检索结果-内蒙古大学图书馆

Graph-Based Approach for Industrial Market Segmentation Using Financial Transaction Network Structure and Firm's Attribute

引用

IEEE ACCESS 2025年 13卷 16394-16412页

作者： Bose, Aparajita Kim, Byunghoon Hanyang Univ Dept Ind & Management Engn Ansan 15588 South Korea

Market segmentation is a challenging and necessary task for improving marketing strategies and allocating resources effectively in a complex scenario of industrial or business-to-business (B2B) markets. Most of the traditional methods have not provided comprehensive and detailed guidelines for processing massive, complex, and complicated data from financial transactions in industrial markets. Furthermore, they often overlook the overlapping nature of segments, where a firm might belong to multiple market segments. Financial transaction networks (FTNs) can be depicted as graphs, where nodes and edges represent firms and transactions, respectively. A limited number of network analysis studies have been employed for industrial market analysis, but those efforts failed to capture the important features of financial transactions, such as the number of transactions, transaction volume, direction of transactions, and firm-specific attributes. In this study, we propose a novel method for industrial market segmentation that utilizes both financial multiple transactions and an attribute of firms. By integrating a graph-based generative probabilistic model, we reveal and understand the complex and overlapping relationships within financial transaction data. Subsequently, we apply the proposed method to a real-world dataset. The results show that the proposed method outperforms established methods in network analysis, such as clustering and community detection in transactional industrial market (B2B) networks.

关键词： Network analyzers Probabilistic logic Optimization Industries Codes clustering algorithms Systematic literature review Standards Resource management Couplings Industrial market segmentation financial transaction network analysis graph transaction network and firms' attribute graph-based market analysis interfirm relationship

来源：评论

学校读者我要写书评

暂无评论

Commonality Feature Representation Learning for Unsupervised Multimodal Change Detection

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2025年 34卷 1219-1233页

作者： Liu, Tongfei Zhang, Mingyang Gong, Maoguo Zhang, Qingfu Jiang, Fenlong Zheng, Hanhong Lu, Di Shaanxi Univ Sci & Technol Shaanxi Joint Lab Artificial Intelligence Xian 710021 Peoples R China Xidian Univ Key Lab Collaborat Intelligent Syst Minist Educ Xian 710071 Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

The main challenge of multimodal change detection (MCD) is that multimodal bitemporal images (MBIs) cannot be compared directly to identify changes. To overcome this problem, this paper proposes a novel commonality feature representation learning (CFRL) and constructs a CFRL-based unsupervised MCD framework. The CFRL is composed of a Siamese-based encoder and two decoders. First, the Siamese-based encoder can map original MBIs in the same feature space for extracting the representative features of each modality. Then, the two decoders are used to reconstruct the original MBIs by regressing themselves, respectively. Meanwhile, we swap the decoders to reconstruct the pseudo-MBIs to conduct modality alignment. Subsequently, all reconstructed images are input to the Siamese-based encoder again to map them in a same feature space, by which representative features are obtained. On this basis, latent commonality features between MBIs can be extracted by minimizing the distance between these representative features. These latent commonality features are comparable and can be used to identify changes. Notably, the proposed CFRL can be performed simultaneously in two modalities corresponding to MBIs. Therefore, two change magnitude images (CMIs) can be generated simultaneously by measuring the difference between the commonality features of MBIs. Finally, a simple threshold algorithm or a clustering algorithm can be employed to divide CMIs into binary change maps. Extensive experiments on six publicly available MCD datasets show that the proposed CFRL-based framework can achieve superior performance compared with other state-of-the-art approaches.

