检索结果-内蒙古大学图书馆

International Conference on Advanced Learning Technologies (ICALT)

作者： Joice Cazanoski Gomes Patricia A. Jaques Graduate Program in Informatics (PPGInf) Universidade Federal do Paraná (UFPR) Curitiba Brazil Graduate Program in Computing (PPGC) Universidade Federal de Pelotas (UFPEL) Pelotas Brazil

Misconceptions play a significant role in the learning process as they reflect an inaccurate understanding of a particular concept. Error diagnosis can help teachers and intelligent learning environments determine the most appropriate type of student assistance. Previously, misconceptions were identified using rule-based expert systems (bug libraries) and clustering algorithms. Bug libraries demand extensive work from developers to identify all potential misconceptions and code rules for each one in advance. Additionally, these solutions cannot detect misconceptions for which rules were not explicitly programmed. Clustering-based solutions overcome these drawbacks by automatically identifying misconceptions based on students' most common errors. To effectively and efficiently identify misconceptions, clustering solutions must have a suitable representation of the problem and its steps, and employ machine learning algorithms capable of discerning patterns from them. This paper proposes a solution that utilizes expression trees to represent algebraic problem-solving steps and the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to identify misconceptions by clustering similar errors in a database containing 1064 steps from 112 students. This database was collected from an intelligent learning system designed to assist in solving first-degree equations. In our final solution, a Natural Language Processing tokenizer was employed to represent each term numerically, which identified 178 homogeneous clusters with minimal noise and few outliers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Method for improvement of transparency: Use of text mining techniques for reclassification of governmental expenditures records in Brazil

引用

International Journal of Business Intelligence and Data Mining 2021年第2期18卷 155-196页

作者： de Oliveira Almeida, Gustavo Revoredo, Kate Cappelli, Claudia Maciel, Cristiano Graduate Program in Business Federal Fluminense University Niteroi/RJ Brazil Graduate Program in Informatics Federal University of Rio de Janeiro State Rio de Janeiro/RJ Brazil Computing Institute Mato Grosso Federal University Cuiabá/MT Brazil

Many countries have transparency laws requiring availability of data. However, often data is available but not transparent. We present the Transparency Portal of Brazilian Federal Government case and discuss limitations of public acquisitions data stored in free text format. We employed text-mining techniques to reclassify descriptive texts of measurement units related to products and services. The solution presented in KNIME and Java aggregated measurements in the original (n = 69,372 with 78% reduction in number of descriptions, 94% items classified) and in cross validation sample (n = 105,266 with 88% reduction, classifying 78% of items). In addition, we tested computational time for processing of texts for a wide range of data input sizes, suggesting the stability and scalability of the solution to process larger datasets. Finally, we produced analysis identifying probable input errors, suppliers and purchasing units with abnormal transactions and factors affecting procurement prices. We present suggestions for future research and improvements. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

MILPdM: A Predictive Maintenance Architecture for the Military Domain 22

MILPdM: A Predictive Maintenance Architecture for the Milita...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Dalzochio, Jovani Kunst, Rafael Barbosa, Jorge Pignaton De Freitas, Edison Binotto, Alecio University of Vale Do Rio Dos Sinos Graduate Program in Applied Computing São Leopoldo Brazil Institute of Informatics Federal University of Rio Grande Do sui Porto Alegre Brazil Ibm Consulting Asset and Edge Optimization Munich Germany

ISBN: (纸本)9798350345346

Equipment monitoring for failure prediction is receiving attention from different sectors of society, such as industry, healthcare, and defense. In the defense domain, assets like military vehicles generate data that one can use to identify behavior changes and anticipate possible real-time failures, avoiding unnecessary maintenance interventions. Failure anticipation is crucial, as assets operated in the military domain perform critical tasks in which unexpected equipment failures result in high material and human costs. Approaches found in the literature typically deal with failure generation, aiming at analyzing the equipment's behavior. This paper proposes a broader approach called MILPdM. This proposal is a failure prediction architecture covering the whole failure prediction and predictive maintenance procedures. We evaluate MILPdM architecture by analyzing an engine-failure scenario where we train models to predict time series by collecting vibration data that describes the degradation of the vehicle's health. Considering the implementation of an LSTM-based neural network and Random Forest, the acquired results lead to a root mean square error of 0.15015 in the best case, which allows to predict the failure status two minutes in advance with only 3 hours of data history. This result shows that MILPdM is capable of anticipating failures with high assertiveness. © 2023 IEEE.

关键词： IoBT machine learning neural networks predictive maintenance random forest

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Study to Assess the Usability of a Groupware with Multi-Agent Systems

An Exploratory Study to Assess the Usability of a Groupware ...

