检索结果-内蒙古大学图书馆

Image-denoising algorithm based on improved K-singular value decomposition and atom optimization

CAAI Transactions on Intelligence technology 2022年第1期7卷 117-127页

作者： Rui Chen Dong Pu Ying Tong Minghu Wu College of Information&Communication Engineering Nanjing Institute of TechnologyNanjingChina College of Electric Power Engineering Nanjing Institute of TechnologyNanjingChina Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Hubei University of technologyWuhanChina

The traditional K-singular value decomposition(K-SVD)algorithm has poor imagedenoising performance under strong *** image-denoising algorithm is proposed based on improved K-SVD and dictionary atom ***,a correlation coefficient-matching criterion is used to obtain a sparser representation of the image *** dictionary noise atom is detected according to structural complexity and noise intensity and removed to optimize the ***,non-local regularity is incorporated into the denoising model to further improve image-denoising *** of the simulated dictionary recovery problem and application on a transmission line dataset show that the proposed algorithm improves the smoothness of homogeneous regions while retaining details such as texture and edge.

关键词： singular value smoothness

来源：评论

学校读者我要写书评

暂无评论

Interpretable DRL-Based Maneuver Decision of UCAV Dogfight

Interpretable DRL-Based Maneuver Decision of UCAV Dogfight

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Han, Haoran Cheng, Jian Lv, Maolong School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China Air Traffic Control and Navigation College Air Force Engineering University Xi'an710051 China College of Aeronautics Engineering Air Force Engineering University Xi'an710038 China

ISBN: (纸本)9781665410205

This paper proposes a three-layer unmanned combat aerial vehicle (UCAV) dogfight frame where Deep reinforcement learning (DRL) is responsible for high-level maneuver decision. A four-channel low-level control law is firstly constructed, followed by a library containing eight basic flight maneuvers (BFMs). Double deep Q network (DDQN) is applied for BFM selection in UCAV dogfight, where the opponent strategy during the training process is constructed with DT. Our simulation result shows that, the agent can achieve a win rate of 85.75% against the DT strategy, and positive results when facing various unseen opponents. Based on the proposed frame, interpretability of the DRL-based dogfight is significantly improved. The agent performs yo-yo to adjust its turn rate and gain higher maneuverability. Emergence of 'Dive and Chase' behavior also indicates the agent can generate a novel tactic that utilizes the drawback of its opponent. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Reliability Allocation of Cruise Ship Automation System Based on BBWM-AHP 6

Reliability Allocation of Cruise Ship Automation System Base...

引用

6th International Conference on System Reliability and Safety engineering, SRSE 2024

作者： Xiang, Jiaxin Sun, Yongquan Wang, Hao Chen, Hongke Harbin University of Science and Technology School of Measurement and Control Technology and Communication Engineering Harbin China China Institute of Marine Technology & Economy Beijing China Xiamen University Tan Kah Kee College School of Mechanical and Electrical Engineering & Automation Zhangzhou China

ISBN: (纸本)9798350356083

Limited reliability data during the development of cruise ship automation systems often leads to subjective weight allocation. This paper proposes an reliability allocation method based on the Bayesian best-worst method and analytic hierarchy process to address this challenge. By considering the system reliability indices, influencing factors, and units need to be allocated, a hierarchical model is established for reliability allocation based on the analytic hierarchy process. The Bayesian best-worst method compares elements in each layer, generating best and worst matrices based on decision-makers. These matrices determine optimal weights for each layer's elements. The analytic hierarchy process determines relative importance weights among the system reliability index, influencing factors, and units. Consequently, the derived optimal weights are converted into allocation factors, which enable the allocation of reliability for cruise ship automation systems. This fusion-based approach presents a novel and effective method for optimizing reliability allocation during the development stage of complex systems. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Distributed Model Architecture for Cuff-Less Blood Pressure measurement System

引用

SN Computer Science 2022年第6期3卷 503页

作者： Dave, Tejal Joshi, Maulin Pandya, Utpal Department of Instrumentation and Control Sarvajanik College of Engineering and Technology Sarvajanik University Surat India Department of Electronics and Communication Sarvajanik College of Engineering and Technology Sarvajanik University Surat India

