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

分类表

所选分类

>> <<

限定检索结果

标题

标题
作者
主题词
出版物名称
出版社
机构
学科分类号
摘要
ISBN
ISSN
基金资助
索书号

作者

作者
标题
主题词
出版物名称
出版社
机构
学科分类号
摘要
ISBN
ISSN
基金资助
索书号

文献类型

2,185 篇 会议
1,182 篇 期刊文献
3 册 图书

馆藏范围

3,370 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,742 篇 工学
- 1,177 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
1,161 篇 理学
- 468 篇 物理学
- 404 篇 数学
- 304 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
73 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
74 篇 training
72 篇 computational mo...
71 篇 machine learning
68 篇 deep learning
57 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

72 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...
32 篇 school of comput...
32 篇 bioinformatics a...
31 篇 photonics initia...
30 篇 department of el...
30 篇 computer science...
30 篇 computer science...
29 篇 photonics initia...
29 篇 computer science...
28 篇 computer science...
27 篇 department of ph...
26 篇 applied physics ...
26 篇 school of inform...

作者

126 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
51 篇 harco leslie hen...
51 篇 ford lumban gaol
48 篇 lukas
40 篇 prabowo harjanto
39 篇 andrea alù
39 篇 alù andrea
37 篇 girsang abba sug...
37 篇 abba suganda gir...
36 篇 benfano soewito
33 篇 utama ditdit nug...
31 篇 yulyani arifin
31 篇 soewito benfano

语言

3,283 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 3370 条记录，以下是41-50 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：

Artificial Intelligence-Powered Intent Classification for Indonesian E-Wallet Customer Service Chatbots 4

Artificial Intelligence-Powered Intent Classification for In...

引用

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

作者： Owen, Christopher Suhartono, Derwin Binus Graduate Program Bina Nusantara University Computer Science Department Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331506490

The rapid expansion of e-wallet services in Indonesia has significantly heightened the need for efficient customer service solutions, making chatbots an essential tool for user support. However, many providers continue to rely on rule-based chatbots, resulting in rigid interactions that struggle to meet diverse user needs or handle the linguistic complexities of the Indonesian language. This study addresses these limitations by developing an AI-powered intent classification model specifically tailored for Indonesian e-wallet customer service, aimed at delivering a more accurate, adaptive, and user-centered experience. A custom dataset was created from user comments on social media associated with Indonesia's top e-wallet providers, followed by data pre-processing and clustering using the BERTopic model. To improve interpretability, OpenAI's GPT-4 was employed for label refinement, resulting in enhanced clarity. Various models were tested, including IndoBERT, RoBERTa, and Convolutional Neural Network (CNN) architectures in both 2D and 3D configurations. The highest-performing model combined IndoBERT embeddings with a 3D CNN classifier, achieving an accuracy of 84.30%, precision of 84.33%, recall of 84.30%, and an F1-score of 84.24%. This study contributes a unique Indonesian-specific dataset and demonstrates the potential of AI to transform customer service interactions in Indonesia's e-wallet sector, offering a clear advancement over traditional rule-based approaches. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Comparison of Spelling Error Correction Algorithms for the Indonesian Language 11

Comparison of Spelling Error Correction Algorithms for the I...

引用

11th International Conference on Information and Education Technology, ICIET 2023

作者： Yanfi, Yanfi Setiawan, Reina Soeparno, Haryono Budiharto, Widodo Bina Nusantara University BINUS Graduate Program Computer Science Jakarta Indonesia Bina Nusantara University BINUS Graduate Program Computer Science School of Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9781665465489

Edit distance as a string measurement metric is often used to help detect misspellings in languages. This paper aims to compare two string spelling error correction algorithms for the Indonesian language. The N-gram, Jaro-Winkler distance, and Levenshtein distance algorithms are used to determine whether they can accurately correct typological errors in the Indonesian language. Moreover, this study utilized KNIME tools to process the data from beginning to end. The data was retrieved from news in Indonesia. After the experiment on N from 1 to 12, the results obtained for the comparative analysis proved that Jaro-Winkler distance performed better than Levenshtein distance for comparing smaller strings like words and names. However, Levenshtein distance performs as well as Jaro-Winkler distance started from four strings. Finally, both Jaro-Winkler distance and Levenshtein distance algorithm got the best performance accuracy for eight strings with an accuracy of 99.52 percent. The result of this study is also presented that both algorithms can support word error correction for the Indonesian language. © 2023 IEEE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Visualization and Simulation of Any MPU Architecture Design with Meta-Instruction 23

Visualization and Simulation of Any MPU Architecture Design ...

引用

23rd International Symposium on Communications and Information Technologies, ISCIT 2024

作者： Morimoto, Tomoyuki Wang, Ziming Luo, Jiahui Ogawa, Sota Tsutsumi, Toshiyuki Meiji University Department of Computer Science School of Science and Technology Kanagawa Japan Graduate School of Science and Technology Meiji University Computer Science Program Kanagawa Japan

ISBN: (纸本)9798350353952

Our conventional architecture design tool converted instructions of microprocessor (MPU) into meta-instructions with both semantic and functional expressions, and it displayed a circuit diagram of the meta-instruction. The tool was able to perform dynamic simulation only on an educational processor called COMET. However, the meta-instruction must be able to express the arbitrary instruction of at least different significant existing MPUs in order to design arbitrary MPUs. Furthermore, it should be possible to visualize all instructions and then execute them. Therefore, we have improved the meta-instruction so that the architecture design tool applies to major MPUs: MIPS, ARM, and RISC-V in addition to COMET. The improved architecture design tool visualizes and simulates the circuit diagram of the improved meta-instruction. The result shows the possibility of the meta-instruction-based architecture design tool being able to design any MPU. © 2024 IEEE.

