检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mohanad Alkhodari Winok Lapidaire Zhaohan Xiong Turkay Kart Yasser Iturria-Medina Leontios Hadjileontiadis Ahsan Khandoker Adam J. Lewandowski Abhirup Banerjee Paul Leeson Radcliffe Department of Medicine Cardiovascular Clinical Research Facility University of Oxford Oxford UK Department of Biomedical Engineering Healthcare Engineering Innovation Center Khalifa University Abu Dhabi UAE Department of Computing Biomedical Image Analysis Group Imperial College London London UK Neuroinformatics for Personalized Medicine Lab McGill University Montreal Canada Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK

Hypertension is a serious medical condition that affects over a billion people worldwide. The proper management of disease progression requires an extended knowledge of the overall functional and structural changes in the whole body in response to the hypertension. Here, we propose HyperScore, an integrative and unified measure of hypertension progression relative to multi-organ and multi-modality clinical measurements and based on a semi-supervised machine learning (ML) approach. We developed the measure based on a large participating cohort from the UK Biobank database (n=27,099) with over 500 imaging and clinical variables from multiple modalities. The semi-supervised approach was developed based on the contrastive trajectory inference mechanism to provide a score that reflects the proximity of a participant to the disease state (range: 0–1). Modelling revealed that majority of hypertensive participants had scores above 0.25, whereas normotensives had scores below this threshold. The sensitivity and specificity were above 89%, with an area under the receiver operating characteristics of 96.4%. The modelling showed a stable performance when evaluating hidden testing sets on a 10-fold cross-validation scheme with nearly 0.1 error. There was a strong association (r 2 >0.6) between HyperScore and organs’ phenotypic patterns, especially for variables such as white matter hyperintensity and body mass index. This study is the first to potentiate ML-based modelling of hypertension progression from a multi-organ perspective, which could significantly aid in clinical decision making to save lives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DivGCL: A Graph Contrastive Learning Model for Diverse Recommendation 39

DivGCL: A Graph Contrastive Learning Model for Diverse Recom...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Gong, Wenwen Geng, Yangliao Zhang, Dan Zhu, Yifan Xu, Xiaolong Xiang, Haolong Beheshti, Amin Zhang, Xuyun Qi, Lianyong School of Information and Electrical Engineering China Agricultural University China School of Computer Science & Technology Beijing Jiaotong University China Department of Computer Science and Technology Tsinghua University China School of Computer Science Beijing University of Posts and Telecommunications China School of Software Nanjing University of Information Science and Technology China School of Computing Macquarie University Australia College of Computer Science and Technology China University of Petroleum (East China China State Key Lab. for Novel Software Technology Nanjing University China

ISBN: (纸本)157735897X

Graph Contrastive Learning (GCL), as a primary paradigm of graph self-supervised learning, spurs a fruitful line of research in tackling the data sparsity issue by maximizing the consistency of user/item embeddings between different augmented views with random perturbations. However, diversity, as a crucial metric for recommendation performance and user satisfaction, has received rather little attention. In fact, there exists a challenging dilemma in balancing accuracy and diversity. To address these issues, we propose a new Graph Contrastive Learning model for Diversifying recommendations (DivGCL). Inspired by the excellence of the determinant point process (DPP), DivGCL adopts a DPP likelihood-based loss function to achieve an ideal trade-off between diversity and accuracy, optimizing it jointly with the advanced Gaussian noise-augmented GCL objective. Extensive experiments on four popular datasets demonstrate that DivGCL surpasses existing approaches in balancing accuracy and diversity, with an improvement of 23.47% at T@20 (abbreviation for trade-off metric) on ML-1M. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). 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

R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?

引用

IEEE Journal on Selected Topics in Signal Processing 2025年

作者： Li, Chunyi Zhang, Jianbo Zhang, Zicheng Wu, Haoning Tian, Yuan Sun, Wei Lu, Guo Min, Xiongkuo Liu, Xiaohong Lin, Weisi Zhang, Xiao-Ping Zhai, Guangtao Shanghai Jiao Tong University Institute of Image Communication and Network Engineering Shanghai200240 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Shanghai AI Lab Shanghai200232 China East China Normal University School of Communication and Electronic Engineering Shanghai200240 China Shanghai Jiao Tong University John Hopcroft Center Shanghai200240 China Toronto Metropolitan University Department of Electrical Computer and Biomedical Engineering TorontoONM5B 2K3 Canada

