检索结果-内蒙古大学图书馆

27th International Conference on Automation and Computing, ICAC 2022

作者： Nikentari, Nerfita Wei, Hua-Liang University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Traditional time series forecasting models based on neural networks are usually designed for a single task, which ignores the source of knowledge or information from other related tasks. On the other hand, multitask learning (MTL) offers a new perspective where one model is not only for one forecasting case or task but several tasks at the same time. The MTL model proposed in this study is based on the Nonlinear AutoRegressive Moving Average with eXogenous input (NARMAX) model and Long-Short Term Memory (LSTM) Neural Networks. The NARMAX-LSTM model is tested and validated using three different time horizons and different cases/tasks. The model forecasting performance is compared with that of three other linear and nonlinear models. The comparison results show that the multi-task NARMAX-LSTM model does not only have better prediction performance but also avoid suffering from negative transfer and overfitting. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Virtual flight deck crew assistance utilizing artificial intelligence methods to interpret NOTAMs: a user acceptance study

引用

CEAS Aeronautical Journal 2024年第4期15卷 1137-1144页

作者： Dieter, Michelle Sprenger, Eric Pasnicu, Otilia Staudt, Josefine Ellenrieder, Nils Institute of Flight Systems and Automatic Control Technical University of Darmstadt Otto-Berndt-Str. 2 Darmstadt64287 Germany Work and Engineering Psychology Research Group Technical University of Darmstadt Alexanderstr. 10 Darmstadt64283 Germany

Over the past few years, artificial intelligence (AI) and machine learning (ML) methods have become deeply embedded in everyday applications. Great progress has been made, which is why these methods are now being introduced to other areas including aviation. The use of such methods in safety-critical areas like aviation, medicine or jurisdiction, entails not only benefits but also challenges, such as regulatory and ethical aspects and the necessary acceptance of users and other stakeholders. This research paper presents the findings of a qualitative user study conducted to investigate the potential benefits of integrating AI on the flight deck to improve the usability of Notices to Airmen (NOTAMs). Currently, pilots receive a large amount of NOTAMs for each flight. This overload of information can lead to important information being overlooked. Semi-structured interviews with ten pilots were conducted to gather their perspectives on current challenges in their daily work with NOTAMs, acceptance of AI-based methods in aviation with focus on the flight deck and possible fields of applications. Recommendations are derived for future developments. The findings suggest that methods based on AI have the potential to improve the usability of NOTAMs, making them more efficient and user-friendly for pilots. Additionally, the study highlights the importance of addressing pilots’ concerns and taking into account human factors, safety considerations, and the need for effective human–machine collaboration. © Deutsches Zentrum für Luft- und Raumfahrt e.V. 2024.

关键词： Aviation medicine

来源：评论

学校读者我要写书评

暂无评论

Output Tracking for Uncertain Time-Delay systems via Robust Reinforcement Learning control

Output Tracking for Uncertain Time-Delay Systems via Robust ...

引用

第43届中国控制会议

作者： Zezhi Tang J Anthony Rossiter Xin Jin Benyuan Zhang George Panoutsos Department of Automatic Control and Systems Engineering University of Sheffield

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The composite optimal output tracking control problem of time-delay uncertain systems is investigated in this paper. To improve the robustness of the uncertain systems, a disturbance observer-based(DOB) compensation scheme is proposed to reduce the influence of the *** further enhance the control efficiency, we incorporate a Smith predictor into the control framework to precisely predict future states of the delayed system. Subsequently, a composite actor-critic reinforcement learning(RL) scheme is built for approximating both the ideal value function associated with the compensated system and the optimal control policy in real-time, by augmenting the system states with the output tracking error. To counteract the impact of the probing signal, concurrent learning is employed in this paper with the data collected from the known system *** results based on an experimental platform of slot die coating machines demonstrate the effectiveness of the proposed scheme.

关键词： Smith Output Tracking for Uncertain Time-Delay systems via Robust Reinforcement Learning control

来源：评论

学校读者我要写书评

暂无评论

Open-Loop and Feedback Nash Trajectories for Competitive Racing with iLQGames 27

Open-Loop and Feedback Nash Trajectories for Competitive Rac...

