检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,190 篇 会议
1,185 篇 期刊文献
3 册 图书

馆藏范围

3,378 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,744 篇 工学
- 1,178 篇 计算机科学与技术...
- 978 篇 软件工程
- 330 篇 信息与通信工程
- 243 篇 电气工程
- 225 篇 电子科学与技术（可...
- 220 篇 生物工程
- 184 篇 生物医学工程（可授...
- 180 篇 控制科学与工程
- 147 篇 光学工程
- 143 篇 化学工程与技术
- 123 篇 材料科学与工程（可...
- 87 篇 仪器科学与技术
- 86 篇 机械工程
- 71 篇 动力工程及工程热...
- 68 篇 土木工程
- 67 篇 建筑学
1,167 篇 理学
- 468 篇 物理学
- 404 篇 数学
- 305 篇 生物学
- 160 篇 化学
- 155 篇 统计学（可授理学、...
- 80 篇 系统科学
521 篇 管理学
- 314 篇 管理科学与工程(可...
- 256 篇 图书情报与档案管...
- 221 篇 工商管理
184 篇 医学
- 150 篇 临床医学
- 142 篇 基础医学(可授医学...
- 69 篇 公共卫生与预防医...
95 篇 法学
- 85 篇 社会学
74 篇 农学
70 篇 经济学
- 69 篇 应用经济学
58 篇 教育学
11 篇 文学
5 篇 军事学
4 篇 艺术学
2 篇 哲学

主题

90 篇 computer science
75 篇 training
74 篇 machine learning
73 篇 computational mo...
69 篇 deep learning
60 篇 accuracy
50 篇 feature extracti...
47 篇 predictive model...
47 篇 data models
46 篇 support vector m...
44 篇 sentiment analys...
41 篇 computer archite...
40 篇 fuzzy logic
39 篇 optimization
37 篇 data mining
36 篇 proposals
35 篇 education
35 篇 visualization
34 篇 information tech...
33 篇 internet of thin...

机构

74 篇 computer science...
69 篇 bioinformatics a...
58 篇 computer science...
55 篇 computer science...
48 篇 bioinformatics a...
48 篇 computer science...
47 篇 computer science...
33 篇 computer science...
33 篇 bioinformatics a...
32 篇 school of comput...
31 篇 photonics initia...
30 篇 photonics initia...
30 篇 department of el...
30 篇 computer science...
30 篇 computer science...
29 篇 computer science...
28 篇 computer science...
27 篇 department of ph...
26 篇 applied physics ...
26 篇 school of inform...

作者

127 篇 bens pardamean
108 篇 pardamean bens
92 篇 gaol ford lumban
66 篇 warnars harco le...
62 篇 heryadi yaya
59 篇 suharjito
58 篇 meyliana
55 篇 yaya heryadi
53 篇 ford lumban gaol
51 篇 harco leslie hen...
48 篇 lukas
41 篇 girsang abba sug...
40 篇 prabowo harjanto
40 篇 andrea alù
39 篇 alù andrea
36 篇 benfano soewito
34 篇 abba suganda gir...
33 篇 utama ditdit nug...
32 篇 yulyani arifin
31 篇 soewito benfano

语言

3,291 篇 英文
62 篇 其他
14 篇 中文
7 篇 日文
2 篇 西班牙文
2 篇 朝鲜文
2 篇 葡萄牙文

检索条件"机构=Graduate Program on Computer Science"

共 3378 条记录，以下是311-320 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Dual Word Embedding Framework for Gender-Based Writing Style Analysis Using Word2Vec and BERT

Dual Word Embedding Framework for Gender-Based Writing Style...

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Aditya Riyanto Amalia Zahra Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

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.

关键词： Biometrics Text analysis Accuracy Social networking (online) Blogs Supervised learning Writing Linguistics Natural language processing Random forests

来源：评论

学校读者我要写书评

暂无评论

A Decision Model for Smart Village in Measuring Socioeconomic Inequality

A Decision Model for Smart Village in Measuring Socioeconomi...

引用

International Conference on ICT For Smart Society (ICISS)

作者： Ditdit Nugeraha Utama Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350389654

ISBN: (纸本)9798350389661

Making socio-economic decisions is critical as they profoundly impact communities. It is imperative to approach these decisions with academic rigour and objectivity to effectively address prevalent community-wide issues. One such challenge often encountered by communities is socio-economic inequality. This study attempts to tackle this challenge by creating a decision model to assess socio-economic inequality in a region. The research was performed via four crucial stages, leading to the creation of a fuzzy decision model based on the Williamson Index (WI) method. This carefully developed model was designed and constructed using an object-oriented approach. The simulation results indicated that the integrated inequality index value for Sawah, an urban village in Ciputat, Indonesia, is 0.65. This em-pirical result provides valuable insights, enabling policymakers and stakeholders (as decision-makers) to design targeted policies and programs to reduce inequality and enhance community prosperity.

