检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Peng Wang, Jianmin Li, Chunyan Wang, Zixu Liu, Yiping Sun, Siqi Lin, Jianxin Wei, Leyi Cai, Xibao Lai, Houtim Liu, Wei Wang, Longyue Liu, Yuansheng Zeng, Xiangxiang College of Information Science and Engineering Hunan University Changsha China The Interdisciplinary Graduate Program in Integrative Biotechnology Yonsei University Incheon21983 Korea Republic of School of Informatics Yunnan Normal University Kunming650500 China Department of Computer Science University of Tsukuba Tsukuba3058577 Japan Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China Shanghai AI Laboratory Shanghai200232 China Centre for Artificial Intelligence driven Drug Discovery Faculty of Applied Science Macao Polytechnic University China School of Informatics Xiamen University Xiamen China Tencent AI Lab China

While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the descriptions through various text prompts. We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements across two-, three-, and four-constraint tasks, with an average molecular validity of over 99% and success ratio of 82.58%, 68.03%, and 67.48%, respectively. The model also exhibits adaptability through zero-shot testing, creating molecules that satisfy combinations of properties that have not been encountered. It can comprehend text inputs with various language styles, extending beyond the confines of outlined prompts, as confirmed through empirical validation. Additionally, the knowledge distillation feature of TSMMG contributes to the continuous enhancement of small models, while the innovative approach to dataset construction effectively addresses the issues of data scarcity and quality, which positions TSMMG as a promising tool in the domains of drug discovery and materials science. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Improved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction

引用

Journal of Open Innovation: Technology, Market, and Complexity 2025年第1期11卷

作者： Wahyuddin, Eko Putra Caraka, Rezzy Eko Kurniawan, Robert Caesarendra, Wahyu Gio, Prana Ugiana Pardamean, Bens Department of Statistical Computing Politeknik Statistika STIS Jakarta 13330 Indonesia Statistics Indonesia (BPS) Jl. Dr Sutomo 6-8 Jakarta Indonesia School of Economics and Business Telkom University Bandung 40257 Indonesia Research Center for Data and Information Sciences Research Organization for Electronics and Informatics National Research and Innovation Agency (BRIN) Bandung 40135 Indonesia Faculty of Integrated Technologies Universiti Brunei Darussalam Gadong BE1410 Brunei Darussalam Department of Mathematics Universitas Sumatera Utara Medan 20155 Indonesia Bioinformatics and Data Science Research Centre Bina Nusantara University DKI Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University DKI Jakarta 11480 Indonesia

This study aims to address the common issue of biased estimation errors in time series modeling by analyzing the error in locating ideal hyperparameters and defining appropriate validation methods. Specifically, it focuses on predicting the stock price of Bank Rakyat Indonesia using a combination of historical stock prices, technical indicators, exchange rates, and news sentiment data, while determining the optimal variables for deep learning models. Employing a deep learning-based Long-Short Term Memory (LSTM) model, the study optimizes hyperparameters alongside walk-forward validation for time series prediction. It explores different combinations of variables and adapts the sliding window approach to the context of the data. The results highlight the importance of optimizing hyperparameters and utilizing walk-forward validation for accurate time series prediction. The model incorporating historical stock prices and sentiment scores outperforms others, achieving an RMSE of 96.61 and MAE of 86.97. Incorporating sentiment scores reduces RMSE by 39.55 % compared to models using only historical stock prices, while adding technical indicators does not yield improvement. This study contributes to the field by addressing the issue of biased estimation errors in time series modeling, offering insights into the optimization of hyperparameters and validation methods for accurate predictions. It also underscores the significance of incorporating sentiment analysis alongside historical stock prices for improved forecasting accuracy. © 2024 The Authors

关键词： LSTM Sentiment analysis Stock price prediction Time series modeling Validation methods

来源：评论

学校读者我要写书评

暂无评论

COWID: an efficient cloud-based genomics workflow for scalable identification of SARS-COV-2

引用

Briefings in Bioinformatics 2023年第5期24卷 bbad280-bbad280页

作者： Lim, Hendrick Gao-Min Fann, Yang C Lee, Yuan-Chii Gladys Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei 11031 Taiwan Department of Medical Research Tzu Chi Hospital Indonesia Pantai Indah Kapuk Greater Jakarta 14470 Indonesia It and Bioinformatics Program Division of Intramural National Institute of Neurological Disorders and Stroke National Institutes of Health Bethesda 20892 MD United States

Implementing a specific cloud resource to analyze extensive genomic data on severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) poses a challenge when resources are limited. To overcome this, we repurposed a cloud platform initially designed for use in research on cancer genomics (https://***) to enable its use in research on SARS-CoV-2 to build Cloud Workflow for Viral and Variant Identification (COWID). COWID is a workflow based on the Common Workflow Language that realizes the full potential of sequencing technology for use in reliable SARS-CoV-2 identification and leverages cloud computing to achieve efficient parallelization. COWID outperformed other contemporary methods for identification by offering scalable identification and reliable variant findings with no false-positive results. COWID typically processed each sample of raw sequencing data within 5 min at a cost of only US$0.01. The COWID source code is publicly available (https://***/hendrick0403/COWID) and can be accessed on any computer with Internet access. COWID is designed to be user-friendly;it can be implemented without prior programming knowledge. Therefore, COWID is a time-efficient tool that can be used during a pandemic. © 2023 Published by Oxford University Press.

