检索结果-内蒙古大学图书馆

A Novel Self-Supervised Learning Network for Binocular Disparity Estimation

computer Modeling in engineering & Sciences 2025年第1期142卷 209-229页

作者： Jiawei Tian Yu Zhou Xiaobing Chen Salman A.AlQahtani Hongrong Chen Bo Yang Siyu Lu Wenfeng Zheng Department of Computer Science and Engineering Major in Bio Artificial IntelligenceHanyang UniversityAnsan-si15577Republic of Korea School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA 70803USA Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11574Saudi Arabia School of Automation University of Electronic Science and Technology of ChinaChengdu610054China

Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical *** study proposes a novel end-to-end disparity estimation model to address these *** approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting *** study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and *** model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video *** results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing ***,the model exhibited faster convergence during training,contributing to overall performance *** study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.

关键词： Parallax estimation parallax regression model self-supervised learning Pseudo-Siamese neural network pyramid dilated convolution binocular disparity estimation

来源：评论

学校读者我要写书评

暂无评论

An AI-Enabled Framework for Transparency and Interpretability in Cardiovascular Disease Risk Prediction

引用

computers, Materials & Continua 2025年第3期82卷 5057-5078页

作者： Isha Kiran Shahzad Ali Sajawal ur Rehman Khan Musaed Alhussein Sheraz Aslam Khursheed Aurangzeb Department of Computer Science University of Engineering and TechnologyLahore39161Pakistan Dipartimento di Farmacia e Biotecnologie Alma Mater Studiorum—Universita di BolognaBologna40126Italy Department of Information Sciences University of EducationLahore54770Pakistan Department of Computer Science National Textile UniversityKarachi CampusKarachi74900Pakistan Department of Computer Science National Textile UniversityFaisalabad37610Pakistan Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Electrical Engineering Computer Engineeringand InformaticsCyprus University of TechnologyLimassol3036Cyprus Department of Computer Science CTL EurocollegeLimassol3077Cyprus

Cardiovascular disease(CVD)remains a leading global health challenge due to its high mortality rate and the complexity of early diagnosis,driven by risk factors such as hypertension,high cholesterol,and irregular pulse *** diagnostic methods often struggle with the nuanced interplay of these risk factors,making early detection *** this research,we propose a novel artificial intelligence-enabled(AI-enabled)framework for CVD risk prediction that integrates machine learning(ML)with eXplainable AI(XAI)to provide both high-accuracy predictions and transparent,interpretable *** to existing studies that typically focus on either optimizing ML performance or using XAI separately for local or global explanations,our approach uniquely combines both local and global interpretability using Local Interpretable Model-Agnostic Explanations(LIME)and SHapley Additive exPlanations(SHAP).This dual integration enhances the interpretability of the model and facilitates clinicians to comprehensively understand not just what the model predicts but also why those predictions are made by identifying the contribution of different risk factors,which is crucial for transparent and informed decision-making in *** framework uses ML techniques such as K-nearest neighbors(KNN),gradient boosting,random forest,and decision tree,trained on a cardiovascular ***,the integration of LIME and SHAP provides patient-specific insights alongside global trends,ensuring that clinicians receive comprehensive and actionable *** experimental results achieve 98%accuracy with the Random Forest model,with precision,recall,and F1-scores of 97%,98%,and 98%,*** innovative combination of SHAP and LIME sets a new benchmark in CVD prediction by integrating advanced ML accuracy with robust interpretability,fills a critical gap in existing *** framework paves the way for more explainable and transparent decision-making in he

关键词： Artificial Intelligence cardiovascular disease(CVD) explainability eXplainable AI(XAI) interpretability LIME machine learning(ML) SHAP

来源：评论

学校读者我要写书评

暂无评论

Close Quarters Permittivity Detection Based on Tagging Antenna Sensor for Solid Material Characterization

引用

Progress in Electromagnetics Research C 2025年 154卷 21-29页

作者： Alam, Syah Surjati, Indra Mardian, Raden D. Sari, Lydia Daffin, Ghatfan Iznih Zakaria, Zahriladha Asrar, Leni D. Firmansyah, Teguh Department of Electrical Engineering Universitas Trisakti West Jakarta11440 Indonesia Faculty of Electronic and Computer Engineering and Technology Universiti Teknikal Malaysia Melaka 76100 Malaysia Department of Electrical Engineering Universitas Sultan Ageng Tirtayasa Banten 42117 Indonesia

