检索结果-内蒙古大学图书馆

Simulating multi-scale optimization and variable selection in species distribution modeling

学校读者我要写书评

暂无评论

Ecological informatics 2024年 83卷

作者： Cushman, Samuel A. Kaszta, Zaneta M. Burns, Patrick Hakkenberg, Christopher R. Jantz, Patrick Macdonald, David W. Brodie, Jedediah F. Deith, Mairin C.M. Goetz, Scott Wildlife Conservation Research Unit The Recanati-Kaplan Centre Department of Biology University of Oxford United Kingdom GEODE Laboratory School of Informatics Computing & Cyber Systems Northern Arizona University United States Division of Biological Sciences and Wildlife Biology Program University of Montana Missoula 59812 MT United States Institute of Biodiversity and Environmental Conservation Universiti Malaysia Sarawak Kota Samarahan 94300 Malaysia Institute for the Oceans and Fisheries University of British Columbia 2202 Main Mall Vancouver V6T 1Z4 BC Canada Department of Biology Northern Arizona University United States

Species distribution modeling (SDM) is a fundamental tool in theoretical and applied ecology. However, relatively little is known about the performance of different approaches for scale optimization, model selection, and algorithmic prediction in the context of nonlinear, multiscale and interactive relationships between environmental variables and species occurrence. Modelers often struggle to optimize a tradeoff between ecological relevance, model robustness, complexity, and overfitting. In this paper, we investigated several methods designed to optimize spatial scale and variable selection in SDMs, in each case evaluating model fitness, parsimony and predictive performance. We used a simulation approach to produce a large pool of alternative underlying habitat relationships that reflect a broad range of realistic habitat associations. We also compared several different modeling algorithms, including logistic regression with a generalized linear model (GLM), Lasso and Elastic-Net Regularized GLMs (GLMNet), and random forest (RF), as well as alternative variable and scale selection methods. We found that GLM methods employing all-subsets dredge routines for variable selection were consistently the best predictors based on all criteria of our model performance assessment and across all attributes of the simulated underlying relationship, including nonlinearity and interaction. We had expected machine learning approaches, such as random forest, to perform better in these more complex forms of species-environment relationships. GLM using dredge variable selection was also the method that included the fewest spurious covariates and included the most correct predictors as a proportion of all predictors. We found that univariate scaling was the most robust method of variable and scale selection, along with Minimal Redundancy Maximal Relevancy (MRMR) which performed equivalently. The simulation experiment presented here provides a robust assessment of simulated multi-speci

关键词： Methods comparison Scale optimization Simulation experiment Species distribution modeling Variable selection

A Unified Framework for Human Centered Design of a Substance Use, Abuse, and Recovery Support System

学校读者我要写书评

暂无评论

A Unified Framework for Human Centered Design of a Substance...

AHFE Virtual Conference on Human Factors and Ergonomics in Healthcare and Medical Devices, and the International Conference on Human Factors in Aging and Special Needs, 2020

作者： Schooley, Benjamin Feldman, Sue Tipper, Bradley Health Information Technology Program College of Engineering and Computing University of South Carolina 550 Assembly Street ColumbiaSC29208 United States Graduate Programs in Health Informatics Department of Health Services Administration School of Health Professions University of Alabama - Birmingham 1716 9th Ave South SHPB #590K BirminghamAL35294 United States

ISBN: (纸本)9783030508371

This research explores the analysis, design, and testing of a software application to support opioid peer specialists working to assist substance users, abusers, those in recovery, and their families. The paper presents a framework integrating best practice approaches from Design Science Research, Community Based Participatory Research, and human centered and user experience design principles for the purpose of: 1) guiding community based, goal-directed software design, and 2) building and evaluating a substance use, abuse, and recovery software application. Focus group findings from 33 participants suggest that using the framework enables alignment between human centered system requirements;personal, family, and community-based program goal achievement;and local/state population health directives. End user feedback indicates that the software application design addresses specific human interaction needs for the complex high-stakes context of opioid use, abuse, and recovery. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Application programs