关键词： cloud repurposing cloud workflow COVID-19 Illumina sequencing parallel computation SARS-CoV-2

来源：评论

学校读者我要写书评

暂无评论

Gut microbial signatures associated with uremic pruritus in hemodialysis patients

引用

Journal of Microbiology, Immunology and Infection 2025年第4期58卷 479-485页

作者： Ko, Mei-Ju Liao, Chun-Hsing Chiu, Yen-Ling Tsai, Wan-Chuan Yang, Ju-Yeh Pai, Mei-Fen Tsai, Ping-Hsiu Hsu, Shih-Ping Peng, Yu-Sen Wu, Hon-Yen Department of Dermatology Taipei City Hospital Taipei City Taiwan Department of Dermatology National Taiwan University Hospital and College of Medicine Taipei City Taiwan School of Medicine College of Medicine National Yang Ming Chiao Tung University Taipei City Taiwan University of Taipei Taipei City Taiwan Department of Internal Medicine Far Eastern Memorial Hospital New Taipei City Taiwan Department of Medical Research Far Eastern Memorial Hospital New Taipei City Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan City Taiwan Graduate Institute of Medicine Yuan Ze University Taoyuan City Taiwan Center for General Education Lee-Ming Institute of Technology New Taipei City Taiwan School of Life Science National Taiwan Normal University Taipei City Taiwan Department of Applied Cosmetology Lee-Ming Institute of Technology New Taipei City Taiwan Department of Healthcare Administration Asia Eastern University of Science and Technology New Taipei City Taiwan Department of Internal Medicine National Taiwan University Hospital and College of Medicine Taipei City Taiwan Institute of Epidemiology and Preventive Medicine College of Public Health National Taiwan University Taipei City Taiwan

Background: The gut microbiota influences the gut–skin–kidney axis, but its role in uremic pruritus remains poorly understood. This study aimed to explore differences in gut microbial profiles between hemodialysis (HD) patients with and without uremic pruritus and identify potential microbial signatures associated with uremic pruritus. Methods: We conducted a cross-sectional study of HD patients with and without uremic pruritus. Stool samples were collected from all participants, and the gut microbiota composition was analyzed using 16S rRNA gene sequencing. Alpha and beta diversity metrics were calculated to assess microbial diversity. LEfSe analysis was performed to identify differentially abundant taxa associated with uremic pruritus. Results: Among 93 HD patients (mean age: 61.9 years, 31.2 % female), uremic pruritus occurred in 61.3 % of patients, with a median visual analog scale (VAS) score of 4.0. While alpha diversity did not differ significantly between groups, beta diversity analysis revealed significant compositional differences (unweighted UniFrac metric, P = 0.004;weighted UniFrac metric, P < 0.001). LEfSe analysis revealed significant enrichment of the order Pasteurellales, family Pasteurellaceae and genus Dialister in patients with uremic pruritus, whereas the order Corynebacteriales was more abundant in patients without pruritus (P < 0.05, LDA score > 3). Conclusion: In this study, we found significant differences in gut microbiota composition between HD patients with and without uremic pruritus and identified potential microbial biomarkers for uremic pruritus. Further studies are needed to elucidate the underlying mechanisms and explore microbiota-targeted therapeutic interventions. © 2025

关键词： Dialysis Gastrointestinal microbiome Microbiota Pruritus Skin diseases Uremia

来源：评论

学校读者我要写书评

暂无评论

Mini Light-Emitting Diode Technology with High Quantum Efficient NIR-II Partially Inverse Spinel MgGa2O4:Cr3+,Ni2+ Nanophosphors

