检索结果-内蒙古大学图书馆

data driven control and learning systems (ddcls)

作者： Honghai Ji Xinjing Liu Li Wang Lingling Fan Shida Liu School of Electronics & Control Engineering North China University of Technology Beijing China School of Automation Beijing Information Science and Technology University Beijing China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Chinese herbal medicine (CHM) has gained significant attention due to its potential in treating various diseases. CHM image classification is crucial in fields such as smart medical care and medical teaching. However, accurately classifying CHM images has been a challenging task due to their fine-grained variability. To achieve automatic identification and classification of Chinese herbal medicines, we designed a method that combines image processing and deep learning. We established a dataset of CHM images, which includes 10 kinds of common Chinese herbal medicines, with 15,719 images in total. the dataset covers medicinal materials in various natural backgrounds and provides ample samples for training deep learning models. Regarding image processing, we proposed a method based on adaptive gamma correction(AGC) and compared it with CLAHE(Contrast Limited Adaptive Histogram Equalization)and traditional gamma correction(TGC) methods. Subsequently, we employed three pre-training models of convolutional neural networks based on transfer learning, namely GoogLeNet, ResNet-18, and MobileNetV2, to identify CHM images. the results of the verification indicate that the AGC-CNN model outperforms the CLAHE-CNN and TGC-CNN models in terms of classification accuracy and image quality improvement.

关键词： Training Image quality Deep learning Adaptation models Accuracy Image recognition data models

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Cross Transformer Network-Based Fault Diagnosis Method for Industrial Process

A Multi-Scale Cross Transformer Network-Based Fault Diagnosi...

引用

data driven control and learning systems (ddcls)

作者： Yuan Xu Rui-Ze Fan Wei Ke Yan-Lin He Qun-Xiong Zhu Ming-Qing Zhang Yang Zhang College of Information Science & Technology Beijing University of Chemical Technology Beijing China Engineering Research Center of Intelligent PSE Ministry of Education of China Beijing China Faculty of Applied Sciences Macao Polytechnic University Macao SAR P.R. China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

the process of industrial production is becoming increasingly complex in modern times, posing higher demands for safety. It's worth noting that data from modern industrial processes often exhibit multivariate, temporal and multiscale characteristics. To address these problems, this paper presents a novel fault diagnosis method based on the Multi-Scale Cross Transformer model. We integrate encoder, convolution and patching mechanisms, making it capable of extracting temporal features from different time scales, effectively capturing short-term dynamics and long-term trends. Additionally, a two-stage attention mechanism is introduced to automatically learn correlations across both time and space dimensions. Experiments conducted on the Tennessee-Eastman process demonstrate the superiority of our proposed method. It shows over 10% accuracy enhancement in diagnostic performance compared to state-of-the-art methods. Furthermore, the method can gradually map data to a discriminative feature space with better intra-class compactness and inter-class separability, reflecting its reliability and validity.

关键词： Fault diagnosis Correlation Attention mechanisms Accuracy Process control Production Transformers

来源：评论

学校读者我要写书评

暂无评论

HemCNN: Deep learning enables decoding of fNIRS cortical signals in hand grip motor tasks

HemCNN: Deep Learning enables decoding of fNIRS cortical sig...

引用

International ieee/EMBS conference on Neural Engineering, CNE

作者： Pablo Ortega Aldo Faisal Brain & Behaviour Lab London UK Brain & Behaviour Lab Imperial College London London UK

We solve the fNIRS left/right hand force decoding problem using a data-driven approach by using a convolutional neural network architecture, the HemCNN. We test HemCNN's decoding capabilities to decode in a streaming way the hand, left or right, from fNIRS data. HemCNN learned to detect which hand executed a grasp at a naturalistic hand action speed of 1 Hz, outperforming standard methods. Since HemCNN does not require baseline correction and the convolution operation is invariant to time translations, our method can help to unlock fNIRS for a variety of real-time tasks. Mobile brain imaging and mobile brain machine interfacing can benefit from this to develop real-world neuroscience and practical human neural interfacing based on BOLD-like signals for the evaluation, assistance and rehabilitation of force generation, such as fusion of fNIRS with EEG signals.

关键词： Neuroimaging Neuroscience Convolution Force Real-time systems Decoding Task analysis

来源：评论

学校读者我要写书评

暂无评论

Cerebellar control of saccadic adaptation using a spiking neural network model integrated into the Neurorobotics platform

Cerebellar control of saccadic adaptation using a spiking ne...

