检索结果-内蒙古大学图书馆

International Conference on computer Supported Cooperative Work in Design

作者： António Correia Dennis Paulino Hugo Paredes Diogo Guimarães Daniel Schneider Benjamim Fonseca UTAD Quinta de Prados INESC TEC and University of Trás-os-Montes e Alto Douro Vila Real Portugal College of Information Science & Technology University of Nebraska at Omaha Omaha NE USA Postgraduate Program in Informatics PPGI/UFRJ Rio de Janeiro Brazil Tércio Pacitti Institute of Computer Applications and Research NCE/UFRJ Rio de Janeiro Brazil

Determining the relatedness of publications by detecting similarities and connections between researchers and their outputs can help science stakeholders worldwide to find areas of common interest and potential collaboration. To this end, many studies have tried to explore authorship attribution and research similarity detection through the use of automatic approaches. Nonetheless, inferring author research relatedness from imperfect data containing errors and multiple references to the same entities is a long-standing challenge. In a previous study, we conducted an experiment where a homogeneous crowd of volunteers contributed to a set of author name disambiguation tasks. The results demonstrated an overall accuracy higher than 75% and we also found important effects tied to the confidence level indicated by participants in correct answers. However, this study left many open questions regarding the comparative accuracy of a large heterogeneous crowd with monetary rewards involved. This paper seeks to address some of these unanswered questions by repeating the experiment with a crowd of 140 online paid workers recruited via MTurk’s microtask crowdsourcing platform. Our replication study shows high accuracy for name disambiguation tasks based on authorship-level information and content features. These findings can be of greater informative value since they also explore hints of crowd behavior activity in terms of time duration and mean proportion of clicks per worker with implications for interface and interaction design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Framework Design of Information Retrieval System for Official Letter Using Extraction of Geometry Feature Method 2

Framework Design of Information Retrieval System for Officia...

引用

2nd International Conference on computer, science, Engineering, and Technology, ICComSET 2019

作者： Fabrianto, L. Hendra Surohman Sfenrianto Faizah, N.M. Master of Computer Science-Postgraduate Program STMIK Nusa Mandiri Jakarta Indonesia Master of Information Systems Management Bina Nusantara University Jakarta11480 Indonesia Information Systems Department Universitas Tama Jagakarsa Jakarta Indonesia

In a government institution many official letters are made daily, the letters have an official format in the Tanggal, No. Surat, Lampiran dan Hal. area, with an OCR (Optical Character Recognition) scanner an official letter can be digitized and processed to obtain characters that will be used as searches, but in fact in certain desired parts there are often handwriting, a method of pattern recognition is needed to recognize the handwriting. The process in this study including of normalization, segmentation and pattern recognition from labels in the Tanggal, No. Surat, Lampiran dan Hal. area,this system will generate output in text form, the output text is result that will use as a term in the process of the Information Retrieval System, so the search for an official letter will be easy to do. This study is only makes the framework design for the next research authors will explain the detail of process and results obtained. © 2020 IOP Publishing Ltd. All rights reserved.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A Software Ecosystem platform for the development of Recommender Systems

Research Square

引用

Research Square 2020年

作者： Abdalla, André Ströele, Victor Campos, Fernanda Braga, Regina David, José Maria N. Postgraduate Program in Computer Science Federal University of Juiz de Fora Juiz de Fora Brazil

Many application domains need to recommend resources for users. The development of solutions focused on the reuse of Recommender System components creates an interesting scenario from a Software Ecosystem perspective. Besides the interaction between actors and technology, a Software Ecosystem for the development of Recommender Systems should allow for integration with systems and platforms that support other ecosystems. The problem addressed by this study is the integration of methods, techniques, and approaches of existing Recommender Systems in a systematic way, facilitating the implementation of new solutions, their reuse and sharing, and the collaboration among the actors involved. This study, therefore, aims to propose ***, a Software Ecosystem platform to support the development and management of Recommender Systems, allowing for integration between multiple applications and other Software Ecosystems. The evaluation was conducted in two stages. First, two feasibility studies were carried out to validate both technology and architecture. Later, two case studies were conducted in real-world contexts. The results point to the viability of the proposal. © 2020, CC BY.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Analytic Center Classifier 9th

An Evolutionary Analytic Center Classifier

引用

9th Brazilian Conference on Intelligent Systems, BRACIS 2020

作者： Goulart, Renan Motta Villela, Saulo Moraes Borges, Carlos Cristiano Hasenclever Neto, Raul Fonseca Postgraduate Program in Computational Modeling Federal University of Juiz de Fora Juiz de ForaMinas Gerais Brazil Department of Computer Science Federal University of Juiz de Fora Juiz de ForaMinas Gerais Brazil

