检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Xu, Chuanhao Cheng, Jingwei Zhang, Fu School of Computer Science and Engineering Northeastern University China

ISBN: (纸本)9798891761681

Entity alignment (EA) aims to find equivalent entities between two Knowledge Graphs. Existing embedding-based EA methods usually encode entities as embeddings, triples as embeddings' constraint and learn to align the embeddings. However, the details of the underlying logical inference steps among the alignment process are usually omitted, resulting in inadequate inference process. In this paper, we introduce NALA, an entity alignment method that captures three types of logical inference paths with Non-Axiomatic Logic (NAL). Type I&II align the entity pairs and type III aligns relations. NALA iteratively aligns entities and relations by integrating the conclusions of the inference paths. Our method is logically interpretable and extensible by introducing NAL, and thus suitable for various EA settings. Experimental results show that NALA outperforms state-of-the-art methods in terms of Hits@1, achieving 0.98+ on all three datasets of DBP15K with both supervised and unsupervised settings. We offer a pioneering in-depth analysis of the fundamental principles of entity alignment, approaching the subject from a unified and logical perspective. Our code is available at https://***/13998151318/NALA. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Novel Intelligent Task Offloading Scheme for Multi-Controller Environment in Software Defined Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第12期12卷 20018-20029页

作者： Hussain, Mir Wajahat Sangaiah, Arun Kumar Reddy, K. Hemant Kumar Roy, Diptendu Sinha Alenazi, Mohammed J.F. Javvaji, Pavan Kumar Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Karnataka Anekal562106 India International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan School of Engineering and Technology Sunway University Selangor Petaling Jaya47500 Malaysia University Centre for Research and Development Chandigarh University Punjab Mohali140413 India School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati522237 India Department of Computer Science and Engineering National Institute of Technology Meghalaya 793003 India College of Computer and Information Sciences Department of Computer Engineering King Saud University Riyadh11451 Saudi Arabia

The Internet of Vehicles (IoV), equipped with sensors, generates vast amounts of data, demanding rigorous computation and network. The cloud computing platform meets these stringent computation requirements, but it has a significant latency that fog computing effectively handles. Software Defined Network (SDN) has become the de facto standard for next-generation networking due to its unique and flexible features, which handle the network pre-requisites in an agile manner. Task Offloading (TO) is a crucial issue in Software Defined-IoV (SDIoV), particularly when the vehicle's resources are insufficient. Fog nodes schedule offloaded tasks;however, neglecting computational and network details during task scheduling can lead to longer completion times, thereby restricting the functionality of SD-IoV due to its time-sensitive nature. Therefore, this paper introduces two proactive Intelligent Task Offloading (ITO' and ITO) schemes. These schemes schedule tasks onto fog nodes with enhanced computational capabilities, dynamically enable the network through the ovs-ofctl SDN utility, and consider vehicle mobility during task scheduling. Experiments with Mininet show that the proposed (ITO' and ITO) schemes improve performance in terms of CPU availability, bandwidth, and throughput by 5.2 times, 50% and (30.7-13.9)% more than the existing scheme. They also reduce average packet loss, delay, Round Trip Time (RTT), and offloaded node time selection by (45.35-21.3)%, (50-33.3)%, (53.9-9.9)% and (43.2-26.06)% which demonstrates the efficacy of the proposed scheme. © 2025 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning for DR Identification: Integrating DenseNet121 and VGG19 Architectures 1

Ensemble Deep Learning for DR Identification: Integrating De...

引用

1st International Conference on Innovative engineering sciences and Technological Research, ICIESTR 2024

作者： Tiwari, Shamik Shukla, Amar School of Computer Science & Engineering Iilm Gurgaon India School of Computer Science Upes Dehradun India

