检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zihan Zhu Ethan X. Fang Zhuoran Yang Department of Statistical Science Duke University Department of Biostatistics and Bioinformatics Duke University Department of Statistics and Data Science Yale University

We study multi-agent games within the innovative framework of decision-dependent games, which establishes a feedback mechanism that population data reacts to agents' actions and further characterizes the strategic interactions among agents. We focus on finding the Nash equilibrium of decision-dependent games in the bandit feedback setting. However, since agents are strategically coupled, classical gradient-based methods are infeasible without the gradient oracle. To overcome this challenge, we model the strategic interactions by a general parametric model and propose a novel online algorithm, Online Performative Gradient Descent (OPGD), which leverages the ideas of online stochastic approximation and projected gradient descent to learn the Nash equilibrium in the context of function approximation for the unknown gradient. In particular, under mild assumptions on the function classes defined in the parametric model, we prove that the OPGD algorithm finds the Nash equilibrium efficiently for strongly monotone decision-dependent games. Synthetic numerical experiments validate our theory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring EfficientNet Variants for Image Encoding in Auxiliary Signal Guided Knowledge Encoder-Decoder Framework

引用

Procedia Computer science 2024年 245卷 391-398页

作者： Matthew Martianus Henry Nur Adhianti Heryanto Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

The growing number of medical images has led to radiologist burnout, which seriously impacts the radiologist's performance. To address the previously mentioned issue, an Auxiliary Signal Guided Knowledge (ASGK) multimodal encoder-decoder framework was designed to automatically generate the medical report based on the proposed medical graph and natural language decoder. It utilizes DenseNet-121 as the image encoder. With DenseNet-121 lack of computational and memory efficiency, this study aims to explore the potential of EfficientNetB0 to EfficientNetB4 as an ASGK image encoder substitute. The framework is trained with IU X-Ray dataset for 30 epochs, with Adam optimizer, a learning rate of 0.01 with 0.8 decay rate, binary cross entropy loss for the medical tags, and cross-entropy loss for the generated medical captions. During the framework training process with each image encoder, the parameter that achieves the highest CIDEr score on the validation set is considered the best image encoder parameter and will be used on the test set. On the test set, EfficientNetB3 as an ASGK image encoder has been shown to increase the CIDEr score to 0.35, a significant increase from the 0.28 CIDEr score obtained by the ASGK using DenseNet-121. This score is only a 1% decrease from the best validation score. It suggests that not only EfficientNetB3 increases the framework's performance, it is also less prone to overfitting. This study has demonstrated that EfficientNetB3 is a potential image encoder substitute for DenseNet-121 in the ASGK framework.

关键词： Automated medical report generation DenseNet-121 EfficientNet Encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Semi-automated meningioma segmentation with bounding boxes

引用

Procedia Computer science 2024年 245卷 583-590页

作者： Nur Adhianti Heryanto Mahmud Isnan Matthew Martianus Henry Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Segmentation is manually performed by physicians, which takes considerable time and may be subject to observers. Automating this task can increase efficiency and consistency. Existing studies on meningioma segmentation used data from limited study centers, indicating the need for research on multi-center data to assess generalizability. In this work, two semi-automated methods with bounding box priors, LiteMedSAM and BBU-Net, are evaluated on the brain tumor segmentation (BraTS) 2023 meningioma dataset collected from five study-centers. Preprocessing included exclusion of small tumors, z-score normalization, and extraction of slices that contain tumors, generating 25,602 2D axial magnetic resonance imaging (MRI) scans. A fine-tuning strategy is adopted for LiteMedSAM while BBU-Net is trained from scratch. The models are evaluated using a five-fold cross-validation, with data split at the case level. Results show that while U-Net models can achieve performance close to LiteMedSAM, the foundation model has overall better performance, with more than 90% in all evaluation scores.

