检索结果-内蒙古大学图书馆

5th International Conference on Machine Learning and Computer Application, ICMLCA 2024

作者： Chen, Siwen Zheng, Xiujuan Shanghai United Imaging Healthcare Co. Ltd. Shanghai China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Engineering Research Center for Metallurgical Automation and Measurement Technology Ministry of Education Wuhan China

ISBN: (纸本)9798331530334

To enhance the prediction accuracy of the remaining useful life (RUL) of lithium-ion batteries, this study proposes a novel RUL prediction model, termed FDNet, which integrates Discrete Fourier Series (DFS) and Densely Connected Convolutional Networks (DenseNet). In contrast to traditional methods that rely on one-dimensional (1D) numerical representations of time-series data, this model utilizes a two-dimensional (2D) visual representation for direct RUL prediction. First, the DFS is employed to convert 1D time-series signals into a 2D time-frequency domain, enabling the extraction of high-dimensional features from the original data. Then, these 2D images are subsequently input into DenseNet, which learns the mapping between the image features and the RUL targets. Finally, the proposed model is validated using the NASA lithium-ion battery aging dataset, and the results indicate that FDNet achieves superior prediction accuracy and exhibits notable robustness. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Sparse Hybrid Linear-Morphological Networks

arXiv

引用

arXiv 2025年

作者： Fotopoulos, Konstantinos Garoufis, Christos Maragos, Petros School of ECE National Technical University of Athens Athens Greece Robotics Institute Athena Research Center Athens Greece

We investigate hybrid linear-morphological networks. Recent studies highlight the inherent affinity of morphological layers to pruning, but also their difficulty in training. We propose a hybrid network structure, wherein morphological layers are inserted between the linear layers of the network, in place of activation functions. We experiment with the following morphological layers: 1) maxout pooling layers (as a special case of a morphological layer), 2) fully connected dense morphological layers, and 3) a novel, sparsely initialized variant of (2). We conduct experiments on the Magna-Tag-A-Tune (music auto-tagging) and CIFAR-10 (image classification) datasets, replacing the linear classification heads of state-of-the-art convolutional network architectures with our proposed network structure for the various morphological layers. We demonstrate that these networks induce sparsity to their linear layers, making them more prunable under L1 unstructured pruning. We also show that on MTAT our proposed sparsely initialized layer achieves slightly better performance than ReLU, maxout, and densely initialized max-plus layers, and exhibits faster initial convergence. Copyright © 2025, The Authors. All rights reserved.

关键词： Mathematical morphology

来源：评论

学校读者我要写书评

暂无评论

Power in Unity: Combining in-Domain and out-of-Domain Pre-Training Strategies for EEG-Based Person Identification

Power in Unity: Combining in-Domain and out-of-Domain Pre-Tr...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Christos Garoufis Marios Glytsos Ioanna Chourdaki Panagiotis P. Filntisis Petros Maragos School of ECE National Technical University of Athens Athens Greece Robotics Institute Athena Research Center Athens Greece

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We present the NTUA-IRAL team’s solution for the Person Identification track of the Signal Processing EEG-Music Emotion Recognition Grand Challenge, hosted at ICASSP. Our approach employs an ensemble of three CNNs, each pretrained using a distinct strategy: contrastive pre-training, traditional ImageNet pre-training, and task-specific pre-training on a publicly available EEG dataset. This diverse pre-training regimen enabled our models to achieve a test set accuracy of 100%, earning third place in the challenge subtrack.

关键词： Emotion recognition Accuracy Neural networks Authentication Signal processing Brain modeling Electroencephalography Acoustics Speech processing Identification of persons

来源：评论

学校读者我要写书评

暂无评论

A policy gradient algorithm integrating long and short-term rewards for soft continuum arm control

引用

Science China(Technological Sciences) 2022年第10期65卷 2409-2419页

作者： DONG Xiang ZHANG Jing CHENG Long XU WenJun SU Hang MEI Tao School of Electrical Engineering and Automation Anhui UniversityHefei 230601China State Key Laboratory for Control and Management of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Robotics Research Center Peng Cheng LaboratoryShenzhen 518055China

The soft continuum arm has extensive application in industrial production and human life due to its superior safety and flexibility. Reinforcement learning is a powerful technique for solving soft arm continuous control problems, which can learn an effective control policy with an unknown system model. However, it is often affected by the high sample complexity and requires huge amounts of data to train, which limits its effectiveness in soft arm control. An improved policy gradient method, policy gradient integrating long and short-term rewards denoted as PGLS, is proposed in this paper to overcome this issue. The shortterm rewards provide more dynamic-aware exploration directions for policy learning and improve the exploration efficiency of the algorithm. PGLS can be integrated into current policy gradient algorithms, such as deep deterministic policy gradient(DDPG). The overall control framework is realized and demonstrated in a dynamics simulation environment. Simulation results show that this approach can effectively control the soft arm to reach and track the targets. Compared with DDPG and other model-free reinforcement learning algorithms, the proposed PGLS algorithm has a great improvement in convergence speed and performance. In addition, a fluid-driven soft manipulator is designed and fabricated in this paper, which can verify the proposed PGLS algorithm in real experiments in the future.

