检索结果-内蒙古大学图书馆

A Novel Channel Pruning Lightweight Pig Face Detection Method Based on Augment Group Diverse Attention Mechanism

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Xu, Shuiqing Yi, Wenhao Shen, Juan Tao, Songbing Wang, Hai Chai, Yi Chen, Hongtian Hefei Univ Technol Sch Elect Engn & Automat Hefei 230009 Peoples R China Anhui Xinhua Univ Sch Big Data & Artificial Intelligence Hefei 230088 Peoples R China Murdoch Univ Discipline Engn & Energy Perth WA 6150 Australia Chongqing Univ Coll Automat Chongqing 400044 Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China

Pig face detection plays a pivotal role in the intelligent management of pig farms. This study proposes a novel lightweight pig face detection model, named channel pruning pig face detection method based on augment group diverse attention mechanism (CPADA). First, to overcome the adverse effects of pig face smudges occlusion and significant intraclass variations on the detection performance, this article innovatively proposes an attention module named augment group diverse attention (ADA). Subsequently, in order to compress the size of the pig face detection model while preserving its detection capability as much as possible, this article designs an efficient channel pruning method. Furthermore, based on the pruning margin for each layer, a hierarchical pruning strategy is designed to mitigate the impact of "layer collapse" phenomenon on the detection capability of the pruned model. The experimental results confirm the effectiveness of our proposed ADA attention method for pig face detection task and also validate that the proposed channel pruning and hierarchical pruning strategy outperform other state-of-the-art pruning methods at the same pruning rate. Furthermore, from the practical implementation perspective, the pruned models are deployed on the Raspberry Pi 4B edge computing platform, achieving nearly five times space compression and nearly four times inference speed improvement on edge devices.

关键词： Face detection Attention mechanisms Face recognition Computational modeling Training Electronic mail YOLO Edge computing Complexity theory classification algorithms Augment group diverse attention (ADA) channel pruning hierarchical pruning strategy pig face detection

来源：评论

学校读者我要写书评

暂无评论

Quantum Computer-Generated Holography

引用

IEEE ACCESS 2025年 13卷 83643-83649页

作者： Shimobaba, Tomoyoshi Wang, Fan Ito, Tomoyoshi Chiba Univ Grad Sch Engn Yayoi ChoInage Ku Chiba 2638522 Japan

Hologram calculations pose a significant challenge for future holographic displays with extensive fields of view and wide viewing angles. Classical computers may encounter difficulties with these owing to immense computational demands. This study introduces quantum computer-generated holography (QGH) as a viable solution. QGH employs a point-cloud algorithm in which point-cloud data are represented by the superposition states of qubits, and lightwave interactions on the hologram are calculated using principles of quantum mechanics. QGH can accelerate hologram computation by a factor of 10(6) in a 1 tera-pixel hologram from 1 tera-object points, compared to classical computer-generated holography. The study discusses advantages, limitations, and future directions.

关键词： Quantum computing Qubit Three-dimensional displays Holography Computers Registers Logic gates Hamming weight Point cloud compression classification algorithms Computer-generated hologram hologram holographic display holography quantum computing

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modeling of Cyberattack Defense Mechanism Using Hybrid Transfer Learning With Snow Ablation Optimization Algorithm in Critical Infrastructures

引用

IEEE ACCESS 2025年 13卷 13329-13340页

作者： Ishak, Mohamad Khairi Ajman Univ Coll Engn & Informat Technol Dept Elect & Comp Engn Ajman U Arab Emirates

Cybersecurity is a significant topic that has turned into an efficient one at present owing to the increasing dependency on interconnected methods and technology. As digitalization upsurges, the requirement for cybersecurity measures becomes even more vital for numerous networks. To certify the security of critical infrastructures, numerous cyber security solutions must be taken together and the essential infrastructure must be developed. Industrial control methods are one of the most vital aspects of the cybersecurity of critical infrastructures. It is possible to entirely stop these physically located devices' operations and do substantial destruction with a cyberattack. Whereas AI solutions are being utilized in numerous fields, cyber security has started to become one of the concentrated fields of artificial intelligence (AI) domain. Consequently, there are many studies on identifying cyberattacks by utilizing AI methods. It is probable to utilize AI to help and support cybersecurity solutions to develop cybersecurity of significant infrastructures. This study develops a Cyberattack Defense Mechanism using Hybrid Transfer Learning with Snow Ablation Optimization Algorithm (CDMHTL-SAOA) technique in Critical infrastructures. The main cause of the CDMHTL-SAOA model is to improve the cyber security maturity level of critical infrastructures and inspect both traditional cyberattack and AI approaches. Primarily, the data normalization process can be implemented to scale the raw data into a uniform format. In addition, the snow ablation optimization (SAO) algorithm can be exploited for the optimum choice of feature subsets. For the cybersecurity classification process, the presented CDMHTL-SAOA technique applies the hybrid of convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) method. Eventually, the parameter choice of the CNN-BiLSTM technique has been implemented by the design of the hippopotamus optimization algorithm (HOA). To repre

