检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Rajendran, Praveen Kumar Mishra, Sumit Vecchietti, Luiz Felipe Har, Dongsoo Division of Future Vehicle KAIST Korea Republic of The Robotics Program KAIST Korea Republic of Data Science Group Institute for Basic Science Korea Republic of The CCS Graduate School of Mobility KAIST Korea Republic of

Relative camera pose estimation, i.e. estimating the translation and rotation vectors using a pair of images taken in different locations, is an important part of systems in augmented reality and robotics. In this paper, we present an end-to-end relative camera pose estimation network using a siamese architecture that is independent of camera parameters. The network is trained using the Cambridge Landmarks data with four individual scene datasets and a dataset combining the four scenes. To improve generalization, we propose a novel two-stage training that alleviates the need of a hyperparameter to balance the translation and rotation loss scale. The proposed method is compared with one-stage training CNN-based methods such as RPNet and RCPNet and demonstrate that the proposed model improves translation vector estimation by 16.11%, 28.88%, and 52.27% on the Kings College, Old Hospital, and St Marys Church scenes, respectively. For proving texture invariance, we investigate the generalization of the proposed method augmenting the datasets to different scene styles, as ablation studies, using generative adversarial networks. Also, we present a qualitative assessment of epipolar lines of our network predictions and ground truth poses. © 2022, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

ζ-QVAE: A Quantum Variational Autoencoder utilizing Regularized Mixed-state Latent Representations

arXiv

引用

arXiv 2024年

作者： Wang, Gaoyuan Warrell, Jonathan Emani, Prashant S. Gerstein, Mark Program in Computational Biology and Bioinformatics Yale University New HavenCT06520 United States Department of Molecular Biophysics and Biochemistry Yale University New HavenCT06520 United States Department of Computer Science Yale University New HavenCT06520 United States Department of Statistics & Data Science Yale University New HavenCT06520 United States Department of Biomedical Informatics & Data Science Yale University New HavenCT06520 United States NEC Laboratories America PrincetonNJ08540 United States

A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves compressing the original data to manageable dimensions while still representing essential information for downstream analysis. In classical machine learning, variational autoencoders (VAEs) facilitate efficient data compression, representation learning for subsequent tasks, and novel data generation. However, no model has been proposed that exactly captures all of these features for direct application to quantum data on quantum computers. Some existing quantum models for data compression lack regularization of latent representations, thus preventing direct use for generation and control of generalization. Others are hybrid models with only some internal quantum components, impeding direct training on quantum data. To bridge this gap, we present a fully quantum framework, ζ-QVAE, which encompasses all the capabilities of classical VAEs and can be directly applied for both classical and quantum data compression. Our model utilizes regularized mixed states to attain optimal latent representations. It accommodates various divergences for reconstruction and regularization. Furthermore, by accommodating mixed states at every stage, it can utilize the full-data density matrix and allow for a"global"training objective. Doing so, in turn, makes efficient optimization possible and has potential implications for private and federated learning. In addition to exploring the theoretical properties of ζ-QVAE, we demonstrate its performance on representative genomics and synthetic data. Our results consistently indicate that ζ-QVAE exhibits similar or better performance compared to matched classical models. © 2024, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Advancements in Quantum Radar Technology An Overview of Experimental Methods and Quantum Electrodynamics Considerations

引用

IEEE Nanotechnology Magazine 2024年第3期18卷 4-14页

作者： Lin, Yu-Cheng Huang, Tsung-Wei Tsai, Pin-Ju Chen, Yen-Hung Zhong, Yuan-Liang Chang, Ching-Ray National Taiwan University Department of Physics Taipei106319 Taiwan Chung-Yuan Christian University Quantum Information Center Taoyuan City320 Taiwan Chung-Yuan Christian University Undergraduate Program in Intelligent Computing and Big Data Taoyuan City320 Taiwan National Central University Department of Optics and Photonics Taoyuan City320 Taiwan National Central University Quantum Technology Center College of Science Taoyuan City320 Taiwan National Central University Center for Astronautical Physics and Engineering Taoyuan City320 Taiwan Chung-Yuan Christian University Department of Physics Taoyuan City320 Taiwan