This research proposes a tagging antenna sensor for permittivity detection of solid materials based on a close quarter approach. The sensor is proposed to operate at a frequency of 2.53 GHz using a single port resonator with a reflection coefficient (S11) ≤ −10 dB. The sample is placed directly in the sensing area of the antenna sensor based on the concentration of the electric field. Permittivity detection is proposed based on the resonant frequency shift of the transmission coefficient (S21) using interrogator antennas separated by a distance of (d) = 100 mm determined using the Fresnel region. Based on the measurement results, the antenna sensor has a high accuracy of 96% while the sensitivity and ∆F are 0.39% and 0.012 GHz, respectively. Moreover, the sensitivity ofthe proposed sensor is still low due the low concentration of the electric field. Therefore, increasing the sensitivity of the antenna sensor can be recommended as further work such as combining the structure of single port resonator with another structure such as interdigital capacitor and artificial magnetic conductor (AMC). Finally, this research makes a significant contribution to the permittivity detection of solid materials with a close quarter approach to support real time and flexible measurements and can be recommended for several applications for the biomedical, pharmaceutical, and material quality control industries. © 2025, Electromagnetics Academy. All rights reserved.

关键词： Permittivity measurement

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-based AI for COVID-19 detection: a comprehensive review of public and private lung ultrasound datasets and studies

引用

Multimedia Tools and Applications 2025年 1-55页

作者： Morshed, Abrar Al Shihab, Abdulla Jahin, Md Abrar Al Nahian, Md Jaber Hossain Sarker, Md Murad Ibne Wadud, Md Sharjis Uddin, Mohammad Istiaq Imtiaz Siraji, Muntequa Anjum, Nafisa Shristy, Sumiya Rajjab Rahman, Tanvin Khatun, Mahmuda Rubel Dewan, Md Hossain, Mosaddeq Sultana, Razia Chakma, Ripel Emon, Sonet Barua Islam, Towhidul Hussain, Mohammad Arafat Department of Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka1208 Bangladesh Department of Electrical and Telecommunication Engineering Daffodil International University Dhaka1216 Bangladesh Khulna9203 Bangladesh Okinawa904-0412 Japan Department of Information and Communication Technology Bangladesh University of Professionals Dhaka1216 Bangladesh Department of Information and Communication Technology Comilla University Cumilla3506 Bangladesh Department of Biomedical Physics and Technology University of Dhaka Dhaka1000 Bangladesh Department of Computer Science and Engineering International Islamic University Chittagong Chittagong4318 Bangladesh Department of Electrical and Electronic Engineering Islamic University of Technology Gazipur1704 Bangladesh Department of Electronics and Telecommunication Engineering Chittagong University of Engineering and Technology Chittagong4349 Bangladesh Department of Computer Science and Engineering Notre Dame University Bangladesh Dhaka1000 Bangladesh Department of Electrical and Electronic Engineering Khulna University of Engineering & Technology Khulna9203 Bangladesh Department of Computer Science and Engineering Institute of Science and Technology Dhaka1209 Bangladesh Department of Electronics and Communication Engineering Institute of Science and Technology Dhaka1209 Bangladesh Department of Mathematics Jahangirnagar University Dhaka1342 Bangladesh Department of Electrical and Electronic Engineering Daffodil International University Dhaka1216 Bangladesh Department of Electrical and Electronic Engineering Dhaka University of Engineering and Technology Gazipur1707 Bangladesh Department of Computer Science and Telecommunication Engineering Noakhali Science and Technology University Noakhali3814 Bangladesh Department of Computer Science and Engineering Northern University Bangladesh Dhaka1230 Bangladesh Boston Children’s Hospital Harvard Medical School BostonMA02

The COVID-19 pandemic has affected millions of people globally, with respiratory organs being strongly affected in individuals with comorbidities. Medical imaging-based diagnosis and prognosis have become increasingly popular in clinical settings for detecting COVID-19 lung infections. Among various medical imaging modalities, ultrasound stands out as a low-cost, mobile, and radiation-safe imaging technology. In this comprehensive review, we focus on AI-driven studies utilizing lung ultrasound (LUS) for COVID-19 detection and analysis. We provide a detailed overview of both publicly available and private LUS datasets and categorize the AI studies according to the dataset they used. Additionally, we systematically analyzed and tabulated the studies across various dimensions, including data preprocessing methods, AI models, cross-validation techniques, and evaluation metrics. In total, we reviewed 60 articles, 41 of which utilized public datasets, while the remaining employed private data. Our findings suggest that ultrasound-based AI studies for COVID-19 detection have great potential for clinical use, especially for children and pregnant women. Our review also provides a useful summary for future researchers and clinicians who may be interested in the field. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Minimum Data Rate Maximization for Uplink Pinching-Antenna Systems

