检索结果-内蒙古大学图书馆

Multi-Modality and Feature Fusion-Based COVID-19 Detection Through Long Short-Term Memory

computers, Materials & Continua 2022年第9期72卷 4357-4374页

作者： Noureen Fatima Rashid Jahangir Ghulam Mujtaba Adnan Akhunzada Zahid Hussain Shaikh Faiza Qureshi Center of Excellence for Robotics Artificial Intelligenceand BlockchainDepartment of Computer ScienceSukkur IBA UniversitySukkurPakistan Department of Computer Science COMSATS University Islamabad–Vehari CampusPakistan Faculty of Computing and Informatics University Malaysia SabahKota Kinabalu88400Malaysia Department of Mathematics Sukkur IBA UniversitySukkurPakistan

The Coronavirus Disease 2019(COVID-19)pandemic poses the worldwide challenges surpassing the boundaries of country,religion,race,and *** current benchmark method for the detection of COVID-19 is the reverse transcription polymerase chain reaction(RT-PCR)***,this testing method is accurate enough for the diagnosis of ***,it is time-consuming,expensive,expert-dependent,and violates social *** this paper,this research proposed an effective multimodality-based and feature fusion-based(MMFF)COVID-19 detection technique through deep neural *** multi-modality,we have utilized the cough samples,breathe samples and sound samples of healthy as well as COVID-19 patients from publicly available COSWARA *** set of experimental analyses were performed to evaluate the performance of our proposed *** useful features were extracted from the aforementioned modalities that were then fed as an input to long short-term memory recurrent neural network algorithms for the classification *** set of experimental analyses were performed to evaluate the performance of our proposed *** experimental results showed that our proposed approach outperformed compared to four baseline approaches published *** believe that our proposed technique will assists potential users to diagnose the COVID-19 without the intervention of any expert in minimum amount of time.

关键词： Covid-19 detection long short-term memory feature fusion deep learning audio classification

来源：评论

学校读者我要写书评

暂无评论

Unpaired Shadow Removal: Enhancing Attention to Shadow Areas via Dropkey

Unpaired Shadow Removal: Enhancing Attention to Shadow Areas...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Yang, Jaewon Shin, Ukcheol Cho, Donghyeon Chungnam National University Dept. of Electronics Engineering Daejeon Korea Republic of Robotics Institute Carnegie Mellon University Pittsburgh United States Hanyang University Dept. of Computer Science Seoul Korea Republic of

ISBN: (纸本)9798331510756

Shadows appear in image areas where an object obstructs the light path. These areas, having lower values than non-shadow areas, degrade image quality and lead to issues in object recognition and segmentation. Supervised shadow removal depends on datasets with shadow and shadow-free image pairs, sparking increased interest in unpaired techniques. However, unpaired shadow removal faces challenges in accurately focusing on shadow areas without direct supervisory signals from ground truth. Consequently, shadows are not effectively removed, and non-shadow areas may suffer from unintended distortions. In this paper, we introduce a transformer-based network designed to identify shadow areas accurately, leveraging global context through spatial and channel attention mechanisms. Additionally, in the training phase, the transformer network is trained to precisely concentrate on shadow areas using a domain classifier and a dropkey mechanism, which randomly drops features of the keys to enhance focus. Our method is tested across several benchmark datasets for shadow removal, such as ISTD, ISTD+, SRD and WSRD, demonstrating better performance compared to current unpaired approaches. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study of Keypoint Descriptor Fusion

An Experimental Study of Keypoint Descriptor Fusion

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Pan, Yaling He, Li Guan, Yisheng Zhang, Hong Guangzhou China Southern University of Science and Technology Shenzhen Key Laboratory of Robotics and Computer Vision Shenzhen China

ISBN: (纸本)9781665481090

Local feature descriptors play a crucial role in computer vision problems, especially robot motion. Existing descriptors are highly accurate, but their performance de-pends on the influence of distracting factors, such as illumi-nation and viewpoint. There is room for further improvement of these descriptors. In this paper, we provide an in-depth analysis of several exciting features of the descriptor fusion model (DFM) we have proposed in our recent work, which uses an autoencoder to combine descriptors and exploit their respective advantages. With this DFM framework, we fur-ther validate that fused descriptors can retain advantageous properties and that our DFM is a generally applicable method with respect to various component descriptors. Specifically, we evaluate multiple combinations of hand-crafted and CNN descriptors concerning their performance on a benchmark dataset with illumination and viewpoint changes to obtain comprehensive experimental results. The results show that the fused descriptors have better matching accuracy than their component descriptors. © 2022 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Deep Transformer Network and CNN Model with About 200k Parameters to Classify P300 EEG Signal

Deep Transformer Network and CNN Model with About 200k Param...

