检索结果-内蒙古大学图书馆

Pre-training transformer with dual-branch context content module for table detection in document images

虚拟现实与智能硬件（中英文） 2024年第5期6卷 408-420页

作者： Yongzhi LI Pengle ZHANG Meng SUN Jin HUANG Ruhan HE School of Computer Science and Artificial Intelligence Wuhan Textile UniversityWuhan 430064China School of Computer Science South-Central Minzu UniversityWuhan 430064China Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion Wuhan Textile UniversityWuhan 430064China

Background Document images such as statistical reports and scientific journals are widely used in information *** detection of table areas in document images is an essential prerequisite for tasks such as information ***,because of the diversity in the shapes and sizes of tables,existing table detection methods adapted from general object detection algorithms,have not yet achieved satisfactory *** detection results might lead to the loss of critical *** Therefore,we propose a novel end-to-end trainable deep network combined with a self-supervised pretraining transformer for feature extraction to minimize incorrect *** better deal with table areas of different shapes and sizes,we added a dualbranch context content attention module(DCCAM)to high-dimensional features to extract context content information,thereby enhancing the network's ability to learn shape *** feature fusion at different scales,we replaced the original 3×3 convolution with a multilayer residual module,which contains enhanced gradient flow information to improve the feature representation and extraction *** We evaluated our method on public document datasets and compared it with previous methods,which achieved state-of-the-art results in terms of evaluation metrics such as recall and ***://***/Yong Z-Lee/TD-DCCAM.

关键词： Table detection Document image analysis Transformer Dilated convolution Deformable convolution Feature fusion

来源：评论

学校读者我要写书评

暂无评论

IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization 38

IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ma, Xiaochen Zhu, Xuekang Su, Lei Du, Bo Jiang, Zhuohang Tong, Bingkui Lei, Zeyu Yang, Xinyu Pun, Chi-Man Lv, Jiancheng Zhou, Jizhe College of Computer Science Sichuan University China Department of Computer and Information Science University of Macao China Engineering Research Center of Machine Learning and Industry Intelligence MOE China

A comprehensive benchmark is yet to be established in the Image Manipulation Detection & Localization (IMDL) field. The absence of such a benchmark leads to insufficient and misleading model evaluations, severely undermining the development of this field. However, the scarcity of open-sourced baseline models and inconsistent training and evaluation protocols make conducting rigorous experiments and faithful comparisons among IMDL models challenging. To address these challenges, we introduce IMDL-BenCo, the first comprehensive IMDL benchmark and modular codebase. IMDL-BenCo: i) decomposes the IMDL framework into standardized, reusable components and revises the model construction pipeline, improving coding efficiency and customization flexibility;ii) fully implements or incorporates training code for state-of-the-art models to establish a comprehensive IMDL benchmark;and iii) conducts deep analysis based on the established benchmark and codebase, offering new insights into IMDL model architecture, dataset characteristics, and evaluation standards. Specifically, IMDL-BenCo includes common processing algorithms, 8 state-of-the-art IMDL models (1 of which are reproduced from scratch), 2 sets of standard training and evaluation protocols, 15 GPU-accelerated evaluation metrics, and 3 kinds of robustness evaluation. This benchmark and codebase represent a significant leap forward in calibrating the current progress in the IMDL field and inspiring future breakthroughs. Code is available at: https://***/scu-zjz/IMDLBenCo. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust intrusion detection for network communication on the Internet of Things: a hybrid machine learning approach

引用

Cluster Computing 2024年第7期27卷 9975-9991页

作者： Soltani, Nasim Rahmani, Amir Masoud Bohlouli, Mahdi Hosseinzadeh, Mehdi Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliu Taiwan Research and Innovation Department Petanux GmbH Bonn Germany Institute of Research and Development Duy Tan University Da Nang Viet Nam Department of Computer Science University of Human Development Sulaymaniyah Iraq

