检索结果-内蒙古大学图书馆

2024 Beyond Technology Summit on Informatics International Conference, BTS-I2C 2024

作者： Riyanto, Aditya Zahra, Amalia Binus Graduate Program Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331508579

Social media has evolved into a vast and multifaceted data repository, presenting valuable opportunities to investigate gender-based variations in writing styles. This study aims to enhance the precision of gender classification on Twitter text by leveraging a combined word embedding approach. The paper proposes a framework that utilizes two distinct word embedding models - a combination of GloVe and BERT, as well as GloVe and Word2Vec - to capture both global and contextual linguistic nuances within the text. The dataset comprises a comprehensive collection of tweets and user profile descriptions harvested from Twitter, which underwent meticulous preprocessing and word representation steps before being further processed using the robust Random Forest algorithm. The experimental findings indicate that the combination of GloVe and BERT outperforms the other combination of GloVe and Word2Vec, and also surpasses the performance of single embedding models, with 62.93% accuracy being the highest achieved result. This study provides valuable insights into the potential of combined word embedding techniques for enhancing the accuracy of gender classification in social media text analysis. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

An Object-Driven Fuzzy Decision Model for Determining Fuel in Boiler Machines 4

An Object-Driven Fuzzy Decision Model for Determining Fuel i...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Utama, Ditdit Nugeraha Widyanto, Jeremia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331506490

There are many alternative fuel types that can be used by a particular type of engine. Determining which fuel alternative is optimal for an engine presents its own challenges. This is especially true in an industrial setting, where certain standards are necessary to select the best fuel alternative to be used and operated. This study aims to develop a decision model for selecting a fuel type for boiler engines based on specific parameters or criteria. The decision model is designed using an object-oriented approach, utilizing three types of diagrams: object, activity, and sequence. An object-oriented model design approach allows for the decision model to be depicted transparently and very close to reality. Additionally, the analytical hierarchical process (AHP) and fuzzy logic are the core methods employed in constructing the decision model. Then, in developing this decision model, four main criteria or parameters are considered: cost, heating value, safety, and emissions. These four parameters were derived from a literature review and interviews with experts. Among the three evaluated fuel types (i.e., natural gas, industrial diesel oil or IDO, and coal), coal received the highest decision score of 0.78. Thus, based on this decision value-the outcome of the model's recommendation-it can be concluded that coal remains an objective choice as a fuel for use in boiler engines. © 2024 IEEE.

关键词： Coal

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Interventions with Students with Autistic Spectrum Disorder (ASD) Using Gamified Geometric Thinking 53

An Analysis of Interventions with Students with Autistic Spe...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Pereira, Lidiane MacIel Barwaldt, Regina De Oliveira, Vinícius Menezes Jung, Mateus Oliveira Graduate Program in Science Education Federal University of Rio Grande Rio Grande Brazil Graduate Program in Computing Federal University of Rio Grande Rio Grande Brazil Graduate Program in Computional Modeling Federal University of Rio Grande Rio Grande Brazil

ISBN: (纸本)9798350336429

Studies have been indicating the use of digital resources for interventions with children diagnosed with Autism Spectrum Disorder (ASD), especially when it comes to supporting communication and social interaction. However, there is research that suggests the use of digital environments not only in these aspects but also to assist them in their academic knowledge, such as in their mathematical skills, specifically related to geometric thinking. From this context, Active Methodologies point to various ways of rethinking traditional teaching, one of them being gamification, which can be understood as the use of game elements in non-game situations. Gamification has shown significant benefits for this audience, proving to be an effective tool to aid in the development and learning of these individuals. Therefore, this article in its complete form presents an excerpt from a doctoral thesis that seeks to understand the geometric thinking of nine autistic participants through gamified activities in their real mode. The research is divided into two stages: the first stage involves a preliminary survey with five teachers through structured interviews, aiming to investigate the demand for gamified activities for students with ASD, as well as indicating possibilities for such activities. From the Discursive Textual Analysis (DTA) of these interviews, three categories emerged: opportunities, skills, and limitations. As for the second stage, conducted with nine participants, who are students with ASD, interventions were carried out with these activities in their real mode, which will be implemented digitally later. Through the researcher's observation analysis, based on recorded videos of the interventions, three subcategories related to the initial categories can be identified: potential interactions (opportunities);strategies for geometric thinking (skills);and gamification in the real mode (limitations). The first subcategory emerged due to the need to describe how students w

关键词： Autism Spectrum Disorder Gamification Geo-metric Thinking

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Pipeline for Emotion Recognition based on Brain Topographic Maps Derived from Electroencephalogram Signals 37

A Machine Learning Pipeline for Emotion Recognition based on...

