检索结果-内蒙古大学图书馆

Quantum Reinforcement Learning for QoS-Aware Real-Time Job Scheduling in Cloud systems

IEEE systems Journal 2025年

作者： Dai, Shuhong Saurabh, Nishant Wang, Qingle Nian, Jiawei Kan, Shuwen Mao, Ying Cheng, Long North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources the School of Control and Computer Engineering Beijing102206 China Utrecht University Department of Information and Computing Sciences CS Utrecht 3584 Netherlands Fordham University Department of Computer and Information Science New YorkNY10458 United States

Effective cloud job scheduling is essential for enhancing the performance and operational efficiency of cloud-based services, directly impacting their quality of service (QoS). Among existing methodologies, deep reinforcement learning (DRL) has proven effective in addressing complex, multidimensional optimization challenges in real-time scheduling. With advancements in quantum computing, quantum neural networks (QNNs) are showing unique advantages in information representation and processing. This study is the first to explore quantum reinforcement learning (QRL) for real-time job scheduling in cloud systems. Specifically, we propose a QRL framework that utilizes variational and encoding layers to convert state information into quantum data, repeatedly embedded into a QNN to compute optimal value returns. This approach aims to enhance QoS by improving job execution success rates and reducing average response times with unpredictable job arrivals. We present the detailed design of our approach, and our simulation results demonstrate that the QRL method significantly exceeds established baselines, including those based on DRL, across a range of workload intensities and computational resource configurations. This is particularly evident under high-load conditions, where our approach can achieve 55.2% higher success rates, underscoring its significant potential in cloud job scheduling optimization. © 2007-2012 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Robust temporal alignment for multivariate time series forecasting

引用

Expert systems with Applications 2025年 289卷

作者： Xuguang Wang Mi Zhang Jie Su School of Control and Computer Engineering North China Electric Power University 619 Yonghuabei Street Lianchi District Baoding 071003 PR China Baoding Key Laboratory of State Detection and Optimization Regulation for Integrated Energy System 619 Yonghuabei Street Lianchi District Baoding 071003 PR China

Temporal alignment of time series is crucial in the task of multivariate time series forecasting, as temporal misalignment can introduce randomness into the learned quantitative relationships between the target and related factor time series, resulting in unreliable forecasting outcomes. Nevertheless, anomalous information gain (AIG) and data outliers present significant challenges to the temporal alignment of time series. To address the issues of AIG and data outliers in this study, a time-delay-related ellipsoid is utilized to construct the alignment deviation metric, an information gain-based regularization term is designed to reinforce this metric by penalizing the occurrence of AIG, and an equiprobable ellipsoid-based outlier filtering process is introduced. Finally, a time-delay estimation (TDE) method robust to AIG and data outliers is proposed, upon which the time series alignment is performed. The robustness of the proposed method against AIG and data outliers is validated through simulation and real-data experiments. The wind speed forecast errors of the forecasting models are significantly reduced after aligning the related time series using our method; for instance, the mean squared error (MSE) achieved by traditional machine learning models and deep learning models is reduced to at least 74 % and 95 %, respectively.

关键词： Alignment deviation metric Equiprobable ellipsoid Information gain Temporal alignment Time series forecasting

来源：评论

学校读者我要写书评

暂无评论

Soybeannet: Transformer-Based Convolutional Neural Network for Soybean Pod Counting from Unmanned Aerial Vehicle (Uav) Images

SSRN

引用

SSRN 2023年

作者： Li, Jiajia Magar, Raju Thada Chen, Dong Lin, Feng Wang, Dechun Yin, Xiang Zhuang, Weichao Li, Zhaojian Department of Electrical and Computer Engineering Michigan State University East LansingMI United States Department of Plant Soil and Microbial Sciences Michigan State University East LansingMI United States Environmental Institute & Link Lab University of Virginia CharlottesvilleVA United States Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China School of Mechanical Engineering Southeast University Nanjing China Department of Mechanical Engineering Michigan State University East LansingMI48824 United States