The importance and growth of the Internet of Things (IoT) in computer networks and applications have been increasing. Additionally, many of these applications generate large volumes of data, which are critical and require protection against attacks. Various techniques have been proposed to identify and counteract these threats. In this paper, we offer a hybrid machine learning approach (using the k-nearest neighbors and random forests as supervised classifiers) to enhance the accuracy of intrusion detection systems and minimize the risk of potential attacks. Also, we employ backward elimination and linear discriminant analysis algorithms for feature reduction and to lower computational costs. Following the training phase, when discrepancies arose between the decisions of the classifiers, the ultimate determination was supported by ISO/IEC 27001 regulations. The performance of the proposed model was assessed within a Python programming framework, utilizing the CICIDS 2017, NSL-KDD, and TON-IoT datasets. The outcomes illustrated that the proposed approach attained a noteworthy accuracy of 99.96% in the multi-class classification of CICIDS 2017, 99.37% in the binary classification of the NSL-KDD dataset, and 99.96% in the multi-class classification of TON-IoT dataset. Furthermore, the attack success rate for each dataset stands at 0.05%, 0.24%, and 0% respectively, demonstrating a significant reduction compared to other methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Early Diagnosis of Lung Tumors for Extending Patients’ Life Using Deep Neural Networks

引用

computers, Materials & Continua 2023年第7期76卷 993-1007页

作者： A.Manju R.Kaladevi Shanmugasundaram Hariharan Shih-Yu Chen Vinay Kukreja Pradip Kumar Sharma Fayez Alqahtani Amr Tolba Jin Wang Department of Computer Science and Engineering SRM Institute of Science and TechnologyRamapuramChennaiIndia Department of Computer Science and Engineering Saveetha Engineering CollegeChennaiIndia Department of Computer Science and Engineering Vardhaman College of EngineeringHyderabadIndia Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin 64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin 64002Taiwan Chitkara University Institute of Engineering and Technology Chitkara UniversityPunjabIndia Department of Computing Science University of AberdeenAberdeenUK Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh 12372Saudi Arabia Computer Science Department Community CollegeKing Saud UniversityRiyadh 11437Saudi Arabia School of Computer&Communication Engineering Changsha University of Science&TechnologyChangshaChina

The medical community has more concern on lung cancer *** experts’physical segmentation of lung cancers is time-consuming and needs to be *** research study’s objective is to diagnose lung tumors at an early stage to extend the life of humans using deep learning ***-Aided Diagnostic(CAD)system aids in the diagnosis and shortens the time necessary to detect the tumor *** application of Deep Neural Networks(DNN)has also been exhibited as an excellent and effective method in classification and segmentation *** research aims to separate lung cancers from images of Magnetic Resonance Imaging(MRI)with threshold *** Honey hook process categorizes lung cancer based on characteristics retrieved using several *** this principle,the work presents a solution for image compression utilizing a Deep Wave Auto-Encoder(DWAE).The combination of the two approaches significantly reduces the overall size of the feature set required for any future classification process performed using *** proposed DWAE-DNN image classifier is applied to a lung imaging dataset with Radial Basis Function(RBF)*** study reported promising results with an accuracy of 97.34%,whereas using the Decision Tree(DT)classifier has an accuracy of 94.24%.The proposed approach(DWAE-DNN)is found to classify the images with an accuracy of 98.67%,either as malignant or normal *** contrast to the accuracy requirements,the work also uses the benchmark standards like specificity,sensitivity,and precision to evaluate the efficiency of the *** is found from an investigation that the DT classifier provides the maximum performance in the DWAE-DNN depending on the network’s performance on image testing,as shown by the data acquired by the categorizers themselves.

关键词： Lung tumor deep wave auto encoder decision tree classifier deep neural networks extraction techniques

来源：评论

学校读者我要写书评

暂无评论

Temporal Difference-Aware Graph Convolutional Reinforcement Learning for Multi-Intersection Traffic Signal Control

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第1期25卷 327-337页

作者： Lin, Wei-Yu Song, Yun-Zhu Ruan, Bo-Kai Shuai, Hong-Han Shen, Chih-Ya Wang, Li-Chun Li, Yung-Hui National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu30010 Taiwan National Tsing Hua University Department of Computer Science Hsinchu300 Taiwan Hon Hai Research Institute Ai Research Center New Taipei City11492 Taiwan

