检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Mandal, Udayan Amir, Guy Wu, Haoze Daukantas, Ieva Newell, Fletcher Lee Ravaioli, Umberto Meng, Baoluo Durling, Michael Hobbs, Kerianne Ganai, Milan Shim, Tobey Katz, Guy Barrett, Clark Center for AI Safety Stanford University Stanford United States School of CS & Engineering The Hebrew University of Jerusalem Jerusalem Israel Department of Computer Science IT University of Copenhagen Copenhagen Denmark Google Mountain View United States GE Aerospace Research Niskayuna United States Air Force Research Laboratory US Air Force Dayton United States Department of Computer Science Stanford University Stanford United States Department of Data Science Stanford University Stanford United States

In recent years, deep reinforcement learning (DRL) approaches have generated highly successful controllers for a myriad of complex domains. However, the opaque nature of these models limits their applicability in aerospace systems and sasfety-critical domains, in which a single mistake can have dire consequences. In this paper, we present novel advancements in both the training and verification of DRL controllers, which can help ensure their safe behavior. We showcase a design-for-verification approach utilizing k-induction and demonstrate its use in verifying liveness properties. In addition, we also give a brief overview of neural Lyapunov Barrier certificates and summarize their capabilities on a case study. Finally, we describe several other novel reachability-based approaches which, despite failing to provide guarantees of interest, could be effective for verification of other DRL systems, and could be of further interest to the community. Copyright © 2024, The Authors. All rights reserved.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

Reliable Indoor Localization in Multi-Building Environments: Leveraging Environment-Invariant and Position-Related Features

引用

IEEE Internet of Things Journal 2025年

作者： Long, Wenhan Wen, Xinlong Liu, Hao Li, Mengyao Li, Songquan Wu, Yonghui Chen, Fuxiang Liu, Lu Zhu, Rongbo Huazhong Agricultural University College of Informatics Wuhan430070 China Ministry of Education Engineering Research Center of Intelligent Technology for Agriculture Wuhan430070 China Hubei Engineering Technology Research Center of Agricultural Big Data Wuhan430070 China University of Leicester School of Computing and Mathematical Sciences Leicester United Kingdom University of Exeter Department of Computer Science Exeter United Kingdom

Received Signal Strength Indicator (RSSI)-based indoor localization offers a cost-effective solution for autonomous mobile robot navigation in 3D indoor environments, including cross-floor and multi-building structures. However, localization accuracy is fundamentally constrained by the low sampling density and unstable measurement of RSSI data. So far, existing methods neglect cross-environment RSSI coherence (e.g., repeated signal patterns in geometrically similar areas), resulting in unreliable fingerprint databases. What’s more, most approaches fail to model the spatial hierarchy of buildings, floors, and coordinates, which leads to lower accuracy in indoor positioning model predictions. To address these issues, we propose EP-3DLoc, a novel 3D indoor localization framework that combines an Environment-Invariant feature-based data Completion (EIC) method with a Position-Related feature-based Localization (PRL) method. The EIC enhances data quality by filling in sparse RSSI data using environment-invariant features, which are recurring RSSI patterns found in similar environmental structures. The PRL module combines multi-scale RSSI signal processing (raw data and image-like data) with a multi-task network that analyzes location relationships, enhancing localization accuracy in 3D environments. Experimental results on public datasets (TUT2018, UTSIndoorLoc, and UJIIndoorLoc) have demonstrated that EP-3DLoc achieves state-of-the-art performance on indoor localization in multi-building environments. Further testing on the self-constructed dataset HZAUIndoorLoc have revealed that EP-3DLoc not only outperforms existing methods in localization accuracy but also maintains low energy consumption and strong resistance to interference. © 2014 IEEE.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning 7

