检索结果-内蒙古大学图书馆

ASRNet: Adversarial Segmentation and Registration Networks for Multispectral Fundus Images

Computer Systems science & Engineering 2021年第3期36卷 537-549页

作者： Yanyun Jiang Yuanjie Zheng Xiaodan Sui Wanzhen Jiao Yunlong He Weikuan Jia School of Information Science and Engineering Shandong Normal UniversityJinan250358China Key Laboratory of Intelligent Computing&Information Security in Universities of Shandong Shandong Provincial Key Laboratory for Novel Distributed Computer Software TechnologyInstitute of Biomedical SciencesShandong Normal UniversityJinan250358China Shandong Provincial Hospital Affiliated to Shandong University Jinan250021China INSA Lyon University of LyonCNRSInsermVilleurbanne69621CedexFrance

Multispectral imaging (MSI) technique is often used to capture imagesof the fundus by illuminating it with different wavelengths of light. However,these images are taken at different points in time such that eyeball movementscan cause misalignment between consecutive images. The multispectral imagesequence reveals important information in the form of retinal and choroidal bloodvessel maps, which can help ophthalmologists to analyze the morphology of theseblood vessels in detail. This in turn can lead to a high diagnostic accuracy of several diseases. In this paper, we propose a novel semi-supervised end-to-end deeplearning framework called “Adversarial Segmentation and Registration Nets”(ASRNet) for the simultaneous estimation of the blood vessel segmentation andthe registration of multispectral images via an adversarial learning process. ASRNet consists of two subnetworks: (i) A segmentation module S that fulfills theblood vessel segmentation task, and (ii) A registration module R that estimatesthe spatial correspondence of an image pair. Based on the segmention-drivenregistration network, we train the segmentation network using a semi-supervisedadversarial learning strategy. Our experimental results show that the proposedASRNet can achieve state-of-the-art accuracy in segmentation and registrationtasks performed with real MSI datasets.

关键词： Deep learning deformable image registration image segmentation multispectral imaging(MSI)

来源：评论

学校读者我要写书评

暂无评论

Enabling Online Fault Prediction in Adaptive Control: A Model Checker and Controller Co-Designed CPS Solution

Enabling Online Fault Prediction in Adaptive Control: A Mode...

引用

International Symposium on Industrial Embedded Systems

作者： Yao Chen Xueli Fan Qixin Wang Nan Guan Shuai Li Zili Shao Department of Computing The Hong Kong Polytechnic University Hong Kong SAR China Department of Computer Sci. Southwest Univ. of Finance and Economics Chengdu China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University China Department of Computer Science City University of Hong Kong Hong Kong SAR China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland Technology Research Center of Finland (VTT) Oulu Finland Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong SAR China

ISBN: (数字)9798350388633

ISBN: (纸本)9798350388640

By combining cyber subsystem of model checker with physical subsystem of control, online model checking of control systems can serve as a runtime fault prediction method to increase control systems safety. Online model checking of adaptive control systems, however, incurs more challenging time costs, due to the uncertainty caused by unknown control system parameter values. In this paper, we first propose a safety-oriented adaptive controller (SOAC) to replace the classic adaptive controller. This cuts online model checking time cost from $\Omega(Jd^{n+p-1})$ to $O(Jd^{n-1})$ , where $J$ and $d$ are scalable configuration parameters, raising which refines numerical computation granularity; $n$ is the dimension of the physical state; and $p+1$ is the dimension of control system parameters with unknown values. We further propose a specialized model checker for SOAC, and prove under mild conditions, the proposed model checker can further cut model checking time cost to $O(J)$ .