Soybean is a critical source of food, protein, and oil, and thus has received extensive research aimed at enhancing their yield, refining cultivation practices, and advancing soybean breeding techniques. Within this context, soybean pod counting plays an essential role in understanding and optimizing production. Despite recent advancements, the development of a robust pod-counting algorithm capable of performing effectively in real-field conditions remains a significant challenge This paper presents a pioneering work of accurate soybean pod counting utilizing unmanned aerial vehicle (UAV) images captured from actual soybean fields in Michigan, USA. Specifically, this paper presents SoybeanNet, a novel point-based counting network that harnesses powerful transformer backbones for simultaneous soybean pod counting and localization with high accuracy. In addition, a new dataset of UAV-acquired images for soybean pod counting was created and open-sourced, consisting of 113 drone images with more than 260k manually annotated soybean pods captured under natural lighting conditions. Through comprehensive evaluations, SoybeanNet demonstrates superior performance over five state-of-the-art approaches when tested on the collected images. Remarkably, SoybeanNet achieves a counting accuracy of 84.51% when tested on the testing dataset, attesting to its efficacy in real-world scenarios. The publication also provides both the source at https://***/JiajiaLi04/Soybean-Pod-Counting-from-UAV-Images and the labeled soybean dataset at https://***/datasets/jiajiali/uav-based-soybean-pod-images, offering a valuable resource for future research endeavors in soybean pod counting and related fields. © 2023, The Authors. All rights reserved.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

SoybeanNet: Transformer-Based Convolutional Neural Network for Soybean Pod Counting from Unmanned Aerial Vehicle (UAV) Images

arXiv

引用

arXiv 2023年

作者： Li, Jiajia Magar, Raju Thada Chen, Dong Lin, Feng Wang, Dechun Yin, Xiang Zhuang, Weichao Li, Zhaojian Department of Electrical and Computer Engineering Michigan State University East LansingMI United States Department of Plant Soil and Microbial Sciences Michigan State University East LansingMI United States Environmental Institute Link Lab University of Virginia CharlottesvilleVA United States Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China School of Mechanical Engineering Southeast University Nanjing China Department of Mechanical Engineering Michigan State University East LansingMI48824 United States

Soybean is a critical source of food, protein and oil, and thus has received extensive research aimed at enhancing their yield, refining cultivation practices, and advancing soybean breeding techniques. Within this context, soybean pod counting plays an essential role in understanding and optimizing production. Despite recent advancements, the development of a robust pod-counting algorithm capable of performing effectively in real-field conditions remains a significant challenge This paper presents a pioneering work of accurate soybean pod counting utilizing unmanned aerial vehicle (UAV) images captured from actual soybean fields in Michigan, USA. Specifically, this paper presents SoybeanNet, a novel point-based counting network that harnesses powerful transformer backbones for simultaneous soybean pod counting and localization with high accuracy. In addition, a new dataset of UAV-acquired images for soybean pod counting was created and open-sourced, consisting of 113 drone images with more than 260k manually annotated soybean pods captured under natural lighting conditions. Through comprehensive evaluations, SoybeanNet demonstrates superior performance over five state-of-the-art approaches when tested on the collected images. Remarkably, SoybeanNet achieves a counting accuracy of 84.51% when tested on the testing dataset, attesting to its efficacy in real-world scenarios. The publication also provides both the source code (https://***/JiajiaLi04/Soybean-Pod-Counting-from-UAV-Images) and the labeled soybean dataset (https://***/datasets/jiajiali/uav-based-soybean-pod-images), offering a valuable resource for future research endeavors in soybean pod counting and related fields. © 2023, CC BY-NC-SA.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of CFB unit combustion system based on comprehensive economics and entropy weight method

Performance evaluation of CFB unit combustion system based o...

引用

2019 International Conference on Sensing, Diagnostics, Prognostics, and control, SDPC 2019

作者： Qin, Ce Gao, Mingming Zhang, Hongfu North China Electric Power University State Key Laboratory of Alternate Electric Power System with Renewable Energy Sources School of Control and Computer Engineering Beijing China

ISBN: (纸本)9781728101996

performance evaluation method for the combustion system in the variable load process of circulating fluidized bed (CFB) unit based on the minimum variance control is proposed. Each operating parameter are initially weighted according to the dynamic economic index of the operating parameters, and entropy weight method is used to adjust the weights of operating parameter under different operating conditions. Then, the minimum variance index based on comprehensive economic and entropy weight method is proposed to evaluate the performance of the combustion system of CFB unit, which reduces the polarization effect generated by the single weighting performance evaluation method and improves the objective scientificality of the operating parameter weighting. Finally, a case study on the combustion system of a 300MW CFB unit reveals that the minimum variance index based on the comprehensive economy and entropy weight method can better evaluate the performance of the combustion system in the dynamic process of the unit, compared with the traditional performance evaluation method. It is of great significance to the operational safety and economy of CFB boiler units. © 2019 IEEE.