Perspectives on risk prioritization of data center vulnerabilities using rank aggregation and multi-objective optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Grisci, Bruno Iochins Kuhn, Gabriela Colombelli, Felipe Matter, Vítor Kehl Lima, Leomar Heinen, Karine Pegoraro, Mauricio Borges, Marcio Rigo, Sandro José Barbosa, Jorge Luis Victória da Rosa Righi, Rodrigo da Costa, Cristiano André de Oliveira Ramos, Gabriel Software Innovation Laboratory - Softwarelab Graduate Program in Applied Computing Universidade do Vale do Rio dos Sinos Av. Unisinos 950 RS São Leopoldo93022-750 Brazil Institute of Informatics Federal University of Rio Grande do Sul Av. Bento Gonçalves 9500 RS Porto Alegre91501-970 Brazil Dell Technologies Brazil Av. Industrial Belgraf 400 Eldorado do Sul RS 92990-000 Brazil

Nowadays, data has become an invaluable asset to entities and companies, and keeping it secure represents a major challenge. Data centers are responsible for storing data provided by software applications. Nevertheless, the number of vulnerabilities has been increasing every day. Managing such vulnerabilities is essential for building a reliable and secure network environment. Releasing patches to fix security flaws in software is a common practice to handle these vulnerabilities. However, prioritization becomes crucial for organizations with an increasing number of vulnerabilities since time and resources to fix them are usually limited. This review intends to present a survey of vulnerability ranking techniques and promote a discussion on how multi-objective optimization could benefit the management of vulnerabilities risk prioritization. The state-of-the-art approaches for risk prioritization were reviewed, intending to develop an effective model for ranking vulnerabilities in data centers. The main contribution of this work is to point out multi-objective optimization as a not commonly explored but promising strategy to prioritize vulnerabilities, enabling better time management and increasing security. Copyright © 2022, The Authors. All rights reserved.

关键词： Multiobjective optimization

Improving health awareness with real-time monitoring through a three-dimensional visualized digital health avatar

学校读者我要写书评

暂无评论

Smart Health 2024年 34卷

作者： Chokphukhiao, Chaturapron Pattaranit, Pattrawan Tun, Wonn Shweyi Thet Masa, Sakaowrat Leemananil, Rattikorn Natteerapong, Nuttaphorn Phetcharaburanin, Jutarop Boonlue, Sophon Sunat, Khamron Patramanon, Rina Information Technology International Program College of Computing Khon Kaen University Khon Kaen 40002 Thailand Center of Excellence in Digital Innovation Faculty of Education Khon Kaen University Khon Kaen 40002 Thailand Integrative Biomedical Informatics and Computational Imaging Center I-BIC Faculty of Associated Medical Science Khon Kaen University Khon Kaen 40002 Thailand Department of System Biosciences and Computational Medicine Faculty of Medicine Khon Kaen University Khon Kaen 40002 Thailand Khon Kaen University National Phenome Institute Khon Kaen University Khon Kaen 40002 Thailand Department of Biochemistry Faculty of Science. Khon Kaen University Khon Kaen 40002 Thailand Department of Microbiology Faculty of Science Khon Kaen University Khon Kaen 40002 Thailand Department of Computer Science College of Computing Khon Kaen University 40002 Thailand

Introduction: The use of modern technologies has become crucial for enhancing people's awareness of health problems. By early health risk detection, there will be better treatment outcomes, the severity of illness will decrease, and costs for treatment will also reduce. Performing routine checkups could help patients feel less anxious about their health in the future. In this study, the innovation of “Digital Health Avatar” enables users to monitor physical changes, raise awareness of medical conditions, and encourage healthy behaviors by visualizing health status as a 3D figure. Methods: Health data were collected using medical devices like blood test strips, body composition meters, and automatic blood pressure monitors. API technology and cloud computing systems were used to process these collected data and produced a three-dimensional avatar that indicated the user's health status. User satisfaction survey on using the health avatar system was assessed through a survey of 61 participants. Results: Health avatar system successfully generate the data and display the measurement results on the health report page of the system. Users can easily check and record their physiological conditions through the avatar. Moreover, users showed satisfaction on the use of the health avatar system and its effectiveness in health check-ups in the survey. Conclusions: The ‘Digital Health Avatar’ has the potential to significantly promote individual well-being and health awareness. Its development will be improved by user feedback and continued study, ensuring it becomes an efficient tool for promoting healthier lifestyles. © 2024 The Authors

关键词： Digital health avatar Health sensors Healthcare Three-dimensional model

A microservice-based approach for increasing software reusability in health applications 16

学校读者我要写书评

暂无评论

A microservice-based approach for increasing software reusab...

