检索结果-内蒙古大学图书馆

Semi-automated meningioma segmentation with bounding boxes

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

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

Implementation of Computer Vision of Jakarta Weather Image Categorization Using ResNet 8

Implementation of Computer Vision of Jakarta Weather Image C...

引用

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

作者： Purwandari, Kartika Sigalingging, Join W.C. Hidayat, Alam Ahmad Cenggoro, Tjeng Wawan Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Database Center Division of BMKG Meteorological Climatological and Geophysical Agency Jakarta10720 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

At the moment, weather data is crucial for supporting neighborhood activities. The economy and trade are both centered in Jakarta, which is also Indonesia's capital. Therefore, it is crucial to have access to weather information so that these activities don't get disrupted, which would then hinder commercial and trade activity. Social media has been a very popular tool for spreading information recently. Particularly on Instagram, where users favor taking images and sharing the information they encounter. @jktinfo is the Instagram account that posts information about the situation in Jakarta and the area, including the current weather. The @jktinfo account is utilized in this project to gather data. Utilizing a variety of techniques, the collected photographs of sunny, cloudy, and wet situations were. © 2023 The Authors. Published by Elsevier B.V.

关键词： computer vision data augmentation deep transfer learning residual network weather image categorization

来源：评论

学校读者我要写书评

暂无评论

Maintaining the Quality and Aroma of Coffee with Fuzzy Logic Coffee Roasting Machine 3

Maintaining the Quality and Aroma of Coffee with Fuzzy Logic...

引用

3rd International Conference on Eco Engineering Development, ICEED 2019

作者： Harsawardana Samodro, Bayu Mahesworo, Bharuno Suparyanto, Teddy Surya Atmaja, Don Bosco Pardamean, Bens Institut Pertanian STIPER Yogyakarta55281 Indonesia Mechatronics and AI Research and Development Center Biotechnic Innovation Yogyakarta55281 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

With the increasing global demands of coffee, Indonesia need to increase their coffee beans supply and improve the quality to maintain its position in the international coffee industry. One of the most important coffeepre-processing, coffee bean roasting, is under developed in Indonesia. Indonesia coffee farmers prefer to use the traditional cauldron to roast their coffee beans. Roasting coffee beans using traditional cauldron is inefficient and resulting unequal roasted level for the coffee beans. In this study, we proposed atemperature control system based on fuzzy logic for coffee roaster machine. The system controls the temperature in accordance with the demanded roasting level. A thermal camera is attached inside the roasting chamber to monitor the heaton the roasted coffee beans. The thermal camera is integrated with a stirring mechanism to equalise the heat among the beans. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

NFT Appraisal Using Machine Learning 23

NFT Appraisal Using Machine Learning

引用

5th Asia Pacific Information Technology Conference, APIT 2023

作者： Dawod, Ahmed Dawod Mohammed Munkhdalai, Lkhagvadorj Park, Kwang Ho Ryu, Keun Ho Pham, Van Huy Database and Bioinformatics Laboratory College of Electrical and Computer Engineering Chungbuk National University Cheongju28644 Korea Republic of Data Science Laboratory Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City700000 Viet Nam

ISBN: (纸本)9781450399500

Non-Fungible Tokens (NFTs) are digital assets based on a blockchain and those are characterized as unique cryptographic tokens and non-interchangeable. To date, research into the NFT marketplace has been relatively limited. As it is an emerging platform with many unique elements, The NFT market has been impacted due to recent fluctuations in crypto-asset markets more broadly. This current bear market cycle has shed light on concerns around the value of NFTs, profit-based motivation, and environmental sustainability. However, periods of volatility and cyclicality are to be expected with any nascent technology as it develops a product-market fit. consequently, the appraisal of real-price for NFT collections is essential for individual financial security and investment making. In this study, we evaluate the machine learning algorithms to appraise their real-price based on NFT item's characteristics, market event information, and their rarity score data acquired by retrieved from the biggest marketplace OpenSea. Furthermore, the procedures were applied to meet the objectives of this study we built prediction models based on various machine-learning algorithms ranging from Random Forest, XGBoost, SVM, Lasso, ElasticNet, Ridge, Linear Polynomial Regression, TabNet, CatBoost, and LightGBM models. From the results, LightGBM regression model outperformed the other by RMSE around 0.905. The best R2 is only found in this model, which has a value of 0.917. © 2023 ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Short-term Weather Forecasting for Wind Energy Generation using A Deep Learning Technique 5

Short-term Weather Forecasting for Wind Energy Generation us...