引用

37th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2024

作者： Alves, Bruno Cascaes Melo, Marla Pereira Cerri, Artur Melchiori de Freitas, Larissa Astrogildo Adamatti, Diana Francisca de Aguiar, Marilton Sanchotene Postgraduate Program in Computing Federal University of Pelotas Pelotas Brazil Undergraduate in Computer Science Federal University of Pelotas Pelotas Brazil Postgraduate Program in Computing Federal University of Rio Grande Rio Grande Brazil

Emotion recognition is an increasingly relevant field due to its direct implications for various sectors of society. The area aims to enhance the understanding of how emotions influence human behavior. Exploring brain activity analysis through electroencephalogram signals becomes possible when considering that emotions can manifest non-verbally. In this scenario, machine learning applications prove promising due to the complexity of recognizing emotions from electrical signal data from the brain. The case study focuses on DEAP, a recognized dataset constructed through experiments in electroencephalography, exposing subjects to musical and visual stimuli. The main objective of this work is to present a pipeline for the classification of emotions based on images of topographic maps generated from the EEGLAB tool and electroencephalogram signals. Additionally, the contributions of this work include the presentation of a structured dataset created through the mapping of temporal, spatial, and frequency data derived from topographic images and models for predicting dimensional emotions of arousal and valence based on the new dataset. Results demonstrate accuracies of 85.46% and 85.05% for the classification of low/high arousal and valence emotions, respectively. Copyright © 2024 by the authors.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Based Decision Support Model for Health Insurance Claim

引用

Informatica (Slovenia) 2022年第7期46卷 119-130页

作者： Susanto, Sumiatie Utama, Ditdit Nugeraha Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Insurance industry in Indonesia has shown promising result based on premium growth in 2014-2018, as recorded in Indonesia General Insurance Market Update 2019. With the increase of premium, the claim rate also grows. Insurance companies face challenges in processing the claims. Many factors need to be carefully considered before making a claim decision. This paper proposes a decision support model (DSM) to score claim cases and to propose claim risk category (CRC) and claim decision (CD). The model was built with 13 parameters, divided into non-fuzzy group and fuzzy group. The analytic hierarchy process (AHP) method was used to determine the priority weight (PW) among parameters. The Tsukamoto’s fuzzy logic (FL) method was applied to process the fuzzy parameters. A simple mathematics method (SMM) was exercised to calculate the non-fuzzy parameters, and to aggregate the result into claim risk score (CRS). Finally, CRC and CD were derived from the CRS using a rule base. The model was tested using 19611 actual claim history records. The result was: 6171 (31.47%) accepted with CRC= low, 3459 (17.64%) pending (CRC medium), and 9981 (50.89%) pending (CRC high). The DSM model was implemented in python with Google COLAB and Datapane to create various graphics. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Synonym Replacement Augmentation for Handling Data Imbalance in Personality Classification 8

Synonym Replacement Augmentation for Handling Data Imbalance...

引用

8th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2024

作者： Pradana, Rilo Chandra Suhartono, Derwin Bina Nusantara University Binus Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350368970

The Myers-Briggs Type Indicator (MBTI) classification is a widely utilized instrument for personality assessment. However, it frequently encounters challenges due to imbalanced data distributions across personality dimensions. It is paramount to address this issue to enhance the accuracy and reliability of personality predictions. Most current research in this field is focused on data balancing techniques, such as oversampling and undersampling, which have been demonstrated to enhance model performance. Nevertheless, there is a dearth of research exploring text augmentation methods, particularly synonym replacement, for this purpose. This study examines the efficacy of synonym replacement as a data augmentation technique for MBTI classification. Experiments are conducted with varying levels of synonym replacement (10%, 30%, 50%, 70%, and 90%) to assess its impact on model accuracy and F1 scores across the four MBTI dimensions. Our findings indicate that low levels of synonym replacement, particularly at 10% to 50%, can enhance the performance of the model in predicting MBTI dimensions. On the other hand, a higher number of replaced words in the synonym replacement augmentation can harm the model's performance. These observations suggest that synonym replacement can effectively address data imbalance in MBTI classification, although its application must be tailored to specific personality dimensions. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

The Effect of Statistical Hypothesis Testing on Machine Learning Model Selection 12th

The Effect of Statistical Hypothesis Testing on Machine Le...

