检索结果-内蒙古大学图书馆

The classification of stages of epiretinal membrane using convolutional neural network on optical coherence tomography image

引用

Methods (San Diego, Calif.) 2023年 214卷 28-34页

作者： Che-Lun Hung Keng-Hung Lin Yu-Kai Lee Dariusz Mrozek Yin-Te Tsai Chun-Hsien Lin Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taiwan ROC Computer Science and Communication Engineering Providence University Taiwan ROC. Electronic address: clhung@nycu.edu.tw. Department of Ophthalmology Taichung Veterans General Hospital Taiwan ROC. Electronic address: linkh@vghtc.gov.tw. Department of Computer Science and Information Engineering Providence University Taiwan ROC. Electronic address: s1091906@gm.pu.edu.tw. Department of Applied Informatics Silesian University of Technology Poland. Electronic address: dariusz.mrozek@polsl.pl. Computer Science and Communication Engineering Providence University Taiwan ROC. Electronic address: yttsai@pu.edu.tw. Department of Ophthalmology Taichung Veterans General Hospital Taiwan ROC. Electronic address: linchunhsien@vghtc.gov.tw.

BACKGROUND AND OBJECTIVE:The gold standard for diagnosing epiretinal membranes is to observe the surface of the internal limiting membrane on optical coherence tomography images. The stages of the epiretinal membrane are used to decide the condition of the health of the membrane. The stages are not detected because some of them are similar. To accurately classify the stages, a deep-learning technology can be used to improve the classification accuracy. METHODS:A combinatorial fusion with multiple convolutional neural networks (CNN) algorithms are proposed to enhance the accuracy of a single image classification model. The proposed method was trained using a dataset of 1947 optical coherence tomography images diagnosed with the epiretinal membrane at the Taichung Veterans General Hospital in Taiwan. The images consisted of 4 stages; stages 1, 2, 3, and 4. RESULTS:The overall accuracy of the classification was 84%. The combination of five and six CNN models achieves the highest testing accuracy (85%) among other combinations, respectively. Any combination with a different number of CNN models outperforms any single CNN algorithm working alone. Meanwhile, the accuracy of the proposed method is better than ophthalmologists with years of clinical experience. CONCLUSIONS:We have developed an efficient epiretinal membrane classification method by using combinatorial fusion with CNN models on optical coherence tomography images. The proposed method can be used for screening purposes to facilitate ophthalmologists making the correct diagnoses in general medical practice.

关键词： Classification Combintorial Fusion Convolutional Neural Network Epiretinal Membrane Optical Coherence Tomography

来源：评论

学校读者我要写书评

暂无评论

YAQQ: Yet Another Quantum Quantizer - Design Space Exploration of Quantum Gate Sets using Novelty Search

arXiv

引用

arXiv 2024年

作者： Sarkar, Aritra Kundu, Akash Steinberg, Matthew Mishra, Sibasish Fauquenot, Sebastiaan Acharya, Tamal Miszczak, Jaroslaw A. Feld, Sebastian Quantum Intelligence research team Quantum Machine Learning research group Quantum Computing division QuTech Netherlands Department of Quantum & Computer Engineering Delft University of Technology Netherlands Joint Doctoral School Silesian University of Technology Gliwice Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland QTF Centre of Excellence Department of Physics University of Helsinki Finland

