检索结果-内蒙古大学图书馆

F-F Diagram: A Two-Dimensional Surrogate Safety Indicator Based on Field Theory for Lane Change Risk Assessment

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年

作者： Liu, Zhenyu Xiang, Qiaojun Southeast Univ Sch Transportat Jiangsu Key Lab Urban ITS Nanjing 211189 Jiangsu Peoples R China

Unsafe lane change behaviors have negative impacts on traffic safety. Identifying these risky patterns can help drivers make safe lane change decisions. In this paper, we develop a two-dimensional indicator based on field theory to evaluate lane change risks on the highway. The driving risk field is constructed by integrating the individual and interaction features of the source vehicle and the interacting vehicle. Parameter calibration with highD trajectory data allows the risk field forces to objectively reflect the risk perception. An adaptive optimization algorithm with cumulative gradient bias correction is introduced for parameter calibration. The enhanced first-order and second-order momentum, along with the long-term memory, are developed to adaptively adjust the learning rate and prune abnormal gradients. A Gaussian mixture model is applied to cluster the calibrated two-dimensional risk indicators, generating the F-F diagram. Experimental results demonstrate the superiority of the proposed driving risk field model and the gradient-based algorithm. Confidence region estimation of the lane change risk distribution further validate the objectivity and interpretability of the F-F diagram. The 95% confidence level offers valuable insights for proactive traffic safety management, and lays a foundation for developing personalized lane change strategies. In the future, the F-F diagram could be integrated into lane change advisory systems or advanced driving assistance systems, helping drivers make informed lane change decisions.

关键词： Accidents Trajectory Force Calibration Indexes Driver behavior Risk management clustering algorithms Videos Vehicle dynamics Lane change risk driving risk field gradient bias correction vehicle trajectory F-F diagram

来源：评论

学校读者我要写书评

暂无评论

An Efficient FPGA Implementation of Approximate Nearest Neighbor Search

引用

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS 2025年第6期33卷 1705-1714页

作者： Song, Yifeng Liu, Chenjie Zhang, Rongrong Zhu, Danyang Wang, Zhongfeng Nanjing Univ Sch Elect Sci & Engn Nanjing 210023 Peoples R China PrimeAI Ltd Nanjing 210023 Peoples R China Sun Yat Sen Univ Sch Integrated Circuits Shenzhen 518107 Peoples R China

Approximate nearest neighbor search (ANNS) plays an important role in modern artificial intelligence (AI) systems, being extensively utilized in search engines, advertising, and recommendation systems. With the advent of large language models (LLMs), ANNS is increasingly finding applications in edge scenarios such as personal assistants. The demand for efficient and fast ANNS solutions is, therefore, more pressing than ever. In this article, we propose a scalable and efficient field-programmable gate array (FPGA) implementation of ANNS based on the inverted file with product quantization (IVF-PQ) algorithm, thus marking the first hardware implementation supporting up to 1024-D datasets. First, we devise a novel architecture for the Top-K module, capable of processing multiple input data streams simultaneously and linearly increasing throughput. Second, we adjust the data precision in several parts of our design, thus achieving obvious performance improvement without losing much recall. Moreover, we introduce a flexible distance calculation (Distance Cal) module that can be reused for various computational tasks at different query stages. We code our design in Verilog and implement it on Xilinx Alveo U280. The experimental results show that our search latency can be as low as 0.0071 ms at a 94% recall, while the power is 19.80 W. Compared to the state-of-the-art application-specified integrated circuit (ASIC) implementations, our design delivers a 4.5x speedup in latency and a 20% reduction in energy consumption.

关键词： Vectors Indexes Field programmable gate arrays Databases Hardware Artificial intelligence Codes Quantization (signal) clustering algorithms Approximation algorithms Approximate nearest neighbor search (ANNS) field-programmable gate array (FPGA) hardware inverted file with product quantization (IVF-PQ)

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Cooperative Cache Strategy Integrating Content Recommendation in IoV

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第2期74卷 2080-2093页

作者： Liang, Yan Zhang, Haijun Ma, Hui Wang, Lina Wang, Xianmei Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China

