检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Bushuiev, Roman Bushuiev, Anton de Jonge, Niek F. Young, Adamo Kretschmer, Fleming Samusevich, Raman Heirman, Janne Wang, Fei Zhang, Luke Dührkop, Kai Ludwig, Marcus Haupt, Nils A. Kalia, Apurva Brungs, Corinna Schmid, Robin Greiner, Russell Wang, Bo Wishart, David S. Liu, Li-Ping Rousu, Juho Bittremieux, Wout Rost, Hannes Mak, Tytus D. Hassoun, Soha Huber, Florian van der Hooft, Justin J.J. Stravs, Michael A. Böcker, Sebastian Sivic, Josef Pluskal, Tomáš Institute of Organic Chemistry and Biochemistry The Czech Academy of Sciences Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Republic Bioinformatics Group Wageningen University & Research Netherlands Department of Computer Science University of Toronto Canada Bioinformatics Institute for Computer Science Friedrich Schiller University Jena Germany Department of Computer Science University of Antwerp Belgium Department of computing science University of Alberta Canada Alberta Machine Intelligence Institute Canada Department of Molecular Genetics University of Toronto Canada Bright Giant GmbH Department of Computer Science Tufts University United States Department of Biological Sciences University of Alberta Canada Department of Computer Science Aalto University Finland Mass Spectrometry Data Center National Institute of Standards and Technology United States Department of Chemical and Biological Engineering Tufts University United States Centre for Digitalisation and Digitality University of Applied Sciences Düsseldorf Germany Department of Biochemistry University of Johannesburg South Africa Eawag Swiss Federal Institute of Aquatic Science and Technology Switzerland

The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym - the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at https://***/pluskal-lab/MassSpecGym. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

P522 Characterization of linkage disequilibrium between DRB1*01 and DRB5

引用

Human Immunology 2023年 84卷 145-146页

作者： Norvell, B. Williams, J. Norvell, B. Williams, J. Liu, H. Iyer, L. Riley, E. Coggins, M. Deters, J. Mone, C. Research and Development Labcorp Burlington North Carolina United States Data Science Artificial Intelligence and Bioinformatics Labcorp Westborough Massachusetts United States Consumer Genetics Labcorp Burlington North Carolina United States

来源：评论

学校读者我要写书评

暂无评论

Implementation of expert systems in potassium deficiency in cocoa plants using forward chaining method 7

Implementation of expert systems in potassium deficiency in ...

引用

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

作者： Hafizal, Muhammad Titan Putra, Dian Pratama Wirianata, Herry Nugraha, Nanda Satya Suparyanto, Teddy Hidayat, Alam Ahmad Pardamean, Bens Faculty of Agriculture STIPER Institute of Agriculture Yogyakarta55282 Indonesia Faculty of Forestry STIPER Institute of Agriculture Yogyakarta55282 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

As one of the largest exporters in the world, cocoa (Theobroma cacao L.) production in Indonesia provides an important contribution to the plantation sector that can, directly and indirectly, attribute to the national economic development. However, recent data shows a decline in cocoa productivity in Indonesia. This is arguably caused by various factors, including poor agricultural management and practices in cocoa plantations, that may lead to lower fertility in the soil and an increased risk of diseases and pests. Potassium deficiency is a major contributing factor to the low soil fertility that affects cocoa yields. Therefore, in this work, we implement an application with an expert system utilizing the forward chaining method to detect potassium deficiency in cocoa plants and then give a fertilization-based recommendation based on the plants' condition. The system employs a set of rules to identify symptoms related to the deficiency on the sample photo of a cocoa leaf according to the channels of red, green, and blue of the image. The sample images of cocoa leaves are submitted to the application with an easy-To-use interface that can show the scanning result and proceed to display the suggested quantity of fertilizers to prevent potassium deficiency. Implementing the system can contribute constructive impacts to improve current practices in the overall cropping system of cocoa plants. © 2022 Elsevier B.V.. All rights reserved.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

Large-scale moral machine experiment on large language models

arXiv

引用

arXiv 2024年

作者： Ahmad, Muhammad Shahrul Zaim bin Takemoto, Kazuhiro Department of Bioscience and Bioinformatics Kyushu Institute of Technology Fukuoka Iizuka Japan Faculty of Engineering and Technology Multimedia University Melaka Malaysia Data Science and AI Research Center Kyushu Institute of Technology Fukuoka Iizuka Japan