引用

Frontiers in Education (FIE) Conference

作者： Joethe Moraes de Carvalho José Francisco de Magalhães Netto Post-Graduate Program in Informatics (PPGI) Institute of Computing (ICOMP) Federal University of Amazonas (UFAM) CMC-Federal Institute of Amazonas (IFAM) Manaus AM Brazil Post-Graduate Program in Informatics (PPGI) Institute of Computing (ICOMP) Federal University of Amazonas (UFAM) Manaus AM Brazil

This Research Full Paper presents a pedagogical approach to evaluate a virtual platform for teaching robotics at a distance. The virtual environment was developed using the principles of Collaborative Learning. This virtual platform, called groupware, should facilitate interaction between those involved in the teaching and learning process, whether the student or the teacher. In this research, we will use Educational Robotics as a mediating tool in the teaching and learning process, because it has become a powerful tool that has stimulated the acquisition of knowledge in computing. In the groupware used in this research, Multi-Agent Systems were used to collaborate with teachers in the management of activities. The purpose of this study was to evaluate the functionality and usability of this virtual environment. A qualitative, exploratory research was used and to assess the usability of this virtual environment, the usability evaluation techniques were used with the Syetem Usabily Scale metric, and the technique of evaluation of feelings through EmoCards. Ten computer teachers participated in this research, with training and specializations in the areas of computing. Collaborative Learning was used as a focus for solving the tasks proposed for this research. The results showed that the participants evaluated the groupware with great potential to collaborate in robotics teaching and with content appropriate to the students' initial level of learning. The teachers' perceptions regarding the usability of the evaluated groupware revealed that it is favorable in the teaching of robotics and allowed an analysis of the importance of collaborative learning in the educational environment, directly impacting their ways of conducting learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 2824-2835页

作者： Chiu, Ching-Yu Muller, Meinard Davies, Matthew E. P. Su, Alvin Wen-Yu Yang, Yi-Hsuan National Cheng Kung University Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701401 Taiwan International Audio Laboratories Erlangen Erlangen91058 Germany University of Coimbra Department of Informatics Engineering Centre for Informatics and Systems Coimbra3004-531 Portugal National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Taiwan AI Labs Yating Music Team Taipei103622 Taiwan Academia Sinica Research Center for IT Innovation Taipei11529 Taiwan

To model the periodicity of beats, state-of-the-art beat tracking systems use 'post-processing trackers' (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called 'predominant local pulses' (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). © 2014 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Alternative Reference Samples to Improve Coding Efficiency for Parallel Intra Prediction Solutions

Alternative Reference Samples to Improve Coding Efficiency f...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Iago Storch Nuno Roma Daniel Palomino Sergio Bampi Graduate Program in Computing Institute of Informatics Federal University of Rio Grande do Sul Porto Alegre Brazil INESC-ID Instituto Superior Técnico Universidade de Lisboa Lisboa Portugal Video Technology Research Group Graduate Program in Computing Federal University of Pelotas Pelotas Brazil

Exploring massive parallelism is a common strategy to mitigate the processing time of modern video encoding standards. Nonetheless, the existing data dependencies in some encoding tools pose difficult challenges to exploit such parallelism, especially during intra prediction, where the reconstructed adjacent blocks are used as references. Although some works made use of different reference samples to allow block-level parallelism in intra prediction, their proposals do not consider the variations caused by different bitrates, leading to some degradation in the output sequence. To deal with multiple bitrates more properly, this work proposes the application of image smoothing techniques to generate alternative reference samples that better represent the nuances of different bitrates. Experimental validations demonstrate that these improved references provide coding efficiency gains while still offering an equivalent parallelization opportunity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Minimizing the Number of Stunting Prevalence Using the Euclid Algorithm Clustering Approach 7

Minimizing the Number of Stunting Prevalence Using the Eucli...

引用

7th IEEE International Conference of Computer Science and Information Technology, ICOSNIKOM 2023

作者： Zarlis, Muhammad Oktavia, Tanty Buaton, Relita Ernawan, Ferda Andrian, Kevin Bina Nusantara University Information System Management Department BINUS Graduate Program - Master of Information System Management Jakarta11480 Indonesia STMIK Kaputama Informatics Engineering Binjai20714 Indonesia Universiti Malaysia Pahang Al-Sultan Abdullah Faculty of Computing Pekan26600 Malaysia BINUS Graduate Program-Master of Information Systems Management Bina Nusantara University Department of Information Systems Management Jakarta Indonesia

