检索结果-内蒙古大学图书馆

MATCNN: Infrared and Visible Image Fusion Method Based on Multiscale CNN With Attention Transformer

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Liu, Jingjing Zhang, Li Zeng, Xiaoyang Liu, Wanquan Zhang, Jianhua Shanghai Univ Sch Microelect Shanghai Key Lab Chips & Syst Intelligent Connecte Shanghai 200444 Peoples R China Fudan Univ State Key Lab Integrated Chips & Syst Shanghai 201203 Peoples R China Fudan Univ State Key Lab Integrated Chipsand Syst Shanghai 201203 Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Shenzhen 510006 Peoples R China

While attention-based approaches have shown considerable progress in enhancing image fusion and addressing the challenges posed by long-range feature dependencies, their efficacy in capturing local features is compromised by the lack of diverse receptive field extraction techniques. To overcome the shortcomings of existing fusion methods in extracting multiscale local features and preserving global features, this article proposes a novel cross-modal image fusion approach based on a multiscale convolutional neural network with an attention Transformer (MATCNN). MATCNN utilizes the multiscale fusion module (MSFM) to extract local features at different scales and employs the global feature extraction module (GFEM) to extract global features. Combining the two reduces the loss of detail features and improves the ability of global feature representation. Simultaneously, an information mask is used to label pertinent details within the images, aiming to enhance the proportion of preserving significant information in infrared images and background textures in visible images in fused images. Subsequently, a novel optimization algorithm is developed, leveraging the mask to guide feature extraction through the integration of content, structural similarity index (SSIM) measurement, and global feature loss. Quantitative and qualitative evaluations are conducted across various datasets, revealing that MATCNN effectively highlights infrared salient targets, preserves additional details in visible images, and achieves better fusion results for cross-modal images. The code of MATCNN will be available at https://***/zhang3849/***.

关键词： Global feature extraction module (GFEM) image fusion multiscale convolutional neural network with atten-tion transformer (MATCNN) multiscale convolutional neural network with atten-tion transformer (MATCNN) multiscale fusion module (MSFM) optimization algorithm optimization algorithm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Modified U-Shaped Transfer Function: Applied to Classify Parkinson'S Disease

引用

COMPUTATIONAL INTELLIGENCE 2025年第2期41卷

作者： Sharma, Suvita Rani Singh, Birmohan Kaur, Manpreet St Longowal Inst Engn & Technol Dept Comp Sci & Engn Sangrur Punjab India St Longowal Inst Engn & Technol Dept Elect & Instrumentat Engn Sangrur Punjab India

Transfer functions have a very important role in metaheuristic optimization-based feature selection algorithms as these functions map the continuous search space into binary space. The U-shaped transfer function (UTF) is one of the transfer functions used to solve the problem of feature selection. However, the UTF requires the selection of parametric values, which can vary for different types of data. To address this issue, an approach to select the parameters of the UTF has been proposed based on a time-varying adaption method, resulting in the modified U-shaped transfer function (MUTF). Furthermore, a methodology has been proposed to enhance feature selection and classification for Parkinson's disease by utilizing z-score normalization in conjunction with a modified U-shaped transfer function and the binary self-adaptive bald eagle search (MUTF-SABES) optimization algorithm. The z-score normalization has been used to mitigate issues caused by outliers. Also, the performance of the k nearest neighbor classifier is improved by selecting an optimal parameter value using the proposed MUTF-SABES algorithm. The effectiveness of the proposed methodology is validated on seven different Parkinson's disease datasets and compared with five state-of-the-art optimization algorithms: Salp Swarm algorithm, Harris Hawks optimization, equilibrium optimizer, aquilla optimizer, and Honey Badger algorithm, to evaluate its performance superiority. The results achieved using the proposed approach have been superior or analogous to the erstwhile algorithms for performance comparability. Friedman's mean rank test is used to check the statistical significance of the propounded approach. The lowest Friedman's mean rank value obtained using the proposed approach indicates that the proposed approach has the potential to become an alternative to other well-known strategies.

关键词： classification feature selection normalization optimization algorithm Parkinson's disease

来源：评论

学校读者我要写书评

暂无评论

Retrieval and Analysis of Sea Surface Salinity in Coastal Waters Using Satellite Data Based on IGWO-BPNN: A Case Study of Qinzhou Bay, Guangxi, China

引用

WATER 2025年第1期17卷 94-94页

作者： Zhong, Maoyuan Yao, Huanmei Liu, Yin Qiao, Junchao Chen, Meijun Zhong, Weiping Guangxi Univ Sch Resources Environm & Mat Nanning 530004 Peoples R China Guangxi Univ Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Environm Protect Nanning 530004 Peoples R China Marine Environm Monitoring Ctr Guangxi Zhuang Auto Marine Ecol Environm Guangxi Field Sci Observat Re Beihai 536000 Peoples R China

