检索结果-内蒙古大学图书馆

1st International Conference on Technology, Engineering, and Computing Applications, ICTECA 2023

作者： Halim, Rico Girsang, Abba Suganda Riftiarrasyid, Mohammad Faisal Binus Graduate Program Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350360554

The advancements in technology during the 20th century resulted in the onset of the digital computer era. This study investigates the relative importance of earlier algorithms in comparison to more recent ones. Various research projects suggest improving vectorization by combining conventional and modern techniques, while others suggest optimizing it through algorithmic methods. This study primarily focuses on employing Bayesian optimization to optimize hyperparameters, hence improving the performance evaluation of TF-IDF FastText sentiment classification models. This study presented four models: the initial model utilized FastText with a preprocessing step that involved removing stopwords, the second model employed Fast-Text without any optimization using Bayesian optimization, the third model utilized FastText with optimization using Bayesian optimization, and the fourth model combined FastText with TF-IDF and was further optimized using Bayesian optimization. The Support Vector Machine (SVM) technique will be employed to evaluate all of the models. The findings suggest that the model's performance stays unchanged when stopwords are eliminated (Precision, Recall, F1: 0.9007). The model demonstrates a slight enhancement through the utilization of Bayesian optimization, resulting in a 0.02% increase, reaching a final accuracy of 0.9019%. Bayesian optimization is frequently employed to improve performance. The performance of Bayesian optimization is affected by the magnitude of the learning rate, and models that do not utilize Bayesian optimization demonstrate inferior performance. Both the TF-IDF FasText model and FastText model yielded comparable outcomes, attaining an F1 score of 0.9019 after being tuned by Bayesian optimization. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Hybrid Database System of MySQL and MongoDB in Web Application Development 3

Hybrid Database System of MySQL and MongoDB in Web Applicati...

引用

3rd International Conference on Information Management and Technology, ICIMTech 2018

作者： Ongo, Gregorius Kusuma, Gede Putra Computer Science Department Bina Nusantara University BINUS Graduate Program-Master of Computer Science Jakarta11480 Indonesia

ISBN: (纸本)9781538658215

The increasing amount of data that need to be processed in a company are affecting the performances of the database system. Relational Database Management System (RDBMS) is a commonly used database system, but also known to having a decreased performance when handling high amount of data. N oSQL is an alternative storage option that is different than RDBMS and known for faster performance when handling high amount of data. In this contribution, we compare the performances between RDBMS MySQL and a hybrid model of MySQL and NoSQL MongoDB when being used on a web application. We implemented a simple social media website to evaluate the performance of using different database models. The website is equipped with chat and profile view features. Experiments are performed using randomly generated user profiles and chat data. Based on our evaluations, the hybrid database of MySQL and MongoDB achieves higher read and write performances than the MySQL alone. Meanwhile MySQL can handle more sensitive data and maintaining data consistency. The hybrid model database MySQL and MongoDB uses less disk space than MySQL alone, but uses more RAM. We also observed that there is not much difference in CPU usage for both database models. © 2018 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Data Center-Disaster Recovery Center (DC-DRC) for High Availability IT Service 3

Data Center-Disaster Recovery Center (DC-DRC) for High Avail...

引用

3rd International Conference on Information Management and Technology, ICIMTech 2018

作者： Dhanujati, Narendra Girsang, Abba Suganda Computer Science Department Bina Nusantara University Jakarta BINUS Graduate Program-Master of Computer Science 11480 Indonesia

ISBN: (纸本)9781538658215

Currently, the companies are required to have conducting business activities and continue constantly in touch with its customers to provide IT service availability continuously. The systems must be available at all times with an ever-on-The-job system, requiring a high availability system to keep the service operable 24×7×365. This issue brings the disaster recovery plan (DRP) becomes an important issue for the data and IT infrastructure. This is a very potential risk because the data will be constantly threatened by disturbance such as viruses, hackers or disasters such as natural disasters. This paper explains the concept rather than disaster recovery service planning and database replication. This study covers the evaluation, planning, implementation and testing of the disaster recovery solution. © 2018 IEEE.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Neural controller design for a class of nonlinear systems with time-varying delay: A bibliometric analysis-based short literature review

Neural controller design for a class of nonlinear systems wi...