关键词： Feature extraction Image reconstruction Training Data mining Autoencoders Representation learning Image sensors Electronic mail Decoding clustering algorithms Multimodal change detection unsupervised change detection heterogeneous images representation learning commonality feature

来源：评论

学校读者我要写书评

暂无评论

Indoor-outdoor interactive thermal response in public building:onsite data collection and classification through cluster algorithm

引用

ENERGY AND BUILDINGS 2025年 328卷

作者： Jin, Zhineng Zhang, Yin Sun, Hongli Han, Meng Zheng, Yanhong Zhao, Ying Han, Wenyang Zhang, Menglong Xu, Bin Zhang, Zequn Lin, Borong Sichuan Univ Coll Architecture & Environm Chengdu 610065 Peoples R China Southwest Minzu Univ Sch Architecture Chengdu 610225 Peoples R China Sichuan Univ State Key Lab Hydraul & Mt River Engn Chengdu Peoples R China China Architecture Design & Res Grp Land Based Rationalism DRC Beijing 100044 Peoples R China Tsinghua Univ Coll Architecture Beijing 100083 Peoples R China

Efficient thermal environment control in large public buildings with atria is critical for reducing energy consumption and carbon emissions. This study investigates the indoor thermal environments of two distinct atria in Suining, China, within a Hot Summer and Cold Winter (HSCW) climate zone. A novel methodology combining Kmeans clustering algorithms and multiple linear regression (CAMLR) was employed to analyze extensive thermal data from a transitional atrium and a traditional atrium. CAMLR significantly outperformed Traditional Building Thermal environment analysis Methods (TBTM), achieving a 33.8 % higher R2 and reducing the residual sum of squares by 62.11 %. Key findings include: 1) A strong correlation (R2 = 0.9555) between outdoor temperature and indoor thermal conditions in the transitional atrium, highlighting a critical outdoor temperature threshold of 30 degrees C that leads to prolonged indoor heat retention. 2) Solar radiation plays a dominant role in the traditional atrium (R2 = 0.5584), influencing rapid temperature fluctuations. These insights underscore the critical role of atrium design in optimizing thermal performance and energy efficiency. Compared to TBTM, CAMLR provides faster, more accurate, and highly visualized data analysis, making it particularly suitable for complex thermal environment studies. This study establishes CAMLR as a robust tool for advancing thermal management strategies in large public buildings, offering practical guidance for energy-efficient architectural designs in similar climate zones.

关键词： clustering algorithms Public buildings Thermal environment Energy efficiency Indoor-outdoor interaction

来源：评论

学校读者我要写书评

暂无评论

Joint Augmentation and Part Learning for Unsupervised Clothing Change Person Re-Identification

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 2944-2956页

作者： Pang, Zhiqi Zhao, Lingling Liu, Yang Sharma, Gaurav Wang, Chunyu Harbin Inst Technol Fac Comp Harbin 150001 Peoples R China Univ Rochester Dept Elect & Comp Engn Rochester NY 14627 USA

Clothing change person re-identification (CC-ReID) is a crucial task in intelligent surveillance, aiming to match images of the same person wearing different clothing. Promising performance in existing CC-ReID methods is achieved at the cost of labor-intensive manual annotation of identity labels. While some researchers have explored unsupervised CC-ReID, these methods still depend on additional deep learning models for preprocessing. To eliminate the need for additional models and improve performance, we propose a joint augmentation and part learning (JAPL) framework that obtains clothing change positive pairs in an unsupervised fashion by synergistically combining augmentation-based invariant learning (AugIL) and part-based invariant learning (ParIL). AugIL first constructs clothing change pseudo-positive pairs and then encourages the model to focus on clothing-invariant information by enhancing feature consistency between the pseudo-positive pairs. ParIL beneficially encourages high similarity between inter-cluster clothing change positive pair using part images and a prediction sharpening loss. PartIL also introduces a soft consistency loss that promotes clothing-invariant feature learning by encouraging consistency of class vectors between the real features actually used for CC-ReID and the part features. Experimental results on multiple ReID datasets demonstrate that the proposed JAPL not only surpasses existing unsupervised methods but also achieves competitive performance compared to some supervised CC-ReID methods.

