检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Torrado, Paolo Levin, Joshua Grotz, Markus Smith, Joshua Electrical and Computer Engineering Department University of Washington United States Paul G. Allen School of Computer Science & Engineering University of Washington United States

Warehouse robotic systems equipped with vacuum grippers must reliably grasp a diverse range of objects from densely packed shelves. However, these environments present significant challenges, including occlusions, diverse object orientations, stacked and obstructed items, and surfaces that are difficult to suction. We introduce TetraGrip, a novel vacuum-based grasping strategy featuring four suction cups mounted on linear actuators. Each actuator is equipped with an optical time-of-flight (ToF) proximity sensor, enabling reactive grasping. We evaluate TetraGrip in a warehouse-style setting, demonstrating its ability to manipulate objects in stacked and obstructed configurations. Our results show that our RL-based policy improves picking success in stacked-object scenarios by 22.86% compared to a single-suction gripper. Additionally, we demonstrate that TetraGrip can successfully grasp objects in scenarios where a single-suction gripper fails due to physical limitations, specifically in two cases: (1) picking an object occluded by another object and (2) retrieving an object in a complex scenario. These findings highlight the advantages of multi-actuated, suction-based grasping in unstructured warehouse environments. The project website is available at: https://***/. Copyright © 2025, The Authors. All rights reserved.

关键词： Linear actuators

来源：评论

学校读者我要写书评

暂无评论

Frequency-Compensated Network for Daily Arctic Sea Ice Concentration Prediction

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Jialiang Gao, Feng Gan, Yanhai Dong, Junyu Du, Qian Ocean University of China School of Computer Science and Technology Qingdao266100 China Mississippi State University Department of Electrical and Computer Engineering StarkvilleMS39762 United States

Accurately forecasting sea ice concentration (SIC) in the Arctic is critical to global ecosystem health and navigation safety. However, current methods still is confronted with two challenges: 1) these methods rarely explore the long-term feature dependencies in the frequency domain. 2) they can hardly preserve the high-frequency details, and the changes in the marginal area of the sea ice cannot be accurately captured. To this end, we present a Frequency-Compensated Network (FCNet) for Arctic SIC prediction on a daily basis. In particular, we design a dual-branch network, including branches for frequency feature extraction and convolutional feature extraction. For frequency feature extraction, we design an adaptive frequency filter block, which integrates trainable layers with Fourier-based filters. By adding frequency features, the FCNet can achieve refined prediction of edges and details. For convolutional feature extraction, we propose a high-frequency enhancement block to separate high and low-frequency information. Moreover, high-frequency features are enhanced via channel-wise attention, and temporal attention unit is employed for low-frequency feature extraction to capture long-range sea ice changes. Extensive experiments are conducted on a satellite-derived daily SIC dataset, and the results verify the effectiveness of the proposed FCNet. © 1980-2012 IEEE.

关键词： Sea ice

来源：评论

学校读者我要写书评

暂无评论

A Confidence-Based Shared Control Strategy for Robotic Electrosurgery

IEEE Transactions on Medical Robotics and Bionics

引用

IEEE Transactions on Medical Robotics and Bionics 2025年第2期7卷 583-594页

作者： Meza-Pantoja, A. Lawson, A.C. Caputo, C.C. Ge, J. Cohen, D.J. Krieger, A. Saeidi, H. University of North Carolina at Wilmington Department of Computer Science WilmingtonNC28403 United States Johns Hopkins University Department of Mechanical Engineering BaltimoreMD21211 United States University of North Carolina at Wilmington Department of Psychology WilmingtonNC28403 United States

Robotic-assisted surgery (RAS) systems take advantage of dexterous tools, enhanced vision, and motion filtering to improve patient outcomes. Whereas most RAS systems are directly controlled by surgeons, the development and application of autonomous RAS are growing owing to their repeatability and precision. Although full autonomy is a long-term goal, human intervention in RAS is still essential. In this work, we develop and test a shared control strategy for robotic electrosurgery in which autonomous robot controllers and human operators collaborate. We designed and implemented identification tests that assessed the effectiveness of autonomous and manual control strategies and the cost of switching between the control modes. Based on the results, we propose a control mode switching strategy and examine it via an experiment on precision cutting on porcine tongue samples. The results indicate that by combining the best elements of autonomous and manual control, we can achieve more accurate soft-tissue incisions as compared to single-mode control strategies. Furthermore, the proposed strategy reduces the required human-in-the-loop time by 69.29%. © 2018 IEEE.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imaging

arXiv

引用

arXiv 2025年

作者： Ekmekci, Canberk Cetin, Mujdat Department of Electrical and Computer Engineering University of Rochester RochesterNY14627 United States Department of Electrical and Computer Engineering Goergen Institute for Data Science University of Rochester RochesterNY14627 United States

