检索结果-内蒙古大学图书馆

Evaluating infant development through a novel hybrid intuitionistic fuzzy classification system

APPLIED SOFT COMPUTING 2025年 169卷

作者： Hsu, Ya-Chi Lin, Ting-Yu Lin, Kuo-Ping Tsan, Yu-Tse Hung, Kuo-Chen Tunghai Univ Dept Ind Engn & Enterprise Informat Taichung Taiwan Taichung Vet Gen Hosp Childrens Med Ctr Div Neonatol Taichung Taiwan Univ Econ Ho Chi Minh City Sch Accounting Ho Chi Minh Vietnam Taichung Vet Gen Hosp Dept Emergency Med Div Occupat Med Taichung Taiwan Chung Shan Med Univ Sch Med Taichung Taiwan Hungkuang Univ Dept Multimedia Game Dev & Applicat Taichung Taiwan

Preterm birth is a global public health concern, necessitating efficient and accurate neurodevelopmental assessments. This study firstly attempts that develops a novel hybrid classification system combining clustering algorithms, intuitionistic fuzzy sets (IFSs), and classification methods to improve neurodevelopmental assessments for preterm infants by analyzing growth trends between 6 months and 1 year of age. The proposed system integrates clustering techniques, including k-means (KM), fuzzy C-means (FCM), and kernel FCM (KFCM), with IFSs to address the vagueness in growth data. These clusters are then classified using advanced algorithms, such as long short-term memory networks (LSTM), support vector machines (SVM), K-nearest neighbours (KNN), naive Bayes (NB), and backpropagation neural networks (BPNN), to predict cognitive, language, and motor outcomes at 1 year old. Experimental results demonstrated that the KFCM+IFS+LSTM approach achieved the highest accuracy (average cognitive score: 0.95) and robustness (low variability) compared to other methods. The LSTM models consistently outperformed KNN and BPNN, which showed weaker and less consistent results. This hybrid system offers a scalable and precise solution for assessing neurodevelopment in very low birth weight preterm infants, reducing reliance on resource-intensive specialist evaluations and advancing early childhood healthcare methodologies.

关键词： Infant development clustering algorithms Intuitionistic fuzzy sets Hybrid system Healthcare Prematurity

来源：评论

学校读者我要写书评

暂无评论

Gas Leak Real-Time Detection and Volume Flow Quantification Based on Infrared Imaging and Advanced algorithms

引用

IEEE ACCESS 2025年 13卷 7284-7292页

作者： Yan, Man Li, Zhou Dong, Zheng Liun, Yiming Chen, Liyun Wu, Xiaosong Wu, Lijun South China Normal Univ Sch Informat & Optoelect Sci & Engn Guangdong Prov Key Lab Nanophoton Funct Mat & Dev Guangzhou 510006 Guangdong Peoples R China Guangzhou Keii Electro Opt Technol Co Ltd Guangzhou 510663 Peoples R China

Due to the semi-transparent and irregular nature of gases, it is still a highly challenging task to effectively detect and quantify gas leaks especially those with small flow rates by only utilizing economical equipments. In this paper, we present a strategy for automating real-time identification and quantification of gases in the mid-infrared band by combining an infrared camera combined with a series optimized algorithms. A basic network DeepLabV3+ is first modified by replacing its Xception backbone with MobileNetv2 for real-time gas detection and segmentation. Then special attention mechanisms tailored to the characteristics of the gas are added into the network to enhance the perception and recognition of the gas edges. The optimized Kmeans clustering algorithm is integrated to identify the Region of Interest (ROI) in the image containing the target gas. The quantification of the volume flow rate within the ROI is realized by integrating the radiation transfer model with the optical flow method. The experimental results indicate that the quantification limit of the gas flow rate can reach 0.01 L/min, which is comparable to that obtained by the methods with complicated instruments. Our detection and quantification strategy can find vast applications in hazardous gas monitoring field.