关键词： Bounding boxes Meningioma Semi-automated segmentation

来源：评论

学校读者我要写书评

暂无评论

data Mining and bioinformatics Approaches to Elucidate Bacterial Communities in the Extreme Environment

Data Mining and Bioinformatics Approaches to Elucidate Bacte...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Joko Pebrianto Trinugroho Alam Ahmad Hidayat Rudi Nirwantono Faisal Asadi Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Mathematics Department School of Computer Science Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Biotechnology Department Faculty of Engineering Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science 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

Bacteria are microscopic organisms that can be found in many environments. They are abundant and have many roles in our life. Studying bacteria is essential so that we can identify the bacteria that are needed for many industrial applications. However, the main problem is that majority of the bacteria are unculturable, hampering the exploration of bacteria from different environments. Metagenomics approach which employs Next Generation Sequencing technology could help study bacteria by utilizing 16S rRNA marker gene. This study aims to demonstrate data mining and bioinformatics approaches to analyze 16S rRNA sequencing data. The raw sequencing data of 16S rRNA was collected from biological database. Then, the data were trimmed, denoised, and clustered to generate Amplicon Sequence Variants (ASVs). Diversity (alpha and beta) and taxonomic analyses were then conducted to elucidate the bacterial diversity and taxonomic profile of ASVs. The results of this work showed that Shannon and PD indices in China's hot spring were higher than Singapore and the USA. Furthermore, a significant difference was observed in the PD index. The unweighted UniFrac distance also showed there was a significant difference of the bacterial communities between the three locations. In addition, the taxonomic investigation unveiled prevalent bacterial groups in the ecosystem, namely Proteobacteria, Chloroflexi, Cyanobacteria, and Crenarchaeota. The research outcomes have the potential to serve as a foundational resource for subsequent bacterial metagenomic research, particularly the hot spring environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LDA Topic Modeling for bioinformatics Terms in arXiv Documents

引用

Procedia Computer science 2024年 245卷 229-238页

作者： Andrea Stevens Karnyoto Matthew Martianus Henry Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

A wide variety of disciplines contribute to bioinformatics research, including computer science, biology, chemistry, mathematics, and physics. This study determines the number of research articles published on arXiv classified as bioinformatics topics and the most frequently used bioinformatics terms using topic modeling, Latent Dirichlet Allocation (LDA). An algorithm based on LDA is used to discover topics hidden within large collections of documents through the use of statistical analysis. Our research examined 226453 articles on arXiv between January 2023 and January 2024. As a result, there are more than 10521 articles categorized into bioinformatics topics. Most commonly, 6352 documents are in the "Mathematical Physics" category. The second most popular category is "Computer science," with 2950 documents. Accordingly, the terms 'RNA,' 'sequence,' 'tree,' and 'homology' are the three most commonly used terms in bioinformatics. The study of RNA plays a vital role in molecular biology; thus, the study of RNA is prevalent in bioinformatics. Sequential data refer to the order in which nucleotides or amino acids can be found in a DNA molecule or a protein.

关键词： arXiv bioinformatics Latent Dirichlet Allocation

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Coffee Bean Binary Classification Through Deep Learning Techniques 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Islamy, Fajrul Muchtar, Kahlil Arnia, Fitri Dawood, Rahmad Febriana, Alifya Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department Master of Computer Science Program BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Coffee beans are one of the high-value commodities in Indonesia, but the sorting method for the quality of coffee beans still uses visual methods and sieves with mechanical machines. This study aims to provide an alternative to classifying coffee beans using Deep Learning algorithms, such as the ResNet-18 and MobileNetV2. The dataset used is USK-COFFEE which consists of two classes, the normal coffee bean class, and the defect coffee bean class. The models were trained using the balanced and imbalanced datasets, meaning that two scenarios were performed. From the results of this study, the accuracy value for the ResNet-18 model was 91.50% when trained on the balanced dataset and 90.87% on the imbalanced dataset. It outperformed the MobileNetV2 architecture, which only achieved 0.8125 and 0.8112 accuracy scores when trained on the balanced and imbalanced datasets, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Digital Twin (DT) Smart City for Air Quality Management 8

Digital Twin (DT) Smart City for Air Quality Management

引用

8th International Conference on Computer science and Computational Intelligence, ICCSCI 2023

作者： Ariansyah, Dedy Isnan, Mahmud Rahutomo, Reza Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

Air pollution is a pressing issue in cities, and managing air quality poses a challenge for urban designers and decision-makers. This study proposes a Digital Twin (DT) Smart City integrated with Mixed Reality technology to enhance visualization and collaboration for addressing urban air pollution. The research adopts an applied research approach, with a focus on developing a DT framework. A use case of DT development for Jakarta, the capital of Indonesia, is presented. By integrating air quality data, meteorological information, traffic patterns, and urban infrastructure data, the DT provides a comprehensive understanding of air pollution dynamics. The visualization capabilities of the DT, utilizing Mixed Reality technology, facilitate effective decision-making and the identification of strategies for managing air quality. However, further research is needed to address data management challenges to build a DT for Smart City at scale. © 2023 The Authors. Published by Elsevier B.V.