Continuous monitoring of blood pressure (BP) can control hypertension and cardiac diseases prevailing in many people due to luxurious lifestyle. Blood pressure measurement using cuff-based technique provides intermittent measurement and inconvenient for long-term monitoring. This work is focused on estimation of continuous blood pressure from electrocardiogram (ECG) and photoplethysmogram (PPG). The distributed model architecture is proposed to estimate blood pressure from time domain features of ECG and PPG to overcome problems with single model-based approach. The proposed work uses support vector regression and back propagation neural network for training distributed models. During testing phase, extracted features are first passed through trained pre-classifier to divert the signal to one of the trained distributed models that carries out blood pressure estimation. The proposed work is tested on 193 record segments of Multi-parameter Intelligent Monitoring in Intensive Care (MIMIC) database and also on wireless data captured from 87 subjects using prototype device. According to the British Hypertension Society (BHS) standard, the proposed method achieves grade A in the estimation of systolic and diastolic pressure for wireless data. For MIMIC database, proposed model achieves grade B for systolic, whereas grade A for diastolic pressure estimation. The values of mean error and standard deviation by proposed method are within limits of Association for the Advancement of Medical Instrumentation (AAMI) standards for wireless as well as MIMIC data. The results show improvement in the accuracy of blood pressure estimation compared to similar work and indicate high acceptability according to BHS and AAMI standards. The proposed work is helpful in wireless monitoring of patients to track the physiological conditions without interrupting their routine activities. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cuff-less blood pressure monitoring Electrocardiogram (ECG) Photoplehysmogram (PPG) Support vector machine classifier Support vector regression (SVR)

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable antenna beam using U-Shaped slot patch for wireless networks

引用

Materials Today: Proceedings 2022年 58卷 547-551页

作者： Suriyan, Kannadhasan Ramalingam, Nagarajan Venusamy, Kanagaraj Department of Electronics and Communication Engineering Cheran College of Engineering Tamilnadu India Department of Electrical and Electronics Engineering Gnanamani College of Technology Tamilnadu India Control Systems Instructor Department of Engineering University of Technology and Applied Sciences-AI Mussanah AI Muladdha Oman

A compact U-Shaped antenna was proposed in this paper. The antenna is designed with dimension of 30*44*1.8 mm. The proposed antenna is used to improvement the ground stub. The antenna works in the various band of Wi-Fi, Wi-Max, WLAN, Wireless communication and Satellite communication applications. The proposed structure having FR4 dielectric substrate with 4.2 relative permittivity and the loss tangent of 0.0025. The gain of the proposed antenna is 5.82 dB and 6.82 dB in the lower band and upper band of frequencies. The U-Shaped structure antenna operating at various bands 1.8 GHz to 2.5 GHz and 3.5 GHz to 4.5 GHz for wireless applications. The VSWR of the proposed structure is 1.4 and 1.8 respectively. The bandwidth is used to operate the U-Shaped structure is 900/1800 MHz. The reflection coefficient of the proposed structure is observed for the range of −7.08 dB and −14.00 dB. The performance parameters of the proposed structure such as good return loss, high gain, high bandwidth and good radiation pattern in nature. © 2022

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Cross Scene Classification Combined Domain Adaptation with XGBoost

Hyperspectral Image Cross Scene Classification Combined Doma...

引用

2024 International Conference on measurement, communication, and Virtual Reality, MCVR 2024

作者： Liu, Chengyang Wu, Haibin Li, Jiarong Liu, Xinyu Yan, Siqi Wang, Aili Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application College of Measurement and Control Technology and Communication Engineering Harbin University of Science and Technology Harbin150080 China School of Electronics and Information Engineering Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9781510691773

