检索结果-内蒙古大学图书馆

3rd International Conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Aswathi, K.P. Yadwad, Sunita Raj, D. Nirmal Rastogi, Shailesh Chennai Institute of Technology Department of Computer Science and Engineering Chennai India Parul University Faculty of Engineering and Technology Department of Computer science and Engineering Vadodara India Pune India Pune India

ISBN: (纸本)9798331508456

As the Internet becomes increasingly image-centric, users face substantial challenges in efficiently locating desired images due to the inherent limitations of image search engines in interpreting visual content and keyword ambiguity. This paper introduces an innovative solution employing psychological intention diagrams to enhance search accuracy. These diagrams harness historical data to depict the search intentions associated with specific keywords, reflecting both user and web designer perspectives. By integrating these diagrams, our proposed search engine significantly refines its ability to predict and retrieve the most relevant images. The implementation of this system involves constructing two types of intention diagrams: one based on past user queries and another derived from the intentions of web designers for cases without historical user data. This dual approach not only captures the semantic essence of images more effectively but also addresses the multi-faceted meanings of search keywords. Our experimental results confirm that incorporating psychological dimensions into image search mechanisms substantially improves precision, facilitating more accurate and user-aligned image retrieval. This pioneering approach is the first to apply psychological profiling in enhancing image search engine functionalities, marking a significant advancement in digital image retrieval technologies. © 2025 IEEE.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Mitigating denial of service attacks in fog-based wireless sensor networks using machine learning techniques

引用

Journal of Data, information and Management 2023年第4期5卷 207-225页

作者： Abidoye, Ademola P. Obagbuwa, Ibidun C. Azeez, Nureni A. Department of Computer Science and Information Technology Clayton State University Morrow GA United States Department of Computer Science and Information Technology Sol Plaatje University Kimberley South Africa Department of Computer Sciences University of Lagos Lagos Nigeria

Wireless sensor networks are considered to be among the most significant and innovative technologies in the twenty-first century due to their wide range of industrial applications. Sensor nodes in this networks are susceptible to a variety of assaults due to their special qualities and method of deployment. In WSNs, denial of service attacks are common attacks in sensor networks. It is difficult to design a detection and prevention system that would effectively reduce the impact of these attacks on WSNs. In order to identify assaults on WSNs, this study suggests using two machine learning models: decision trees and XGBoost. The WSNs dataset was the subject of extensive tests to identify denial of service attacks. The experimental findings demonstrate that the XGBoost model, when applied to the entire dataset, has a higher true positive rate (98.3%) than the Decision tree approach (97.3%) and a lower false positive rate (1.7%) than the Decision tree technique (2.7%). Like this, with selected dataset assaults, the XGBoost approach has a higher true positive rate (99.01%) than the Decision tree technique (97.50%) and a lower false positive rate (0.99%) than the Decision tree technique (2.50%). © This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply 2023.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Incremental Federated Learning for Weather Prediction with UAV based Data Collection 18

Real-Time Incremental Federated Learning for Weather Predict...

引用

18th IEEE International Conference on Vehicular Electronics and Safety, ICVES 2024

作者： Singhal, Priyansh Hazra, Abhishek Joshi, Piyush Indian Institute of Information Technology Sri City Department of Computer Science and Engineering India

ISBN: (纸本)9798350387278

This article presents a comprehensive framework for real-time incremental federated learning aimed at enhancing weather prediction accuracy through UAV-based data collection. In our proposed system, UAVs are deployed across multiple regions within cities to gather diverse and comprehensive weather data. The collected data is streamed in real-time to central city servers, which aggregate the data and transmit it to a state-level server. At the state server, data from multiple cities are combined, and models are incrementally trained on newly received data in a step-wise manner. Each incremental step involves training on 80% of the new data and testing on the remaining 20%. Our key contribution is the integration of a weighted federated learning approach, where periodic federated learning steps utilize the weighted FedAvg algorithm. The weights are determined based on the accuracy of each model, allowing for more effective aggregation of model updates. Experimental results demonstrate a significant improvement in prediction accuracy, achieving a 24% increase compared to baseline independent machine learning models trained separately at the state level. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Proposal Intelligent Hand Gesture Recognition Using CNN 2

Proposal Intelligent Hand Gesture Recognition Using CNN

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Mahfuri, Mahmoud Ghwanmeh, Sameh Ali, Liaqat Al-Zoubi, Hani Q. International University For Science And Technology Computer And Information Technology Department Syria American University In The Emirates Department Of Computer Science United Arab Emirates College Of Engineering And Technology University Of Science And Technology Of Fujairah Fujairah United Arab Emirates College Of Engineering Mutah University Department Of Computer Engineering Jordan

