检索结果-内蒙古大学图书馆

5th international conference on Emerging Electrical Energy, Electronics and Computing Technologies, ICE4CT 2024

作者： Yusoff, C.M.Y.A. Che Mat Nadzri, N.Z. Yusoff, Y. UniKL Robotics and Industrial Automation Center Universiti Kuala Lumpur Malaysia France Institute Selangor Bangi Malaysia

The traditional approach to identifying paddy leaf diseases in Malaysia's agriculture sector involves visual inspection by farmers or agricultural experts. However, this method heavily relies on human expertise to recognize visual symptoms like discoloration, spots, or lesions on the leaves, leading to subjective assessments and delayed diagnosis. While various deep learning models have been utilized to detect paddy leaf diseases, there is a need for a more comprehensive discussion on the appropriate hyperparameters setting. This study focused on utilizing Convolutional Neural Network (CNN) models, specifically ResNet and VGG architectures, to identify paddy leaf diseases in Sekinchan, Selangor. The models were trained on a dataset consisting of both online and real-world images, which underwent several augmentation processes to enhance the model's robustness. The study has highlighted the optimal hyperparameters of the CNN model, resulting in an impressive accuracy rate of 98.71% and a minimal loss rate of 0.001. The integration of the final model into a specific Graphical User Interface has further enhanced its utility. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

FeaKM: Robust Collaborative Perception under Noisy Pose Conditions 24

FeaKM: Robust Collaborative Perception under Noisy Pose Cond...

引用

4th international Joint conference on robotics and Artificial Intelligence, JCRAI 2024

作者： Hao, Jiuwu Sun, Liguo Xiang, Ti Wan, Yuting Song, Haolin Lv, Pin University of Chinese Academy of Sciences Beijing China Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400710100

Collaborative perception is essential for networks of agents with limited sensing capabilities, enabling them to work together by exchanging information to achieve a robust and comprehensive understanding of their environment. However, localization inaccuracies often lead to significant spatial message displacement, which undermines the effectiveness of these collaborative efforts. To tackle this challenge, we introduce FeaKM, a novel method that employs Feature-level Keypoints Matching to effectively correct pose discrepancies among collaborating agents. Our approach begins by utilizing a confidence map to identify and extract salient points from intermediate feature representations, allowing for the computation of their descriptors. This step ensures that the system can focus on the most relevant information, enhancing the matching process. We then implement a target-matching strategy that generates an assignment matrix, correlating the keypoints identified by different agents. This is critical for establishing accurate correspondences, which are essential for effective collaboration. Finally, we employ a fine-grained transformation matrix to synchronize the features of all agents and ascertain their relative statuses, ensuring coherent communication among them. Our experimental results demonstrate that FeaKM significantly outperforms existing methods on the DAIR-V2X dataset, confirming its robustness even under severe noise conditions. The code and implementation details are available at https://***/uestchjw/FeaKM. © 2024 Copyright held by the owner/author(s).

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Experimental Study of Machine Learning models for Prediction of Non-Stationary Non-Seasonal Time Series 1

引用

7th international Russian automation conference, RusAutoCon 2024

作者： Shustrova, M. Mukhamadiev, R. Staroverova, N. Kazan National Reseach Technological Univercity 72 Karl Marks Street Kazan420015 Russia

ISBN: (数字)9783031824944

ISBN: (纸本)9783031824937

This article is devoted to the issue of forecasting the duration of projects in an it company specializing in automation of technological and business processes. The initial data for the study are information about real projects over 10 years. The processed data set with inclusion of additional correlating characteristics is considered. This data does not have pronounced seasonal characteristics and an explicit trend sufficient for project planning, so the task of predicting the duration of work in this case is of great relevance. The study examined time series prediction models for data of a similar nature. Machine learning models were experimentally used to predict the studied data set. To improve the selection of characteristics, modern methods of optimization and search for configuration parameters were used. The experimental part of the study investigated the results of predictions obtained by the models LSTM, Auto ARIMA, Linear regression, K-averages, ARIMA, SARIMA, Prophet. The results of each model construction were analyzed on the basis of which the models were modified to achieve the necessary criteria for the task. Comparison of the results of forecasting models on the dataset under consideration revealed that LSTM neural network models are most suitable for solving the problem. The LSTM model showed an accuracy ~ 61 times that of the Prophet model based on standard error. Linear regression and K-averages also showed a satisfactory result. The information presented in this paper can be useful for forecasting modelers, data analysts and IT specialists, engineers in the field of automation and process control. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Deep Learning models for Predictive Stability in Renewable Energy 3

Deep Learning Models for Predictive Stability in Renewable E...

