检索结果-内蒙古大学图书馆

Covid-19 detection using chest X-rays: is lung segmentation important for generalization?

Research on Biomedical engineering 2022年第4期38卷 1121-1139页

作者： Bassi, Pedro R. A. S. Attux, Romis Department of Computer Engineering and Industrial Automation School of Electrical and Computer Engineering University of Campinas - UNICAMP SP Campinas13083-970 Brazil Alma Mater Studiorum - University of Bologna BO Bologna40126 Italy Istituto Italiano Di Tecnologia GE Genoa16163 Italy

Purpose: We evaluated the generalization capability of deep neural networks (DNNs) in the task of classifying chest X-rays as Covid-19, normal or pneumonia, when trained in a relatively small and mixed datasets. Methods: We proposed a DNN to perform lung segmentation and classification, stacking a segmentation module (U-Net), an original intermediate module and a classification module (DenseNet201). To evaluate generalization capability, we tested the network with an external dataset (from distinct localities) and used Bayesian inference to estimate the probability distributions of performance metrics. Furthermore, we introduce a novel evaluation technique, which uses layer-wise relevance propagation (LRP) and Brixia scores to compare the DNN grounds for decision with radiologists. Results: The proposed DNN achieved 0.917 AUC (area under the ROC curve) on the external test dataset, surpassing a DenseNet without segmentation, which showed 0.906 AUC. Bayesian inference indicated mean accuracy of 76.1% and [0.695, 0.826] 95% HDI (high-density interval, which concentrates 95% of the metric’s probability mass) with segmentation and, without segmentation, 71.7% and [0.646, 0.786]. Conclusion: Employing an analysis based on LRP and Brixia scores, we discovered that areas where radiologists found strong Covid-19 symptoms are the most important for the stacked DNN classification. External validation showed smaller accuracies than internal, indicating difficulty in generalization, which is positively affected by lung segmentation. Finally, the performance on the external dataset and the analysis with LRP suggest that DNNs can successfully detect Covid-19 even when trained on small and mixed datasets. © 2022, The Author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning-based Green Workload Placement for Energy Internet in Smart Cities

引用

Journal of Modern Power Systems and Clean Energy 2022年第1期10卷 91-99页

作者： Qihua Zhou Yanfei Sun Haodong Lu Kun Wang School of Automation and School of Artificial Intelligence Nanjing University of Posts and TelecommunicationsNanjingChina School of Internet of Things Nanjing University of Posts and TelecommunicationsNanjingChina Department of Electrical and Computer Engineering University of CaliforniaLos AngelesUSA

The Energy Internet is a fundamental infrastructure for deploying green city applications, where energy saving and job acceleration are two critical issues to address. In contrast to existing approaches that focus on static metrics with the assumption of complete prior knowledge of resource information, both application-level properties and energy-level requirements are realized in this paper by jointly considering energy saving and job acceleration during job runtime. Considering the online environment of smart city applications, the main objective is transferred as an optimization problem with a model partition and function assignment. To minimize the energy cost and job completion time together, a green workload placement approach is proposed by using the multi-action deep reinforcement learning method. Evaluations with real-world applications demonstrate the superiority of this method over state-of-the-art methods.

关键词： Energy saving workload scheduling Energy Internet green city

来源：评论

学校读者我要写书评

暂无评论

One-shot functional photoacoustic microscopy for monitoring traumatic brain injury 16

One-shot functional photoacoustic microscopy for monitoring ...

引用

16th International Conference on Photonics and Imaging in Biology and Medicine, PIBM 2023

作者： Zhang, Yameng Chen, Yang Qi, Xinping Li, Weitao Department of Computer Engineering Nanjing Institute of Technology No.1 Hongjing Avenue Nanjing Jiangsu211167 China College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu211106 China

ISBN: (纸本)9781510667341

Photoacoustic microscopy (PAM) is a novel medical imaging technique developed rapidly in recent years with the advantages of high resolution, high contrast, and no ionizing radiation. In this study, we developed a one-shot functional photoacoustic microscopy (OS-fPAM) system for assessing traumatic brain injury (TBI). The OS-fPAM system only employed a single 532 nm nanosecond pulse laser with Raman delay optical path control, which can produce both 532 nm and 553 nm laser beams. The dual-wavelength beams were then coupled via a dichroic mirror and focused on the surface of the experimental sample. Then, the photoacoustic signal was collected and amplified in the ultrasonic signal acquisition module, and the blood oxygen saturation (sO2) image was calculated by two wavelength photoacoustic images. The feasibility of the OS-fPAM system was performed through the calibration experiments with different ratios of red ink and blue ink. Meanwhile, the OS-fPAM system can monitor microvascular structures and sO2 in the TBI model on mice for 96 hours in vivo with a spatial resolution of ∼40 μm, demonstrating the potential to evaluate rehabilitation and cerebral vascular damage. © 2023 SPIE.