ISBN: (纸本)9798350394962

This paper addresses the crucial goal of improving communication between the deaf and mute community and the broader public. We present the development of a sign language translator that effectively converts hand gestures into text, encompassing alphabets and digits, thereby facilitating comprehension of the conveyed messages. Our approach incorporates an intelligent hand gesture recognition system powered by Convolutional Neural Networks (CNNs) and utilizes a comprehensive dataset comprising 44 distinct gestures, including letters and numbers. The proposed model plays a pivotal role in preprocessing input images by employing a threshold mechanism to eliminate noise and enhance image smoothness. To ensure accuracy and continuity in the regions of interest, we implement a region filling technique. TensorFlow serves as the backend for our CNN-based Keras model, which undergoes rigorous training on the collected dataset. After the training phase, the model is rigorously tested to validate its performance. Upon successful testing, users can express their gestures, and the system displays the corresponding text representation while simultaneously converting it into speech. This groundbreaking work contributes significantly to bridging the communication gap and fostering inclusivity within our society. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Artificial Bee Colony with Cuckoo Search for Solving Service Composition

引用

Intelligent Automation & Soft Computing 2023年第3期35卷 3385-3402页

作者： Fadl Dahan Abdulelah Alwabel Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Sciences Faculty of Computing and Information Technology AlturbahTaiz UniversityTaiz9674Yemen Department of Computer Sciences College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia

In recent years,cloud computing has provided a Software As A Service(SaaS)platform where the software can be reused and applied to fulﬁll compli-cated user demands according to speciﬁc Quality of Services(QoS)*** user requirements are formulated as a workﬂow consisting of a set of ***,many services may satisfy the functionality of each task;thus,searching for the composition of the optimal service while maximizing the QoS is formulated as an NP-hard *** work will introduce a hybrid Artiﬁcial Bee Colony(ABC)with a Cuckoo Search(CS)algorithm to untangle service composition *** ABC is a well-known metaheuristic algorithm that can be applied when dealing with different NP-hard problems with an outstanding record of ***,the ABC suffers from a slow convergence ***,the CS is used to overcome the ABC’s limitations by allowing the abandoned bees to enhance their search and override the local *** proposed hybrid algorithm has been tested on 19 datasets and then compared with two standard algorithms(ABC and CS)and three state-of-the-art swarm-based composition *** addition,extensive parameter study experiments were conducted to set up the proposed algorithm’s *** results indicate that the proposed algorithm outperforms the standard algorithms in the three comparison criteria(bestﬁtness value,averageﬁtness value,and average execution time)overall datasets in 30 different ***,the proposed algorithm also exhibits better performance than the state–of–the–art algorithms in the three comparison criteria over 30 different runs.

关键词： Cloud computing web service composition artiﬁcial bee colony cuckoo search

来源：评论

学校读者我要写书评

暂无评论

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

引用

IEEE Transactions on information Forensics and Security 2025年 20卷 5888-5903页

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Qilu University of Technology Shandong Academy of Sciences Faculty of Computer Science and Technology Jinan250014 China National University of Singapore School of Computing 21 Lower Kent Ridge Rd 119077 Singapore Great Bay University School of Computing and Information Technology Dongguan523000 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Shandong Artificial Intelligence Institute Jinan250014 China Tianjin University of Technology Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Shenzhen University Computer Vision Institute College of Computer Science and Software Engineering Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. © 2005-2012 IEEE.

关键词： Salt and pepper noise

来源：评论

学校读者我要写书评

暂无评论

Data Driven Vibration Control:A Review

引用

IEEE/CAA Journal of Automatica Sinica 2024年第9期11卷 1898-1917页

作者： Weiyi Yang Shuai Li Xin Luo Chongqing Institute of Green and Intelligent Technology Chinese Academy of SciencesChongqing 400714 Chongqing School University of Chinese Academy of SciencesChongqing 400714China Faculty of Information Technology and Electrical Engineering University of OuluOulu 90570 VTT-Technology Research Center of Finland Oulu 90570Finlan College of Computer and Information Science Southwest UniversityChongqing 400715China

With the ongoing advancements in sensor networks and data acquisition technologies across various systems like manufacturing,aviation,and healthcare,the data driven vibration control(DDVC)has attracted broad interests from both the industrial and academic *** shaping(IS),as a simple and effective feedforward method,is greatly demanded in DDVC *** convolves the desired input command with impulse sequence without requiring parametric dynamics and the closed-loop system structure,thereby suppressing the residual vibration *** on a thorough investigation into the state-of-the-art DDVC methods,this survey has made the following efforts:1)Introducing the IS theory and typical input shapers;2)Categorizing recent progress of DDVC methods;3)Summarizing commonly adopted metrics for DDVC;and 4)Discussing the engineering applications and future trends of *** doing so,this study provides a systematic and comprehensive overview of existing DDVC methods from designing to optimizing perspectives,aiming at promoting future research regarding this emerging and vital issue.