ISBN: (纸本)9798350348637

Diabetic retinopathy (DR) is a severe complication of diabetes affecting the retina, potentially leading to vision impairment or blindness. Deep learning for diabetic retinopathy identification leverages intricate neural network architectures, enabling automated and precise analysis of fundus images. This paper provides a technique for DR identification based on fundus pictures. The suggested ensemble model combines the characteristics of the DenseNet121 and VGG19 architectures, taking advantage of their distinct features using average ensembling. This ensemble approach capitalizes on the complementary features extracted by both DenseNet121 and VGG19, enhancing the model's skill to discern subtle patterns indicative of diabetic retinopathy. The proposed ensembled model surpassed all individual models with an impressive accuracy of 0.964. The comparison analysis confirms the ensemble model's improved performance in capturing the delicate nuances of fundus pictures, indicating its potential as an advanced tool for early and accurate diabetic retinopathy identification © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Integrating deep and handcrafted features for enhanced decision-making assistance in breast cancer diagnosis on ultrasound images

引用

Multimedia Tools and Applications 2025年 1-23页

作者： Abhisheka, Barsha Biswas, Saroj Kumar Purkayastha, Biswajit Das, Soumen School of Computer Science UPES Bidholi Uttrakhand Dehradun248007 India Computer Science Engineering National Institute of Technology Silchar NIT Road Assam Silchar788010 India

The classification of breast cancer has emerged as a significant concern in the healthcare sector in recent times. This is primarily due to its status as the second leading cause of cancer-related fatalities among women. Prior research in the field of breast cancer classification has mainly focused on either traditional Machine Learning (ML) based models or employing Deep Learning (DL) models. However, both approaches solely fail to capture the complete spectrum of features necessary for accurate classification. Therefore, this paper introduces a classification model named Hybrid Breast Cancer Prediction System (HBCPS), which utilizes a combination of features derived from deep Convolutional Neural Network (CNN) model and handcrafted features, to improve classification performance. The proposed HBCPS uses the pre-trained ResNet50 network to extract the deep features, while the handcrafted features are obtained using Histogram Orientation Gradient (HOG). For classification the proposed approach uses Support Vector Machine (SVM). In addition, the proposed method integrates the Block Matching 3D(BM3D) denoising filter. This filter efficiently reduces multiplicative noise such as speckle noise from Breast Ultrasound (BUS) images, resulting in improved image quality. This enhancement technique has significantly contributed to improve the overall performance of the system. The proposed framework is evaluated using a widely used Breast Ultrasound Image (BUSI) dataset. The proposed HBCPS exhibited satisfactory performance with an accuracy, precision, recall, F1-score, specificity, and AUC values of 89.02%, 87.67%, 87.17%, 87.36%, 83.87%, and 0.8717, respectively. These metrics indicate the robustness and reliability of the proposed method and offer a comprehensive framework for breast cancer classification using BUS images. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Effective Intrusion Detection System Based on the FSA-BGRU Hybrid Model

引用

China Communications 2025年第2期22卷 188-198页

作者： Deng Zaihui Li Zihang Guo Jianzhong Gan Guangming Kong Dejin School of Electronic and Electrical Engineering Wuhan Textile UniversityWuhan 430200China School of Computer Science and Artificial Intelligence Wuhan Textile UniversityWuhan 430200China School of Physics and Electronic Information Engineering Hubei Engineering UniversityXiaogan 432000China

Intrusion detection systems play a vital role in cyberspace *** this study,a network intrusion detection method based on the feature selection algorithm(FSA)and a deep learning model is developed using a fusion of a recursive feature elimination(RFE)algorithm and a bidirectional gated recurrent unit(BGRU).Particularly,the RFE algorithm is employed to select features from high-dimensional data to reduce weak correlations between features and remove redundant features in the numerical feature ***,a neural network that combines the BGRU and multilayer perceptron(MLP)is adopted to extract deep intrusion behavior ***,a support vector machine(SVM)classifier is used to classify intrusion *** proposed model is verified by experiments on the NSL-KDD *** results indicate that the proposed model achieves a 90.25%accuracy and a 97.51%detection rate in binary classification and outperforms other machine learning and deep learning models in intrusion *** proposed method can provide new insight into network intrusion detection.

