检索结果-内蒙古大学图书馆

Kidney Tumor Detection and Classification Based on Deep Learning Approaches: A New Dataset in CT Scans

Journal of Healthcare engineering 2022年第1期2022卷 3861161页

作者： Alzu'Bi, Dalia Abdullah, Malak Hmeidi, Ismail Alazab, Rami Gharaibeh, Maha El-Heis, Mwaffaq Almotairi, Khaled H. Forestiero, Agostino Hussein, Ahmad Mohdaziz Abualigah, Laith Department of Computer Information Systems Jordan University of Science and Technology Irbid2210 Jordan Department of General Surgery and Urology University of Science and Technology Irbid22110 Jordan Department of Diagnostic and Interventional Radiology Faculty of Medicine Jordan University of Science and Technology Irbid2210 Jordan Computer Engineering Department Computer and Information Systems College Umm Al-Qura University Makkah21955 Saudi Arabia Institute for High Performance Computing and Networking CNR CS Rende Italy Deanship of E-Learning and Distance Education Umm Al-Qura University Makkah21955 Saudi Arabia Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Faculty of Information Technology Middle East University Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia

Kidney tumor (KT) is one of the diseases that have affected our society and is the seventh most common tumor in both men and women worldwide. The early detection of KT has significant benefits in reducing death rates, producing preventive measures that reduce effects, and overcoming the tumor. Compared to the tedious and time-consuming traditional diagnosis, automatic detection algorithms of deep learning (DL) can save diagnosis time, improve test accuracy, reduce costs, and reduce the radiologist's workload. In this paper, we present detection models for diagnosing the presence of KTs in computed tomography (CT) scans. Toward detecting and classifying KT, we proposed 2D-CNN models;three models are concerning KT detection such as a 2D convolutional neural network with six layers (CNN-6), a ResNet50 with 50 layers, and a VGG16 with 16 layers. The last model is for KT classification as a 2D convolutional neural network with four layers (CNN-4). In addition, a novel dataset from the King Abdullah University Hospital (KAUH) has been collected that consists of 8,400 images of 120 adult patients who have performed CT scans for suspected kidney masses. The dataset was divided into 80% for the training set and 20% for the testing set. The accuracy results for the detection models of 2D CNN-6 and ResNet50 reached 97%, 96%, and 60%, respectively. At the same time, the accuracy results for the classification model of the 2D CNN-4 reached 92%. Our novel models achieved promising results;they enhance the diagnosis of patient conditions with high accuracy, reducing radiologist's workload and providing them with a tool that can automatically assess the condition of the kidneys, reducing the risk of misdiagnosis. Furthermore, increasing the quality of healthcare service and early detection can change the disease's track and preserve the patient's life. © 2022 Dalia Alzu'bi et al.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Stability analysis of MHD Jeffery–Hamel flow using artificial neural network

引用

International Journal of Thermofluids 2024年 24卷

作者： Ullah, Hakeem Alqahtani, Aisha M. Fiza, Mehreen Ullah, Kashif Shoaib, Muhmmad Khan, Ilyas Jan, Aasim Ullah Omer, Abdoalrahman S.A. Department of Mathematics Abdul Wali Khan University Mardan23200 Pakistan Department of Mathematical Sciences College of Science Princess Nourah bint Abdulrahman University P. O. Box 84428 Riyadh11671 Saudi Arabia Yuan Ze University AI Centre Taoyun320 Taiwan Department of Mathematics College of Science Al-Zulfi Majmaah University Al-Majmaah11952 Saudi Arabia Department of Mathematics Saveetha School of Engineering SIMATS Tamil Nadu Chennai India Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan Al-Ayen Research Center Al-Ayen University Iraq Department of Mathematics and Statitics Bacha Khan University Charsadda Pakistan Department of Mathematics College of Education Al-Fasher University Sudan Department of Information System College of Computer and Information Sciences Majmaah University Al-Majmaah11952 Saudi Arabia