Impact of CLAHE-based image enhancement for diabetic retinop...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Hayati, Mira Muchtar, Kahlil Roslidar Maulina, Novi Syamsuddin, Irfan Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Universitas Syiah Kuala Banda Aceh23111 Indonesia Faculty of Medicine Universitas Syiah Kuala Banda Aceh23111 Indonesia Department of Computer and Networking Engineering Politeknik Negeri Ujung Pandang Makassar90245 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Diabetic retinopathy (DR) is a type of diabetes mellitus that attacks the retina of the eye. DR will cause patients to experience blindness slowly. Generally, DR can be detected by using a special instrument called an ophthalmoscope to view the inside of the eyeball. However, in conditions where there is a very small difference between the normal image and the DR image, computer-based assistance is needed for maximizing image reading value. In this research, a method of image quality improvement will be carried out which will then be integrated with a classification algorithm based on deep learning. The results of image improvement using Contrast Limited Adaptive Histogram Equalization (CLAHE) shows that the average accuracy of the method on several models is very competitive, 91% for the VGG16 model, 95% for InceptionV3, and 97% for EfficientNet compared to the results original image which only has an accuracy of 87% for VGG16 model, 90% for InceptionV3 model, and 95% for EfficientNet. However, in ResNet34 better accuracy is obtained in the original image with an accuracy of 95% while in the CLAHE image the accuracy value is only 84%. The results of this comprehensive evaluation and recommendation of famous backbone networks can be useful in the computer-aided diagnosis of diabetic retinopathy. © 2022 Elsevier B.V.. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention

arXiv

引用

arXiv 2025年

作者： Wang, Tianyi Fan, Jianan Zhang, Dingxin Liu, Dongnan Xia, Yong Huang, Heng Cai, Weidong School of Computer Science The University of Sydney SydneyNSW2006 Australia National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen518057 China Ningbo Institute of Northwestern Polytechnical University Ningbo315048 China Department of Computer Science University of Maryland College ParkMD20742 United States

Histopathology and transcriptomics are fundamental modalities in cancer diagnostics, encapsulating the morphological and molecular characteristics of the disease. Multi-modal self-supervised learning has demonstrated remarkable potential in learning pathological representations by integrating diverse data sources. Conventional multi-modal integration methods primarily emphasize modality alignment, while paying insufficient attention to retaining the modality-specific intrinsic structures. However, unlike conventional scenarios where multi-modal inputs often share highly overlapping features, histopathology and transcriptomics exhibit pronounced heterogeneity, offering orthogonal yet complementary insights. Histopathology data provides morphological and spatial context, elucidating tissue architecture and cellular topology, whereas transcriptomics data delineates molecular signatures through quantifying gene expression patterns. This inherent disparity introduces a major challenge in aligning these modalities while maintaining modality-specific fidelity. To address these challenges, we present MIRROR, a novel multi-modal representation learning framework designed to foster both modality alignment and retention. MIRROR employs dedicated encoders to extract comprehensive feature representations for each modality, which is further complemented by a modality alignment module to achieve seamless integration between phenotype patterns and molecular profiles. Furthermore, a modality retention module safeguards unique attributes from each modality, while a style clustering module mitigates redundancy and enhances disease-relevant information by modeling and aligning consistent pathological signatures within a clustering space. Extensive evaluations on The Cancer Genome Atlas (TCGA) cohorts for cancer subtyping and survival analysis highlight MIRROR’s superior performance, demonstrating its effectiveness in constructing comprehensive oncological feature representations and be

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Technology Landscape for Epidemiological Prediction and Diagnosis of COVID-19

引用

computers, Materials & Continua 2021年第5期67卷 1679-1696页

作者： Siddhant Banyal Rinky Dwivedi Koyel Datta Gupta Deepak Kumar Sharma Fadi Al-Turjman Leonardo Mostarda Department of Instrumentation and Control Netaji Subhas University of TechnologyNew Delhi110078India Department of Computer Science&Engineering Maharaja Surajmal Institute of TechnologyNew Delhi110058India Department of Information Technology Netaji Subhas University of TechnologyNew Delhi110078India Research Center for AI and IoT Near East UniversityNicosiaMersin10Turkey Computer Science Department Camerino UniversityCamerino62032Italy

The COVID-19 outbreak initiated from the Chinese city of Wuhanand eventually affected almost every nation around the globe. From China,the disease started spreading to the rest of the world. After China, Italybecame the next epicentre of the virus and witnessed a very high death *** nations like the USA became severely hit by SARS-CoV-2 virus. TheWorld Health Organisation, on 11th March 2020, declared COVID-19 a pandemic. To combat the epidemic, the nations from every corner of the worldhas instituted various policies like physical distancing, isolation of infectedpopulation and researching on the potential vaccine of SARS-CoV-2. Toidentify the impact of various policies implemented by the affected countrieson the pandemic spread, a myriad of ai-based models have been presented toanalyse and predict the epidemiological trends of COVID-19. In this work, theauthors present a detailed study of different articial intelligence frameworksapplied for predictive analysis of COVID-19 patient record. The forecastingmodels acquire information from records to detect the pandemic spreadingand thus enabling an opportunity to take immediate actions to reduce thespread of the virus. This paper addresses the research issues and correspondingsolutions associated with the prediction and detection of infectious diseaseslike COVID-19. It further focuses on the study of vaccinations to cope withthe pandemic. Finally, the research challenges in terms of data availability,reliability, the accuracy of the existing prediction models and other open issuesare discussed to outline the future course of this study.