引用

5th IEEE International Conference on Smart Systems and Technologies, SST 2022

作者： Zim, Abid Hasan Zeyad, Mohammad Ahmed, S.M. Masum Hossain, Eftakhar Energy and Technology Research Division Advanced Bioinformatics Computational Biology and Data Science Laboratory Bangladesh ABCD Laboratory Bangladesh Chattogram Bangladesh Heriot-Watt University Edinburgh United Kingdom University of Antwerp Faculty of Applied Engineering - Construction Antwerp Belgium

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

Inadequate or erroneous weather predictions have a great impact on wind turbine energy output. Certain weather fluctuations and interruptions affect the efficient operation of wind turbines. Short-term weather predictions that are calibrated and verified make it simple to reduce the threat presented by meteorological uncertainty. Conventional physics-based techniques for forecasting are relatively weaker than data-driven approaches since wind turbine components usually have a multipart nonlinear relationship. Compared to physical methods, non-parametric alternatives like deep learning are thought to be more stable and lead to fewer mistakes in analyst predictions. This research presents the state-of-the-art Temporal Convolutional Network (TCN), one of the deep learning methods, which is introduced as a means of enhancing the precision of short-term forecasting of weather variables. TCN is an architecture that makes use of casual convolutions and dilations in order to be adaptable for sequential data with its temporality and huge receptive fields. Seven significant meteorological parameters from the NASA POWER dataset of Chouchala Sea Beach in Chittagong, Bangladesh, over a period of four months were used in this research. The accuracy was measured using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results obtained from the suggested TCN model demonstrate that the predicted outcome is pretty accurate and consistent. © 2022 IEEE.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

SARS-CoV-2: lessons in virus mutation prediction and pandemic preparedness

引用

Current Opinion in Immunology 2025年 95卷 102560-102560页

作者： Tang, Weiyi Kim, Jenna Lee, Raphael TC Maurer-Stroh, Sebastian Renia, Laurent Tay, Matthew Z A*STAR Infectious Diseases Labs (AIDL) Agency for Science Technology and Research (A*STAR) Singapore Bioinformatics Institute (BII) Agency for Science Technology and Research (A*STAR) Singapore GISAID Global Data Science Initiative (GISAID) Munich Germany National Public Health Laboratory Singapore Singapore Department of Biological Sciences National University of Singapore Singapore Singapore Human Potential Translational Research Programme Yong Loo Lin School of Medicine National University of Singapore Singapore Singapore Lee Kong Chian School of Medicine Nanyang Technological University Singapore School of Biological Sciences Nanyang Technological University Singapore Department of Biochemistry National University of Singapore Singapore

The COVID-19 pandemic has prompted an unprecedented global response. In particular, extraordinary efforts have been dedicated toward monitoring and predicting variant emergence due to its huge impact, particularly for vaccine escape. Broadly, we classify such methods into two categories: forward mutation prediction, where phenotypes are first observed and the responsible genotypes traced, and reverse mutation prediction, which starts with selected pathogen genetic profiles and characterizes their associated phenotypes. Reverse mutation prediction strategies have advantages in being able to sample a more complete evolutionary space since sequences that do not yet exist can be sampled. The rapid improvement in the maturity and scale of reverse mutation prediction strategies, such as deep mutational scanning, has led to significant amounts of data for machine learning, with concomitant improvement in the prediction results from computational tools. Such integrated prediction approaches are generalizable and offer significant opportunities for anticipating viral evolution and for pandemic preparedness. © 2025 The Author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Computational Approach for Elucidating a Nonstructural Protein Interaction in Dengue Virus 2 9th

An Exploratory Computational Approach for Elucidating a Nons...