The current research explores the useful impact of artificial neural networks (ANN) back-propagation along Levenberg-Marquardt Method (ANN-BLMM), for findng the influence of dimensionless numbers on the flow distribution pertaining magnetohydrodynamics (MHD) Jeffery–Hamel fluid amid two plates which are enclined at angles 2α. We have employed a numerical approach, ANN-BLMM to assess various aspects of our data, including testing, training, validation, Mean Square Errors (MSE), performance, and fitting. The methodology being used has been tested and validated through comparison with other results obtain numerically, showing extreme level of accuracy. Moreover, we have confirmed our findings through error histograms and regression tests. We used OHAM for the data set. Furthermore, we have also explored the influence of Reynolds number (R) on both flow and pressure distribution, visually representing our findings through graphical analysis. We have discussed about the nature and variations of velocity profiles within MHD Jefery–Hamel flow (MHDJHF), taking into account various values of Ha and Re in both convergent and divergent channels. It was discovered that a significant stabilizing influence of an increase in the magnetic field intensity was observed for both diverging and converging channel geometries and as the Hartman numbers rise, so does the fluid velocity. The absolute error is reduced to 10–2 to 10–6. © 2024 The Author(s)

关键词： Reynolds number

来源：评论

学校读者我要写书评

暂无评论

A Tunable Transition Metal Dichalcogenide Entangled Photon-Pair Source

arXiv

引用

arXiv 2023年

作者： Weissflog, Maximilian A. Fedotova, Anna Tang, Yilin Santos, Elkin A. Laudert, Benjamin Shinde, Saniya Abtahi, Fatemeh Afsharnia, Mina Pérez, Inmaculada Pérez Ritter, Sebastian Qin, Hao Janousek, Jiri Shradha, Sai Staude, Isabelle Saravi, Sina Pertsch, Thomas Setzpfandt, Frank Lu, Yuerui Eilenberger, Falk Institute of Applied Physics Abbe Center of Photonics Friedrich Schiller University Jena Albert-Einstein-Straße 15 Jena07745 Germany Max Planck School of Photonics Hans-Knöll-Straße 1 Jena07745 Germany Institute of Solid State Physics Friedrich Schiller University Jena Helmholtzweg 3 Jena07743 Germany School of Engineering College of Science and Computer Science The Australian National University CanberraACT Australia Australian Research Council Centre of Excellence for Quantum Computation and Communication Technology The Australian National University CanberraACT Australia Institute for Condensed Matter Physics Technical University of Darmstadt Hochschulstraße. 6-8 Darmstadt64289 Germany Fraunhofer Institute for Applied Optics and Precision Engineering IOF Albert-Einstein-Straße 7 Jena07745 Germany

Entangled photon-pair sources are at the core of quantum applications like quantum key distribution, sensing, and imaging. Operation in space-limited and adverse environments such as in satellite-based and mobile communication requires robust entanglement sources with minimal size and weight requirements. Here, we meet this challenge by realizing a cubic micrometer scale entangled photon-pair source in a 3R-stacked transition metal dichalcogenide crystal. Its crystal symmetry enables the generation of polarization-entangled Bell states without additional components and provides tunability by simple control of the pump polarization. Remarkably, generation rate and state tuning are decoupled, leading to equal generation efficiency and no loss of entanglement. Combining transition metal dichalcogenides with monolithic cavities and integrated photonic circuitry or using quasi-phasematching opens the gate towards ultrasmall and scalable quantum devices. Copyright © 2023, The Authors. All rights reserved.

关键词： Crystal symmetry

来源：评论

学校读者我要写书评

暂无评论

Closed-looped sensing and stimulation system for Parkinson's disease early diagnosis and rehabilitation

引用

Smart Health 2022年 26卷

作者： Cai, Yi Qian, Xiaoye Li, Qin Lin, Feng Huang, Ming-Chun Department of Electrical Computer and Systems Engineering Case Western Reserve University Cleveland OH United States Department of Data and Computational Science Duke Kunshan University Jiangsu 215316 China ZJU-Hangzhou Global Scientific and Technological Innovation Center School of Cyber Science and Technology Zhejiang University Zhejiang 310058 China Suzhou Huanmu Intelligence Technology Co. Ltd. Jiangsu China