关键词： Adaptation models Costs Uncertainty Computational modeling Model checking Predictive models Control systems Numerical models Safety Adaptive control

来源：评论

学校读者我要写书评

暂无评论

Releasing Inequality Phenomena in L∞-Adversarial Training via Input Gradient Distillation

arXiv

引用

arXiv 2023年

作者： Chen, Junxi Dong, Junhao Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou510006 China

Since adversarial examples appeared and showed the catastrophic degradation they brought to DNN, many adversarial defense methods have been devised, among which adversarial training is considered the most effective. However, a recent work showed the inequality phenomena in l∞-adversarial training and revealed that the l∞-adversarially trained model is vulnerable when a few important pixels are perturbed by i.i.d. noise or occluded. In this paper, we propose a simple yet effective method called Input Gradient Distillation (IGD) to release the inequality phenomena in l∞-adversarial training. Experiments show that while preserving the model’s adversarial robustness, compared to PGDAT, IGD decreases the l∞adversarially trained model’s error rate to inductive noise and inductive occlusion by up to 60% and 16.53%, and to noisy images in Imagenet-C by up to 21.11%. Moreover, we formally explain why the equality of the model’s saliency map can improve such robustness. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Real-Time Big Data Analytics for ICU Resource Management

AI-Powered Real-Time Big Data Analytics for ICU Resource Man...

引用

Visual Analytics and Data Visualization (ICVADV), International Conference on

作者： S. Kalaichelvi N. Mohankumar C. Uthayakumar Barkathulla A K.S. Manojee S. Murugan Department of Computer Science and Applications Vivekanandha College of Arts and Sciences for Women (Autonomous) Tiruchengode Tamil Nadu India Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India Department of Electronics and Communication Engineering Vivekanandha College of Engineering For Women Tiruchengode Namakkal Tamil Nadu India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Tamil Nadu India Department of Information Technology Kongunadu College of Engineering and Technology (Autonomous) Trichy Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

Improving patient outcomes and operational efficiency in intensive care units (ICUs) relies heavily on efficient resource management. This work presents a novel LSTM-based methodology for real-time optimization of ICU resources, using big data to enhance decision-making. Patient vitals, equipment utilization, and staff activities are just a few examples of the real-time data gathered from the many ICU sensors and monitoring devices the system incorporates using LSTM networks. LSTM networks excel in processing time-series data, allowing the system to anticipate resource requirements, spot bottlenecks, and allocate resources optimally. The proposed system offers predicted insights together with practical suggestions by analyzing historical and real-time data streams. Simulations and case studies show that the system can increase operational efficiency and predict demand. Findings point to major gains in patient care, savings, and decision-making assistance in fast-paced ICUs. This method uses LSTM networks to tackle the intricacies of contemporary hospital environments, revolutionizing ICU management with innovative AI and big data analytics. LSTM networks improve real-time decision-making, resource management, and patient outcomes in ICUs.

关键词： Analytical models Accuracy Decision making Predictive models Big Data Real-time systems Data models Resource management Long short term memory Load modeling

来源：评论

学校读者我要写书评

暂无评论

Using Simulated Data to Predict Birthweight from Prenatal Ultrasound Images

Using Simulated Data to Predict Birthweight from Prenatal Ul...

引用

Western New York Image Processing Workshop (WNYIPW)

作者： Caitlin Dreisbach Arunaggiri Pandian Karunanidhi Yuka Shimazaki Neha Rana Loralei Thornburg Linwei Wang Susan Groth Stefanie Hollenbach School of Nursing and Goergen Institute for Data Science University of Rochester Rochester New York Goergen Institute for Data Science University of Rochester Rochester New York University of Rochester Medcical Center Rochester New York Department of Computing and Information Science Rochester Institute of Technology Rochester New York School of Nursing Unviersity of Rochester Rochester New York