引用

12th Brazilian Conference on Intelligent Systems, BRACIS 2023

作者： Gonçalves, Marcel Chacon Silva, Rodrigo Graduate Program on Computer Science Universidade Federal de Ouro Preto Ouro Preto Brazil Department of Computer Science Universidade Federal de Ouro Preto Ouro Preto Brazil

ISBN: (纸本)9783031453885

Statistical tests of hypothesis play a crucial role in evaluating the performance of machine learning (ML) models and selecting the best model among a set of candidates. However, their effectiveness in selecting models over larger periods of time remains unclear. This study aims to investigate the impact of statistical tests on ML model selection in sequential experiments. Specifically, we examine whether selecting models based on statistical tests leads to higher quality models after a significant number of iterations and explore the effect of the number of tests performed and the preferred statistical test for different experimental time horizons. The study on binary classification problems reveals that the use of statistical tests should be approached with caution, particularly in challenging scenarios where generating improved models is difficult. The analysis demonstrates that statistical tests may impede progress and impose overly stringent acceptance criteria for new models, hindering the selection of high-quality models. The findings also indicate that the dominance of versions without statistical tests remained consistent, suggesting the need for further research in this area. Although this study is limited by the number of datasets and the absence of pre-test assumption verification, it emphasizes the importance of understanding the impact of statistical tests on ML model selection. © 2023, The Author(s), under exclusive license to 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

Variational quantum neural network with optimized ansatz for predicting malignant ventricular arrhythmias 9th

Variational quantum neural network with optimized ansatz for...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Dominic, Nicholas Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

Preventive strategies should be the utmost priority when dealing with diverse patients suffering from malignant ventricular arrhythmia (MVA) that can lead to sudden cardiac death (SCD). Electrocardiogram (ECG) data is commonly used as a predictor for MVA predictive models. In this study, all ECG signals from MIT-BIH databases were fragmented into five-minute durations with a frequency sampling of 128 Hz. To solve the absence of hybrid optimizations in Machine Learning (ML) models, a novel Variational Quantum Neural Network (VQNN) was invented. Empowered by deep learning capabilities and optimized quantum circuits design, VQNN achieved remarkable performances designated by an accuracy of up to 95.1%, a perfect 100% recall, and a 95.2% score of the area under the Receiver Operating Characteristic curve (AUC ROC) with Conjugate Gradient as an optimizer and EfficientSU2 as a quantum ansatz. Despite the susceptibility to quantum noise, this research settles a new trajectory of utilizing quantum variational algorithms to predict and expand its applicability for MVA cases. © 2024 The Authors.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

GAN.s Approach On Generating Synthetical Skin Image Dataset for Imbalance Dataset 8

GAN.s Approach On Generating Synthetical Skin Image Dataset ...

引用

8th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2024

作者： Setiawan, Tri Agus Heryadi, Yaya Lukas Wulandari, Lili Ayu Sonata, Ilvico Binus Graduate Program -Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia

ISBN: (纸本)9798350368970

The use of balanced medical datasets is essential to improve the precision and accuracy of machine learning models in the healthcare field. However, dataset imbalance often becomes an obstacle, especially in the diagnosis of skin diseases. This research aims to develop a Generative Adversarial Networks (GAN) method that is more effective in generating synthetic skin datasets to overcome problems in integrating medical datasets. The methods used include developing and training a GAN model to produce realistic synthetic skin images, with a focus on improving the quality and diversity of the synthetic data produced. Important results from this research show that the developed GAN model is able to produce synthetic skin images that are not only realistic but also able to balance the original dataset. The implications of these findings include improving the accuracy and performance of machine learning models in the diagnosis of skin diseases, as well as the potential use of these methods in other medical fields that face similar problems with imbalanced datasets. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Input Representation on Text Data for E-Commerce Product Review Summarization using Graph Convolutional Network 6

Input Representation on Text Data for E-Commerce Product Rev...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Sari, Azani Cempaka Heryadi, Yaya Kartowisastro, Iman Herwidiana Budiharto, Widodo Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798331539603

This paper investigates recent advancements and methodologies in Automatic Text Summarization, a field that has garnered significant attention for its ability to condense lengthy documents into concise summaries while preserving key information and themes. The study examines the development of Automatic Text Summarization models, including both extractive and abstractive approaches. Additionally, the research delves into the use of graph convolutional networks for text representation in e-commerce product review summarization. The study employs an e-commerce dataset in conjunction with a graph convolutional network model, covering stages from preprocessing and tokenization to constructing graph-based data representation. The expected outcome is a graph-structured representation of input text data derived from Indonesian-language e-commerce product reviews. © 2024 IEEE.

关键词： Convolutional E-commerce Graph Network Product Review Summarization Text

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：