检索结果-内蒙古大学图书馆

Invasive or More Direct Measurements Can Provide an Objective Early-Stopping Ceiling for Training Deep Neural Networks on Non-invasive or Less-Direct Biomedical Data

引用

SN computer science 2023年第2期4卷 161页

作者： Bartlett, Christopher W. Bossenbroek, Jamie Ueyama, Yukie McCallinhart, Patricia Peters, Olivia A. Santillan, Donna A. Santillan, Mark K. Trask, Aaron J. Ray, William C. Department of Pediatrics The Ohio State University College of Medicine Columbus OH United States The Steve and Cindy Rasmussen Institute for Genomic Medicine Battelle Center for Computational Biology The Abigail Wexner Research Institute at Nationwide Children’s Hospital Columbus OH United States Department of Computer Science and Engineering The Ohio State University College of Engineering Columbus OH United States Center for Cardiovascular Research The Abigail Wexner Research Institute at Nationwide Children’s Hospital Columbus OH United States Department of Obstetrics & Gynecology University of Iowa Hospitals & Clinics Iowa City IA United States The Interdisciplinary Graduate Program in Biophysics The Ohio State University Graduate School Columbus OH United States

Early stopping is an extremely common tool to minimize overfitting, which would otherwise be a cause of poor generalization of the model to novel data. However, early stopping is a heuristic that, while effective, primarily relies on ad hoc parameters and metrics. Optimizing when to stop remains a challenge. In this paper, we suggest that for some biomedical applications, a natural dichotomy of invasive/non-invasive measurements, or more generally proximal vs distal measurements of a biological system can be exploited to provide objective advice on early stopping. We discuss the conditions where invasive measurements of a biological process should provide better predictions than non-invasive measurements, or at best offer parity. Hence, if data from an invasive measurement are available locally, or from the literature, that information can be leveraged to know with high certainty whether a model of non-invasive data is overfitted. We present paired invasive/non-invasive cardiac and coronary artery measurements from two mouse strains, one of which spontaneously develops type 2 diabetes, posed as a classification problem. Examination of the various stopping rules shows that generalization is reduced with more training epochs and commonly applied stopping rules give widely different generalization error estimates. The use of an empirically derived training ceiling is demonstrated to be helpful as added information to leverage early stopping in order to reduce overfitting. © 2023, The Author(s).

关键词： Health Invasive Machine learning Model Non-invasive Overfitting

来源：评论

学校读者我要写书评

暂无评论

GranatumX:A Community-engaging, Modularized, and Flexible Webtool for Single-cell Data Analysis

引用

Genomics, Proteomics & Bioinformatics 2021年第3期19卷 452-460页

作者： David G.Garmire Xun Zhu Aravind Mantravadi Qianhui Huang Breck Yunits Yu Liu Thomas Wolfgruber Olivier Poirion Tianying Zhao Cédric Arisdakessian Stefan Stanojevic Lana X.Garmire Department of Electrical Engineering&Computer Science University of MichiganAnn ArborMI 48109USA Epidemiology Program University of Hawaii Cancer CenterHonoluluHI 96813USA Department of Biostatistics University of MichiganAnn ArborMI 48109USA Department of Computational Medicine and Bioinformatics University of MichiganAnn ArborMI 48105USA Molecular Biosciences and Bioengineering Graduate Program University of Hawaii at ManoaHonoluluHI 96822USA

We present GranatumX,a next-generation software environment for single-cell RNA sequencing(scRNA-seq)data *** is inspired by the interactive webtool *** enables biologists to access the latest scRNA-seq bioinformatics methods in a web-based graphical *** also offers software developers the opportunity to rapidly promote their own tools with others in customizable *** architecture of GranatumX allows for easy inclusion of plugin modules,named Gboxes,which wrap around bioinformatics tools written in various programming languages and on various *** can be run on the cloud or private servers and generate reproducible *** is a community-engaging,flexible,and evolving software ecosystem for scRNA-seq analysis,connecting developers with bench *** is freely accessible at http://***/granatumx/app.