关键词： COVID-19 diagnosis deep learning forecasting models machine learning metaheuristics prediction big data pandemic

来源：评论

学校读者我要写书评

暂无评论

SARA: Semantic-assisted Reinforced Active Learning for Entity Alignment

SARA: Semantic-assisted Reinforced Active Learning for Entit...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ching-Hsuan Liu Chih-Ming Chen Jing-Kai Lou Ming-Feng Tsai Jiun-Lang Huang Chuan-Ju Wang Data Science Degree Program National Taiwan University Academia Sinica Taiwan Research Center for Information Technology Innovation Academia Sinica KKCompany Taiwan Department of Computer Science National Chengchi University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

This paper introduces SARA, a semantic-assisted reinforced active learning framework for enhancing entity alignment (EA) under limited supervision scenarios. SARA addresses the challenges of EA in real-world scenarios, including knowledge graph heterogeneity and limited training ground truth. SARA effectively selects valuable entity pairs with limited labeled data by combining reinforced active learning and semantic information. It utilizes a pair-wise language model based on Sentence-BERT to learn informative name embeddings that capture entity name semantics. These embeddings are combined with structural embeddings and trained using a novel semantic-assisted alignment loss. Extensive experiments on benchmark datasets and a real-world dataset demonstrate the superiority of SARA over existing approaches, particularly in limited labeled data scenarios. The paper also provides insights into fine-tuning strategies, presents ablation studies, and conducts sensitivity analyses to validate the effectiveness of SARA.

关键词： Training Sensitivity analysis Semantics Neural networks Knowledge graphs Benchmark testing data models

来源：评论

学校读者我要写书评

暂无评论

A 1D Plug-and-Play Synthetic data Deep Learning For Undersampled Magnetic Resonance Image Reconstruction

A 1D Plug-and-Play Synthetic Data Deep Learning For Undersam...

引用

IEEE International Conference on Image Processing

作者： Min Xiao Zi Wang Jiefeng Guo Di Guo Xiaobo Qu Institute of Artificial Intelligence Xiamen University Xiamen China Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen China Department of Microelectronics and Integrated Circuit Xiamen University Xiamen China School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Magnetic resonance imaging (MRI) plays a pivotal role in modern medical diagnosis yet is often hindered by the long imaging time. MRI imaging can be accelerated through undersampling, but the introduced aliasing artifacts should be removed during image reconstruction. While deep learning reconstruction methods excel at image de-aliasing, they may yield suboptimal results when training sampling settings differ from those at the time of reconstruction. To decouple from specific sampling settings, we propose using synthetic data to generate a substantial training dataset and pre-train a 1D deep denoiser. We then integrate the trained deep denoiser into the iterative reconstruction process as a replacement for the approximation operator within the deep plug-and-play framework. In vivo results indicate that the proposed method exhibits robust and visually appealing image reconstruction when there is a mismatch between the training and reconstruction undersampling settings, such as different undersampling patterns and sampling rates.

关键词： Training Deep learning In vivo Magnetic resonance imaging Magnetic resonance Training data Trajectory

来源：评论

学校读者我要写书评

暂无评论

Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering

arXiv

引用

arXiv 2024年

作者： Lin, Jiuheng Lai, Yuxuan Feng, Yansong Wangxuan Institute of Computer Technology Peking University China State Key Laboratory of General Artificial Intelligence Peking University China Department of Computer Science The Open University of China China Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of Education China

