检索结果-内蒙古大学图书馆

arXiv 2022年

作者： von Rohr, Alexander Solowjow, Friedrich Trimpe, Sebastian Institute for Data Science in Mechanical Engineering RWTH Aachen University Aachen Germany Max Planck Institute for Intelligent Systems Stuttgart Germany IAV GmbH Ingenieurgesellschaft Auto und Verkehr Germany

Robust controllers ensure stability in feedback loops designed under uncertainty but at the cost of performance. Model uncertainty in time-invariant systems can be reduced by recently proposed learning-based methods, which improve the performance of robust controllers using data. However, in practice, many systems also exhibit uncertainty in the form of changes over time, e.g., due to weight shifts or wear and tear, leading to decreased performance or instability of the learning-based controller. We propose an event-triggered learning algorithm that decides when to learn in the face of uncertainty in the LQR problem with rare or slow changes. Our key idea is to switch between robust and learned controllers. For learning, we first approximate the optimal length of the learning phase via Monte-Carlo estimations using a probabilistic model. We then design a statistical test for uncertain systems based on the moment-generating function of the LQR cost. The test detects changes in the system under control and triggers relearning when control performance deteriorates due to system changes. We demonstrate improved performance over a robust controller baseline in a numerical example. Copyright © 2022, The Authors. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights

arXiv

引用

arXiv 2024年

作者： Heidari, Moein Azad, Reza Kolahi, Sina Ghorbani Arimond, René Niggemeier, Leon Sulaiman, Alaa Bozorgpour, Afshin Aghdam, Ehsan Khodapanah Kazerouni, Amirhossein Hacihaliloglu, Ilker Merhof, Dorit School of Biomedical Engineering University of British Columbia BC Canada Faculty of Electrical Engineering and Information Technology RWTH Aachen University Aachen Germany Department of Industrial and Systems Engineering Tarbiat Modares University Tehran Iran Faculty of Information Science and Technology Universiti Kebangsaan Bangi Malaysia Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Department of Electrical Engineering Shahid Beheshti University Tehran Iran Department of Computer Science University of Toronto Toronto Canada Department of Radiology Department of Medicine University of British Columbia BC Canada Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Intrigued by the inherent ability of the human visual system to identify salient regions in complex scenes, attention mechanisms have been seamlessly integrated into various Computer Vision (CV) tasks. Building upon this paradigm, Vision Transformer (ViT) networks exploit attention mechanisms for improved efficiency. This review navigates the landscape of redesigned attention mechanisms within ViTs, aiming to enhance their performance. This paper provides a comprehensive exploration of techniques and insights for designing attention mechanisms, systematically reviewing recent literature in the field of CV. This survey begins with an introduction to the theoretical foundations and fundamental concepts underlying attention mechanisms. We then present a systematic taxonomy of various attention mechanisms within ViTs, employing redesigned approaches. Amulti-perspective categorization is proposed based on their application, objectives, and the type of attention applied. The analysis includes an exploration of the novelty, strengths, weaknesses, and an in-depth evaluation of the different proposed strategies. This culminates in the development of taxonomies that highlight key properties and contributions. Finally, we gather the reviewed studies along with their available open-source implementations at our *** aim to regularly update it with the most recent relevant papers. © 2024, CC BY-NC-SA.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

On Controller Tuning with Time-Varying Bayesian Optimization

arXiv

引用

arXiv 2022年

作者： Brunzema, Paul von Rohr, Alexander Trimpe, Sebastian Institute for Data Science in Mechanical Engineering RWTH Aachen University Aachen Germany Max Planck Institute for Intelligent Systems Stuttgart Germany IAV GmbH Ingenieurgesellschaft Auto und Verkehr Germany

Changing conditions or environments can cause system dynamics to vary over time. To ensure optimal control performance, controllers should adapt to these changes. When the underlying cause and time of change is unknown, we need to rely on online data for this adaptation. In this paper, we will use time-varying Bayesian optimization (TVBO) to tune controllers online in changing environments using appropriate prior knowledge on the control objective and its changes. Two properties are characteristic of many online controller tuning problems: First, they exhibit incremental and lasting changes in the objective due to changes to the system dynamics, e.g., through wear and tear. Second, the optimization problem is convex in the tuning parameters. Current TVBO methods do not explicitly account for these properties, resulting in poor tuning performance and many unstable controllers through over-exploration of the parameter space. We propose a novel TVBO forgetting strategy using Uncertainty-Injection (UI), which incorporates the assumption of incremental and lasting changes. The control objective is modeled as a spatio-temporal Gaussian process (GP) with UI through a Wiener process in the temporal domain. Further, we explicitly model the convexity assumptions in the spatial dimension through GP models with linear inequality constraints. In numerical experiments, we show that our model outperforms the state-of-the-art method in TVBO, exhibiting reduced regret and fewer unstable parameter configurations. Copyright © 2022, The Authors. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Graph Matching Optimization Network for Point Cloud Registration

