检索结果-内蒙古大学图书馆

Two fully automated data-driven 3D whole-breast segmentation strategies in MRI for MR-based breast density using image registration and U-Net with a focus on reproducibility

引用

Visual Computing for Industry,Biomedicine,and Art 2022年第1期5卷 303-314页

作者： Jia Ying Renee Cattell Tianyun Zhao Lan Lei Zhao Jiang Shahid M.Hussain Yi Gao H‑H.Sherry Chow Alison T.Stopeck Patricia A.Thompson Chuan Huang Department of Biomedical Engineering Stony Brook UniversityStony BrookNY 11794USA Department of Radiation Oncology Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA Department of Medicine Northside Hospital GwinnettLawrencevilleGA 30046USA Program of Public Health Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA Department of Radiology Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA Department of Biomedical Informatics Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA School of Biomedical Engineering Health Science CenterShenzhen UniversityShenzhen 518060China University of Arizona Cancer Center TucsonAZ 85719USA Department of Medicine Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA Stony Brook Cancer Center Stony Brook UniversityStony BrookNY 11794USA Department of Medicine Cedar Sinai CancerCedars Sinai Medical CenterLos AngelesCA 90048USA

Presence of higher breast density(BD)and persistence over time are risk factors for breast cancer.A quantitatively accurate and highly reproducible BD measure that relies on precise and reproducible whole-breast segmentation is *** this study,we aimed to develop a highly reproducible and accurate whole-breast segmentation algorithm for the generation of reproducible BD *** datasets of volunteers from two clinical trials were *** MR images were acquired on 3T Siemens Biograph mMR,Prisma,and Skyra using 3D Cartesian six-echo GRE sequences with a fat-water separation *** whole-breast segmentation strategies,utiliz-ing image registration and 3D U-Net,were *** segmentation was performed.A task-based analysis was performed:a previously developed MR-based BD measure,MagDensity,was calculated and assessed using automated and manual *** mean squared error(MSE)and intraclass correlation coefficient(ICC)between MagDensity were evaluated using the manual segmentation as a *** test-retest reproducibility of MagDensity derived from different breast segmentation methods was assessed using the difference between the test and retest measures(Δ_(2-1)),MSE,and *** results showed that MagDensity derived by the registration and deep learning segmentation methods exhibited high concordance with manual segmentation,with ICCs of 0.986(95%CI:0.974-0.993)and 0.983(95%CI:0.961-0.992),*** test-retest analysis,MagDensity derived using the regis-tration algorithm achieved the smallest MSE of 0.370 and highest ICC of 0.993(95%CI:0.982-0.997)when compared to other segmentation *** conclusion,the proposed registration and deep learning whole-breast segmentation methods are accurate and reliable for estimating *** methods outperformed a previously developed algorithm and manual segmentation in the test-retest assessment,with the registration exhibiting superior performance for highly reproducibl

关键词： Breast cancer Breast density Breast segmentation Image registration Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Development of Color Lighting Device to Indicate Subjective Palatability

A Development of Color Lighting Device to Indicate Subjectiv...

引用

IEEE/SICE International Symposium on System Integration

作者： Akira Kashihara Tomoyuki Yamaguchi Program in Empowerment Informatics Empowerment Informatics 1-1-1 Tennodai Tsukuba Ibaraki Japan Faculty of Engineering Information and Systems University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki Japan

ISBN: (数字)9781728166674

ISBN: (纸本)9781728166681

This study aims to realize a display subjective palatability device to facilitate emotional communication with family or friends at mealtime. Of late, the importance of eating together where family and friends gather and eat together is increasing. However, each member of the family or community eats separated foods at mealtimes. This situation weakens the community bonding because it becomes difficult for people to empathize with the subjective emotion. Therefore, this paper describes a novel device that can help in sharing the subjective palatability of humans who eat together. The proposed device makes humans perceive the subjective palatability of their friends who are eating by using an appropriate color of the LED. In the experiments, we have confirmed that the colors blue and orange expresses the color of subjective palatability, and the experiment of transmitting the subjective palatability of the proposed device using those colors was conducted to evaluate the accuracy and speed of meal communication.

关键词： Color Light emitting diodes Bonding Lighting Automobiles Heart Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

Understanding disposition decision-making for older adults as it occurs within the emergency department work system 66th

Understanding disposition decision-making for older adults a...