引用

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

作者： Wijaya, Santo Gaol, Ford Lumban Wibowo, Antoni Zarlis, Muhammad Bina Nusantara University BINUS Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program - Master of Information System Management Information System Management Department Jakarta11480 Indonesia

ISBN: (纸本)9798350320954

Real-world practical systems inherently exhibit non-linearities in their dynamics. Also, it is known that a time-varying delay exists in the system state or input-output. Combined, it affects the stability of the closed-loop system. It also increases the complexity of the controller design. In-depth controller design research on the class of Nonlinear Systems with Time-Varying Delay (NSTVD) has been the focus of the control community for many years. However, there is a lack of Systematic Literature Review (SLR) and classifications of the papers on this topic. This paper aims to review controller design utilizing a neural network model for the class of NSTVD systems. The study employs Kitchenham's SLR method to gather, analyze and synthesize published papers from reliable databases between 2017 and 2021. The bibliometric analysis for the selected 38 papers reveals the prolific authors, countries, affiliations, publishers, co-authorship network, co-occurrences of keywords, and ten most-cited papers. Finally, this paper developed a conceptual map outlining six multi-layered findings: the addressed problem, control design method, nonlinear system properties, time-varying delay properties, system constraint properties, and actuator limit properties. A brief qualitative analysis of the ten most-cited papers is performed based on the map. The findings highlighted that the proposed methods have shown encouraging results in the simulation domain and can be used as a source of inspiration for future studies and implementation of the neural controller design of the NSTVD system. © 2023 IEEE.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Fingermath - Arithmetic Hand Gesture Game to Improve Early Childhood Mathematics Learning 4

Fingermath - Arithmetic Hand Gesture Game to Improve Early C...

引用

4th International Conference on Information Management and Technology, ICIMTech 2019

作者： Yuliana, Dewi Suharjito Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781728133331

Teaching mathematics has received priority in schools, because mathematics is the basis for development in understanding mathematics as a whole at school. computer technology used in teaching and learning can help improve children's preferences and abilities to learn mathematics in class, and can change attitudes of early childhood who are more critical, creative, and innovative. Jarimagic method is one method for learning to count on the fingers, where early childhood often communicate with fingers in learning mathematics in the classroom. For this reason, research attempts learning methods with interactive games with hand movements using the Jarimajic method and tools scratch 2.0. In this study, evaluation of data obtained through 20 child respondents was carried out by testing before using the game and after using the game, using Pre-Test and Post-Test analysis, which was divided into 2 results based on the preferences and abilities of early childhood learning mathematics in the classroom. From the study, the game development was carried out using the System Development Life Cycle (SDLC) method by taking the model of implementation the waterfall model. then a game is designed to overcome this problem. After the game is made, the game will be tested again for early childhood, with T-Test statistical analysis as the final data obtained from research that shows whether early childhood likes and increases ability to learn mathematics after the game is implemented. The results of this study are the realization of interactive game-based learning methods for early childhood in learning to count mathematics. especially in learning additions and collection using the jarimajic method so that children have the ability and preference in learning mathematics. © 2019 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Recommendation System Journalist for Getting Top News Based on Twitter Data

Recommendation System Journalist for Getting Top News Based ...

