检索结果-内蒙古大学图书馆

Fuzzy Min-Cut With Soft Balancing Effects

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2025年第2期33卷 767-778页

作者： Chen, Huimin Zhang, Runxin Wang, Rong Nie, Feiping Northwestern Polytech Univ Sch Comp Sci Sch Artificial Intelligence Opt & Elect iOPEN Xian 710072 Peoples R China Northwestern Polytech Univ Key Lab Intelligent Interact & Applicat Minist Ind & Informat Technol Xian 710072 Peoples R China Northwestern Polytech Univ Sch Artificial Intelligence OPt & Elect iOPEN Xian 710072 Peoples R China

The clustering algorithm has always been a hot spot in machine learning, which has made great progress and been widely used in different scenarios. Due to the characteristics and requirements of some application scenarios, the branch of the balanced clustering algorithm has been developed. The ideal of these algorithms is to obtain clusters containing approximately the same number of samples. However, when there are data points distributed at the boundary of different clusters, resulting in different probabilities of their belonging, hard-partitioned balanced clustering may not be able to handle these boundary data well, thus limiting their performance. Motivated by this, we propose a Fuzzy Min-Cut with Soft Balancing Effects (FCBE) method in this article. Specifically, the FCBE model utilizes fuzzy constraints to simultaneously enhance the ability of the balanced algorithm to capture boundary data members and the advantage of directly obtaining the partitioning results of graph-cut problem without postprocessing. In addition, a sparse regularization is introduced to avoid trivial solutions and maintain the separability of the relationship matrix. Furthermore, the proposed FCBE method can be viewed as a flexibly adjustable generalization pattern that not only has clear interpretability but also can become special cases with clear physical meanings under different parameter values. The feasibility of FCBE has been verified on real datasets.

关键词： clustering algorithms Partitioning algorithms Fuzzy systems Vectors Sparse matrices Switches Data models clustering methods Wireless sensor networks Uncertainty Fuzzy constraints soft-balanced sparse regularization spectral clustering (SC)

来源：评论

学校读者我要写书评

暂无评论

Only Pick Once: algorithms for Efficiently Picking an Exact Number of Multiple Identical Objects

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 14723-14737页

作者： Ye, Zihe Frumento, Ricardo Sun, Yu Rutgers State Univ Dept Comp Sci New Brunswick NJ 08901 USA Univ South Florida USF Bellini Coll Artificial Intelligence Cybersecur & Robot Percept & Act Lab RPAL Tampa FL 33620 USA Univ South Florida USF Ctr Innovat Technol & Aging CITA Tampa FL 33620 USA

Picking up multiple objects at once is a grasping skill that makes a human worker efficient in many domains. This work tackles the problem of getting a requested number of identical objects in a shallow bin by only pick once (OPO) using a simple parallel gripper. The proposed system contains several graph-based algorithms that convert the layout of objects into a graph, cluster vertices in the graph, rank and select candidate clusters based on their topology. Our algorithm also has a multi-object picking predictor based on a convolutional neural network for estimating how many objects would be picked up with a given gripper location and orientation. This paper presents four evaluation metrics and three protocols to evaluate the proposed system. The results show that our proposed system has very high success rates for two and three objects when only picking once. Utilizing our approach can significantly outperform single object picking two to three times in terms of efficiency. The results also show our algorithm can be applied to one unseen shape (hexagon) and unseen sizes cube and cylinder during training without fine-tuning to achieve decent accuracy. Note to Practitioners-This paper is motivated by the current bottleneck in robotics picking which restricts the mass deployment of robots in tasks that are similar to batch-picking in logistics. The state of the art (SOTA) picking algorithm is fast but only focuses on picking one object at a time, which inspires us to look into picking multiple objects at once to increase the efficiency. We design a custom-sized parallel-jaw gripper based on the object sizes' need, and we train a deep-learning model for each designed gripper to predict the number of objects that a grasp pose can retrieve. Our simulation and real-life evaluations have very good results in picking 2 to 3 objects at once in a random setting. Our future work will consider more complex scenarios and rearrangements that can break some hard settings.