关键词： soft arm control Cosserat rod deep reinforcement learning policy gradient algorithm high sample complexity

来源：评论

学校读者我要写书评

暂无评论

Optimizing Steering Angle Predictive Convolutional Neural Network for Autonomous Car

引用

Computers, Materials & Continua 2022年第5期71卷 2285-2302页

作者： Hajira Saleem Faisal Riaz Asadullah Shaikh Khairan Rajab Adel Rajab Muhammad Akram Mana Saleh Al Reshan Control Automotive and Robotics Lab Affiliated lab of National Center of Robotics and Automation(NCRA HEC Pakistan)and with the Department of Computer Science and Information TechnologyMirpur University of Science and Technology(MUST)Mirpur Azad Kashmir10250Pakistan College of Computer Science and Information System Najran UniversityNajran61441Saudi Arabia College of Computer Science and Engineering University of South FloridaTampa33620United States

Deep learning techniques,particularly convolutional neural networks(CNNs),have exhibited remarkable performance in solving visionrelated problems,especially in unpredictable,dynamic,and challenging *** autonomous vehicles,imitation-learning-based steering angle prediction is viable due to the visual imagery comprehension of *** this regard,globally,researchers are currently focusing on the architectural design and optimization of the hyperparameters of CNNs to achieve the best *** has proven the superiority of metaheuristic algorithms over the manual-tuning of ***,to the best of our knowledge,these techniques are yet to be applied to address the problem of imitationlearning-based steering angle ***,in this study,we examine the application of the bat algorithm and particle swarm optimization algorithm for the optimization of the CNN model and its hyperparameters,which are employed to solve the steering angle prediction *** validate the performance of each hyperparameters’set and architectural parameters’set,we utilized the Udacity steering angle dataset and obtained the best results at the following hyperparameter set:optimizer,Adagrad;learning rate,0.0052;and nonlinear activation function,exponential linear *** per our findings,we determined that the deep learning models show better results but require more training epochs and time as compared to shallower *** show the superiority of our approach in optimizing CNNs through metaheuristic algorithms as compared with the manual-tuning *** testing was also performed using the model trained with the optimal architecture,which we developed using our approach.

关键词： Bat algorithm convolutional neural network hyperparameters metaheuristic optimization algorithm steering angle prediction

来源：评论

学校读者我要写书评

暂无评论

Principle and Analysis of Variable Stiffness Joints

Principle and Analysis of Variable Stiffness Joints

引用

robotics, Control and Automation (ICRCA), International Conference on

作者： Wei Sun Shujian Liu Yunfei Liu Weijun Wang Yangzhou Zhao Robotics Engineering Center Corporation (China Electronics Technology Robotics CO.LTD) The 21ST Research Institute of China Electronic Technology Group Shanghai China

ISBN: (数字)9798350344721

ISBN: (纸本)9798350344738

Variable stiffness joints (VSJs) is a kind of robot mechanism with the essence of flexibility, which can improve the safety of human-robot interaction. A classification of the different VSJs based on the ranges of stiffness adjustments is proposed in this paper. Then the principle of variable stiffness, stiffness curve and pros and cons of each kind of VSJ s are investigated, respectively. According to the analysis results of this paper, researchers can select and optimize the relevant variable stiffness mechanism based on the requirements and structural characteristics. The existing problems and the shortcomings of the VSJ s are analyzed and discussed, and future research and exploration direction have been planned.

关键词： Graphics Automation Human-robot interaction Safety Robots Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Design and development of a shape measurement system for 3D construction printing with a manipulator

Design and development of a shape measurement system for 3D ...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Reina Nakanishi Hiroki Ogura Shinya Yamamoto Hiroyuki Abe Ryu Kikuchi Robotics Research Center Institute of Technology Shimizu Corporation Japan Center for Social System Engineering Institute of Technology Shimizu Corporation Japan

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

We describe a 3D construction printing system comprising an industrial robot with a six-degrees-of-freedom manipulator and a pump that supplies mortar. Printing is realized by linking the manipulator to the pump. To measure and evaluate printed object shapes, we attached a time-of-flight camera with ±2-mm measurement accuracy to an end effector mounted on the manipulator, thereby acquiring point-cloud data for printed objects. Using software developed to control the manipulator, and an open-source robotics middleware suite as the robot operating system, we merge the obtained point clouds. After printing mortar objects, we use the developed system to measure their shapes. Experimental results show that point clouds for printed objects have errors of 0 to 10 mm, while data from a conventional stationary 3D laser scanner has measurement accuracy of ±1 mm. Although merged point clouds show increased errors, measurement times decreased to approximately one-sixth those of conventional scanners. The increased error is likely due to factors such as the manipulator’s weight and its installation at the end effector and the sensor. We use a total station to measure deflections to confirm the manipulator’s positioning accuracy.