Graph Matching Optimization Network for Point Cloud Registra...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Qianliang Wu Yaqi Shen Haobo Jiang Guofeng Mei Yaqing Ding Lei Luo Jin Xie Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Faculty of Engineering and Information Technology University of Technology Sydney Sydney NSW Australia

Point Cloud Registration is a fundamental and challenging problem in 3D computer vision. Recent works often utilize geometric structure features in downsampled points (patches) to seek correspondences, then propagate these sparse patch correspondences to the dense level in the corresponding patches' neighborhood. However, they neglect the explicit global scale rigid constraint at the dense level point matching. We claim that the explicit isometry-preserving constraint in the dense level on a global scale is also important for improving feature representation in the training stage. To this end, we propose a Graph Matching Optimization based Network (GMONet for short), which utilizes the graph-matching optimizer to explicitly exert the isometry preserving constraints in the point feature training to improve the point feature representation. Specifically, we exploit a partial graph-matching optimizer to enhance the super point (i.e., down-sampled key points) features and a full graph-matching optimizer to improve the dense level point features in the overlap region. Meanwhile, we leverage the inexact proximal point method and the mini-batch sampling technique to accelerate these two graph-matching optimizers. Given high discriminative point features in the evaluation stage, we utilize the RANSAC approach to estimate the transformation between the scanned pairs. The proposed method has been evaluated on the 3DMatch/3DLoMatch and the KITTI datasets. The experimental results show that our method performs competitively compared to state-of-the-art baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving the Performance of Robust Control through Event-Triggered Learning

Improving the Performance of Robust Control through Event-Tr...

引用

IEEE Conference on Decision and Control

作者： Alexander von Rohr Friedrich Solowjow Sebastian Trimpe Institute for Data Science in Mechanical Engineering RWTH Aachen University Aachen Germany Max Planck Institute for Intelligent Systems Stuttgart Germany IAV GmbH Ingenieurgesellschaft Auto und Verkehr Germany

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

关键词： Robust control Uncertain systems Uncertainty Costs Switches Probabilistic logic Control systems

来源：评论

学校读者我要写书评

暂无评论

Identification of Clinical Features Associated with Mortality in COVID-19 Patients

引用

Operations Research Forum 2023年第1期4卷 16页

作者： Eskandarian, Rahimeh Alizadehsani, Roohallah Behjati, Mohaddeseh Zahmatkesh, Mehrdad Sani, Zahra Alizadeh Haddadi, Azadeh Kakhi, Kourosh Roshanzamir, Mohamad Shoeibi, Afshin Hussain, Sadiq Khozeimeh, Fahime Darbandy, Mohammad Tayarani Joloudari, Javad Hassannataj Lashgari, Reza Khosravi, Abbas Nahavandi, Saeid Islam, Sheikh Mohammed Shariful Internal Medicine Research Center Semnan University of Medical Sciences Semnan Iran Institute for Intelligent Systems Research and Innovation (IISRI) Deakin University Victoria Australia Rajaei Cardiovascular Medical and Research Center Iran University of Medical Sciences Tehran Iran Omid Hospital Iran University of Medical Sciences Tehran Iran Department of Biology Faculty of Basic Sciences Shahrekord Branch Islamic Azad University Shahrekord Iran Department of Computer Engineering Faculty of Engineering Fasa University Fasa 74617-81189 Iran Data Science and Computational Intelligence Institute University of Granada Granada Spain System Administrator Dibrugarh University Assam 786004 India School of Architecture Islamic Azad University Taft Taft *** Iran Department of Computer Engineering Faculty of Engineering University of Birjand Birjand Iran Department of Computer Engineering Amol Institute of Higher Education Amol Iran Institute of Medical Science and Technology Shahid Beheshti University Tehran Iran School of Engineering and Applied Sciences Harvard Paulson Harvard University Allston 02134 MA United States Institute for Physical Activity and Nutrition School of Exercise and Nutrition Sciences Deakin University Geelong 3220 VIC Australia Cardiovascular Division The George Institute for Global Health Newtown Australia Sydney Medical School University of Sydney Camperdown Australia

Understanding clinical features and risk factors associated with COVID-19 mortality is needed to early identify critically ill patients, initiate treatments and prevent mortality. A retrospective study on COVID-19 patients referred to a tertiary hospital in Iran between March and November 2020 was conducted. COVID-19-related mortality and its association with clinical features including headache, chest pain, symptoms on computerized tomography (CT), hospitalization, time to infection, history of neurological disorders, having a single or multiple risk factors, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia were investigated. Based on the investigation outcome, decision tree and dimension reduction algorithms were used to identify the aforementioned risk factors. Of the 3008 patients (mean age 59.3 ± 18.7 years, 44% women) with COVID-19, 373 died. There was a significant association between COVID-19 mortality and old age, headache, chest pain, low respiratory rate, oxygen saturation < 93%, need for a mechanical ventilator, having symptoms on CT, hospitalization, time to infection, neurological disorders, cardiovascular diseases and having a risk factor or multiple risk factors. In contrast, there was no significant association between mortality and gender, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia. Our results might help identify early symptoms related to COVID-19 and better manage patients according to the extracted decision tree. The proposed ML models identified a number of clinical features and risk factors associated with mortality in COVID-19 patients. These models if implemented in a clinical setting might help to early identify patients needing medical attention and care. However, more studies are needed to confirm these findings. © 2023, The Author(s).