Conditional question answering (CQA) is an important task that aims to find probable answers and identify missing conditions. Existing approaches struggle with CQA due to two challenges: (1) precisely identifying necessary conditions and the logical relationship, and (2) verifying conditions to detect any that are missing. In this paper, we propose a novel prompting approach, Chain of condition, by first identifying all conditions and constructing their logical relationships explicitly according to the document, then verifying whether these conditions are satisfied, finally solving the logical expression to indicate any missing conditions and generating the answer accordingly. Experiments on two CQA benchmark datasets show our chain of condition outperforms existing prompting baselines, establishing a new state of the art. Furthermore, with only a few examples, our method can facilitate GPT-3.5-Turbo or GPT-4 to outperform all existing supervised models. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Plane Pose Estimation for Cardiac Left Ventricle Coverage Estimation via Deep Adversarial Regression Network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4738-4752页

作者： Zhang, Le Bronik, Kevin Piechnik, Stefan K. Lima, Joao A. C. Neubauer, Stefan Petersen, Steffen E. Frangi, Alejandro F. University of Birmingham School of Engineering College of Engineering and Physical Sciences BirminghamB15 2TT United Kingdom University of Oxford Department of Engineering Science OxfordOX1 3PJ United Kingdom Division of Cardiovascular Medicine OxfordOX3 9DU United Kingdom Johns Hopkins University School of Medicine Division of Cardiology BaltimoreMD21287 United States Queen Mary University of London Centre for Cardiovascular Medicine The William Harvey Research Institute LondonE1 1BB United Kingdom Barts Health Nhs Trust Barts Heart Center LondonE1 1BB United Kingdom The University of Manchester Division of Informatics Imaging and Data Science School of Health Sciences The Department of Computer Science School of Engineering ManchesterM13 9PL United Kingdom

Accurate segmentation of the ventricles plays a crucial role in determining cardiac functional parameters such as ventricular volume, ventricular mass, and ejection fraction. However, poor image quality, such as inadequate coverage of the left ventricle (LV) and right ventricle (RV) in cardiac magnetic resonance (CMR) image sequences, can significantly affect the assessment of cardiac function. This study investigates issues related to missing or corrupted imaging planes, which often lead to incomplete ventricle coverage. To address the challenge of estimating ventricle coverage in CMR images regardless of variations in imaging parameters such as device type, magnetic field strength, and protocol execution, we introduce a novel convolutional neural network (CNN) based on adversarial learning. Additionally, we integrate supplementary information (e.g., cross-view image data) as privileged information to enhance the interpretability of our model's predictions and identify potential biases or inaccuracies. This research represents the first attempt to automatically estimate ventricular coverage by identifying missing slices and plane orientations in CMR images using a dataset-agnostic approach. The effectiveness of the proposed model is demonstrated through the evaluation of datasets from three diverse and sizable image acquisition cohorts, demonstrating superior performance compared to existing methods. © 2020 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Using Meta-Heuristic Methods to Detect Botnet Attacks in Internet of Things

SSRN

引用

SSRN 2023年

作者： Mardani, Shayan Boroujeni, Farsad Zamani Akbari, Mehdi Department of Engineering Sepahan Institute of Higher Education Science and Technology Iran Department of Computer Engineering Islamic Azad University Science and Research Branch Tehran Iran Faculty of Computer Engineering Islamic Azad University Najafabad Branch Najafabad Iran Big Data Research Center Islamic Azad University Najafabad Branch Najafabad Iran

The need for timely detection of botnet attacks due to the increase in the number of Internet of Things devices is very necessary to minimize security risks and ensure network security. Recently, botnet attack detection methods are based on artificial intelligence techniques;And in order to deal with the growing dimensions of Internet of Things data, they have used various filtering and wrapping feature selection methods. In this paper, for the challenge of IoT data dimensions in detecting botnet attacks, a comparison has been made between 7 different old and new meta-heuristic methods including PSO, Giza, RSO, Firefly, PEC, BAT and GWO. In this model, decision tree algorithm is used to detect attacks. The experimental results of the methods on two data sets IOT-BotNet and N-BaioT show that all meta-heuristic methods in binary classification have similar performance and have been able to achieve accuracy above 99%. In detecting the type of attacks (multi-class classification), the results show that the best performance belongs to RSO, Giza, which reached an accuracy of over 99% and are among the latest meta-heuristic methods. The results of the methods show that meta-heuristic feature selection algorithms can effectively reduce data dimensions;So that the accuracy of the proposed attack detection model has increased compared to previous methods. © 2023, The Authors. All rights reserved.

关键词： Botnet

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：