关键词： bidirectional GRU feature selection intrusion detection system multilayer perceptron recursive feature elimination support vector machine

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Frequency-Domain Pruning Algorithms for Accelerating Human Activity Recognition Tasks Based on Sensor Data

引用

computers, Materials & Continua 2024年第11期81卷 2219-2242页

作者： Jian Su Haijian Shao Xing Deng Yingtao Jiang School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas VegasNV 89154USA

The rapidly advancing Convolutional Neural Networks(CNNs)have brought about a paradigm shift in various computer vision tasks,while also garnering increasing interest and application in sensor-based Human Activity Recognition(HAR)***,the significant computational demands and memory requirements hinder the practical deployment of deep networks in resource-constrained *** paper introduces a novel network pruning method based on the energy spectral density of data in the frequency domain,which reduces the model’s depth and accelerates activity *** traditional pruning methods that focus on the spatial domain and the importance of filters,this method converts sensor data,such as HAR data,to the frequency domain for *** emphasizes the low-frequency components by calculating their energy spectral density ***,filters that meet the predefined thresholds are retained,and redundant filters are removed,leading to a significant reduction in model size without compromising performance or incurring additional computational ***,the proposed algorithm’s effectiveness is empirically validated on a standard five-layer CNNs backbone *** computational feasibility and data sensitivity of the proposed scheme are thoroughly ***,the classification accuracy on three benchmark HAR datasets UCI-HAR,WISDM,and PAMAP2 reaches 96.20%,98.40%,and 92.38%,***,our strategy achieves a reduction in Floating Point Operations(FLOPs)by 90.73%,93.70%,and 90.74%,respectively,along with a corresponding decrease in memory consumption by 90.53%,93.43%,and 90.05%.

关键词： Convolutional neural networks human activity recognition network pruning frequency-domain transformation

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-Based Frameworks for Liver and Tumor Segmentation Task on LiTS

引用

SN computer science 2024年第6期5卷 741页

作者： Randar, Shyam Shah, Vedanshi Kulkarni, Harshmohan Suryawanshi, Yash Joshi, Amit Sawant, Suraj Department of Computer Science and Engineering School of Computational Science COEP Technological University Pune

Accurate liver tumor diagnosis in clinical practice relies on precisely delineating the liver and identifying potential tumors in Computed Tomography scans. This study aims to develop a lightweight liver and tumor segmentation model, balancing computational cost and accuracy. Traditional methods use Convolutional Neural Networks that enhance the performance but heighten the computational costs. Addressing it, this study presents three frameworks: Sim-Seg, Seg-Seg, and BB-Seg for liver and liver tumor segmentation tasks, leveraging the You Look Only Once network. The proposed Sim-Seg framework achieves a dice score of 89.54% for liver segmentation, while the BB-Seg framework attains a dice score of 80.55% for tumor segmentation on the Liver Tumor Segmentation Benchmark. In conclusion, this study effectively balances computational resources and accuracy, achieving results comparable to those of more compute-intensive methods. It aims to advance the development of YOLO-based frameworks in the medical field. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Healthcare Liver tumor segmentation Medical image segmentation Object detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Enhancing surrogate-assisted evolutionary optimization for medium-scale expensive problems: a two-stage approach with unsupervised feature learning and Q-learning

引用

Neural Computing and Applications 2024年第25期36卷 15545-15565页

作者： Gong, Yiyun Yu, Haibo Kang, Li Sun, Chaoli Zeng, Jianchao School of Electrical and Control Engineering North University of China Taiyuan030051 China School of Computer Science and Technology North University of China Taiyuan030051 China School of Environment and Safety Engineering North University of China Taiyuan030051 China School of Computer Science and Technology Taiyuan University of Science and Technology Taiyuan030024 China

This paper presents a novel two-stage progressive search approach with unsupervised feature learning and Q-learning (TSLL) to enhance surrogate-assisted evolutionary optimization for medium-scale expensive problems. The method attempts to address the challenges posed by multi-polar and multi-variable coupling properties in such problems. During the iteration, TSLL splits the optimization process into two distinct stages. First, two unsupervised feature learning techniques: principal component analysis (PCA) and Autoencoder, are utilized to improve the representation of potential optimal samples in the solution space. PCA is used for feature reduction, extracting the most important features. On the other hand, Autoencoder focuses on reconstructing features within the medium-scale solution space. To ensure comprehensive exploration of the entire solution space, TSLL employs two distinct surrogate modeling approaches along with Q-learning in the second stage to dynamically select the mutation strategy for the differential evolution operator. Numerous experiments demonstrate the superiority of TSLL over five state-of-the-art surrogate-assisted approaches and two sophisticated evolutionary algorithms including the winner of CEC 2017 on medium-scale benchmark problems and a wind farm layout problem. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Novel and Optimized Collaborative Diversity-Driven Routing Mechanism in MANETs