Parkinson's disease (PD) patients are involved in motor dysfunctions and gait issues. The absence of long-term reliable gait rehabilitations could result in poor gait function, gait deficits, and locomotion problems. Meanwhile, PD patients usually face significant challenges to complete the rehabilitation programs effectively without a specialized gait laboratory or after discharge from the hospital. This paper presents a closed-loop sensing and computing system to facilitate long-term medical care for PD patients. The proposed system consists of wearable sensing, data streaming, online data processing, real-time auditory stimulation for PD gait rehabilitation, and data services for medical providers. To address the potential issues of user-friendly and comforts, we implemented a wrapped shoe based plantar pressure sensing device for under-feet pressure data collection. Afterward, quantitative measurements of gait are fulfilled through online data streaming and processing architecture. Physical therapy is generally preferred for PD rehabilitation because it provides a more significant benefit superior to the drugs. Hence, applications of gait activity recognition and closed-loop stimulation are proposed to build a reliable closed-loop system and support self-contained training. To evaluate the proposed system, we conduct experiments with three gait and PD related datasets. It broads Parkinson's gait health care prospects that make long-term PD rehabilitation possible in community-living environment. © 2022 Elsevier Inc.

关键词： Data streaming processing Gait rehabilitation Rhythmic auditory stimulation Wearable sensing

来源：评论

学校读者我要写书评

暂无评论

Topological edge states at singular points in non-Hermitian plasmonic systems

arXiv

引用

arXiv 2021年

作者： Huang, Yin Shen, Yuecheng Veronis, Georgios Department of Optoelectrics Information Science and Engineering School of Physics and Electronics Central South University Hunan Changsha410012 China State Key Laboratory of Optoelectronic Materials and Technologies School of Electronics and Information Technology Sun Yat-Sen University Guangdong Guangzhou510275 China School of Electrical Engineering and Computer Science Louisiana State University Baton RougeLA70803 United States Center for Computation and Technology Louisiana State University Baton RougeLA70803 United States

We introduce non-Hermitian plasmonic waveguide-cavity systems with topological edge states (TESs) at singular points. The compound unit cells of the structures consist of metal-dielectric-metal (MDM) stub resonators side-coupled to an MDMwaveguide. We show that we can realize both a TES and an exceptional point at the same frequency when a proper amount of loss is introduced into a finite three-unit-cell structure. We also show that the finite structure can exhibit both a TES and a spectral singularity when a proper amount of gain is introduced into the structure. In addition, we show that we can simultaneously realize a unidirectional spectral singularity and a TES when proper amounts of loss and gain are introduced into the structure. We finally show that this singularity leads to extremely high sensitivity of the reflected light intensity to variations of the refractive index of the active materials in the structure. TESs at singular points could potentially contribute to the development of singularity-based plasmonic devices with enhanced performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Plasmonics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Routing Protocol for Underwater Wireless Sensor Network Based on AUV 1st

Adaptive Routing Protocol for Underwater Wireless Sensor Net...

引用

1st EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2019

作者： Ding, Yuying Li, Cheng Hao, Kun Du, Xiujuan Zhao, Lu Liu, Qi School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China School of Computer Science and Technology Qinghai Normal University Qinghai810008 China Computation Center Tianjin Chengjian University Tianjin300384 China

ISBN: (纸本)9783030229672

Underwater Wireless Sensor Networks (UWSNs) have the characteristics of high energy consumption, low transmission rate, and narrow bandwidth. How to extend the lifespan of UWSNs is a research hotspot of underwater routing protocols. An adaptive routing protocol (ARPA) based on autonomous underwater vehicle (AUV) is proposed in this paper. In the phase of network layering, ARPA takes AUV as the sink node to dynamically layer the network. In the data transmission stage, the next hop forwarding node that meets the requirements is selected based on the horizontal and vertical mechanism. In this paper, the ARPA is verified by the network simulator NS-3. The simulation results show that compared with the existing underwater routing protocols, the ARPA not only guarantees the efficient and stable data transmission rate but also reduces the network delay and improves the energy utilization rate. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2019.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Pretty good measurement for bosonic Gaussian ensembles