This study proposes a high-precision method for retrieving sea surface salinity (SSS) using GF-1 satellite imagery, focusing on Qinzhou Bay along the Guangxi coast. The analysis identified the spectral index B3xB4/(B1xB2) as having the strongest correlation with SSS (R = 0.929). To enhance the performance of the Back Propagation Neural Network (BPNN) model, optimization algorithms including Improved Grey Wolf optimization (IGWO), Particle Swarm optimization (PSO), and White Shark optimization (WSO) were applied. Comparative results show that IGWO significantly optimized network weights and thresholds, yielding superior test performance metrics (MAE = 0.906 psu, MAPE = 4.124%, RMSE = 1.067 psu, and R2 = 0.953), demonstrating strong generalization ability. Validation using third-party data indicated accuracy reductions of 10.9% and 8.6% in Qinzhou Bay and Tieshan Port, respectively, highlighting the model's robustness and broad applicability. SSS retrieval results for Qinzhou Bay in 2023 revealed significant spatial and seasonal variations: the Inner Bay exhibited lower salinity (average 14 psu) from April to September due to freshwater inflows, while salinity increased (average 22 psu) from November to February. The Outer Bay, influenced by its connection to the South China Sea, maintained consistently high salinity levels (25-30 psu) year-round. Additionally, different models showed varying levels of effectiveness in Qinzhou Bay's complex salinity environment;the IGWO-BPNN model, with its dynamic weight adjustment mechanism, demonstrated superior adaptability in areas with high salinity variability, outperforming other models. These findings suggest that the IGWO-BPNN model provides high accuracy and stability, supporting real-time, precise monitoring in Qinzhou Bay and similar coastal waters, thereby offering robust support for water quality management and marine conservation.

关键词： Qinzhou Bay sea surface salinity BPNN GF-1 satellite optimization algorithm Improved Grey Wolf optimization

来源：评论

学校读者我要写书评

暂无评论

A Reconstruction Method for Weak Magnetic Pipeline Inspection Signals Based on Adaptive Multiscale Signal Reconstruction

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Liu, Bin Liu, Yuze Lian, Zheng Wu, Zihan He, Luyao Yang, Lijian Shenyang Univ Technol Sch Informat Sci & Engn Shenyang 110870 Peoples R China

The weak magnetic pipeline stress detection technology is at the forefront of international pipeline safety maintenance. However, the noise embedded in weak magnetic stress detection signals significantly impacts detection accuracy. To address this issue, this article proposes a reconstruction method for weak magnetic inspection data that integrate adaptive parameter optimization and multiscale signal decomposition (MSD), aiming to enhance the detection accuracy of weak magnetic stress inspection systems. First, the method combines intrinsic computing expressive empirical mode decomposition with adaptive noise (ICEEMDAN) with MSD technology to handle residual complex noise. Second, fuzzy entropy (FE) is employed for the selection of intrinsic mode functions (IMFs) to tackle the nonstationarity of weak magnetic signals. Finally, an improved sparrow search algorithm (ISSA) is introduced to dynamically adjust key parameter configurations, effectively resolving tuning difficulties and significantly improving signal reconstruction performance. The method's performance is evaluated through the reconstruction of synthetic signals and weak magnetic simulation signals of external pipeline defects, as well as reconstruction experiments on weak excitation signals collected from Q235 pipelines. The results indicate that the method, while ensuring the highest signal-to-noise ratio (SNR), significantly reduces the total variation (TV) from 20887.5 to 1158.6 and reduces the peak distortion (Pd) factor to approximately 57, improving by about 27.62% compared to the second-best method. Furthermore, the inversion of pipeline stress distribution demonstrates that this method can effectively improve model accuracy and robustness.

关键词： Improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) optimization algorithm signal reconstruction stress distribution inversion weak magnetic signals Improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) optimization algorithm signal reconstruction stress distribution inversion weak magnetic signals

来源：评论

学校读者我要写书评

暂无评论

Design, fabrication and measurement of Terahertz flexible broadband beam splitter

引用

OPTICS AND LASER TECHNOLOGY 2025年 184卷

作者： Teng, Yan Li, Chun Xie, Guoao Huang, Zhengwei Yao, Haiyun Zhang, Yonggang Liang, Lanju Ren, Yuan Jiang, Ling Nanjing Forestry Univ Coll Informat Sci & Technol Nanjing 210037 Peoples R China Chinese Acad Sci Purple Mt Observ Nanjing 210033 Peoples R China Zaozhuang Univ Zaozhuang 277160 Peoples R China Anhui Univ Sci & Technol Sch Elect & Informat Engn Huainan 232001 Anhui Peoples R China