关键词： Clothing Shape Optimization Identification of persons Costs Feature extraction clustering algorithms Cameras Surveillance Deep learning Unsupervised learning contrastive learning clustering algorithm clothing change person re-identification

来源：评论

学校读者我要写书评

暂无评论

Two-Round Optimization Algorithm Based on Quadric Error Metrics

引用

IEEE ACCESS 2025年 13卷 30021-30035页

作者： Chang, Han Zhang, Di Dong, Yanan Yang, Yijun Shafiq Ur Rehman Khalil, Hafiz Wang, Xueting Xi An Jiao Tong Univ Sch Human Settlement & Civil Engn Dept Architecture Xian 710049 Peoples R China Xi An Jiao Tong Univ Sch Comp Sci & Technol Xian 710049 Peoples R China

Triangular mesh models are widely used for 3D model displays, but large models can cause slow loading and transmission, especially on mobile or web platforms. The quadric error metrics (QEM) algorithm is known for its efficient simplification and effectiveness. Nevertheless, it lacks clear prioritization for folding flat areas within the model, leaving room for improvement. This paper reproduces the work of Zhang Yun et al., finding that while their method reduces simplification errors, it increases the folding time of flat areas. The study improves the QEM algorithm by combining the angle and area of the first-order neighboring triangles of the edge, resulting in faster simplification but higher errors, making it less versatile. To address these issues, a two-round simplification method is proposed. The first round simplifies planar areas, and the second focuses on the entire model. Compared to the recursive algorithm, the two-round method showcases shorter simplification times, particularly evident when the *** exhibits a lower simplification ratio. For simplification rates below 40%, it reduces the average simplification time by 22.77% and yields better model accuracy than the QEM algorithm. On bunny_***, the simplification error is smaller than with the QEM algorithm, showcasing an average error reduction of 21.82%. Visually, the two-round proposed algorithm retains more detailed features and has better visual effects. However, because of the lower computational efficiency of the two-round simplification, future research directions may involve parallel computing and GPU utilization for acceleration.

关键词： Approximation algorithms Solid modeling Three-dimensional displays Vectors Measurement uncertainty Costs Faces Load modeling Computational modeling clustering algorithms Quadric error metrics two-round proposed algorithm first-order neighborhood triangle area approximate curvature

来源：评论

学校读者我要写书评

暂无评论

RAPO: An Automated Performance Optimization Tool for Redis Clusters in Distributed Storage Metadata Management

引用

IEEE ACCESS 2025年 13卷 58060-58074页

作者： Zhu, Yunkai Xia, Tian Zhu, Te Zhao, Zhoujie Li, Kexin Hu, Xingbo East China Normal Univ Sch Commun & Elect Engn Shanghai 200241 Peoples R China Chinese Univ Hong Kong Sch Data Sci Shenzhen 518172 Guangdong Peoples R China

Distributed storage systems are well-equipped to address the demands of massive data storage and rapid access in the era of big data. However, as the scale of these systems continues to expand, challenges related to data localization, performance optimization, and secure access have become increasingly prominent, making effective metadata management critically important. Redis, a memory-based NoSQL (Not only SQL) database, has emerged as an ideal choice for metadata management in distributed storage systems due to its high performance, flexible data structures, excellent scalability, and robust data persistence mechanisms. This study employs Redis as the caching layer for metadata services in distributed storage systems and develops the Redis-cluster Automatic Performance Optimizer (RAPO) to enhance performance. By implementing load balancing among main nodes and read-write separation between main and secondary nodes, the tool aims to improve the metadata service performance of Redis clusters during system maintenance and in high-concurrency scenarios. To address load balancing among main nodes, the research defines the Load Balance Index (LBI) as a metric for evaluating the degree of load distribution within the cluster. Greedy and random iterative search algorithms are designed to migrate hash slots from selected nodes, thereby balancing the node loads and enhancing overall cluster performance. By optimizing with the greedy and random iterative search algorithms, the cluster's LBI was reduced by an average of 29.36% and 25.20% respectively during random read operations and by 24.98% and 24.03% respectively during imbalanced write operations. A load threshold is defined to achieve read-write separation between main and secondary nodes. Random allocation, round-robin, weighted round-robin, and smooth weighted round-robin are employed to optimize the read-write separation. Experimental results demonstrate that the weighted round-robin and smooth weighted round-robin

关键词： Metadata Load management Main-secondary Optimization Distributed databases clustering algorithms Synchronization Resource management Indexes Cloud computing Distributed storage metadata management Redis cache load balancing read-write separation