关键词： Cameras Gases Accuracy Real-time systems Training Optical filters Image edge detection clustering algorithms Gas lasers Fluid flow Gas identification gas quantification DeeplabV3+neural network Kmeans clustering algorithm optical flow method

来源：评论

学校读者我要写书评

暂无评论

Multi-View Graph-Based Hierarchical Representation Learning for Money Laundering Group Detection

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 2035-2050页

作者： Li, Zhong Yang, Xueting Jiang, Changjun Donghua Univ Coll Informat Sci & Technol Shanghai 201620 Peoples R China Minist Educ Key Lab Embedded Syst & Serv Comp Shanghai 201804 Peoples R China Tongji Univ Dept Comp Sci & Engn Shanghai 201804 Peoples R China

Anti-money laundering (AML) is crucial to maintaining national financial security. Contemporary AML methods focus on homogeneous mining or unitary money laundering pattern. These methods ignore a characteristic of gang operation in money laundering. Thus, in this paper, we propose a multi-view graph-based hierarchical representation learning method, named MG-HRL, to mine organized money laundering groups. In particular, we extract multi-level representations of transaction subgraphs, including transaction features, user features, structural features, and high-order association features from multiple observational perspectives. To learn the correlation between users, we model transaction networks as heterogeneous information networks (HINs) and design six meta-paths related to money laundering scenarios to mine correlations among users. Combining with correlation representations of users, we propose a heterogeneous hypergraph representation learning method to learn high-order representations of transaction subgraphs. Through hierarchical representation learning, the MG-HRL achieves full exploration of money laundering groups. Finally, we conduct experiments on two public transaction datasets. The result shows that MG-HRL method performs better than other state-of-the-art baselines.

关键词： Feature extraction Automated machine learning Representation learning Correlation Stars Transformers Encoding clustering algorithms Bidirectional control Topology Anti-money laundering money laundering group detection correlation mining hierarchical representation learning heterogeneous hypergraph

来源：评论

学校读者我要写书评

暂无评论

Automated clustering of Video Games into Groups with Distinctive Names 23rd

Automated Clustering of Video Games into Groups with Disti...

引用

23rd IFIP TC 14 International Conference on Entertainment Computing, ICEC 2024

作者： Grelier, Nicolas Kaufmann, Stéphane Pullup Entertainment Paris France

ISBN: (纸本)9783031743528

When doing a study on a large number of video games, it may be difficult to cluster them into coherent groups to better study them. In this paper, we introduce a novel algorithm, that takes as input any set of games S that are released on Steam and an integer k, and cluster S into k groups. Each group is then assigned a distinctive name in the form of a Steam tag. We believe our tool to be valuable for gaining deeper insights into the video game market. Our algorithm consistently achieves high scores on an objective function that we introduce, the naming score, which assesses the quality of a clustering and how distinctive its name is. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Auto-Weighted Multi-View Deep Non-Negative Matrix Factorization With Multi-Kernel Learning

引用

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS 2025年 11卷 23-34页

作者： Yang, Xuanhao Che, Hangjun Leung, Man-Fai Liu, Cheng Wen, Shiping Southwest Univ Coll Elect & Informat Engn Chongqing 400715 Peoples R China Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China Anglia Ruskin Univ Fac Sci & Engn Sch Comp & Informat Sci Cambridge CB1 1PT England Shantou Univ Dept Comp Sci Shantou 515063 Guangdong Peoples R China Univ Technol Sydney Australian Artificial Intelligence Inst Fac Engn & Informat Technol Sydney NSW 2007 Australia

Deep matrix factorization (DMF) has the capability to discover hierarchical structures within raw data by factorizing matrices layer by layer, allowing it to utilize latent information for superior clustering performance. However, DMF-based approaches face limitations when dealing with complex and nonlinear raw data. To address this issue, Auto-weighted Multi-view Deep Nonnegative Matrix Factorization with Multi-kernel Learning (MvMKDNMF) is proposed by incorporating multi-kernel learning into deep nonnegative matrix factorization. Specifically, samples are mapped into the kernel space which is a convex combination of several predefined kernels, free from selecting kernels manually. Furthermore, to preserve the local manifold structure of samples, a graph regularization is embedded in each view and the weights are assigned adaptively to different views. An alternate iteration algorithm is designed to solve the proposed model, and the convergence and computational complexity are also analyzed. Comparative experiments are conducted across nine multi-view datasets against seven state-of-the-art clustering methods showing the superior performances of the proposed MvMKDNMF.