引用

66th International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2022

作者： Rutkowski, Rachel A. Pulia, Michael S. Salwei, Megan Loveless, Emma Jaeger, Lily Rawson, Michael Wust, Kathryn Hoonakker, Peter King, Barbara Shah, Manish N. Patterson, Brian W. Dáil, Paula V. W. Smith, Maureen Carayon, Pascale Werner, Nicole E. Department of Industrial and Systems Engineering University of Wisconsin-Madison United States Berbee Walsh Department of Emergency Medicine University of Wisconsin-Madison United States Center for Research and Innovation in Systems Safety Department of Anesthesiology Department of Biomedical Informatics Vanderbilt University Medical Center United States School of Nursing University of Wisconsin-Madison United States University of Wisconsin-Madison Health Sciences Patient and Family Advisory Council member United States University of Wisconsin-Madison School of Medicine and Public Health Departments of Population Health Sciences and Family Medicine and Community Health United States University of Wisconsin Institute of Clinical and Translational Research Health Innovation Program United States

来源：评论

学校读者我要写书评

暂无评论

SRBench++: Principled Benchmarking of Symbolic Regression With Domain-Expert Interpretation

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： de Franca, F.O. Virgolin, M. Kommenda, M. Majumder, M.S. Cranmer, M. Espada, G. Ingelse, L. Fonseca, A. Landajuela, M. Petersen, B. Glatt, R. Mundhenk, N. Lee, C.S. Hochhalter, J.D. Randall, D.L. Kamienny, P. Zhang, H. Dick, G. Simon, A. Burlacu, B. Kasak, Jaan Machado, Meera Wilstrup, Casper Cavaz, W.G.L. Federal University of ABC Santo Andre Brazil Evolutionary Intelligence group Centrum Wiskunde and Informatica Science Park Amsterdam Netherlands University of Applied Sciences Upper Austria Hagenberg Austria Computational Health Informatics Program Boston Children’s Hospital Harvard Medical School Boston USA Center for Computational Astrophysics Flatiron Institute and Department of Astrophysical Sciences of Princeton University USA LASIGE Faculdade de Ciências Universidade de Lisboa Lisboa Portugal Computational Engineering Division Lawrence Livermore National Laboratory Livermore USA Department of Mechanical Engineering University of Utah Utah USA Meta FAIR France Victoria University of Wellington School of Engineering and Computer Science New Zealand University of otago Department of Information Science New Zealand Institut für Angewandte Physik Universität TübingenMax Planck Institute for Intelligent Systems Tübingen Germany Abzu AI Orient Plads 1 Nordhavn Denmark

Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main promise of this approach is that it may return an interpretable model that can be insightful to users, while maintaining high accuracy. The current standard for benchmarking these algorithms is SRBench, which evaluates methods on hundreds of datasets that are a mix of real-world and simulated processes spanning multiple domains. At present, the ability of SRBench to evaluate interpretability is limited to measuring the size of expressions on real-world data, and the exactness of model forms on synthetic data. In practice, model size is only one of many factors used by subject experts to determine how interpretable a model truly is. Furthermore, SRBench does not characterize algorithm performance on specific, challenging sub-tasks of regression such as feature selection and evasion of local minima. In this work, we propose and evaluate an approach to benchmarking SR algorithms that addresses these limitations of SRBench by 1) incorporating expert evaluations of interpretability on a domain-specific task, and 2) evaluating algorithms over distinct properties of data science tasks. We evaluate 12 modern symbolic regression algorithms on these benchmarks and present an in-depth analysis of the results, discuss current challenges of symbolic regression algorithms and highlight possible improvements for the benchmark itself. Authors

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Canopy cover estimation based on support vector regression derived from Lidar & Landsat 8 OLI 40

Canopy cover estimation based on support vector regression d...

引用

40th Asian Conference on Remote Sensing: Progress of Remote Sensing Technology for Smart Future, ACRS 2019

作者： Hudjimartsu, Sahid Tampinongkol, Felliks Rudianto, Yoga Setiawan, Yudi Prasetyo, Lilik Budi Forests2020 Programme Environmental Analysis and Spatial Modelling Laboratory Department of Forest Resource Conservation Faculty of Forestry Bogor Agricultural University Bogor West Java Indonesia Geoinformatic of Informatics Engineering Study Program Faculty of Engineering and Science Ibn Khaldun University Jalan KH Soleh Iskandar KM 2 Tanah Sereal Bogor West Jawa Indonesia

