检索结果-内蒙古大学图书馆

Target Detection-Oriented RGCN Inference Enhancement Method

computers, Materials & Continua 2025年第4期83卷 1219-1237页

作者： Lijuan Zhang Xiaoyu Wang Songtao Zhang Yutong Jiang Dongming Li Weichen Sun School of Internet of Things Engineering Wuxi UniversityWuxi214105China College of Computer Science and Engineering Changchun University of TechnologyChangchun130012China Computer Science and Technology at Guohao Academy Tongji UniversityShanghai200092China China North Vehicle Research Institute Beijing100072China

In this paper,a reasoning enhancement method based on RGCN(Relational Graph Convolutional Network)is proposed to improve the detection capability of UAV(Unmanned Aerial Vehicle)on fast-moving military targets in urban battlefield *** combining military images with the publicly available VisDrone2019 dataset,a new dataset called VisMilitary was built and multiple YOLO(You Only Look Once)models were tested on *** to the low confidence problem caused by fuzzy targets,the performance of traditional YOLO models on real battlefield images decreases ***,we propose an improved RGCN inference model,which improves the performance of the model in complex environments by optimizing the data processing and graph network *** results show that the proposed method achieves an improvement of 0.4%to 1.7%on mAP@0.50,which proves the effectiveness of the model in military target *** research of this paper provides a new technical path for UAV target detection in urban battlefield,and provides important enlightenment for the application of deep learning in military field.

关键词： RGCN target detection urban battlefield YOLO visual reasoning

来源：评论

学校读者我要写书评

暂无评论

Unleashing the power of pseudo-code for binary code similarity analysis

引用

Cybersecurity 2023年第2期6卷 44-61页

作者： Weiwei Zhang Zhengzi Xu Yang Xiao Yinxing Xue School of Computer Science and Engineering University of Science and Technology of ChinaHefeiChina School of Computer Science and Engineering Nanyang Technological UniversitySingaporeSingapore Institute of Information Engineering Chinese Academy of SciencesBeijingChina School of Cyber Security University of Chinese Academy of SciencesBeijingChina

Code similarity analysis has become more popular due to its significant applicantions,including vulnerability detection,malware detection,and patch *** the source code of the software is difficult to obtain under most circumstances,binary-level code similarity analysis(BCSA)has been paid much attention *** recent years,many BCSA studies incorporating Al techniques focus on deriving semantic information from binary functions with code representations such as assembly code,intermediate representations,and control flow graphs to measure the ***,due to the impacts of different compilers,architectures,and obfuscations,binaries compiled from the same source code may vary considerably,which becomes the major obstacle for these works to obtain robust *** this paper,we propose a solution,named UPPC(Unleashing the Power of Pseudo-code),which leverages the pseudo-code of binary function as input,to address the binary code similarity analysis challenge,since pseudocode has higher abstraction and is platform-independent compared to binary *** selectively inlines the functions to capture the full function semantics across different compiler optimization levels and uses a deep pyramidal convolutional neural network to obtain the semantic embedding of the *** evaluated UPPC on a data set containing vulnerabilities and a data set including different architectures(X86,ARM),different optimization options(O0-O3),different compilers(GCC,Clang),and four obfuscation *** experimental results show that the accuracy of UPPC in function search is 33.2%higher than that of existing methods.

关键词： Binary code similarity Machine learning Software security Pseudo-code

来源：评论

学校读者我要写书评

暂无评论

Multiple object tracking based on appearance and motion graph convolutional neural networks with an explainer

引用

Neural Computing and Applications 2024年第22期36卷 13799-13814页

作者： Zhang, Yubo Huang, Qingming Zheng, Liying School of Computer Science and Technology Harbin Engineering University 145 Nantong Street Heilongjiang Harbin150001 China School of Computer Science and Technology University of Chinese Academy of Sciences Huairou District Beijing100019 China

The tracking performance of Multi-Object Tracking (MOT) has recently been improved by using discriminative appearance and motion features. However, dense crowds and occlusions significantly reduce the reliability of these features, resulting in unsatisfied tracking performance. Thus, we design an end-to-end MOT model based on Graph Convolutional Neural Networks (GCNNs) which fuses four classes of features that characterize objects from their appearances, motions, appearance interactions, and motion interactions. Specifically, a Re-Identification (Re-ID) module is used to extract more discriminative appearance features. The appearance features from object tracklets are then averaged to simplify the proposed tracker. Then, we design two GCNNs to better distinguish objects. One is for extracting interactive appearance features, and the other is for interactive motion features. A fusion module then fuses those features, getting the global feature similarity based on which an association component calculates the MOT matching results. Finally, we semantically visualize relevant structures with the GNNExplainer for insight into the proposed tracker. The evaluation results on MOT16 and MOT17 benchmarks show that our model outperforms the state-of-the-art online tracking methods in terms of Multi-Object Tracking Accuracy and Identification F1 score which is consistent with the results from the GNNExplainer. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security in Communication Networks through Quantum Key Distribution 2