关键词： Snow Computer security Security Cyberattack Artificial intelligence Optimization Critical infrastructure classification algorithms Transfer learning Vectors hybrid transfer learning snow ablation optimization hyperparameter selection data normalization

来源：评论

学校读者我要写书评

暂无评论

Waterfall: Fast Network Flow Rules Checking and Conflict Resolution

引用

IEEE TRANSACTIONS ON NETWORKING 2025年第2期33卷 881-896页

作者： Vadnere, Neha Huang, Dijiang Sabur, Abdulhakim Luo, Jim Zhao, Ming Arizona State Univ Sch Comp & Augmented Intelligence SCAI Tempe AZ 85281 USA Taibah Univ Coll Comp Sci & Engn Dept Cybersecur Madinah 42353 Saudi Arabia US Naval Res Lab Washington DC 20375 USA

Software Defined Networking (SDN) enables a centralized manageable framework to control network devices and their policies using device-specific flow rules. When administrators deploy flow rules to support business policies, the network controller checks them against existing rules to detect conflicts and ensure consistency, security, and functionality in the data plane. Existing offline conflict detection methods are not scalable due to state explosion and often lead to networking chaos due to inefficiency. This paper presents Waterfall, designed to minimize the number of flow rule-checking operations. We propose a novel Equivalence Class (EC) creation and prioritization technique that simplifies conflict detection by organizing rules with similar patterns and processing them accordingly. Analogous to a multi-stage waterfall, our algorithm optimizes downstream stages by reducing unnecessary comparisons, ensuring efficient conflict detection. Our comprehensive evaluation demonstrates Waterfall's effectiveness through significant reductions in computation time (O(mKH), where $m$ is the number of matched flow-rules which is far less than the total number of flow-rules, K is the number of attributes (headers) in flow rules, H is the number of hash functions in Bloom filter for attribute matching), making it ideal for real-time flow rule checking and conflict resolution in SDN environments. In our evaluation, Waterfall achieved a remarkable 1.3X improvement in conflict detection and 4.4X improvement for conflict resolution over the state-of-the-art solution for the Stanford topology which is a popular topology to represent real-world networking scenarios. We also evaluate the scalability of the solution using a synthetic dataset containing 15K flow rules that have three virtual network functions. Our solution achieved a 90.53 mu conflict detection and resolution time for the large synthetic dataset. This lightweight approach promises substantial benefits for real-time f

关键词： Process control Software defined networking Real-time systems Object recognition Matched filters IP networks Accuracy classification algorithms Topology Synthetic data Software-defined networking (SDN) OpenFlow policy conflict detection policy conflict resolution intent-based networking

来源：评论

学校读者我要写书评

暂无评论

Predicting Postoperative Re-Tear of Arthroscopic Rotator Cuff Repair Using Artificial Intelligence on Imbalanced Data

引用

IEEE ACCESS 2025年 13卷 24487-24497页

作者： Zhang, Zhibin Zhang, Zhewei Peng, Zhaoxiang Dong, Yihong Ningbo Univ Fac Elect Engn & Comp Sci Ningbo 315211 Peoples R China Ningbo Univ Li Huili Hosp Ningbo 315211 Peoples R China Ningbo Univ Hlth Sci Ctr Ningbo 315211 Peoples R China

Retears after rotator cuff surgery are a common complication. Accurate prediction of retear is essential to minimise the risk of retear. Most of the existing big methods for assisted diagnosis are tested on balanced datasets, whereas in the medical field there is data imbalance due to the rare nature of a particular disease or case. Therefore, this paper proposes a weight-based logits cross-entropy loss function. The model in this paper is mainly divided into two parts. This paper employs a pairwise associative encoder (PAE) to construct edges, calculating similarity scores between different nodes to effectively handle the complementary relationship between phenotypic and non-phenotypic data. The other part is the weight network, which calculates the weights of different nodes of different classes to assign weights to the objective function through the GCN model. The main body of the final objective function is the weighted cross-entropy loss function, while the logits of the model output are adjusted and a regularisation term is added to the objective function in order to deal with the discrete points in the data. The classification performance of the proposed method is tested on the dataset of whether rotator cuff is re-torn after surgery, and the results show that our method achieves state-of-the-art performance in a five-fold cross-validation *** code of this work is available at https://***/nishuihan111/***.