The standard model of quantum computation is based on quantum circuits, where the number and quality of the quantum gates composing the circuit influence the runtime and fidelity of the computation. The fidelity of the decomposition of quantum algorithms, represented as unitary matrices, to bounded depth quantum circuits depends strongly on the set of gates available for the decomposition routine. To investigate this dependence, we explore the design space of discrete quantum gate sets and present a software tool for comparative analysis of quantum processing units and control protocols based on their native gates. The evaluation is conditioned on a set of unitary transformations representing target use cases on the quantum processors. The cost function considers three key factors: (i) the statistical distribution of the decomposed circuits’ depth, (ii) the statistical distribution of process fidelities for the approximate decomposition, and (iii) the relative novelty of a gate set compared to other gate sets in terms of the aforementioned properties. The developed software, called YAQQ (Yet Another Quantum Quantizer), enables the discovery of an optimized set of quantum gates through this tunable joint cost function. To identify these gate sets, we use the novelty search algorithm, circuit decomposition techniques (like Solovay-Kitaev, Cartan, and quantum Shannon decomposition), and stochastic optimization to implement YAQQ within the Qiskit quantum simulator environment. YAQQ exploits reachability tradeoffs conceptually derived from quantum algorithmic information theory. Our results demonstrate the pragmatic application of identifying gate sets that are advantageous to popularly used quantum gate sets in representing quantum algorithms. Consequently, we demonstrate pragmatic use cases of YAQQ in comparing transversal logical gate sets in quantum error correction codes, designing optimal quantum instruction sets, and compiling to specific quantum processors. © 202

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization

arXiv

引用

arXiv 2022年

作者： Peng, Chong Liu, Yang Chen, Yongyong Wu, Xinxin Cheng, Andrew Kang, Zhao Chen, Chenglizhao Cheng, Qiang College of Computer Science and Technology Qingdao University China The College of Computer Science Harbin Institute of Technology The School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Computer Science University of Kentucky Department of Statistics and Applied Probability University of California Santa Barbara United States The Institute of Biomedical Informatics University of Kentucky

In this paper, we propose a novel nonconvex approach to robust principal component analysis for HSI denoising, which focuses on simultaneously developing more accurate approximations to both rank and column-wise sparsity for the low-rank and sparse components, respectively. In particular, the new method adopts the log-determinant rank approximation and a novel 2,log norm, to restrict the local low-rank or column-wisely sparse properties for the component matrices, respectively. For the 2,log-regularized shrinkage problem, we develop an efficient, closed-form solution, which is named 2,log-shrinkage operator. The new regularization and the corresponding operator can be generally used in other problems that require column-wise sparsity. Moreover, we impose the spatial-spectral total variation regularization in the log-based nonconvex RPCA model, which enhances the global piece-wise smoothness and spectral consistency from the spatial and spectral views in the recovered HSI. Extensive experiments on both simulated and real HSIs demonstrate the effectiveness of the proposed method in denoising HSIs. Copyright © 2022, The Authors. All rights reserved.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Location Functions for Self-stabilizing Byzantine Tolerant Swarms 1

引用

23rd International Symposium on Stabilization, Safety, and Security of Distributed Systems, SSS 2021

作者： Ashkenazi, Yotam Dolev, Shlomi Kamei, Sayaka Katayama, Yoshiaki Ooshita, Fukuhito Wada, Koichi Department of Computer Science Ben-Gurion University of the Negev Beersheba Israel Graduate School of Advanced Science and Engineering Hiroshima University Higashihiroshima Japan Graduate School of Engineering Nagoya Institute of Technology Nagoya Japan Graduate School of Science and Technology Nara Institute of Science and Technology Ikoma Japan Department of Applied Informatics Faculty of Science and Engineering Hosei University Koganei Japan

ISBN: (数字)9783030910815

ISBN: (纸本)9783030910808

This paper proposes a novel framework to realize self-stabilizing Byzantine tolerant swarms. In this framework, non-Byzantine robots execute tasks while satisfying location functions, that is, the robots use a policy for their location choice, which restricts their location to satisfy the functions. We give a general Byzantine-resilient self-stabilizing algorithm based on the location function, and then provide an efficient implementation of the self-stabilizing algorithms for special classes of tasks, called polynomial-based tasks and shape-based tasks. We also demonstrate the usefulness of the proposed framework by implementing typical tasks of robots. © 2021, Springer Nature Switzerland AG.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Electrically Programmable Non-Volatile Silicon Photonic Content Addressable Memory (CAM) Cell