关键词： Object oriented modeling Simulation Indexes Stakeholders Socioeconomics

来源：评论

学校读者我要写书评

暂无评论

Deep neural networks and weighted word embeddings for sentiment analysis of drug product reviews 7

Deep neural networks and weighted word embeddings for sentim...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Suhartono, Derwin Purwandari, Kartika Jeremy, Nicholaus Hendrik Philip, Samuel Arisaputra, Panji Parmonangan, Ivan Halim Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

One of the major tasks of natural language processing is sentiment analysis. The web is a source of unstructured and rich informa-tion with thousands of opinions and reviews. Individuals, businesses, and governments can all benefit from recognizing sentiment. As part of this study, we propose a deep learning-based approach for sentiment analysis on drug product review data obtained from the UCI machine learning repository. As an alternative to deep learning models, this architecture integrates glove word embedding with convolutional neural networks (CNN). Word2vec and GloVe word embedding schemes have been evaluated empirically for their predictive performance in CNN architectures. Based on a comparison of the deep learning architecture with RoBERTa, itcan be seen that BERT architecture outperforms both of them in training and validation. However, CNN models using Glove word embedding provided superior results in testing. © 2022 Elsevier B.V.. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Parallelization of LSTM-GRU Architectures for Multivariate Prediction of Stock Prices

Parallelization of LSTM-GRU Architectures for Multivariate P...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Gabriel Asael Tarigan Eric Hermawan Abba Suganda Girsang Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

Anticipating stock market movements is challenging, as hasty prediction risks large financial losses. Stock price prediction is complex due to the high volatility and many influencing external factors. Recurrent Neural Network (RNN) models are made to learn time series data making it ideal for stock prediction based on records. Well-known RNN architectures for forecasting problems are Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). However, past studies only explored standalone models and have not generated convincing performance results. By integrating the efficiency of GRU to effectively handle shorter data sequences with LSTM's ability to capture long-term dependencies, our model aims to improve stock price forecasting accuracy by collaborating the strength between both architectures. The proposed model was used to forecast multivariate stock prices and evaluated using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). We found that parallelization of LSTM-GRU offers better prediction, up to 9.1% improvement compared to sequential LSTM-GRU and Bidirectional LSTM (Bi-LSTM).

关键词： Analytical models Sentiment analysis Accuracy Time series analysis Predictive models Logic gates Data models Information management Forecasting Stock markets

来源：评论

学校读者我要写书评

暂无评论

Object-Driven Fuzzy Decision Model for Assessing the Employees' Work from Home Eligibility

Object-Driven Fuzzy Decision Model for Assessing the Employe...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Ditdit Nugeraha Utama Christiawan Immanuel Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

Work from Home (WFH), especially in the post-pandemic era, has emerged as an alternative work system adopted by many companies. Efficiency and effectiveness are the two main reasons why WFH is favored. In addition, the implementation of the WFH system in conducting business processes within the company allows for greater flexibility in work methods. For certain types of jobs or specific industry domains, this WFH system can be quite reliable. Workers can perform their tasks from anywhere and at any time. Also, monitoring systems enable employees to be remotely tracked by the company. However, the question remains: is an employee's work environment suitable enough to ensure the successful implementation of WFH? To answer this, a standardized model is needed to assess the level of eligibility for WFH implementation. This study aims to develop a fuzzy-based decision model to evaluate the eligibility of an employee's work environment for implementing WFH. An object-oriented approach is used to describe the design of the decision model, while fuzzy logic serves as the primary method for building the model. The model successfully simulated 24 raw employee data points, yielding a highest eligibility score of 88.61 with a similarity index of 0.78 when compared to the model proposed in previous research.

关键词： Industries Fuzzy logic Object oriented modeling Buildings Companies Data models Reliability Monitoring Business

来源：评论

学校读者我要写书评

暂无评论

Web Application based Ridesharing Your Transportation in Jakarta 2

Web Application based Ridesharing Your Transportation in Jak...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Kusuma, Giovanni Randy Handana, Afan Rizqi Warnars, Harco Leslie Hendric Spits School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Binus Graduate Program - Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665400527

The city of Jakarta is getting more and more congested and crowded by the number and types of vehicles. Lack of public awareness to use public transportation causes this congestion to worsen, especially during rush hours in the morning before going to work or school and in the afternoon when returning home. This is also caused by the lack of the government of the capital city of Jakarta in providing cheap, safe, and comfortable public transportation. It is not surprising that the Indonesian government has plans to move the capital city of the Indonesian government from Jakarta on the island of Java to East Kalimantan on the island of Kalimantan. Therefore, seeing this severe traffic jam, it is essential to propose an application that can reduce congestion so that drivers who bring their vehicles can share with people around them to travel to work as a routine activity during weekdays. The model of this vehicle sharing application was designed using use case diagrams, and the database design was designed using class diagrams. In addition, security issues are also significant considering that people meet in this vehicle sharing application, and some bad people may take advantage of it. Therefore user registration and moderation are essential. It is hoped that this vehicle sharing application will reduce congestion in the capital city of Jakarta and become an example in other cities. © 2022 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Drowsiness Detection in Low-Light Conditions Using YOLO and CLAHE Augmentation for Real-Time Applications