引用

2023 IEEE International Conference on Smart Information Systems and Technologies, SIST 2023

作者： Otarbay, Zhenis Orazaly, Merey Assaiyn, Yerkegul Chagirov, Sanzhar Pernebayev, Sanzhar Tleuzhan, Amir Seds Nazarbayev University Department of Robotics Astana Kazakhstan Astana It University Department of Computer Science Astana Kazakhstan Astana It University Dept of Is&cs Astana Kazakhstan

ISBN: (纸本)9798350335040

This research gathers participants' electroencephalographic (EEG) data to build classifiers that can decode users' mental states. Although deep learning models can incorporate domain-dependent feature extraction into the classifier design, the architecture selection process for BCIs is often based on domain expertise. This paper examines whether it can build reliable classifiers for interpreting P300 event-related potentials using a systematic model selection mixed with common deep learning architectures. We report the findings of a CNNTransformer network model with 50k and 200k parameters in particular. We systematically investigate if a hybrid architecture which is Transformer and CNN, can improve the classification performance of P300 datasets. Because we would like to know how to improve the model selection process for P300 signals data analysis. To help the readers understand that the best model selection strategy with more muscular models than the existing ones may make the lives of stroke patients more convenient. If our readers are targeting to know the modern muscular deep learning architectures to analyze their recorded P300 dataset, then we recommend reading this paper. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Classification of Areca Nut Yellow Leaf Disease with ResNet-50 CNN

Deep Learning-Based Classification of Areca Nut Yellow Leaf ...

引用

2024 IEEE International Conference on Recent Advances in science and Engineering Technology, ICRASET 2024

作者： Veeresha, R.K. Lathish Kumar, N.D. Shetty, Samarth S. Prasad, Shrajan G. Poojary, Swaroop S. Karegoudra, Shilpa Koten, Hasan Department of Robotics and Artificial Intelligence Udupi574110 India Department of Computer Science and Engineering Udupi574110 India Istanbul Medeniyet University Faculty of Engineering and Pure Sciences Department of Mechanical Engineering Istanbul Turkey

ISBN: (纸本)9798350388602

Detecting healthy arecanut leaves, yellow leaf disease in arecanut, and differentiating these from other types of leaves using deep learning involves designing an advanced neural network model for precise image classification. The model is trained on a dataset comprising images of healthy arecanut leaves, arecanut leaves affected by yellow leaf disease, and various other leaves from different plant species. Convolution Neural Networks (CNNs) are leveraged to extract and analyze intricate patterns in the images, enabling the model to effectively classify each leaf type. Transfer learning techniques might be utilized to improve the model's performance and adaptability. The model's effectiveness is evaluated using accuracy, precision, recall, and F1 score on a dedicated test dataset. This paper explores the methodology and results of employing image detection for the identification of healthy arecanut leaves, yellow leaf disease, and other leaf types, with potential applications in agricultural diagnostics, disease management, and crop monitoring. © 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

Aug3D: Augmenting large scale outdoor datasets for Generalizable Novel View Synthesis

arXiv

引用

arXiv 2025年

作者： Rauniyar, Aditya Alama, Omar Yong, Silong Sycara, Katia Scherer, Sebastian Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States

Recent photorealistic Novel View Synthesis (NVS) advances have increasingly gained attention. However, these approaches remain constrained to small indoor scenes. While optimization-based NVS models have made attempts to address this, generalizable feed-forward methods—offering significant advantages—remain underexplored. In this work, we train PixelNeRF, a feed-forward NVS model, on the large-scale UrbanScene3D dataset. We propose four training strategies to cluster and train on this dataset, highlighting that performance is hindered by limited view overlap. To address this, we introduce Aug3D, an augmentation technique that leverages reconstructed scenes using traditional Structure-from-Motion (SfM). Aug3D generates well-conditioned novel views through grid and semantic sampling to enhance feed-forward NVS model learning. Our experiments reveal that reducing the number of views per cluster from 20 to 10 improves PSNR by 10%, but the performance remains suboptimal. Aug3D further addresses this by combining the newly generated novel views with the original dataset, demonstrating its effectiveness in improving the model’s ability to predict novel views. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

On the Enhancement of Energy Efficiency of Wireless Rechargeable Sensor Networks through Mobile Charger Scheduling 2

On the Enhancement of Energy Efficiency of Wireless Recharge...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Kamaruzzaman, Md. Chandra, Abhijit Azharuddin, Md. The Neotia University Dept.of Robotics and Automation Kolkata India Jadavpur University Dept. of Instrumentation and Electronics Engineering Kolkata India Aliah University Dept. of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798350382952