关键词： Robots Grippers Grasping Shape clustering algorithms Training Solid modeling Prediction algorithms Pneumatic systems Layout Intelligent robots intelligent manufacturing systems grasping

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Feature Extraction Technique for Single Document Summarization Using Hybrid Optimization Technique

引用

IEEE ACCESS 2025年 13卷 24515-24529页

作者： Rautaray, Jyotirmayee Panigrahi, Sangram Nayak, Ajit Kumar Sahu, Premananda Mishra, Kaushik Siksha O Anusandhan Univ Inst Tech Educ & Res Dept Comp Sci & Engn Bhubaneswar Odisha India Siksha O Anusandhan Univ Inst Tech Educ & Res Dept Comp Sci & Informat Technol Bhubaneswar Odisha India Lovely Profess Univ Sch Comp Sci & Engn Phagwara Punjab India Manipal Acad Higher Educ Manipal Inst Technol Bengaluru Dept Comp Sci & Engn Manipal India

Presently, the exponential growth of unstructured data on the web and social networks has made it increasingly challenging for individuals to retrieve relevant information efficiently. Over the years, various text summarization techniques have been developed to address this issue. However, traditional approaches that rely on directly extracting words often lead to redundancies and fail to establish a strong connection between the summary and the original document. This paper presents a novel Deep Learning (DL)-based text summarization approach incorporating the following phases: pre-processing, feature extraction, vectorization, and summarization using a hybrid Cat Swarm Optimization (CSO) and Harris Hawk Optimization (HHO) algorithm. Initially, input documents undergo pre-processing steps, including sentence segmentation, word tokenization, stop word removal, and lemmatization, to enhance text quality. Features are then extracted using a Restricted Boltzmann Machine (RBM) to obtain nine key attributes. Vectorization is performed using Term Frequency-Inverse Document Frequency (TF-IDF) to represent sentences in vector form. The hybrid CSO-HHO algorithm is subsequently applied to generate summaries. The proposed method's efficiency was evaluated using datasets from the Document Understanding Conference (DUC), specifically DUC-2002, DUC-2003, and DUC-2005. Metrics such as sensitivity, readability, coherence, precision, BLEU score, ROUGE score, and F-score were analyzed to assess performance. The proposed approach's results were compared with existing methods, including CSO, QABC, PSO, GJO, FF, and machine learning techniques like SVM and RF. The hybrid CSO-HHO algorithm achieved an accuracy of 99.56%, demonstrating its superiority in text summarization tasks.

关键词： Optimization Feature extraction Text summarization Particle swarm optimization Genetic algorithms clustering algorithms Support vector machines Deep learning Data mining Computer science single document summarization pre-processing feature extraction vectorization hybrid CSO-HHO algorithm

来源：评论

学校读者我要写书评

暂无评论

Deep-Reinforcement-Learning-Based Continuous Workflows Scheduling in Heterogeneous Environments

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第10期12卷 14036-14050页

作者： Wang, Zhi Zhan, Wenhan Duan, Hancong Min, Geyong Huang, Hualong Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Univ Exeter Coll Engn Math & Phys Sci Dept Comp Sci Exeter EX4 4QF England

Workflow scheduling plays a critical role in optimizing completion time and throughput in distributed cloud environments, leveraging the parallelism of heterogeneous computing resources. However, existing workflow scheduling algorithms often fall short due to heuristic limitations and the challenges in adaptability within heterogeneous settings, leading to suboptimal scheduling solutions. In this article, we present a novel deep reinforcement learning (DRL) framework tailored for continuous workflow scheduling in heterogeneous environments. First, we propose an intelligent scheduler that updates the policy network through interactions with a multitenant environment, triggered by scheduling events. Next, the framework incorporates a graph attention network (GAT) and a self-attention multilayer perceptron (MLP) to preprocess the workflow topology and embed dynamic features of ready tasks and available processors into the state input at each scheduling step. Additionally, a k-dimensional tree-based k-nearest neighbors (kNN) algorithm is employed to map the output action vector to a pair of executed ready task and processor, facilitating the transition from continuous to discrete action spaces and addressing challenges associated with dynamic action spaces. Experimental results demonstrate that our method converges effectively in continuous workflow scheduling scenarios and significantly outperforms the best-known methods in terms of average makespan and load balancing efficiency.