As the proliferation of in-vehicle information services continues to grow, the size of cached content expands, consequently extending the caching duration for vehicle users. Internet of Vehicles (IoV) technology can provide a multitude number of communication services between vehicles and Roadside Units (RSUs), making vehicle cooperative caching a viable solution. Nevertheless, for new energy vehicles such as electric ones, how to reduce the energy consumption of the vehicle network system remains a formidable challenge. Additionally, the task delay of vehicle cooperative caching can also be further reduced. In this paper, a clustering caching model is proposed by considering constraints for tolerable delay of tasks and the residence time of vehicles, and the kinetic energy recovery scheme of vehicles and the Energy Harvesting (EH) mechanism of RSUs are designed to reduce the system energy consumption. Terahertz (THz) communication is employed in vehicle to vehicle (V2V) to accelerate the completion of tasks. Subsequently, the energy consumption optimization problem for the vehicle cooperative caching system is constructed. Furthermore, the continuity and high-dimensionality properties of the decision variables for the optimization problem are analyzed, and we propose the joint Download Size and Bandwidth Allocation (DSBA) algorithm to explore an approximate optimal solution for task decomposition and resource allocation in the high-dynamic environment. We also propose an algorithm named Vehicle Cache Content Recommendation (VCCR) to avoid the additional delay and the waste of energy caused by the vehicle user cache miss-hit problem. The simulation results demonstrate that our proposed algorithms have significant advantages in saving task delay and system energy consumption compared to other solutions.

关键词： Delays Terahertz communications Cooperative caching Optimization Energy consumption Resource management clustering algorithms Internet of Vehicle (IoV) resource allocation vehicle cooperative cache deep reinforcement learning recommendation system

来源：评论

学校读者我要写书评

暂无评论

Evaluation of K-Means Algorithm for Faulted Landforms Extraction and Offset Measurement With an Example From the Eastern Kunlun Fault

引用

IEEE ACCESS 2025年 13卷 47848-47859页

作者： Zhou, Shengchao Lin, Zhou Zhejiang Univ Sch Earth Sci Hangzhou 310012 Peoples R China

Accurate offset measurement is crucial for recovering the size of past earthquakes and understanding the recurrence patterns of strike-slip faults. Traditional methods, which rely on manual delineation of displaced geomorphic markers from satellite images, often introduce significant uncertainties. This study aims to develop a more objective and accurate method for identifying faulted landforms and measuring offsets. Although supervised deep learning methods have great potential for image recognition and segmentation, due to the absence of data sets, we apply the K-means algorithm, an easy and practical unsupervised machine learning method with minimal parameters, to extract displaced geomorphic markers. Our research is conducted in the Kusai Lake segment of the Eastern Kunlun Fault using high-resolution satellite imagery. Initially, we identify multiple well-preserved geomorphic markers along the fault traces and manually label some to form an imagery dataset. The K-means algorithm demonstrates its efficacy in extracting landforms clearly when the classification number is set to three. Furthermore, a quantitative comparison of several commonly used unsupervised algorithms confirmed that K-means performs best, achieving a recall of 0.70 and an accuracy of 0.906 on the dataset. The validity of our measurements is corroborated by examining two specific sites around Hongshui Gou. Quantitative analysis comparing our imagery-based measurements with field data reveals a strong agreement, evidenced by a Pearson's correlation coefficient of 0.997. Repeated measurements of the same geomorphic markers across different images indicate that the geomorphic features obtained from the images significantly affect the accuracy of offset measurements. This study underscores the potential of our approach for both extracting faulted landforms and accurately measuring their offsets, emphasizing the importance of assessing the integrity of geomorphic markers when using satellite imagery

关键词： Satellite images Earthquakes Lakes Seismic measurements Fault diagnosis Accuracy clustering algorithms Vectors Geologic measurements Machine learning Strike-slip fault offset measurement K-means algorithm Eastern Kunlun fault

来源：评论

学校读者我要写书评

暂无评论

DCMM: Dynamic Cluster-Based Mobile Node Migration Scheme for Blockchain Collaborative Storage in Mobile IoT Networks

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第2期12卷 584-598页

作者： Peng, Kai Liao, Tongxin Liao, Xi Xie, Jiangshan Xu, Bo Deng, Tianping Hu, Menglan Huazhong Univ Sci & Technol Sch Elect Informat & Commun Hubei Key Lab Smart Internet Technol Wuhan 430074 Peoples R China

As blockchain technology becomes widely adopted in Mobile Internet of Things (MIoT) networks, the growing volume of blockchain data significantly increases storage pressure on peer nodes. Collaborative storage, which distributes blockchain data across nodes in cluster, offers a promising solution. However, the frequent movement of mobile nodes disrupts cluster structures, and existing static solutions fail to address this dynamic nature, rendering them ineffective. To address this issue, we propose a Dynamic Cluster-based Mobile Node Migration Scheme (DCMM), comprising two key components: new cluster selection and block redistribution. The Dynamic Node Synchronization Algorithm (DNSA) optimizes cluster selection, and the Dynamic Block Allocation Algorithm (DBAA) manages efficient block redistribution. Comparative analysis with five baseline approaches shows that DCMM improves performance by over 16.69% in the weighted optimization objective, which considers access costs, migration costs, and dwell times. These results demonstrate that our approach significantly optimizes network costs compared to baseline algorithm.