关键词： Economics

来源：评论

学校读者我要写书评

暂无评论

Prediction model of SCR outlet NOx based on LSTM algorithm 2019

Prediction model of SCR outlet NOx based on LSTM algorithm

引用

2nd International Conference on Intelligent Science and Technology, ICIST 2019

作者： Chen, Jiyu Hong, Feng Gao, Mingming Chang, Taihua Xu, Liying State Key Laboratory of Alternate Electric Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (纸本)9781450371742

Pollutants emissions is strictly controlled in modern power plants, and Nitrogen Oxides (NOx), which is the main contaminants is the exhaust gas. The Selective Catalytic Reduction process (SCR) is commonly used for denitration. For achieving an effective the SCR outlet NOx concentration control, an accurate outlet NOx concentration model is necessary. A model using historical data is proposed, and long-short term memory(LSTM) algorithm is applied, which could describe relevance in time series. The accuracy performances for proposed data-driven model are verified, and root mean square error (RMSE) and mean absolute error (MAPE) for training set are, 0.706 mg/m3 and 1.99%, respectively, which for test set are 1.44 mg/m3 and 2.90%, respectively, The verification reveals that the accuracy for data-driven model is acceptable for control system design. © 2019 Association for Computing Machinery.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Practical and High-Performance Nitrogen Dioxide Gas Sensor that Can Be Rapidly Mass-Produced Based on Gallium Nitride Quantum Dots Film

SSRN

引用

SSRN 2022年

作者： Han, Dan Chen, Yi Li, Donghui Dong, Hailiang Xu, Bingshe Sang, Shengbo He, Xiuli Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan030024 China Key Laboratory of Interface Science and Engineering in Advanced Materials Taiyuan University of Technology Ministry of Education Taiyuan030024 China State Key Laboratory of Transducer Technology Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Shanxi Research Institute of 6D Artificiat Intelligence Biomedical Science Taiyuan030024 China

Gallium nitride (GaN) has some challenges for gas sensing, such as high detection lower limit (LOD) or controlling the epitaxy of nanostructures. To address these issues, we exclusively designed a device to enhance the gas interaction capabilities of GaN quantum dots (QDs) film fabricated by metal-organic chemical vapor deposition (MOCVD). The GaN QDs film gas sensor exhibited a low LOD (5 ppb) to NO2 at room temperature (RT), which has much superior gas performance than other GaN-based sensors. The results manifest that many ultra-small QDs around 2 nm in diameter are stacked to form QDs of larger size, and confirm the existence of vacancies. The sensor displays a ultra-high electron mobility of 1237.37 cm2 V−1s−1, demonstrate that great shallow donor impurities in GaN QDs film that ionize easily at RT, which is greatly beneficial for gas sensing. The sensing mechanisms were analyzed based on its abundant active sites, ultrahigh carrier mobility, high surface energy and chemical activity, grain boundary barrier and good electrical conductivity. Moreover, the sensor processes high selectivity, repeatability, stability and reusability based on MOCVD technology which can realize precise control of structure, morphology and surface energy level, which is expected to achieve rapid industrialization. © 2022, The Authors. All rights reserved.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

LDGCN: An Edge-End Lightweight Dual GCN Based on Single-Channel EEG for Driver Drowsiness Monitoring

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Huang, Jingwei Wang, Chuansheng Huang, Jiayan Fan, Haoyi Xue, Xingsi Zhang, Fuquan Fuzhou University College of Computer and Big Data Fuzhou China Polytechnic University of Catalonia Department of Automatic Control Barcelona Spain Putian University New Engineering Industry College Putian China Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian Fuzhou350118 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Minjiang University College of Computer and Control Engineering Fuzhou China Sichuan Conservatory of Music Digital Media Art Key Laboratory of Sichuan Province Chengdu China Minjiang University Fuzhou Technology Innovation Center of Intelligent Manufacturing information System Fuzhou China Fuzhou China