The rapid advancement of Large Language Models (LLMs) and their potential integration into autonomous driving systems necessitates understanding their moral decision-making capabilities. While our previous study examined four prominent LLMs using the Moral Machine experimental framework, the dynamic landscape of LLM development demands a more comprehensive analysis. Here, we evaluate moral judgments across 52 different LLMs, including multiple versions of proprietary models (GPT, Claude, Gemini) and open-source alternatives (Llama, Gemma), to assess their alignment with human moral preferences in autonomous driving scenarios. Using a conjoint analysis framework, we evaluated how closely LLM responses aligned with human preferences in ethical dilemmas and examined the effects of model size, updates, and architecture. Results showed that proprietary models and open-source models exceeding 10 billion parameters demonstrated relatively close alignment with human judgments, with a significant negative correlation between model size and distance from human judgments in open-source models. However, model updates did not consistently improve alignment with human preferences, and many LLMs showed excessive emphasis on specific ethical principles. These findings suggest that while increasing model size may naturally lead to more human-like moral judgments, practical implementation in autonomous driving systems requires careful consideration of the trade-off between judgment quality and computational efficiency. Our comprehensive analysis provides crucial insights for the ethical design of autonomous systems and highlights the importance of considering cultural contexts in AI moral decision-making. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLM2Vec Sentence Embeddings Analysis in Sentiment Classification

LLM2Vec Sentence Embeddings Analysis in Sentiment Classifica...

引用

International Conference on data and Software Engineering (ICODSE)

作者： Matthew Martianus Henry Nur Adhianti Hervanto Mahmud Isnan Dian Kurnianingrum Chyntia Ika Ratnapuri Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Entrepreneurship Department Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506407

ISBN: (纸本)9798331506414

Sentiment analysis is crucial method in business intelligence to extract insights, which typically begin with sentiment classification. One of the latest frameworks for generating sentence embeddings for sentiment classification is LLM2Vec, which allows Transformer decoder-based models to generate sentence embeddings for text representation. Its capability is deemed language-agnostic, which, in this study, the framework is leveraged for Tokopedia tweet sentiment analysis to prove the claim. The base decoder models used in the LLM2Vec framework were Llama 3 8B, Llama 2 7B, Sheared Llama 1.3B, and Mistral 7B. Two BERT-based models, which are the Indonesian SBERT model and IndoBERT trained with the SimCSE approach, were employed as a comparison. The generated embeddings were classified using logistic regression, SVM, and MLP Classifier. Classifiers using embedding generated by LLM2Vec with Llama 3 8B and Mistral 7B achieves on-par performance with classifiers that utilize IndoBERT SimCSE embeddings, while classifiers using embeddings generated by LLM2Vec with Llama 2 7B and Sheared Llama 1.3B achieves much lower performance. Classifiers with Indonesian SBERT embeddings achieve the highest F1 score performance. Despite slightly lower performance, this study has proven the language-agnostic capability of LLM2Vec, especially with Llama 3 8B and Mistral 7B in colloquial Bahasa Indonesia sentiment analysis, since none of the base decoders were ever trained using the Bahasa Indonesia corpus.

关键词： Support vector machines Sentiment analysis Logistic regression Social networking (online) Blogs Transformers Encoding Decoding Business intelligence Software engineering

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in IBD: How Will It Change Patient Management?

引用

Current Treatment Options in Gastroenterology 2023年第4期21卷 365-377页

作者： Stone, Molly L. Stidham, Ryan W. Division of Gastroenterology Department of Internal Medicine Michigan Medicine Ann Arbor USA Department of Computational Medicine and Bioinformatics University of Michigan Ann Arbor USA Michigan Institute for Data Science (MIDAS) University of Michigan Ann Arbor USA

Artificial intelligence (AI) is quickly evolving and will be integral to the management of IBD patients. In this review, we provide an overview of technologies powering applications for Crohn’s disease and ulcerative colitis, with particular attention to information extraction from imaging and text records. Recent data highlight machine learning capability to replicate expert interpretation and judgment at population scale with accuracy in endoscopic and histology disease grading. Computer vision techniques are also detecting important findings difficult for even expert clinicians to reliably appreciate, including dysplasia on colonoscopy and fibrosis on CT and MRI imaging. Further, segmentation and radiomics can extract more information than manually possible, enabling new possibilities for disease measurement. Finally, natural language processing (NLP) is showing promise automatically extracting IBD-related medical concepts from text and generating conversational responses for both clinicians and patients. Quickly mounting evidence supports AI reliability grading disease severity in endoscopy, histology, and imaging. In particular use cases, AI can surpass the ability of humans for disease feature detecting and the generation of new measures of IBD activity. Ultimately, AI-powered information extraction will provide significant incremental improvement in the personalization predictions of outcomes and treatment course in IBD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

data mining for epidemiology: The correlation of typhoid fever occurrence and environmental factors

引用

Procedia Computer science 2023年 216卷 284-292页

作者： Faisal Asadi Joko Pebrianto Trinugroho Alam Ahmad Hidayat Reza Rahutomo Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Information System Department School of Information System Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

Typhoid fever is an endemic disease that burdens Indonesia and has a potentially fatal infection multisystem. Salmonella typhi bacterium is responsible for typhoid fever disease. Poor sanitation, crowding, and slums are the main factors of increasing typhoid fever incidences. Environmental factors directly connected to meteorological factors are the main factor in breeding the Salmonella typhi bacterium. This study aims to identify the correlation between meteorological parameters and typhoid fever disease occurrence. The study was carried out in Jakarta, Indonesia, and the Bureau of Meteorological, Climatology, and Geophysics (BMKG) provided the meteorological parameter data. In addition, the Jakarta health surveillance office provided information on typhoid fever hospitalizations from 2019 to 2021. Pearson's concept was utilized d to investigate the correlation between typhoid fever incidences and the meteorological parameters. Humidity, precipitation, and wind speed are the meteorological parameters that significantly affect in contribute to the occurrence of typhoid fever disease. These findings might be used as a reference for Indonesia's government in making public policy to prevent typhoid fever in Indonesia.

