检索结果-内蒙古大学图书馆

Efficient deep learning model for classifying lung cancer images using normalized stain agnostic feature method and FastAI-2

引用

PeerJ Computer Science 2025年 11卷 1-22页

作者： Saxena, Pranshu Singh, Sanjay Kumar Rashid, Mamoon Alshamrani, Sultan S. Alnfiai, Mrim M. School of Computer Science Engineering and Technology Bennett University Greater Noida India University School of Automation and Robotics Guru Gobind Singh Indraprastha University Delhi India School of Information Communication and Technology Bahrain Polytechnic Isa Town Bahrain Department of Information Technology College of Computers and Information Technology Taif University Taif Saudi Arabia

Background: Lung cancer has the highest global fatality rate, with diagnosis primarily relying on histological tissue sample analysis. Accurate classification is critical for treatment planning and patient outcomes. Methods: This study develops a computer-assisted diagnosis system for non-small cell lung cancer histology classification, utilizing the FastAI-2 framework with a modified ResNet-34 architecture. The methodology includes stain normalization using LAB colour space for colour consistency, followed by deep learning-based classification. The proposed model is trained on the LC25000 dataset and compared with VGG11 and SqueezeNet1_1, demonstrating modified ResNet-34’s optimal balance between depth and performance. FastAI-2 enhances computational efficiency, enabling rapid convergence with minimal training time. Results: The proposed system achieved 99.78% accuracy, confirming the effectiveness of automated lung cancer histopathology classification. This study highlights the potential of artificial intelligence (AI)-driven diagnostic tools to assist pathologists by improving accuracy, reducing workload, and enhancing decision-making in clinical settings. Copyright 2025 Saxena et al.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Synchronization Error Elimination for Heterogeneous Discrete-Time Multi-Agent Systems: A Reinforcement Learning Design Approach

Synchronization Error Elimination for Heterogeneous Discrete...

引用

American Control Conference (ACC)

作者： Xinyang Wang Martin Guay Shimin Wang Hongwei Zhang Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Guangdong China Department of Chemical Engineering Queen's University Kingston Ontario Canada

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

This paper proposes a novel reinforcement learning approach to solve the optimal output synchronization problem for discrete-time heterogeneous multi-agent systems. Different from existing learning methods, the optimal control protocol is obtained to guarantee zero synchronization error by solving the augmented algebraic Riccati equations (AREs). The proposed adaptive dynamic programming (ADP) method can stabilize the output synchronization error and solve the output regulator equations implicitly. To eliminate the dependency on information of system dynamics, an online Q-function-based policy iteration (PI) algorithm is developed. Finally, a numerical example is provided to demonstrate the advantages of the proposed ADP over traditional ADP in terms of synchronization performance.

关键词： Regulators Q-learning Protocols System dynamics Riccati equations Optimal control Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Spiking neural networks: Towards bio-inspired multimodal perception in robotics

arXiv

引用

arXiv 2024年

作者： Oikonomou, Katerina Maria Balaska, Vasiliki Tsintotas, Konstantinos A. Mavridis, Christos N. Kansizoglou, Ioannis Gasteratos, Antonios The Department of Production and Management Engineering Laboratory of Robotics and Automation Democritus University of Thrace Xanthi Greece The Department of Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

Spiking neural networks (SNNs) have captured apparent interest over the recent years, stemming from neuroscience and reaching the field of artificial intelligence. However, due to their nature SNNs remain far behind in achieving the exceptional performance of deep neural networks (DNNs). As a result, many scholars are exploring ways to enhance SNNs by using learning techniques from DNNs. While this approach has been proven to achieve considerable improvements in SNN performance, we propose another perspective: enhancing the biological plausibility of the models to leverage the advantages of SNNs fully. Our approach aims to propose a brain-like combination of audio-visual signal processing for recognition tasks, intended to succeed in more bio-plausible human-robot interaction applications. © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Research on Mobile Robot path Planning Based on improved Q-Learning 2

Research on Mobile Robot path Planning Based on improved Q-L...