关键词： Data driven vibration control(DDVC) data science designing method feedforward control industrial robot input shaping optimizing method residual vibration

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Securing information in Cyber Security system using Authentication, Intrusion Detection and Deep Learning-based Risk Prediction Tasks 5

A Novel Framework for Securing Information in Cyber Security...

引用

5th IEEE International Conference for Emerging technology, INCET 2024

作者： Naik, R. Lakshman Jain, Sourabh Department of Computer Science and Engineering Indian Institute of Information Technology Haryana Sonepat India

ISBN: (纸本)9798350361155

The cyber security has become a hot research topic nowadays. The term cyber security is frequently employed replaceable with the term data security. In recent days, each system faces the cyber security threat virtually and the model framework should have the capacity to combine the security features and work as the system's integral elements. Various works have been conducted to discover the answer to the evaluation challenge of cyber security and numerous architectures have been designed. However, the techniques face distinct issues though it is functioning well initially at the development time. Hence, an efficient and advanced cyber security framework is implemented in this paper to prevent cyber attacks using deep learning. Initially, to predict the risks in cyber security devices, the necessary data is fetched from the available resources. The gathered data is forwarded to the authentication operation and then the authenticated data is given to the intrusion detection stage. After that, the intrusion-detected data is subjected to the risk prediction stage, where the Weighted Recurrent Neural Network (WRNN) is supported to forecast the risk level of the network. Here, the Dung Beetle Optimizer (DBO) is utilized to tune the weights optimally in WRNN. This authentication, intrusion detection, and risk prediction operations have enriched the security of the cyber networks. Lastly, the efficacy and the security of the implemented model are analyzed with its related models by utilizing several performance metrics. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An Extensive Analysis of Green Cloud Computing: Overview, Associated Challenges and Research Directions 3

An Extensive Analysis of Green Cloud Computing: Overview, As...

引用

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Suratia, Nishi Thakkar, Priyansh Sheth, Kunal Ramoliya, Dipak Patel, Anand K. Department of Computer Science and Engineering Gujarat Changa India Dharmsinh Desai University Faculty of Technology Department of Information Technology India

ISBN: (纸本)9798350343632

Current questions and challenges for environmental shielding are introduced by Cloud Computing. Reliability, high performance, and scalability are application states that are offered by cloud computing technologies. The Cloud Computing revolution promises environmental protection, modern networking redesign, and economic and technological advantages. Huge data centers are needed for this facility and they are coupled with a system that increases energy consumption and enormous CO2 emissions. Since the prime concern is energy, the problem generates the need for Green Cloud Computing, which can boost the efficiency of energy and to lower down tracks of carbon and electronic waste. © 2023 IEEE.

关键词： Architecture Challenges Green Cloud Computing Green Initiatives Merits and Demerits

来源：评论

学校读者我要写书评

暂无评论

Penetration Testing-Aware IDS for Wireless Networks in Urban Digital Ecosystems Integrated with Edge Computing and Machine Learning

Penetration Testing-Aware IDS for Wireless Networks in Urban...

引用

2024 Global Congress on Emerging Technologies, GCET 2024

作者： Zhukabayeva, Tamara Ahmad, Zulfiqar Adamova, Aigul Satybaldina, Dina L.N. Gumilyov Eurasian National University Faculty of Information Technology Astana Kazakhstan Hazara University Department of Computer Science and Information Technology Mansehra21300 Pakistan

ISBN: (纸本)9798331542603

This research study introduces a new concept of Penetration Testing-Aware Intrusion Detection system (IDS) for wireless networks in urban digital environments. By integrating edge computing and machine learning with the proposed framework, it improves the security controls specific to the threats in urban wireless environments. An analysis was conducted using the UNSW-NB15 dataset for testing and validating two machine learning models of logistic regression and gradient boosting to assess their accuracy in real-time network intrusion detection. Comparing the results obtained in applying the gradient boosting and logistic regression, the first model described an accuracy of 95%, a precision-recall value of 0.97, and an AUC score of 0.94, whereas the second model described an accuracy of 88%, a precision-recall value of 0.92, and an AUC score of 0.81. The IDS also proactively passed a thorough vulnerability analysis and penetration testing and proved the possibility of the identification of a high percentage of attack scenarios with low false positives. The results of the present research highlight the importance of using machine learning approaches coupled with active vulnerability scanning to enhance the protection of wireless networks in urban digital ecosystems. © 2024 IEEE.

关键词： Adversarial machine learning

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：