关键词： typhoid fever salmonella typhi endemic disease meteorological factors

来源：评论

学校读者我要写书评

暂无评论

Identify Non-mutational p53 Functional Deficiency in Human Cancers

引用

Genomics, Proteomics & bioinformatics 2024年第5期22卷 85-98页

作者： Qianpeng Li Yang Zhang Sicheng Luo Zhang Zhang Ann L.Oberg David E.Kozono Hua Lu Jann N.Sarkaria Lina Ma Liguo Wang National Genomics Data Center China National Center for BioinformationBeijing 100101China Beijing Institute of Genomics Chinese Academy of SciencesBeijing 100101China University of Chinese Academy of Sciences Beijing 100049China Division of Computational Biology Mayo Clinic College of Medicine and ScienceRochesterMN 55905USA Department of Radiation Oncology Dana-Farber Cancer Institute and Brigham and Women's HospitalBostonMA 02215USA Department of Biochemistry&Molecular Biology and Tulane Cancer Center Tulane University School of MedicineNew OrleansLA 70112USA Department of Radiation Oncology Mayo Clinic College of Medicine and ScienceRochesterMN 55905USA Department of Biochemistry and Molecular Biology Mayo Clinic College of Medicine and ScienceRochesterMN 55905USA Bioinformatics and Computational Biology Graduate Program University of Minnesota RochesterRochesterMN 55904USA

An accurate assessment of p53's functional statuses is critical for cancer genomic ***,there is a significant challenge in identifying tumors with non-mutational p53 inactivation which is not detectable through DNA *** undetected cases are often misclassified as p53-normal,leading to inaccurate prognosis and downstream association *** address this issue,we built the support vector machine(SVM)models to systematically reassess p53's functional statuses in TP53 wild-type(TP53^(WT))tumors from multiple The Cancer Genome Atlas(TCGA)***-validation demonstrated the good performance of the SVM models with a mean area under the receiver operating characteristic curve(AUROC)of 0.9822,precision of 0.9747,and recall of *** study revealed that a significant proportion(87%-99%)of TP53^(WT) tumors actually had compromised p53 *** analyses uncovered that these genetically intact but functionally impaired(termed as predictively reduced function of p53 or TP53^(WT)-pRF)tumors exhibited genomic and pathophysiologic features akin to TP53-mutant tumors:heightened genomic instability and elevated levels of ***,patients with TP53^(WT)-pRF tumors experienced significantly shortened overall survival or progression-free survival compared to those with predictively normal function of p53(TP53^(WT)-pN)tumors,and these patients also displayed increased sensitivity to platinum-based chemotherapy and radiation therapy.

关键词： Cancer Composite expression DNA mutation Machine learning p53 deficiency

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

引用

Procedia Computer science 2023年 227卷 524-533页

作者： Dedy Ariansyah Mahmud Isnan Reza Rahutomo Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 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.

关键词： Digital Twin Smart City Mixed Reality Augmented Reality

来源：评论

学校读者我要写书评

暂无评论

Federated PCA and Estimation for Spiked Covariance Matrices: Optimal Rates and Efficient Algorithm

arXiv

引用

arXiv 2024年

作者： Li, Jingyang Cai, T. Tony Xia, Dong Zhang, Anru R. Department of Statistics Department of Mathematics University of Michigan Ann Arbor United States Department of Statistics and Data Science University of Pennsylvania United States Department of Mathematics Hong Kong University of Science and Technology Hong Kong Department of Biostatistics & Bioinformatics Department of Computer Science Duke University United States

Federated Learning (FL) has gained significant recent attention in machine learning for its enhanced privacy and data security, making it indispensable in fields such as healthcare, finance, and personalized services. This paper investigates federated PCA and estimation for spiked covariance matrices under distributed differential privacy constraints. We establish minimax rates of convergence, with a key finding that the central server’s optimal rate is the harmonic mean of the local clients’ minimax rates. This guarantees consistent estimation at the central server as long as at least one local client provides consistent results. Notably, consistency is maintained even if some local estimators are inconsistent, provided there are enough clients. These findings highlight the robustness and scalability of FL for reliable statistical inference under privacy constraints. To establish minimax lower bounds, we derive a matrix version of van Trees’ inequality, which is of independent interest. Furthermore, we propose an efficient algorithm that preserves differential privacy while achieving near-optimal rates at the central server, up to a logarithmic factor. We address significant technical challenges in analyzing this algorithm, which involves a three-layer spectral decomposition. Numerical performance of the proposed algorithm is investigated using both simulated and real data. © 2024, CC BY.

关键词： Federated 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：