检索结果-内蒙古大学图书馆

Design of Denoising Method for Underwater Communication Based on Adaptive Chunking Algorithm and Quantum Mechanics Theory

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第3期12卷 2498-2513页

作者： Liu, Xin Meng, Xiangxu Xu, Yinan Wu, Yujing Lee, Hojun Liu, Bingqi Xu, Yihu Yanbian Univ Coll Engn Yanji 133002 Peoples R China Hoseo Univ Asan Dept Informat & Commun Engn Asan 31499 South Korea

With the deepening exploitation of marine resources, the application of underwater communication is becoming increasingly widespread, and the noise in the underwater channel will severely impact the reliability of underwater communication. Therefore, researchers have focused on improving the accuracy and reliability of underwater communication through denoising. Currently, denoising methods are widely used based on algorithms, such as Fourier transform, wavelet transform, convolutional neural network, and time-space domain filtering. Still, they all have some areas for improvement in the application of underwater communication. In this regard, inspired by quantum mechanical tools and adaptive algorithms, this article proposes a quantum adaptive chunk denoising algorithm applied in underwater communication. First, this article proposes an adaptive chunking algorithm to dynamically adjust the chunk size according to the local signal characteristics to capture the signal details better. Second, the chunked signal and image are taken as potentials in the discrete Schr & ouml;dinger equation and solved for the eigenvalues and eigenvectors of the discrete Hamiltonian matrix constructed by the adaptive chunking algorithm. Finally, the solved values are subjected to total variational denoising and reconstruction after denoising. The algorithm proposed in this article is compared with wavelet denoising based on hard and soft thresholding, Denoising Algorithm Based on an ideal low-pass adaptive filter, sparsity-assisted signal smoothing (SASS) algorithm and Quantum Mechanics Adaptive Basis Denoising Algorithm. The experimental results show that the quantum adaptive chunking denoising algorithm proposed in this article can effectively remove underwater noise from signals and images under the condition of low-signal-to-noise ratio, which improves the reliability and signal quality of underwater communication and meets the denoising standard of underwater communication.

关键词： Noise Noise reduction Quantum mechanics Underwater communication Signal processing algorithms Thermal noise Mathematical models Wavelet transforms classification algorithms Time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

Optimization of Adversarial Reprogramming for Transfer Learning on Closed Box Models

引用

IEEE ACCESS 2025年 13卷 48999-49006页

作者： Bott, Alexander Siems, Moritz Puchta, Alexander Fleischer, Juergen Karlsruhe Inst Technol KIT Wbk Inst Prod Sci D-76131 Karlsruhe Germany

In this work, we optimise a transfer learning approach for predicting the Remaining Useful Life (RUL) of ball bearings, particularly in scenarios with limited data availability. Accurate RUL prediction is crucial for improving maintenance strategies, reducing downtime and improving machine reliability, making it highly relevant to industry. We use the Black Box Adversarial Reprogramming (BAR) algorithm to process target domain data in a source domain model through adversarial reprogramming. While it has been shown that this concept can work well in image classification, and a further modification has been developed to classify time series features, this work focuses primarily on the remaining key challenges such as the selection and comparison of appropriate loss functions, the optimisation of hyperparameters using Bayesian methods, and data labelling in the absence of ground truth. Our results show an increase in the performance of the BAR algorithm on the macro f1 score of 0.23 on the training set and up to 0.21 on the test set.

