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

2,602 篇 会议
2,274 篇 期刊文献
8 册 图书

馆藏范围

4,884 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,577 篇 工学
- 1,365 篇 计算机科学与技术...
- 1,131 篇 软件工程
- 352 篇 信息与通信工程
- 300 篇 电气工程
- 296 篇 化学工程与技术
- 289 篇 电子科学与技术（可...
- 266 篇 生物工程
- 257 篇 核科学与技术
- 238 篇 控制科学与工程
- 236 篇 生物医学工程（可授...
- 220 篇 材料科学与工程（可...
- 176 篇 光学工程
- 129 篇 动力工程及工程热...
- 123 篇 仪器科学与技术
- 122 篇 机械工程
- 109 篇 环境科学与工程（可...
2,007 篇 理学
- 1,010 篇 物理学
- 496 篇 数学
- 430 篇 生物学
- 325 篇 化学
- 181 篇 统计学（可授理学、...
- 107 篇 天文学
- 105 篇 系统科学
616 篇 管理学
- 375 篇 管理科学与工程(可...
- 281 篇 图书情报与档案管...
- 262 篇 工商管理
365 篇 医学
- 264 篇 临床医学
- 206 篇 基础医学(可授医学...
- 125 篇 公共卫生与预防医...
134 篇 农学
125 篇 法学
- 113 篇 社会学
106 篇 教育学
84 篇 经济学
12 篇 文学
5 篇 军事学
4 篇 艺术学
3 篇 哲学

主题

108 篇 computer science
84 篇 machine learning
80 篇 computational mo...
80 篇 training
71 篇 deep learning
66 篇 accuracy
60 篇 hadron colliders
55 篇 optimization
53 篇 predictive model...
53 篇 software
51 篇 feature extracti...
49 篇 education
48 篇 computer archite...
48 篇 data models
47 篇 sentiment analys...
46 篇 fuzzy logic
46 篇 data mining
45 篇 support vector m...
44 篇 visualization
43 篇 higgs bosons

机构

416 篇 department for p...
412 篇 faculty of scien...
400 篇 department of ph...
394 篇 kirchhoff-instit...
389 篇 department of ph...
387 篇 department of ph...
387 篇 institute of phy...
368 篇 institute of phy...
363 篇 fakultät für phy...
351 篇 instituto de fís...
310 篇 department of ph...
298 篇 dipartimento di ...
294 篇 nikhef national ...
288 篇 department of ph...
283 篇 graduate school ...
280 篇 department of ph...
278 篇 department of ph...
273 篇 universidade fed...
263 篇 ictp trieste
260 篇 department of ph...

作者

337 篇 c. alexa
337 篇 g. bella
337 篇 d. calvet
337 篇 c. amelung
335 篇 j. strandberg
335 篇 g. spigo
335 篇 f. siegert
334 篇 j. m. izen
323 篇 r. ströhmer
322 篇 m. rijssenbeek
322 篇 s. jin
322 篇 g. gaudio
320 篇 s. mohapatra
313 篇 s. guindon
310 篇 a. kaczmarska
308 篇 y. tayalati
300 篇 j. schaarschmidt
294 篇 a. d. pilkington
290 篇 m. klein
290 篇 l. chevalier

语言

4,377 篇 英文
459 篇 其他
22 篇 中文
10 篇 葡萄牙文
5 篇 日文
5 篇 斯洛文尼亚文
4 篇 德文
3 篇 西班牙文
3 篇 法文
2 篇 朝鲜文
1 篇 捷克文
1 篇 意大利文

检索条件"机构=Graduate Program in Computer Science of the Federal University"

共 4884 条记录，以下是721-730 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：

Implementation of Fine-Tuned BERT for Enzyme Classification Based on Gene Ontology

Implementation of Fine-Tuned BERT for Enzyme Classification ...

引用

International Conference of Advanced Informatics: Concept, Theory and Application (ICAICTA)

作者： Matthew Martianus Henry Christian Kenneth Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331520311

ISBN: (纸本)9798331520328

Enzymes are biocatalysts with vital roles in biological functions and many industrial applications. Diverse enzymes are classified using Enzyme Commission (EC) nomenclature, making differentiation challenging. On the other hand, another biological information, gene ontology (GO), can describe the biological aspects of enzymes, covering related biological processes (BP), molecular functions (MF), and their locations within cells (CC). This study proposes a novel EC class and subclass classification of enzymes within the ontology subclass based on their GO semantics using a Bidirectional Encoder Representation of Transformer (BERT). The BERT model is first fine-tuned using the preprocessed GO term name and definition, with the enzymes in each ontology class (BP, MF, or CC) are also divided based on how the GO assigned, either through manual annotation (NONIEA) or electronically inferred (IEA). BERT successfully obtained 0.93, 0.60, 0.99, 0.90, 0.40, and 0.35 F1 scores during fine-tuning for BP IEA, BP NONIEA, MF IEA, MF NONIEA, CC IEA, and CC NONIEA, respectively. On the test set, the fine-tuned BERT significantly outperformed GOntoSim, a framework to calculate semantic similarity based on classical information theory, in EC class classification across all metrics with less inference time in all ontology subclass. Expanded further to the EC subclass, BERT can classify the enzyme on the EC subclass level in BP IEA and MF IEA ontology subclass. However, longer epochs are needed in fine-tuning. This result shows that the names and definitions of GO terms are distinguishable features in classifying enzymes as an alternative to the information content approach.