引用

International ieee/EMBS conference on Neural Engineering, CNE

作者： Junya Inoue Alberto Antonietti Alessandra Pedrocchi Faculty of Science University of Tuebingen Tuebingen Germany Politecnico di Milano Milano Italy

the cerebellum is essential for motor learning and adaptation since it can change the relationship between sensory input and motor output. Cerebellar activity contributes to the motor execution with the aim of optimizing the resulting performance. this optimization is driven by the error information, that the cerebellum receives through the sensory feedback. In this study, we aim at studying the cerebellar contribution in the saccadic adaptation, fine and rapid control of eye movements. We set up a virtual experiment where an iCub robot, controlled by a cerebellar-inspired spiking neural network, was challenged in a saccadic adaptation task. the virtual robot, at first, made inaccurate saccades and therefore attempted to adjust them, trial after trial, based on sensory error feedback. the spiking neural network model was equipped with plasticity mechanisms, that allowed the robot to change and adapt the amplitude of the saccade movement after a few trials. Interestingly, we observed that for this task a single plasticity mechanism was sufficient to produce a fast adaptation, while in other cerebellar-driven tasks, the addition of more plasticities granted an improvement of the adaptation performances.

关键词： Cerebellum Adaptation models Neural networks Neural engineering Robot sensing systems Task analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Convergence of Intelligent data Acquisition and Advanced Computing systems

引用

SENSORS 2021年第7期21卷 2262页

作者： Stamatescu, Grigore Sachenko, Anatoliy Popescu, Dan Univ Politehn Bucuresti Dept Automat & Ind Informat 313 Splaiul Independentei Bucharest 060042 Romania Kazimierz Pulaski Univ Technol & Humanities Radom Dept Informat Ul Malczewskiego 29 PL-26600 Radom Poland West Ukrainian Natl Univ Res Inst Intelligent Comp Syst 3 Peremoga Sq UA-46020 Ternopol Ukraine

the special issue welcomed submissions as extended versions of conference articles published in the proceedings of the “10th ieee International conference on Intelligent data Acquisition and Advanced Computing systems: Technology and Applications (IDAACS’2019)” allowing the authors to expand on their theoretical and experimental contributions. Potential topics of the special issue that were initially defined were mapped onto the core areas and special streams of the IDAACS’2019 conference, and included but were not limited to: advanced instrumentation and data acquisition systems, advanced mathematical methods for data acquisition and computing systems, computational intelligence for instrumentation and data acquisition systems, data analysis and modeling, intelligent distributed systems and remote control, intelligent information systems, data mining, and ontology, Internet of things, pattern recognition, digital image, and signal processing, intelligent instrumentation and data acquisition systems in advanced manufacturing for Industry 4, intelligent robotics and sensors, machine learning, application for smart buildings and smart cities. [2] presents a system that combines scalar, ground level measurements, from sensor networks with aerial robotic platforms (UAVs) as data collection and communication relay infrastructure. data are colected through existing building automation system (BAS) infrastructure with wireless components for sensing, room temperature sensors, and control, motor valves for the heating elements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention M-net for Automatic Pixel-Level Micro-crack Detection of Photovoltaic Module Cells in Electroluminescence Images

Attention M-net for Automatic Pixel-Level Micro-crack Detect...

引用

data driven control and learning systems (ddcls)

作者： Yu Jiang Chunhui Zhao Waner Ding Ling Hong Qu Shen State Key Laboratory of Industrial Control Technology and College of Control Science and Engineering Zhejiang University Hangzhou P.R. China Zhejiang Provincial Key Laboratory of Solar Energy Utilization & Energy Saving Technology Zhejiang Energy Group R&D Hangzhou P.R. China

ISBN: (数字)9781728159225

ISBN: (纸本)9781728159232

In the solar power industry, quality inspection of solar cells is a very important part of the production and application process. Micro-crack is a type of common defect that may be present in photovoltaic (PV) module cells which can reduce the power generation efficiency and service lifetime. However, it is difficult to identify micro-crack by the naked eye because it is readily confused with non-uniform backgrounds and complex textures in Electroluminescence (EL) images. In this paper, we propose Attention M-net which combines efficient segmentation model structure and attention mechanism. It is a novel micro-crack detection model for automated pixel-level micro-crack detection of PV module cells. the M-shaped structure solves "All Black" issue that is easy to occur due to the severe imbalance of the micro-crack segmentation dataset. And integration of attention mechanism into the network significantly improves the accuracy of segmentation. Because of the above two advantages, the proposed model can be accurately learned from a small annotated dataset, thereby saving the time of micro-crack EL images collection and pixel-level annotations. We extensively trained the proposed model on a small dataset of 20 annotated EL images which include 10 monocrystalline and 10 polycrystalline. the evaluated results on the test dataset demonstrate the high efficiency and accuracy of Attention M-net for pixel-level micro-crack detection of PV module cells in EL images.

关键词： Feature extraction Image segmentation Photovoltaic cells Decoding Task analysis Silicon Convolution

来源：评论

学校读者我要写书评

暂无评论

learning Model Predictive control with Error Dynamics Regression for Autonomous Racing

Learning Model Predictive Control with Error Dynamics Regres...