来源：评论

学校读者我要写书评

暂无评论

Chaotic Initialization Particle Filter AUV Cluster Position Calibration Algorithm Based on Intragroup Distance Measurement Under Large Initial Position Error

引用

IEEE JOURNAL OF OCEANIC ENGINEERING 2025年第2期50卷 1140-1152页

作者： Zhang, Qingyu Fu, Jin Zou, Nan Qi, Bin Fan, Yuan Hang Harbin Engn Univ Natl Key Lab Underwater Acoust Technol Harbin 150001 Peoples R China Harbin Engn Univ Key Lab Marine Informat Acquisit & Secur Minist Ind & Informat Technol Harbin 150001 Peoples R China Harbin Engn Univ Coll Underwater Acoust Engn Harbin 150001 Peoples R China Beihang Univ Coll Elect Informat Engn Beijing 100191 Peoples R China

With the increasing diversity and complexity of maritime mission requirements, the technology of collaborative multiautonomous underwater vehicles (AUVs) has garnered widespread attention. In this domain, the positional calibration technology of AUV clusters is an integral aspect that cannot be overlooked. Traditional leader-follower AUV cluster positional calibration models and algorithms have utilized information from either a single leader AUV or multiple leader AUVs in conjunction with a single follower AUV. However, with the expansion of the scale of follower AUVs, the availability of follower-follower AUV information increases. Consequently, this article develops a novel AUV cluster positional calibration model that leverages both the distance information between leader and follower AUVs, and the follower-follower AUV distance information. The observability of this model is analyzed, and building upon this, a chaos-initialized particle filter algorithm for AUV cluster positional calibration is proposed. Finally, experiments are conducted to compare the performance of the algorithm presented in this article with the particle filtering algorithm under different initial error conditions. The results demonstrate that the proposed algorithm exhibits stable convergence speed and calibration error at low initial errors. At high initial errors, it achieves faster convergence, lower calibration error within a finite time, and enhanced stability.

关键词： Calibration Observability clustering algorithms TV Accuracy Location awareness Distance measurement Position measurement Vectors Sea measurements Array position calibration autonomous underwater vehicles (AUVs) cluster chaotic mapping particle filter (PF)

来源：评论

学校读者我要写书评

暂无评论

POSR: Pose-Aligned Outlier Sample Relabeling for Unsupervised Person Reidentification

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Yu, Hang Fan, Huijie Chen, Xiai Wang, Qiang Han, Zhi Shenyang Univ Chem Technol Sch Informat Engn Shenyang 110142 Peoples R China Chinese Acad Sci Shenyang Inst Automat State Key Lab Robot Shenyang 110016 Peoples R China Shenyang Univ Key Lab Mfg Ind Integrated Automat Shenyang 110003 Peoples R China

Unsupervised person reidentification (Re-ID) is crucial since it enables the matching of individuals without labeled data. Existing clustering-based methods directly discard outlier samples. However, these discarded outliers are not noise samples. In contrast, they are some high-quality samples that are especially meaningful for implementing Re-ID cross-camera retrieval. To capitalize on the diversity of data, we propose a pose-aligned outlier sample relabeling (POSR) model to relabel these outliers to mine diverse data representations for accurate cross-camera retrieval. POSR consists of a pose-aligned feature learning (PFL) module and a biclustering outlier relabeling (BOR) module. The PFL module learns pose features with fine-grained information about human joint points by dynamically matching tokens and obtains the pose-aligned feature via average pooling. The pose-aligned features can compensate for the limitations of global features obtained through the transformer encoder for alignment processing. Therefore, the BOR module is proposed to relabel outlier samples through the complementarity of pose-aligned features and global features, which can learn ID-consistent representations and achieve more robust performance for cross-camera retrieval of unsupervised Re-ID by training meaningful outlier samples. Extensive experiments on three datasets demonstrate the effectiveness of our method and significantly improve Re-ID accuracy.