Fetal weight estimation during pregnancy is critical for monitoring growth and planning delivery, yet current ultrasound-based estimations are prone to error. This study leveraged open access ultrasound images and simulated clinical data to develop a deep learning pipeline for fetal weight prediction. The dataset consisted of n=1,570 ultrasound images from 333 pregnant individuals at 18-40 weeks’ gestation. Relevant maternal and fetal attributes like body mass index, gestational age, amniotic fluid index, and newborn birth weight were simulated based on population averages. A convolutional neural network (CNN) using transfer learning was applied to extract imaging features. The pre-trained Xception model was adapted by adding a global average pooling layer and freezing layers during feature extraction. Extracted imaging features were combined with clinical metadata and input into linear regression and random forest models. Hyperparameter tuning via randomized search identified a random forest configuration minimizing error. On a 20% test set, the pipeline achieved a mean absolute error of 328.6 grams in predicting birth weight, suggesting feasibility of the approach. While clinical conclusions are limited without real-world data, this study demonstrates a pipeline leveraging open science resources to address an important maternal-fetal health problem. Tailored CNN architectures and further model optimization on population-representative data could enhance performance and clinical utility. This work highlights the potential of open datasets to enable rapid scientific progress and proposes a deep learning methodology for improved fetal weight assessment during pregnancy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HealthEdge: A Machine Learning-Based Smart Healthcare Framework for Prediction of Type 2 Diabetes in an Integrated IoT, Edge, and Cloud computing System

arXiv

引用

arXiv 2023年

作者： Hennebelle, Alain Materwala, Huned Ismail, Leila Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates Lab School of Computing and Information Systems The University of Melbourne Australia

Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR. © 2023, CC BY-NC-ND.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Anti-Jamming Precoding Against Disco Intelligent Reflecting Surfaces Based Fully-Passive Jamming Attacks

arXiv

引用

arXiv 2023年

作者： Huang, Huan Dai, Lipeng Zhang, Hongliang Tian, Zhongxing Cai, Yi Zhang, Chongfu Lee Swindlehurst, A. Han, Zhu School of Electronic and Information Engineering Soochow University Suzhou215006 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Electronics Peking University Beijing100871 China Center for Pervasive Communications and Computing University of California IrvineCA92697 United States University of Houston HoustonTX77004 United States

Emerging intelligent reflecting surfaces (IRSs) significantly improve system performance, but also pose a huge risk for physical layer security. Existing works have illustrated that a disco IRS (DIRS), i.e., an illegitimate IRS with random time-varying reflection properties (like a "disco ball"), can be employed by an attacker to actively age the channels of legitimate users (LUs). Such active channel aging (ACA) generated by the DIRS can be employed to jam multi-user multiple-input single-output (MU-MISO) systems without relying on either jamming power or LU channel state information (CSI). To address the significant threats posed by DIRS-based fully-passive jammers (FPJs), an anti-jamming precoder is proposed that requires only the statistical characteristics of the DIRS-based ACA channels instead of their CSI. The statistical characteristics of DIRS-jammed channels are first derived, and then the anti-jamming precoder is derived based on the statistical characteristics. Furthermore, we prove that the anti-jamming precoder can achieve the maximum signal-to-jamming-plus-noise ratio (SJNR). To acquire the ACA statistics without changing the system architecture or cooperating with the illegitimate DIRS, we design a data frame structure that the legitimate access point (AP) can use to estimate the statistical characteristics. During the designed data frame, the LUs only need to feed back their received power to the legitimate AP when they detect jamming attacks. Numerical results are also presented to evaluate the effectiveness of the proposed anti-jamming precoder against the DIRS-based FPJs and the feasibility of the designed data frame used by the legitimate AP to estimate the statistical characteristics. Copyright © 2023, The Authors. All rights reserved.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Smart Irrigation System using Internet of Things

Smart Irrigation System using Internet of Things

引用

International Conference on computing for Sustainable Global Development (INDIACom)

作者： Nagendra Panini Challa Shyam Mohan J S Venkata Sasi Deepthi Sivaram Rajeyyagari School of Computer Science and Engineering (SCOPE) VIT-AP University Andhra Pradesh India Department of Computer Science and Engineering Gitam University Bangalore India Department of Computer Science and Engineering Shri Vishnu Engineering College for Women (A) Bhimavram Andhra Pradesh India Department of Computer Science College of Computing and Information Technology Shaqra University Saudi Arabia