引用

2019 International Conference of science and Information Technology in Smart Administration, ICSINTeSA 2019

作者： Girsang, Abba Suganda Isa, Sani Muhamad Harvy, Ikrar Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

One application that can be utilized in finding the latest news is by utilizing the development of information and communication technology such as seeing the delivery of public information through social media such as twitter. This study implements the system which is able to get the trending or top news based on twitter data. This information will connect to the journalist via mobile application. It helps journalists to get the potential news to be reported in their media. The application will group each tweets into various themes based on the cosine similarity. The tweets which are more the certain threshold, can be indicated as the top news. The top news is then classified into one category news by using SVM algorithm. The training data becomes from the source data of one media news. The specific topic of this result will ease to order the journalist cover this top news. The system can be implemented well. © Published under licence by IOP Publishing Ltd.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Big Data Security Approach in Cloud: Review 3

Big Data Security Approach in Cloud: Review

引用

3rd International Conference on Information Management and Technology, ICIMTech 2018

作者： Damayanti, Finka Ria Elmizan, Kemal Anshari Alfredo, Yoel Frans Agam, Zidni Nurrobi Wibowo, Antoni Computer Science Department Bina Nusantara University BINUS Graduate Program-Master of Computer Science Jakarta11480 Indonesia

ISBN: (纸本)9781538658215

In big data era, data may be in the form of structured, unstructured and semi-structured. They become an asset for companies that contain important insights and support in decision-making processes. Big data is one of technologies that used by many organizations for managing store data and data analysis. Therefore, storage management is one of important processes in big data management to ensure that data are stored correctly, safely and easily to be accessed. Despite having many advantages, big data technology still has several issues on storage management, especially if we relate between big data and cloud computing, such as data security which is very important. In this paper, we reviewed the previous works for data security in storage management in big data technology and provide a suggestion to answer the challenge of data security. © 2018 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Automatic Speech Recognition in Indonesian Using the Transformer Model

Automatic Speech Recognition in Indonesian Using the Transfo...

引用

2023 International Conference on Informatics, Multimedia, Cyber and Information Systems, ICIMCIS 2023

作者： Sonata, Ilvico Bina Nusantara University Binus Graduate Program Computer Sciiene Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350307306

Automatic Speech Recognition (ASR) is useful for converting speech into text. ASR is needed to display automatic subtitles on movies or when conducting video conferencing. The use of deep learning in ASR applications is currently still dominated by Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN). Several previous studies used the Transformer deep learning model in building the ASR model. The accuracy results obtained are better than the LSTM or RNN models. However, ASR research using the Transformer model is still very limited. This paper will discuss the use of the Transformer model for ASR in Indonesian. The dataset used is the Indonesian language private speech dataset. The experimental results show that the Word Error Rate (WER) and Character Error Rate (CER) produced by the proposed model using the Indonesian language primary dataset are almost the same as using the English language public dataset where the resulting WER and CER are 27.34 and 7.96 for Indonesian and 25.28 and 6.02 for English. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

ALPINE: An Interpretable Approach for Decoding Phenotypes from Multi-condition Sequencing Data

ALPINE: An Interpretable Approach for Decoding Phenotypes ...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Lee, Wei-Hao Li, Lechuan Dannenfelser, Ruth Yao, Vicky Systems Synthetic and Physical Biology Graduate Program Rice University Houston United States Department of Computer Science Rice University Houston United States Ken Kennedy Institute Rice University Houston United States Rice Synthetic Biology Institute Rice University Houston United States

ISBN: (纸本)9783031902512

Advancements in sequencing technology have expanded data availability, capturing diverse phenotypic traits and biological perturbations. However, increased resolution also raises complexity, as studies now examine multiple dimensions, including donor phenotypes, anatomical regions, cell types, and time points. Integrating datasets across studies promises insights into health and disease beyond the scope of individual experiments, but this requires methods that can separate technical artifacts from meaningful biological signals while providing interpretable insights into condition-related genetic factors. Existing approaches tend to focus on either integration or interpretability, rarely addressing both simultaneously. To overcome these challenges, we introduce ALPINE, a joint supervised-unsupervised non-negative matrix factorization framework that disentangles technical and biological variation while directly identifying condition-associated genes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Matrix factorization

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：