关键词： COVID‐19 Machine learning Mortality Risk factors Symptoms

来源：评论

学校读者我要写书评

暂无评论

Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution

Feature Aggregating Network with Inter-Frame Interaction for...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yawei Li Zhao Zhang Suiyi Zhao Jicong Fan Haijun Zhang Mingliang Xu School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Computer Science Harbin Institute of Technology Shenzhen China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spark based Parallel Frequent Pattern Rules for Social Media data Analytics

Spark based Parallel Frequent Pattern Rules for Social Media...

引用

Cluster, Cloud and Internet Computing Workshops (CCGridW), IEEE/ACM International Symposium on

作者： Shubhangi Chaturvedi Sri Khetwat Saritha Animesh Chaturvedi Computer Science and Engineering PDPM Indian Institute of Information Technology Design and Manufacturing Jabalpur (IIITDM Jabalpur) Jabalpur M.P. India Computer Science and Engineering Maulana Azad National Institute of Technology (NIT Bhopal) Bhopal M.P. India Data Science and Intelligent Systems Indian Institute of Information Technology Dharwad (IIIT Dharwad) Dharwad Karnataka India

The number of users on social media are increasing, thus the data produced is also increasing tremendously. Social media data mining and analysis can produce a lot of hidden information, which can be helpful in decision-making. Prediction of the co-occurring words with confidence can provide deep insights of social media. The paper presents an applied process to mine social media dataset to retrieve frequent patterns (or rules) in cost effective time. The retrieved patterns can be useful in making decisions related to social media. The experiment is performed on three social media datasets and various rules are analyzed by varying the values of threshold (minimum support and minimum confidence). Experiments are also performed for both Frequent Pattern (FP) Growth and Parallel FP (PFP) Growth using the same datasets. The parallel computation is achieved with the help of a scalable Apache Spark environment. Execution time for both FP-Growth and PFP-Growth on the same datasets is also described. While performing experiments it is found that FP-Growth of SPMF requires preprocessing to convert item-sets into transactional databases. The pre-processing time is required only once, as a result the time required to generate rules is less. Whereas, the PFP-Growth does not require preprocessing on the dataset to generate rules. This saves time to directly generate the association rules using PFP-Growth.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation

arXiv

引用

arXiv 2024年

作者： Li, Yicong Sun, Xiangguo Chen, Hongxu Zhang, Sixiao Yang, Yu Xu, Guandong Data Science and Machine Intelligence Lab Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW2007 Australia Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong999077 Hong Kong School of Information Technology and Electrical Engineering The University of Queensland BrisbaneQLD4072 Australia Department of Systems Engineering and Engineering Management Nanyang Technological University Singapore999077 Singapore Department of Computing The Hong Kong Polytechnic University Hong Kong999077 Hong Kong

Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on four real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning Based Adaptive Crop Price Prediction for Agriculture Application 5

Meta-Learning Based Adaptive Crop Price Prediction for Agric...

引用

5th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2021

作者： Dhanasekaran, K. Ramprasath, M. Sathiyamoorthi, V. Poornima, N. Jayaraj, Irrai Anbu SRM Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Data Science and Business Systems TN Chennai Chengalpattu603 203 India Sona College of Technology TN Salem India CSL Australia Pty Ltd Australia

ISBN: (纸本)9781665435246

Dealing with unexpected changes in agricultural product prices that affect the farmers and the economic growth of a country is inevitable in the current day context. A unique approach is proposed for time-series prediction, which utilizes the power of crop price prediction and crop yield prediction of select crops to identify the relevant information with respect to the market prices, and crop yields. Many uncertain conditions such as climate changes, fluctuations in market, flooding, etc., cause problems to the agricultural process. In this work, the prices of selected essential crops analyzed for time-series prediction using meta-learning. The Self-Organized Map (S OM), LSTM (Long-Short Term Model), and this proposed Meta-Learning Based Adaptive Crop Price Prediction (MLACPP) was trained using crop price dataset, and crop yield dataset. Meta-learning function used in the approach utilizes the input, optimization-output, and task-related estimators for calculating meta-loss over multiple meta-network. The meta-learning with self-organizing capability learns a meta-network observing additional information from specialized support set. Moreover, this method deals with a task-oriented loss. Interestingly, it compares the current optimal-output of the optimization function g with the target-specific information. Experimental results show significant improvement in terms of prediction accuracy and cross-correlation entropy over the existing crop price prediction approaches. This research work provides the basis for making better decisions for price-fixing and crop yield maximization based on insights obtained from the dataset. © 2021 IEEE.

关键词： Crops

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：