ISBN: (纸本)9798350360752

Superior and quality human resources are based on healthy human resources with indicators of adequate nutritional intake according to age development. However, the world still faces the problem of hunger and malnutrition today. According to a UNICEF report, the number of people suffering from malnutrition in the world will reach 767.9 million people in 2021. The World Health Organization (WHO) said that malnutrition is a dangerous threat to the health of the world's population. Stunting also has an impact in Indonesia, the prevalence of toddlers experiencing stunting in Indonesia is 24.4% in 2021. The solution created is to classify and cluster the prevalence of stunting to produce a pattern that can be used as best practice to be transmitted to other affected areas. The algorithm used is Euclid. The Euclid algorithm can cluster stunting prevalence data into 4 clusters with the very little category at 79%, the little category at 67%, the many categories at 51%, and the very much category at 21%. The results of the classification and clustering of the best stunting prevalence in cluster one with a very small number, can be used as a source of accurate and updated information that can be used by the government in its efforts to optimize stunting handling in each district/city based on artificial intelligence which can provide handling and optimization patterns. stunting in every district/city. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

CONVERGENCE ANALYSIS OF A SCHRÖDINGER PROBLEM WITH MOVING BOUNDARY

arXiv

引用

arXiv 2024年

作者： Alfaro Vigo, Daniel G. Gomes, Daniele C.R. Carmo, Bruno A.D.O. Rincon, Mauro A. Institute of Computing Graduate Program in Informatics Federal University of Rio de Janeiro Caixa Postal 68530 RJ Rio de JaneiroCEP 21941-590 Brazil Graduate Program in Informatics Federal University of Rio de Janeiro Caixa Postal 68530 RJ Rio de JaneiroCEP 21941-590 Brazil

In this article, we present the mathematical analysis of the convergence of the linearized Crank-Nicolson Galerkin method for a nonlinear Schrödinger problem related to a domain with a moving boundary. The convergence analysis of the numerical method is carried out for both semi-discrete and fully discrete problems. An optimal error estimate in the L2-norm with order O(τ2 + hs), 2 ≤ s ≤ r, where h is the finite element mesh size parameter, τ is the time step, and r−1 represents the degree of the finite element polynomial basis. Numerical simulations are provided to confirm the consistency between theoretical and numerical results, validating the method and the order of convergence for different degrees p ≥ 1 of the Lagrange polynomials and also for Hermite polynomials (degree p = 3), which form the basis of the approximate solution. © 2024, CC BY-NC-ND.

关键词： Schrodinger equation

来源：评论

学校读者我要写书评

暂无评论

Exploring Security Threats by Hardware-Faults in Approximate Arithmetic computing

Exploring Security Threats by Hardware-Faults in Approximate...

引用

Annual IEEE Northeast Workshop on Circuits and Systems (NEWCAS)

作者： Morgana M. A. Da Rosa Eduardo A. C. Da Costa Rafael I. Soares Sergio Bampi Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil PPGC & PGMICRO - Informatics Institute Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

Approximate computing (AxC) emerged as a design alternative to boost design efficiency by leveraging the inherent error resiliency of many applications. Recent literature shows attackers could exploit some AxC mechanisms to create new attack surfaces. This work proposes integrity checking and exclusive logic-based methods detect attacks by hardware faults on AxC systems. During ASIC-based synthesis, we investigate the security vulnerabilities of the Approximate Parallel Prefix Adder (AxPPA). We compare the expected output of the designer with the output netlists of ASIC-based synthesis. We propose a verification methodology consisting of a golden model (GM) described in a Simulink model and the DUT represented at the netlist level in a standard cell library after logic synthesis. Experimental results show that the AxPPA has an error range of 1.263 × 10 −5 to 0.0098 concerning the designer’s expected output under ASIC-based synthesis attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

New Energy-Efficient 3-2 and 4-2 Approximate Adder Compressors Topologies

New Energy-Efficient 3-2 and 4-2 Approximate Adder Compresso...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Rodrigo Lopes Leonardo Antonietti Morgana M. A. Rosa Eduardo Costa Rafael Soares Sergio Bampi Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil PPGC & PGMICRO - Informatics Institute Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

Addition units are present across many computational kernels inherent in various error-tolerant applications, including machine learning, signal, image, and video processing. Notably, adder compressors are the target when high speed and low power are the main design concerns. This work introduces energy-efficient structures of 3-2 approximate adder compressors (Ax3-2) and three distinct versions of 4-2 approximate adder compressors (Ax4-2). We compared our proposed Ax3-2 and Ax4-2 compressors with state-of-the-art energy-efficient approximate adder compressors (AxACs). Both Ax3-2 and Ax4-2 models passed through rigorous tests as standalone units. Furthermore, we integrated the Ax4-2 models into an essential application kernel appearing in video coding, i.e., the Sum Squared Differences (SSD) video accelerator. We introduce Ax3-2 and Ax4-2 that yield a new Pareto front concerning both energy-quality and area-quality trade-offs, thereby demonstrating a marked improvement over the prevailing state-of-the-art energy-efficient AxACs.

关键词：

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：