关键词： Data models Maintenance engineering classification algorithms Artificial intelligence Surgery Feature extraction Training Predictive models Medical diagnostic imaging Deep learning Arthroscopic rotator cuff repair imbalance data artificial intelligence graph neural network

来源：评论

学校读者我要写书评

暂无评论

CCO: A Cluster Core-Based Oversampling Technique for Improved Class-Imbalanced Learning

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第2期9卷 1153-1165页

作者： Mondal, Priyobrata Ansari, Faizanuddin Das, Swagatam Indian Stat Inst Elect & Commun Sci Unit Kolkata 700108 India

Supervised classification problems from the real world typically face a challenge characterized by the scarcity of samples in one or more target classes compared to the rest of the majority classes. In response to such class imbalance, we propose an oversampling technique based on clustering, aiming to populate the minority class with synthetic samples. This approach capitalizes on the notion of "Cluster Cores," representing locally dense regions within clusters. These Cluster Cores act as central, densely crowded areas that capture intricate topological properties of the corresponding clusters, especially in complex datasets with a non-convex spatial orientation in the feature space. By concentrating on these high-density regions, our clustering-based oversampling technique generates synthetic samples within the convex hull region of minority class instances in the formed clusters. This strategy ensures the creation of points that align with the data space and considers each minority instance within a specific cluster, thereby averting the problems encountered due to the generation of artificial samples by mere linear combination of the minority class data points, as is encountered in SMOTE (Synthetic Minority Oversampling Technique)-based algorithms. To assess the efficacy of our proposal, we conducted experimental comparisons against several cutting-edge algorithms, considering an array of evaluation metrics on well-known datasets used in the literature for both binary and multi-class classification. Additionally, we undertook a detailed ablation study, scrutinized existing algorithms in our context, delineated their strengths and limitations, and contemplated potential research directions in this domain.

关键词： Clustering algorithms Noise measurement Interpolation Noise Computational intelligence classification algorithms Task analysis classification imbalanced data oversampling synthetic minority oversampling technique

来源：评论

学校读者我要写书评

暂无评论

Sparse Linear Discriminant Analysis With Constant Between-Class Distance for Feature Selection

引用

IEEE ACCESS 2025年 13卷 618-632页

作者： Guo, Shuangle Li, Yongxia Zhang, Jianguang Liu, Yue Tian, Tian Guo, Mengchen Shandong Univ Aeronaut Sch Informat Engn Binzhou 256600 Shandong Peoples R China Hengshui Univ Off Acad Affairs Hengshui 053000 Peoples R China Hengshui Univ Dept Math & Comp Sci Hengshui 053000 Peoples R China Hengshui Univ Off Human Resources Hengshui 053000 Peoples R China Univ Calif Davis Dept Appl Math Davis CA 95616 USA Xiamen Univ Malaysia Dept Elect & Elect Engn Sepang 43900 Malaysia

Feature selection is an important preprocessing step in machine learning to remove irrelevant and redundant features. Due to its ability to effectively maintain the discriminability of extracted features, Trace Ratio Linear Discriminant Analysis (TR-LDA) has become the foundation for many feature selection algorithms. As is known, TR-LDA is a challenging problem to solve because of its trace-ratio form, and it also faces the scale invariance problem. These two drawbacks of TR-LDA significantly reduce the performance of feature selection algorithms based on it. To overcome these drawbacks, this paper proposes the sparse LDA with constant between-class distance (SLDA-CBD) model to select relavant features. This model first transforms TR-LDA into a non-trace ratio problem with a constant between-class distance constraint, and then imposes row constraints on the projection matrix to implement feature selection. Since the SLDA-CBD model is rooted in TR-LDA, it ensures the discriminative performance of the selected features. The constant between-class distance constraint successfully avoids the scale invariance problem. Additionally, due to the non-trace ratio form of the SLDA-CBD model, it is easily solvable. The experimental results show that the proposed method has better performance compared to the baseline and six state-of-the-art relative methods, with improvements of over 1% on image datasets and over 2% on video datasets in most cases, while also demonstrating high stability, proving its effectiveness and advantage in practical applications.

