检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yi, Jihun Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Seoul Korea Republic of Department of Electrical and Computer Engineering and Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

The task of image anomaly detection (IAD) aims to identify deviations from normality in image data. These anomalies are patterns that deviate significantly from what the IAD model has learned from the data during training. However, in real-world scenarios, the criteria for what constitutes normality often change, necessitating the reclassification of previously anomalous instances as normal. To address this challenge, we propose a new scenario termed "normality addition," involving the post-training adjustment of decision boundaries to incorporate new normalities. To address this challenge, we propose a method called Normality Addition via Normality Detection (NAND), leveraging a vision-language model. NAND performs normality detection which detect patterns related to the intended normality within images based on textual descriptions. We then modify the results of a pre-trained IAD model to implement this normality addition. Using the benchmark dataset in IAD, MVTec AD, we establish an evaluation protocol for the normality addition task and empirically demonstrate the effectiveness of the NAND method. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Machine learning assisted mid-infrared spectrochemical fibrillar collagen imaging in clinical tissues

Machine learning assisted mid-infrared spectrochemical fibri...

引用

Advanced Chemical Microscopy for Life Science and Translational Medicine 2025

作者： Adi, Wihan Rubio Perez, Bryan E. Liu, Yuming Runkle, Sydney Eliceiri, Kevin W. Yesilkoy, Filiz Department of Biomedical Engineering University of Wisconsin-Madison MadisonWI53705 United States Department of Electrical and Computer Engineering University of Wisconsin-Madison MadisonWI53705 United States Center for Quantitative Cell Imaging University of Wisconsin-Madison MadisonWI53706 United States Department of Computer Science University of Wisconsin-Madison MadisonWI53705 United States Morgridge Institute for Research MadisonWI53706 United States

ISBN: (纸本)9781510684126

Label-free multimodal imaging methods are essential for comprehensive tissue analysis, particularly for studying the tumor microenvironment where changes in fibrillar collagen architecture are linked to cancer progression. This study presents a novel multimodal computational imaging approach combining mid-infrared spectral imaging (MIRSI) with second harmonic generation (SHG) microscopy to detect fibrillar collagen in biological tissues. Using SHG images as ground truth, a supervised machine learning (ML) model, specifically a random forest (RF) classifier, was trained to classify fibrillar collagen in mid-infrared hyperspectral images. The study utilized five human pancreatic tissue samples, encompassing 2.8 million MIRSI spectra for training and 68 million spectra for validation. The RF-MIRSI model demonstrated robust performance in collagen segmentation (boundary F-score: 0.8 at 4-pixel thresholds), orientation (Pearson’s R: 0.82), and alignment (Pearson’s R: 0.66) when compared to SHG ground truth. These findings highlight the potential of ML-driven label-free MIRSI for detailed collagen fiber and tumor microenvironment analysis, offering a complementary structural and chemical imaging tool for tumor pathology. © 2025 SPIE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Introducing δ -XAI: a novel sensitivity-based method for local AI explanations

arXiv

引用

arXiv 2024年

作者： De Carlo, Alessandro Parimbelli, Enea Melillo, Nicola Nicora, Giovanna Department of Electrical Computer and Biomedical Engineering University of Pavia Italy Telfer school of management University of Ottawa Canada

Explainable Artificial Intelligence (XAI) is central to the debate on integrating Artificial Intelligence (AI) and Machine Learning (ML) algorithms into clinical practice. High-performing AI/ML models, such as ensemble learners and deep neural networks, often lack interpretability, hampering clinicians' trust in their predictions. To address this, XAI techniques are being developed to describe AI/ML predictions in human-understandable terms. One promising direction is the adaptation of sensitivity analysis (SA) and global sensitivity analysis (GSA), which inherently rank model inputs by their impact on predictions. Here, we introduce a novel δ-XAI method that provides local explanations of ML model predictions by extending the δ index, a GSA metric. The δ-XAI index assesses the impact of each feature's value on the predicted output for individual instances in both regression and classification problems. We formalize the δ-XAI index and provide code for its implementation. The δ-XAI method was evaluated on simulated scenarios using linear regression models, with Shapley values serving as a benchmark. Results showed that the δ-XAI index is generally consistent with Shapley values, with notable discrepancies in models with highly impactful or extreme feature values. The δ-XAI index demonstrated higher sensitivity in detecting dominant features and handling extreme feature values. Qualitatively, the δ-XAI provides intuitive explanations by leveraging probability density functions, making feature rankings clearer and more explainable for practitioners. Overall, the δ-XAI method appears promising for robustly obtaining local explanations of ML model predictions. Further investigations in real-world clinical settings will be conducted to evaluate its impact on AI-assisted clinical workflows. © 2024, CC BY-NC-ND.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

computer Vision-Based Hydroponic Lettuce Contour and Area Recognition System

Computer Vision-Based Hydroponic Lettuce Contour and Area Re...

