检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Elmelegy, Mohamed Ali Elhosseini, Mostafa A. Ali, Hesham Arafat Haikal, Amira Y. Instrument maintenance support engineer DLNG Damietta LNG Egypt College of Computer Science and Engineering Taibah University Yanbu Saudi Arabia Department of Computers and Control Systems Engineering Faculty of Engineering Mansoura University Mansoura Egypt

The incidence of surge within axial compressors profoundly influences the efficacy and reliability of aero-engines. Conventional methodologies in engine design have predominantly concentrated on the precise and efficient forecasting of critical characteristics during such occurrences. This paper presents a novel approach for predicting the surge phenomenon in axial compressors. Surge is a major issue in the operation of axial compressors, causing reduced performance, increased wear and tear, and in some cases, complete machine failure. The proposed approach utilizes a neural network model based on the compressor's design data to forecast the behavior of the compressor's working map under off-design conditions. The model is verified using real data collected over five years during compressor operation, including the opening angle of the Inlet Guided Van (IGV), an important parameter often ignored or assumed to be fixed in previous studies. The results show that the neural network-based approach effectively predicts the compressor's behavior under different operating conditions, providing valuable insights into the onset of surge and offering a real-time surge prediction and control tool. The ability to predict the compressor's working map enables optimizing its performance and controlling instability. This model was validated by comparing its predictions with real operating conditions observed over five years across various compressor operating modes. As a result, this predictive model enables the safe operation of axial compressors by mitigating instability risks during operation. This study's findings highlight the model's effectiveness, as evidenced by the minimal error observed between the predicted and actual data collected across various compressor operating modes. The model exhibits a strong performance, characterized by a high regression factor of 0.92667 and a low mean squared error of 3.04465 x 10^-3. These numerical values underscore the reliability and pr

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Multiple Surrogate-Assisted Hybrid Evolutionary Feature Selection Algorithm

SSRN

引用

SSRN 2024年

作者： Zhang, Wan-Qiu Hu, Ying Zhang, Yong Zheng, Zi-Wang Peng, Chao Song, Xianfang Gong, Dunwei School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China School of Computer and Information Anhui Normal University Wuhu241000 China College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao266100 China

Feature selection (FS) is an important data processing technology. However, existing FS methods based on evolutionary computation have still the problems of "curse of dimensionality" and high computational cost, with the increase of the number of feature and/or the size of instance. In view of this, the paper proposes a multiple surrogate-assisted hybrid evolutionary feature selection (MSa-HEFS). Two kinds of surrogates (i.e., objective regression surrogate and sample surrogate) and two kinds of FS methods (i.e., filter and wrapper) are integrated into MSa-HEFS to improve its performance. Firstly, an ensemble filter FS method is designed to reduce the search space of subsequent wrapper evolutionary FS method. Secondly, in the proposed evolutionary FS method, a dual-surrogate-assisted hierarchical individual evaluation mechanism is developed to reduce the evaluation cost on feature subsets, an online management and update strategy is used to adaptively choose appropriate surrogates for individuals. The proposed algorithm is applied to 12 typical datasets and compared with 4 state-of-the-art FS algorithms. Experimental results show that MSa-HEFS can obtain good feature subsets at the smallest computational cost on all datasets. © 2024, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Active Noise control with Tap-Decomposed Robust Volterra

SSRN

引用

SSRN 2023年

作者： Yin, Kai-Li Zhao, Hao-Ran Pu, Yi-Fei Lu, Lu College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao266520 China College of Computer Science Sichuan University Chengdu610065 China School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China College of Electronics and Information Engineering Sichuan University Chengdu610065 China

The Volterra filter is proven to be a structurally simple method for nonlinear active noise control (NLANC). However, its wide application is deeply constrained by computational complexity. This paper proposes a tapdecomposed Volterra filter, in which a long-tap Volterra filter is approximated as multiple short-tap filters by the nearest Kronecker decomposition. Since the number of taps of decomposed filters is much less than that of the original counterpart, the proposed method greatly reduces the implementation cost of the Volterra filter. Moreover, for impulsive noise sources in NLANC, decomposed filters are updated using the maximum correntropy criterion derived from information theory. Simulation experiments with different noise source types highlight the noise control performance of the proposed approach. © 2023, The Authors. All rights reserved.

关键词： Adaptive filters

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

arXiv

引用

arXiv 2024年

作者： Huang, Jingwei Wang, Chuansheng Huang, Jiayan Fan, Haoyi Grau, Antoni Zhang, Fuquan The College of Computer and Big Data Fuzhou University Fuzhou China The Department of Automatic Control Polytechnic University of Catalonia Barcelona Spain The New Engineering Industry College Putian University Putian China School of Computer and Artificial Intelligence Zhengzhou University China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Control Engineering Minjiang University Fuzhou China Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu China Fuzhou Technology Innovation Center of Intelligent Manufacturing information System Minjiang University Fuzhou China Fujian Polytechnic Normal University Fujian Province University Fuzhou China

Driver drowsiness electroencephalography (EEG) signal monitoring can timely alert drivers of their drowsiness status, 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. Furthermore, to deploy our method on the fourth-generation Raspberry Pi, we utilize Adaptive Pruning Optimization (APO) on both channels and neurons, reducing inference latency by almost half. Experiments on benchmark datasets demonstrate that LDGCN offers the best trade-off between monitoring performance and hardware resource utilization compared to existing state-of-the-art algorithms. All our source code can be found at https://***/BryantDom/Driver-Drowsiness-Monitoring. Copyright © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Testing and Development of a Multi-Object Tracker Based on Deep Learning Techniques 1st

Testing and Development of a Multi-Object Tracker Based on D...