arXiv

引用

arXiv 2023年

作者： Mishra, Hemant K. Lami, Ludovico Mandayam, Prabha Wilde, Mark M. School of Electrical and Computer Engineering Cornell University IthacaNY14850 United States Hearne Institute for Theoretical Physics Department of Physics and Astronomy Center for Computation and Technology Louisiana State University Baton RougeLA70803 United States Institute of Theoretical Physics and IQST Universität Ulm Albert-Einstein-Allee Ulm11D-89069 Germany QuSoft Science Park 123 Amsterdam1098 XG Netherlands Korteweg–de Vries Institute for Mathematics University of Amsterdam Science Park 105-107 Amsterdam1098 XG Netherlands Institute for Theoretical Physics University of Amsterdam Science Park 904 Amsterdam1098 XH Netherlands Center for Quantum Information Communication and Computing IIT Madras Chennai600036 India Department of Physics Indian Institute of Technology Madras Chennai600036 India

The pretty good measurement is a fundamental analytical tool in quantum information theory, giving a method for inferring the classical label that identifies a quantum state chosen probabilistically from an ensemble. Identifying and constructing the pretty good measurement for the class of bosonic Gaussian states is of immediate practical relevance in quantum information processing tasks. Holevo recently showed that the pretty good measurement for a bosonic Gaussian ensemble is a bosonic Gaussian measurement that attains the accessible information of the ensemble [IEEE Trans. Inf. Theory, 66(9):5634–564, 2020]. In this paper, we provide an alternate proof of Gaussianity of the pretty good measurement for a Gaussian ensemble of multimode bosonic states, with a focus on establishing an explicit and efficiently computable Gaussian description of the measurement. We also compute an explicit form of the mean square error of the pretty good measurement, which is relevant when using it for parameter estimation. Generalizing the pretty good measurement is a quantum instrument, called the pretty good instrument. We prove that the post-measurement state of the pretty good instrument is a faithful Gaussian state if the input state is a faithful Gaussian state whose covariance matrix satisfies a certain condition. Combined with our previous finding for the pretty good measurement and provided that the same condition holds, it follows that the expected output state is a faithful Gaussian state as well. In this case, we compute an explicit Gaussian description of the post-measurement and expected output states. Our findings imply that the pretty good instrument for bosonic Gaussian ensembles is no longer merely an analytical tool, but that it can also be implemented experimentally in quantum optics laboratories. Copyright © 2023, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Designing Environments Conducive to Interpretable Robot Behavior

arXiv

引用

arXiv 2020年

作者： Kulkarni, Anagha Sreedharan, Sarath Keren, Sarah Chakraborti, Tathagata Smith, David E. Kambhampati, Subbarao Dept of Computer Science Arizona State University United States School of Engineering and Applied Sciences Harvard University Center for Research on Computation and Society United States IBM Research

Designing robots capable of generating interpretable behavior is essential for effective human-robot collaboration. This requires robots to be able to generate behavior that aligns with human expectations but exhibiting such behavior in arbitrary environments could be quite expensive for robots, and in some cases, the robot may not even be able to exhibit expected behavior. However, in structured environments (like warehouses, restaurants, etc.), it may be possible to design the environment so as to boost the interpretability of a robot’s behavior or to shape the human’s expectations of the robot’s behavior. In this paper, we investigate the opportunities and limitations of environment design as a tool to promote a particular type of interpretable behavior – known in the literature as explicable behavior. We formulate a novel environment design framework that considers design over multiple tasks and over a time horizon. In addition, we explore the longitudinal effect of explicable behavior and the trade-off that arises between the cost of design and the cost of generating explicable behavior over an extended time horizon. Copyright © 2020, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Opportunities for machine learning in scientific discovery

