检索结果-内蒙古大学图书馆

Research on feature point matching algorithm improvement using depth prediction

JOURNAL OF ENGINEERING-JOE 2019年第23期2019卷 8905-8909页

作者： Chen, Yongbin Wang, Guitang Wu, Liming Guangdong Univ Technol Guangzhou 510006 Peoples R China

Feature point matching plays an important role in feature-based image registration such as the scale-invariant feature transform algorithm. Feature-based image registration is widely used in visual simultaneous localisation and mapping, augmented reality, self-driving etc. The most meaningful study on feature matching is to improve the accuracy and efficiency and this study pays attention to improving the accuracy by removing the mismatching feature points. Since most of the existed feature-based image registration algorithms are not so strong and efficient enough in mismatch removing, in this study, the authors propose a novel mismatch removal algorithm by incorporating depth prediction into feature matching to improve the performance. In this approach, the depth maps are predicted in pixel-wise through the given red-green-blue images using a deep learning algorithm. Experimental results show that their method outperforms conventional ones in mismatch removing.

关键词： learning (artificial intelligence) image matching feature extraction transforms image registration image colour analysis red-green-blue images feature-based image registration algorithms visual simultaneous localisation feature point matching algorithm improvement deep learning algorithm depth prediction novel mismatch removal algorithm mismatch removing mismatching feature points feature matching

来源：评论

学校读者我要写书评

暂无评论

Prediction of Color Change in Heat-Treated Wood Based on Improved Zebra algorithm Optimized Deep Hybrid Kernel Extreme Learning Machine Model (IZOA-DHKELM)

引用

FORESTS 2025年第2期16卷 253-253页

作者： Liang, Jingjie Wang, Wei Qu, Zening Cao, Ying Gong, Jingxiang Northeast Forestry Univ Coll Mech & Elect Engn Harbin 150040 Peoples R China

In this study, an Improved Zebra Optimization algorithm (ZOA) is proposed based on the search mechanism of the Sparrow Optimization algorithm (SSA), the perturbation mechanism of the Particle Swarm algorithm (PSO), and the adaptive function. Then, Improved Zebra Optimization algorithm (IZOA) was used to optimize the Deep Hybrid Kernel Extreme Learning Machine Model (DHKELM), and the IZOA-DHKELM was obtained. The model has been used to predict the color of heat-treated wood for different species, temperatures, times, media, and profile types. In this article, the original DHKELM and the ZOA-DHKELM were compared to verify the validity and accuracy of the model. The results indicated that the IZOA-DHKELM decreased the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) by 56.2%, 67.4%, and 34.2%, respectively, while enhancing the coefficient of determination, R2, to 0.9952 compared to the ZOA-DHKELM. This demonstrated that the model was significantly optimized, with improved generalization ability and prediction accuracy. It can better meet the actual engineering needs.

关键词： heat-treated wood performance prediction algorithm improvement DHKELM wood color

来源：评论

学校读者我要写书评

暂无评论

Multi-Type Ship Target Detection in Complex Marine Background Based on YOLOv11

引用

PROCESSES 2025年第1期13卷 249-249页

作者： Wang, Yao Zeng, Weigui Xu, Huiqi Jiang, Yi Liu, Minggang Xiao, Chuanliang Zhao, Ke Naval Aviat Univ Yantai 264001 Peoples R China Shandong Univ Technol Elect & Elect Engn Acad Zibo 255000 Peoples R China

Realizing accurate control of ship target information in complex marine environments is of great significance for maintaining marine environment security and safeguarding maritime sovereignty. With the rapid development of material technology and manufacturing industry, the types and styles of ships are increasing, and the distribution of multi-type ships on the sea is widespread. How to realize the accurate detection and identification of dynamic multi-type ship targets in the complex marine environment is an important and difficult problem that needs to be solved urgently in current marine environment detection. In this paper, an improved YOLOv11 ship target detection algorithm is proposed, which firstly utilizes the improved EfficientNetv2 network to replace the original backbone network of YOLOv11 to improve the learning ability of ship features under complex sea conditions;in order to solve the problem of interference by moving objects at sea when detecting dense ship targets and reduce the problems of missing detection and false alarms, the algorithm borrows from ConvNext block idea in the process of a neck feature pyramid network fusion;the algorithm introduces the WIoU loss function, which compensates for the effect of the small number of pixels of the small target in the process of regression loss computation, so as to improve the network's performance in detecting small targets. In order to test the network performance in actual application scenarios, the article builds a visible ship target dataset, including complex background, occlusion and overlap, small targets, and other factors. Through experimental verification, the detection accuracy of the improved algorithm is improved by 5.6% compared with the original algorithm, and compared with typical algorithms in terms of detection accuracy, speed, and number of parameters, ablation experiments are designed to comprehensively validate and analyze the algorithm's performance.