This paper provides a brief introduction of the current state of quantum radar (QR) technology development, focusing on the experimental methods used for modifying QR in a laboratory setting. We delve into the foundational principles of quantum electrodynamics and consider interferometric aspects. Quantum radar systems, empowered by quantum measurements, extend their capabilities beyond conventional target detection and recognition, encompassing the detection and identification of RF stealth platforms and advanced weapons systems. Quantum technology is gaining paramount significance in various research domains, with the emergence of the concept of quantum radar, which leverages the quantum states of photons to extract information from distant targets. The mechanism involves dispatching photons, or photon clusters, toward the target, whereupon they are absorbed and subsequently re-emitted. The crucial measurement process can be executed in two distinct manners. One approach entails an interferometric measurement, often referred to as phase measurement, conducted on the photons, while the alternative method involves the straightforward quantification of returning photons. These methods are respectively known as Interferometric QR and Quantum Illumination (QI). In both approaches, one can opt to employ stationary quantum states of photons or harness entangled states. Extensive research has demonstrated that the use of entangled states yields the most significant resolution enhancement, achieving optimal results under ideal conditions. Quantum states offer a substantial advantage by virtue of their inherent correlations, referred to as quantum correlations, which augment both resolution and signal-to-noise ratio (SNR) in the radar system. This paper explores the intricacies of these advancements in quantum radar technology, shedding light on the underlying principles and experimental methodologies. © 2007-2011 IEEE.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Scalable Gaussian-process regression and variable selection using Vecchia approximations

arXiv

引用

arXiv 2022年

作者： Cao, Jian Guinness, Joseph Genton, Marc G. Katzfuss, Matthias Department of Statistics Institute of Data Science Texas A&M University United States Department of Statistics Cornell University United States Statistics Program King Abdullah University of Science and Technology Saudi Arabia

Gaussian process (GP) regression is a flexible, nonparametric approach to regression that naturally quantifies uncertainty. In many applications, the number of responses and covariates are both large, and a goal is to select covariates that are related to the response. For this setting, we propose a novel, scalable algorithm, coined VGPR, which optimizes a penalized GP log-likelihood based on the Vecchia GP approximation, an ordered conditional approximation from spatial statistics that implies a sparse Cholesky factor of the precision matrix. We traverse the regularization path from strong to weak penalization, sequentially adding candidate covariates based on the gradient of the log-likelihood and deselecting irrelevant covariates via a new quadratic constrained coordinate descent algorithm. We propose Vecchia-based mini-batch subsampling, which provides unbiased gradient estimators. The resulting procedure is scalable to millions of responses and thousands of covariates. Theoretical analysis and numerical studies demonstrate the improved scalability and accuracy relative to existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Cryptocurrency Analysis using Machine Learning and Deep Learning

Cryptocurrency Analysis using Machine Learning and Deep Lear...

引用

2021 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2021

作者： Thomas, C. Watson, Z. Kim, M. Baidya, A. Lamsal, M. Chowdhury, M.H. Basnet, M. Poudel, K.N. East Central University Department of Mathematics and Computer Science AdaOK United States Middle Tennessee State University Computational Science Program MurfreesboroTN United States University of Memphis Department of Electrical and Computer Engineering MemphisTN United States Embry-Riddle Aeronautical University Department of Mathematics and Data Science FL United States

来源：评论

学校读者我要写书评

暂无评论

Determining environmental indicators related to the propagation of contagious diseases and health issues: A Systematic Literature Review

Determining environmental indicators related to the propagat...