arXiv

引用

arXiv 2024年

作者： Vinuesa, Ricardo Rabault, Jean Azizpour, Hossein Bauer, Stefan Brunton, Bingni W. Elofsson, Arne Jarlebring, Elias Kjellström, Hedvig Markidis, Stefano Marlevi, David Cinnella, Paola Brunton, Steven L. FLOW Engineering Mechanics KTH Royal Institute of Technology Stockholm Sweden Stockholm Sweden IT Department Norwegian Meteorological Institute Oslo0313 Norway KTH Royal Institute of Technology Stockholm Sweden TUM School of Computation Information and Technology Technical University Munich Munich Germany Helmholtz AI Helmholtz Center Munich Munich Germany Department of Biology University of Washington SeattleWA98195 United States Dept. of Biochemistry and Biophysics Science for Life Laboratory Stockholm University Solna171 21 Sweden Dept. Mathematics KTH Royal Institute of Technology Stockholm100 44 Sweden Department of Computer Science KTH Royal Institute of Technology Stockholm Sweden Dept. Molecular Medicine and Surgery Karolinska Institutet Stockholm171 77 Sweden Inst. for Medical Engineering and Science Massachusetts Institute of Technology CambridgeMA02139 United States Institut Jean le Rond D’Alembert Sorbonne Université France Department of Mechanical Engineering University of Washington SeattleWA98195 United States

Technological advancements have substantially increased computational power and data availability, enabling the application of powerful machine-learning (ML) techniques across various fields. However, our ability to leverage ML methods for scientific discovery, i.e. to obtain fundamental and formalized knowledge about natural processes, is still in its infancy. In this review, we explore how the scientific community can increasingly leverage ML techniques to achieve scientific discoveries. We observe that the applicability and opportunity of ML depends strongly on the nature of the problem domain, and whether we have full (e.g., turbulence), partial (e.g., computational biochemistry), or no (e.g., neuroscience) a-priori knowledge about the governing equations and physical properties of the system. Although challenges remain, principled use of ML is opening up new avenues for fundamental scientific discoveries. Throughout these diverse fields, there is a theme that ML is enabling researchers to embrace complexity in observational data that was previously intractable to classic analysis and numerical investigations. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Dipole-matter interactions governed by the asymmetry of Maxwell equations

arXiv

引用

arXiv 2023年

作者： Zhong, Yuhan Wang, Chan Bian, Chenxu Chen, Xuhuinan Chen, Jialin Zhu, Xingjian Hu, Hao Low, Tony Chen, Hongsheng Zhang, Baile Lin, Xiao Interdisciplinary Center for Quantum Information State Key Laboratory of Extreme Photonics and Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China International Joint Innovation Center Key Lab. of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang The Electromagnetics Academy at Zhejiang University Zhejiang University Haining314400 China Jinhua Institute of Zhejiang University Zhejiang University Jinhua321099 China Department of Electrical and Computer Engineering Technion-Israel Institute of Technology Haifa32000 Israel School of Physics Zhejiang University Hangzhou310027 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States Department of Physics University of Minnesota MinneapolisMN55455 United States Shaoxing Institute of Zhejiang University Zhejiang University Shaoxing312000 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore637371 Singapore Centre for Disruptive Photonic Technologies Nanyang Technological University Singapore637371 Singapore

Directionally molding the near-field and far-field radiation lies at the heart of nanophotonics and is crucial for applications such as on-chip information processing and chiral quantum networks. The most fundamental model for radiating structures is a dipolar source located inside a homogeneous matter. However, the influence of matter on the directionality of dipolar radiation is oftentimes overlooked, especially for the near-field radiation. We show that the dipole-matter interaction is intrinsically asymmetric and does not fulfill the duality principle, originating from the inherent asymmetry of Maxwell’s equations, i.e., electric charge and current are ubiquitous but their magnetic counterparts are non-existent to elusive. Moreover, we find that the asymmetric dipole-matter interaction could offer an enticing route to reshape the directionality of not only the near-field radiation but also the far-field radiation. As an example, both the near-field and far-field radiation directionality of Huygens dipole (located close to a dielectric-metal interface) would be reversed, if the dipolar position is changed from the dielectric region to the metal region. © 2023, CC BY.

关键词： Maxwell equations

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：