关键词： Feature extraction classification algorithms Training Filtering algorithms Computational modeling Machine learning algorithms Sparse matrices Mathematical models Vectors Predictive models Feature selection TR-LDA sparse regression

来源：评论

学校读者我要写书评

暂无评论

FIE-Net: Foreground Instance Enhancement Network for Domain Adaptation Object Detection in Remote Sensing Imagery

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Zhang, Jun Zhang, Xupeng Liu, Shuai Pan, Bin Shi, Zhenwei Hebei Univ Technol Sch Artificial Intelligence Tianjin 300401 Peoples R China Hebei Prov Key Lab Big Data Calculat Tianjin 300401 Peoples R China Nankai Univ Sch Stat & Data Sci KLMDASR LEBPS Tianjin 300071 Peoples R China Nankai Univ LPMC Tianjin 300071 Peoples R China Beihang Univ Image Proc Ctr Sch Astronaut Beijing 100191 Peoples R China Bei hang Univ State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China

Domain adaptation methods can mitigate performance degradation in remote sensing image object detection that arises from interdomain differences. However, current approaches often overlook the focused attention on foreground features, and the differences between the foreground and the background in remote sensing images implicitly diminish the characteristics of the foreground. To address this challenge, we propose a foreground instance enhancement network (FIE-Net) to balance the differences between the foreground and the background in remote sensing images, while enhancing the alignment and application of foreground features. The FIE-Net cooperates with the foreground-focused multigranularity feature alignment (FMA) module with the label filtering and application (LFA) module, progressively focusing on the salient foreground features during the processes of feature alignment and label application. Specifically, FMA directs feature alignment toward the foreground focus during the multigranularity feature alignment process, through foreground-focus perception attention and instance-centered emphasis approach. LFA balances the foreground and background difference information contained in labels, through the hybrid threshold label filtering method and the progressive label switching strategy. The experimental results indicate superior performance and generalization capabilities of our proposed FIE-Net in multiple remote sensing adaptation scenarios. The code is released at https://***/Lab-PANbin/

关键词： Remote sensing Feature extraction Object detection Training Filtering Computational modeling Fast Fourier transforms Detectors Data mining classification algorithms Domain adaptation foreground focus object detection remote sensing imagery

来源：评论

学校读者我要写书评

暂无评论

Quantum Feasibility Labeling for NP-Complete Vertex Coloring Problem

引用

IEEE ACCESS 2025年 13卷 46972-46982页

作者： Zhan, Junpeng Alfred Univ Dept Renewable Energy Engn Alfred NY 14802 USA

Many important science and engineering problems can be converted into NP-complete problems which are of significant importance in computer science and mathematics. Currently, neither existing classical nor quantum algorithms can solve these problems in polynomial time. To address this difficulty, this paper proposes a quantum feasibility labeling (QFL) algorithm to label all possible solutions to the vertex coloring problem, which is a well-known NP-complete problem. The QFL algorithm converts the vertex coloring problem into the problem of searching an unstructured database where good and bad elements are labeled. The recently proposed variational quantum search (VQS) algorithm was demonstrated to achieve an exponential speedup, in circuit depth, up to 26 qubits in finding good element(s) from an unstructured database. Using the labels and the associated possible solutions as input, the VQS can find all feasible solutions to the vertex coloring problem. The number of qubits and the circuit depth required by the QFL each is a polynomial function of the number of vertices, the number of edges, and the number of colors of a vertex coloring problem. We have implemented the QFL on an IBM Qiskit simulator to solve a 4-colorable 4-vertex 3-edge coloring problem.

关键词： Qubit Quantum computing NP-complete problem Labeling Quantum algorithm Polynomials Color classification algorithms Optimization Databases quantum algorithm unstructured database variational quantum search vertex coloring problem

来源：评论

学校读者我要写书评

暂无评论

An overview of recent distributed algorithms for learning fuzzy models in Big Data classification

引用

JOURNAL OF BIG DATA 2020年第1期7卷 1-29页

作者： Ducange, Pietro Fazzolari, Michela Marcelloni, Francesco Dipartimento Ingn Informaz Largo Lucio Lazzarino 1 I-56122 Pisa Italy CNR Ist Informat & Telemat Via Giuseppe Moruzzi 1 I-56124 Pisa Italy

Nowadays, a huge amount of data are generated, often in very short time intervals and in various formats, by a number of different heterogeneous sources such as social networks and media, mobile devices, internet transactions, networked devices and sensors. These data, identified as Big Data in the literature, are characterized by the popular Vs features, such as Value, Veracity, Variety, Velocity and Volume. In particular, Value focuses on the useful knowledge that may be mined from data. Thus, in the last years, a number of data mining and machine learning algorithms have been proposed to extract knowledge from Big Data. These algorithms have been generally implemented by using ad-hoc programming paradigms, such as MapReduce, on specific distributed computing frameworks, such as Apache Hadoop and Apache Spark. In the context of Big Data, fuzzy models are currently playing a significant role, thanks to their capability of handling vague and imprecise data and their innate characteristic to be interpretable. In this work, we give an overview of the most recent distributed learning algorithms for generating fuzzy classification models for Big Data. In particular, we first show some design and implementation details of these learning algorithms. Thereafter, we compare them in terms of accuracy and interpretability. Finally, we argue about their scalability.

关键词： Big Data Fuzzy models Data mining classification algorithms Distributed computing

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：