ISBN: (纸本)9783030613761

Classification is an essential task in the field of Machine Learning, where developing a classifier that minimizes errors on unknown data is one of its central problems. It is known that the analytic center is a good approximation of the center of mass of the version space that is consistent with the Bayes-optimal decision surface. Therefore, in this work, we propose an evolutionary algorithm, relying on the convexity properties of the version space, that evolves a population of perceptron classifiers in order to find a solution that approximates its analytic center. Hyperspherical coordinates are used to guarantee feasibility when generating new individuals and enabling exploration to be uniformly distributed through the search space. To evaluate the individuals we consider using a potential function that employs a logarithmic barrier penalty. Experiments were performed on real datasets, and the obtained results indicate concrete possibilities for applying the proposed algorithm for solving practical problems. © 2020, Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Collaboration analysis in global software development 23

Collaboration analysis in global software development

引用

23rd IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2019

作者： Horta, Vitor Stroele, Victor Schettino, Vinicius Oliveira, Jonice Maria David, Jose Araujo, Marco Antonio P. Computer Science Postgraduate Program Federal University of Juiz de Fora Juiz de Fora Brazil

ISBN: (纸本)9781728103501

In global software development distributed teams are often challenged by global distances, such as cultural diversity and linguistic barriers. This stimulates the search for groups of people that can work together and collaborate in a positive way, even though they are working in a distributed environment. In addition, the demand for high quality software motivates the search for experienced developers who are able to solve complex tasks or to help others with their own tasks. This work aims to detect experts and to identify collaborative groups with experienced members in some topics of software development. To achieve these goals the StackOverflow forum was used and modeled as a complex network. The presented method uses NetSCAN algorithm to detect overlapping communities, expert developers and their topics of expertise in social networks. Through a temporal analysis over the social network multidisciplinary developers were found as well as people who are changing their interests over time. In a first evaluation a statistic test showed that experts (indicated by the proposed method) have a higher performance than common users. A second evaluation showed that these experts are suitable for recommendation systems in question-answer forums. © 2019 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Specialized Classifiers with SHAP Feature Selection: Application to the Tennessee Eastman Process

Specialized Classifiers with SHAP Feature Selection: Applica...

引用

IEEE/IAS International Conference on Industry Applications (INDUSCON)

作者： Gabriel S. Sereno Thomas W. Rauber Celso J. Munaro Postgraduate Program in Computer Science Universidade Federal do Espírito Santo Vitória Brazil Departamento de Informática Centro Tecnológico Universidade Federal do Espírito Santo Vitória Brazil Departamento de Engenharia Elétrica Lab. de Controle e Instrumentação Centro Tecnológico Universidade Federal do Espírito Santo Vitória Brazil

In this paper, specialized classifiers are trained using features selected via SHAP method for the purpose of diagnosing multiple faults in industrial processes. The multi-class problem of fault diagnosis is decomposed via One-vs-All scheme. The Tennessee Eastman process is considered, and for each fault, a Random Forest classifier is trained using features selected via SHAP method. Four feature selection techniques are compared with respect to their performance and the cardinality of the selected feature set. SHAP method presented approximately 89% of the $F_{1}$ -score, used as the performance index, with similar values to the other methods. However, the SHAP feature selection selects fewer features to achieve this result, about four features less in comparison to Recursive Feature Elimination (RFE) which selected eight in average. The study suggests that SHAP can reduce the dimensionality of the dataset with a good $F_{1}$ -score performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Fault Detection in Industrial Processes Based on the SHAP Algorithm

Feature Selection for Fault Detection in Industrial Processe...

引用

IEEE/IAS International Conference on Industry Applications (INDUSCON)

作者： Alexandre R. Lemos Thomas W. Rauber Celso J. Munaro Postgraduate Program in Computer Science Universidade Federal do Espírito Santo Vitória Brazil Departamento de Informática Centro Tecnológico Universidade Federal do Espírito Santo Vitória Brazil Departamento de Engenharia Elétrica Lab. de Controle e Instrumentação Centro Tecnológico Universidade Federal do Espírito Santo Vitória Brazil

We apply SHapley Additive exPlanations (SHAP) feature selection method to improve fault detection models in an industrial production context. An illustrative synthetic process and the benchmark Tennessee Eastman Chemical Plant Simulator (TES) were used for the experiments. The principal hypothesis of this work is that the proposed SHAP feature selection methodology produces a subset of features with better discriminatory information, or at least approximately the same, than the original feature set. For the synthetic data experiment, the subset obtained achieved approximately the same results while reducing the number of features. For the experiment using the Tennessee Eastman simulation, the methodology produced a reduced feature subset that was able to obtain, overall, better values of the $F_{1}$ -score and the Fault Detection Rate (FDR, aka. recall) compared to the original feature set. The set obtained using the proposed SHAP feature selection resulted in an average $F_{1}$ -score of 82.36% and an average FDR of 78.03% for all the faults. These results represent an increase of 2.77% and 1.84% of the $F_{1}$ -score and FDR, respectively, when compared to the original feature set while using an average of six features, a reduction of the cardinality by approximately 97.12%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Big Data Experiment to Evaluate the Effectiveness of Traditional Machine Learning Techniques Against LSTM Neural Networks in the Hotels Clients Opinion Mining

A Big Data Experiment to Evaluate the Effectiveness of Tradi...