引用

27th IEEE International Conference on Intelligent Transportation systems, ITSC 2024

作者： Rowold, Matthias Langmann, Alexander Lohmann, Boris Betz, Johannes Tum School of Engineering and Design Technical University of Munich Chair of Automatic Control Germany Tum School of Engineering and Design Technical University of Munich Professorship of Autonomous Vehicle Systems Germany

ISBN: (纸本)9798331505929

Interaction-aware trajectory planning is crucial for closing the gap between autonomous racing cars and human racing drivers. Prior work has applied game theory as it provides equilibrium concepts for non-cooperative dynamic problems. With this contribution, we formulate racing as a dynamic game and employ a variant of iLQR-called iLQGames-to solve the game. iLQGames finds trajectories for all players that satisfy the equilibrium conditions for a linear-quadratic approximation of the game and has been previously applied in traffic scenarios. We analyze the algorithm's applicability for trajectory planning in racing scenarios and evaluate it based on interaction awareness, competitiveness, and safety. With the ability of iLQGames to solve for open-loop and feedback Nash equilibria, we compare the behavioral outcomes of the two equilibrium concepts in simple scenarios on a straight track section. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Improving Motor Imagery-Based Brain-Computer Interfaces with Simple EEG Data Augmentation Algorithms: A Comparative Analysis 3

Improving Motor Imagery-Based Brain-Computer Interfaces with...

引用

3rd IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2024

作者： Goswami, Sourojit Phelan, Jacob Anderson, Sean Arvaneh, Mahnaz University of Sheffield Sheffield United Kingdom Automatic Control and Systems Engineering Sheffield Sheffield United Kingdom Insigneo Institute Neuroscience Institute Sheffield United Kingdom

ISBN: (纸本)9798350378009

One of the primary challenges in motor imagery (MI) based brain-computer interfaces (BCIs) is the extensive calibration time required for individual users. This paper systematically reviews and compares various straightforward EEG data augmentation techniques aimed at reducing calibration time and enhancing model performance. We explored several algorithms, including segmentation and recombination in the time-frequency domain using short-time Fourier transform (TFSR), time warping (TW), noise injection (NI), and naïve transfer learning (NTL). Additionally, we introduced a novel algorithm called time instance segment concatenation (TISC), which merges EEG segments from periods immediately before and after the traditional motor imagery segments to capture a broader range of neural dynamics. Our experimental results on the BCI Competition IV dataset 2a indicated that NTL was the top-performing algorithm, achieving average accuracy improvements of 4.9%, 3%, 1.7%, and 3.2% over the baseline model without any data augmentation when 5, 10, 15, and 20 training trials per class were available, respectively. The proposed TISC algorithm showed potential, particularly in scenarios with moderate training trials, e.g., achieving an average accuracy increase of 1.5% over the baseline when 10 training trials per class were available. These findings suggest that TISC could be a useful addition to EEG data augmentation methods to improve the efficiency and usability of MI-based BCIs. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Tide Level Prediction Using NARX-based Recurrent Neural Networks 27

Tide Level Prediction Using NARX-based Recurrent Neural Netw...

引用

27th International Conference on Automation and Computing, ICAC 2022

作者： Nikentari, Nerfita Wei, Hua-Liang University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Tide level forecasting is one of major components in oceanography and marine research. The future prediction of tides is an important issue for human and environment. This study proposes new tide level prediction methods with multiple input multiple output (MIMO) approach based on nonlinear autoregressive with exogenous inputs (NARX) model and three types of recurrent neural networks (RNNs), namely, long short-term memory (LSTM), bi-directional long short-term memory (biLSTM) and gated recurrent unit (GRU) networks. We develop three types of NARX models: NARX-LSTM, NARX-biLSTM and NARX-GRU. We evaluate the three models and compare their performances with LSTM, biLSTM and GRU network models. It turns out that the proposed MIMO NARX based RNN models, especially NARX-LSTM and NARX-GRU have better performance in comparison with their RNN counterparts (i.e., LSTM, biLSTM, and GRU). The NARX-GRU model shows the best performance for one step and three step ahead prediction in terms of RMSE in each location and average RMSE, while NARX-LSTM performs better for two steps ahead prediction in terms average RMSE. The results also show that the mixture of RNN and NARX improves the performance of RNN model for all the four tasks at four locations in the UK (Wick, Workington, Ullapol and New Heaven) and for the three time horizons (i.e., 1, 2 and 3 steps ahead). © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Hybrid 1DCNN-SVM Model for Bearing Fault Recognition and Classification 27

A Hybrid 1DCNN-SVM Model for Bearing Fault Recognition and C...