关键词： Measurement Enzymes Semantics Bidirectional control Manuals Ontologies Transformers Encoding Biological information theory Informatics

来源：评论

学校读者我要写书评

暂无评论

Development of an air quality station using low-cost sensors

Development of an air quality station using low-cost sensors

引用

Brazilian Symposium on Computing System Engineering (SBESC)

作者： Mateus Maruzka Roncaglio Edson Tavares de Camargo Leila Droprinchinski Martins Marcio Seiji Oyamada Graduate Program in Computer Science State University of Western Paraná (UNIOESTE) Cascavel Brazil Federal Technology University of Paraná (UTFPR) Toledo Brazil Federal Technology University of Paraná (UTFPR) Londrina Brazil

Air pollution is one of the most important health problems causing various diseases. According to the World Health Organization (WHO), it is estimated that more than 7 million deaths are due to air pollution. For this reason, air quality monitoring is an important indicator for guiding public policy. However, government stations are widely scattered and their high cost makes it unprofitable to invest in higher resolution. Low-cost air quality monitoring sensors can overcome this problem, but also bring new challenges. This paper presents the development of a low-cost air quality monitoring device. The low-cost station collects the following measurements: carbon monoxide (CO), nitrogen dioxide (NO 2 ), sulfur dioxide (SO 2 ), ozone (O 3 ), and particulate matter. The collected data is corrected using a machine learning model and sent to the Internet in real time via the LoRaWAN protocol. Mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), linearity coefficient (R 2 ), and Pearson r were used to compare model performance. Our results show that linear models such as the Alphasense equation and linear model regression cannot accurately describe the sensor response to the reference gas sensor, whereas the RF model performs better in each metric. The performance of the RF model demonstrates the potential to improve air quality monitoring and the decision-making process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis in Indonesian Trading using Lexicon-based and Support Vector Machine

Sentiment Analysis in Indonesian Trading using Lexicon-based...

引用

computer science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Raymond Sunardi Oetama Yanfi Yanfi Masagus M. Ikhsan Assiddiq U.P Sani Muhamad Isa Information System DepartmentFaculty of Engineering and Informatics Universitas Multimedia Nusantara Jakarta Indonesia Computer Science Department BINUS Graduate Program Computer Science School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

Many individuals now trade online utilizing trading software in the digital world. Binomo is one of Indonesia's most popular trading platforms. This is because some influencers made several promises to Binomo customers. Since many customers were deceived, this case became quite popular. This study was executed to see how Indonesians felt about the Binomo application after the case went viral. The solution taken was in the form of sentiment analysis because there had been no previous research on sentiment analysis that discussed the Binomo case. The data was scanned using Netlytic tools, a cloud-based text and social network analyzer capable of identifying any talks on social media sites such as Twitter. The sentiment analysis of Binomo trading tweets by using the Multi-Perspective Question Answering lexicon utilized the KNIME tool. But unfortunately, the accuracy of sentiment analysis results is low. Furthermore, the Support Vector Machine technique is also being conducted. The Term Frequency-Inverse Document Frequency method is applied to perform feature extraction whilst the chi-square approach is utilized to identify features that are thought to be useful for inclusion in the classification process and to exclude features that are irrelevant to the target class. The obtained accuracy is 86%. The study proposes that words from the algorithm's outputs can be utilized to improve the quality of sentiment analysis using the lexicon. As an outcome of the algorithm, positive and negative terms are added to the lexicon, increasing the accuracy of sentiment analysis using the new vocabulary from 58.984% to 71.146%.

关键词： Support vector machines Training Sentiment analysis Vocabulary Dictionaries Social networking (online) Blogs

来源：评论

学校读者我要写书评

暂无评论

Leveraging ChemBERTa Robustness in Drug-Drug Interaction Classification via Molecular Decomposition

Leveraging ChemBERTa Robustness in Drug-Drug Interaction Cla...