关键词： Processor scheduling Program processors Scheduling Heuristic algorithms Costs clustering algorithms Scheduling algorithms Internet of Things Dynamic scheduling Computational efficiency Cloud computing continuous workflows deep reinforcement learning (DRL) graph attention network (GAT) workflow scheduling

来源：评论

学校读者我要写书评

暂无评论

Enhancing SR-Tree for Nearest Neighbor Search

引用

IEEE ACCESS 2025年 13卷 63324-63333页

作者： Abduaziz, Kayumov Lee, Shincheol Shin, Ji Sun Sejong Univ Dept Comp & Informat Secur & Convergence Engn Inte Seoul 05006 South Korea Sejong Univ Dept Comp & Informat Secur Seoul 05006 South Korea

Nearest neighbor search, also known as k-nearest neighbors (kNN), has become one of the essential backbones in machine learning and data mining tasks, particularly in multidimensional dynamic and evolving data environments. While dynamic index structures have been extensively utilized for indexing dynamic data, their performance in nearest neighbor search can further be improved. This paper aims to enhance SR-Tree as it has been shown to be effective for indexing high dimensional clustered data. We propose enhancements to SR-Tree structure to better handle multidimensional data and reduce query processing time. First, we improve SR-Tree using a variance-based bulk-loading algorithm to build an efficient tree structure. Second, we apply the approximation of the smallest enclosing ball and leaf-level pruning methods to improve performance of kNN queries. Third, we adapt the dual-tree algorithm for SR-Tree that outperforms sequential queries for the all-nearest neighbors problem in low-to-medium dimensional large datasets. These improvements were evaluated using real-world datasets across varying dimensionalities by comparing against several freely available indexing structure frameworks. Experimental results indicated considerable speedup over the state-of-the-art dynamic index implementation in nearest neighbor retrieval across high-dimensional conditions. This work also provides an open-source implementation of our enhancements to SR-Tree for the Rust ecosystem.

关键词： Nearest neighbor methods Indexes Heuristic algorithms Indexing clustering algorithms Approximation algorithms Information security High dimensional data Computer security Sun Nearest-neighbor search kNN similarity indexing

来源：评论

学校读者我要写书评

暂无评论

An Efficient Large-Scale 3D Map Stitching Algorithm Using Automatic Overlapping Area Identification

引用

IEEE ACCESS 2025年 13卷 42587-42607页

作者： Lin, Hsien-, I Ahsan Fatwaddin Shodiq, Muhammad Jeng, An-Kai Chang, Chun-Wei Natl Yang Ming Chiao Tung Univ Inst Elect & Control Engn Hsinchu 30010 Taiwan Ind Technol Res Inst Hsinchu 310401 Taiwan

Quality of 3D point cloud maps is essential for navigation and localization in Autonomous Mobile Robots, yet creating these maps for large-scale areas presents challenges, stemming from the processing of numerous points. In such situations, constructing a 3D map can be accomplished by dividing it into smaller regions and then merging them to generate a complete map by performing a 3D map stitching algorithm. Currently, these overlapping areas are manually selected, which leads to potential errors. In response, a novel method to automatically identify overlapping areas is proposed to perform map stitching based on the overlapping areas only instead of the entire maps. Utilizing the proposed method results in a significant reduction in time consumption. The proposed automatic method incorporates the DBSCAN algorithm for clustering, template matching for identifying corresponding clusters, and a binary-search algorithm for parameter optimization. The proposed method was evaluated on several large-scale 3D maps, including the KITTI dataset, and compared against manual selection and the use of entire maps in the map-merge-3D algorithm. The method achieves a significant reduction in the time required for the 3D map stitching process, amounting to a 38.64% decrease compared to using the entire maps. In terms of accuracy, the proposed method reduces translation error to 0.1723m and rotation error to 0.1763 degrees, representing decreases of 5.28% and 16.16%, respectively, while manual selection results in a translation error of 0.4278m and rotation error of 0.7123 degrees, increases of 135.25% and 238.75% respectively, compared to the entire maps 0.1819m and 0.2103 degrees.