Drowsiness Detection in Low-Light Conditions Using YOLO and ...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Sella Joanita Nur Aprilia Devi Fitrianah Computer Science Department Binus Graduate Program–Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

In the era of advancing technology, deep learning, particularly within the realm of computer vision, has emerged as a critical tool for enhancing human safety. This research focuses on developing a drowsiness detection system for car drivers using the YOLOv5 algorithm, aimed at mitigating the risks associated with microsleep, a temporary loss of attention that poses a significant threat on the roads. The prevalence of traffic accidents attributed to drowsy driving is alarming, with statistics indicating that over 9.5% of accidents in Indonesia during late 2019 were linked to drowsiness. To address this pressing issue, our study employs the YOLOv5 model to classify driver states into ‘Drowsy’ and ‘Awake’ categories, enhanced by the Contrast Limited Adaptive Histogram Equalization (CLAHE) augmentation technique, which optimizes performance in low-light conditions. The drowsiness detection system is designed as a user-friendly application that provides real-time alerts to drivers upon detecting signs of drowsiness. The implementation process includes data collection, preprocessing, and model training, leading to the evaluation of the system’s accuracy. Evaluation results demonstrate a detection accuracy of 94%, with precision and recall both reaching 93%. These findings underscore the efficacy of integrating YOLO and CLAHE in developing a reliable drowsiness detection system, contributing to road safety by reducing the risk of accidents related to driver fatigue.

关键词： YOLO Deep learning Training Adaptation models Accuracy Real-time systems Sensor systems Intelligent sensors Vehicles Accidents

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effect of Attention Mechanism and Aspect Embedding on the Performance of Long Short-term Memory Model for Aspect-Based Sentiment Analysis

Comparing the Effect of Attention Mechanism and Aspect Embed...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

The attention mechanism is one of the key enablers which have positioned transformer models as the state-of-the-art models in Natural Language Processing. By having the attention mechanism, the first version (vanilla) transformer model can retrieve the hidden state but at the same time can maintain a low requirement on the context vector dimension by selectively choosing to which encoder hidden states to give priority attention. The objective of this study is to evaluate the effect of modified Long Short-term Memory models architecture on the model performance as a predictive model. The first model is modified by adding an attention mechanism to its architecture;whilst, the second model is modified by adding additional input to its architecture. The performance of both models is compared by assigning each model the same task: to address the aspect-based sentiment analysis task. The experiment results show that adding an attention mechanism is not significantly increase the performance of the Long Short-term Memory model in comparison to adding input to the same model. In particular, the average training accuracy of the former model is 0.885;whilst, the average training accuracy of the latter model is 0.942. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Enhanced Personality Prediction: Fusing Structural and BERT-Based Lexical Features on Augmented Twitter Data 7

Enhanced Personality Prediction: Fusing Structural and BERT-...

引用

7th International Conference on Information Management and Technology, ICIMTech 2022

作者： Roslynlia Suhartono, Derwin BINUS Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (数字)9781665450904

ISBN: (纸本)9781665450904

Conventionally, assessing people's personality done by psychology experts requires more time and effort. Hence automatic personality prediction is starting to get noticed by researchers. Nowadays, many people engage themselves in social media platforms, one of which is Twitter. This platform stores actions done in this media which reflect one's personality. This research focuses on improving the performance of personality prediction models based on machine learning algorithms, by augmenting the dataset using Easy Data Augmentation to overcome imbalance dataset, thereafter combining n-grams with POS-tag weighted by TF-IDF. Results show that this method outperforms other machine learning approaches and decreases bias, with a maximum of 72.62% of the best average accuracy and 72.72% best average Fl score using Support Vector Machine classifier. The second-best model is obtained by XGBoost and, lastly, Naive Bayes classifier. Overall, this study shows that data augmentation with the addition of POS-tag feature is evident in improving the performance of personality prediction models. However, larger data is needed. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Indonesian Tweet Emotion Detection Using IndoBERT

Indonesian Tweet Emotion Detection Using IndoBERT

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Nikita Ananda Putri Masaling Ricky Reynardo Siswanto Abba Suganda Girsang Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

This study investigates emotion detection on tweets written in the Indonesian language, using the IndoBERT model that has been trained for 50 epochs. The examination conducted in this study provides a comprehensive analysis of the performance dynamics shown by the model. The assessment results provide an accuracy score of 0.74, indicating the model's proficiency in identifying sentiments within the collection of tweets. By using assessment criteria such as accuracy, recall, and the F1-score, the model's comprehensive analytical ability is validated, emphasizing its effectiveness in deciphering various emotional circumstances. The accuracy, recall, and F1-score of the model, with average values of 0.79, 0.78, and 0.78 respectively, combined demonstrate its resilience in accurately capturing subtle emotional subtleties. This study enhances our comprehension of language model applications in the field of emotional intelligence by exploring the complexities of sentiment analysis. It emphasizes the practical value of these applications in real-world scenarios.

关键词： Analytical models Sentiment analysis Emotion recognition Accuracy Prevention and mitigation Stability criteria Ecosystems Robustness Information management Resilience

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共338页 << < 28 29 30 31 32 33 34 35 36 37 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：