引用

2021 2nd International Conference on Machine Learning and Computer Application, ICMLCA 2021

作者： Cui, Xujing Liu, Zihong Shi, Zhengjin Fan, Xiaoliang Xie, Feng Wang, Bolun School of Automation and Electrical Engineering Shenyang Ligong University Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110169 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

ISBN: (纸本)9783800757398

With the wide application of indoor mobile platforms, path planning is a significant challenge for the autonomous navigation of mobile robots. Generally, in an indoor environment, the ground mobile platform cannot obtain the interaction and perception of the destination and the surrounding. And cannot effectively plan a collision-free path, accurately. To address this problem, we propose to adopt a new search strategy and enhanced orientation based on the traditional Q-learning algorithm, which reduces the possibility of falling into local optimal and speeds up the learning efficiency. The simulation results show that our method can quickly and accurately realize the path planning and fully autonomous navigation of the indoor ground mobile platform. In structured spaces represented by storage centers, unmanned chemical factories and prisons, our method is more suitable for practical application scenarios of the indoor ground mobile platform. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Optimal Bioprinting Parameters and Experimental Investigation of Acellular Dermal Matrix Scaffold

引用

Journal of Renewable Materials 2021年第1期9卷 1-16页

作者： Qingxi Hu Yiming Wang Dongchao Yang Haiguang Zhang Zhicheng Song Yan Gu Rapid Manufacturing Engineering Center School of Mechatronic Engineering and AutomationShanghai UniversityShanghaiChina Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai UniversityShanghaiChina National Demonstration Center for Experimental Engineering Training Education Shanghai UniversityShanghaiChina Shanghai Ninth People’s Hospital Shanghai JiaoTong University School of MedicineShanghai200011China

Acellular dermal matrix(ADM)as a biomaterial is currently believed to be promising tissue repair *** the development of tissue engineering,ADM is increasingly used as biological *** explored the feasibility and performance of ADM biological scaffolds that fabricated by 3D *** paper presented our study on the printability of 3D printed ADM scaffolds,with a focus on identifying the influence of printing parameters/conditions on *** characterize the printability,we examined the fiber morphology,pore size,strand diameter,and mechanical property of the printed *** results revealed that the printability could be affected by a number of factors and among them,the most considerable one was related to the nozzle diameter and the composition of *** then evaluated the biocompatibility in terms of cytotoxicity,cell proliferation and *** vitro evaluation of the ADM scaffolds was carried out and the experimental results indicated that cells were viable and proliferative during the period of *** vivo results also indicated that the defect area was well repaired without any noticeable infection,hematoma and other *** conclusion,ADM could be reconstructed with 3D printing technology and ADM biological scaffold has potential applications for tissue engineering.

关键词： Bioprinting acellular dermal matrix scaffolds printability tissue engineering

来源：评论

学校读者我要写书评

暂无评论

Imitation and Adaptation Based on Consistency: A Quadruped Robot Imitates Animals from Videos Using Deep Reinforcement Learning

Imitation and Adaptation Based on Consistency: A Quadruped R...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Yao, Qingfeng Wang, Jilong Yang, Shuyu Wang, Cong Zhang, Hongyin Zhang, Qifeng Wang, Donglin State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Guangzhou511458 China School of Engineering Westlake University Hangzhou310024 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781665481090

The essence of quadruped movements is the move-ment of the center of gravity, which has a pattern in the movement of quadrupeds. However, planning the gait motion of the quadruped robot is time consuming. Animals in nature can provide a large amount of gait information for robots to imitate skills. Common methods learn the posture of animals with a motion capture system or numerous motion data points. In this paper, we propose a video imitation adaptation network that can imitate the action of animals from a few seconds of video and adapt skills to the robot. The deep learning model extracts key points of animal motion from videos. A motion adaptor that eliminates noise and extracts key information of motion is proposed;the information of the extracted movements was used as a motion pattern to help deep reinforcement learning complete the imitation of skills. To ensure similarity between the learning result and the animal motion in the video, we introduce rewards that are based on the consistency of the motion. The results show that our framework can help robots learn periodic and aperiodic skills from several seconds of videos of different types of animals. And we deploy the trained model to the real robot to complete the walking and backflip tasks without fine-tuning. © 2022 IEEE.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

SPONGE: Sequence Planning with Deformable-ON-Rigid Contact Prediction from Geometric Features

arXiv

引用

arXiv 2023年

作者： Le, Tran Nguyen Abu-Dakka, Fares J. Kyrki, Ville Intelligent Robotics Group The Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Finland MIRMI Technische Universität München München80992 Germany