Electrically Programmable Non-Volatile Silicon Photonic Cont...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Chuanyu Lian Hongyi Sun Yi-Siou Huang Steven A. Vitale Juejun Hu Ichiro Takeuchi Nathan Youngblood Christos Vagionas Carlos A. Ríos Ocampo Department of Materials Science & Engineering University of Maryland College Park MD USA Institute for Research in Electronics and Applied Physics University of Maryland College Park MD USA Advanced Materials and Microsystems Group MIT Lincoln Laboratory Lexington MA USA Department of Materials Science & Engineering MIT Cambridge MA USA Department of Physics Quantum Materials Center University of Maryland College Park MD USA Electrical & Computer Engineering Department The University of Pittsburgh Pittsburgh PA USA Department of Informatics Center for Interdisciplinary Research and Innovation Aristotle University of Thessaloniki Thessaloniki Greece

We experimentally demonstrate the first electrically programmable, non-volatile silicon photonic content addressable memory cell using Sb 2 Se3 phase change material on microring resonators, opening the path for light... 详细信息

ISBN: (纸本)9798350369311

关键词： Phase change materials Associative memory Nonvolatile memory Lasers and electrooptics Silicon photonics Table lookup Resonators Electro-optical waveguides

来源：评论

学校读者我要写书评

暂无评论

AlGaAs soliton microcombs at room temperature

AlGaAs soliton microcombs at room temperature

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Lue Wu Weiqiang Xie Chao Xiang Lin Chang Yan Yu Hao-Jing Chen Yoshihisa Yamamoto John E. Bowers Kerry J. Vahala Myoung-Gyun Suh T. J. Watson Laboratory of Applied Physics California Institute of Technology Pasadena CA USA Department of Electrical and Computer Engineering University of California Santa Barbara Santa Barbara CA USA Physics & Informatics Laboratories NTT Research Inc. Sunnyvale CA USA

Soliton generation in AlGaAs microresonators at room temperation is reported for the first time. The destabilizing thermo-optic effect is shown to instead provide stability for high soliton repetition rates. The optic... 详细信息

ISBN: (纸本)9781957171258

关键词： Dielectric microcavities Frequency combs Microresonators Mode locking Q factor Thermo optic effects

来源：评论

学校读者我要写书评

暂无评论

Security Protection with Dynamic Assigned Address Mechanism in Industrial Control Systems

Security Protection with Dynamic Assigned Address Mechanism ...

引用

2020 ACM International Conference on Intelligent Computing and its Emerging Applications, ICEA 2020

作者： Liu, Chuan-Gang Wu, Chin-Jui Liu, I-Hsien Wu, Chi-Che Li, Jung-Shian Department of Applied Informatics and Multimedia Chia-Nan University of Pharmacy and Science Tainan Taiwan Department of Electrical Engineering Institute of Computer and Communication Engineering National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9781450383042

In recent years, industrial control systems (ICS) are widely used in many occasions, which makes information security of ICS an important issue. This study discusses the communication and management on ICS to make ICS intelligent. We proposed a method to avoid attack of communication, and elaborated the means of our proposed communication in which all communication parties communicate with each other without transmitting IP information. Moreover, as an intelligent ICS, the transmission module we design can detect anomaly in the system and change the transmission rule based on our algorithm, also known as a type of moving target defense. Therefore, we proposed the scheme to improve the transmission security in ICS. The experimental results also show that our scheme can be feasible in ICS. © 2020 ACM.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Morphosyntactic Probing of Multilingual BERT Models

arXiv

引用

arXiv 2023年

作者： Acs, Judit Hamerlik, Endre Schwartz, Roy Smith, Noah A. Kornai, Andras Budapest Hungary Budapest University of Technology and Economics Budapest Hungary Department of Applied Informatics Comenius University in Bratislava Faculty of Mathematics Physics and Informatics Bratislava Slovakia Hebrew University of Jerusalem Jerusalem Israel Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States Allen Institute for Artificial Intelligence SeattleWA United States