The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images will not be as ideal as in simulations, presenting significant challenges for the practical application of LMMs. To address this issue, we introduce R-Bench, a benchmark focused on the Real-world Robustness of LMMs. Specifically, we: (a) model the complete link from user capture to LMMs reception, comprising 33 corruption dimensions, including 7 steps according to the corruption sequence, and 7 groups based on low-level attributes;(b) collect reference/distorted image dataset before/after corruption, including 2,970 question-answer pairs with human labeling;(c) propose comprehensive evaluation for absolute/relative robustness and benchmark 20 mainstream LMMs. Results show that while LMMs can correctly handle the original reference images, their performance is not stable when faced with distorted images, and there is a significant gap in robustness compared to the human visual system. We hope that R-Bench will inspire improving the robustness of LMMs, extending them from experimental simulations to the real-world application. © 2007-2012 IEEE.

关键词： AI-Generated Content Image Compression Perceptual Quality Ultra-Low Bitrate

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Defect Detection Algorithm for Solar Panels

Deep Learning based Defect Detection Algorithm for Solar Pan...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Jiaqi Li Hongxu Li Yifan Wu Hailiang Zhou Luigi Manfredi Peng Li Hong Zhang Department of Key Lab of Industrial Computer Control Engineering Hebei Province Yanshan University Qinhuangdao China Department of Computing Science University of Alberta Edmonton AB Canada Hebei Baoding Jiasheng Photovoltaic Technology Co. Ltd. Department of Institute for Medical Science and Technology (IMSaT) University of Dundee United Kingdom Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

Defect detection of solar panels plays an essential role in guaranteeing product quality within automated production lines. However, traditional manual inspection of solar panel defects suffers from low efficiency. This paper proposes an enhanced YOLOv5 algorithm (EL-YOLOv5) fused with the CBAM hybrid attention module to ensure product quality. The algorithm focuses on detecting five common types of defects that frequently appear on photovoltaic production lines, namely hidden cracks, scratches, broken grids, black spots, and short circuits. This study utilizes publicly available solar panel datasets, as well as datasets collected from actual photovoltaic production lines. These datasets are annotated accordingly and used to train the proposed algorithm. The experimental results demonstrate that the proposed algorithm achieves good performance on both the public and actual solar panel defect datasets. Particularly in actual datasets, where defect features are often less apparent and defects are smaller in size, the proposed algorithm can still detect even minor black spots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PARCIV: Recognizing physical activities having complex interclass variations using semantic data of smartphone

PARCIV: Recognizing physical activities having complex inter...

引用

作者： Usman Sarwar, Muhammad Rehman Javed, Abdul Kulsoom, Farzana Khan, Suleman Tariq, Usman Kashif Bashir, Ali Department of Computer Sciences Air University and ASET: Ambient Systems and Emerging Technologies Lab Islamabad Pakistan National Center for Cyber Security Air University and ASET: Ambient Systems and Emerging Technologies Lab Islamabad Pakistan Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy College of Computer Science Engineering Prince Sattam bin Abdulaziz University Al-Kharj Saudi Arabia School of Computing Mathematics and Digital Technology Manchester Metropolitan University Manchester United Kingdom

Smartphones are equipped with precise hardware sensors including accelerometer, gyroscope, and magnetometer. These devices provide real-time semantic data that can be used to recognize daily life physical activities for personalized smart health assessment. Existing studies focus on the recognition of simple physical activities but they lacked in providing accurate recognition of physical activities having complex interclass variations. Therefore, this research focuses on the accurate recognition of physical activities having complex interclass variations. We propose a two-layered approach called PARCIVthat first clusters similar activities based on semantic data and then recognize them using a machine learning classifier. Our two-layered approach first bounds the highly indistinguishable activities in clusters to avoid misclassification with other distinguishable activities and thereafter recognize them on a fine-grained level within each cluster. To evaluate our approach, we make an android application that collects labeled data by using smartphone sensors from 10 participants, while performing activities. PARCIV recognizes distinguishable as well as indistinguishable activities with high accuracy of 99% on the self-collected dataset. Furthermore, PARCIV achieve 95% accuracy on the publicly available dataset used by state-of-the-art studies. PARCIVoutperforms various state-of-the-art studies by 8%-17% for simple activities as well as complex activities. © 2020 John Wiley & Sons, Ltd.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis and Enhancement of Beamforming Training in 802.11ad

arXiv

引用

arXiv 2023年

作者： Wu, Wen Cheng, Nan Zhang, Ning Yang, Peng Aldubaikhy, Khalid Shen, Xuemin The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada State Key Lab. of ISN The School of Telecommunications Engineering Xidian University Xian710071 China The Department of Computing Sciences Texas A&M University Corpus ChristiTX78412 United States The School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China The Department of Electrical Engineering Qassim University Buraydah52571 Saudi Arabia