Planning robotic manipulation tasks, especially those that involve interaction between deformable and rigid objects, is challenging due to the complexity in predicting such interactions. We introduce SPONGE, a sequence planning pipeline powered by a deep learning-based contact prediction model for contacts between deformable and rigid bodies under interactions. The contact prediction model is trained on synthetic data generated by a developed simulation environment to learn the mapping from point-cloud observation of a rigid target object and the pose of a deformable tool, to 3D representation of the contact points between the two bodies. We experimentally evaluated the proposed approach for a dish cleaning task both in simulation and on a real Franka Emika Panda with real-world objects. The experimental results demonstrate that in both scenarios the proposed planning pipeline is capable of generating high-quality trajectories that can accomplish the task by achieving more than 90% area coverage on different objects of varying sizes and curvatures while minimizing travel distance. Code and video are available at: https://***/sponge/. Copyright © 2023, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Modeling of dynamic-elastic deformation error for a collaborative robot

Modeling of dynamic-elastic deformation error for a collabor...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Shijing Zhu Xinan Pan Hongguang Wang Dianqi Li School of Mechanical Engineering Shenyang University of Technology Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences

In the operation of a collaborative robot, the inertial force, gravity force, and other factors can cause elastic deformation of links and joints, and hence results in considerable deviations from the desired trajectory. However, the effects of inertial force, gravity force, and Jacobian matrix are rarely considered in common deformation analyses. This paper proposes a method for modeling dynamic elastic deformation of collaborative robots including joint torsional stiffness and complementary stiffness. Firstly, the dynamics equation was established based on the Newton-Euler method, and the driving torque of the joint was analyzed. Secondly, a dynamic-elastic deformation error model was established based on the joint torsional stiffness and complementary stiffness. Finally, the simulation results show that the established dynamic error model has good predictability, and the relative error is less than 1.63% compared with the ADAMS simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sim-Suction: Learning a Suction Grasp Policy for Cluttered Environments Using a Synthetic Benchmark

arXiv

引用

arXiv 2023年

作者： Li, Juncheng Cappelleri, David J. Multi-Scale Robotics & Automation Lab School of Mechanical Engineering Purdue University West LafayetteIN United States Purdue University West LafayetteIN United States

This paper presents Sim-Suction, a robust objectaware suction grasp policy for mobile manipulation platforms with dynamic camera viewpoints, designed to pick up unknown objects from cluttered environments. Suction grasp policies typically employ data-driven approaches, necessitating largescale, accurately-annotated suction grasp datasets. However, the generation of suction grasp datasets in cluttered environments remains underexplored, leaving uncertainties about the relationship between the object of interest and its surroundings. To address this, we propose a benchmark synthetic dataset, Sim- Suction-Dataset, comprising 500 cluttered environments with 3.2 million annotated suction grasp poses. The efficient Sim-Suction- Dataset generation process provides novel insights by combining analytical models with dynamic physical simulations to create fast and accurate suction grasp pose annotations. We introduce Sim-Suction-Pointnet to generate robust 6D suction grasp poses by learning point-wise affordances from the Sim-Suction-Dataset, leveraging the synergy of zero-shot text-to-segmentation. Realworld experiments for picking up all objects demonstrate that Sim-Suction-Pointnet achieves success rates of 96.76%, 94.23%, and 92.39% on cluttered level 1 objects (prismatic shape), cluttered level 2 objects (more complex geometry), and cluttered mixed objects, respectively. The codebase can be accessed at https://***/junchengli1/Sim-Suction-API. Copyright © 2023, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A bionic mimosa soft robot composed by PNIPAM-PEGDA copolymer

A bionic mimosa soft robot composed by PNIPAM-PEGDA copolyme...

引用

WRC Symposium on Advanced robotics and automation (WRC SARA)

作者： Xiaowen Wang Wenguang Yang Zhixing Ge School of Electromechanical and Automotive Engineering Yantai University Yantai China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

Deformation is very important for biological survival, more and more researchers are committed to 3D deformation of 2D materials. In this research, we make 3D deformation by applying different internal stresses to 2D materials. At the beginning, single layer PNIPAM hydrogel sheets with different combinations of microchannels were fabricated by UV curing technology. Because of the uneven distribution of internal stresses, they deformed into different 3D structures. In order to maintain these 3D structures though without continuous stimulation, PNIPAM-PEGDA bilayer structure was prepared. It was found that the bilayer structure could respond to both temperature and solvent composition due to the difference of solubility between PNIPAM and PEGDA. Based on the bilayer structure, we made the bionic Mimosa, which could not only realize the open-closing reversibly, but also maintained the normally closed state without continuous stimulation. This research provides a reference for the development of directionally programmable soft materials and has great potential in the fields of bionics and biomedicine.

关键词：

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：