关键词： Bars Time series analysis Transfer learning Prediction algorithms classification algorithms Closed box Vectors Training Feature extraction Predictive maintenance Adversial reprogramming closed box transfer learning machine learning RUL-classification

来源：评论

学校读者我要写书评

暂无评论

Research on Density Peak Clustering Color-Separation Algorithm Based on SOM Neural Network

引用

IEEE ACCESS 2025年 13卷 16811-16823页

作者： Ru, Xin Wang, Yanhao Chen, Ran Zeng, Zhifa Peng, Laihu Tang, Wei Shi, Weimin Wang, Hui Zhejiang Sci Tech Univ Sch Mech Engn Hangzhou 310018 Peoples R China Shanxi Univ Sch Comp & Informat Technol Taiyuan 237016 Peoples R China Zhejiang Hengqiang Technol Co Ltd Hangzhou 311100 Peoples R China Zhejiang Sci Tech Univ Longgang Inst Wenzhou 325802 Peoples R China

Pattern images input to The knitting CAD system have a large number of different colors, and it is necessary to reduce the number of colors in the image by merging similar colors through color-separation algorithms. However, current pattern images usually have the problem of image degradation, which seriously affects the accuracy of color-separation algorithms. In addition, the traditional color-separation algorithm needs to rely on the manual setting of clustering parameters, which is very time-consuming and laborious. To solve these problems, In this paper, we propose a density peak clustering color-separation algorithm based on self-organizing mapping (SOM) neural network, which firstly uses enhanced super-resolution generative adversarial network (Real-ESRGAN) blind super-resolution reconstruction network to clarify the degraded image and obtain a high-resolution image with clear boundaries;secondly, we carry out the initial clustering through the SOM neural network to simplify the image information;and then we use an improved density peak clustering (DPC) algorithm to calculate clustering centers under the conditions of conforming to the perception of human eyes, and carry out secondary clustering on the image;finally, carry out image post-processing through the variegated spots merging algorithm based on the connected component analysis. The experimental results show that the algorithm proposed in this study can effectively deal with degraded pattern images, and the clustering effectiveness evaluation indices perform well.

关键词： Image color analysis Clustering algorithms Neural networks Image reconstruction Superresolution Degradation Image segmentation classification algorithms Computational efficiency NIST Color-separation algorithm density peak clustering (DPC) knitting CAD self-organizing mapping (SOM) neural network blind super-resolution reconstruction network

来源：评论

学校读者我要写书评

暂无评论

A Novel Ensemble Classifier Selection Method for Software Defect Prediction

引用

IEEE ACCESS 2025年 13卷 25578-25597页

作者： Dong, Xin Wang, Jie Liang, Yan Chengdu Technol Univ Comp Engn Coll Chengdu 611730 Peoples R China Sci & Technol Elect Informat Control Lab Chengdu 610036 Peoples R China

The presence of software defects significantly impacts the quality of software systems and increases development and maintenance costs. To improve system quality and reduce costs, it is necessary to predict software defects in the early stages of the software development lifecycle. This paper proposes Double Fault Disagreement (DFD), a novel diversity metric and method for selecting competent base classifiers for ensemble learning-based software defect prediction. To consider the diversity features of the base learners, several base learners with strong diversity are chosen to build ensemble learning. This method makes full use of the diversity characteristics of base learners, leverages their classification ability, optimizes the selection method for ensemble learning, and enhances the predictive performance of the ensemble model. The experimental results demonstrate that the DFD ensemble learning-based software defect prediction model outperforms the ten other models, including five common machine learning (ML) classification algorithms (logistic regression (LR), na & iuml;ve Bayes (NB), K-nearest neighbor (KNN), decision tree (DT), and support vector machine (SVM)), two deep learning (DL) algorithms (multi-layer perceptron (MLP) and convolutional neural network (CNN)), and three ensemble learning algorithms (random forest (RF), extreme gradient boosting (XGB), and stacking). The DFD model achieves superior performance on eight public NASA and PROMISE datasets (six of which are imbalanced) across five performance indicators, including area under the curve (AUC), geometric mean (G-Mean), F1 score, Matthews correlation coefficient (MCC), and Balance. Furthermore, the DFD method is not only highly performant but also requires a small number of base learners to converge rapidly, thereby reducing the amount of data and computation time required.