Beamforming (BF) training is crucial to establishing reliable millimeter-wave communication connections between stations (STAs) and an access point. In IEEE 802.11ad BF training protocol, all STAs contend for limited BF training opportunities, i.e., associated BF training (A-BFT) slots, which results in severe collisions and significant BF training latency, especially in dense user scenarios. In this paper, we first develop an analytical model to evaluate the BF training protocol performance. Our analytical model accounts for various protocol components, including user density, the number of A-BFT slots, and protocol parameters, i.e., retry limit and contention window size. We then derive the average successful BF training probability, the BF training efficiency and latency. Since the derived BF training efficiency is an implicit function, to reveal the relationship between system parameters and BF training performance, we also derive an approximate expression of BF training efficiency. Theoretical analysis indicates that the BF training efficiency degrades drastically in dense user scenarios. To address this issue, we propose an enhancement scheme which adaptively adjusts the protocol parameters in tune with user density, to improve the BF training performance in dense user scenarios. Extensive simulations are carried out to validate the accuracy of the developed analytical model. In addition, simulation results show that the proposed enhancement scheme can improve the BF training efficiency by 35% in dense user scenarios. © 2023, CC BY-NC-SA.

关键词： Analytical models

来源：评论

学校读者我要写书评

暂无评论

Block Hunter: Federated Learning for Cyber Threat Hunting in Blockchain-based IIoT Networks

arXiv

引用

arXiv 2022年

作者： Yazdinejad, Abbas Dehghantanha, Ali Parizi, Reza M. Hammoudeh, Mohammad Karimipour, Hadis Srivastava, Gautam The Cyber Science Lab University of Guelph Canada The College of Computing and Software Engineering Kennesaw State University GA United States Information & Computer Science Department King Fahd University of Petroleum & Minerals Saudi Arabia The School of Engineering Department of Electrical and Software Engineering The University of Calgary Alberta Canada The Department of Math and Computer Science Brandon University Manitoba Canada The Research Centre for Interneural Computing China Medical University Taichung Taiwan

Nowadays, blockchain-based technologies are being developed in various industries to improve data security. In the context of the Industrial Internet of Things (IIoT), a chain-based network is one of the most notable applications of blockchain technology. IIoT devices have become increasingly prevalent in our digital world, especially in support of developing smart factories. Although blockchain is a powerful tool, it is vulnerable to cyber attacks. Detecting anomalies in blockchain-based IIoT networks in smart factories is crucial in protecting networks and systems from unexpected attacks. In this paper, we use Federated Learning (FL) to build a threat hunting framework called Block Hunter to automatically hunt for attacks in blockchain-based IIoT networks. Block Hunter utilizes a cluster-based architecture for anomaly detection combined with several machine learning models in a federated environment. To the best of our knowledge, Block Hunter is the first federated threat hunting model in IIoT networks that identifies anomalous behavior while preserving privacy. Our results prove the efficiency of the Block Hunter in detecting anomalous activities with high accuracy and minimum required bandwidth. © 2022, CC BY.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

The impact of feature importance methods on the interpretation of defect classifiers

arXiv

引用

arXiv 2022年

作者： Rajbahadur, Gopi Krishnan Wang, Shaowei Oliva, Gustavo A. Kamei, Yasutaka Hassan, Ahmed E. The Centre for Software Excellence Huawei Canada School of Computing Queen’s University Canada The department of computer science University of Manitoba Canada Lab Graduate School and Faulty of Information Science and Electrical Engineering Kyushu University Japan

Classifier specific (CS) and classifier agnostic (CA) feature importance methods are widely used (often interchangeably) by prior studies to derive feature importance ranks from a defect classifier. However, different feature importance methods are likely to compute different feature importance ranks even for the same dataset and classifier. Hence such interchangeable use of feature importance methods can lead to conclusion instabilities unless there is a strong agreement among different methods. Therefore, in this paper, we evaluate the agreement between the feature importance ranks associated with the studied classifiers through a case study of 18 software projects and six commonly used classifiers. We find that: 1) The computed feature importance ranks by CA and CS methods do not always strongly agree with each other. 2) The computed feature importance ranks by the studied CA methods exhibit a strong agreement including the features reported at top-1 and top-3 ranks for a given dataset and classifier, while even the commonly used CS methods yield vastly different feature importance ranks. Such findings raise concerns about the stability of conclusions across replicated studies. We further observe that the commonly used defect datasets are rife with feature interactions and these feature interactions impact the computed feature importance ranks of the CS methods (not the CA methods). We demonstrate that removing these feature interactions, even with simple methods like CFS improves agreement between the computed feature importance ranks of CA and CS methods. In light of our findings, we provide guidelines for stakeholders and practitioners when performing model interpretation and directions for future research, e.g., future research is needed to investigate the impact of advanced feature interaction removal methods on computed feature importance ranks of different CS methods. © 2022, CC BY-NC-ND.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Few-shot Object Detection on Remote Sensing Images