引用

Advanced Optical Materials 2024年第19期12卷

作者： Satpathy, Aishwarya Huang, Wen-Tse Liu, Tzu-Hsuan Su, Ting-Yi Zhang, Wei Kamiński, Mikolaj Grzegorczyk, Maciej Chen, Jia-Hao Cherng, Ding-Hua Lu, Kuang-Mao Chen, Xueyuan Mahlik, Sebastian Liu, Ru-Shi Department of Chemistry National Taiwan University Taipei106 Taiwan Fujian Key Laboratory of Nanomaterials and CAS Key Laboratory of Design and Assembly of Functional Nanostructures Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Fujian Fuzhou350002 China Nanoscience and Technology Program Taiwan International Graduate Program Academia Sinica and National Taiwan University Academia Road 128 Taipei Nankang115 Taiwan Institute of Experimental Physics Faculty of Mathematics Physics and Informatics University of Gdańsk Wita Stwosza 57 Gdańsk80–308 Poland Everlight Electronics Co. Ltd. New Taipei City238 Taiwan International Centre for Theory of Quantum Technologies University of Gdańsk Gdańsk80–308 Poland

The increasing demand for second near-infrared (NIR-II) region materials, which retain the advantage of minimal scattering and immense applications in the medical and NIR spectroscopy field, has led to considerable research in this region. A mini light-emitting diode (mini-LED) is essential for backlighting liquid crystal displays, indicating the need for the small size of phosphors. However, current market phosphors must be more significant to be a viable option for mini-LEDs. This scenario necessitates the synthesis of small-sized phosphors to be used in mini-LEDs. In this work, a mesoporous silica nanoparticle (MSN) and incorporated the Mg1−yGa2−xO4:xCr3+,yNi2+ system is fabricated. The structural investigation confirmed the single phase of MgGa2O4 with a pore size of 2.73 nm for the MSN. The results showed a steady NIR-II signal at 1270 nm and an enhanced energy transfer with a high quantum yield of 79.2% for a nanophosphor. The mini-LED package revealed a 1000–1600 nm signal, qualifying the nanophosphor for realistic applications. This work can make provisions for various NIR-II nanophosphors in the LED industry. © 2024 Wiley-VCH GmbH.

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

Domain-guided data augmentation for deep learning on medical imaging

arXiv

引用

arXiv 2022年

作者： Athalye, Chinmayee Arnaout, Rima Department of Medicine Division of Cardiology Bakar Computational Health Sciences Institute University of California San Francisco United States Department of Medicine Division of Cardiology Bakar Computational Health Sciences Institute Chan Zuckerberg Biohub Intercampus Research Award Investigator Biological and Medical Informatics Graduate Program University of California San Francisco United States

While domain-specific data augmentation can be useful in training neural networks for medical imaging tasks, such techniques have not been widely used to date. Here, we test whether domain-specific data augmentation is useful for medical imaging using a well-benchmarked task: view classification on fetal ultrasound FETAL-125 and OB-125 datasets. We found that using a context-preserving cut-paste strategy, we could create valid training data as measured by performance of the resulting trained model on the benchmark test dataset. When used in an online fashion, models trained on this data performed similarly to those trained using traditional data augmentation (FETAL-125 F-score 85.33 ± 0.24 vs 86.89 ± 0.60, p-value 0.0139;OB-125 F-score 74.60 ± 0.11 vs 72.43 ± 0.62, p-value 0.0039). Furthermore, the ability to perform augmentations during training time, as well as the ability to apply chosen augmentations equally across data classes, are important considerations in designing a bespoke data augmentation. Finally, we provide open-source code to facilitate running bespoke data augmentations in an online fashion. Taken together, this work expands the ability to design and apply domain-guided data augmentations for medical imaging tasks. © 2022, CC BY-NC-ND.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Early-Life Risks of Central Precocious Puberty

引用

Endocrine Practice 2025年

作者： Yin, Wei-Jou Hsu, Jhih-Wei Chen, Chun-Chang Su, Emily Chia-Yu Wang, San-Yuan Chen, Yan-Jen Chen, Yang-Ching College of Medicine Taipei Medical University Taipei Taiwan Department of Family Medicine School of Medicine College of Medicine Taipei Medical University Taipei Taiwan Graduate Institute of Biomedical Informatics Taipei Medical University Taipei Taiwan Master Program in Clinical Genomics and Proteomics Department of Pharmaceutical Sciences Taipei Medical University Taipei Taiwan Department of Family Medicine Wan Fang Hospital Taipei Medical University Taipei Taiwan Nutrition Research Center Taipei Medical University Hospital Taipei Taiwan