关键词： Ensemble learning Predictive models Measurement Computational modeling classification algorithms Software Volume measurement Weight measurement Stacking Prediction algorithms Diversity measures double fault disagreement ensemble classifier selection imbalanced data classification software defect prediction

来源：评论

学校读者我要写书评

暂无评论

Optimized Path Planning for Autonomous Guided Vehicle Through Fusion of Improved A* and Dynamic Window Approach

引用

IEEE ACCESS 2025年 13卷 68577-68586页

作者： Luo, Yixuan Lin, Shusen Wang, Yifan Liang, Kai Taizhou Univ Coll Intelligent Mfg Taizhou 318001 Peoples R China

This paper addresses the issues of slow speed, safety concerns, and non-smooth paths in traditional A* algorithm-based path planning for Autonomous Guided Vehicle (AGV) in complex environments. The study proposes an improved fusion algorithm combining the A* and Dynamic Window Approach (DWA). The enhanced A* algorithm first plans the global path, and then the DWA algorithm handles local path planning under the guidance of the global path. First, by introducing the concept of obstacle density, the study integrates environmental information, optimizes the evaluation function, refines the child node selection process, and applies bidirectional smoothness optimization to the paths. These improvements enhance search efficiency, ensure adequate safety distances from obstacles, and strengthen the safety margin and rationality of the paths, making them more aligned with the robot's needs. Next, the integration of the DWA algorithm allows for dynamic obstacle identification and local path regeneration for avoidance, resulting in more realistic paths for dynamic obstacle navigation. Finally, key nodes from the global path planning of the A* algorithm are extracted to serve as references for local planning in the DWA algorithm, ensuring that local paths are more closely aligned with global paths. Simulations and practical experiments confirm the effectiveness of the proposed algorithm, providing a more efficient and feasible solution to the path planning problem.

关键词： Heuristic algorithms Path planning Vehicle dynamics Safety Collision avoidance classification algorithms Planning Navigation Mobile robots Dynamics A* algorithm path planning dynamic window approach autonomous guided vehicle

来源：评论

学校读者我要写书评

暂无评论

FRAME: Feature Rectification for Class Imbalance Learning

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第3期37卷 1167-1181页

作者： Cheng, Xu Shi, Fan Zhang, Yao Li, Huan Liu, Xiufeng Chen, Shengyong Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300386 Peoples R China Aalborg Univ Dept Comp Sci DK-9220 Aalborg Denmark Tech Univ Denmark Dept Technol Management & Econ DK-2800 Kongens Lyngby Denmark

Class imbalance learning is a challenging task in machine learning applications. To balance training data, traditional class imbalance learning approaches, such as class resampling or reweighting, are commonly applied in the literature. However, these methods can have significant limitations, particularly in the presence of noisy data, missing values, or when applied to advanced learning paradigms like semi-supervised or federated learning. To address these limitations, this paper proposes a novel and theoretically-ensured latent Feature Rectification method for clAss iMbalance lEarning (FRAME). The proposed FRAME can automatically learn multiple centroids for each class in the latent space and then perform class balancing. Unlike data-level methods, FRAME balances feature in the latent space rather than the original space. Compared to algorithm-level methods, FRAME can distinguish different classes based on distance without the need to adjust the learning algorithms. Through latent feature rectification, FRAME can effectively mitigate contaminated noises/missing values without worrying about structural variations in the data. In order to accommodate a wider range of applications, this paper extends FRAME to the following three main learning paradigms: fully-supervised learning, semi-supervised learning, and federated learning. Extensive experiments on 10 binary-class datasets demonstrate that our FRAME can achieve competitive performance than the state-of-the-art methods and its robustness to noises/missing values.