关键词： Collaboration Heuristic algorithms Costs Blockchains Internet of Things Vehicle dynamics Dynamic scheduling Resource management clustering algorithms Mobile nodes Blockchain MIoT network collaborative storage data migration

来源：评论

学校读者我要写书评

暂无评论

Cooperative Path Planning of Multiple Unmanned Aerial Vehicles Using Cylinder Vector Particle Swarm Optimization With Gene Targeting

引用

IEEE SENSORS JOURNAL 2025年第5期25卷 8470-8480页

作者： Huang, Chen Ma, Hongjiang Zhou, Xiangbing Deng, Wu Shenyang Aerosp Univ Coll Civil Aviat Shenyang 110136 Peoples R China Yibin Univ Sch Big Data & Artificial Intelligence Yibin 644000 Peoples R China Sichuan Tourism Univ Sch Informat & Engn Chengdu 610100 Peoples R China Civil Aviat Univ China Coll Elect Informat & Automat Tianjin 300300 Peoples R China

Cooperative route planning is crucial to ensure safe and effective flight of unmanned aerial vehicle (UAV) formation. Complicated scenarios, however, put forward new challenges for path planning of multiple UAVs;therefore, a novel cylindrical coordinate particle swarm optimization (PSO) planner with gene targeting (GTCPSO) is presented to obtain feasible and accurate flight routes for multiple UAVs. In the GTCPSO planner, to satisfy UAV dynamic characteristics, the cylindrical coordinate is exploited to represent the flight route;the PSO algorithm with cylindrical coordinates can quickly find a feasible trajectory in a complex environment. Meanwhile, by incorporating gene targeting (GT) operation into improved cylindrical coordinate PSO, the bottleneck waypoint in the global best trajectory is found by waypoint detection, and then the detected bottleneck waypoint is modified by the adjustment operation based on two-phase the updating strategy. A series of experiments based on real map examples on multi-sensors are designed to test the search capability of this GTCPSO planner. The simulation results indicate that the proposed planner GTCPSO has the potential to handle multi-UAV cooperative planning problems under complex constraints.

关键词： Autonomous aerial vehicles Costs Vectors Sensors Radar Planning Heuristic algorithms Search problems clustering algorithms Trajectory Cylinder vector gene targeting multiple unmanned aerial vehicles (UAVs) multisensors particle swarm optimization (PSO) path planning

来源：评论

学校读者我要写书评

暂无评论

A Novel Color Difference-Based Method for Palette Extraction and Evaluation Using Images of Birds

引用

IEEE ACCESS 2025年 13卷 52270-52283页

作者： Kosesoy, Melike Bektas Yilmaz, Seckin Bursa Tech Univ Grad Sch Dept Comp Engn TR-16310 Yildirim Bursa Turkiye Kocaeli Univ Fac Engn Dept Software Engn TR-41001 Izmit Kocaeli Turkiye Bursa Tech Univ Fac Engn & Nat Sci Dept Comp Engn TR-16310 Yildirim Bursa Turkiye

Color palettes are important sources of inspiration for designers. In most coloring studies, designers and interior architects use ready-made color palettes that are known to be harmonious and popular with clients. In this study, a new color palette extraction and evaluation method is proposed that differs from existing methods because it accelerates designers' product coloring processes by identifying the color-area and color-neighborhood relationship. Furthermore, attractive color palettes will be identified by focusing on living creatures, primarily colorful birds. For this purpose, a new data set of images of birds was created. In the literature, the success of color palettes is usually evaluated through questionnaires, while measurements are made without relying on numerical metrics. In this study and, for the first time, a new metric based on CIEDE2000 and the Hungarian algorithm to measure the accuracy of color palettes is demonstrated. In the proposed method birds are first segmented from background using Mask R-CNN and PointRend models. Then, Fuzzy c-means (FCM), Gaussian Mixture Model (GMM), k-means, Mean Shift, and mini batch k-means algorithms were used to extract the color palette of each bird image. Color reduction based on the CIEDE2000 was performed on the color palettes using various threshold values, resulting in the final color palettes. In the last step, color-area and color-neighborhood relationships are shown through graph-based color palettes. Experimental results showed that the PointRend method, with a 93.92% success rate, produced the most successful results. However, k-means and GMM methods were more successful in extracting the colors of birds. The evaluation of the palettes was performed with the proposed numerical metric rather than questionnaires, resulting in more robust and repeatable findings. Furthermore, the proposed graph-based color palette results in considerably simplified coloring process by reducing the computational complex

关键词： Image color analysis Birds clustering algorithms Accuracy Color Image segmentation Feature extraction Generative adversarial networks Gaussian mixture model Data mining CIEDE2000 color difference color palette extraction clustering algorithms Hungarian algorithm