To address the issues of domain discrepancies and limited labeled samples in hyperspectral image classification of cross scene, this paper proposes an ensemble learning framework that integrates eXtreme Gradient Boosting (XGBoost) with confidence domain adaptation strategies to improve classification performance. First, the Houston dataset from different scenes is input separately into a deep embedding model. The hyperspectral images are embedded into a low-dimensional space, ensuring that similar spectra are represented more closely in this space, thereby capturing the intrinsic structure and distribution of the hyperspectral image dataset. Subsequently, these samples are mapped into a discriminator model, where domain adaptation techniques are employed to reduce differences in feature distributions across different scenes. Additionally, confidence-based learning is used to identify and remove noisy samples in the Houston dataset, thereby enhancing the alignment of feature distributions among various scenes. Finally, through ensemble learning, a weighted voting strategy is employed to combine multiple base classifiers into a strong classification model. This approach better captures the complex features within the data, thereby reducing the bias of individual classifiers and enhancing the overall generalization ability and robustness of the model. Experimental results on the Houston dataset demonstrate that the proposed method outperforms popular domain adaptation learning models and traditional methods in terms of classification accuracy and robustness, showcasing its potential and advantages in practical applications. This result confirms the effectiveness of combining XGBoost and confidence domain adaptation strategies in handling hyperspectral image classification. © 2025 SPIE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Optimization Research on Pedestrian Multi Objects Tracking Model Based on TBD Strategy

Optimization Research on Pedestrian Multi Objects Tracking M...

引用

2023 International Conference on Algorithm, Imaging Processing, and Machine Vision, AIPMV 2023

作者： Wang, Shi Liu, XiangJu Liu, XinShu Chen, JiaHui Wang, XiaoHong Qilu Institute of Technology College of Computer and Communication Engineering Shandong Jinan250200 China College of Artificial Intelligence and Software Liaoning Petrochemical University Liaoning Fushun113001 China College of Information and Control Engineering Liaoning Petrochemical University Liaoning Fushun113001 China

ISBN: (纸本)9781510672444

The main task of pedestrian multi objects tracking technology is to continuously track multiple pedestrian objects simultaneously in video sequences and maintain their unique ID numbers. However, current pedestrian multi objects tracking models still have many problems, such as false detection, missed detection, and frequent ID number switching when pedestrians are obstructed or have overly similar appearances, ultimately leading to tracking failure. Therefore, this paper proposes a pedestrian multi objects tracking model based on TBD strategy. It mainly consists of two parts: pedestrian detector and pedestrian tracker. In terms of pedestrian detectors, this paper uses ES-YOLO pedestrian detectors. In terms of pedestrian trackers, this paper draws on the Omni-scale feature learning module in OSNet to redesign the StrongSORT pedestrian appearance feature extraction network, and ultimately obtains the StrongSORT pedestrian tracker based on omni-scale feature fusion, further enhancing its pedestrian feature extraction ability. In terms of experimental results. The experimental results of the pedestrian multi objects tracking model based on the TBD strategy in this paper on the MOT16 dataset show that the proposed pedestrian multi-objective tracking model can effectively improve the accuracy of pedestrian multi objects tracking and reduce the problem of frequent pedestrian ID number switching. © 2024 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Reverse Time Migration of Ultra-Wideband Ground-Penetrating Radar Based on Multiple Time-Gating Algorithm

Reverse Time Migration of Ultra-Wideband Ground-Penetrating ...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Wu, Junjie Li, Haixiao Zhou, Yuanguo Cao, Le Wang, Yan Xi'an University of Science and Technology College of Communication and Information Engineering Xi'an China Xi'an University of Science and Technology College of Electrical and Control Engineering Xi'an China Graduate School of Chinese Aeronautical Establishment Yangzhou China Aviation Key Laboratory of Science and Technology on Electromagnetic Environment Effects Shenyang China National Key Laboratory of Electromagnetic Information Control and Effects Shenyang China

ISBN: (纸本)9798350355581

To address the issue of clutter interference in ground-penetrating radar (GPR) imaging using a VNA (Vector Network Analyzer), this paper improves the traditional reverse time migration (RTM) technique for ultra-wideband GPR imaging. The improved method retains the effective signals in the detection wavefield as the valid imaging area and suppresses signals in non-valid areas. Due to variations in the distance between the transmitting and receiving antennas and the number of anomalies in the experiment, the traditional time window cross-correlation is not ideal for this scenario. The improved method automatically applies reasonable windowing to each data channel, avoiding the simultaneous enhancement of clutter interference and effective signals through direct stacking, and preventing the filtering out of effective signals. Experimental results demonstrate that this method, when applied to real measured data and compared with the traditional cross-correlation RTM method, shows advantages in more accurately locating anomalous areas and suppressing clutter interference. This validates that the Multiple Time-Gating Reverse Time Migration (MTG-RTM) method offers better localization and higher imaging accuracy in practical engineering applications. © 2024 IEEE.