关键词： Single-cell RNA sequencing Analysis Pipeline Webtool Module

来源：评论

学校读者我要写书评

暂无评论

Directed discovery of high-loading nanoaggregates enabled by drug-matched oligo-peptide excipients

引用

Chem 2025年第6期11卷

作者： Berisha, Naxhije Farahpour, Atena Ramakrishnan, Maithreyi Chen, Chen McPhee, Scott A. Wang, Tong Li, Tai-De Hema, Kuntrapakam Panagiotakopoulou, Magdalini Athiyarath, Vignesh Coste, Maeva Marciano, Yaron Sherman, Emmet Ulijn, Rein V. Heller, Daniel A. Nanoscience Initiative Advanced Science Research Center CUNY Graduate Center City University of New York New York 10031 NY United States Department of Chemistry and Biochemistry Hunter College City University of New York New York 10065 NY United States PhD Program in Chemistry CUNY Graduate Center City University of New York New York 10016 NY United States Molecular Pharmacology Program Memorial Sloan Kettering Cancer Center New York 10065 NY United States Tri-Institutional PhD Program in Chemical Biology Memorial Sloan Kettering Cancer Center New York 10065 NY United States Department of Physics City College of New York City University of New York New York 10031 NY United States Department of Chemistry Brooklyn College City University of New York 2900 Bedford Avenue Brooklyn 11210 NY United States PhD Program in Biochemistry CUNY Graduate Center City University of New York New York 10016 NY United States Weill Cornell Medicine Cornell University New York 10065 NY United States

Nanoparticles can improve drug pharmacokinetics, but low loading efficiencies can limit treatment efficacy. Drug-aggregation-based nanoparticles have demonstrated improved loadings of up to 90%, but few excipients facilitate efficient co-assembly. We investigated peptides as designer excipients because of their diverse chemical space and inherent biodegradability. We designed pentapeptide scaffolds to mimic the structure of known indocyanine excipients by modulating aromaticity, rigidity, and charge. We screened 184 formulations by using diverse drug cargoes. We found drug-peptide combinations that formed nanoparticles with up to 98% drug loading. Molecular dynamics simulations and mass spectrometry analysis demonstrated that tryptophan-drug interactions and solvent exposure of charged amino acid residues drove the formation of core-shell structures. Peptide-drug formulations containing the JAK2/FLT3 inhibitor lestaurtinib were investigated in acute myeloid leukemia models, resulting in enhanced anti-tumor efficacy. This work found that oligopeptides can be designed to efficiently co-assemble with therapeutic cargoes to result in high-loading nanoparticles that improve anti-tumor efficacy. © 2024

关键词： co-assembly directed discovery drug delivery excipient nanocarrier design nanoparticle oligopeptides SDG3: Good health and well-being

来源：评论

学校读者我要写书评

暂无评论

Database management system design for automatic weather information with twitter data collection 6

Database management system design for automatic weather info...

引用

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

作者： Purwandari, Kartika Perbangsa, Anzaludin Samsinga Sigalingging, Join W. C. Krisna, Adhi Asta Anggrayani, Suci Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Meteorological Climatological and Geophysical Agency Database Center Division of Bmkg Jakarta10720 Indonesia Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665449373

Improvement of data management about weather in Indonesia is very supportive of the need for weather information. Currently, the weather information that is disseminated to the public is only based on sensor location points that are spread across Indonesia. However, supporting data generated from these sensors is only limited to certain areas. We hence develop a database system that can help collect weather information automatically via Twitter. This facilitates the Indonesian people in knowing weather information based on the completeness of data from sensor data and Twitter. The steps from the database that are built will be very helpful in collecting data about the weather throughout Indonesia. The basic step that we use in our database are conceptual, logical and physical design. The information obtained in this study is very important for efficient and effective data collection to achieve real-time automation of weather information. © 2021 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Reproducing ATT&CK Techniques and Lifecycles to Train Machine Learning Classifier

引用

IEEE Network 2025年

作者： Yudha, Fietyata Lin, Ying-Dar Lai, Yuan-Cheng Sudyana, Didik Hwang, Ren-Hung EECS International Graduate Program National Yang Ming Chiao Tung University Hsinchu City300 Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu City300 Taiwan The Department of Information Management National Taiwan University of Science and Technology Tapei106 Taiwan The Computer and Network Center National Cheng Kung University Tainan701 Taiwan The College of Artificial Intelligence National Yang Ming Chiao Tung University Tainan711 Taiwan