Light detection and ranging (LiDAR) provides geospatial information with massive amounts of data to use in a variety of applications. Canopy cover percentage of tree crown is one application that is estimated through LiDAR data. This study aims to estimate a canopy cover derived from LiDAR used as reference data with multispectral Landsat 8 OLI. Statistical or machine learning approaches can be used to estimate a canopy cover. In statistical inference, the form of distribution chosen by the analyst and parameter is estimated from the data. This will be a problem in the construction function for the National scale, due to many ecosystems and then will have many functions for each ecosystem. Machine learning (ML) methods, in contrast, are various kinds of algorithms that are used to learn the mapping function or classification rules inductively, directly from the training data. ML can solve problems related to big data and global method and it will be used as a methodical approach to estimate canopy cover on the National scale. In this study, we use a support vector regression (SVR) as ML method to estimate the canopy cover. The estimated percentage of canopy cover will be used as one of the parameters to classify a forest. © 2020 40th Asian Conference on Remote Sensing, ACRS 2019: "Progress of Remote Sensing Technology for Smart Future". All rights reserved.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Over-Privileged Permissions: Using Technology and Design to Create Legal Compliance

SSRN

引用

SSRN 2020年

作者： Raymond, Anjanette Schubauer, Jonathan Madappa, Dhruv Program on Data Management and Information Governance Ostrom Workshop Department of Business Law and Ethics Indiana University Kelley School of Business Data Management and Information Governance Ostrom Workshop Center for Security and Privacy Department of Informatics Indiana University School of Informatics Computing & Engineering Indiana University School of of Informatics Computing & Engineering

Consumers in the mobile ecosystem can putatively protect their privacy with the use of application permissions. However, this requires the mobile device owners to understand permissions and their privacy implications. Yet, few consumers appreciate the nature of permissions within the mobile ecosystem, often failing to appreciate the privacy permissions that are altered when updating an app. Even more concerning is the lack of understanding of the wide use of third-party libraries, most which are installed with automatic permissions, that is permissions that must be granted to allow the application to function appropriately. Unsurprisingly, many of these third-party permissions violate consumers’ privacy expectations and thereby, become ‘over-privileged’ to the user. Consequently, an obscurity of privacy expectations between what is practiced by the private sector and what is deemed appropriate by the public sector is exhibited. Despite the growing attention given to privacy in the mobile ecosystem, legal literature has largely ignored the implications of mobile permissions. This article seeks to address this omission by analyzing the impacts of mobile permissions and the privacy harms experienced by consumers of mobile applications. The authors call for the review of industry self-regulation and the over-reliance upon simple notice and consent. Instead, the authors set out a plan for greater attention to be paid to socio-technical solutions, focusing on better privacy protections and technology embedded within the automatic permission-based application ecosystem. © 2020, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Dual UPQC to Mitigate Sag/Swell, Interruption, and Harmonics on Three Phase Low Voltage Distribution System

A Dual UPQC to Mitigate Sag/Swell, Interruption, and Harmoni...

引用

Vocational Education and Electrical engineering, International Conference on

作者： Amirullah Adiananda Ontoseno Penangsang Adi Soeprijanto Electrical Engineering Study Program Faculty of Engineering Universitas Bhayangkara Surabaya Surabaya Indonesia Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9781728174341

ISBN: (纸本)9781728174358

The Unified Power Quality Conditioner (UPQC) is a combination of a series active filter (SeAF) and a shunt active filter (ShAF) connected in parallel by a DC link capacitor. This device can mitigate power quality (PQ) problems i.e. sag/swell, harmonics, and unbalance on the source and load bus of threephase three-wire (3P3W) on low voltage distribution systems simultaneously. The disadvantage of UPQC is that it is unable to overcome the voltage interruption so that the source can not deliver power to the load. This paper proposes a dual UPQC model to overcome the voltage interruption on the source bus so that the load bus continues to get power supply. There are six disturbance cases i.e. sinusoidal supply-sag-non-linear load (SSag-NL-L), sinusoidal supply-swell-NL-L (S-Swell-NL-L), sinusoidal-interruption-NL-L (S-Inter-NL-L), distorted supplysag-NL-L load (D-Sag-NL-L), distorted supply-swell-NL-L (DSwell-NL-L), and distorted supply-interruption-NL-LL (DInter-NL-L). The proportional Integral (PI) method is used to control the SeAF and the ShAF in the dual UPQC circuit model. The simulation results show that in the D-Inter-NL-LL case, a Dual UPQC model can maintain a load voltage magnitude of 266.60 V (voltage drop only of 14%), higher compared to a Single UPQC model of 173.97 V (voltage drop of 43.88%). In the same case, a dual UPQC model is capable of resulting in an average total harmonics distortion (THD) of load voltage of 10.10%, lower compared to a single UPQC model of 26.70%.