Agriculture is an important sector of our Indian Economy. Crops may be harmed due to non-availability of necessary resources. To avoid this problem, this paper proposes a smart irrigation system which works on IoT based platform. This paper focuses on capturing and data transfer over a wireless network without any human intervention applicable for any crop land. It makes use of smart wireless sensors which monitors soil moisture, temperature, and humidity for farming land. The control unit functions using the microcontroller on the Node MCU platform. Various sensors for soil, temperature and humidity are deployed to determine the exact levels of moisture and frequently monitored via the Blynk mobile app. This method analyses the collected sensor information and keep track of the moisture content of the soil and specifies the required amount of water to be used and avoiding overwatering. The results obtained here justify the proposed model is energy efficiency, cost-effective and ease of use.

关键词： Temperature sensors Temperature measurement Irrigation Moisture Crops Land surface temperature Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Exploring genetic mechanisms underlying EEG endophenotypes via summary-data-based Mendelian randomization

Exploring genetic mechanisms underlying EEG endophenotypes v...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jing Chen Pengfei Zhu Jinghui Pan Tao Wang School of Computer Science and Engineering Xi’an University of Technology Xi’an China Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science Northwestern Polytechnical University Xi’an China School of Electronic Information Wuhan University Wuhan China Department of Radiation Oncology Renmin Hospital of Wuhan University Wuhan China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Oscillations in neuronal activity play a crucial role in neural processing. Electroencephalogram (EEG) records the amplitudes of oscillations at different frequencies. The robust interindividual variation and the high intraindividual stability of EEG oscillations can be explained by genetic variants. However, our knowledge of how genetic variants affect EEG endophenotypes is still limited. In this paper, we aim to identify the linkage between genes and EEG oscillations at different frequencies. We integrate the summary-level datasets from the genome-wide association studies (GWASs) of seven EEG endophenotypes and expression quantitative trait loci (eQTL) study of the human brain, to explore the genetic mechanisms underlying EEG using summary-data-based two-sample Mendelian randomization. As a result, twelve candidate causal genes are prioritized across four EEG endophenotypes. These genes offer opportunities for a deeper understanding of the molecular mechanisms whereby genomic variation leads to variable brain activities.

关键词： Couplings Brain Genomics Electroencephalography Stability analysis Gene expression Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning based Facial Expression and Emotion Recognition for Human Computer Interaction through Fuzzy Logic System

A Machine Learning based Facial Expression and Emotion Recog...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： K Vinutha Manoj Kumar Niranjan Jagdish Makhijani B. Natarajan V. Nirmala T. R Vijaya Lakshmi Department of Information Science and Engineering BMS Institute of Technology and Management Bengaluru Karnataka India Department of Computer Applications Rustamji Institute of Technology Gwalior Madhya Pradesh India Department of Computer Science and Engineering Rustamji Institute of Technology Gwalior Madhya Pradesh India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai Tamil Nadu India Department of Science and Humanities Faculty of engineering Karpagam academy of higher education Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering Mahatma Gandhi institute of technology Hyderabad Telangana India

Facial recognition is in use for the past decade there are many applications that needs facial expression to learn the human behaviour and emotions for certain activities. Facial recognition is in a development phase where many service providers use this feature to find the expression of the people on using their BlogSpot or website or reading any news article. This recognition of facial expression is highly possible with the help of machine learning technology. This research study has developed a facial expression recognizing algorithm using Python programming language with the help of Keras software package. This algorithm is purely based on machine learning approach that enables the programmer to process the facial image and convert it into data that is helpful in prediction of facial expression using the fuzzy logic technique. The fuzzy logic technique is a prediction method that helps programmer to predict the intermediate data by providing the initial and ending conditions. For enabling the facial recognition to process any system or a mobile device the algorithm needs permission to access the camera, once the onto the access is permitted the algorithm retrieves the image from the Vision sensor and with the help of image processing technology of the machine learning algorithm the program the program converts the data from the vision sensor into required facial expression and emotional content.

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：