检索结果-内蒙古大学图书馆

7th International Conference on computing Methodologies and Communication, ICCMC 2023

作者： Ramapriya, B. Kalpana, Y. School of Computing Science Department of Information Technology VISTAS Chennai India

ISBN: (纸本)9781665464086

Steganography is considered a reliable solution for avoiding third-party attacks. It is the process of embedding confidential information in another image. So that, they can be sent to the user's end with full security. When it comes to data privacy and authentication, steganography techniques are essential. This proposedmedical image steganography procedure by exploiting Dual Tree-Complex Wavelet Transform based transform and image encryption procedure were proposed in this proposed work. Then an improved SSOAoptimization algorithm is engaged to detect smooth edge blocks. As a result, the selection of pixels for embedding is facilitated. Embedding the Secret data into the cover image is then done using a double matrix XOR encoding. After the embedding process, the stego image is produced. The Stego output image is further compressed with Huffman Coding which produces the stego Compressed image. The stego image is compressed for fast transmission of secret data via the wireless network. Thus, the proposed method shows the best results with high payload capacity, security, and image quality than the existing methods. Testing was performed on PSNR, MSE, IF, and SSIM metrics to verify the performance of proposed methodologies. © 2023 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Wind Speed Forecasting Using Bi-LSTM with Selected Features

引用

Intelligent Automation & Soft computing 2023年第3期35卷 3829-3844页

作者： Siva Sankari Subbiah Senthil Kumar Paramasivan Karmel Arockiasamy Saminathan Senthivel Muthamilselvan Thangavel Department of Computer Science and Engineering Sreenivasa Institute of Technology and Management StudiesChittoor517127India School of Information Technology&Engineering Vellore Institute of TechnologyVellore632014India School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India School of Computing College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur603203India

Wind speed forecasting is important for wind energy *** the modern era,the increase in energy demand can be managed effectively by fore-casting the wind speed *** main objective of this research is to improve the performance of wind speed forecasting by handling uncertainty,the curse of dimensionality,overﬁtting and non-linearity *** curse of dimensionality and overﬁtting issues are handled by using Boruta feature *** uncertainty and the non-linearity issues are addressed by using the deep learning based Bi-directional Long Short Term Memory(Bi-LSTM).In this paper,Bi-LSTM with Boruta feature selection named BFS-Bi-LSTM is proposed to improve the performance of wind speed *** model identiﬁes relevant features for wind speed forecasting from the meteorological features using Boruta wrapper feature selection(BFS).Followed by Bi-LSTM predicts the wind speed by considering the wind speed from the past and future time *** proposed BFS-Bi-LSTM model is compared against Multilayer perceptron(MLP),MLP with Boruta(BFS-MLP),Long Short Term Memory(LSTM),LSTM with Boruta(BFS-LSTM)and Bi-LSTM in terms of Root Mean Square Error(RMSE),Mean Absolute Error(MAE),Mean Square Error(MSE)and *** BFS-Bi-LSTM surpassed other models by producing RMSE of 0.784,MAE of 0.530,MSE of 0.615 and R2 of *** experimental result shows that the BFS-Bi-LSTM produced better forecasting results compared to others.

关键词： Bi-directional long short term memory boruta feature selection deep learning machine learning wind speed forecasting

来源：评论

学校读者我要写书评

暂无评论

An indoor delivery robot based on YOLOv8 and ROS 7

An indoor delivery robot based on YOLOv8 and ROS

引用

2024 7th International Conference on Intelligent Manufacturing and Automation, IMA 2024

作者： Sun, Zhijin Fan, Jianan Lu, Jialin Zhang, Lei Li, Xiaoyang Deng, Baoru School of Electronic Information Engineering Zhuhai College of Science and Technology Zhuhai China School of Mechanical Engineering Zhuhai College of Science and Technology Zhuhai China School of Computing Zhuhai College of Science and Technology Zhuhai China

Aiming at the problems of inflexible movement, poor operation efficiency, low space utilization in the storage area and poor compatibility of placed items, intelligent route planning ability and weak intelligent obstacle avoidance ability in the current indoor delivery robot operation process, this paper takes ROS combined with YOLOv8 as the intelligent driving core, uses the A∗ algorithm to make the robot go to the target position, plan a reasonable route, take STM32 as the intelligent control core, and use the Mecanum wheel as the power take-off wheel. Based on this, an indoor delivery robot based on ROS and the McNum wheel motion scheme is designed. This paper designs the robot as a whole, designs the mechanical structure and functional modules of the robot, and simulates and analyzes the obstacle avoidance scheme and key functions of intelligent driving. Experiments have proved that the design of the delivery robot can not only achieve efficient and accurate distribution, but also reduce energy consumption to a certain extent, and provide new ideas for the intelligent transformation and development of the logistics industry. © Published under licence by IOP Publishing Ltd.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

SketchBoard: Sketch-Guided Storyboard Generation for Game Characters in the Game Industry 22