引用

SN computer science 2024年第1期5卷 22页

作者： Malyadri, Neelam Ramakrishna, M. Department of Computer Science and Engineering Vemana Institute of Technology VTU Belagavi India School of Computer Science and Engineering REVA University Karnataka Bengaluru India Department of Computer Science and Engineering Vemana Institute of Technology Karnataka Bengaluru India

Wireless networks such as MANETs present unique challenges due to their dynamic and decentralized nature. Efficient routing protocols are essential for achieving reliable and robust communication in such networks. In this research, we propose a novel routing mechanism called collaborative diversity-driven routing (CollabNet) that integrates collaborative diversity to enhance the routing process in ad hoc networks. CollabNet utilizes a collaborative approach to address the challenges posed by dynamic network environments. CollabNet incorporates collaborative power control, adaptive power allocation, and energy-efficient routing to automatically adjust the dynamic power of nodes. By promoting collaborative behavior and optimizing power levels. It fosters collaborative behavior among nodes by establishing cooperation groups and leveraging multiple relay nodes. Through collaborative multipath diversity CollabNet facilitates the transmission of packets toward the destination via multiple paths within the transmission range. This approach increases the probability of successful packet delivery by establishing redundant connections. By promoting collaboration among nodes, CollabNet improves the reliability and connectivity of wireless ad hoc networks. The mechanism leverages the strength of collaborative diversity to enhance the overall performance of routing protocols. Extensive simulations demonstrate that CollabNet outperforms traditional routing protocols in terms of network connectivity, reliability, and efficiency. The proposed mechanism offers a promising solution for efficient routing in MANETs contributing to the advancement of wireless communication in dynamic ad hoc network environments. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Collaborative diversity Collaborative diversity-driven routing MANETs Routing protocols Wireless ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Holistic Analysis and Development of a Pregnancy Risk Detection Framework: Unveiling Predictive Insights Beyond Random Forest

引用

SN computer science 2024年第8期5卷 1074页

作者： Irfan, Neha Zafar, Sherin Hussain, Imran Department of Computer Science and Engineering School of Engineering Sciences and Technology Jamia Hamdard New Delhi India

This paper presents a cutting-edge framework for predicting psychological health risks in pregnant women, supported by robust analytics and a user-friendly application interface. Utilizing a dataset of 1504 postpartum women, state-of-the-art machine learning algorithms, particularly Random Forest, achieved an impressive accuracy score of 0.7508. This underscores the framework's effectiveness in identifying psychological health risks with high precision. Beyond traditional accuracy metrics, the study adopts a comprehensive approach to performance evaluation, incorporating precision, recall, and F1 score to provide a nuanced understanding of classifier performance, essential for informed decision-making in healthcare settings. The primary goal is to establish a seamless computerized prediction pathway, enabling healthcare providers to proactively address mental well-being in pregnant women. The framework encompasses several key stages, including meticulous data collection, rigorous preprocessing, strategic feature selection, and algorithmic selection. Advanced data preprocessing techniques, such as outlier removal and null value elimination, were employed to enhance data quality and reliability. Feature selection focused on identifying pivotal attributes for precise prediction of psychological health risks, optimizing model efficacy. A distinguishing aspect of this research is its emphasis on user-centric application development. The bespoke Women's Mental Health Tracker, crafted using Python's Tkinter library, boasts a user-friendly interface with personalized recommendations, weekly progress tracking, access to a rich resource library, community support, reminders, and notifications. This empowers pregnant women to manage their mental well-being proactively with ease and confidence. Attribute analysis highlights critical psychological health indicators, including feelings of sadness, irritability, sleep disturbances, concentration issues, overeating, and anxiety. Wh

关键词： Feature selection Maternal mental health Predictive analytics Pregnancy risk detection Proactive mental health management Psychological health risks User- friendly application interface Women’s Mental Health Tracker

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：