arXiv

引用

arXiv 2020年

作者： Deng, Jingyu Li, Xiang Fang, Yi Multimedia and Visual Computing Lab NYU Tandon and Abu Dhabi Department of Electrical and Computer Engineering NYU Tandon United States Department of Electrical and Computer Engineering NYU Abu Dhabi United Arab Emirates Multimedia and Visual Computing Lab NYU Tandon and Abu Dhabi Department of Electrical and Computer Engineering Abu Dhabi United Arab Emirates

In this paper, we deal with the problem of object detection on remote sensing images. Previous methods have developed numerous deep CNN-based methods for object detection on remote sensing images and the report remarkable achievements in detection performance and efficiency. However, current CNN-based methods mostly require a large number of annotated samples to train deep neural networks and tend to have limited generalization abilities for unseen object categories. In this paper, we introduce a few-shot learning-based method for object detection on remote sensing images where only a few annotated samples are provided for the unseen object categories. More specifically, our model contains three main components: a meta feature extractor that learns to extract feature representations from input images, a reweighting module that learn to adaptively assign different weights for each feature representation from the support images, and a bounding box prediction module that carries out object detection on the reweighted feature maps. We build our few-shot object detection model upon YOLOv3 architecture and develop a multi-scale object detection framework. Experiments on two benchmark datasets demonstrate that with only a few annotated samples our model can still achieve a satisfying detection performance on remote sensing images and the performance of our model is significantly better than the well-established baseline models. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Encryption with Image Steganography Based Data Hiding Technique in IIoT Environment

引用

computers, Materials & Continua 2022年第7期72卷 1323-1338页

作者： Mahmoud Ragab Samah Alshehri Hani A.Alhadrami Faris Kateb Ehab Bahaudien Ashary SAbdel-khalek Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Centre of Artificial Intelligence for Precision Medicines King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Mathematics Faculty of ScienceAl-Azhar UniversityNaser City11884CairoEgypt Department of Pharmacy Practice Faculty of PharmacyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Medical Laboratory Technology Faculty of Applied Medical SciencesKing Abdulaziz UniversityJeddah21589Saudi Arabia Molecular Diagnostic Lab King Abdulaziz University HospitalKing Abdulaziz UniversityJeddah21589Saudi Arabia Special Infectious Agent Unit King Fahd Medical Research CenterKing Abdulaziz UniversityJeddah21589Saudi Arabia Electrical and Computer Engineering Department Faculty of EngineeringKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Mathematics Faculty of ScienceTaif UniversityTaif21944Saudi Arabia Department of Mathematics Faculty of ScienceSohag UniversitySohag82524Egypt

Rapid advancements of the Industrial Internet of Things(IIoT)and artificial intelligence(AI)pose serious security issues by revealing secret ***,security data becomes a crucial issue in IIoT communication where secrecy needs to be guaranteed in real ***,AI techniques can be utilized to design image steganographic techniques in *** addition,encryption techniques act as an important role to save the actual information generated from the IIoT devices to avoid unauthorized *** order to accomplish secure data transmission in IIoT environment,this study presents novel encryption with image steganography based data hiding technique(EISDHT)for IIoT *** proposed EIS-DHT technique involves a new quantum black widow optimization(QBWO)to competently choose the pixel values for hiding secrete data in the cover *** addition,the multi-level discrete wavelet transform(DWT)based transformation process takes ***,the secret image is divided into three R,G,and B bands which are then individually encrypted using Blowfish,Twofish,and Lorenz Hyperchaotic *** last,the stego image gets generated by placing the encrypted images into the optimum pixel locations of the cover *** order to validate the enhanced data hiding performance of the EIS-DHT technique,a set of simulation analyses take place and the results are inspected interms of different *** experimental outcomes stated the supremacy of the EIS-DHT technique over the other existing techniques and ensure maximum security.

关键词： IIoT security data hiding technique image steganography encryption secure communication

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

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

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：