SketchBoard: Sketch-Guided Storyboard Generation for Game Ch...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Chan, Elicia Min Yi Seow, Chee Kiat Tan, Esther Su Wee Wang, Min Yau, Peter Chunyu Cao, Qi School of Computing Science University of Glasgow Singapore School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China

ISBN: (纸本)9798331527471

Research outcomes have been reported to various industrial applications of Artificial Intelligence generated content (AIGC). This paper explores AI assisted creative production of storyboard and game characters in the game industry, by leveraging Stable Diffusion 1.5 coupled with Control Nets (SD-1.5+CN) for image generations and Generative Pretrained Transformer (GPT) of OpenAI for narrative generations. Experiment evaluations are conducted for visual appeal and narrative flows of the generated contents using SketchBoard. The results illustrate SketchBoard with weighted prompts achieving a higher Contrastive Language-Image Pre-Training (CLIP) score than the baseline models. In addition to reducing the time and effort required for manual creation, it obtains strong alignments between the generated images and provided text prompts. User study is conducted where the user feedback indicates a high level of satisfaction, with 92% of participants expressing enjoyment and contentment with SketchBoard. Its ability to generate visually appealing storyboard frames with coherent narratives offers opportunities for efficient storyboard creation, paving the way for future advancements in automated storyboard generation. © 2024 IEEE.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Multiuser Computation Offloading for Long-Term Sequential Tasks in Mobile Edge computing Environments

引用

Tsinghua science and technology 2023年第1期28卷 93-104页

作者： Huanhuan Xu Jingya Zhou Wenqi Wei Baolei Cheng School of Computer Science and Technology Soochow UniversitySuzhou 215006China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214125China Provincial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou 215006China School of Computer Science Georgia Institute of TechnologyAtlantaGA 30332USA

Mobile edge computing has shown its potential in serving emerging latency-sensitive mobile applications in ultra-dense 5G networks via offloading computation workloads from the remote cloud data center to the nearby network ***,current computation offloading studies in the heterogeneous edge environment face multifaceted challenges:Dependencies among computational tasks,resource competition among multiple users,and diverse long-term *** applications typically consist of several functionalities,and one huge category of the applications can be viewed as a series of sequential *** this study,we first proposed a novel multiuser computation offloading framework for long-term sequential ***,we presented a comprehensive analysis of the task offloading process in the framework and formally defined the multiuser sequential task offloading ***,we decoupled the long-term offloading problem into multiple single time slot offloading problems and proposed a novel adaptive method to solve *** further showed the substantial performance advantage of our proposed method on the basis of extensive experiments.

关键词： mobile edge computing sequential tasks computation offloading dependency

来源：评论

学校读者我要写书评

暂无评论

An Explainable Intelligent Intrusion Detection System

An Explainable Intelligent Intrusion Detection System

引用

2024 International Symposium on Networks, Computers and Communications, ISNCC 2024

作者： Mahmoud, Maiada Youssef, Yasser Omar Abdel-Hamid, Ayman College of Computing and Information Technology Arab Academy for Science Technology and Maritime Transport Egypt School of Library and Information Studies University of Oklahoma United States

ISBN: (纸本)9798350364910

In the rapidly evolving field of cybersecurity, sophisticated cyber threats pose significant challenges to Intrusion Detection Systems (IDS). Machine learning (ML) models have become increasingly integral to IDS, leveraging their ability to analyze extensive data and perceive complex patterns indicative of potential threats. However, despite their effectiveness, the black-box nature of many ML models poses a challenge their adoption in critical security environments. This paper focuses on increasing trust in ML-based IDS through eXplainable Artificial Intelligence (XAI) and improving model interpretability. Various ML models, including LinearSVC, Stochastic Gradient Descent (SGD) classifiers, Decision Tree, Random Forest, and XGBoost, were trained and tested on the CICIDS2017 dataset. Superior performance was demonstrated by XGBoost, achieving 0.99 accuracy, precision, recall, and F1-score, with notably low FNR of 0.0005 and FPR of 0.0016. SHapley Additive exPlanations (SHAP) was employed to enhance transparency and trust by providing insights into the model's decision-making process. The results underscore XGBoost's effectiveness in intrusion detection while minimizing false alarms, highlighting the importance of interpretability in cybersecurity. This paper validates the efficacy of XGBoost and emphasizes XAI's critical role rendering ML models more transparent and trustworthy. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Predicting software vulnerability based on software metrics: a deep learning approach

引用

Iran Journal of Computer science 2024年第4期7卷 801-812页

作者： Agbenyegah, Francis Kwadzo Asante, Micheal Chen, Jinfu Akpaku, Ernest Department of Computer Science Kwame Nkrumah University of Science and Technology Kumasi Ghana School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Department of Information Technology Faculty of Computing and Information Systems Ghana Communication Technology University Accra Ghana