Enhancing Security in Communication Networks through Quantum...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Purushottam, Vaishnavi V Meena, S. Guruprasad, N. Global Academy of Technology Dept. of Computer Science and Engineering Bengaluru India Buddha Institute of Technology Computer Science and Engineering Gorakhpur India

ISBN: (纸本)9798350368109

Quantum Key Distribution or QKD revolutionizes secure communication using quantum mechanics. Unlike traditional cryptographic methods vulnerable to advances in computing power, QKD guarantees unconditional security by detecting any eavesdropping attempt. Quantum Key Distribution (QKD) constitutes a through development in the realm of secure communications by utilizing the ideas of quantum mechanics to provide potentially unbreakable encryption. This study examines the most current advancements in QKD, including the recently announced Measurement-Device-Independent QKD (MDI-QKD) and protocols like BB84 and E91. We analyze the real-world implementation, including satellite-based QKD and quantum repeaters. Furthermore, we discuss the challenges and opportunities of integrating QKD into present communication infrastructure. The significance of QKD in attaining secure communication networks for the next generation is underscored by our findings, which also have ramifications for forthcoming research and applications. Ultimately, this research aims to contribute to the development of robust and impenetrable communication networks in an increasingly interconnected world. © 2024 IEEE.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

A Wireless Multifunctional Structural Health Monitoring System 3

A Wireless Multifunctional Structural Health Monitoring Syst...

引用

3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems, ACCESS 2023

作者： Prabhakaran, Anagha Swapna Kumar, S. Vidya Academy of Science Technology Dept. of Electronics & Communication Engineering Kerala India

ISBN: (纸本)9798350346169

Structural vibrations have a great impact on civil structures. Most of the damage happening to structures that lead to a reduction in their life span is due to vibration. This vibration can be natural or man-made. This paper explains the importance of SHM(Structural health monitoring) and proposes a system for continuously monitoring the structural health status. The prototype consists of an ADXL-335 accelerometer, Arduino Uno, GPS (Global positioning system) and GSM (Global system for mobile communication). The functionalities of the system include detection of variation in the structural parameters, locating the position of the structure by means of GPS and sending the health status of the structure to authority where the GSM consists of a prioritized list of numbers. The paper also focuses on analyzing the dynamic parameters like acceleration and tilt angle in three modes: no vibration mode, normal vibration mode and collapse mode. Also analysis of time-domain features of vibration data in three modes are also analyzed. © 2023 IEEE.

关键词： Structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

Advancements in Cancer Disease Prediction Using Modified Multi Model Deep Neural Networks 3

Advancements in Cancer Disease Prediction Using Modified Mul...

引用

3rd IEEE Asian Conference on Innovation in technology, ASIANCON 2023

作者： Balakrishnan, D. Mariappan, Umasree Reddy, Sangam Sravya Nikitha, Ishnumolakala Likitha, S. Sirisha, S. Kalasalingam Academy of Research and Education Department of Computer Science and Engineering TamilNadu Krishnankoil626126 India Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering TamilNadu Virudhunagar626001 India

ISBN: (纸本)9798350302288

Cancer disease prediction is a critical task in healthcare that can significantly impact patient outcomes. This abstract presents a multimodal deep neural network (DNN) approach for cancer disease prediction, implemented in MATLAB. The proposed model leverages the power of DNNs to handle diverse types of data, such as medical images, genomic profiles, clinical records, and patient demographics. By integrating these multimodal data sources, the model aims to capture a comprehensive view of the disease, incorporating both genetic and phenotypic information. The MATLAB implementation allows for efficient data processing, model training, and evaluation. The performance of the proposed multimodal DNN model is assessed using benchmark datasets, and the results demonstrate its potential in accurate cancer disease prediction. Further research is needed to explore the interpretability of the model's predictions and expand its application to real-world clinical settings. Overall, this work contributes to advancing the field of cancer diagnostics by utilizing a multimodal DNN approach implemented in MATLAB for improved disease prediction. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Advanced Forecasting and Analysis Techniques for Optimizing Website Performance: A Comparative Study of Time Series Models 2

Advanced Forecasting and Analysis Techniques for Optimizing ...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Raikar, Gayathri Harshith, D. Guruprasad, N. Global Academy of Technology Dept. of Computer Science and Engineering Bangalore India Buddha Institute of Technology Computer Science and Engineering Gorakhpur India

ISBN: (纸本)9798350368109

Analyzing website performance is crucial for optimizing a site's functionality, enhancing user engagement, and aligning with business goals. This evaluation focuses on essential metrics such as average engagement time per session, engagement rate, and events per session, which significantly impact user experience and overall business success. Through effective performance analysis, organizations can improve user satisfaction, boost conversion rates, and enhance their profitability and reputation. This paper reviews different approaches for analyzing these key metrics, explores their effects on user behavior and business performance, and offers best practices for optimizing website performance. By employing detailed performance analysis, businesses can make informed decisions and realize their strategic goals in the digital environment. © 2024 IEEE.