引用

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

作者： Christian Kenneth Alyssa Imani Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

Understanding drug-drug interactions (DDIs) can benefit us by enhancing drug effectiveness and preventing side effects that arise from consuming multiple drugs administered together. However, as the number of novel drugs increases, predicting potential DDIs becomes more challenging. Previous studies have used the molecular language model ChemBERTa to predict potential DDIs, but the predictions were only tested on unseen drugs and not dissimilar drugs, while also performing poorly. In this study, we demonstrate that a simple molecular preprocessing method using BRICS decomposition can enhance ChemBERTa robustness in predicting potential DDIs for unseen-dissimilar drugs. Specifically, we employ fragmentation with a minimum fragment size of 5 (BRICS-5), which balances the number of fragments and decomposition speed. Using this method, we were able to improve ChemBERTa robustness, reflected by an approximate increase of 1.5% in recall and 2.2% in the f1-score compared to non-decomposed molecules. Our findings suggest that this preprocessing method could be useful in the development of future AI-based approaches for solving challenging molecular tasks across different settings and various model architectures.

关键词： Drugs Seminars Accuracy Data preprocessing Predictive models Robustness Data models Intelligent systems Information technology

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-SVM Approach for Malaria in Blood Cell Detection

A Hybrid CNN-SVM Approach for Malaria in Blood Cell Detectio...

引用

Software Engineering and Information Technology (ICoSEIT), International Conference on

作者： Andrea Stevens Karnyoto Mahmud Isnan Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

There is still a severe malaria problem worldwide, particularly in regions with limited access to diagnostic tools. It is crucial to develop a system for detecting malaria in blood cells. This paper presents a hybrid Convolutional Neural Network (CNN), and as a classifier, we use a Support Vector Machine (SVM) framework for the automated detection of malaria parasites in blood cell images. The proposed system leverages the strengths of CNNs in feature extraction and representation learning from images, combined with the discriminative power of SVMs for classification. Initially, CNN extracts intricate features from blood cell images, capturing essential patterns indicative of malaria infection. Subsequently, the extracted features are used to train an SVM classifier, enabling accurate discrimination between parasitized and uninfected blood cells. Experimental dataset evaluations were obtained from the Lister Hill National Center for Biomedical Communications website of the National Library of Medicine. The proposed model achieves a better f1-score, outperforming individual CNN or SVM models, around 0.015 compared to individual CNN models and 0.27 compared to individual SVM models. This hybrid CNN-SVM methodology offers a promising solution for accurately and efficiently detecting malaria parasites in blood cell images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mitigating Berkson's Paradox with Neural Propensity Score Matching in E-Commerce Deals

Mitigating Berkson's Paradox with Neural Propensity Score Ma...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Nicholas Dominic Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Within observational Data science workloads, Berkson's paradox can lead to false causal inferences. One of the prominent quasi-experimental methods to mitigate this selection bias is Propensity Score Matching (PSM). An approach called Neural PSM (NPSM) was developed to overcome the drawbacks of conventional regression-based PSM, including its limited flexibility to model high-dimensional data and non-linear relationships that could cause imperfect covariate balance. In this study, a three-layer depth of Deep Neural Networks was designed to estimate propensity scores and finally balance both control and treatment groups of the Groupon dataset. An unsupervised k-Nearest Neighbor algorithm then helped the model to efficiently detect and cluster similar matching points. From the five salient features presented, NPSM successfully achieved lower differences in Cohen's d effect size, i.e., 0.313 for coupon duration, 0.017 for promotion length, 0.425 for quantity sold, -0.199 for limited supply, and 0.395 for Facebook likes. While these results mostly outperformed Linear Regression (LR) and Random Forest (RF) models, further evaluation is needed to verify the true effectiveness of NPSM in mitigating Berkson's paradox in broader e-commerce contexts.

关键词： Radio frequency Social networking (online) High dimensional data Linear regression Nearest neighbor methods Data science Electronic commerce Intelligent systems Cybernetics Context modeling

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph-Enhanced Semantic Cache for Low-Latency and Cost-Effective Inference in Large Language Models

Knowledge Graph-Enhanced Semantic Cache for Low-Latency and ...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Nicholas Dominic Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

In organizational knowledge management, Large Language Model (LLM) caches act as a semantic repository gathered from previous LLM responses. Due to intensive calls from multiple users, LLM may suffer from high inference latency. While there are many prior available approaches to solve this problem, most of them are inherently complex. This paper introduced a Knowledge Graph-enhanced Semantic Cache mechanism as an alternative, lightweight technique to boost retrieval for similar prompts. The latest state-of-the-art open-source LLM, named Google's Gemma-2B-it, was used to generate sample prompts and responses as a draft, while a knowledge graph (KG) was built from Wikipedia sentences. To create embeddings of prompts and KG, all-MiniLM-L6-v2 from SentenceTransformer was used. This new cache system resulted in up to 28% improvement over a standard model. In particular, reinforcement with KG cache embeddings yielded more than 85% semantic cache accuracy. To map the next trajectory of this pilot study, an overview of the extended framework for LLM knowledge management was also presented in this paper. The framework includes the new KG- enhanced cache system equipped with scalable security and fallback mechanisms that can promote green technology through substantial improvements in latency, throughput, and overall LLM costs.