We introduce an extensive dataset for multilingual probing of morphological information in language models (247 tasks across 42 languages from 10 families), each consisting of a sentence with a target word and a morphological tag as the desired label, derived from the Universal Dependencies treebanks. We find that pre-trained Transformer models (mBERT and XLM-RoBERTa) learn features that attain strong performance across these tasks. We then apply two methods to locate, for each probing task, where the disambiguating information resides in the input. The first is a new perturbation method that "masks" various parts of context;the second is the classical method of Shapley values. The most intriguing finding that emerges is a strong tendency for the preceding context to hold more information relevant to the prediction than the following context. © 2023, CC BY.

关键词： Perturbation techniques

来源：评论

学校读者我要写书评

暂无评论

Differential Privacy Protection with Group Onion Routing based on AI-based URL Classification

Differential Privacy Protection with Group Onion Routing bas...

引用

2020 ACM International Conference on Intelligent Computing and its Emerging Applications, ICEA 2020

作者： Liu, I-Hsien Chang, Yung-Lin Li, Jung-Shian Liu, Chuan-Gang Department of Electrical Engineering Institute of Computer and Communication Engineering National Cheng Kung University Tainan Taiwan Department of Applied Informatics and Multimedia Chia-Nan University of Pharmacy and Science Tainan Taiwan

ISBN: (纸本)9781450383042

Due to the rapid spread of tablet computers, smartphones, and other mobile information devices, wireless communication technology is fully developed and deployed widely. Mobile Internet access has been a main and important way to communicate the world in daily and it privacy protection also catches much attentions. The Onion Router, better known as Tor, is a technique for anonymous communication over internet without regional restrictions for privacy protection. Apart from this, Tor can reach sites that normal search engine cannot search. As the opinion of Tor, the transmitted data has been encrypted layer by layer, just like onion, before it reaching server. Our research proposed a system predicting URL's category with the use of machine learning technique before visiting. According to the category prediction, we represent different privacy level with three kinds of RSA key lengths on onion routing. Depending on various situations, our system can obtain the balance between security and time cost. Hence, our proposed scheme can make onion routing more flexible and efficiently. © 2020 ACM.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Indoor 3D Visible Light Positioning Analysis with Channel Estimation Errors

Indoor 3D Visible Light Positioning Analysis with Channel Es...

引用

International Conference on Systems, Signals and Image Processing, IWSSIP

作者： Dimitrios Bozanis Nikos G. Evgenidis Vasilis K. Papanikolaou Pavlos S. Bouzinis Sotiris A. Tegos Alexis A. Dowhuszko Panagiotis D. Diamantoulakis George K. Karagiannidis Department of Electrical and Computer Engineering Wireless Communications and Information Processing Group (WCIP) Aristotle University of Thessaloniki Thessaloniki Greece Institute for Digital Communications (IDC) Friedrich-Alexander Universitat Erlangen-Nurnberg (FAU) Germany Department of Applied Informatics University of Macedonia Thessaloniki Greece Department of Communications and Networking Aalto University Espoo Finland Cyber Security Systems and Applied AI Research Center Lebanese American University (LAU) Lebanon

Since radio-frequency signals are affected signifi-cantly by multipath fading, the localization accuracy they offer cannot meet the sixth generations (6G) demanding specifications. On the other hand, visible light positioning (VLP) has emerged as a low cost alternative that takes into account the highly deterministic channel characteristics of visible light communications to provide cm-level accuracy provided that the investigated spaces are adequately covered by LEDs. However, imperfect channel state information and modeling can lead to positioning errors. In this paper, localization accuracy is quantified in terms of channel estimation errors via low complexity lateration algorithm. The channel estimation errors can be caused by a variety of issues and the provided analysis is general so that it can be easily applied to a plethora of applications. Finally, Monte Carlo simulations validate the proposed method and offer valuable insights for the design and performance bounds of VLP systems.

关键词：

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：