引用

ieee International conference on Robotics and Automation (ICRA)

作者： Haoru Xue Edward L. Zhu John M. Dolan Francesco Borrelli Robotics Institute Carnegie Mellon University Pittsburgh PA USA Department of Mechanical Engineering University of California Berkeley Berkeley CA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

this work presents a novel learning Model Predictive control (LMPC) strategy for autonomous racing at the handling limit that can iteratively explore and learn unknown dynamics in high-speed operational domains. We start from existing LMPC formulations and modify the system dynamics learning method. In particular, our approach uses a nominal, global, nonlinear, physics-based model with a local, linear, data-driven learning of the error dynamics. We conducted experiments in simulation and on 1/10th scale hardware, and deployed the proposed LMPC on a full-scale autonomous race car used in the Indy Autonomous Challenge (IAC) with closed loop experiments at the Putnam Park Road Course in Indiana, USA. the results show that the proposed control policy exhibits improved robustness to parameter tuning and data scarcity. Incremental and safety-aware exploration toward the limit of handling and iterative learning of the vehicle dynamics in high-speed domains is observed both in simulations and experiments.

关键词： System dynamics Roads Robustness Hardware Nonlinear dynamical systems Safety Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Machine learning-driven Traffic Flow Prediction Using Cloud control Big data Analysis

Machine Learning-Driven Traffic Flow Prediction Using Cloud ...

引用

Virtual Reality (ICVR), ieee International conference on

作者： Khurrum Jalil Qian Chen Muhammad Noaman Zahid Fazila Jalil Department of Traffic Engineering University of Shanghai for Science and Technology Shanghai China School of Information Hunan University of Humanities Science and Technology Loudi China School of Economics and Management University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350364231

ISBN: (纸本)9798350364248

Due to the increasing number of intelligent vehicles (IVs) on existing roads, IVs present several challenges, such as congestion, CO 2 emissions, idling, and travel delays. Transportation departments rely on forecasting methods using traffic flow data to address issues before implementing new plans for smooth traffic flow. To achieve this, managing the vast amounts of intelligent transportation system (ITS) data necessitates the adoption of cloud computing for data storage capabilities and machine learning methods to facilitate efficient traffic prediction analysis. In addition, real-time data analysis is crucial for evaluating the effectiveness of the on-going implementation of the ITS plans and identifying gaps for improvement. In this paper, the proposed method integrates a machine learning-based traffic flow prediction model that uses cloud computing for traffic data analytics. then, the efficiency ratio of the proposed method is evaluated. through experimentation, we demonstrate the effectiveness of our method, achieving a prediction accuracy of up to 90%. this result suggests that the proposed approach is highly competitive compared to existing solutions.

关键词： Cloud computing Solid modeling data analysis Roads Transportation Memory Virtual reality Machine learning Predictive models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Combining Model-Based and data-Based Approaches for Online Predictions of Human Trajectories

Combining Model-Based and Data-Based Approaches for Online P...

引用

ieee/RAS-EMBS International conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： Aymeric Orhan Dorian Verdel Olivier Bruneau Franck Geffard Bastien Berret CEA List Université Paris-Saclay Palaiseau France Department of Bioengineering Human Robotics Group Imperial College of Science Technology and Medicine London United-Kingdom LURPA Mechanical Engineering Department ENS Paris-Saclay Université Paris-Saclay Gif-sur-Yvette France CIAMS Sport Sciences Department Univcrsité Paris-Saclay Orsay France CIAMS Université d'Orléans Orléans France

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Accurately predicting human movement trajectories is of critical interest in multiple fields, including human-exoskeleton interaction. In general, such predictions can be obtained from model-based approaches (e.g., optimal control theory) or from data-driven approaches (e.g., learning from human demonstrations). data-driven methods generally require numerous demonstrations but avoid the computational burden of model-based methods. In this paper, we introduce a hybrid method mixing the strengths of these two approaches to enable the prediction of human trajectories in a receding-horizon fashion when the number of actual demonstrations is very limited. First, we propose to use the stochastic optimal feedforward-feedback control framework to generate a large set of humanlike trajectories, including their variability. Second, we used the probabilistic movement primitives (ProMPs) frame-work to learn the distribution of these synthetic trajectories and make online predictions about the upcoming human trajectories from the observation of past movement data. Here, we evaluated our hybrid method on an existing data set composed of arm reaching movements in a parasagittal plane. Overall, our method proves to be advantageous when generalization is needed and demonstrations are lacking, such as in novel targets scenarios. the introduced method shows promise to efficiently predict realistic human trajectories on a given time horizon, even when limited or no human demonstration is available for the task at hand.

关键词： Computational modeling Optimal control Stochastic processes Training data Predictive models Motors Cost function Real-time systems Trajectory Robots

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：