引用

International Conference on electrical engineering and Informatics, ICEEI

作者： Samuel Raymond Pranowo Zener Lie Sukra Muhammad Zacky Asy'ari Marisa Paryasto Computer Engineering Department Automotive and Robotics Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Electrical Engineering Department Computer Engineering Program Telkom University Bandung Indonesia

Agriculture is a vital industry for the people of Indonesia, but there are several obstacles, including limited space in urban areas and inefficient conventional sorting and harvesting methods. Using computer vision to choose hydroponic lettuce that is ready to be harvested and a robotic arm to bring the selected lettuce yields, the produced system aims to solve this problem. The system's computer vision algorithms include color space conversion, intensity transformation, and an algorithm for following borders. This project's research methodology combines a quantitative approach with an experimental approach, which consists of conducting several trials on the built system. Several trials demonstrated that the computer vision software was able to accomplish the specified objectives. The average success rate of the developed computer vision system is 93%, while the average success rate of the robot arm is 85%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure Electronic Transaction Using AADHAAR Based QR Code and Biometric Authentication

Secure Electronic Transaction Using AADHAAR Based QR Code an...

引用

2022 International Conference on Communication, Computing and Internet of Things, IC3IoT 2022

作者： Shanmugapriyan, J. Parthasarathy, R. Sathish, S. Prasanth, S. Nsn Electrical & Electronics Engineering College of Engineering &technology Karur India Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science & Technology Computer Science and Engineering Avadi India Veltech Multitech Dr Rangarajan Dr Sakunthala Engineering College Department of Biomedical Engineering Avadi India Grt Department of Biomedical Engineering Insitute of Engineering &technology Tirutani India

ISBN: (纸本)9781665479950

Bank services have become more convenient in recent years thanks to electronic banking, but their security is also improving. Hence security in banking services is enhanced using QR code embedded in the aadhaar card and biometric authentication. Using aadhaar number enables the users to access their accounts in multiple banks. Of all the biometrics, fingerprint trait is chosen because of its characteristics like availability, reliability and high accuracy. Finger print recognition system is used for both verification and identification to make the system more secure. In this system, ATM machine can be operated using the aadhaar card instead of ATM card. The in-built camera in the ATM machine will scan the QR code embedded in the aadhaar card and then match it with fingerprint of the user obtained using the biometric sensor. Only after successful authentication, the user will be allowed to perform cash transactions. Hence the need of ATM card for each bank account is completely eliminated by this system. The work of the people as well as the banking sector is simplified. Not only cash withdrawal but also an android application is developed which uses aadhaar number to perform online cash transactions. Hence the system is designed with large number of security features so that a costumer can perform financial transactions without any security issues. © 2022 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Direct laser speckle contrast imaging with sampling bias correction

Direct laser speckle contrast imaging with sampling bias cor...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Shuqi Zheng Jerome Mertz Department of Electrical and Computer Engineering Boston University Boston MA Department of Biomedical Engineering Boston University Boston MA

Speckle contrast is generally calculated from localized window containing limited statistics, resulting a systematic bias in the estimation. We achieve sampling bias correction and demonstrate accurate quantitative la... 详细信息

ISBN: (纸本)9781957171258

关键词： Brain imaging Laser speckle Speckle analysis Speckle imaging Speckle noise Statistics

来源：评论

学校读者我要写书评

暂无评论

Treatment Effects in Extreme Regimes

arXiv

引用

arXiv 2023年

作者： Aloui, Ahmed Hasan, Ali Ng, Yuting Pajic, Miroslav Tarokh, Vahid Department of Electrical and Computer Engineering Duke University United States Department of Biomedical Engineering Duke University United States

Understanding treatment effects in extreme regimes is important for characterizing risks associated with different interventions. This is hindered by the unavailability of counterfactual outcomes and the rarity and difficulty of collecting extreme data in practice. To address this issue, we propose a new framework based on extreme value theory for estimating treatment effects in extreme regimes. We quantify these effects using variations in tail decay rates of potential outcomes in the presence and absence of treatments. We establish algorithms for calculating these quantities and develop related theoretical results. We demonstrate the efficacy of our approach on various standard synthetic and semi-synthetic datasets. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Automated License Plate Recognition and Tracking of Runaway Vehicles 3

Real-time Automated License Plate Recognition and Tracking o...

