检索结果-内蒙古大学图书馆

7th International Conference on Computer Science and Computational Intelligence, CSCI 2022

作者： Gunawan, Kevin William Hidayat, Alam Ahmad Cenggoro, Tjeng Wawan Pardamean, Bens Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Accurately predicting an owl species based on its sound can be helpful for owl conservation. To build an accurate model for owl sound classification, deep learning is currently the most preferred algorithm, due to its excellent performance for modeling audio data. However, deep learning is generally underperformed for a small dataset, which is the case for recognizing scops owl sound. To overcome the issue, we proposed a transfer learning strategy, which is common for computer vision tasks, that can alleviate overfitting in a deep learning model for the owl sound classification. In our approach, we propose a neural network architecture consisting of the backbone of a EfficientNet model pre-Trained on the massive ImageNet database. The model takes the sound input that has been converted as two image representations: Spectrogram and Mel Frequency Cepstral Coefficients. Our strategy enables the use of a relatively small size of pre-Trained image classification model, which is widely available, for transfer learning in owl sound classification. Deploying the lightweight model in an automatic sound classifier provides a fast and accurate tool for various owl conservation purposes. © 2022 Elsevier B.V.. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

BERT-based Topic Modeling Approach for Malaria Research Publication 4

BERT-based Topic Modeling Approach for Malaria Research Publ...

引用

4th International Conference on Informatics, Multimedia, Cyber and Information System, ICIMCIS 2022

作者： Hidayat, Alam Ahmad Nirwantono, Rudi Budiarto, Arif Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665473279

Malaria is a communicable disease with half of the global population at risk due to its high morbidity and mortality rates. A massive number of studies are dedicated to malaria research, so it plays a key role in formulating the proper prevention strategy and effective malaria treatment. With the overwhelming number of updated publications in the field, an unsupervised text mining approach such as topic modeling may provide an alternative method for the malaria researcher to keep pace with new insights. In this work, we collect metadata of malaria publications from the PubMed database to perform BERT-based topic modeling to find well-defined topics regarding malaria research. The method is largely based on the popular BERTopic pipeline. We compare the performance of three different language models to generate document embeddings from the data. The dimension reduction and the density-based clustering algorithm are used to cluster the embeddings. The topic representation is computed based on the semantic similarity of the class TF-IDF representation. The substance of the resulting topics is then manually annotated based on the top words of each topic. We demonstrate that by merging initial topics into larger topics using hierarchical clustering and manual content-based examination, the evaluated coherence measure can be further improved, thus enhancing the topic's interpretability. Our modeling result is able to extract ten major topics recurring in the malaria research publication published from 2017-2022. The result provides preliminary insight to understand the dynamics and patterns of malaria research over the years © 2022 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

South jakarta's air quality using PM 2.5 data at the beginning of COVID-19 Restriction 6

South jakarta's air quality using PM 2.5 data at the beginni...

引用

6th International Conference on Information Management and Technology, ICIMTech 2021

作者： Rahutomo, Reza Purwandari, Kartika Hidayat, Alam Ahmad Pardamean, Bens Bina Nusantara University School of Information Systems Information System Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665449373

As soon as the lockdown was established in Jakarta, Indonesia, people experienced a change in Jakarta's air quality. This research was conducted to answer several challenges such as: where to find Indonesia's air quality open data platforms, how to handle the acquired data with SQL technology, and how to validate whether the air quality of Jakarta was significantly changed from a period to another or not. With particulate matter 2.5 (PM 2.5) data acquired by The United States Diplomatic Post in South Jakarta, a data visualization was generated to describe the fluctuation of PM 2.5 from February 29th to June 29th. By conducting a two-sample t-test, a significant change in South Jakarta's air quality was revealed. The test concluded that South Jakarta's air quality got worse even after a lockdown was established. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Identifying Important Usernames in 'Biofarma' Conversation using Twitter Network Analysis 7

Identifying Important Usernames in 'Biofarma' Conversation u...

引用

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

作者： Rahutomo, Reza Jariyah, Ainun Trinugroho, Joko Pebrianto Pardamean, Bens School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia BINUS Graduate Program-Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (数字)9781665450904

ISBN: (纸本)9781665450904

This study analyzed interactions between Twitter users in conversations regarding Indonesia's state-owned vaccine manufacturer 'Biofarma' in 2021. The primary objective of this study is to identify Key Opinion Leaders (KOL) due to the need of authentic and trustworthy persona in social media. A technique called network centrality was employed in this research alongside four centrality measurements, namely degree of centrality, eigenvector centrality, betweenness centrality, and closeness centrality. Focused on using a reply network interaction dataset, the research discovered several important usernames with different roles that enlivened the conversation and have a potential for social media marketing optimization. © 2022 IEEE.