Uncertainty quantification plays an important role in achieving trustworthy and reliable learning-based computational imaging. Recent advances in generative modeling and Bayesian neural networks have enabled the development of uncertainty-aware image reconstruction methods. Current generative model-based methods seek to quantify the inherent (aleatoric) uncertainty on the underlying image for given measurements by learning to sample from the posterior distribution of the underlying image. On the other hand, Bayesian neural network-based approaches aim to quantify the model (epistemic) uncertainty on the parameters of a deep neural network-based reconstruction method by approximating the posterior distribution of those parameters. Unfortunately, an ongoing need for an inversion method that can jointly quantify complex aleatoric uncertainty and epistemic uncertainty patterns still persists. In this paper, we present a scalable framework that can quantify both aleatoric and epistemic uncertainties. The proposed framework accepts an existing generative model-based posterior sampling method as an input and introduces an epistemic uncertainty quantification capability through Bayesian neural networks with latent variables and deep ensembling. Furthermore, by leveraging the conformal prediction methodology, the proposed framework can be easily calibrated to ensure rigorous uncertainty quantification. We evaluated the proposed framework on magnetic resonance imaging, computed tomography, and image inpainting problems and showed that the epistemic and aleatoric uncertainty estimates produced by the proposed framework display the characteristic features of true epistemic and aleatoric uncertainties. Furthermore, our results demonstrated that the use of conformal prediction on top of the proposed framework enables marginal coverage guarantees consistent with frequentist principles. Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

ImageGuard: Advanced User Authentication via Dynamic Graphical Password Manipulation and Secured Image Sequences 4

ImageGuard: Advanced User Authentication via Dynamic Graphic...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Dhinesh, M. Geetha, B. Sathish, P. Saravanakumar, Lavanya Jude, P. Sebastian Vindro Balaram, Allam Tamilnadu Chennai77 India Saveetha College of Liberal Arts and Sciences Simats Department of Computer Science Chennai India India Kalasalingam Academy of Research and Education Departmentof C.S.E Viruthunagar India Sri Ramkrishna Engineering College Department of Eee Coimbatore India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331523923

User authentication is a critical aspect of cybersecurity, traditionally relying on alphanumeric passwords. However, these passwords are prone to various attacks, including brute force, dictionary, and shoulder-surfing attacks. As a result, there has been a shift towards more secure and user-friendly authentication methods. This study evaluates a secured image sequence-based user authentication system utilizing graphical password manipulation. By leveraging the human brain's superior ability to recognize and remember images over text, this system offers enhanced security against traditional password vulnerabilities such as brute force or dictionary attacks. The methodology involves click-based and choice-based graphical techniques, ensuring robust and user-friendly authentication. The proposed system demonstrates significant improvements in password security and usability, achieving a success rate of 92% with high user satisfaction. © 2025 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Explainable AI Model for Automatic Irrigation System using IOT

Explainable AI Model for Automatic Irrigation System using I...

引用

IT Innovation and Knowledge Discovery (ITIKD), International Conference on

作者： R Rajagopal D. Sumathi Akey Sungheetha Rajesh Sharma R Sheila Mahapatra N. Sivakumar Department of Computer Science and Engineering Alliance College of Advanced Computing Alliance University Bangalore India Department of Computer Science and Engineering Alliance University Bengaluru India Department of Electrical and Electronics Engineering Alliance University Bengaluru Karnataka India Department of Computer Engineering Marwadi University Rajkot Gujarat India

ISBN: (数字)9798350355468

ISBN: (纸本)9798350355475

This paper presents an explainable artificial intelli-gence (XAI) model for automatic irrigation systems using Inter-net of Things (IoT) technology. The proposed system integrates soil moisture sensors, temperature sensors, and humidity sensors with a microcontroller to make data-driven irrigation decisions. A Random Forest classifier i s employed top redict irrigation requirements based on environmental parameters, with SHAP (SHapley Additive exPlanations) values providing transparency and interpretability of model decisions. The system demonstrates a 35 % reduction in water usage and a 20 % increase in crop yield compared to traditional irrigation methods. The integration of explainability enhances user trust and system adoption, making advanced agricultural technology accessible to farmers with varying technical expertise. Experimental results show that the Random Forest model outperforms XGBoost and SVM in accuracy (75%), precision (100% for non-irrigation decisions), and robustness for irrigation management.

关键词： Temperature sensors Support vector machines Irrigation Explainable AI Soil moisture Water conservation Sensor systems Sensors Internet of Things Random forests

来源：评论

学校读者我要写书评

暂无评论

RAFA-Net: Region Attention Network for Food Items and Agricultural Stress Recognition

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 121-133页

作者： Bera, Asish Krejcar, Ondrej Bhattacharjee, Debotosh Birla Institute of Technology and Science Department of Computer Science and Information Systems Pilani333031 India University of Hradec Kralove Center for Basic and Applied Science Faculty of Informatics and Management Hradec Kralove50003 Czech Republic Skoda Auto University Mlada Boleslav29301 Czech Republic Universiti Teknologi Malaysia Malaysia Japan International Institute of Technology Kuala Lumpur81310 Malaysia Jadavpur University Department of Computer Science and Engineering Kolkata700032 India