关键词： Augmented Reality Digital Twin Mixed Reality Smart City

来源：评论

学校读者我要写书评

暂无评论

Yale at "Discharge Me!": Evaluating Constrained Generation of Discharge Summaries with Unstructured and Structured Information 23

Yale at "Discharge Me!": Evaluating Constrained Generation o...

引用

23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024

作者： Socrates, Vimig Huang, Thomas Ai, Xuguang Fereydooni, Soraya Chen, Qingyu Taylor, R. Andrew Chartash, David Department of Biomedical Informatics and Data Science Yale University School of Medicine United States Department of Emergency Medicine Yale School of Medicine United States Program of Computational Biology and Bioinformatics Yale University United States School of Medicine University College Dublin National University of Ireland Dublin Ireland

ISBN: (纸本)9798891761308

In this work, we propose our top-ranking (2nd place) pipeline for the generation of discharge summary subsections as a part of the BioNLP 2024 Shared Task 2: "Discharge Me!". We evaluate both encoder-decoder and state-of-the-art decoder-only language models on the generation of two key sections of the discharge summary. To evaluate the ability of NLP methods to further alleviate the documentation burden on physicians, we also design a novel pipeline to generate the brief hospital course directly from structured information found in the EHR. Finally, we evaluate a constrained beam search approach to inject external knowledge about relevant patient problems into the text generation process. We find that a BioBART model fine-tuned on a larger fraction of the data without constrained beam search outperforms all other models.. ©2024 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Comparison of K-Nearest Neighbor and Support Vector Regression for Predicting Oil Palm Yield 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Pardamean, Bens Suparyanto, Teddy Sinaga, Gokma Sahat Tua Elwirehardja, Gregorius Natanael Firmansyah, Erick Ginting, Candra Mawandha, Hangger Gahara Putra, Dian Pratama Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program—Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Faculty of Agriculture Institute of Agriculture STIPER Yogyakarta55282 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

With the high demand for oil palm production, implementations of Machine Learning (ML) technologies to provide accurate predictions and recommendations to assist oil palm plantation management tasks have become beneficial, such as in predicting annual oil palm. However, different geographical and meteorological conditions may result in different scales of influence for each variable. In this research, K-Nearest Neighbors (KNN) and Support Vector Regression (SVR) were used in predicting oil palm yield based on data collected in Riau, Indonesia. Pearson’s correlation coefficient was also calculated in selecting the input features for the models, whereas normalization and standardization were used in scaling the data. By setting the minimum absolute correlation threshold to 0.1 and using standardization, both models managed to obtain more than 0.81 R2, with SVR obtaining the overall best performance with 0.8709 R2, 1.372 MAE, and 1.8025 RMSE without hyperparameter fine-tuning. It was also discovered that the oil palm yield in the previous year is the variable with the most influence in estimating oil palm yield in the current year, followed by the number of plants and soil types. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Literature study of stunting supplementation in Indonesian utilizing text mining approach 7

Literature study of stunting supplementation in Indonesian u...

引用

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

作者： Sudigyo, Digdo Hidayat, Alam Ahmad Nirwantono, Rudi Rahutomo, Reza Trinugroho, Joko Pebrianto Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

Numerous research on stunting supplementation interventions in Indonesia have been published. The information can be extracted through data mining, especially from academic research databases. In this paper, we presented a text mining-based literature review strategy to create a pipeline that researchers can use to accelerate the development of stunting supplementation intervention research in Indonesia. Utilizing various NLP (Natural Language Processing) techniques, data were crawled, processed, and visualized using Python. The crawling dataset used a module from the Pubmed API (Application Programming Interface) to collect literature papers. The NLTK (Natural Language Toolkit) module and itertools were used to process text data. The n-grams model was applied to process tokens into bigrams and trigrams. Text information was visualized using Matplotlib and Word cloud packages. There is an increasing number of publication in stunting supplementation intervention according to our result, which was observed from 2015 to 2021. West Java was the province where most of the stunting research has been conducted, as determined by research abstracts. Top occurrences obtained from the bigram and trigrams models calculation produced different terms. The word pairings that occurred the most frequently in the bigram and trigram model analyses were "child-aged" and "iron-folic-acid," respectively. The findings of this study are expected to help researchers to obtain the latest research topics related to stunting supplementation interventions in Indonesia. © 2022 Elsevier B.V.. All rights reserved.

关键词： data mining

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：