关键词： Kernel Data models Matrix decomposition Vectors Manifolds Information processing clustering algorithms Adaptation models Optimization Computational modeling Multi-view clustering deep matrix factorization multi-kernel learning

来源：评论

学校读者我要写书评

暂无评论

Federated Contrastive Learning With Feature-Based Distillation for Human Activity Recognition

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2025年

作者： Xiao, Zhiwen Tong, Huagang Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Nanjing Tech Univ Coll Econ & Management Nanjing 211816 Peoples R China

This article proposes a federated contrastive learning with feature-based distillation (FCLFD) framework tailored for human activity recognition (HAR). The FCLFD system integrates a central server with multiple mobile users to address a diverse range of HAR challenges. The framework encompasses two pivotal elements: a contrastive student--teacher (CST) architecture with feature-based distillation and an average weight scheme (AWS). The CST framework facilitates the transfer of comprehensive knowledge from a teacher model to a student model through feature-based distillation and contrastive learning, with both models sharing an identical architecture. Each participating user periodically uploads the weights of its student model to the central server, where the AWS deployed on the server calculates the average weights based on contributions from all connected users. The aggregated weights are then redistributed to each user, who updates their teacher model accordingly. Experimental evaluations demonstrate that when 50 users are connected, the proposed FCLFD scheme obtains the highest F-1 values of 89.01 and 94.19, outperforming several state-of-the-art federated learning algorithms on the wireless sensor data mining (WISDM) and PAMAP2 datasets.

关键词： Data models Feature extraction Computational modeling Human activity recognition Semantics Fuzzy logic Servers Training Hidden Markov models clustering algorithms Contrastive learning (CL) federated learning (FL) human activity recognition (HAR) knowledge distillation (KD) wearable sensor

来源：评论

学校读者我要写书评

暂无评论

Perception Assisted Transformer for Unsupervised Object Re-Identification

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2025年 34卷 2112-2123页

作者： Chen, Shuoyi Ye, Mang Dong, Xingping Du, Bo Wuhan Univ Inst Artificial Intelligence Natl Engn Res Ctr Multimedia Software Sch Comp SciHubei Key Lab Multimedia & Network Co Wuhan 430072 Peoples R China

Unsupervised object re-identification (Re-ID) aims to learn discriminative features without identity annotations. Existing mainstream methods are usually developed based on convolutional neural networks for feature extraction and pseudo-label estimation. However, convolutional neural networks suffer from limitations in capturing dispersed long-range dependencies and integrating global information. In comparison, vision transformers demonstrate superior robustness in complex environments, leveraging their versatile modeling capabilities to process diverse data structures with greater precision. In this paper, we delve into the potential of vision transformers in unsupervised Re-ID, proposing a Transformer-based perception-assisted framework (PAT). Considering Re-ID is a typical fine-grained task, existing unsupervised Re-ID methods relying on pseudo-labels generated by clustering algorithms provide only category-level discriminative supervision, with limited attention to local details. Therefore, we propose a novel target-aware mask alignment (TMA) strategy that provides additional supervision signals by leveraging low-level visual cues. Specifically, we employ pseudo-labels to guide the fine-grained alignment of features with local pixel information from critical discriminative regions. This method establishes a mutual learning mechanism via a shared Transformer, effectively balancing discriminative learning and detailed understanding. Furthermore, we propose a perceptual fusion feature augmentation (PFA) method to optimize instance-level discriminative learning. The proposed method is evaluated on multiple Re-ID datasets, demonstrating superior performance and robustness in comparison to state-of-the-art techniques. Notably, without annotations, our method achieves better results than many supervised counterparts. The code will be released.

关键词： Transformers Computer vision Training Feature extraction Contrastive learning Visualization Convolutional neural networks Image reconstruction Robustness clustering algorithms Person re-identification (Re-ID) unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification

引用

IEEE ACCESS 2025年 13卷 54611-54621页

作者： Chen, Jiayi Ma, Yanbiao Dai, Wei Chen, Xiaohua Li, Shuo Xidian Univ Sch Telecommun Engn Xian 710071 Peoples R China Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with noisy and biased data, the model's representation network is more reliable than the classification network. Additionally, label generation methods based on model predictions often show poor adaptability across different datasets, necessitating customization of the classification network. Therefore, we propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. We also introduce an adaptive method for selecting hyperparameters in HDL, enhancing its versatility. Moreover, HDL can be combined with general image encoders (e.g., CLIP) to serve as a fundamental data processing module. We extract embeddings from datasets with class-balanced and long-tailed distributions using pre-trained semi-supervised models. Subsequently, samples are re-labeled using HDL, and the re-labeled samples are used to further train the semi-supervised models. Experiments demonstrate improved model performance, validating the motivation that representation networks are more reliable than classifiers or predictors. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.