关键词： Microprocessor chips

来源：评论

学校读者我要写书评

暂无评论

Detection of Employee Fatigue Based on Image Processing Using Deep Learning Model 4

Detection of Employee Fatigue Based on Image Processing Usin...

引用

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

作者： Ethan, Michael Kusuma, I. Gede Putra Bina Nusantara University Computer Science Department Binus Graduate Program Jakarta11480 Indonesia

ISBN: (纸本)9798331506490

Fatigue in workplace is a common thing shared by all employees. Continuous exposure of fatigue could lead to negative productivity for companies. Current research on fatigue detection mostly focused to detect fatigues from a single 2D image data, meanwhile research on fatigue detection using each frames from video data is needed for better detection for fatigue process. The main advantage of using each timesteps of frames from video data which makes the model is able to predict long term dependency of fatigue person. To solve this problem, a deep learning model is proposed that could detect employee fatigue based on image processing using video data. Three models are used to train data using Convolutional Neural Network (CNN), which are Time Distributed CNN LSTM, 3D CNN, and 3D CNN LSTM. Out of those three models, the best model to detect fatigue person from video data is Time Distributed CNN Model with F-1 Score value of 0.77 and Accuracy Score of 0.76 for testing data. The model that gives best inference time is also Time Distributed CNN Model with the average value of 382 miliseconds to detect fatigues from 58 testing data with each of the data has duration of 3 seconds and 12 frames. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Efficiency of Multi-Language Data Serialization for Hybrid Cloud-Edge HRIS 9th

Efficiency of Multi-Language Data Serialization for Hybrid C...

引用

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

作者： Winata, Andreas Soeparno, Haryono Gaol, Ford Lumban Arifin, Yulyani Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

In hybrid cloud-edge systems, data processing is distributed between cloud servers and edge servers, this makes data serialization critical for efficient data transfer between servers. This study evaluates the efficiency of multi-language data serialization of Human Resources Information System (HRIS) in a hybrid cloud-edge environment. Because lack of existing studies that specifically evaluate multi-language data serialization for hybrid cloud-edge HRIS, this study conducted a Systematic Literature Review (SLR) to get the list of current state of the art of data serialization methods and then used this result to evaluate the methods. By focusing on HRIS employee data from the employee management module, this study measures both data serialization and deserialization using performance metrics of time, data size, and CPU usage. The results indicate that no methods excel in all metrics, but FlatBuffers, Protocol Buffer, and Apache Avro can provide balanced effectivity across the metrics. The study gives valuable insight for selecting data serialization methods, architecture, and systems requirements in hybrid cloud-edge HRIS to ensure the performance efficiency of the system. © 2024 The Authors.

关键词： Cloud platforms

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 4

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

引用

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

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

ISBN: (纸本)9798331506490

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. © 2024 IEEE.

关键词： Personnel

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

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

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

Model of Text-to-Text Transfer Transformer for Hadith Question Answering System 11

Model of Text-to-Text Transfer Transformer for Hadith Questi...

引用

11th International Conference on Information Technology, computer and Electrical Engineering, ICITACEE 2024

作者： Sulistio, Bambang Suhartono, Derwin Soeparno, Haryono Budiharto, Widodo Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Computer Science Program Jakarta11480 Indonesia

ISBN: (纸本)9798350389289

The advancement of Artificial Intelligence (AI), notably in Natural Language Processing (NLP), has been remarkable. Among its applications, Question-Answering (QA) systems stand out, assisting users in accessing pertinent information across various topics, including religious contexts. Religion plays a significant role in providing guidance on moral values to modern society, such as tolerance, compassion and social norms. Religious practices taught by religion serve as significant foundations for addressing the increasingly advancing influence of technology. The primary goal of this paper is to create a question-answering system proficient in analyzing user inquiries and precisely extracting data from translated Indonesian Hadith datasets. This research endeavors to enhance question-answering accuracy through Deep Learning techniques. Employing pre-processing methods, the system interprets user query intents. Furthermore, the Text-to-Text Transfer Transformer (T5), a text-based language Transformer model, is utilized to streamline the retrieval process for Hadith-related queries based on relevant subjects. The research findings demonstrate the precision of answers through BLEU and ROUGE scores. The novelty of this study lies in the creation of a dataset of hadith translations in Indonesian and the fine-tuning of the T5 model that has been trained using a dataset of questions and answers based on these translations. This research demonstrates the following evaluation scores: BLEU: 0.606, ROUGE-1: 0.702, ROUGE-2: 0.548, and ROUGE-L: 0.701, indicating that the answers generated by this particular research model are better compared to those produced using the standard mT5 model. © 2024 IEEE.

关键词： Deep learning

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337页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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

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：