关键词： YOLOv11 multi-type ship target detection complex environment algorithm improvement

来源：评论

学校读者我要写书评

暂无评论

A novel approach to analyzing the mechanical response of component failure in cable truss structures using an improved LSTM neural network

引用

ENGINEERING FAILURE ANALYSIS 2025年 174卷

作者： Liu, Zhansheng Shi, Guoliang Liu, Yue Beijing Univ Technol Key Lab Urban Secur & Disaster Engn Minist Educ 100 Pingleyuan Beijing 100124 Peoples R China Univ Sci & Technol Beijing Res Inst Urbanizat & Urban Safety Sch Future Cities Beijing 100083 Peoples R China

In the large cable structure, the cable as the main force component bears a large load. How to accurately analyze the influence of cable rupture on the structure and give reasonable maintenance measures has become the key to health monitoring of large cable structures. In this study, a cable truss structure (CTS) is taken as the research object, the model experiment is established, and the numerical analysis method of component failure mechanics is proposed. Firstly, the component failure and mechanical response acquisition mechanism are designed according to the CTS experimental model. The measured parameters are used as indicators to evaluate the simulation accuracy. In order to improve the accuracy of finite element simulation, a transient dynamic analysis method is proposed. Based on the simulation model and calculation method, the mechanical response analysis and parameter analysis of typical failure conditions are carried out. The most unfavorable failure mode is obtained, and the best maintenance measures for component failure are given. Considering the time correlation of component failure, a mechanical response prediction method based on convolutional neural network (CNN)- Bi long short-term memory (BiLSTM) optimized by improved particle swarm optimization (IPSO) is proposed. Combined with finite element simulation data samples and prediction methods, the mapping relationship between component failure and mechanical response is established. Finally, the continuous dynamic analysis of component failure is realized, and the most unfavorable failure path is obtained. The research results show that the accuracy of the established simulation model and calculation method is more than 95%. The improved deep learning prediction model significantly improves the prediction accuracy and efficiency, and the analysis error and time cost are reduced by 7.5% and 23.7%, respectively.

关键词： Cable truss structure Component failure Cable rupture analysis Mechanical response algorithm improvement

来源：评论

学校读者我要写书评

暂无评论

Research on Two Refined algorithms for Creep Calculation for Reinforced Concrete Components

引用

BUILDINGS 2025年第3期15卷 478-478页

作者： Wu, Pengfei Cui, Jianchao Dalian Univ Technol State Key Lab Coastal & Offshore Engn Dalian 116024 Peoples R China Shenyang City Univ Sch Intelligence & Engn Shenyang 110112 Peoples R China

Existing refined creep calculation methods primarily include the numerical recursive method. Previous algorithms merely provided a theoretical possibility for refined creep calculations. Their massive computational load, complex derivation processes, and limited applicability conditions made it difficult to apply them practically in engineering. Therefore, this study improves upon existing refined creep algorithms by proposing two new calculation methods: the trapezoidal method and the difference method. The study shows that when calculating creep under different conditions, the proposed methods only require adjustments to certain elements in the calculation model, without the need to re-derive the creep calculation formula;this thus provides a convenient solution for creep calculation under varying operating conditions. Compared to the traditional numerical recursive method, the proposed methods significantly reduce computational effort;compared to the midpoint integration method, the proposed methods offer broader applicability. Under different calculation conditions, both methods exhibit high computational accuracy.