Traffic light control plays a crucial role in intelligent transportation systems. This paper introduces Temporal Difference-Aware Graph Convolutional Reinforcement Learning (TeDA-GCRL), a decentralized RL-based method for efficient multi-intersection traffic signal control. Specifically, we put forward a new graph architecture using each lane as a node for considering intersection relations. Additionally, we propose two new rewards by considering temporal information, namely Temporal-Aware Pressure on Incoming Lanes (TAPIL) and Temporal-Aware Action Consistency (TAAC), which enhance learning efficiency and time-interval sensitivity. Experimental results on five datasets show the superiority of TeDA-GCRL over state-of-the-art methods by at least 9.5% in average travel time. © 2000-2011 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Heuristic for Direct Product Graph Decomposition

引用

Journal of Graph Algorithms and Applications 2023年第7期27卷 581-601页

作者： Calderoni, Luca Margara, Luciano Marzolla, Moreno Dept. of Computer Science and Engineering University of Bologna Italy Center for Inter-Department Industrial Research ICT Università di Bologna Italy

In this paper we describe a heuristic for decomposing a directed graph into factors according to the direct product (also known as Kronecker, cardinal or tensor product). Given a directed, unweighted graph G with adjacency matrix Adj(G), our heuristic aims at identifying two graphs G1 and G2 such that G = G1 × G2, where G1 × G2 is the direct product of G1 and G2. For undirected, connected graphs it has been shown that graph decomposition is "at least as difficult" as graph isomorphism;therefore, polynomial-time algorithms for decomposing a general directed graph into factors are unlikely to exist. Although graph factorization is a problem that has been extensively investigated, the heuristic proposed in this paper represents – to the best of our knowledge – the first computational approach for general directed, unweighted graphs. We have implemented our algorithm using the MATLAB environment;we report on a set of experiments that show that the proposed heuristic solves reasonably-sized instances in a few seconds on general-purpose hardware. Although the proposed heuristic is not guaranteed to find a factorization, even if one exists;however, it always succeeds on all the randomly-generated instances used in the experimental evaluation. © 2023, Brown University. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

An Adaptable Algorithm for Optimizing Bus Line Distribution Using the Clustering Method

引用

Wireless Personal Communications 2024年第4期134卷 2347-2370页

作者： Sheikhi, Fatemeh Rahmani, Amir Masoud Computer Engineering Department Science and Research Branch Islamic Azad University Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

The current fleet of cars requires reevaluation, upgrades, and replacement in response to the expanding human population, the increase in urban traffic volume, and the elevated levels of air pollution attributed to vehicular emissions. In densely populated cities, bus routes effectively compete with private transportation, optimize user accessibility, and provide access to all urban residents. This study proposes a novel method for optimizing bus routes, encompassing four primary processes: preprocessing, site clustering, ridership prediction, and optimization. The clustering process employs the K-means technique to classify available bus stops based on their geographical information. The suggested method utilizes an artificial neural network model to forecast the number of passengers at different locations. Subsequently, the bee colony optimization algorithm is implemented to determine bus frequencies and achieve an optimal distribution of buses across various traffic lines. Results obtained using a real traffic line dataset indicate a 32% increase in traffic fleet capacity and a 22.33% reduction in passenger waiting time upon application of the proposed method. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Auto Insurance Fraud Detection with Multimodal Learning

引用

Data Intelligence 2023年第2期5卷 388-412页

作者： Jiaxi Yang Kui Chen Kai Ding Chongning Na Meng Wang Financial Technological Research Center Zhejiang LabHangzhou 361005China School of Computer Science and Engineering Southeast UniversityNanjing 211189China

In recent years,feature engineering-based machine learning models have made significant progress in auto insurance fraud ***,most models or systems focused only on structural data and did not utilize multi-modal data to improve fraud detection *** solve this problem,we adapt both natural language processing and computer vision techniques to our knowledge-based algorithm and construct an Auto Insurance Multi-modal Learning(AIML)*** then apply AIML to detect fraud behavior in auto insurance cases with data from real scenarios and conduct experiments to examine the improvement in model performance with multi-modal data compared to baseline model with structural data only.A selfdesigned Semi-Auto Feature Engineer(SAFE)algorithm to process auto insurance data and a visual data processing framework are embedded within *** show that AIML substantially improves the model performance in detecting fraud behavior compared to models that only use structural data.