关键词： Receiving antennas

来源：评论

学校读者我要写书评

暂无评论

Reflection signal classification of deep-sea surface sediment based on 1DCNN-DLSTM networks

Reflection signal classification of deep-sea surface sedimen...

引用

2023 International Workshop on Signal Processing and Machine Learning, WSPML 2023

作者： Qu, Zhiguo Zhong, Zhi Cao, Xinghui Shan, Mingguang Xie, Yongqiang College of Information and Communication Engineering Harbin Engineering University Harbin China Laboratory of Survey Control Xinjiang Institute of Technology Akesu China Institute of Systems Engineering AMS PLA Beijing China

ISBN: (纸本)9781510671928

Classification of reflected signals from surface sediments can improve our understanding of the properties of these sediments. In this paper, we propose a method for classifying reflection signals using deep learning techniques. The method uses a pulse compression algorithm to convert reflection signals into reflection compressed data, and then uses a one-Dimensional Convolutional Neural Network - Double Long Short-Term Memory (1DCNN-DLSTM) network to classify these data. The advantage of this method is that the pulse compression algorithm can improve the resolution of the stratigraphic reflection signal, thus better capturing the details of the signal. Meanwhile, 1DCNN can effectively extract the spatial features of reflection compression signals and capture the differences between different sediment types. DLSTM, on the other hand, can capture the temporal dynamic features of the signals, which is very advantageous for modeling temporal information. By fusing these two network structures, it is possible to categorize deep-sea surface sediments in a more comprehensive way. To verify the feasibility of the method, we conducted experiments using reflection data from surface sediments on the South China Sea continental slope. The experimental results show that the method is feasible in classifying the reflection signals from deep-sea surface sediments. We obtain high classification accuracy by training and testing different types of reflection compression data. This indicates that the method can effectively distinguish different types of deep-sea surface sediments, which helps us to better understand the deep-sea environment and related geological processes. © 2023 SPIE. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Study the influence of using guide vanes blades on the performance of cross-flow wind turbine

引用

Applied Nanoscience (Switzerland) 2023年第2期13卷 1115-1124页

作者： Yahya, Waled Ziming, Kou Juan, Wu Al-Nehari, Mohammed Tengyu, Li Qichao, Ren Alhayani, Bilal College of Mechanical and Vehicle Engineering Taiyuan of University of Technology Taiyuan 030024 China Shanxi Province Engineering Technology Research Center for Mine Fluid Control Taiyuan 030024 China Yildiz Technical University Electronics and communication department Istanbul Turkey

A cross-flow wind turbine has a high torque coefficient at a low tip speed ratio;therefore, it is a good candidate for a self-starting turbine. This study aims to investigate the best configuration between guide vanes and cross-flow vertical axis wind turbine. The experiment test was carried out to determine the turbine with the highest power coefficient. The cross-flow turbine has 14, 18, and 22 blades with using 6,10 and 14 blades of guide vane (GV) was developed in this study, employing 15°, 25°, 35°, 45°, 55°, 65°, and 75° of tilt angles in fifth different wind speed conditions 4 m/s, 6 m/s, 7.5 m/s, 9.20 m/s, and 11 m/s. The turbine has 22 blades with 14 GV blades at 55° of tilt angle blades producing more remarkable turbine performance improvement than other blades. The highest power coefficient (CP) of cross-flow using 14 GV blades at 55° was 0.0162 at 0.289 TSR, which increased around 59% of the turbine's performance using GV. © 2021, King Abdulaziz City for Science and technology.

关键词： Cross-flow wind turbines Guide vanes (GV) Power coefficient (CP) Tilt angles

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：