Beam splitters are an important part of optical systems and have a wide range of applications in wireless communications and target detection. In this study, bendable structures based on subwavelength nanostructured metasurfaces with an arbitrary number of beams are constructed. To achieve multiple beams, the phase distribution of a multi-beam splitting metasurface in the 2D direction is calculated directly by an optimized phase recovery algorithm. The cells exhibiting high polarization conversion efficiency are arranged periodically according to the discrete phase. By full-wave simulation, the beam-splitting metasurfaces realize 2 x 2, 4 x 4, and 6 x 6 main beams with high power efficiency and homogeneity from 0.2 THz to 0.37 THz. In addition, the effect of metasurface bending on beam splitting is further investigated using flexible materials that can be fitted into more devices. It is demonstrated that the performance remains optimal at curvatures of less than 1/10,000 mu m-1. Due to the 2D structure, this beam splitter allows electromagnetic waves to be incident at an angle of more than 40 degrees for more demanding applications. Finally, a flexible beam splitter fabrication method based on commercially available polyimide films is proposed and measured, and the results are in agreement with the simulation results. Compared to other beam splitters, the flexible metasurface is fabricated in this paper to reduce the cost, is suitable for large-scale production, and is easy to integrate. These devices can be used in THz optical systems, as well as in mobile applications.

关键词： Multi-Beam Splitter Terahertz optimization algorithm Phase Recovery Flexible Material

来源：评论

学校读者我要写书评

暂无评论

Efficient Automatic Design of IGBT Structural Parameters Using Differential Evolution and Machine Learning Model

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2025年第3期44卷 1059-1069页

作者： Yao, Qing Chen, Jing Yang, Kemeng Yao, Jiafei Zhang, Jun Dai, Yuxuan Tang, Weihua Zhang, Bo Guo, Yufeng Nanjing Univ Posts & Telecommun Coll Integrated Circuit Sci & Engn Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Natl & Local Joint Engn Lab RF Integrat & Micropac Nanjing 210023 Peoples R China Univ Elect Sci & Technol China State Key Lab Elect Thin Films & Integrated Device Chengdu 610054 Peoples R China

Insulated gate bipolar transistors (IGBTs) are the key component in power electronics, and the intricate relationship between their performance and structural parameters poses a formidable challenge in the design process. This article proposes an automatic optimal design method for IGBT structural parameters to leverage the pretrained machine learning (ML) model to efficiently predict the initial IGBT device's performance, followed by utilizing the differential evolution (DE) algorithm to automatically adjust structural parameters based on the disparity between predicted and expected device performance until the expected performance is achieved. The method is validated in the design of punch-through IGBTs (PT-IGBTs) and trench gate field-stop IGBTs (FS-IGBTs), and the performance of technology computer-aided design (TCAD) simulation of the designed device is similar to the target performance. In particular, the simulation results of the designed FS-IGBT are highly fitted to the datasheet of the commercial device, which verifies the generalizability and effectiveness of the method. In addition, comparative analyses with various algorithms show DE provides the fastest optimization and extraordinary robustness under the exact specifications. Crucially, the proposed design scheme aligns with semiconductor physics. The method simplifies IGBT design without the need for manual tuning and TCAD tool simulation.

关键词： Insulated gate bipolar transistors Structural engineering Performance evaluation Predictive models optimization Training Prediction algorithms Artificial neural networks (ANNs) automatic optimization electrical performance insulated gate bipolar transistor (IGBT) optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Cross-Entropy Method for Laser Defense Applications

引用

JOURNAL OF AEROSPACE INFORMATION SYSTEMS 2025年第1期22卷 53-58页

作者： Hanak, J. Novak, J. Ben-Asher, J. Z. Chudy, P. Brno Univ Technol Fac Informat Technol Brno 61200 Czech Republic Technion Israel Inst Technol Dept Aerospace Engn IL-32000 Haifa Israel Univ Wurzburg Inst Comp Sci D-97074 Wurzburg Germany

来源：评论

学校读者我要写书评

暂无评论

Research on Calibration Method of Triaxial Magnetometer Based on Improved PSO-Ellipsoid Fitting algorithm

引用

ELECTRONICS 2025年第9期14卷 1778-1778页

作者： Guan, Jun Chen, Zhihui Jiang, Guilin Jiangsu Univ Sci & Technol Sch Automat Zhenjiang 212100 Peoples R China Nanjing Univ Sci & Technol Natl Key Lab Transient Phys Nanjing 210094 Peoples R China Huaihai Ind Grp Co Ltd Changzhi 046012 Peoples R China