关键词： Auto Insurance Multi-modal Learning Fraud detection Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Grassland Mouse Hole Recognition Model Based on UAV Remote Sensing and Improved YOLOv7

Grassland Mouse Hole Recognition Model Based on UAV Remote S...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Han, Yu Bai, Xiangyu Gao, Xiaochen Cheng, Haoran Zhou, Kexin College of Computer Science Inner Mongolia University Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China School of Computer Science Inner Mongolia University Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China

ISBN: (纸本)9781665410205

As the most widely distributed vegetation type on Earth, grasslands are the second largest ecosystem after forests, and are known as the 'skin of the earth'. However, the frequency of rodent infestation has been increasing year by year in recent years due to climate change, loose soil and other factors. As the current traditional monitoring methods are time-consuming and laborious, while the deep learning method has the advantages of low cost, high efficiency and high accuracy. Therefore, this paper proposes a combination of UAV remote sensing and deep learning methods to monitor grassland mouse hole. First, because there is no publicly available grassland mouse hole dataset, this study used a UAV to capture images to create a grassland mouse hole dataset. Second, an improved YOLOv7 model, YOLOAPM, is proposed with the goal of improving the accuracy of small target recognition. Through ablation and comparison experiments, the validity of the improved model as well as the method of this paper are verified to be improved compared to other models. Finally, in order to facilitate the monitoring task of the researchers, a monitoring system is established and the mouse hole identification of this paper is embedded into the system. © 2024 IEEE.

关键词： Abiotic

来源：评论

学校读者我要写书评

暂无评论

Robust Facial Biometric Authentication System Using Pupillary Light Reflex for Liveness Detection of Facial Images

引用

computer Modeling in engineering & sciences 2024年第4期139卷 725-739页

作者： Puja S.Prasad Adepu Sree Lakshmi Sandeep Kautish Simar Preet Singh Rajesh Kumar Shrivastava Abdulaziz S.Almazyad Hossam M.Zawbaa Ali Wagdy Mohamed CSE Department Geethanjali College of EngineeringHyderabadTelangana501301India Department of Computer Science LBEF CampusKathmandu44600Nepal School of Computer Science Engineering and Technology(SCSET) Bennett UniversityGreater Noida201310India Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia CeADAR Ireland’s Centre for AI Technological University DublinDublinD07 EWV4Ireland Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research Center Applied Science Private UniversityAmman11937Jordan

Pupil dynamics are the important characteristics of face spoofing *** face recognition system is one of the most used biometrics for authenticating individual *** main threats to the facial recognition system are different types of presentation attacks like print attacks,3D mask attacks,replay attacks,*** proposed model uses pupil characteristics for liveness detection during the authentication *** pupillary light reflex is an involuntary reaction controlling the pupil’s diameter at different light *** proposed framework consists of two-phase *** the first phase,the pupil’s diameter is calculated by applying stimulus(light)in one eye of the subject and calculating the constriction of the pupil size on both eyes in different video *** above measurement is converted into feature space using Kohn and Clynes model-defined *** Support Vector Machine is used to classify legitimate subjects when the diameter change is normal(or when the eye is alive)or illegitimate subjects when there is no change or abnormal oscillations of pupil behavior due to the presence of printed photograph,video,or 3D mask of the subject in front of the *** the second phase,we perform the facial recognition ***-invariant feature transform(SIFT)is used to find the features from the facial images,with each feature having a size of a 128-dimensional *** features are scale,rotation,and orientation invariant and are used for recognizing facial *** brute force matching algorithm is used for matching features of two different *** threshold value we considered is 0.08 for good *** analyze the performance of the framework,we tested our model in two Face antispoofing datasets named Replay attack datasets and CASIA-SURF datasets,which were used because they contain the videos of the subjects in each sample having three modalities(RGB,IR,Depth).The CASIA-SURF datasets showed an 89.9%Equal Err

关键词： SIFT pupil CASIA-SURF pupillary light reflex replay attack dataset brute force

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：