来源：评论

学校读者我要写书评

暂无评论

Resilient Fusion of LMB Densities Based on Medoids

引用

IEEE SENSORS JOURNAL 2025年第6期25卷 10370-10379页

作者： Zhou, Yao Gao, Lin Li, Gaiyou Wei, Ping Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

This article deals with the problem of resilient fusion of labeled multi-Bernoulli (LMB) densities, which arises in the situation that the sensor network (SN) undergoes abnormal behaviors like malicious attacks, resulting in the change of transmitted data from each sensor node. Compared to fusion algorithms based on perfect SN conditions, a detection procedure should be deployed before performing fusion so as to exclude abnormal data. To this end, we propose to decompose the LMB densities as the union of Bernoulli components (BCs), and then the medoids of BCs are exploited to form the fused LMB density. Besides, a new density-based spatial clustering of applications with noise (DBSCAN)-based label-matching algorithm is proposed. The performance of the proposed algorithm is verified via simulations.

关键词： Sensors Sensor fusion clustering algorithms Target tracking Radio frequency Filtering algorithms Noise Matched filters Information theory Filtering theory Labeled multi-Bernoulli (LMB) medoid multiobject fusion random finite set resilient algorithm

来源：评论

学校读者我要写书评

暂无评论

A Power-and-Area-Efficient Channel-Interleaved Neural Signal Processor for Wireless Brain-Computer Interfaces With Unsupervised Spike Sorting

引用

IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2025年第1期19卷 108-119页

作者： Hu, Zichen Zhou, Zhining Lyu, Hongming ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China Chinese Acad Sci Shanghai Inst Microsyst & Informat Technol Shanghai 200050 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China ShanghaiTech Univ State Key Lab Adv Med Mat & Devices Shanghai 201210 Peoples R China Shanghai Engn Res Ctr Energy Efficient & Custom AI Shanghai 201210 Peoples R China

Next generation of wireless brain-computer-interface (BCI) devices require dedicated neural signal processors (NSPs) to extract key neurological information while operating within given power consumption and transmission bandwidth limits. Spike detection and clustering are important signal processing steps in neuroscience research and clinical applications. Computational-friendly spike detection and feature extraction algorithms are first systematically evaluated in this work. The nonlinear energy operator (NEO) and the first-and-second-derivative (FSDE) together with the 'perturbed' K-mean clustering achieve the highest accuracy performance. An NSP ASIC is implemented in a channel-interleaved architecture and the folding ratio of 16 leads to the minimum power-and-area product. As the result, the NSP consumes 2-mu W power consumption and occupies 0.0057 mm(2) for each channel in a 65-nm CMOS technology. The proposed system achieves the unsupervised spike classification accuracy of 92% and a data-rate reduction of 98.3%, showing the promise for realizing high-channel-count wireless BCIs.

关键词： Feature extraction Signal processing algorithms Wireless communication clustering algorithms Bandwidth Noise level Hardware Neural signal processing spike detection feature extraction unsupervised clustering spike sorting ASIC channel-interleaving CMOS low-power hardware-efficiency

来源：评论

学校读者我要写书评

暂无评论

Interpretability-Oriented Adjustment of K-Means: A Multiple-Objective Particle Swarm Optimization Framework

引用

IEEE ACCESS 2025年 13卷 68084-68096页

作者： Chen, Liang Sun, Leming Zhong, Caiming Ningbo Univ Coll Sci & Technol Cixi 315000 Peoples R China

clustering is an unsupervised machine learning technique used to partition unlabeled data into different groups. However, traditional clustering methods only provide a set of results without any explanations. While numerous methods in the literature attempt to explain clustering results, the explanation rules provided by these models are fixed and sacrificing clustering quality for the sake of making the rules easier to understand. To address this, this paper proposes a feature selection model to balance the interpretability and clustering quality. The model consists of two stages. In the first stage, the concept of explanatory radius is defined, and the explanatory radius of each cluster in the initial clustering results is calculated. In the second stage, a feature subspace is selected, and the dataset is re-clustered in this subspace using a proposed formula to obtain a new clustering result. Three objective functions are designed to evaluate the performance of the new clustering results in terms of cluster quality and interpretability. Subsequently, the model utilizes a multi-objective optimization framework to optimize the three objective functions in the solution space formed by different feature subspaces, resulting in a set of Pareto solutions. Each solution in the Pareto set represents a trade-off between clustering quality and interpretability. Finally, the contribution of features during the generation process of each cluster is used to represent the interpretability of each cluster's result. The proposed method is validated on both artificial datasets and real-world datasets, and comparative analyses are conducted with the latest explainable clustering algorithms in the literature. The analysis results demonstrate the effectiveness of the proposed method.

关键词： clustering algorithms Optimization Linear programming Machine learning algorithms Decision trees Prediction algorithms Particle swarm optimization Vectors Prototypes Feature extraction Feature selection interpretability K-means clustering

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：