Driver drowsiness electroencephalogram (EEG) signal monitoring can promptly alert drivers of their drowsiness in edge-end Consumer Electronics (CE), thereby reducing the probability of traffic accidents. Graph convolutional networks (GCNs) have shown significant advancements in processing the non-stationary, time-varying, and non-Euclidean nature of EEG signals. However, the existing single-channel EEG adjacency graph construction process lacks interpretability, which hinders the ability of GCNs to effectively extract adjacency graph features, thus affecting the performance of drowsiness monitoring. To address this issue, we propose an edge-end Lightweight Dual Graph Convolutional Network (LDGCN). Specifically, we are the first to incorporate neurophysiological knowledge to design a Baseline Drowsiness Status Adjacency Graph (BDSAG), which characterizes driver drowsiness status. Additionally, to express more features within limited EEG data, we introduce the Augmented Graph-level Module (AGM). This module captures global and local information at the graph level, ensuring that BDSAG features remain intact while enhancing effective feature expression capability. To further enhance the application of CE, we apply Adaptive Pruning Optimization (APO) to the channels and neurons of LDGCN, which nearly halves the inference latency. Experiments on benchmark datasets demonstrate that LDGCN offers the best trade-off between monitoring performance and hardware resource utilization, outperforming existing state-of-the-art algorithms. © 1975-2011 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Robust Beamforming Based on Covariance Matrix Reconstruction and ADMM

Robust Beamforming Based on Covariance Matrix Reconstruction...

引用

IEEE International Conference on Radar

作者： Pengcheng Gong Zhaobin Wang Kaiyan Xu School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Hubei University of Technology Wuhan China

ISBN: (纸本)9781665468893

Considering at the issue that the performance of the traditional beamforming algorithm will decrease sharply when the disturbance occurs at the disturbed position and the steering vector mismatch occurs, a new robust beamforming method based on covariance matrix reconstruction and Alternating Direction Method of Multipliers (ADMM) is proposed. Firstly, based on the maximum output power criterion of beamformers, an optimization model is designed to solve the optimal steering vector. Then, the covariance matrix is reconstructed by using the defined interference range to widen the nullity and enhance the anti-motion interference ability of the system. Then, for the quadratic inequality constraint problem of the steering vector, this paper uses ADMM to solve the model iteratively, and obtains the specific solution of the steering vector in each iteration. In addition, the complexity of the algorithm is also analyzed. The experimental results show that, compared with the existing beamforming algorithms, the proposed method Widen the width of zero notch in the interference area, improves the anti-interference performance of the beam, and can well correct the mismatched steering vector.

关键词： systematics Array signal processing Interference Radar Resists Convex functions Robustness

来源：评论

学校读者我要写书评

暂无评论

Domain-invariant similarity activation map contrastive learning for retrieval-based long-term visual localization

arXiv

引用

arXiv 2020年

作者： Hu, Hanjiang Wang, Hesheng Liu, Zhe Chen, Weidong Autonomous Robot Lab Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai200240 China The State Key Laboratory of Robotics and System HIT The Department of Computer Science and Technology University of Cambridge United Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous driving. Image retrieval is an efficient and effective technique in image-based localization methods. Due to the drastic variability of environmental conditions, e.g. illumination, seasonal and weather changes, retrieval-based visual localization is severely affected and becomes a challenging problem. In this work, a general architecture is first formulated probabilistically to extract domain-invariant feature through multi-domain image translation. And then a novel gradient-weighted similarity activation mapping loss (Grad-SAM) is incorporated for finer localization with high accuracy. We also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised manner. The final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models without and with Grad-SAM loss. Extensive experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons dataset. The strong generalization ability of our approach is verified on RobotCar dataset using models pre-trained on urban part of CMU-Seasons dataset. Our performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision, especially under the challenging environments with illumination variance, vegetation and night-time images. The code and pretrained models are available on https://***/HanjiangHu/DISAM. Copyright © 2020, The Authors. All rights reserved.

关键词： Image retrieval

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：