关键词： Marketing

来源：评论

学校读者我要写书评

暂无评论

Towards a Healthy AI Tradition: Lessons from Biology and Biomedical Science

arXiv

引用

arXiv 2024年

作者： Kasif, Simon Department of Biomedical Engineering Bioinformatics Graduate Program Department of Computer Science Boston University United States Department of Computer Science Tel Aviv University

AI is a magnificent field that directly and profoundly touches on numerous disciplines ranging from philosophy, computer science, engineering, mathematics, decision and data science and economics, to cognitive science, neuroscience and more. The number of applications and impact of AI is second to none and the potential of AI to broadly impact future science developments is particularly thrilling. While attempts to understand knowledge, reasoning, cognition and learning go back centuries, AI remains a relatively new field. In part due to the fact it has so many wide-ranging overlaps with other disparate fields it appears to have trouble developing a robust identity and culture. Here we suggest that contrasting the fast-moving AI culture to biological and biomedical sciences is both insightful and useful way to inaugurate a healthy tradition needed to envision and manage our ascent to AGI and beyond (independent of the AI Platforms used). After all, the human brain is a biological organ produced by evolution and human intelligence is a remarkable bi-product of nature and nurture and their complex interaction. In this perspective, we focus on traditions and culture, namely the commonly observed practices of evaluating, recognizing applauding, critiquing, debating and managing all progress including useful advances and discovery of challenging limitations. We are not discussing specific scientific exchanges between AI and Biology that include interdisciplinary cross fertilization of scientific methods, technology, ideas and applications that have been amply demonstrated and will continue to be transformative in the future. In a previous perspective, we suggested that biomedical laboratories or centers can usefully embrace logistic traditions in AI labs that will allow them to be highly collaborative, improve the reproducibility of research, reduce risk aversion and produce faster mentorship pathways for PhDs and fellows. This perspective focuses on the benefits of AI a

关键词： Biological organs

来源：评论

学校读者我要写书评

暂无评论

An Improved Version of Texture-based Foreground Segmentation: Block-based Adaptive Segmenter 3

An Improved Version of Texture-based Foreground Segmentation...

引用

3rd International Conference on Computer Science and Computational Intelligence, ICCSCI 2018

作者： Muchtar, Kahlil Rahman, Faris Cenggoro, Tjeng Wawan Budiarto, Arif Pardamean, Bens Nodeflux Inc. Jakarta Indonesia Syiah Kuala University Aceh Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia

Foreground segmentation is one of moving object detection techniques of computer vision applications. To date, modern moving object detection methods require complex background modeling and thresholds tuning to confront illumination changes. This paper proposes an adaptive approach based on non-overlapping block texture representation. It aims to design a computationally light and efficient solution to improve the robustness of detection. We evaluate our proposed method on internal and public sequences and provide the quantitative and qualitative measurements. Experimental results show that the proposed method can improve the results of previous method and suitable for real-time challenges. © 2018 The Authors. Published by Elsevier Ltd.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Simultaneous identification for synergistic transcription factors and their transcription factor binding sites

Simultaneous identification for synergistic transcription fa...

引用

5th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2011

作者： Tsai, Zing Tsung-Yeh Huang, Grace Tzu-Wei Tsai, Huai-Kuang Institute of Information Science Academia Sinica Taipei 115 Taiwan Bioinformatics Program Taiwan International Graduate Program Taiwan Institute of Biomedical Informatics National Yang-Ming University Taiwan Joint CMU-Pitt PhD Program in Computational Biology University of Pittsburgh Carnegie Mellon University Pittsburgh PA United States Research Center for Information Technology Innovation Taipei 115 Taiwan Computer Science and Engineering National Taiwan Ocean University Keelung 202 Taiwan

ISBN: (纸本)9780769543734

Identifying transcription factor binding sites (TFBSs) is crucial for understanding the mechanism of transcriptional regulation. It is known that transcription factors (TFs) often cooperate to regulate genes. While traditional approaches can be used to discover binding motifs of a group of co-regulated genes, they often fail to accurately assign motifs to the corresponding TFs. Here, we consider two TFs together to infer their TFBSs and their synergistic relationship simultaneously. The basic idea is that if two TFs interact, their TFBSs, if distinct, would be conserved across species and coincided in the promoter regions of the genes they co-regulated. Applying our method to Saccharomyces cerevisiae chromatin immunoprecipitation data, we predicted 110 TF pairs with statistically significant motif assignments. A majority of these TF pairs have literature support to be synergistic, and the designated motifs to TFs match well with their known consensus. We further examined the synergism of predicted TF pairs in seven experimental conditions using ANOVA, and identified significant interactions. © 2011 IEEE.