16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019

作者： Da Silva, Marcio Alexandre Pereira Times, Valeria Cesario De Araujo, Andre Magno Costa Da Silva, Paulo Caetano Center for Informatics Federal University of Pernambuco Recife/PE Brazil Department of Information Systems Federal University of Alagoas Penedo/AL Brazil Master Program in Computing Salvador University Salvador/BA Brazil

ISBN: (纸本)9781728150529

Traditionally, legacy Health applications use software architecture models that make it difficult to reuse components. Reusability is an essential attribute in the software lifecycle, as it improves the quality of applications and reduces maintenance and development costs. This paper proposes the cloud tool Microservice4EHR, which dynamically generates reusable components from existing software artifacts (e.g., graphical interfaces), while conforming to the standards used in the healthcare domain. A software architecture based on Connectors and Microservice components is specified and made tangible by means of three algorithms. The use of both components is applied to a real-world scenario (a Brazilian blood donation center) and serves as an example. As a result, it is possible to notice that Health applications achieve greater reusability when they employ the microservice architecture. Thus, Microservice4EHR enables the use of reusable components in Health application architectures (for both new and legacy systems), increasing software reusability in this context. © 2019 IEEE.

关键词： Health

Efficient and scalable neural residual waveform coding with collaborative quantization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhen, Kai Lee, Mi Suk Sung, Jongmo Beack, Seungkwon Kim, Minje Indiana University Luddy School of Informatics Computing and Engineering BloomingtonIN United States Indiana University Cognitive Science Program BloomingtonIN United States Electronics and Telecommunications Research Institute Daejeon Korea Republic of

Scalability and efficiency are desired in neural speech codecs, which supports a wide range of bitrates for applications on various devices. We propose a collaborative quantization (CQ) scheme to jointly learn the codebook of LPC coefficients and the corresponding residuals. CQ does not simply shoehorn LPC to a neural network, but bridges the computational capacity of advanced neural network models and traditional, yet efficient and domain-specific digital signal processing methods in an integrated manner. We demonstrate that CQ achieves much higher quality than its predecessor at 9 kbps with even lower model complexity. We also show that CQ can scale up to 24 kbps where it outperforms AMR-WB and Opus. As a neural waveform codec, CQ models are with less than 1 million parameters, significantly less than many other generative models. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Precision Rehabilitation for Patients Post-Stroke based on Electronic Health Records and Machine Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gao, Fengyi Zhang, Xingyu Sivarajkumar, Sonish Denny, Parker E. Aldhahwani, Bayan M. Visweswaran, Shyam Shi, Ryan Hogan, William Bove, Allyn Wang, Yanshan Department of Health Information Management University of Pittsburgh PittsburghPA United States Department of Communication Science and Disorders University of Pittsburgh PittsburghPA United States Intelligent Systems Program School of Computing and Information University of Pittsburgh PittsburghPA United States Department of Physical Therapy University of Pittsburgh PittsburghPA United States Department of Medical Rehabilitation Sciences Umm Al-Qura University Makkah Saudi Arabia Department of Biomedical Informatics University of Pittsburgh PittsburghPA United States Department of Computer Science University of Pittsburgh Medical Center PittsburghPA United States Data Science Institute Medical College of Wisconsin MilwaukeeWI United States Hillman Cancer Center University of Pittsburgh Medical Center PittsburghPA United States

Objective In this study, we utilized statistical analysis and machine learning methods to examine whether rehabilitation exercises can improve patients post-stroke functional abilities, as well as forecast the improvement in functional abilities. Our dataset is patients’ rehabilitation exercises and demographic information recorded in the unstructured electronic health records (EHRs) data and free-text rehabilitation procedure notes. Through this study, our ultimate goal is to pinpoint the specific rehabilitation exercises that can effectively aid post-stroke patients in improving their functional outcomes in basic mobility (BM) and applied cognitive (AC) domains. Data sources We collected data for 265 stroke patients from the University of Pittsburgh Medical Center, accessed through the Rehabilitation Datamart With informatics iNfrastructure for Research (ReDWINE). Methods We employed a pre-existing natural language processing (NLP) algorithm to extract data on rehabilitation exercises and developed a rule-based NLP algorithm to extract Activity Measure for Post-Acute Care (AM-PAC) scores, covering basic mobility (BM) and applied cognitive (AC) domains, from procedure notes. AM-PAC scores were collected at the initial rehabilitation visit and followed up at one and two months—key recovery periods. Changes in AM-PAC scores were classified based on the minimal clinically important difference (MCID), and significance was assessed using Friedman and Wilcoxon tests. To identify impactful exercises, we used Chi-square tests, Fisher's exact tests, and logistic regression for odds ratios. Additionally, we developed five machine learning models—logistic regression (LR), Adaboost (ADB), support vector machine (SVM), gradient boosting (GB), and random forest (RF)—to predict outcomes in functional ability. Results Statistical analyses revealed significant associations between functional improvements and specific exercises. In the AC domain, the BALANCE exercise showed substant