关键词： creep refinement method algorithm improvement trapezoid method difference method T-shaped beam

来源：评论

学校读者我要写书评

暂无评论

The adaptive two-stage ant colony Simulated Annealing algorithm for solving the Traveling Salesman Problem

引用

RAIRO-OPERATIONS RESEARCH 2025年第2期59卷 1199-1213页

作者： Wu, Yingnian Wang, Hao Li, Manhua Tan, Hao Wang, Ding Sheng, Meiqi Beijing Informat Sci & Technol Univ Sch Automat Beijing Peoples R China

In the process of solving the Traveling Salesman Problem (TSP), both the Ant Colony Optimization and Simulated Annealing algorithm exhibit different limitations depending on the dataset. This paper aims to address these limitations by Using the Ant Colony Optimization as a search strategy for the Simulated Annealing algorithm and designs two adaptive search stages based on the search characteristics of the Simulated Annealing algorithm. Thus solving the problem of slow convergence speed and easy getting stuck in local optimal solutions in the Simulated Annealing algorithm. By conducting tests on various TSPLIB datasets, the algorithm proposed in this article demonstrates improved convergence speed and solution quality compared to traditional algorithms. Furthermore, it exhibits certain advantages over other existing improved algorithms.

关键词： Ant colony optimization simulated annealing algorithm algorithm improvement traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Research on Detection and Counting Method of Green Walnut Based on YOLOv8n-RBP

引用

IEEE ACCESS 2025年 13卷 39275-39288页

作者： Chen, Bangbang Tan, Keke Li, Kun Ma, Baojian Liu, Xiangdong Xinjiang Inst Technol Sch Mechatron Engn Aksu 843100 Peoples R China Xian Technol Univ Sch Mechatron Engn Xian 710021 Peoples R China

In natural environments, green walnuts often experience occlusion by branches and leaves, fruit overlap, and varying lighting conditions. To address the issues of low detection accuracy, missed detections, and false positives in the YOLO model, this study proposes an improved YOLOv8n-based detection and counting model for green walnuts, named YOLOv8n-RBP. First, a receptive field-concentrated attention module (RFCBAM) is integrated into the backbone network to enhance feature extraction capabilities. Second, a BiFPN-GLSA module is introduced to replace the Path Aggregation Network (PANet) in the neck, improving the fusion of feature layers from the backbone and Neck networks and enhancing the model's ability to capture both global and local spatial features. Lastly, to address the weak generalization and slow convergence issues of the CIoU loss function in detection tasks, the PIoUv2 loss function is employed to accelerate bounding box regression and improve detection performance. Experimental results demonstrate that the YOLOv8n-RBP model excels across multiple evaluation metrics. Specifically, the model achieves a mean average precision (mAP@0.5) of 82.2% and a recall rate of 72.4%, with a model size of only 4.65 MB, 2.2 million parameters, and 8.3 GFLOPs. Compared to the original YOLOv8n model, the recall rate and mAP@0.5 improve by 2.7% and 2.5%, respectively, while the number of parameters, FLOPs, and model size decrease by 26.7%, 0.6%, and 22.0%, respectively. Further deployment on the NVIDIA Jetson Xavier NX demonstrates the model's robust performance under natural conditions, indicating its suitability for orchard operations.

关键词： Feature extraction Accuracy Green products YOLO Training Real-time systems Neck Computational modeling Data models Data augmentation Natural environment green walnut detection algorithm improvement equipment deployment

来源：评论

学校读者我要写书评

暂无评论

DIBTBL: A Novel Text Sentiment Analysis Model Based on an Improved Swarm Intelligence algorithm and Deep Learning

引用

IEEE ACCESS 2024年 12卷 158669-158684页

作者： Mu, Guangyu Dai, Li Li, Xiurong Ju, Xiaoqing Chen, Ying Dai, Jiaxiu Jilin Univ Finance & Econ Sch Management Sci & Informat Engn Changchun 130000 Peoples R China Lab Financial Technol Jilin Prov Changchun 130000 Peoples R China Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China

Analyzing and understanding emotional expressions in user comments is a crucial and complex task in business. Conducting text sentiment analysis is of great significance. This paper constructs a novel DIBTBL model that integrates an extended sentiment dictionary, an improved swarm intelligence algorithm, and deep learning techniques to accurately capture and analyze user emotions. Firstly, this paper expands the sentiment dictionary to extract emotion feature words from the review text. Secondly, the BERT model embeds these emotional feature words and pre-processed text into high-dimensional semantic space to obtain richer semantic representations and improve sentiment classification performance. Then, the TextCNN-BiLSTM feature extraction model is established to balance the grasping ability of local and global features. Fourthly, this paper innovatively improves the swarm intelligence algorithm BWO to optimize the parameters of the TextCNN-BiLSTM. Finally, MLP is employed for sentiment classification. The experimental data is crawled from Ctrip, China's largest hotel booking website. In the comparative experiment, the proposed model achieves a higher accuracy than TBL, DTBL, BTBL, and IBTBL by 2.94%, 2.44%, 1.64%, and 0.66%, respectively. In addition, we compare the proposed model with seven advanced models in the open dataset waimai_10k. The experimental results indicate that this model outperforms all the other models, with an average improvement in accuracy of 8.21%. The study offers precise insights into user sentiment, assisting companies in better understanding and meeting customer needs.