关键词： Data models Noise classification algorithms Machine learning Neural networks Training Noise measurement Machine learning algorithms Federated learning Fans Class imbalance learning feature rectification latent space learning paradigm

来源：评论

学校读者我要写书评

暂无评论

Tunnel Crack Segmentation Algorithm Based on Feature Enhancement

引用

IEEE ACCESS 2025年 13卷 70650-70662页

作者： Feng, Lihua Yao, Aijun Huang, An Beijing Univ Technol Coll Architecture & Civil Engn Beijing 100124 Peoples R China China Railway First Grp Second Engn Co Ltd Tangshan 063000 Hebei Peoples R China

Tunnel cracks, as one of the early indicators of tunnel damage, have a significant impact on the safe operation of tunnels. However, due to the complex lighting conditions, background noise, and diverse nature of cracks inside tunnels, traditional image segmentation algorithms often struggle to achieve sufficient accuracy in crack segmentation tasks. To address these challenges, this paper proposes a tunnel crack detection method. Firstly, a novel Dynamic Feature Enhancement Network (DFEN) module is designed to extract preliminary features using a feature extractor and selectively enhance feature representations through a gating mechanism. Additionally, a new Multi-Head Interaction Learning (MHIL) is introduced, facilitating feature sharing by incorporating information exchange across different attention heads, thereby improving feature representation capabilities. Lastly, the Adaptive Switchable Atrous Convolution (ASAC) module is introduced, combining the advantages of adaptive convolution and deformable convolution while incorporating Switchable Atrous Convolution (SAC) to enhance multi-scale feature capturing capabilities. Ablation experiments, through both qualitative and quantitative evaluations, demonstrate the effectiveness of the proposed method. Comparative analysis with existing semantic segmentation methods further confirms the superiority of the proposed method in tunnel crack detection.

关键词： Feature extraction Accuracy Convolution YOLO Attention mechanisms Transformers Robustness Heuristic algorithms classification algorithms Switches Crack segmentation dynamic feature enhancement network multi-head interaction learning adaptive switchable atrous convolution

来源：评论

学校读者我要写书评

暂无评论

YOLO-MES: An Effective Lightweight Underwater Garbage Detection Scheme for Marine Ecosystems

引用

IEEE ACCESS 2025年 13卷 60440-60454页

作者： Huang, Chengxu Zhang, Wenyuan Zheng, Beitian Li, Jiahao Xie, Bochen Nan, Ruisi Tan, Zongming Tan, Baohua Xiong, Neal N. Hubei Univ Technol Sch Sci Sch Chip Ind Wuhan 430068 Peoples R China Hubei Univ Technol Natl Res Ctr Microelect & Integrated Circuits 111 Wuhan 430068 Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing 210096 Peoples R China Hubei Univ Technol Coll Engn & Technol Wuhan 430068 Peoples R China Cogdel Cranleigh High Sch Wuhan 432200 Peoples R China Southern New Hampshire Univ Dept Comp Sci Manchester NH 03106 USA

Marine pollution significantly impacts the sustainable development of marine ecosystems and the marine economy. Accurate detection of marine debris is essential for effective pollution control. However, existing high-precision detection algorithms are challenging to deploy on performance-constrained IoT underwater devices due to their large computational complexity and model size. To address this issue, this paper introduces YOLO-MES, an innovative underwater debris detection algorithm that integrates a lightweight design and a feature enhancement mechanism to enable efficient model deployment while preserving high accuracy. Unlike traditional YOLO models, YOLO-MES incorporates MobileNetV3 into underwater target detection, replacing the CSPDarknet backbone network, and optimizes the C3 and Conv layers through the bneck structure, significantly reducing computational demands and parameter scale at the architectural level. Additionally, YOLO-MES embeds the Efficient Channel Attention (ECA) module within the bneck structure to form the MECAneck module, which enhances adaptive feature extraction, significantly improving the network's cross-channel feature capture and target recognition capabilities. This paper also proposes a streamlined Slim-neck design strategy, which effectively reduces the number of parameters in the neck network while maintaining multi-scale feature fusion accuracy. Experimental results indicate that YOLO-MES achieves 95.8% accuracy on the dataset, while reducing model size and computational complexity by 64% and 67%, respectively. Compared to existing mainstream detection algorithms, YOLO-MES offers significant advantages in lightweight design and computational efficiency, providing a practical and deployable solution for underwater target detection on mobile devices.