The security of IT systems is the topmost priority of software developers. Software vulnerabilities undermine the security of computer systems. Lately, there have been a lot of reported issues of software vulnerabilities recorded in individuals and corporate systems. Software metrics-based techniques have been used and found to be effective due to low false positives and false negatives. However, there are software metrics that have not been investigated and could have an impact on the performance of the predictive model. In this study, we developed an ensemble deep learning algorithm made of LSTM, CNN, and MLP models with the non-investigated metrics as a feature to learn the latent representation of code metrics to predict anomalies in source code effectively. We trained the proposed model on the SySeVR datasets and compared the model's performance against five deep learning algorithms and four state-of-the-art SVPs. The proposed model performs better than the other deep learning with a classification accuracy of 96.17%, and a precision of 97.72%. The model's classification accuracy is 4.98% higher than that of the five deep learning models and 1.71% lower in precision than the state-of-the-art SVP. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Deep learning Machine learning Software metrics Software security Software vulnerabilities

来源：评论

学校读者我要写书评

暂无评论

Multiple moving object classification and tracking using DenCNN classifier

引用

Journal of Intelligent and Fuzzy Systems 2024年第5-6期46卷 11311-11329页

作者： Premanand, V. Arulalan, V. Kumar, Dhananjay School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Chengalpattu District Tamil Nadu Kattankulathur India Department of Information Technology Anna University Madras Institute of Technology Campus Tamil Nadu Chennai India

A Multiple moving object detection, tracking, and counting algorithm is mainly designed exclusively suitable for congested areas. The counting system can alleviate the betrayal performance in the crowded areas. Most of the existing methods developed for tracking and counting face serious challenges in detection due to high densities of the target. This condition urged the researchers to update the existing systems. The present methodology was designed to address such issues. In the present methodology, the contrast was initially enhanced between the objects and their backgrounds using a Double Plateau Histogram Equalization (DPHE). Then, the motion was estimated for the contrast-enhanced image to identify the moment of the object using the modified Adaptive Distance Covariance Rood Pattern Search (ADCRPS) algorithm. After that, the morphological operation was deployed to sharpen the images by removing all the unwanted things. Then, the features were extracted and important features were selected using the modified Chaotic Tent Shuffled Shepherd Optimization (CTSSO) Algorithm. With the selected features object, detection was done using the proposed Scaled Non-Monotonic Cauchy Dense Convolutional Neural Network (SNMC-DenCNN). The detected object was then tracked with the aid of Channel and Spatial Reliability Tracker (CSRT). Finally, the objects were counted by intersection over union (IOU) by explicitly computing the association between detected and tracked objects. Also, the experimental results showed the effectiveness and efficiency of the proposed system with enhanced accuracy. © 2024 - IOS Press. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Two-step Runge–Kutta methods for Volterra integro-differential equations

引用

International Journal of Computer Mathematics 2024年第1期101卷 37-55页

作者： Wen, Jiao Huang, Chengming Guan, Hongbo College of Mathematics and Information Science Zhengzhou University of Light Industry Zhengzhou China School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan China

In this paper, we investigate two-step Runge–Kutta methods to solve Volterra integro-differential equations. Two-step Runge–Kutta methods increase the order of convergence in comparing the classical Runge–Kutta method without extra computational cost. First, the local order conditions and convergence theorem are derived. Then, stability properties of two-step Runge–Kutta methods corresponding to the basic and convolution test equations are analysed. Furthermore, one-stage method with order four and two-stage method with order six are constructed and we plot the stability regions. Numerical examples are presented to confirm the theoretical analyses. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Industrial Control Anomaly Detection Based on Distributed Linear Deep Learning

引用

Computers, Materials & Continua 2025年第1期82卷 1129-1150页

作者： Shijie Tang Yong Ding Huiyong Wang School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin541004China School of Electronic Engineering and Automation Guilin University of Electronic TechnologyGuilin541004China Guangxi Engineering Research Center of Industrial Internet Security and Blockchain Guilin University of Electronic TechnologyGuilin541004China Institute of Cyberspace Technology HKCT Institute for Higher EducationHong Kong999077China School of Mathematics&Computing Science Guilin University of Electronic TechnologyGuilin541004China

As more and more devices in Cyber-Physical Systems(CPS)are connected to the Internet,physical components such as programmable logic controller(PLC),sensors,and actuators are facing greater risks of network attacks,and fast and accurate attack detection techniques are *** key problem in distinguishing between normal and abnormal sequences is to model sequential changes in a large and diverse field of time *** address this issue,we propose an anomaly detection method based on distributed deep *** method uses a bilateral filtering algorithm for sequential sequences to remove noise in the time series,which can maintain the edge of discrete *** use a distributed linear deep learning model to establish a sequential prediction model and adjust the threshold for anomaly detection based on the prediction error of the validation *** method can not only detect abnormal attacks but also locate the sensors that cause *** conducted experiments on the Secure Water Treatment(SWAT)and Water Distribution(WADI)public *** experimental results show that our method is superior to the baseline method in identifying the types of attacks and detecting efficiency.

关键词： Anomaly detection CPS deep learning MLP(multi-layer perceptron)

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：