关键词： Channel Performance Data Analysis Time Series Forecasting User Engagement Website Performance

来源：评论

学校读者我要写书评

暂无评论

Real Time Eye-Tracking Mouse Control Using Recurrent Neural Network

Real Time Eye-Tracking Mouse Control Using Recurrent Neural ...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Balakrishnan, D. Mariappan, Umasree Niteesh, Vedula Reddy, Yeruva Akhileswara Reddy, Vangala Mahesh Reddy, Velagala Venkata Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnakoil India Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Virudhunagar India

ISBN: (纸本)9798350315455

Machine Learning (ML) techniques, specifically Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost), were employed to achieve precise and intuitive real-time eye tracking mouse control through computer vision. However, XGBoost may suffer from overfitting when dealing with a large number of features compared to the training data size, or when dealing with noisy or imbalanced data. To address this issue, this paper introduces a Recurrent Neural Network (RNN), for eye tracking mouse control in Human computer Interaction (HCI). Gaze Direction Estimation (GDE) is initially employed to estimate gaze direction, utilizing pupil positions and camera calibration parameters. The estimated gaze direction is then used as input for the RNN to eye-tracking mouse control for HCI. The experimental results shows that the GDE-RNN has 26.03% and 8.24% superior accuracy, 24.93% and 86.76% better precision, and 27.36% and 8.75% high recall in comparison to SVM and XGBoost for eye tracking mouse control. © 2023 IEEE.

关键词： Eye tracking gaze direction estimation human computer interaction mouse control recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

A dual hashing-based authentication and secure data transmission scheme for vehicular cloud environment using MECC with optimal resource allocation mechanism

引用

Soft Computing 2024年第17-18期28卷 10423-10437页

作者： Varalakshmi, J. Dhanasekaran, S. Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil India Department of Information Technology Kalasalingam Academy of Research and Education Krishnankoil India

Vehicle cloud computing (VCC) is a recent area of study that blends vehicular networks with cloud computing, offering networking and sensor capabilities to vehicles for interaction with other vehicles and roadside infrastructure. Integrating unidentified vehicles and infrastructure through a public network has raised concerns about security and privacy in VCC. Several researchers have proposed secure authentication mechanisms to address these issues and ensure secure data transmission in VCC. However, exchanging vehicle data in a vehicular cloud (VC) system presents specific challenges, including maintaining data privacy and implementing lightweight authentication procedures. Therefore, this study proposes an efficient authentication and secure data transfer mechanism for VC systems. The proposed approach utilizes Dual Hashing-based Secure Hashing Algorithm-384 (DHS384) and Modified Elliptical Curve Cryptography (MECC). An optimal resource allocation (RA) scheme is introduced to allocate VC resources optimally to a suitable virtual machine using the Improved Harris Hawks Optimization (IHHO) algorithm. Simulation results demonstrate that the proposed method outperforms existing approaches and enhances security. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Earlier Detection of Plant Disease and Recommending Pesticides using Convolutional Neural Network

Earlier Detection of Plant Disease and Recommending Pesticid...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Balakrishnan, D. Mariappan, Umasree Kavya, Dyapa Sindhuja, Nerella Srija, Anugu Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnakoil India Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Virudhunagar India

ISBN: (纸本)9798350315455

Plant disease detection systems may face challenges in accurately distinguishing between various diseases, especially when symptoms overlap or environmental factors introduce ambiguity, impacting the system's reliability. The agricultural innovation described involves an integrated system for early plant disease detection and targeted pesticide recommendations. It utilizes preprocessing, feature extraction, and advanced classification algorithms. Data from IoT sensors and high-resolution imaging devices are collected to monitor crop conditions and remove image noise using Gaussian smoothing. Feature extraction, particularly the Histogram Oriented Gradients method, is employed to identify disease symptoms and environmental parameters. Advanced machine learning algorithms, including Convolutional Neural Networks (CNN), are used to classify diseases and recommend pesticides based on disease type, severity, crop, and environmental conditions. This innovation enhances timely disease identification and promotes more precise and sustainable pesticide use, leading to increased agricultural productivity and reduced environmental impact. MATLAB is used for research evaluation, showing 7% superior performance compared to existing methodologies. © 2023 IEEE.

关键词： Agricultural Innovation Convolutional neural network Gaussian smoothing Histogram oriented gradients pesticides Plant disease

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：