he MITRE ATT&CK framework categorizes threat actor behaviors into a sequence of techniques called the attack lifecycle. Based on this, Our work introduces a dual-labeled dataset that is accurately labeled with distinct techniques and lifecycles defined by ATT&CK. The dataset offered a more thorough perspective than previous datasets that employed binary or attack classification. It encompassed 17 distinct techniques throughout five lifecycles and was generated through an automated method that guarantees reproducibility and learnability. Reproducibility guarantees the dataset’s consistency, whereas learnability signifies its use in training machine learning models. Our analysis produced a positive result. The dataset achieved a Pearson correlation coefficient of 0.7 for reproducibility. Regarding distinguishing classes, it exhibits an average AUC-ROC score of 0.92 for techniques and 0.82 for lifecycles. The model training yielded an average F1 score of 0.95 for technique classification and 0.9 for lifecycle classification, but only for the traffic dataset. © 1986-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Model Updates Through GAN Data Augmentation and Transfer Learning

Intrusion Detection Model Updates Through GAN Data Augmentat...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Pedro Horchulhack Eduardo K. Viegas Altair O. Santin Jhonatan Geremias Pontificia Universidade Catolica do Parana (PUCPR) ― Graduate Program in Computer Science (PPGIa) Brazil Secure Systems Research Center ― Technology Innovation Institute (TII) Abu Dhabi

ISBN: (纸本)9781665435413

Current machine learning techniques for network-based intrusion detection cannot handle the evolving behavior of network traffic, requiring periodic model updates to be conducted. Besides requiring huge amounts of labeled network traffic to be provided, traditional model updates demand expressive computational costs. This paper proposes a new feasible model update procedure implemented in two steps. First, we use a Generative Adversarial Network (GAN) to augment the sampled network traffic. Next, we use the augmented dataset to perform model updates through a transfer learning-based approach. Thus, our model can decrease both the number of instances that must be labeled and the computational costs during model updates. Our experiments on a one-year dataset with over 8 TB of data show that literature techniques cannot handle changes in network traffic behavior. In contrast, the proposed model without updates improved true-positive rates by up to 25.6%. With monthly model updates, it requires only 14% of computational costs and 2.3% of instances to be provided.

关键词： Computational modeling Transfer learning Intrusion detection Telecommunication traffic Generative adversarial networks Data models Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Towards Multi-view Android Malware Detection Through Image-based Deep Learning

Towards Multi-view Android Malware Detection Through Image-b...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Jhonatan Geremias Eduardo K. Viegas Altair O. Santin Alceu Britto Pedro Horchulhack Pontificia Universidade Catolica do Parana (PUCPR) - Graduate Program in Computer Science (PPGIa) Brazil Secure Systems Research Center - Technology Innovation Institute (TII) Abu Dhabi

Over the last years, several works have proposed highly accurate Android malware detection techniques. Surprisingly, modern malware apps can still pave their way to official markets, thus, demanding the provision of more robust and accurate detection approaches. This paper proposes a new multi-view Android malware detection through image-based deep learning, implemented threefold. First, apps are evaluated according to several feature sets in a multi-view setting, thus, increasing the information provided for the classification task. Second, extracted feature sets are converted to an image format while maintaining the principal components of the data distribution, keeping the information for the classification task. Third, built images are jointly represented in a single shot, each in a predefined image channel, enabling the application of deep learning architectures. Experiments on a new version of a publicly available Android malware dataset composed of over 11 thousand Android apps have shown our proposal's feasibility. It reaches true-negative rates of up to 99.5% when implemented with a single-view approach with our new image-building technique. In addition, if our proposed multi-view scheme is used, the classification accuracies of malware families become more stable, reaching a true-positive rate of up to 98.7%.

关键词： Deep learning Wireless communication Buildings computer architecture Feature extraction Malware Proposals

来源：评论

学校读者我要写书评

暂无评论

Smart Dome 4.0: Low-Cost, Independent, Automated Energy System for Agricultural Purposes enabled by Machine Learning 2

Smart Dome 4.0: Low-Cost, Independent, Automated Energy Syst...