引用

Iberian Conference on Information Systems and Technologies (CISTI)

作者： Janeth Domínguez Portillo Laura M. Rodríguez Peralta Paulo N. M. Sampaio Eldman de Oliveira Nunes Faculty of Information Technologies and Data Science Universidad Popular Autónoma del Estado de Puebla (UPAEP) México Graduate Program in Computing and Systems University of Salvador (UNIFACS) Salvador Bahia Brazil

The environmental indicators provide significant information in order to describe the state of a phenomenon, environment or area [1]. This paper addresses the indicators present in the air and their relationship in the accommodation and transmission of viruses, as well as how these environmental indicators can lead to health problems. Therefore, the main goal of this work is to review the scientific contributions in the literature in order to determine and select the potential environmental indicators present in indoor environments which have an impact on the health of people who work and live within these spaces. For this purpose, we carried out a Systematic Literature Review (SLR) related to environmental monitoring, COVID-19, Internet of things, air pollution and environmental indicators within indoor spaces. This SLR allowed us to identify indicators that according to their level of presence can represent a high risk for people’s health. Therefore, the process of planning, conducting and reporting the Systematic Literature Review enabled us not only to identify some environmental indicators, but also their corresponding monitoring advantages and disadvantages, and multiple perspectives and approaches of each contribution in the literature. Further on, this study will be the basis for the proposal of an automatic and intelligent platform based on Internet of Things for monitoring indoor environments in order to detect high risk levels for the contamination of contagious diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interactive Ultrasound Prostate Cancer Segmentation using Deep Learning with Principal Curve-based Fine-tuning

Interactive Ultrasound Prostate Cancer Segmentation using De...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Peng, Tao Mao, Hui Wang, Caishan Di, Gongye Hu, Ting Zhang, Lei Soochow University School of Future Science and Engineering Suzhou China Ut Southwestern Medical Center Department of Radiation Oncology DallasTX United States Huangshi Central Hospital Department of Dermatology Hubei China Second Affiliated Hospital of Soochow University Department of Ultrasound Suzhou China Medical University Taizhou People's Hospital Affiliated to Nanjing Department of Ultrasonic Taizhou China The First Affiliated Hospital of Soochow University Department of Obstetrics and Gynaecology Ultrasonography Suzhou China Duke Kunshan University Graduate Program of Medical Physics and Data Science Research Center Kunshan China

ISBN: (纸本)9798350337488

Segmentation of prostate cancer on ultrasound (US) images is challenging because of the low-intensity contrast around the region of interest (ROI) contour caused by the intestinal gas. To the best of our knowledge, our work is one of the extremely rare groups to segment prostate cancer on US images, which designs a coarse-to-refinement segmentation framework with four merits: 1) it fuses the advantages of the deep learning- and principal curve-based algorithms to locate the ROI and fit the data center automatically, respectively;2) a principal curve-based polygon searching method is designed by newly adding some constraints so that the performance of our method could be enhanced;3) the quantum characteristics are added into evolution network, while newly adding numerous- operator scheme and global optimum search schemes;4) an interpretable mathematical mapping model is developed to denote the ROI contour. Segmentation results show that our network outperforms other medical image segmentation models. © 2023 IEEE.

关键词： Automatic segmentation explainability-guided mathematical expression polygon searching quantum evolution network ultrasound prostate cancer image

来源：评论

学校读者我要写书评

暂无评论

ECG Heart-Beat Classification Using Multimodal Image Fusion

ECG Heart-Beat Classification Using Multimodal Image Fusion

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Zeeshan Ahmad Anika Tabassum Ling Guan Naimul Khan Ryerson University Toronto ON Master of Data Science program Ryerson University Toronto ON

ISBN: (纸本)9781728176055;9781728176062

In this paper, we present a novel Image Fusion Model (IFM) for ECG heart-beat classification to overcome the weaknesses of existing machine learning techniques that rely either on manual feature extraction or direct utilization of 1D raw ECG signal. At the input of IFM, we first convert the heart-beats of ECG into three different images using Gramian Angular Field (GAF), Recurrence Plot (RP) and Markov Transition Field (MTF) and then fuse these images to create a single imaging modality. We use AlexNet for feature ex-traction and classification and thus employ end-to-end deep learning. We perform experiments on PhysioNet's MIT-BIH dataset for five different arrhythmias in accordance with the AAMI EC57 standard and on PTB diagnostics dataset for myocardial infarction (MI) classification. We achieved an state-of-an-art results in terms of prediction accuracy, precision and recall.