关键词： Yeast

来源：评论

学校读者我要写书评

暂无评论

The Technology behind Genomic Database 4

The Technology behind Genomic Database

引用

4th International Conference on Cybernetics and Intelligent System, ICORIS 2022

作者： Trinugroho, Joko Pebrianto Perbangsa, Anzaludin Samsinga Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665453950

In this digital era, we are exposed to a large amount of data. This includes biological data, which stores information about living organisms, including Deoxyribonucleic acid (DNA), genes, and proteins. With the development of information technology and information system, most of available biological data are stored in an online public database. Many of the databases are free-access and easily used, which helps the users, especially researchers, to make use of the data. Among the known public biological databases are the University of California Santa Cruz (UCSC) Genome Browser Database and the Rat Genome Database (RGD). These two databases provide access to the biological data from different organisms. This paper aims to describe the technology of public biological databases. Also elucidated in this paper are the differences features between UCSC Genome Browser Database and the RGD. Our results showed that the UCSC contains much more biological data and features than the RGD. However, the genome browser of UCSC has a complex display, while the RGD has a simple display. Overall, both databases give the users the option to choose the most suitable database for them. © 2022 IEEE.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Database Management System Design Improvement for Child Stunting Data Collection in Multiple Observation Areas 7

Database Management System Design Improvement for Child Stun...

引用

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

作者： Rahutomo, Reza Elwirehardja, Gregorius Natanael Dominic, Nicholas Caesario, Benedict Pardamean, Bens School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia BINUS Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (数字)9781665450904

ISBN: (纸本)9781665450904

The launch of StuntingDB is believed to enliven the role of database management systems (DBMS) in Indonesia's stunting research. However, a novelty in stunting data management that enables parallel project activation in multiple observation areas is necessary. Several improved functionalities in StuntingDB must be designed to prevent the high demand for accessibility in the middle of stunting research. Connolly and Begg's principle of database design is adopted along with Software Development Life Cycle's Waterfall model for creating a continuous development of the system. This research produces a new database design in the form of Entity Relationship Diagram (ERD) and Use Case Diagram to help system developers realizing a new version of StuntingDB for stunting research in several observation areas. © 2022 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

A Study of Classification Techniques Based on Spike Protein Sequences of MERS-CoV 23

A Study of Classification Techniques Based on Spike Protein ...

引用

Proceedings of the 2023 10th International Conference on Biomedical and bioinformatics Engineering

作者： Hayeon Kim Myeongji Cho Hyeon S. Son Laboratory of Computational Biology & Bioinformatics Graduate School of Public Health Seoul National University Republic of Korea and Institute of Health and Environment Seoul National University Republic of Korea Laboratory of Computational Biology & Bioinformatics Graduate School of Public Health Seoul National University Republic of Korea Laboratory of Computational Biology & Bioinformatics Graduate School of Public Health Seoul National University Republic of Korea Institute of Health and Environment Seoul National University Republic of Korea and Interdisciplinary Graduate Program in Bioinformatics College of Natural Science Seoul National University Republic of Korea

ISBN: (纸本)9798400708343

MERS-CoV, which belongs to the beta-coronaviruses together with SARS-CoV-2, although it has received relatively less attention by the COVID-19 pandemic, there is a sufficient possibility of new MERS-CoV lineages and variants. Previous studies have discussed the possibility of frequent recombination of MERS-CoV. We thus present a highly accurate method for the phylogenetic analysis and classification of MERS-CoV including recombinant sequences. We collected the sequences of S protein from MERS-CoV and divided them into five phylogenetic groups, of which recombinant sequences were divided into seven types. Physicochemical properties of amino acids were then calculated from the S protein sequences, and the results were used for the random forest model, Naïve Bayes classification, and k-nearest neighbor method. We also constructed several feature subsets based on the ranked amino acid properties and applied them to the random forest model. In each dataset, the amino acid physicochemical properties were ranked differently. Using this information, classification of MERS-CoV based on machine learning algorithms showed that the random forest model had the best accuracy and area under the curve compared with the k-nearest neighbor and Naïve Bayes classification methods. Several feature subsets were constructed using the correlation feature selection algorithm and applied to the random forest model. Overall, the performance of the classifier was improved compared to that when using all features. Coronaviruses including MERS-CoV continue to evolve into new forms through recombination or mutation. We thus present a method to increase the accuracy of their classification using additional information of the viral protein sequence, and confirm that a subunit consisting of optimal prominent features can improve the performance of the classifier by removing the unnecessary characteristic information.

关键词： MERS-CoV classification machine learning

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：