引用

IEEE Wireless Communications Letters 2025年第5期14卷 1516-1520页

作者： Tegos, Sotiris A. Diamantoulakis, Panagiotis D. Ding, Zhiguo Karagiannidis, George K. Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki54124 Greece University of Manchester Department of Electrical and Electronic Engineering ManchesterM13 9PL United Kingdom Khalifa University Department of Computer and Information Engineering Abu Dhabi United Arab Emirates

This letter addresses, for the first time, the uplink performance optimization of multi-user pinching-antenna (PA) systems, recently developed for next-generation wireless networks. By leveraging the unique capabilities of PAs to dynamically configure wireless channels, we focus on maximizing the minimum achievable data rate between devices to achieve a balanced trade-off between throughput and fairness. An effective approach is proposed that separately optimizes the positions of the PAs and the resource allocation. The antenna positioning problem is reformulated into a convex one, while a closed-form solution is provided for the resource allocation. Simulation results demonstrate the superior performance of the investigated system using the proposed algorithm over corresponding counterparts, emphasizing the significant potential of PA systems for robust and efficient uplink communication in next-generation wireless networks. © 2012 IEEE.

关键词： Antennas Uplink Resource management Wireless communication Optimization Transmitting antennas Reliability Performance evaluation Next generation networking AWGN

来源：评论

学校读者我要写书评

暂无评论

Binary-Level Formal Verification Based Automatic Security Ensurement for PLC in Industrial IoT

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2211-2226页

作者： Zhang, Xuankai Li, Jianhua Wu, Jun Chen, Guoxing Meng, Yan Zhu, Haojin Zhang, Xiaosong Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai200240 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu610054 China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518055 China

Currently, the security of the control logic of Programmable Logic Controllers (PLCs) is facing a serious threat, significantly impacting industrial production. Consequently, ensuring the security of PLC control logic becomes imperative. Formal verification emerges as a promising methodology for verifing PLC security through behavioral modeling and security testing. However, existing formal verification approaches primarily focus on modeling the PLC source code, overlooking the identification of compile-time errors and real-time runtime logic checks. Therefore, it is essential to apply formal verification to PLC control logic at the binary level. In this study, we introduce VoICS, a system designed to facilitate binary-level formal verification. Using reverse engineering, VoICS automatically parses PLC programs written by various programming languages at the binary level and constructs control flow graphs (CFGs). Furthermore, we use an algorithm combining two model optimization methods (i.e., trim invalid states and unnecessary states compression) to convert the reversed PLC assembly program into nuXmv format model. Lastly, VoICS establishes the corresponding constraints and performs formal verification on the model using nuXmv. The evaluation results demonstrate the capability of VoICS in identifying instances of unreliable control logic within PLC control programs, thus reinforcing the dependability of the industrial automation system. © 2024 IEEE.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

Measuring the Discrepancy between 3D Geometric Models using Directional Distance Fields

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 1-16页

作者： Ren, Siyu Hou, Junhui Chen, Xiaodong Xiong, Hongkai Wang, Wenping City University of Hong Kong Department of Computer Science Hong Kong Tianjin University School of Precision Instruments and OptoElectronic Engineering Tianjin300072 China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai200240 China Texas A& M University Department of Computer Science & Engineering United States

Qualifying the discrepancy between 3D geometric models, which could be represented with either point clouds or triangle meshes, is a pivotal issue with board applications. Existing methods mainly focus on directly establishing the correspondence between two models and then aggregating point-wise distance between corresponding points, resulting in them being either inefficient or ineffective. In this paper, we propose DirDist, an efficient, effective, robust, and differentiable distance metric for 3D geometry data. Specifically, we construct DirDist based on the proposed implicit representation of 3D models, namely directional distance field (DDF), which defines the directional distances of 3D points to a model to capture its local surface geometry. We then transfer the discrepancy between two 3D geometric models as the discrepancy between their DDFs defined on an identical domain, naturally establishing model correspondence. To demonstrate the advantage of our DirDist, we explore various distance metric-driven 3D geometric modeling tasks, including template surface fitting, rigid registration, non-rigid registration, scene flow estimation and human pose optimization. Extensive experiments show that our DirDist achieves significantly higher accuracy under all tasks. As a generic distance metric, DirDist has the potential to advance the field of 3D geometric modeling. © 1979-2012 IEEE.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Routing and Spectrum Allocation in Broadband Quantum Entanglement Distribution