关键词： Training Accuracy Pedestrians Identification of persons clustering algorithms Cameras Transformers Representation learning Pose estimation Data mining Outlier sample person reidentification (Re-ID) pose-aligned feature relabeling unsupervised learning (USL)

来源：评论

学校读者我要写书评

暂无评论

A Noise-Adaptive Machine Learning Framework for Optimizing User Grouping in Dynamic IM-OFDMA Systems

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2025年第3期73卷 1862-1878页

作者： Ay, Fahrettin Althunibat, Saud Qaraqe, Khalid A. Kurban, Hasan Texas A&M Univ Dept Elect & Comp Engn College Stn TX 77840 USA Al Hussein Bin Talal Univ Dept Commun Engn Maan 71111 Jordan Texas A&M Univ Qatar Dept Elect & Comp Engn Doha Qatar Hamad Bin Khalifa Univ Coll Sci & Engn Doha Qatar

This paper addresses the challenge of optimizing user grouping in Index Modulation-based Orthogonal Frequency-Division Multiple Access (IM-OFDMA) systems within dynamic and stochastic noise environments. Utilizing the eXtreme Gradient Boosting (XGBoost) machine learning algorithm, we devised a framework capable of accurately predicting the optimality of user groupings across varying Signal-to-Noise Ratio (SNR) levels. Six models corresponding to different noise conditions were created, showcasing adaptability to adjacent noise levels via distribution shift handling, thereby ensuring robust performance across a wide noise spectrum. To accurately identify the most appropriate optimality prediction model for dynamic environments, we introduced a specialized model for precisely estimating the system's internal noise power. The accuracy of this model is crucial for the selection process and was significantly enhanced by implementing sequential Bayesian updating, facilitating a more precise estimation of internal noise power. Following this, we introduced a provisional optimization algorithm designed to refine user groupings within dynamic IM-OFDMA systems. Simulation results highlight the algorithm's effectiveness in markedly improving system performance, evidenced by a significant decrease in bitrate errors. These findings illuminate the significant potential of applying machine learning strategies to wireless communication systems, providing insightful contributions to the enhancement of IM-OFDMA systems in practical settings.

关键词： Heuristic algorithms Predictive models NOMA Table lookup Signal to noise ratio clustering algorithms Adaptation models Index modulation IM-OFDMA user grouping machine learning noisy data extreme gradient boosting XGBoost

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Blind Signal Detection for Ambient Backscatter Communication Systems

引用

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2025年第2期11卷 1172-1183页

作者： Zhu, Han Zhan, Jiamiao Lam, Chan-Tong Chen, Bidong Ng, Benjamin K. Macao Polytech Univ Fac Appl Sci Macau Peoples R China Baosight Software Nanchang Co Ltd Prod Res & Dev Dept Nanchang 330199 Peoples R China

Ambient backscatter communication (AmBC) is emerging as a promising energy-saving and spectrum-efficient passive Internet of Things (IoT) technology that can be used for battery-less communication devices due to its low power consumption and cost constraints. However, in AmBC systems, recovering tag information at the reader is a challenging problem due to the difficulty in obtaining relevant channel state information (CSI). In this paper, we propose a variational Bayesian inference and machine learning (VBI-ML) based blind signal detection method, which can automatically recover tag information in AmBC systems. Firstly, two known labels are transmitted from the tag to the reader before valid data is transmitted, thus eliminating the need for CSI estimation. Secondly, we use the VBI approach with the Gaussian mixture model to obtain the real constellation information, which does not require a priori signal modulation technology to recover the tag information at the reader automatically. Using real constellation information, the signal detection problem is converted into a clustering problem. Finally, we cluster all the received signals using an improved expectation maximization algorithm in ML to learn the parameters in labeled and unlabeled signals and recover the signals. Thorough simulation results demonstrate that our proposed method performs similarly to the optimal detector with perfect CSI and outperforms traditional constellation learning methods. More critically, ML algorithms can mitigate direct link interference and simplify the number of estimated parameters.

关键词： Radio frequency Signal detection Detectors Backscatter clustering algorithms Internet of Things Modulation Ambient backscatter communication blind signal detection expectation maximization algorithm Gaussian mixture model variational Bayesian inference

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：