关键词： Three-dimensional displays clustering algorithms Point cloud compression Noise Correlation Elbow Accuracy Shape Sensors Optimization 3D map stitching point cloud map DBSCAN template matching binary-search algorithm

来源：评论

学校读者我要写书评

暂无评论

Y-Graph: A Max-Ascent-Angle Graph for Detecting Clusters

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第1期37卷 542-556页

作者： Guan, Junyi Li, Sheng He, Xiongxiong Chen, Jiajia Zhao, Yangyang Zhang, Yuxuan Hangzhou Normal Univ Sch Informat Sci & Technol Hangzhou 311121 Peoples R China Zhejiang Univ Technol Coll Informat Engn Hangzhou 310023 Peoples R China

Graph clustering technique is highly effective in detecting complex-shaped clusters, in which graph building is a crucial step. Nevertheless, building a reasonable graph that can exhibit high connectivity within clusters and low connectivity across clusters is challenging. Herein, we design a max-ascent-angle graph called the "Y-graph", a high-sparse graph that automatically allocates dense edges within clusters and sparse edges across clusters, regardless of their shapes or dimensionality. In the graph, every point x is allowed to connect its nearest higher-density neighbor delta, and another higher-density neighbor gamma, satisfying that the angle angle delta x gamma is the largest, called "max-ascent-angle". By seeking the max-ascent-angle, points are automatically connected as the Y-graph, which is a reasonable graph that can effectively balance inter-cluster connectivity and intra-cluster non-connectivity. Besides, an edge weight function is designed to capture the similarity of the neighbor probability distribution, which effectively represents the density connectivity between points. By employing the Normalized-Cut (Ncut) technique, a Ncut-Y algorithm is proposed. Benefiting from the excellent performance of Y-graph, Ncut-Y can fast seek and cut the edges located in the low-density boundaries between clusters, thereby, capturing clusters effectively. Experimental results on both synthetic and real datasets demonstrate the effectiveness of Y-graph and Ncut-Y.

关键词： clustering algorithms Merging Buildings Shape Couplings Resource management Costs Tuning Symmetric matrices Standards Complex-shaped clusters normalized-cut graph clustering

来源：评论

学校读者我要写书评

暂无评论

High-Throughput Barcode Fluorescence Sensor Signal Rapid Processing: Integration of Multiple algorithms and Visualization Implementation

引用

IEEE SENSORS JOURNAL 2025年第2期25卷 3348-3357页

作者： Wang, Baole Geng, Qingfubo Zhan, Weihe Geng, Zhaoxin Minzu Univ China Sch Informat Engn Beijing 100081 Peoples R China Minzu Univ China Sch Informat Engn Key Lab Ethn Language Intelligent Anal & Secur Gov Beijing 100081 Peoples R China

The field of fluorescence barcode sensor signal processing is the focus, with the development of a high-throughput fluorescence detection visualization platform that integrates multiple efficient fluorescence array localization algorithms, including manual mask positioning, an optimized k-means++ algorithm, and a projection iterative algorithm designed based on fluorescence image projection data. Comprehensive monitoring, real-time adjustment, and integrated data analysis are enabled by the platform, significantly enhancing the accuracy, speed, and convenience of fluorescence image processing. Experimental results demonstrate that the projection iterative algorithm excels in both accuracy and processing speed, achieving a mean squared error (mse) of 6.42130, which is 20.97% lower than that of the k-means++ algorithm, and a processing time of 1095 ms, which is 80.21% and 94.37% faster than the mask positioning and k-means++ algorithms, respectively. Furthermore, evaluation of different fitting algorithms shows that sigmoid curve fitting performs best across various metrics, with an R-2 value as high as 0.987480, indicating excellent data interpretability and fitting accuracy. Overall, precise, rapid, and efficient signal processing in high-throughput fluorescence detection is achieved, providing robust technical support and innovative tools for related research fields.