引用

3rd IEEE international conference on automation and Computation, AUTOCOM 2025

作者： Banka, Sujatha Kumar, Chava Sunil Anupriya, Theegala Vineela, Jakkula Harshitha, Arakala Poojitha, Bhimpavu Bvrit Hyderabad College of Engineering for Women Department of Electrical and Electronics Engineering Hyderabad India

ISBN: (纸本)9798331542375

The usage of renewable energy sources is changing the distribution of energy. This makes customers both energy users and producers, which means that energy flows both ways in smart grids. In this complicated system, keeping the balance between supply and demand in check is necessary for keeping the grid safe. Researchers are currently focusing on decentralized smart grid control (DSGC) systems that measure grid frequency, which is a key indicator of power balance, to get a real-time idea of how stable the system is. Using math equations, the DSGC model predicts grid stability in a simple 4node star structure. That being said, this model is too simple and needs more complex approaches. To make a better analysis, this study uses deep learning methods, such as Keras' sequential model. For prediction purposes, the model includes 60,000 examples and 12 predictive features. These include reaction time, nominal power, and price elasticity. Cross-validation can be used to create an artificial neural network (ANN) with three hidden layers after scaling. When it came to predicting grid safety, this model had an accuracy of 97.73% compared to simpler models. © 2025 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

AE-TabNet: A Two-stage Framework for Traffic Accident Severity Prediction with Imbalanced Data 24

AE-TabNet: A Two-stage Framework for Traffic Accident Severi...

引用

2nd international conference on Frontiers of Intelligent Manufacturing and automation, CFIMA 2024

作者： Han, Wenkai Zhou, Xinhao Zhang, Ancai Zhao, Lin Pan, Guangyuan Linyi University Linyi China

ISBN: (纸本)9798400710681

Traffic Accident Severity Prediction (TASP) is a key and challenging issue in traffic safety management. Real-world traffic accident data exhibit significant imbalances due to uneven spatial and temporal distributions. This imbalance tends to bias prediction methods towards the majority class, posing significant difficulties in developing severity prediction models. In this paper, a two-stage accident severity prediction framework, namely AE-TabNet, for imbalanced traffic accident data, is proposed. This framework combines ADASYN oversampling, EasyEnsemble undersampling and ensemble learning to learn the intrinsic knowledge of the data. Then, it trains an improved two-stage TabNet model and uses Bayesian optimization to automatically search and adjust optimal parameters for accident severity prediction. At last, experiments are designed using real-world traffic accident datasets collected from the United States, France, and Canada, and the model’s effectiveness is validated by comparing with other benchmarks in terms of precision, recall, F1-score, and accuracy. The results also show that AE-TabNet superiors in stability and reliability, especially in predicting minority class samples. © 2024 Copyright held by the owner/author(s).

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Review of Degradation Prediction methods for Proton Exchange Membrane Fuel Cells

A Review of Degradation Prediction Methods for Proton Exchan...

引用

2025 international conference on Electrical automation and Artificial Intelligence, ICEAAI 2025

作者： Ma, Jun Liu, Xiaoqian Wu, Ziheng Shen, Rui Liu, Haining Li, Fajia AECC Hunan Aviation Powerplant Research Institute Hunan Zhuzhou China School of mechanical Engineering University of Jinan Jinan China

ISBN: (纸本)9798331506797

Proton exchange membrane fuel cells (PEMFCs), as a new type of clean and pollution-free power generation device, have the advantages of high energy conversion efficiency, low noise and fast start-up. However, the operation of PEMFCs is affected by multiple factors, and degradation problems are inevitable. Such degradation issues may cause safety hazards, reduce energy conversion efficiency and shorten their service life. Therefore, accurately predicting the degradation process is crucial for developing reliable and durable PEMFCs. This study reviews fuel cell degradation prediction models from three perspectives: model-based, data-driven, and fusion approaches. The study mentioned above is finally discussed. © 2025 IEEE.

关键词： Data-driven Degradation prediction Fusion Model-based PEMFC

来源：评论

学校读者我要写书评

暂无评论

Evaluating Robot Influence on Pedestrian Behavior models for Crowd Simulation and Benchmarking 16th

Evaluating Robot Influence on Pedestrian Behavior Models fo...