关键词： Statistical tests

Knowledge-Guided Multiview Deep Curriculum Learning for Elbow Fracture Classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luo, Jun Kitamura, Gene Arefan, Dooman Doganay, Emine Panigrahy, Ashok Wu, Shandong Intelligent Systems Program School of Computing and Information University of Pittsburgh PittsburghPA United States Department of Radiology School of Medicine University of Pittsburgh PittsburghPA United States University of Pittsburgh Medical Center Children’s Hospital of Pittsburgh PittsburghPA United States Department of Biomedical Informatics Department of Bioengineering University of Pittsburgh PA United States

Elbow fracture diagnosis often requires patients to take both frontal and lateral views of elbow X-ray radiographs. In this paper, we propose a multiview deep learning method for an elbow fracture subtype classification task. Our strategy leverages transfer learning by first training two single-view models, one for frontal view and the other for lateral view, and then transferring the weights to the corresponding layers in the proposed multiview network architecture. Meanwhile, quantitative medical knowledge was integrated into the training process through a curriculum learning framework, which enables the model to first learn from "easier" samples and then transition to "harder" samples to reach better performance. In addition, our multiview network can work both in a dual-view setting and with a single view as input. We evaluate our method through extensive experiments on a classification task of elbow fracture with a dataset of 1,964 images. Results show that our method outperforms two related methods on bone fracture study in multiple settings, and our technique is able to boost the performance of the compared methods. The code is available at https://***/ljaiverson/multiview-curriculum. Copyright © 2021, The Authors. All rights reserved.

关键词： Curricula

Synthetic biology in Indonesia: Potential and projection in a country with mega biodiversity

学校读者我要写书评

暂无评论

Biotechnology Notes 2023年第1期4卷 41-48页

作者： Sanka, Immanuel Kusuma, Ali Budhi Martha, Faustina Hendrawan, Andre Pramanda, Ihsan Tria Wicaksono, Adhityo Jati, Afif Pranaya Mazaya, Maulida Dwijayanti, Ari Izzati, Nurul Maulana, Muhammad Farhan Widyaningrum, Aulia Reski Synthetic Biology Indonesia (Synbio.id) Jl. Raya Lintas Sumbawa-Bima Block AA No. 1 Boak Village Subdistrict Unter Iwes Sumbawa 84316 Indonesia Department of Chemistry and Biotechnology Tallinn University of Technology Akadeemia tee 15 Tallinn 12618 Estonia Indonesian Centre for Extremophile Bioresources and Biotechnology (ICEBB) Faculty of Life Sciences and Technology Sumbawa University of Technology Jl. Raya Olat Maras Sumbawa 84371 Indonesia Science Communication Steering Committee iGEM Foundation 45 Prospect St Cambridge 02139 MA United States Department of Bio Technology Indonesia International Institute for Life Sciences (i3L) Jl. Pulomas Barat Kav. 88 Pulomas Jakarta 13210 Indonesia Division of Biotechnology Genbinesia Foundation Jalan Swadaya Barat no. 4 Gresik 61171 Indonesia Infection Program Monash Biomedicine Discovery Institute and Department of Microbiology Monash University Melbourne VIC Australia Research Center for Computing Research Organization for Electronics and Informatics National Research and Innovation Agency (BRIN) Cibinong Science Center Jl. Raya Jakarta-Bogor KM 46 West Java Cibinong 16911 Indonesia

Synthetic biology has gained many interest around the globe in the last two decades, not only due to its rapid development but also the potential to provide addressable solutions using standardized design of biological systems. Considering its huge population, biodiversity, and natural resources, Indonesia could play an important role in shaping the future of synthetic biology towards a sustainable bio-circular economy. Here, we provide an overview of synthetic biology development in Indonesia, especially on exploring the potential of our biodiversity. We also discuss some potentials of synthetic biology in solving national issues. Furthermore, we also provide the projection and future landscape of synthetic biology development in Indonesia. In addition, we briefly explain the potential challenges that may arise during the development. © 2023 The Authors

关键词： Indonesia Mega biodiversity Synbio development Synthetic biology