关键词： Large language models Semantics Throughput Knowledge management Internet Trajectory Security Online services Low latency communication Standards

来源：评论

学校读者我要写书评

暂无评论

Threats, Risks, and Mitigations in Cloud Computing Environment

Threats, Risks, and Mitigations in Cloud Computing Environme...

引用

International Conference on Informatics and Computing (ICIC)

作者： Nur Chalik Azhar Muhammad Zarlis Yulyani Arifin Benfano Soewito Computer Science Department BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia Information System Management Department Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Cloud computing has many benefits in various sectors. However, there are threats such as malware, data loss, and misuse of access rights, as well as risks, that occur in the cloud computing environment. This study aims to identify and further explore the types of threats, risks, and mitigation strategies in the cloud computing environment, as well as what risk mitigation components are needed to mitigate risks in the cloud computing environment. This research method uses Kitchenham because it is commonly used to conduct systematic literature reviews (SLR). Sources only refer to journals and proceedings indexed in the IEEE Explorer, scienceDirect, Springer, ACM Digital Library, Wiley Online Library, and Emerald Insight database. The results of this study identified 173 papers based on keywords, 68 papers based on titles, and abstracts, and produced 59 selected papers based on inclusion and exclusion criteria, where the type of threat produced 20 findings, the type of risk 11 findings, and risk mitigation strategies 13 findings, and produced 4 findings for risk mitigation components. Based on the findings, it can be used to mitigate risks in the cloud computing environment.

关键词： Cloud computing Databases Prevention and mitigation Permission Libraries Malware Informatics Risk mitigation Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Real-time monitoring system for sudden cardiac death based on container orchestration and Binary Serialization

Real-time monitoring system for sudden cardiac death based o...

引用

2021 International Symposium on Electronics and Smart Devices, ISESD 2021

作者： Surantha, Nico Wincent Muhamad Isa, Sani BINUS Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9781665441469

Sudden Cardiac Death (SCD) is happening because the heart stops pumping the blood to the brain, lungs, et cetera, which will cause death within an hour. With this high risk and low survivability rate, real-time Internet of Things (IoT) monitoring systems have become a solution to tackle this problem. The system needs to be accessible at any time and condition by multiple users who bring up the needs of the availability and scalability of the system. Some research had been conducted on IoT monitoring system but still the result of availability and scalability not acceptable for a real-life scenario. The purpose of this research is to propose an architecture for a real-time IoT monitoring system for sudden cardiac death by using Kubernetes as the container orchestration and ProtocolBuffers as the Binary Serialization. The result shows us applying Kubernetes and ProtocolBuffers gives a good result with 100% successfully stored data and 50.5s end-to-end Execution time for 50000 requests which reflect a high availability and fast system. © 2021 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

The Information Systems and Model for Succession Planning in Higher Education Institutions

The Information Systems and Model for Succession Planning in...

引用

computer Applications (ICCA), IEEE Conference on

作者： Devyano Luhukay Ford Lumban Gaol Meyliana Harjanto Prabowo Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331534592

ISBN: (纸本)9798331534608

Succession planning is important in organization management. It is a strategic level management that involves not only finding the best successor but also including the development program for the successor so that they will be ready for the new prospective position. The integration and collaboration between all related stakeholders are important. Specifically, in succession planning at higher education, key positions play an important role so that institutional operations can run well. In this research, a succession planning model in higher education was built using the Systematic Literature Review(SLR), and the Software Development Lifecycle(SDLC) method was used for the application development, also, to be able to evaluate the implementation of one of the steps of the model, the simulation technique used machine learning (ML) to find the best algorithm for predicting the readiness of potential successors at higher education. Six algorithms were used: Logistic Regression, Decision Tree, K-Nearest Neighbor, Linear Discriminant Analysis, Gaussian Naïve Bayes, and Support Vector Machine. The data prepared for the simulation is based on the factors for the best successor candidate. The results obtained in this research are the succession planning model and the application design, as well as the Support Vector Machine (SVM) algorithm as the best algorithm for predicting the readiness status of successor candidates based on SVM’s accuracy score that is compared to the other algorithm in some variance amounts of data. The Succession Planning Model that is actualized in the application design provides a reference for the higher education institution to implement the Succession Model in their institution.

关键词： Support vector machines Machine learning algorithms Systematics Education Software algorithms Machine learning Predictive models Prediction algorithms Planning Information systems

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489页 << < 69 70 71 72 73 74 75 76 77 78 > >>

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：