关键词： Heart beat Imaging Manuals Electrocardiography Markov processes Signal processing Myocardium

来源：评论

学校读者我要写书评

暂无评论

Machine learning approaches for predicting 5-year breast cancer survival: A multicenter study

引用

Cancer science 2023年第10期114卷 4063-4072页

作者： Quynh Thi Nhu Nguyen Phung-Anh Nguyen Chun-Jung Wang Phan Thanh Phuc Ruo-Kai Lin Chin-Sheng Hung Nei-Hui Kuo Yu-Wen Cheng Shwu-Jiuan Lin Zong-You Hsieh Chi-Tsun Cheng Min-Huei Hsu Jason C Hsu School of Pharmacy College of Pharmacy Taipei Medical University Taipei City Taiwan. Clinical Data Center Office of Data Science Taipei Medical University Taipei City Taiwan. Clinical Big Data Research Center Taipei Medical University Hospital Taipei Medical University Taipei City Taiwan. Research Center of Health Care Industry Data Science College of Management Taipei Medical University Taipei City Taiwan. Department of Surgery School of Medicine College of Medicine Taipei Medical University Taipei City Taiwan. Oncology Center Taipei Medical University Hospital Taipei City Taiwan. Graduate Institute of Data Science College of Management Taipei Medical University Taipei City Taiwan. International Ph.D. Program in Biotech and Healthcare Management College of Management Taipei Medical University Taipei City Taiwan.

The study used clinical data to develop a prediction model for breast cancer survival. Breast cancer prognostic factors were explored using machine learning techniques. We conducted a retrospective study using data from the Taipei Medical University Clinical Research database, which contains electronic medical records from three affiliated hospitals in Taiwan. The study included female patients aged over 20 years who were diagnosed with primary breast cancer and had medical records in hospitals between January 1, 2009 and December 31, 2020. The data were divided into training and external testing datasets. Nine different machine learning algorithms were applied to develop the models. The performances of the algorithms were measured using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score. A total of 3914 patients were included in the study. The highest AUC of 0.95 was observed with the artificial neural network model (accuracy, 0.90; sensitivity, 0.71; specificity, 0.73; PPV, 0.28; NPV, 0.94; and F1-score, 0.37). Other models showed relatively high AUC, ranging from 0.75 to 0.83. According to the optimal model results, cancer stage, tumor size, diagnosis age, surgery, and body mass index were the most critical factors for predicting breast cancer survival. The study successfully established accurate 5-year survival predictive models for breast cancer. Furthermore, the study found key factors that could affect breast cancer survival in Taiwanese women. Its results might be used as a reference for the clinical practice of breast cancer treatment.

关键词： TMUCRD breast cancer survival machine learning prediction models real-world data

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous quantization regularizes spiking neural network activity

arXiv

引用

arXiv 2024年

作者： Moyal, Roy Mama, Kyrus R. Einhorn, Matthew Borthakur, Ayon Cleland, Thomas A. Computational Physiology Lab Department of Psychology Cornell University IthacaNY14853 United States AI for Science Institute Cornell University IthacaNY14853 United States Neurosciences Graduate Program Stanford University StanfordCA94305 United States Mehta Family School of Data Science and Artificial Intelligence IIT Guwahati Assam Guwahati781039 India

The learning and recognition of object features from unregulated input has been a longstanding challenge for artificial intelligence systems. Brains are adept at learning stable representations given small samples of noisy observations;across sensory modalities, this capacity is aided by a cascade of signal conditioning steps informed by domain knowledge. The olfactory system, in particular, solves a source separation and denoising problem compounded by concentration variability, environmental interference, and unpredictably correlated sensor affinities. To function optimally, its plastic network requires statistically well-behaved input. We present a data-blind neuromorphic signal conditioning strategy whereby analog data are normalized and quantized into spike phase representations. Input is delivered to a column of duplicated spiking principal neurons via heterogeneous synaptic weights;this regularizes layer utilization, yoking total activity to the network’s operating range and rendering internal representations robust to uncontrolled open-set stimulus variance. We extend this mechanism by adding a data-aware calibration step whereby the range and density of the quantization weights adapt to accumulated input statistics, optimizing resource utilization by balancing activity regularization and information retention. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantization (signal)

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：