关键词： Predictive models Labeling Semisupervised learning Hardware design languages clustering algorithms Annotations Heuristic algorithms Adaptation models Training Data models Image classification representational learning semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

ClusPar: A Game-Theoretic Approach for Efficient and Scalable Streaming Edge Partitioning

引用

IEEE TRANSACTIONS ON COMPUTERS 2025年第1期74卷 116-130页

作者： Ding, Zezhong Kong, Deyu Zhang, Zhuoxu Xie, Xike Xu, Jianliang Univ Sci & Technol China USTC Sch Artificial Intelligence & Data Sci Hefei 230026 Peoples R China USTC Suzhou Inst Adv Res Data Darkness Lab Suzhou 215123 Peoples R China USTC Sch Software Engn Suzhou 215123 Peoples R China Hong Kong Univ Sci & Technol Guangzhou Guangzhou 511453 Peoples R China USTC Suzhou Inst Adv Res Suzhou 215123 Peoples R China Hong Kong Baptist Univ Dept Comp Sci Hong Kong 999077 Peoples R China

Streaming edge partitioning plays a crucial role in the distributed processing of large-scale web graphs, such as pagerank. The quality of partitioning is of utmost importance and directly affects the runtime cost of distributed graph processing. However, streaming graph clustering, a key component of mainstream streaming edge partitioning, is vertex-centric. This incurs a mismatch with the edge-centric partitioning strategy, necessitating additional post-processing and several graph traversals to transition from vertex-centric clusters to edge-centric partitions. This transition not only adds extra runtime overhead but also risks a decline in partitioning quality. In this paper, we propose a novel algorithm, called ClusPar, to address the problem of streaming edge partitioning. The ClusPar framework consists of two steps, streaming edge clustering and edge cluster partitioning. Different from prior studies, the first step traverses the input graph in a single pass to generate edge-centric clusters, while the second step applies game theory over these edge-centric clusters to produce partitions. Extensive experiments show that ClusPar outperforms the state-of-the-art streaming edge partitioning methods in terms of the partitioning quality, efficiency, and scalability.

关键词： Partitioning algorithms clustering algorithms Runtime Computers Costs Memory management Computational efficiency Games Transforms Synchronization Distributed graph system streaming edge partitioning parallelization

来源：评论

学校读者我要写书评

暂无评论

Dynamic Event-Triggered Cluster Consensus of Multi-Agent Systems via PSO-GA Co-Design

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 11505-11518页

作者： Yang, Yanping Shen, Bo Ge, Xiaohua Li, Shenrong Han, Qing-Long Donghua Univ Coll Informat Sci & Technol Shanghai 201620 Peoples R China Donghua Univ Engn Res Ctr Digitized Text & Apparel Technol Minist Educ Shanghai 201620 Peoples R China Swinburne Univ Technol Sch Engn Melbourne Vic 3122 Australia

This paper is concerned with cluster consensus of multi-agent systems (MASs) with homogeneous and heterogeneous dynamics. Firstly, a resilient dynamic event-triggered (RDET) mechanism is proposed by introducing two parameters in the dynamic triggering threshold to describe busy and free networks of each cluster. An auxiliary function is configurated to describe the network status of agents in different clusters. Agents allocated in multiple clusters are classified into two categories: some agents are in the busy network environment and the rest are in the free network environment. The resulting consensus error system is modeled as an augmented system involving two time-varying delays with different bounds. Then, some sufficient criteria are derived for the stability analysis of homogeneous and heterogeneous MASs, respectively. Based on the obtained stability criteria, an algorithm consisting of particle swarm optimization (PSO) and a genetic algorithm (GA) is designed for a co-design of control gains and event-triggered parameters. Finally, a numerical example of satellite formation flying is simulated to illustrate the merits of the developed theoretical results.

关键词： Vehicle dynamics Event detection Linear matrix inequalities Genetic algorithms Symmetric matrices Laplace equations Delays Collaboration clustering algorithms Optimization Dynamic event-trigger cluster consensus resilient control homogeneous and heterogeneous dynamics

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：