引用

27th International Conference on Automation and Computing, ICAC 2022

作者： Wang, Guoliang Wei, Hua-Liang University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Rolling bearings play a significant role in the operation of rotating machinery. Finding bearing faults in the early stage can not only keep machinery running safely but also avoid economic loss. Traditional machine learning (ML) and deep learning (DL) are two important classes of fault diagnosis methods. The process of feature extraction is significant for ML based methods and many signal processing techniques have been used in this process. However, when dealing with massive and complex signals, features extracted by these techniques may not fully describe the characteristics of faults. Convolutional neural network (CNN) models are applied in many areas, including image identification and classification, pattern recognition, and speech processing. In this paper, a novel hybrid model by combining one dimensional CNN (1DCNN) and support vector machine (SVM) is proposed for bearing fault diagnosis and classification, which is called 1DCNN-SVM model or method. The first part of the model, 1DCNN, is used to extract features of raw data, whereas the second part, SVM, is employed to carry out the fault recognition and classification tasks. The evaluation of the proposed method is operated based on a real dataset. The experiment results show that the fault diagnosis accuracy of proposed method based on the hybrid model is highly improved compared to the traditional SVM based methods. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Analysing and Modelling Human Trust to a Navigation Robot 2

Analysing and Modelling Human Trust to a Navigation Robot

引用

2nd Edition IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2023

作者： Onyeoru, Happy Chidi Wirth, Christopher Giles, Joshua Arvaneh, Mahnaz University of Sheffield Department of Automatic Control and Systems Engineering United Kingdom School of Medical Sciences University of Manchester United Kingdom

ISBN: (纸本)9798350300802

Human trust plays a crucial role in Human-Machine Interactions (HMIs) within autonomous systems. This paper delves into the factors that influence human trust in machines, including varying error rates and types made by the machine, as well as the human's ability to intervene and rectify errors. To explore these factors, we conducted three scenarios involving a simulated claw robot navigating through multiple objects to detect and locate a target object. The first scenario examined the effect of changing error rates on human trust in the machine. In the second scenario, we investigated how variability in speed and accuracy of reaching the target impacted human trust. Lastly, we explored whether human trust in the machine changed when individuals had the capability to intervene and correct severe errors made by the machine. We then proposed a regression model to estimate human trust. Our results showed that human trust is significantly affected by changes in error rates. Our participants reported a higher trust on robot with low speed but higher accuracy in performing the task than the robot with high speed but lower accuracy. Interestingly, the ability to intervene and correct the robot's errors improved the participants' trust in the robot. Our regression result showed that we can estimate trust using different type of errors committed by machine which can be applied in real world scenarios. © 2023 IEEE.

关键词： computational modelling error rates human-machine interactions (HMIs) machine or robot action perceptions target identification trust

来源：评论

学校读者我要写书评

暂无评论

Efficient Mask Attention-Based NARMAX (MAB-NARMAX) Model Identification 27

Efficient Mask Attention-Based NARMAX (MAB-NARMAX) Model Ide...

引用

27th International Conference on Automation and Computing, ICAC 2022

作者： Sun, Yiming Wei, Hua-Liang University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Model structure selection is crucial in system identification and data-driven modelling. Many spurious candidate variables can influence the determination of model structures due to the lack of prior knowledge of the system of interest. The commonly used method is to test as many possible models as possible and select a set of best models. This study proposes a novel mask attention-based NARMRAX (MAB-NARMAX) modelling method for nonlinear dynamic system identification. The mask attention mechanism comes from the widely used neural network Transformer to reduce the dependency of the features and neurons. The performance of the proposed method is tested on three simulation datasets. Results show that the proposed MAB-NARMAX modelling framework has convincing multistep-ahead prediction performance for nonlinear system identification in that it can produce the precious model structure. Even when the data are polluted with high noise (resulting in low SNR), the proposed method can still generate reliable system models compared with the state-of-the-art machine learning methods, e.g., LASSO and LSTM. © 2022 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Medical and Healthcare Data Analysis and Modelling: Case Studies and Performance Comparisons of Different Methods 27

Machine Learning for Medical and Healthcare Data Analysis an...

引用

27th International Conference on Automation and Computing, ICAC 2022

作者： Sun, Bo Wei, Hua-Liang University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

In smart healthcare, binary classification is one of the most important tasks for disease or clinical outcome prediction. Machine learning (ML) methods have great potential to discover knowledge from data. While there are a wide range of ML methods that are potentially useful, the selection, design and implementation of an appropriate method from a variety of ML models for specific prediction tasks is still quite challenging in many medical and healthcare data modelling tasks. This paper investigates, evaluate and compares nine typical representative ML methods using four clinical and healthcare datasets. The main attention is paid to the strengths and weaknesses of these methods and provide suggestions to researchers in related fields. Results demonstrate that ensemble learning (such as Adaboost and random forest) outperform the other approaches in prediction accuracy and interpretability. © 2022 IEEE.

关键词： Adaptive boosting

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：