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1856-1870页

作者： Bali, Rohan Tittelbaugh, Ashley N. Jenkins, Shelbi L. Agrawal, Anuj Horgan, Jerry Ruffini, Marco Kilper, Daniel C. Bash, Boulat A. The Department of Electrical and Computer Engineering Department University of Arizona TucsonAZ United States The School of Computer Science and Statistics CONNECT Center Trinity College Dublin Dublin Ireland The Electronic and Electrical Engineering Department CONNECT Centre Trinity College Dublin Dublin Ireland

We investigate resource allocation for quantum entanglement distribution over an optical network. We characterize and model a network architecture that employs a single broadband quasi-deterministic time-frequency heralded Einstein-Podolsky-Rosen (EPR) pair source, and develop a routing and spectrum allocation scheme for distributing entangled photon pairs over such a network. As our setting allows separately solving the routing and spectrum allocation problems, we first find an optimal polynomial-time routing algorithm. We then employ max-min fairness criterion for spectrum allocation, which presents an NP-hard problem. Thus, we focus on approximately-optimal schemes. We compare their performance by evaluating the max-min and median number of EPR-pair rates assigned by them, and the associated Jain index. We identify two polynomial-time approximation algorithms that perform well, or better than others under these metrics. We also investigate scalability by analyzing how the network size and connectivity affect performance using Watts-Strogatz random graphs. We find that a spectrum allocation approach that achieves higher minimum EPR-pair rate can perform significantly worse when the median EPR-pair rate, Jain index, and computational resources are considered. Additionally, we evaluate the effect of the source node placement on the performance. © 2025 IEEE. All rights reserved.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Ultra Reliable and Low Latency Vehicular OCC

引用

IEEE Transactions on Communications 2025年第5期73卷 3254-3267页

作者： Islam, Amirul Thomos, Nikolaos Musavian, Leila Department of Electrical and Electronics Engineering Dhaka1229 Bangladesh University of Essex School of Computer Science and Electronic Engineering ColchesterCO4 3SQ United Kingdom

In this paper, we present a deep reinforcement learning (DRL) framework for vehicular optical camera communication (OCC) systems that ensures ultra-reliable and low-latency communication (uRLLC). We first formulate a throughput maximization problem that aims at optimizing speed of vehicles, channel code rate, and modulation order while respecting the uRLLC requirements. We model reliability by satisfying a target bit error rate and latency as transmission latency. To improve the transmission rate and provide high reliability and low latency, our scheme uses low-density parity-check codes and adaptive modulation. We then solve the optimization problem using the actor-critic-based DRL scheme with Wolpertinger framework. We employ a deep deterministic policy gradient algorithm to operate over continuous action spaces. The evaluation confirms that our proposed DRL-based optimization scheme achieves superior performance compared to radio frequency-based communication systems as well as variants of the proposed scheme. Finally, we verify through simulations that our proposed solution can maximize the communication rate while meeting the uRLLC constraints. © 1972-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DGeC: Dynamically and Globally Enhanced Convolution

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 921-933页

作者： Zhang, Zihang Liu, Yuling Zhou, Zhili Yang, Gaobo Liao, Xin Wu, Q. M. Jonathan Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Guangzhou University Institute of Artificial Intelligence and Blockchain Guangzhou510006 China University of Windsor Department of Electrical and Computer Engineering WindsorON250101 Canada

We explore the reasons for the poorer feature extraction ability of vanilla convolution and discover that there mainly exist three key factors that restrict its representation capability, i.e., regular sampling, static aggregation, and limited receptive field. With the cost of extra parameters and computations, existing approaches merely alleviate part of the limitations. It drives us to seek a more lightweight operator to further improve the extracted image features. Through a closer examination of the convolution process, we discover that it is composed of two distinct interactions: spatial-wise interaction and channel-wise interaction. Based on this discovery, we decouple the convolutional blocks into these two interactions which not only reduces the parameters and computations but also enables a richer ensemble of interactions. Then, we propose the dynamically and globally enhanced convolution (DGeC), which includes several components as follows: a dynamic area perceptor block (DAP) that dynamically samples spatial cues, an adaptive global context block (AGC) that introduces the location-aware global image information, and a channel attention perceptor block (CAP) that merges different channel-wise features. The experiments on ImageNet for image classification and on COCO-2017 for object detection validate the effectiveness of DGeC. As a result, our proposed method consistently improves the performance with fewer parameters and computations. In particular, DGeC achieves a 3.1% improvement in top-1 accuracy on ImageNet dataset compared to ResNet50. Moreover, with Faster RCNN and RetinaNet, our DGeC-ResNet50 also consistently outperforms ResNet and ResNeXt. © 2024 IEEE.

关键词： Convolutional neural networks

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：