Objectives: To investigate the factors in early life that may contribute to central precocious puberty (CPP). Methods: The study utilized data from the Taiwan Puberty Longitudinal Study, including 2241 children under pubertal assessment and a questionnaire of risk factors. We analyzed associations using the Fitting Generalized Linear Models in R (R Core Team, 2023), with R studio (Posit, 2023) version 4.3.1. Results: Among the 2241 children examined, 745 had CPP. Overall, higher gestational weight gain (GWG) increased the risk of CPP (odds ratio [OR]: 1.03, 95% CI: 1.01-1.05);while higher GWG served as a protective factor in females (OR: 0.97, 95% CI: 0.95-0.99). Maternal gestational diabetes mellitus (GDM) also increased the CPP risk, particularly in males (OR: 2.66, 95% CI: 1.00-7.25). Longer exclusive breastfeeding was linked to lower CPP risk overall (OR: 0.96, 95% CI: 0.93-1.00) but was not significant when analyzed by gender. Conclusions: Higher maternal GWG was associated with an increased risk of CPP overall, while GWG became negatively associated with CPP, only in females. Maternal GDM was linked to a higher risk of CPP, particularly in males. The duration of exclusive breastfeeding was inversely correlated with CPP risk, but this effect was not significant when analyzed by gender. © 2025 AACE

关键词： central precocious puberty early-life risk factors pediatrics

来源：评论

学校读者我要写书评

暂无评论

Parameter Optimization of Support Vector Regression Using Harris Hawks Optimization

引用

Procedia Computer Science 2021年 179卷 17-24页

作者： I Nyoman Setiawan Robert Kurniawan Budi Yuniarto Rezzy Eko Caraka Bens Pardamean Computational Statistics Department Polytechnic of Statistics - STIS Jakarta 13330 Indonesia Department of Information Management College of Informatics Chaoyang University of Technology Taiwan (ROC) Bioinformatics and Data Science Research Center Bina Nusantara University Indonesia 11530 Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia. 11530.

Support Vector Regression (SVR) is often used in forecasting. Adjustment of parameters in the SVR affects the results of forecasting. This study aims to analyze the SVR method that is optimized using Harris Hawks Optimization (HHO), hereinafter referred to as HHO-SVR. The HHO-SVR was evaluated using five benchmark datasets to determine the performance of this method. The HHO process is also compared based on the type of kernel and other metaheuristic algorithms. The results showed that the HHO-SVR has almost the same performance as other methods but is less efficient in terms of time. In addition, the type of kernel also affects the process and results.

关键词： SVR harris hawks optimization parameter optimization kernel forecasting

来源：评论

学校读者我要写书评

暂无评论

Adaptive optimal multi key based encryption for digital image security

Adaptive optimal multi key based encryption for digital imag...

引用

作者： Shankar, K. Lakshmanaprabu, S.K. Gupta, Deepak Khanna, Ashish de Albuquerque, Victor Hugo C. School of Computing Kalasalingam Academy of Research and Education Krishnankoil India B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Maharaja Agrasen Institute of Technology Delhi India Graduate Program in Applied Informatics University of Fortaleza Fortaleza Brazil

The security of digital images is an essential and challenging task on shared communication Model. Generally, high secure working environment and data are also secured with an encryption and decryption method by using secret and public keys. In this paper, the innovative encryption technique for image security, ie, Multiple key-based Homomorphic Encryption (MHE) technique is proposed. For increasing the security level of encryption and decryption processes, the optimal key is selected using Adaptive Whale Optimization (AWO) algorithm. Fitness function was considered for optimization as PSNR of plain and cipher images. The original image was transformed into blocks and then rearranged utilizing encryption process, this work achieved maximum security, much better than other encryption techniques. From the outcomes, one can achieve incredible quality of the proposed model, the maximum PSNR, and the minimum MSE contrasted with other encryption schemes. © 2018 John Wiley & Sons, Ltd.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Comparison of Fetal Heart Rate Detection Using Envelope Extraction and Shannon Energy

Comparison of Fetal Heart Rate Detection Using Envelope Extr...

引用

2019 International Seminar on Application for Technology of Information and Communication, iSemantic 2019

作者： Setiawan, Agung W. Sujatmiko, Wahyu Biomedical Engineering Research Group School of Electrical Engineering and Informatics ITB Bandung Indonesia Graduate Program in Electrical Engineering School of Electrical Engineering and Informatics ITB Bandung Indonesia

ISBN: (纸本)9781728138329

Heart rate monitoring is widely used as a general procedure to examine fetal health condition. Fetal heart rate can be used to identified possibilities of fetal anomaly and warn the obstetrician to provide immediate intervention before any further abnormalities. The purpose of this research is to compare fetal heart rate detection result using envelope extraction and Shannon energy envelope method. There are 115 fetal phonocardiography and maternal phonocardiography that is used in this research. The dataset was obtained from Hafez Hospital, Shiraz University of Medical Science. Envelope extraction method can be used to detect fetal heart rate signal with 89.2% accuracy for all fetal phonocardiography signal while Shannon energy envelope method can be used to detect fetal heart rate signal with 88.3% accuracy for all fetal phonocardiography signal. © 2019 IEEE.

关键词： Phonocardiography

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：