In recent years, wireless rechargeable sensor networks (WRSNs) have become more popular because of its diverse array of applications. However, the limited energy resources of individual sensors pose a significant challenge in maintaining network operations over an extended period. To address this challenge, this research paper presents an energy-efficient scheduling scheme based on distance based scheduling for mobile charging vehicle (MCV) in WRSNs. The proposed scheme capitalizes on the MCV, allowing them to dynamically adjust their charging schedules to cater to the energy demands of sensor nodes (SNs). By efficiently allocating charging tasks to MCV, the scheme aims to balance the energy distribution and mitigate the energy imbalance across the network. By conducting comprehensive simulations with various scenarios, the proposed scheme has been compared with some existing schemes in relation to charging path length, total energy received and charging utility. The simulation results manifest significant advantages of the proposed scheme. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware hybrid paradigm of nonlinear MPC and model-based RL for offroad navigation: Exploration of transformers in the predictive model

Uncertainty-aware hybrid paradigm of nonlinear MPC and model...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Faraz Lotfi Khalil Virji Farnoosh Faraji Lucas Berry Andrew Holliday David Meger Gregory Dudek Mobile Robotics Lab (MRL) Faculty of Computer Science McGill University Montreal Canada

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In this paper, we investigate a hybrid scheme that combines nonlinear model predictive control (MPC) and model-based reinforcement learning (RL) for navigation planning of an autonomous model car across offroad, unstructured terrains without relying on predefined maps. Our innovative approach takes inspiration from BADGR, an LSTM-based network that primarily concentrates on environment modeling, but distinguishes itself by substituting LSTM modules with transformers to greatly elevate the performance of our model. Addressing uncertainty within the system, we train an ensemble of predictive models and estimate the mutual information between model weights and outputs, facilitating dynamic horizon planning through the introduction of variable speeds. Further enhancing our methodology, we incorporate a nonlinear MPC controller that accounts for the intricacies of the vehicle’s model and states. The model-based RL facet produces steering angles and quantifies inherent uncertainty. At the same time, the nonlinear MPC suggests optimal throttle settings, striking a balance between goal attainment speed and managing model uncertainty influenced by velocity. In the conducted studies, our approach excels over the existing baseline by consistently achieving higher metric values in predicting future events and seamlessly integrating the vehicle’s kinematic model for enhanced decision-making. The code and the evaluation data are available at (Github-repo).

关键词： Uncertainty Navigation Reinforcement learning Predictive models Transformers Planning Trajectory

来源：评论

学校读者我要写书评

暂无评论

Intersection Coordination with Priority-Based Search for Autonomous Vehicles 37

Intersection Coordination with Priority-Based Search for Aut...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Li, Jiaoyang Hoang, The Anh Lin, Eugene Vu, Hai L. Koenig, Sven Robotics Institute Carnegie Mellon University United States Department of Civil Engineering Monash University Australia Computer Science Department University of Southern California United States

ISBN: (纸本)9781577358800

The development of connected and autonomous vehicles opens an opportunity to manage intersections without signals. One promising approach is to use a central autonomous intersection manager to optimize the movement of the vehicles in the intersection. Existing work uses Mixed Integer Linear Programming (MILP) to find optimal solutions for this problem but is time-consuming and cannot be applied in real-time. On the other hand, the coordination of the vehicles is essentially a Multi-Agent Path Finding (MAPF) problem, for which dozens of efficient algorithms have been proposed in recent years. Inspired by these MAPF algorithms, we propose a three-level algorithm called PSL to solve the intersection coordination problem. Theoretically, PSL is complete and polynomial-time in the number of vehicles. Empirically, PSL runs significantly faster with only a slight compromise in the solution quality than the optimal MILP method. It also generates significantly better solutions with a slightly larger runtime than the traditional First-Come-First-Served strategy. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark

DarkGS: Learning Neural Illumination and 3D Gaussians Religh...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Tianyi Zhang Kaining Huang Weiming Zhi Matthew Johnson-Roberson Robotics Institute School of Computer Science Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination. We wish to endow robots with this same capability. In this paper, we tackle the challenge of constructing a photorealistic scene representation under poorly illuminated conditions and with a moving light source. We approach the task of modeling illumination as a learning problem, and utilize the developed illumination model to aid in scene reconstruction. We introduce an innovative framework that uses a data-driven approach, Neural Light Simulators (NeLiS), to model and calibrate the camera-light system. Furthermore, we present DarkGS, a method that applies NeLiS to create a relightable 3D Gaussian scene model capable of real-time, photorealistic rendering from novel viewpoints. We show the applicability and robustness of our proposed simulator and system in a variety of real-world environments. Code released at https://***/proj/***

关键词： Solid modeling Three-dimensional displays Codes Lighting Rendering (computer graphics) Robustness Real-time systems Cognitive science Intelligent robots Light sources

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：