引用

16th international conference on Social robotics, ICSR + AI 2024

作者： Agrawal, Subham Dengler, Nils Bennewitz, Maren Humanoid Robots Lab University of Bonn Bonn Germany The Lamarr Institute Bonn Germany Center for Robotics Bonn Germany

ISBN: (纸本)9789819635184

The presence of robots amongst pedestrians affects them causing deviation to their trajectories. Existing methods suffer from the limitation of not being able to objectively measure this deviation in unseen cases. In order to solve this issue, we introduce a simulation framework that repetitively measures and benchmarks the deviation in trajectory of pedestrians due to robots driven by different navigation algorithms. We simulate the deviation behavior of the pedestrians using an enhanced Social Force Model (SFM) with a robot force component that accounts for the influence of robots on pedestrian behavior, resulting in the Social Robot Force Model (SRFM). Parameters for this model are learned using the pedestrian trajectories from the JRDB dataset [1]. Pedestrians are then simulated using the SRFM with and without the robot force component to objectively measure the deviation to their trajectory caused by the robot in 5 different scenarios. Our work in this paper is a proof of concept that shows objectively measuring the pedestrian reaction to robot is possible. We use our simulation to train two different RL policies and evaluate them against traditional navigation models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language models through Simulation and Task Decomposition 31

Decompose-ToM: Enhancing Theory of Mind Reasoning in Large L...

引用

31st international conference on Computational Linguistics, COLING 2025

作者： Sarangi, Sneheel Elgarf, Maha Salam, Hanan NYU Abu Dhabi United Arab Emirates

ISBN: (纸本)9798891761964

Theory of Mind (ToM) is the ability to understand and reflect on the mental states of others. Although this capability is crucial for human interaction, testing on Large Language models (LLMs) reveals that they possess only a rudimentary understanding of it. Although the most capable closed-source LLMs have come close to human performance on some ToM tasks, they still perform poorly on complex variations of the task that involve more structured reasoning. In this work, we utilize the concept of "pretend-play", or "Simulation Theory" from cognitive psychology to propose "Decompose-ToM": an LLM-based inference algorithm that improves model performance on complex ToM tasks. We recursively simulate user perspectives and decompose the ToM task into a simpler set of tasks: subject identification, question-reframing, world model up-dation, and knowledge availability. We test the algorithm on higher-order ToM tasks and a task testing for ToM capabilities in a conversational setting, demonstrating that our approach shows significant improvement across models compared to baseline methods while requiring minimal prompt tuning across tasks and no additional model training. Our code is publicly available. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Development of a toolchain for robust Sim2Real transfer of learning-based robotics applications 1st

Development of a toolchain for robust Sim2Real transfer of l...

引用

1st international conference on Applications of AI in 5G and IOT, ICAAI5GI 2024

作者： Wrede, K. Jain, V. Dehmel, M. Hartmann, N. Lange, R. Dresden Germany

ISBN: (纸本)9781032874036

The increasing complexity of industrial production demands innovative automation solutions. This paper presents a toolchain developed for the robust Sim2Real transfer of reinforcement learning-based control policies in robotic systems, addressing challenges in the inefficient manual programming of task-specific control. Our toolchain facilitates the training within a simulated environment in NVIDIA Isaac or MuJoCo and the subsequent implementation on real-world robotic hardware using ROS 2 for seamless interaction with low-level robot controllers. Several methods to ensure robust performance on real hardware are an integral part of our approach. The first real-world experiments of a dual-arm robotic assembly task demonstrate a 100% success rate, with process times closely matching those in simulations, verifying the model’s robustness to uncertainties in system dynamics and sensor noise. © 2025 the Author(s).

关键词： Robotic assembly

来源：评论

学校读者我要写书评

暂无评论

Data-based tuning of bumpless feedforward for tracking of multi-phase trajectories with application to wire-bonding machine

引用

ISA Transactions 2025年 160卷 257-267页

作者： Xu, Yifan Chen, Silu Xu, Zhuang Zhang, Chi Wang, Weizhen Halim, Dunant Department of Mechanical Materials and Manufacturing Engineering The University of Nottingham Ningbo China 199 Taikang East Road Zhejiang Ningbo315100 China Zhejiang Provincial Key lab of Robotics and Intelligent Manufacturing Equipment Technology Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences 1219 Zhongguan West Road Zhejiang Ningbo315201 China Department of Electrical and Electronic Engineering The University of Nottingham Ningbo China 199 Taikang East Road Zhejiang Ningbo315100 China Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute The University of Nottingham Ningbo China 199 Taikang East Road Zhejiang Ningbo315100 China

To improve the settling time for high-speed point-to-point motion, a piecewise-model feedforward controller is introduced which utilizes multiple inverse sub-models with bumpless transfer between them. As the transfer function of this bumpless feedforward controller is non-commutative and non-invertible, a set of special perturbation and reference inputs are designed to extract the signals required for computing the gradient of the cost function. In this way, the optimal parameters within different motion phases are found within an integrated process. It is experimentally demonstrated in a wire-bonding machine that the root-mean-square of tracking error is improved by at least 15.3% in settling phase by the proposed data-based tuning method with bumpless feedforward controller, compared with existing tuning methods with uniform feedforward controller. © 2025 international Society of automation

关键词： Inverse problems

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：