引用

1st International Conference on Machine Intelligence for Research and Innovations, MAiTRI 2023

作者： Rajput, Shaurya Verma, Sourabh Verma, Om Prakash Gupta, Himanshu Sharma, Tarun Ateya, Abdelhamied A. Centre for Artificial Intelligence Dr. B.R. Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar India Department of Instrumentation and Control Engineering Dr. B.R. Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar India Department of Computer Science-Internet of Things ABES Institute of Technology Ghaziabad201009 India University Meerut India Department of Electronics and Communications Engineering Zagazig University Sharqia Zagazig44519 Egypt EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia

ISBN: (纸本)9789819981342

In today’s scenario, computer vision is one of the fundamental research areas of artificial intelligence including object detection and object tracking which are the upcoming trends. In the present work, the TransTrack model has been reimplemented which includes ResNet50 as a backbone network. Further, to improve the overall performance of the TransTrack model, some recently developed backbones such as ResNet152 and SwinT have been incorporated. Moreover, to test the optimum training of the existing model, it has been retrained for higher epochs (such as 160 epochs). However, the accuracy of the existing tracker has improved significantly as the number of epochs increases but, at the same time, it increases the computational complexity. On the contrary, when the existing tracker (yields 68.4% accuracy with ResNet50) is incorporated with ResNet152 and SwinT, the performance has significantly improved (71% for ResNet152 and 71.6% for SwinT) by 1.7% and 2.1%, respectively. The mentioned analysis is enough to prove that the incorporation of a more efficient backbone has the potential to improve the performance of trackers. In the future, the newly introduced backbone may open the window to improve the performance of multi-object tracking (MOT). © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

LSU-NET: LIGHTWEIGHT AUTOMATIC ORGANS SEGMENTATION NETWORK FOR MEDICAL IMAGES

arXiv

引用

arXiv 2025年

作者： Ding, Yujie Teng, Shenghua Li, Zuoyong Chen, Xiao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao266590 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou350121 China

UNet and its variants have widespread applications in medical image segmentation. However, the substantial number of parameters and computational complexity of these models make them less suitable for use in clinical settings with limited computational resources. To address this limitation, we propose a novel Lightweight Shift U-Net (LSU-Net). We integrate the Light Conv Block and the Tokenized Shift Block in a lightweight manner, combining them with a dynamic weight multi-loss design for efficient dynamic weight allocation. The Light Conv Block effectively captures features with a low parameter count by combining standard convolutions with depthwise separable convolutions. The Tokenized Shift Block optimizes feature representation by shifting and capturing deep features through a combination of the Spatial Shift Block and depthwise separable convolutions. Dynamic adjustment of the loss weights at each layer approaches the optimal solution and enhances training stability. We validated LSU-Net on the UWMGI and MSD Colon datasets, and experimental results demonstrate that LSU-Net outperforms most state-of-the-art segmentation architectures. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heat Transfer in Smart Buildings using Internet of Things based Artificial Intelligence 3

Prediction of Heat Transfer in Smart Buildings using Interne...

引用

3rd International Conference on Electronics and Sustainable Communication Systems, ICESC 2022

作者： Rehman, TasneemBano Madiajagan, M. Ramya, D. Saratha, M. Mohan Krishna, P.B. Kumar, Prashant Sage University Department of Computer Science and Engineering Madhya Pradesh Bhopal India Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Vellore India Sathyabama Institute of Science and Technology Department of Eee Tamil Nadu Chennai India M.Kumarasamy College of Engineering Department of Mca Tamil Nadu Karur India National Institute of Technology Department of Process Control Telangana Warangal India Lovely Professional University Department of Chemical Engineering Punjab India

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479714

With rapid growth and a higher standard of living, the demand for usable energy has increased tremendously over the last few decades, with the construction industry being one of the most notable examples. The energy efficiency of a building is influenced by a variety of factors, including the weather in the area, the structure characteristics, and how people use electricity. These algorithms can be used to generate a prediction model for smart building indoor temperature forecasting using the Internet of Things and several commonly used artificial intelligence algorithms, which can then be used to generate a prediction model for smart building outdoor temperature forecasting. It was necessary to employ freely accessible software tools in order to make geometric and sensory data available in a virtual reality application and to build the PMV and PPD indices. On a low-cost edge computing device, semi-automatic analysis of streaming thermal images from a non-intrusive sensor was performed in order to offer near real-time Mean Radiant Temperature (MRT)estimations. An experimental space that had been mechanically preconditioned was filled with a dynamic temperature environment, and a prototype of the system was employed in a series of trials. Results show that the data backs up the fact that the system output and the heat sensations felt under different settings are consistent. © 2022 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Robust Maximum Power Point Tracking in PV Generation System: A Hybrid ANN-Backstepping Approach With PSO-GA Optimization

