstract":"Named Entity Recognition problem’s objective is to automatically identify and classify entities like persons, places,organizations, and so forth. That is an area in Natural Language Processing and Information Extraction. NamedEntity Recognition is important because it is a fundamental step of preprocessing for several applications like relationextraction. However, it is a hard problem to solve as several categories of named entities are written similarly andthey appear in similar contexts. To accomplish it, we can use some hybrid approaches. Nevertheless, in this presentstudy, we use linguistic flavor by applying Local Grammar and Cascade of Transducers. Local Grammars are used torepresent the rules of a particular linguistic structure. They are often built manually to describe the entities we aimto recognize. In our study, we adapted a Local Grammar to improve the Recognition of Named Entities. The resultsshow an improvement of up to 7% on the F-measure metric in relation to the previous Local Grammar. Also, we builtanother Local Grammar to recognize family relationships from the improved Local Grammar. We present a practicalapplication for the extracted relationships using Prolog.","PeriodicalId":391667,"journal":{"name":"Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129864343","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

Low-Cost Machine Learning for Effective and Efficient Bad Smells Detection 低成本机器学习的有效和高效的坏气味检测

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17468

J. Figuerêdo, V. T. Sarinho, R. Calumby

{"title":"Low-Cost Machine Learning for Effective and Efficient Bad Smells Detection","authors":"J. Figuerêdo, V. T. Sarinho, R. Calumby","doi":"10.5753/kdmile.2021.17468","DOIUrl":"https://doi.org/10.5753/kdmile.2021.17468","url":null,"abstract":"Bad smells are characteristics of software that indicate a code or design problem which can make information system hard to understand, evolve, and maintain. To address this problem, different approaches, manual and automated, have been proposed over the years, including more recently machine learning alternatives. However, despite the advances achieved, some machine learning techniques have not yet been effectively explored, such as the use of feature selection techniques. Moreover, it is not clear to what extent the use of numerous source-code features are necessary for reasonable bad smell detection success. Therefore, in this work we propose an approach using low-cost machine learning for effective and efficient detection of bad smells, through explicit feature selection. Our results showed that the selection allowed to statistically improve the effectiveness of the models. For some cases, the models achieved statistical equivalence, but relying on a highly reduced set of features. Indeed, by using explicit feature selection, simpler models such as Naive Bayes became statistically equivalent to robust models such as Random Forest. Therefore, the selection of features allowed keeping competitive or even superior effectiveness while also improving the efficiency of the models, demanding less computational resources for source-code preprocessing, model training and bad smell detection.","PeriodicalId":391667,"journal":{"name":"Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127867753","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

Evaluation of Machine Learning Models for Estimating Sales in Physical Retail 评估实体零售销售的机器学习模型

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17459

G. O. Alves, Jorge C. B. Fonsêca, A. M. A. Maciel

引用次数: 0

Combining Clustering and Regression Models for Recommending Researchers 结合聚类和回归模型推荐研究人员

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17471

J. Lima, E. Oliveira

引用次数: 1

Characterizing and understanding ensemble-based anomaly-detection 描述和理解基于集成的异常检测

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17473

Gustavo de P. Avelar, G. Campos, W. Meira Jr.

{"title":"Characterizing and understanding ensemble-based anomaly-detection","authors":"Gustavo de P. Avelar, G. Campos, W. Meira Jr.","doi":"10.5753/kdmile.2021.17473","DOIUrl":"https://doi.org/10.5753/kdmile.2021.17473","url":null,"abstract":"Anomaly Detection (AD) has grown in importance in recent years, as a result of an increasing digitalization of services and data storage, and abnormal behavior detection has become a key task. However, discovering abnormal data that is mixed with the huge amount of data available is a daunting problem and the efficacy of the current methods depends on a wide range of assumptions. One effective strategy for detecting anomalies is to combine multiple models, which are called \"ensembles\", but the factors that determine their performance are often hard to determine, making their calibration and improvement a challenging task. In this paper we address these problems by employing a four-step method for the characterization and understanding of ensemble-based anomaly-detection task. We start by characterizing several datasets and analyzing the factors that make it hard to detect their anomalies. We then evaluate to what extent existing algorithms are able to detect anomalies in the same datasets. On the basis of both analyses, we propose a stacking-based ensemble that outperformed a state-of-the-art baseline, Isolation Forest. Finally, we examine the benefits and drawbacks of our proposal.","PeriodicalId":391667,"journal":{"name":"Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)","volume":"318 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122222614","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

Comparing ARIMA and LSTM models to predict time series in the oil industry 比较ARIMA和LSTM模型对石油行业时间序列的预测

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17470

Jaqueline B. Correia, M. Pivetta, Givanildo Santana Do Nascimento, Karin Becker

引用次数: 0

Study of the evolution of antiemetic treatment through the application of Triadic Formal Concept Analysis 应用三元形式概念分析研究止吐疗法的演变

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17454

Lucas Ferreira, Cristiane Nobre, L. Zarate, M. Song

引用次数: 1

Combining Data Mining Techniques to Analyse Factors Associated with Allocation of Socioeconomic Resources at IFMG 结合数据挖掘技术分析IFMG社会经济资源配置相关因素

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17465

Eduardo Melo, Elisa Tuler, Leonardo Rocha

{"title":"Combining Data Mining Techniques to Analyse Factors Associated with Allocation of Socioeconomic Resources at IFMG","authors":"Eduardo Melo, Elisa Tuler, Leonardo Rocha","doi":"10.5753/kdmile.2021.17465","DOIUrl":"https://doi.org/10.5753/kdmile.2021.17465","url":null,"abstract":"The granting of socioeconomic assistance to students from Federal Education Institutions is one of the ways found to provide finantial support during their studies, focusing primarily on those who are more socially vulnerable. Institutions carry out selection processes to identify students with a profile of demand and appropriately distribute the grants according to the budget available for this purpose. This article applied Data Mining techniques to a set of information from students who applied to receive scholarships at IFMG - Campus Bambuí, seeking to identify the attributes associated with the distribution of benefits and analyzing the adequacy of the current indicator used by the institution to classify the level of social vulnerability of students. The proposed methodology involved combining different machine learning algorithms, such as data classification and feature selection techniques. In addition to identifying the degree of importance of each attribute in the constructed model, the differential of this article is to present well-founded suggestions for new attributes that could be able to improve the index used by the institution and, consequently, optimize the workload of those involved with the analysis of selective processes. The composition of the institution's index with five new attributes resulted in a gain of around 10% in rating performance.","PeriodicalId":391667,"journal":{"name":"Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125251713","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 Machine Learning Approach to Interpolating Indoors Trajectories 室内轨迹插值的机器学习方法

Anais do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021) Pub Date : 2021-10-04 DOI: 10.5753/kdmile.2021.17472

Daniel Carvalho, Daniel Sullivan, Rafael Almeida, Carlos Caminha

引用次数: 1