关键词： Printing Point cloud compression Three-dimensional displays Accuracy Shape Mortar Shape measurement Measurement uncertainty Robot vision systems End effectors

来源：评论

学校读者我要写书评

暂无评论

AMA: An Analytical Approach to Maximizing the Efficiency of Deep Learning on Versal AI Engine

AMA: An Analytical Approach to Maximizing the Efficiency of ...

引用

International Conference on Field Programmable Logic and Applications

作者： Xiaodong Deng Shijie Wang Tianyi Gao Jing Liu Longjun Liu Nanning Zheng National Key Laboratory of HumanMachine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University

ISBN: (数字)9798331530075

ISBN: (纸本)9798331530082

The traditional cache-based multi-core architecture represented by CUDA has been plagued by the “memory wall” problem, and a large number of applications represented by large language model inference are unable to meet the high computational intensity requirements. The Versal AI Engine architecture provides a variety of rich inter-core connections in the processor array, increasing many data reuse opportunities and potentially alleviating the “memory wall” issue. However, traditional parallel programming models cannot be directly applied to this architecture, and how to map computations to achieve high computational utilization becomes a new challenge. To address this, we propose AMA, a hierarchical performance analysis model built on the Versal AI Engine architecture, designed to maximize the efficiency of typical deep learning applications. Experiments show that AMA modeling is accurate and efficient. On the VCK190 platform, we achieved a matrix multiplication throughput of 5867.29 GFLOPS in fp32 and 88.55 TOPS in int8, and a convolution throughput of 99.6770 TOPS. In terms of energy efficiency, AMA achieved 142.68 GFLOPS/W in fp32 precision and 1.416 TOPS/W in int8 matrix multiplication. Compared to the current state-of-the-art methods, we achieved a $\mathbf{1 4. 9 9 \%}$ increase in throughput and a 22.92% increase in energy efficiency, providing new analytical performance model and practical guidance for efficient deep learning deployment on AI Engine.

关键词： Deep learning Analytical models Convolution Computational modeling Computer architecture Throughput Energy efficiency Performance analysis Computational efficiency Engines

来源：评论

学校读者我要写书评

暂无评论

3D Intra-articular Dense Reconstruction from Arthroscopic Images

3D Intra-articular Dense Reconstruction from Arthroscopic Im...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Zhang, Yanhao Cheng, Chonghao Falque, Raphael Zhao, Liang Huang, Shoudong Chen, Yongbo Australian National Univeristy School of Computing 108 North Road ActonACT2601 Australia University of Technology Sydney Robotics Institute Faculty of Engineering and Information Technology UltimoNSW2007 Australia

ISBN: (纸本)9798350325706

Arthroscopy is an important clinical technique for knee joint damage treatment, where a small fibre-optic camera is manipulated in a narrow space to provide a live 2D view of the inner joint. The small field of view from the surgical scope makes the 3D guidance for instruments manipulation very difficult. Therefore, a 3D reconstruction of the articular surface becomes very helpful. This paper provides a framework that recovers joint inner dense surface for arthroscopy using only a sequence of intra-articular images. A self-supervised convolutional neural network is trained pre-operatively to predict dense depth maps from the intra-articular images. The depth maps and images are fused together and a local-to-global SLAM pipeline is proposed for tissue surface reconstruction. Compared with existing works on 3D reconstruction using arthroscopic images, the proposed framework does not require additional sensors. Ex-vivo experiments are conducted and the result demonstrates reconstruction ability as well as the potential clinical value of this framework. © 2023 IEEE.

关键词： 3D reconstruction knee arthroscopy self-supervised learning SLAM

来源：评论

学校读者我要写书评

暂无评论

Ball sition ature bedded Group Activity Recognition del for Team Sport Games 4

Ball sition ature bedded Group Activity Recognition del for ...

引用

4th International Conference on Machine Learning and Intelligent Systems, MLIS 2022

作者： Jamsrandorj, Ankhzaya Chao, Vanyi Oo, Yin May Mun, Kyung-Ryoul Kim, Jinwook Department of Human Computer Interface & Robotics Engineering University of Science & Technology Korea Republic of Department of Ai Robotics University of Science & Technology Korea Republic of Center for Artificial Intelligence Korea Institute of Science and Technology Korea Republic of

ISBN: (纸本)9781643683560

Most group activity recognition models focus mainly on spatio-temporal features from the players in sports games. Often they do not pay enough attention to the game object, which heavily affects not only individual action but also a group activity. We propose a new group activity recognition model for sports games that incorporates players' motion information and game object positional information. The proposed method uses a transformer encoder for temporal feature extraction and a 'simple' conventional convolutional neural network for extracting spatial features and fusing them with the relative ball position-embedded features. The experimental results show that our model achieved comparable results to state-of-the-art methods on the Volleyball dataset by using only one transformer encoder block and the ball position. © 2022 The authors and IOS Press.

关键词： Sports

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：