引用

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

作者： Hidayat, Alam Ahmad Nirwantono, Rudi Pardamean, Bens Mathematics Department School of Computer Science Bina Nusantara University 11480 Indonesia Biotechnology Department Faculty of Engineering Bina Nusantara University 11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

As the dengue infection still impacts hundreds of millions of people globally, unprecedented efforts in dengue drug development have been more progressive in recent decades. Computational methods provide a fast, sustainable, and efficient screening of active compounds and newly created drug molecules, including those specifically targeting nonstructural proteins (NS) of dengue viruses. In this work, protein modeling for the NS proteins of DENV-2/16681 strain was performed using a template-based homology modeling for the NS3 protein and an Artificial Intelligence (AI)-based prediction via AlphaFold for the NS4B protein. Moreover, the protein-protein interaction between the two structures was predicted using the HADDOCK server, which employs information about active and passive residues of the interaction interface to guide the docking process. After the modeling and its respective refinement process, the predicted structures of NS3 and NS4B improved their steric clashing scoring from MolProbity assessment. The refined models were then docked, and the resulting docking pose was analyzed to extract the interacting residues based on the polar contacts within the interface of the two proteins. Our result presents a preliminary study to create a dataset related to in silico molecular interactions of the NS3-NS4B interaction of different DENV types. It is helpful for building a computational pipeline for elucidating protein-ligand problems in dengue drug screenings. © 2024 The Authors.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

Nonconvex Factorization and Manifold Formulations are Almost Equivalent in Low-rank Matrix Optimization

arXiv

引用

arXiv 2021年

作者： Luo, Yuetian Li, Xudong Zhang, Anru R. Data Science Institute University of Chicago United States School of Data Science Fudan University China Departments of Biostatistics & Bioinformatics Computer Science Electrical & Computer Engineering Mathematics and Statistical Science Duke University United States

In this paper, we consider the geometric landscape connection of the widely studied manifold and factorization formulations in low-rank positive semidefinite (PSD) and general matrix optimization. We establish a sandwich relation on the spectrum of Riemannian and Euclidean Hessians at first-order stationary points (FOSPs). As a result of that, we obtain an equivalence on the set of FOSPs, second-order stationary points (SOSPs), and strict saddles between the manifold and the factorization formulations. In addition, we show the sandwich relation can be used to transfer more quantitative geometric properties from one formulation to another. Similarities and differences in the landscape connection under the PSD case and the general case are discussed. To the best of our knowledge, this is the first geometric landscape connection between the manifold and the factorization formulations for handling rank constraints, and it provides a geometric explanation for the similar empirical performance of factorization and manifold approaches in low-rank matrix optimization observed in the literature. In the general low-rank matrix optimization, the landscape connection of two factorization formulations (unregularized and regularized ones) is also provided. By applying these geometric landscape connections, in particular, the sandwich relation, we are able to solve unanswered questions in literature and establish stronger results in the applications on geometric analysis of phase retrieval, well-conditioned low-rank matrix optimization, and the role of regularization in factorization arising from machine learning and signal processing. © 2021, CC BY-SA.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Chemical-Induced Disease Detection Using Invariance-based Pattern Learning Model 1

Chemical-Induced Disease Detection Using Invariance-based Pa...

引用

1st International Workshop on Digital Disease Detection using Social Media, DDDSM 2017, co-located with the 8th International Joint Conference on Natural Language Processing, IJCNLP 2017

作者： Warikoo, Neha Chang, Yung-Chun Hsu, Wen-Lian Institute of Biomedical Informatics National Yang-Ming University Taipei112 Taiwan Bioinformatics Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei115 Taiwan Institute of Information Science Academia Sinica Taipei115 Taiwan Graduate Institute of Data Science Taipei Medical University Taipei106 Taiwan

ISBN: (纸本)9781948087070

In this work, we introduce a novel feature engineering approach named "algebraic invariance" to identify discriminative patterns for learning relation pair features for the chemical-disease relation (CDR) task of BioCreative V. Our method exploits the existing structural similarity of the key concepts of relation descriptions from the CDR corpus to generate robust linguistic patterns for SVM tree kernel-based learning. Preprocessing of the training data classifies the entity pairs as either related or unrelated to build instance types for both inter-sentential and intra-sentential scenarios. An invariant function is proposed to process and optimally cluster similar patterns for both positive and negative instances. The learning model for CDR pairs is based on the SVM tree kernel approach, which generates feature trees and vectors and is modeled on suitable invariance based patterns, bringing brevity, precision and context to the identifier features. Results demonstrate that our method outperformed compared approaches, achieved a high recall rate of 85.08%, and averaged an F1-score of 54.34% without the use of any additional knowledge bases. © 2017 AFNLP

关键词： Forestry

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：