关键词： Photoacoustic microscopy

来源：评论

学校读者我要写书评

暂无评论

BFuse-Net: Bonferroni Mean Operator-Aided Fusion of Neural Networks for Medical Image Classification 5th

BFuse-Net: Bonferroni Mean Operator-Aided Fusion of Neural ...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Ghosh, Triyas Chakraborty, Soham Kaplun, Dmitrii Gulvanskii, Vyacheslav Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata700032 India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9789819638628

In this paper, we have proposed a novel model, called Bonferroni Mean Operator-aided Fusion of Neural Networks (BFuse-Net). Here, we have taken advantage of the capabilities of four deep learning models as the base learners and then applied a customized attention method to prioritize different fine-grained features by passing their outputs via four parallel pipelines. Next, we have employed a novel aggregation method, a modified Bonferroni Mean operator, to merge the decision scores acquired from every pipeline, prioritizing their individual contributions above their interactions with others in the decision scores. Three medical image datasets— LC25000 (colon cancer), Oral Squamous Cell Carcinoma, and Malaria Cell Images have been used for experimentation. The model yields state-of-the-art outcomes for the three datasets. The source codes and additional results can be found at GitHub repository. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Sampled-data synchronization for heterogeneous delays inertial neural networks with generally uncertain semi-Markovian jumping and its application

引用

Neural Computing and Applications 2024年第33期36卷 20963-20982页

作者： Wang, Junyi He, Wenyuan Xu, Hongli Cai, Haibin Chen, Xiangyong Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China Foshan Graduate School of Innovation Northeastern University Foshan528311 China College of Information Science and Engineering Northeastern University Liaoning Shenyang110819 China Department of Computer Science Loughborough University LoughboroughLE11 3TU United Kingdom School of Automation and Electrical Engineering Linyi University Linyi276000 China

This article is concerned with sampled-data synchronization problem of heterogeneous delays inertial neural networks (INNs) with generally uncertain semi-Markovian (GUSM) jumping. Different from traditional Markovian inertial neural networks (MINNs), the INNs with GUSM are investigated in this paper by fully considering the sojourn time and the lacking transition rates, which is more general and applicable for practical system. The new extended two-sided looped-functional (ETSLF) approach is adopted in this paper, and some improved less conservative criteria are derived to achieve the synchronization of the drive and response INNs. The controller gain matrices are acquired based on synchronization criteria. Finally, the viability of the method is presented through three examples. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Aspect Level Songs Rating Based Upon Reviews in English

引用

computers, Materials & Continua 2023年第2期74卷 2589-2605页

作者： Muhammad Aasim Qureshi Muhammad Asif Saira Anwar Umar Shaukat Atta-ur-Rahman Muhammad Adnan Khan Amir Mosavi Department of Computer Science Bahria University Lahore54000Pakistan Lahore Institute of Science and Technology Lahore 54792Pakistan Department of Multidisciplinary Engineering Texas A&M UniversityCollege Station77843USA Department of Computer Science College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam 31441Saudi Arabia Department of Software Gachon UniversitySeongnam13120Korea John von Neumann Faculty of Informatics Obuda UniversityBudapest1034Hungary Institute of Information Engineering Automation and MathematicsSlovak University of Technology in BratislavaBratislava81107Slovakia Faculty of Civil Engineering TU-DresdenDresden01062Germany

With the advancements in internet facilities,people are more inclined towards the use of online *** service providers shelve their items for *** users post their feedbacks,reviews,ratings,*** the use of the *** enormous increase in these reviews has raised the need for an automated system to analyze these reviews to rate these *** Analysis(SA)is a technique that performs such decision *** research targets the ranking and rating through sentiment analysis of these reviews,on different *** a case study,Songs are opted to design and test the decision *** aspects of songs namely music,lyrics,song,voice and video are *** the reason,reviews of 20 songs are scraped from YouTube,pre-processed and formed a *** machine learning algorithms—Naïve Bayes(NB),Gradient Boost Tree,Logistic Regression LR,K-Nearest Neighbors(KNN)and Artificial Neural Network(ANN)are *** performed the best with 74.99%*** are validated using K-Fold.