引用

3rd International Informatics and Software engineering Conference, IISEC 2022

作者： Ramadan, Montaser N. A. Hilles, Shadi M S Alkhedher, Mohammad Ghazal, Mohammed Istanbul Okan University Computer Engineering Department Istanbul Turkey Istanbul Okan University Software Engineering Department Istanbul Turkey Abu Dhabi University Mechanical and Industrial Engineering Department Abu Dhabi United Arab Emirates Abu Dhabi University Electrical Computer and Biomedical Engineering Department Abu Dhabi United Arab Emirates

ISBN: (数字)9781665459952

ISBN: (纸本)9781665459952

We propose real-time vehicle plate number recognition in this study, which aids law enforcement in detecting and stopping wanted vehicles. The system is made up of smart devices that are dispersed throughout the county via major thoroughfares. A camera, an industrial computer, and a wireless RF module are included in each device. The system detects vehicle activity, then recognizes the plate number and matches it to the wanted list plat numbers uploaded to the server by the cops. When the system detects a wanted plate number, it sends an automatic signal to the next police checkpoint via a radio frequency RF module, allowing the officers to intervene and halt the car. Furthermore, without using GPS, the system can be used to track vehicles throughout the country. Each smart unit detects a vehicle license plate number and sends the information to the server, which records the information within the specified time range. Tracking all vehicles in the county and knowing each vehicle when it passes each road by verifying its history would be efficient. The system will assist police in instantly locating and tracking any desired vehicles around the county, saving time and effort by eliminating the need to study the history of video recording devices. The proposed method uses an 80-frame-per-second camera system to evaluate license plates from moving cars traveling at 100 km/h. In scenarios where more than a thousand car images are gathered and examined, our findings demonstrate that the system has a 98 percent recognition accuracy. © 2022 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Translation Identifiability-Guided Unsupervised Cross-Platform Super-Resolution for OCT Images

Translation Identifiability-Guided Unsupervised Cross-Platfo...

引用

Sensor Array and Multichannel Signal Processing Workshop

作者： Jiahui Song Sagar Shrestha Xueshen Li Yu Gan Xiao Fu School of Electrical Engineering and Computer Science Oregon State University Corvallis USA Department of Biomedical Engineering Stevens Insitute of Technology Hoboken USA

ISBN: (数字)9798350344813

ISBN: (纸本)9798350344820

Optical Coherence Tomography (OCT) is a non-invasive technique for obtaining detailed, cross-sectional images of coronary arteries. However, cost-effective OCT systems produce only low-resolution (LR) images. Unsupervised OCT super-resolution (OCT-SR) presents a cost-effective solution, eliminating the need for high-resolution (HR) systems or co-registered LR-HR image pairs. Existing unsupervised OCT-SR methods formulate the SR task as an image-to-image translation problem, and use CycleGAN as their backbone. However, CycleGAN is known to lack translation identifiability that can result in incorrect SR results. Existing methods often empirically combat this issue by using multiple regularization terms to incorporate expert-annotated side information, resulting in complicated learning losses and extensive annotations. This work proposes a translation identifiability-guided framework based on recent advances in unsupervised domain translation. Employing a diversified distribution matching module, our approach guarantees OCT translation identifiability under reasonable conditions using a simple and succinct learning loss. Numerical results indicate that our framework matches or surpasses the state-of-the-art (SOTA) baseline's performance while requiring considerably fewer resources, e.g., annotations, computation time, and memory.

关键词： Annotations Optical coherence tomography Superresolution Optical imaging Optical sensors Task analysis Optical signal processing

来源：评论

学校读者我要写书评

暂无评论

DEEP LEARNING FOR ACCELERATED AND ROBUST MRI RECONSTRUCTION: A REVIEW

arXiv

引用

arXiv 2024年

作者： Heckel, Reinhard Jacob, Mathews Chaudhari, Akshay Perlman, Or Shimron, Efrat Technical University of Munich Department of Computer Engineering Munich Germany University of Iowa Department of Electrical and Computer Engineering Iowa CityIA United States Stanford University Department of Radiology Department of Biomedical Data Science StanfordCA United States Tel Aviv University Department of Biomedical Engineering Tel Aviv Israel Tel Aviv University Sagol School of Neuroscience Tel Aviv Israel Technion - Israel Institute of Technology Department of Electrical and Computer Engineering Department of Biomedical Engineering Haifa Israel

Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction. It focuses on DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. These include end-to-end neural networks, pre-trained networks, generative models, and self-supervised methods. The paper also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling subtle bias. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices. © 2024, CC BY.

关键词： Image reconstruction

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：