关键词： Fluorescence Sensors Accuracy Software systems Gray-scale Noise clustering algorithms Signal processing algorithms Sensor arrays Image sensors Barcode biochip fluorescence image high throughput sensor signal software design

来源：评论

学校读者我要写书评

暂无评论

Viewpoint Generation Algorithm for Gimbal-Mounted Robots for Visual Inspection of Civil Engineering Structures

引用

IEEE ACCESS 2025年 13卷 40813-40823页

作者： Haneda, Masaya Wu, Weitong Funabora, Yuki Doki, Shinji Doki, Kae Nagoya Univ Grad Sch Engn Dept Elect Engn & Comp Sci Nagoya Aichi 4648603 Japan Aichi Inst Technol Dept Elect & Elect Engn Toyota Aichi 4700392 Japan

We propose a viewpoint generation algorithm for the visual inspection of civil engineering structures using robots equipped with a gimbal-mounted camera. This algorithm enables robots to completely inspect target surfaces at the required spatial resolution while reducing movement by effectively utilizing the gimbal. Previous studies generally assume that the camera is always oriented orthogonally to the target surface, and they focus on the inspection position optimization problem, resulting in the underutilization of gimbals and heavy movement of robots. In this study, firstly we have formulated the conditions under which the collected data's quality does not deteriorate in terms of damage detection, and we have relaxed the orthogonal measuring restrictions. Based on the conditions, we propose a viewpoint generation algorithm that can carry out inspection work by changing measurement orientations instead of moving the robot. In simulation experiments, our method reduces inspection time by 47.7% compared to the benchmark method for the same tasks of inspecting a pier surface with the required spatial resolution. In addition, the viewpoint generation time was reduced by 96.8% compared to the benchmark method. We also conducted experiments in real environments using pan-tilt heads and confirmed that our algorithm can collect data qualified for the damage detection of visual inspections.

关键词： Inspection Cameras Spatial resolution Visualization Autonomous aerial vehicles Planning Data collection Robot vision systems clustering algorithms Classification algorithms Surface inspection coverage path planning (CPP) autonomous robots remote sensing condition monitoring data collection

来源：评论

学校读者我要写书评

暂无评论

Subsurface Temperature and Salinity Structures Inversion Using a Stacking-Based Fusion Model from Satellite Observations in the South China Sea

引用

Advances in Atmospheric Sciences 2025年第1期42卷 204-220页

作者： Can LUO Mengya HUANG Shoude GUAN Wei ZHAO Fengbin TIAN Yuan YANG Frontier Science Center for Deep Ocean Multispheres and Earth System(FDOMES)and Physical Oceanography Laboratory/Key Laboratory of Ocean Observation and Information of Hainan Province Sanya Oceanographic InstitutionOcean University of ChinaQingdao 266100/Sanya 572000China Laoshan Laboratory Qingdao 266237China

Three-dimensional ocean subsurface temperature and salinity structures(OST/OSS)in the South China Sea(SCS)play crucial roles in oceanic climate research and disaster ***,real-time OST and OSS are mainly obtained through in-situ ocean observations and simulation by ocean circulation models,which are usually challenging and ***,dynamical,statistical,or machine learning models have been proposed to invert the OST/OSS from sea surface information;however,these models mainly focused on the inversion of monthly OST and *** address this issue,we apply clustering algorithms and employ a stacking strategy to ensemble three models(XGBoost,Random Forest,and LightGBM)to invert the real-time OST/OSS based on satellite-derived data and the Argo ***,a fusion of temperature and salinity is employed to reconstruct OST and *** the validation dataset,the depth-averaged Correlation(Corr)of the estimated OST(OSS)is 0.919(0.83),and the average Root-Mean-Square Error(RMSE)is0.639°C(0.087 psu),with a depth-averaged coefficient of determination(R~2)of 0.84(0.68).Notably,at the thermocline where the base models exhibit their maximum error,the stacking-based fusion model exhibited significant performance enhancement,with a maximum enhancement in OST and OSS inversion exceeding 10%.We further found that the estimated OST and OSS exhibit good agreement with the HYbrid Coordinate Ocean Model(HYCOM)data and BOA_Argo dataset during the passage of a mesoscale *** study shows that the proposed model can effectively invert the real-time OST and OSS,potentially enhancing the understanding of multi-scale oceanic processes in the SCS.

关键词： subsurface temperature and salinity structures clustering algorithms stacking strategy temperature and salinity fusion the South China Sea

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：