关键词： Machine learning natural language processing songs reviews:sentiment analysis songs rating aspect level sentiment analysis reviews analysis text classification music

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Dysplasia Grading in Colorectal Polyps Using an Explainable Weakly Supervised Deep Learning Model

SSRN

引用

SSRN 2025年

作者： Hernández, Nerea Ortuño, Francisco Rojas, Ignacio Department of Computer Engineering Automation and Robotics ETSIIT CITIC-UGR University of Granada 18071 Spain

Colorectal cancer remains one of the leading causes of mortality worldwide, often developing from precancerous polyps. The risk of malignant transformation is closely linked to the degree of dysplasia, characterized by abnormalities in cell morphology and tissue organization. Accurate dysplasia grading is vital for early diagnosis and improved patient outcomes. Whole slide imaging (WSI) facilitates high-resolution digital analysis of tissue samples, but the complexity of histological patterns and subjective human interpretation highlight the need for more automated analysis *** this study, we propose a deep learning model for dysplasia classification in colorectal histology using a weakly supervised learning approach. Unlike traditional methods, our model does not require pixel-level annotations and can automatically identify the most relevant regions for classification. We achieve state-of-the-art accuracy, reaching 96.7\% on the CRS10K dataset and 95.5\% in external validation using TCGA images. To enhance model transparency, we integrate interpretability mechanisms through heatmap visualizations, allowing a better understanding of the model’s decision-making process. Additionally, we emphasize the importance of uncertainty-aware classification in medical Artificial Intelligence (AI), ensuring that highly confident predictions can be automated while directing expert attention to ambiguous cases. Our goal is to develop reliable and explainable AI tools that support pathologists in making accurate and timely diagnoses, ultimately improving colorectal cancer detection and patient care. © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

PATSMA: Parameter Auto-tuning for Shared Memory Algorithms

arXiv

引用

arXiv 2024年

作者： Fernandes, Joao B. Santos-Da-Silva, Felipe H. Barros, Tiago Assis, Italo A.S. Xavier-De-Souza, Samuel Department of Computer Engineering and Automation UFRN Natal Brazil Department of Engineering and Technology UFERSA Pau dos Ferros Brazil

Programs with high levels of complexity often face challenges in adjusting execution parameters, particularly when the ideal value for these parameters may change based on the execution context. These dynamic parameters significantly impact the program’s performance. For instance, ideal parallel loop scheduling may vary depending on factors like the execution environment, program input, or the choice of compiler. Given the expensive nature of testing each case individually, one viable solution is to automate parameter adjustments using optimization methods. This article introduces PATSMA, a parameter auto-tuning tool that leverages Coupled Simulated Annealing (CSA) and Nelder–Mead (NM) optimization methods to fine-tune existing parameters in an iterative application. We demonstrate how auto-tuning can contribute to the real-time optimization of parallel algorithms designed for shared memory systems. PATSMA is a C++ library readily available under the MIT license. Copyright © 2024, The Authors. All rights reserved.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

A Scalable Synthesis Algorithm for Reversible Functions

arXiv

引用

arXiv 2025年

作者： Sarvaghad-Moghaddam, Moein Zamani, Morteza Saheb Sedighi, Mehdi Quantum Design Automation Laboratory Department of Computer Engineering Amirkabir University of Technology Tehran Iran

Reversible computation is an emerging technology that has gained significant attention due to its critical role in quantum circuit synthesis and low-power design. This paper introduces a transformation-based method for exact synthesis of reversible circuits. The proposed approach utilizes a modified Quine-McCluskey algorithm to eliminate input-output discrepancies in the truth table, transforming the permutation matrix into an identity matrix. Furthermore, a novel search space reduction technique is presented which, combined with the primary method, enables the synthesis algorithm to handle high-input reversible functions. This approach combines the influence of multiple control qubits on a target qubit, evaluating their collective impact. This aggregation can decrease the control qubit count within quantum gates. Consequently, it proves beneficial for applications like surface code error correction architectures as well as current Noisy Intermediate-Scale Quantum (NISQ) hardwares. Experimental results demonstrate significant improvements over the state-of-the-art exact synthesis methods, achieving up to 99% improvements in terms of the number of levels of T-gates. Copyright © 2025, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Mathematical Model of Device for Measuring Rheological Parameters of Viscoplastic Liquids 13

Mathematical Model of Device for Measuring Rheological Param...

引用

13th International Conference on Advanced computer Information Technologies, ACIT 2023

作者： Pistun, Yevhen Matiko, Halyna Krykh, Hanna Lviv Polytechnic National University Department of Automation and Computer-Integrated Technologies Lviv Ukraine Lviv Polytechnic National University Department of Heat Engineering and Thermal and Nuclear Power Plants Lviv Ukraine

The paper proposes a hydrodynamic device for measuring plastic viscosity and yield stress of a viscoplastic liquid. Four tubes are the sensitive elements of the device. They are connected in a bridge diagram by chambers. The shear rate of the liquid is different in all tubes of the hydraulic bridge due to the additional flow through the intertubular chambers. A mathematical model of the measuring device has been built, which allows one to choose its operational and constructive characteristics for the specified measuring ranges of rheological parameters. Based on the developed model, a hydrodynamic device is designed for measuring the plastic viscosity and yield stress of crude oil described by the Bingham rheological model. © 2023 IEEE.

关键词： Hydrodynamics

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：