Deep convolutional neural networks (CNNs) have facilitated remarkable success in recognizing various food items and agricultural stress. A decent performance boost has been witnessed in solving the agro-food challenges by mining and analyzing region-based partial feature descriptors. Also, computationally expensive ensemble learning schemes fusing multiple CNNs have been studied in earlier works. This work proposes a region attention scheme for modeling long-range dependencies by building a correlation among different regions within an input image. The attention method enhances feature representation by learning the usefulness of context information from complementary regions. Spatial pyramidal pooling and average pooling pairs aggregate partial descriptors into a holistic representation. Both pooling methods establish spatial and channelwise relationships without incurring extra parameters. A context gating scheme is applied to refine the descriptiveness of weighted attentional features, which is relevant for classification. The proposed region attention network for food items and agricultural stress recognition method, dubbed RAFA-Net, has been experimented on three public food datasets, and has achieved state-of-the-art performances with distinct margins. The highest top-1 accuracy of RAFA-Net is 91.69%, 91.56%, and 96.97% on the UECFood-100, UECFood-256, and MAFood-121 datasets, respectively. In addition, better accuracies have been achieved on two benchmark agricultural stress datasets. The best top-1 accuracies on the Insect Pest (IP-102) and PlantDoc-27 plant disease datasets are 92.36%, and 85.54%, respectively;implying RAFA-Net's generalization capability. © 2023 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

LASS: A Novel and Economical Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization 31

LASS: A Novel and Economical Data Augmentation Framework Bas...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Yanyue Li, Pengfei Lai, Yilong He, Yulan Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King's College London United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)9798891761964

As more than 70% of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are hesitant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the reliance on a specific structure is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, large-scale data augmentation based on large language models faces an apparent disadvantage, the expensive costs. Therefore, in this paper, we propose LASS, a novel data augmentation framework based on both LArge and Small language models for debiaSing opinion summarization. Specifically, a small number of synthesized negative reviews is obtained by rewriting the positive text via a large language model. Then, a disentangle reconstruction model is trained based on the generated data. After training, a large amount of synthetic data can be obtained by decoding the new representation obtained from the combination of different sample representations and filtering based on perplexity degree and sentiment classification. Experiments have proved that LASS can effectively alleviate emotional bias, similar to using only large models, but in a more economical way. © 2025 Association for Computational Linguistics.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Mode Participation and Inter-Area-Observability Blocking Controllers for Power Networks

arXiv

引用

arXiv 2025年

作者： Anguluri, Rajasekhar Al Maruf, Abdullah Department of Computer Science and Electrical Engineering University of Maryland Baltimore CountyMD85281 United States Department of Electrical and Computer Engineering California State University Los AngelesCA90032 United States

In recent papers [1] and [2], the second author developed full-state feedback controllers for networked systems to block the observability and controllability of certain remote nodes. In this paper, we build on these control schemes to an interconnected power system with the aims of blocking (i) mode participation factors and (ii) inter-area mode observability in tie-line power flow measurements. Since participation factors depend on both controllable and observable eigenvectors, the control techniques from the cited works must be carefully tailored to this setting. Our research is motivated by cybersecurity concerns in power systems, where an adversary aims to deceive the operator by tampering the system’s modal content. We present extensive numerical results on a 3-machine, 9-bus system and a 16-machine, 68-bus system. © 2025, CC BY.

关键词： Controllability

来源：评论

学校读者我要写书评

暂无评论

A 1D Residual CNN with SMOTE-Tomek and Cosine Annealing for Enhanced ECG Arrhythmia Classification 16

A 1D Residual CNN with SMOTE-Tomek and Cosine Annealing for ...

引用

16th IEEE Latin American Symposium on Circuits and Systems, LASCAS 2025

作者： Jiang, Feng Lim, Yang Wei Ahmad, Siti Anom Ahmad, Faisul Arif Ismail, Luthffi Idzhar Hussein, Ahmed Faeq Rokhani, Fakhrul Zaman Universiti Putra Malaysia Department of Computer and Communication Systems Engineering Faculty of Engineering Malaysia Universiti Putra Malaysia Department of Electrical and Electronics Engineering Faculty of Engineering Malaysia Al-Nahrain University Department of Biomedical Engineering Faculty of Engineering Baghdad Iraq

ISBN: (纸本)9798331522124

This paper proposes a 1D residual convolutional neural network (CNN) for classifying arrhythmias based on electrocardiogram (ECG) signals. The additional residual blocks and skip connections effectively alleviate the gradient problem in deep neural networks by providing a direct path for gradient propagation and enhancing the feature information propagation. In addition, the SMOTE-Tomek technique was demonstrated in this work to mitigate the effects of class imbalance caused by a large amount of data during model training and effectively increase the SNR of the training set. The robustness of the model is increased by adding the cosine annealing technique and L 2 regularization. The proposed model was evaluated with various performance metrics, resulting in an accuracy of 9 8. 7 4 %, sensitivity of 9 8. 3 5 %, specificity of 9 1. 8 6 %, precision of 9 7. 9 5 %, and F1 score of 9 8. 1 4 % on the MIT-BIH Arrhythmia Database. The result shows better performance for classifying previously unseen data for the proposed approach as compared to the state-of-the-art works. © 2025 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：