关键词： Low voltage Simulation Power quality Harmonic analysis Integrated circuit modeling Power harmonic filters Load modeling

来源：评论

学校读者我要写书评

暂无评论

Kano Model Analysis of Android Apps Quality from End User's Preferences

引用

Journal of Physics: Conference Series 2021年第1期1737卷

作者： R A S Putra Priyanto Electronics and Informatics Engineering Education Postgraduate Program Yogyakarta State University Indonesia

This study aimed to explore the end user's preferences regarding the features of an android app by classifying them with the Kano Model. The list of features was based on ISO/IEC 25010 combined with Android Core App Quality Guidelines. This expert system android app which is named 'Pilih Media' is used to help teachers selecting learning media based on Anderson's theory of learning media selection. Respondents in this study were 50 teachers. Kano model was used in this study as a guideline in making questionnaires and also analyzing the data. From the study, it can be concluded that there are 17 features classified as the Attractive requirement category, six features classified as One-dimensional category, one feature classified as Must-be category, and five features classified as the Indifferent category. Overall, it seems that a lot of features have the potential to increase the end user's satisfaction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuned MobileNetV2 and VGG16 Algorithm for Fish Image Classification

Fine-Tuned MobileNetV2 and VGG16 Algorithm for Fish Image Cl...

引用

International Conference on informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Devi Fitrianah Kristien Margi Suryaningrum Noviyanti Tri Maretta Sagala Vina Ayumi Siew Mooi Lim Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Mathematics Statistics Department School of Computer Science Bina Nusantara University Jakarta Indonesia Informatics Engineering Program Faculty of Computer Science Universitas Mercu Buana Jakarta Indonesia Computer Science Department Faculty of Computing and Information Technology Tunku Abdul Rahman University College Kuala Lumpur Malaysia

ISBN: (纸本)9781665473286

Study on the identification and classification of fish is challenging and valuable because of its role in advancing the marine and agricultural fields. This research has benefits interms of monitoring fish populations and ecosystems in a particular area. Furthermore, this research helps monitor fish that are considered threatened or endangered so that it makes iteasier to map prohibited areas for fishing. This research aims to know performance of MobileNetV2 and VGG16 with parameter tuning process by identifying the value of batch size, epoch, learning rate, and optimizer for fish image dataset. The proposed research phase consists of five main stages, including experimental setup, dataset construction, dataset preprocessing, dataset training and modelling and evaluation. As the result, VGG16 obtained the highest accuracy value. For VGG16 without fine-tuning, the testing accuracy is 98.07%. For VGG16 with fine-tuning, the testing accuracy is 96.56%.

关键词： Training Biological system modeling Sociology Ecosystems Fish Statistics Monitoring

来源：评论

学校读者我要写书评

暂无评论

LoRaWAN Intelligent Outdoor Smart Street Lighting

LoRaWAN Intelligent Outdoor Smart Street Lighting

引用

IEEE International Conference on Communication, Networks and Satellite (ComNetSat)

作者： Pandapotan Siagian Erick Fernando Faculty of Informatics and Electrical Engineering Computer Engineering Study Program Del Institute of Technology North Sumatera Indonesia School of Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9780738125176

ISBN: (纸本)9781665418614

Nowadays, The roads have increased the number of streetlights for the roads vehicles/pedestrians, which raises investment and energy. Observations made to obtain most of the road lights are always active at night, even when there are no vehicles or pedestrians on the road. The problems that occur are the waste of energy sources that are used in streetlights. This research designs the concept of intelligent traffic flow based (LED) for energy optimization, maximum efficiency. This concept uses intelligent light architecture using the LoRaWAN Mesh network. The application of this concept offers system reliability, reduces costs, and makes user satisfaction. The results of this study are demonstrated by experimenting with comparing conventional LED lights. The proposed system, resulting in 33% to 62% energy savings depending on when the usage process in streetlights. Smart lighting LEDs with LoRaWAN provide a remote-control mechanism that can be dynamically adjusted based on environmental conditions, distance, and automatic motion.

关键词： Lighting Sensors Light emitting diodes Intelligent sensors Sensor systems Batteries Roads

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：