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Hussan, Umair Waheed, Ahsan Bilal, Hazrat Wang, Huaizhi Hassan, Mudasser Ullah, Inam Peng, Jianchun Hosseinzadeh, Mehdi Shenzhen University College of Mechatronics and the Control Engineering Shenzhen518060 China The University of Faisalabad Department of Electrical Engineering Faisalabad38000 Pakistan University of Tasmania School of Engineering HobartTAS7005 Australia Gachon University Department of Computer Engineering Seongnam13120 Korea Republic of Macquarie University School of Computing Sydney Australia Duy Tan University School of Computer Science Da Nang Viet Nam

The growing diversity of consumer loads emphasizes the need for efficient operation of photovoltaic generation systems (PVGSs). This paper presents a novel control framework for maximum power point tracking (MPPT) in PVGSs, designed to enhance efficiency, robustness, and adaptability under dynamic environmental conditions. The proposed methodology integrates optimized Artificial Neural Network (ANN) with nonlinear backstepping controller. Hybrid particle swarm optimization (PSO) and genetic algorithm (GA) approach is used to optimize ANN, which leverages the global search capabilities of PSO and the local refinement strengths of GA to optimize the ANN’s weights and biases, ensuring accurate prediction of the PV reference voltage that is critical for MPPT. Additionally, the nonlinear backstepping controller ensures system stability and precise tracking of the predicted reference voltage by recursively constructing Lyapunov functions to guarantee asymptotic stability. The effectiveness of this control framework is evaluated through MATLAB/Simulink and validated with hardware testing. It is observed from simulation and hardware testing results, compared to existing ANN and conventional techniques, the proposed approach yielded significant improvements by achieving root mean square error of 0.103%, tracking accuracy of 99. 8%, and reduction of power loss to 0. 2%. The proposed control framework significantly enhances MPPT robustness and efficiency in dynamic environments and enables higher integration of renewable energy. This advancement supports scalable, resilient PV systems critical for sustainable energy transitions. © 1975-2011 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory ...

引用

computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Xiuen Wu Tao Wang Yuanzheng Cai Lingyu Liang George Papageorgiou Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Data Science Fuzhou University Fuzhou China School of Electronic and Information Engineering South China University of Technology Guangzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians’ future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method.

关键词： Deep learning Pedestrians Computational modeling Predictive models Prediction algorithms Vectors Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Measurement of atmospheric nanoparticles:Bridging the gap between gas-phase molecules and larger particles

引用

Journal of Environmental Sciences 2023年第1期123卷 183-202页

作者： Chao Peng Chenjuan Deng Ting Lei Jun Zheng Jun Zhao Dongbin Wang Zhijun Wu Lin Wang Yan Chen Mingyuan Liu Jingkun Jiang Anpei Ye Maofa Ge Weigang Wang State Key Laboratory for Structural Chemistry of Unstable and Stable Species Beijing National Laboratory for Molecular Sciences(BNLMS)CAS Research/Education Center for Excellence in Molecular SciencesInstitute of ChemistryChinese Academy of SciencesBeijing 100190China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China School of Environment Science and Engineering Nanjing University of Information Science&TechnologyNanjing 210044China School of Atmospheric Sciences Sun Yat-sen UniversityZhuhaiGuangdong 519082China State Key Joint Laboratory of Environmental Simulation and Pollution Control College of Environmental Sciences and EngineeringPeking UniversityBeijing 100871China Shanghai Key Laboratory of Atmospheric Particle Pollution and Prevention(LAP3) Department of Environmental Science&EngineeringFudan UniversityShanghai 200433China Key Laboratory for the Physics and Chemistry of Nanodevices Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China University of Chinese Academy of Sciences Beijing 100049China

Atmospheric nanoparticles are crucial components contributing to fine particulate matter(PM_(2.5)),and therefore have significant effects on visibility,climate,and human *** to the unique role of atmospheric nanoparticles during the evolution process from gas-phase molecules to larger particles,a number of sophisticated experimental techniques have been developed and employed for online monitoring and characterization of the physical and chemical properties of atmospheric nanoparticles,helping us to better understand the formation and growth of new *** this paper,we firstly review these state-of-the-art techniques for investigating the formation and growth of atmospheric nanoparticles(e.g.,the gas-phase precursor species,molecular clusters,physicochemical properties,and chemical composition).Secondly,we present findings from recent field studies on the formation and growth of atmospheric nanoparticles,utilizing several advanced ***-more,perspectives are proposed for technique development and improvements in measuring atmospheric nanoparticles.

关键词： Nanoparticle Measurement techniques Size distributions Physical properties Chemical composition

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：