引用

2021 2nd International Symposium on Automation, Information and Computing, ISAIC 2021

作者： Budiman, Arief S Gunawan, Fergyanto Djuana, Endang Pardamean, Bens Romeli, Sugiarto Putri, Dianing Nn Aji, Daisman Pb Rahardjo, Kuat Stevanus Ilham Wibowo, M. Daffa, Nadiev Owen, Raymond Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia Department of Manufacturing and Mechanical Engineering and Technology Oregon Institute of Technology Klamath FallsOR97601 United States Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta Indonesia 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 PT. Impack Pratama Industri Tbk Jakarta Indonesia Mechanical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta Indonesia Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia

Many economically essential crops in Indonesia (such as coffee, tea, chocolate, or copra) require storage or drying under certain environmental conditions, especially temperature and humidity. The solar dryer dome, typically used for agricultural purposes in Indonesia, produces a sufficient amount of heat to increase the evaporation rate inside the dome and reduce the moisture content of the commodity. A hybrid solar dryer accompanied by a photovoltaic panel, fan, and ventilation system is generally suitable. The system can provide an optimum environment with minimum control. However, as the outdoor temperature and humidity change dramatically, such as at night time, more control is required. Based on Industry 4.0 technologies, we have developed a new kind of hybrid solar dryer that provides an optimum environment 24/7. The system, called Smart Dome 4.0, is an intelligent, low-cost, self-sufficient drying and storage system to support Indonesia Agriculture 4.0. The system has a local power generation unit to self-sustain the required energy and operate without connecting to the electricity grid. The system utilizes a machine-learning algorithm to predict the environmental condition and optimally uses self-generated electric power. The developed Smart Dome 4.0 technology is critical to producing a sustainable solar dome under drastic environmental dynamics. © Published under licence by IOP Publishing Ltd.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

IoT for Water Quality Categorization

IoT for Water Quality Categorization

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Hermantoro Sastrohartono Andreas Wahyu Krisdiarto Arief Ika Uktoro Reza Rahutomo Teddy Suparyanto Bens Pardamean Agricultural Engineering Department Faculty of Agricultural Technology Institute of Agriculture STIPER Yogyakarta Indonesia Information System Department School of Information Systems Bina Nusantara University Jakarta Indonesia Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

In agricultural water research, the adoption of Internet of Things (IoT) technology has emerged as a pivotal approach for large-scale data collection. Water availability in the context of water quality is very important, both for domestic and industrial purposes. For domestic purposes, drinking water and bathing water are separated. Meanwhile, for the palm oil industry, boiler filler is differentiated from additional process water (dilution water). Water quality parameters can be assessed from turbidity and Total Dissolve Solid (TDS). Measurements using measuring instruments separately and repeatedly require significant energy, time, and costs. This research was conducted with the primary objective of presenting a novel method for categorizing water quality with the approach of IoT sensor technology. The research methodology entailed the utilization of an integrated IoT water sensors system in conjunction with manual water categorization. The methods consist of (1) system design, (2) design and installation of sensor and IoT-based microcontrollers, and (3) accuracy and precision testing compared with laboratory measurements. The precision of the integrated IoT water sensors was assessed through a dedicated sensor precision test, resulting in an accuracy rate of 94.4% for the turbidity sensor and 97.5% for the TDS sensor. Notably, this approach successfully discriminated drinking water with valid categorization, while other water types, including groundwater, water with tea, and water with coffee, yielded null categorization results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recommendation system based on recognition of prior learning to support curriculum design in online higher education 6

Recommendation system based on recognition of prior learning...

引用

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

作者： Murad, Dina Fitria Hassan, Rosilah Heryadi, Yaya Wijanarko, Bambang Dwi Titan Bina Nusantara University BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Universiti Kebangsaan Malaysia Center for Cyber Security Faculty of Information Science Technology UKM Bangi Selangor Malaysia Bina Nusantara University BINUS Graduate Program- Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Online Learning Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665449373

Based on the policy of independent study and independent campus, where students can participate in part of the study period and load from within the campus, as well as others outside the campus, so that they can complete all periods and study loads as needed qualification is determined by the study program conducted through assessors. and this requires a variety of processes and takes a lot of time. For this reason, an alternative technique is needed to conduct an automatic Recognition of Prior Learning (RPL) assessment through the application of a recommendation system. The purpose of this research is to find out how the recommendation system approach is used to predict RPL assessments and provide support for curriculum development in tertiary institutions that can meet the learning needs of the digital community. This study has succeeded in classifying learning outcomes based on independent assessment data of prospective students and can provide recommendations for curriculum development in colleges that organize online learning. This study proves that the use of a recommendation system using deep learning in the RPL assessment has an accuracy (97, 24%) and is relatively the same as the assessor's assessment. © 2021 IEEE.

关键词： Recommender systems

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：