To address the measurement accuracy degradation of triaxial magnetometers caused by manufacturing errors and environmental interference, and the limited robustness of traditional calibration methods, this study proposes a Dynamic Hierarchical Elite-guided Particle Swarm optimization (DHEPSO)-based ellipsoid fitting algorithm. First, an error model for the triaxial magnetometers is established. Next, the DHEPSO algorithm is utilized to fit the ellipsoid parameters by integrating a dynamic hierarchical mechanism, elite guidance strategy, and adaptive inertia weight adjustment, thereby balancing global exploration and local exploitation to efficiently optimize the parameters. Finally, error compensation and precise calibration are achieved using the optimized parameters. The simulation results show that, compared to the Least Squares Method (LSM), it reduces the absolute distance between the simulated data and the ellipsoid by 63.10% and the post-calibration total magnetic field intensity standard deviation by 60% under outlier interference. Against the traditional PSO, TSLPSO, MPSO, and AWPSO, DHEPSO achieves total distance reductions of 48.52%, 47.74%, 56.71%, and 33.09%, respectively, with faster convergence. The statistical analysis of 60 trials confirms DHEPSO's stability, exhibiting lower median error and interquartile range. The results validate DHEPSO's high precision and robustness in high-noise environments, offering theoretical support for engineering applications.

关键词： triaxial magnetometer error calibration ellipsoid fitting least squares method optimization algorithm particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

An Ultrasonic Synthetic Jet Piezo Pump for Air Delivery

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2025年第5期72卷 5177-5186页

作者： Wang, Meng Liu, Zenghao Wang, Conghui Liu, Guojun Jilin Univ Sch Mech & Aerosp Engn Changchun 130025 Peoples R China

A combination of piezoelectric drive and synthetic jet technology is proposed for an ultrasonic synthetic jet piezo pump. The piezo vibrator operates silently and has a resonant frequency exceeding 20 kHz. The inlet channel of the proposed piezo pump is equipped with a special Tesla structure to increase the flow resistance difference and reduce flow loss. The results demonstrate that the proposed piezo pump has a significant advantage over a typical pump in flow rate. The optimized piezo pump achieves a flow rate of 1037 mL/min when subjected to a typical square wave signal excitation. The optimized waveform enhances the flow rate to 1343.9 mL/min, resulting in a 29.6% improvement. Additionally, this article also investigates the ultrasonic synthetic jet piezo pump in the form of a dual cavity. The two cavities are positioned on either side of the piezo vibrator and alternate between suction and discharge. When the two cavities were connected in parallel, the flow rate was 1912.68 mL/min. Finally, the proposed piezo pump was explored for impact cooling applications. The impact cooling effect on the heated ceramic is good at an impact distance and angle of 30 mm and 60 degrees, respectively.

关键词： Acoustics Cooling Voltage Resonant frequency Vibrations Ceramics Surface acoustic waves Plasmas Heat pumps Genetic algorithms Impact cooling optimization algorithm piezo pump synthetic jet ultrasonic

来源：评论

学校读者我要写书评

暂无评论

A layered metastructure-based smart radiant regulator with enhanced emissivity modulation utilizing phase change material

引用

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER 2025年 164卷

作者： Yao, Ting-Shuo Sui, Jun-Yang Du, Rui Zhang, Ting-Hao Zhang, Hai-Feng Nanjing Univ Posts & Telecommun Coll Elect & Opt Engn Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Flexible Elect Future Technol Nanjing 210023 Peoples R China

Based on thermal radiation, radiative cooling is a widely used technology, and plays an important role in many scenarios such as passive building cooling and infrared camouflage. Currently, dynamic control of thermal radiation devices is endowed with great expectations. However, a more efficient systematic strategy for designing smart radiant temperature regulators (SRTRs) is still urgently needed. By leveraging the phase change properties of vanadium dioxide, the proposed SRTR achieves dynamic modulation of thermal emissivity, demonstrating an average total directional emissivity exceeding 0.9 when the temperature is above the threshold temperature, and dropping below 0.1 when the threshold temperature is not been reached, particularly within the atmospheric transparent window band. The optimization results achieved by using Autonomous Particles Groups for Particle Swarm optimization demonstrate better performance metrics compared to those obtained using conventional methods. Notably, the absorption mechanism of layered metastructure is further investigated, and its high angle dependency is effectively addressed. The demonstrates excellent angular stability and polarization insensitivity, with up to 73 degrees in transverse electric mode and 60 degrees in transverse magnetic one. Without taking non-radiative heat transfer into account, the cooling power achieves 214.59 W.m(-2). In this paper, a more systematic strategy for designing SRTRs is exhibited, which offers extensive potential in fields such as surface radiative cooling, infrared camouflage, and spacecraft thermal management.

关键词： Radiative cooling Layered metastructure Phase change material Smart radiant temperature regulation optimization algorithm

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：