关键词： Feature extraction Dictionaries Analytical models Optimization Long short term memory Classification algorithms Sentiment analysis Particle swarm optimization Deep learning Semantics deep learning text features algorithm optimization algorithm improvement

来源：评论

学校读者我要写书评

暂无评论

A Framework for algorithmic improvement to Mitigate the Effects of Equifinality in the Calibration of High-dimensional Parameters for Hydrological Models

引用

WATER RESOURCES MANAGEMENT 2024年第1期38卷 251-267页

作者： Tang, Xiaoyang Tang, Deshan Zhang, Fulin Hohai Univ Coll Water Conservancy & Hydropower Engn Nanjing Jiangsu Peoples R China

When performing hydrological model parameter calibration, equifinality inevitably reduces the simulation and prediction ability of hydrological models. To lessen the impact of equifinality, a novel algorithmic improvement framework is proposed in this paper. This framework allows the parameters to be searched hierarchically in order of sensitivity size and shrinks the original ranges of the parameters before the final search. The shuffled complex evolution (SCE_UA) algorithm, which is the most popular method for addressing hydrological model calibration issues, is improved using this new framework yielding HSRS_SCE algorithm, which stands for the SCE_UA algorithm with hierarchical search (HS) and range shrinkage (RS). A 26-dimensional parametric calibration problem is constructed and solved in this study utilizing 12 schemes based on the HSRS_SCE algorithm with various parameters and a control scheme based on the SCE_UA algorithm. The results show that the HSRS_SCE algorithm can not only produce calibrated parameter results significantly superior to those of the traditional scheme (p < 0.05) but also produce objective function values 26.1% better than those of the traditional scheme and reduce the search time through parallel computing.

关键词： Equifinality Hydrological models Parameter calibration algorithm improvement SCE_UA algorithm

来源：评论

学校读者我要写书评

暂无评论

Progressive failure process-considered deformation safety diagnosis method for in-service high arch dam

引用

ENGINEERING FAILURE ANALYSIS 2024年第PartB期163卷

作者： Yang, Guang Zhao, Ahui Sun, Jin Niu, Jingtai Zhang, Jianwei Wang, Lin North China Univ Water Resources & Elect Power Sch Water Conservancy Zhengzhou 450046 Peoples R China North China Univ Water Resources & Elect Power Coll Surveying & Geoinformat Zhengzhou 450046 Peoples R China Nanchang Inst Technol Sch Hydraul & Ecol Engn Nanchang 330099 Peoples R China

Conventional methods cannot effectively characterize the progressive failure process, which limits their use in the deformation safety diagnosis of in-service high arch dam. This work proposes a novel method utilizing the frontier theories of mathematics, mechanics, and dam safety monitoring. First, considering the implicit assumption of traditional method, hybrid model (HM) is improved to calibrate the elastic deformation state of high arch dam. Second, the adaptive proportion selection and the neighborhood search strategy are applied to improve artificial bee colony (ABC) algorithm. The undetermined parameters of HM are optimized by the improved ABC. Third, the dangerous degrees of single-point deformation and multi-point deformation are characterized using HM analysis results and information entropy. On this basis, the progressive diagnosis criteria are constructed based on probability principle. Finally, two case studies are conducted to validate the proposed methodology. The analysis results demonstrate that the performance of HM is better than that of the statistical model (SM);the improved ABC promotes the HM performance;and the progressive diagnosis criteria compared with the traditional confidence interval criteria have stricter probabilistic and physical meanings. The 5-level safety control is realized, promoting the emergency response ability of high arch dam in operating condition.

关键词： High arch dam Deformation safety diagnosis Progressive failure process Hybrid modelling Parameter optimization algorithm improvement

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

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

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：