引用

IEEE International Conference on Big Data

作者： Thiago de Oliveira Lima Methanias Colaço Kleber H. de J. Prado Israel Dias de J. Frederico Resende de Oliveira Postgraduate Program in Computer Science - PROCC - Federal University of Sergipe (UFS) São Cristóvão Sergipe Brazil State of Sergipe’s General Accounting Court (TCE-SE) Aracaju Sergipe Brazil

ISBN: (纸本)9781665445993

Context: Nowadays, client reviews on social networks can be a great source of knowledge extraction for strategic marketing planning. In the tourism area, opinions given by hotel clients in tourism social networks can drive improvements in service. In this context, traditional text mining techniques and new deep learning technologies should be tried out to select the best options for classifying opinions. Objective: Evaluate the performance and quality of the LDA (Latent Dirichlet Allocation), Naives Bayes (NB), Logistic Regression, SVM (Support Vector Machine) and LSTM - Long Short-Term Memory Units algorithms in the task of opinion mining of hotel reviews published on the TripAdvisor hotel booking website. Method: An In Vivo Controlled Experiment (Case Study) to compare the performance of the classifiers by means of accuracy, precision, recall, F1-measure and average training and classification times. Results: The LSTM model presented the best results regarding quality metrics. However, it did not present satisfactory results regarding processing time. Conclusion: The LSTM classifier had clearly superior performance when compared to the other evaluated ones. On the other hand, its average training and classification times greater than the others classifiers considered.

关键词： Training Support vector machines Text mining Sentiment analysis Social networking (online) Neural networks Big Data

来源：评论

学校读者我要写书评

暂无评论

ARRay-Tracing - A Middleware to Provide Ray Tracing Capabilities to Augmented Reality Libraries

ARRay-Tracing - A Middleware to Provide Ray Tracing Capabili...

引用

Symposium on Virtual Reality (SVR)

作者： Lidiane T. Pereira Wellingston Cataldo R. Junior Jairo F. Souza Rodrigo L. S. Silva Postgraduate Program in Computer Science Federal University of Juiz de Fora Juiz de Fora Minas Gerais

ISBN: (数字)9781728192314

ISBN: (纸本)9781728192321

In recent years we saw the increase and popularization of Augmented Reality applications. However, the visual mismatch between real and virtual elements produce the absence of realism, discouraging the use of these applications. Rendering techniques, as Ray Tracing, can produce very photorealistic scenes. Despite its high computational cost, recent advances in graphics hardware allow the use of these techniques in real-time applications, like those of Augmented Reality. In the literature, we can find some works combining these two technologies, AR and Ray Tracing, but rigidly, without modularization, making the solutions dependent on certain frameworks. In this work, we propose a middleware to integrate Augmented Reality and Ray Tracing in a modularized way, allowing the developer to switch between existing libraries and frameworks to better fulfill their needs and expertise. To evaluate the proposal, we build an application using the artoolkitX library and the Optix framework. Through our middleware, we verified that it was possible to integrate these tools in a simple way, maintaining performance and photorealism in our AR application.

关键词： Ray tracing Cameras Augmented reality Rendering (computer graphics) Middleware Libraries Engines

来源：评论

学校读者我要写书评

暂无评论

Comparison of naive bayes and K-NN method on tuition fee payment overdue prediction 4

Comparison of naive bayes and K-NN method on tuition fee pay...

引用

4th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2019

作者： Kusrini, Kusrini Luthfi, Emha Taufiq Muqorobin, Muqorobin Abdullah, Robi Wariyanto Universitas AMIKOM Yogyakarta Postgraduate Program Yogyakarta Indonesia Universitas AMIKOM Yogyakarta Computer Science Faculty Yogyakarta Indonesia

ISBN: (纸本)9781728151182

Attending basic education is an obligation for all Indonesian citizens. The financial cost is one of the input components to implement an education or even can be considered as the main requirement in achieving the goal of education. For a private education institution in Indonesia, the financial cost is mainly covered by students' tuition payments. SMK Al-Islam Surakarta is a private school that manages all its students to pay school tuition fees monthly. According to its last year's administrative report, the number of students who are late in paying school tuition fee is around 60%. Since the school's operational costs are heavily depended on their income from tuition fees, this considered an essential problem and has to be managed and predicted as well. This research will discuss techniques in predicting the late payment of tuition fees. From many popular methods available in this area, we observed two of them namely Naive Bayes and K-Nearest Neighbor (K-NN). This study will compare the accuracy between those two methods. The data used for the lab work is the official education basic data of Al-Islam Surakarta Vocational School in 2017/2018 totaling 236 data. To increase its accuracy, this study also combines the prediction methods with feature selection technique Information Gain which is commonly used to select an optimal parameter for the prediction process. In the end, the system is tested using the Confusion Matrix method. The results showed that the Naive Bayes Method with Information Gain attribute selection produced the highest accuracy of 69%. © 2019 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：