关键词： Feature extraction Convolution Computational modeling Accuracy YOLO Computational complexity classification algorithms Real-time systems Performance evaluation Neck Deep learning underwater garbage detection lightweight MobileNetv3

来源：评论

学校读者我要写书评

暂无评论

MSFFNet: A Multilevel Sparse Feature Fusion Network for Infrared Dim Small Target Detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 147-159页

作者： Ren, Xiangyang Jiao, Boyang Peng, Zhenming Kou, Renke Wang, Peng Li, Mingyuan Zhengzhou Univ Affiliated Hosp 1 Med 3D Printing Ctr Henan Prov Zhengzhou 450000 Peoples R China Zhengzhou Univ Clin Med Coll 1 Zhengzhou 450000 Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Lab Imaging Detect & Intelligent Percept Chengdu 610054 Peoples R China Army Engn Univ Shijiazhuang Campus Shijiazhuang 050003 Peoples R China Zhengzhou Univ Sch Elect & Informat Engn Zhengzhou 450001 Peoples R China Zhengzhou Univ Affiliated Hosp 1 Natl Engn Lab Internet Med Syst & Applicat Zhengzhou 450001 Peoples R China

The sparse characteristics of target features poses significant challenges when using deep learning methods for infrared dim small targets. To tackle this issue, this article proposes a novel multilevel sparse feature fusion network for detecting infrared dim small targets. A feature-level sparse feature fusion network fuses target features of the same level and different depths to express small target features. A decision-level sparse feature fusion network fuses features from different decision spaces to improve decision confidence. To enrich the feature representation of the target, different levels of target global features are introduced into the decision-level sparse feature fusion network. During the network training process, a deep joint supervision training strategy is proposed to supervise and train the multilevel sparse feature fusion network, aiming to fully learn the feature representation of the target. According to the experimental results, the proposed infrared dim small targets detection method outperforms existing popular methods under sparse target features.

关键词： Feature extraction Object detection Training Deep learning Noise Interference classification algorithms Accuracy YOLO Shape Decision-level sparse feature fusion deep joint supervision feature-level sparse feature fusion infrared small target

来源：评论

学校读者我要写书评

暂无评论

Adaptive Zero Velocity Detector for Pedestrian Navigation Based on Relative Test Statistics

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第6期12卷 7320-7331页

作者： Niu, Ze Qin, Honglei Cong, Li Cao, Shuo Beihang Univ Sch Elect Informat Engn Beijing 100191 Peoples R China Beijing Inst Control & Elect Technol Natl Key Lab Informat Syst Engn Beijing 100038 Peoples R China

Autonomous pedestrian localization involving complex motion modes is important for applications, such as firefighting and counter-terrorism in global navigation satellite system denied environments. Inertial navigation based on Zero Velocity Update is a crucial method, and adaptive zero velocity detector (AZVD) is a key part to improve performance. However, current AZVD still face challenges in adaptability to different motion speeds and complex motion modes (such as crawling), as well as high-computational load. To address these issues, this article proposes an AZVD that represents the generalized likelihood ratio test statistics within a time window as a ratio relative to the minimum statistic and sets thresholds based on these ratios (relative statistics). First, we theoretically analyze the method based on relative statistics. To ensure that the time window for data segmentation includes zero-velocity phases, and the minimum statistic corresponds to the zero-velocity phase, we divide the algorithm into two steps: 1) design a gait cycle (GC) detection suitable for single support motions and segment the data according to the GC. For motions where the GC cannot be detected, a designed time window is used for data segmentation and 2) for motions where steps are detectable, we restrict the zero-velocity phase to a specific range within the GC;for motions where the GC are undetectable, no restriction is imposed. Then, the threshold is set based on the relative statistics. Finally, through experiments involving multiple individuals and various motion speeds and motion modes, the adaptability of the proposed algorithm is validated.

关键词： Detectors Motion segmentation Legged locomotion classification algorithms Pedestrians Accuracy Training Windows Internet of Things Phase detection Complex motion mode crawling gait analysis pedestrian inertial navigation zero velocity update

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：