检索结果-内蒙古大学图书馆

Enhanced Object Detection and Classification via Multi-Method Fusion

computers, Materials & Continua 2024年第5期79卷 3315-3331页

作者： Muhammad Waqas Ahmed Nouf Abdullah Almujally Abdulwahab Alazeb Asaad Algarni Jeongmin Park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Engineering Tech University of Korea237 Sangidaehak-roSiheung-siGyeonggi-do15073South Korea

Advances in machine vision systems have revolutionized applications such as autonomous driving,robotic navigation,and augmented *** substantial progress,challenges persist,including dynamic backgrounds,occlusion,and limited labeled *** address these challenges,we introduce a comprehensive methodology toenhance image classification and object detection *** proposed approach involves the integration ofmultiple methods in a complementary *** process commences with the application of Gaussian filters tomitigate the impact of noise *** images are then processed for segmentation using Fuzzy C-Meanssegmentation in parallel with saliency mapping techniques to find the most prominent *** Binary RobustIndependent Elementary Features(BRIEF)characteristics are then extracted fromdata derived fromsaliency mapsand segmented *** precise object separation,Oriented FAST and Rotated BRIEF(ORB)algorithms *** Algorithms(GAs)are used to optimize Random Forest classifier parameters which lead toimproved *** method stands out due to its comprehensive approach,adeptly addressing challengessuch as changing backdrops,occlusion,and limited labeled data concurrently.A significant enhancement hasbeen achieved by integrating Genetic Algorithms(GAs)to precisely optimize *** minor adjustmentnot only boosts the uniqueness of our system but also amplifies its overall *** proposed methodologyhas demonstrated notable classification accuracies of 90.9%and 89.0%on the challenging Corel-1k and MSRCdatasets,***,detection accuracies of 87.2%and 86.6%have been *** ourmethod performed well in both datasets it may face difficulties in real-world data especially where datasets havehighly complex *** these limitations,GAintegration for parameter optimization shows a notablestrength in enhancing the overall adaptability and performance of our system.

关键词： BRIEF features saliency map fuzzy c-means object detection object recognition

来源：评论

学校读者我要写书评

暂无评论

An Innovation Development of Decentralized Prove Piercing Data Recuperation Using Improved Red in Mobile Grid Computing 2

An Innovation Development of Decentralized Prove Piercing Da...

引用

2nd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Karthikeyan, S. Thomas, Merin Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

The recent advancements in mobile computing have opened up the possibilities of decentralized data recovery in mobile grid computing. With the help of improved Red (Recovery of Erased Data) technique, data recovery can be done in a decentralized manner. This method is a combination of distributed computing, data replication, and data recovery algorithms which improves the data recovery process. The improved Red technique uses distributed computing to replicate the data and store it in multiple nodes in the grid. This helps to ensure that the data is distributed and available in multiple nodes for recovery. Data recovery is done by the Red algorithm which traverses the grid and identifies the nodes which have the data and then recovers it. The algorithm uses a technique called "greedy search"to identify the nodes which have the data. This helps to reduce the time and cost associated with the recovery process. The improved Red technique also makes use of data replication which helps to improve the data recovery process. The data is replicated and stored in multiple nodes which helps to improve the speed of data recovery. The replication process helps to ensure that the data is always available and can be recovered quickly. The improved Red technique also makes use of distributed computing to improve the scalability of the data recovery process. The distributed computing helps to ensure that the data recovery process can be done efficiently and quickly. The data recovery process can also be done on a large scale which helps to improve the speed of data recovery. © 2023 IEEE.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

A General Scalable Approach for Knowledge Selection based on Iterative Hybrid Encoding and Re-ranking

引用

Data Intelligence 2025年第1期7卷 124-142页

作者： Zhisheng Huang Xudong Jia Tao Chen Zhongwei Zhang Faculty of Intelligent Manufacturing Wuyi UniversityJiangmen 529020GuangdongChina College of Engineering and Computer Science California State UniversityNorthridge CA 91330USA

Knowledge selection is a challenging task that often deals with semantic drift issues when knowledge is retrieved based on semantic similarity between a fact and a question. In addition, weak correlations embedded in pairs of facts and questions and gigantic knowledge bases available for knowledge search are also unavoidable issues. This paper presents a scalable approach to address these issues. A sparse encoder and a dense encoder are coupled iteratively to retrieve fact candidates from a large-scale knowledge base. A pre-trained language model with two rounds of fine-tuning using results of the sparse and dense encoders is then used to re-rank fact candidates. Top-k facts are selected by a specific re-ranker. The scalable approach is applied on two textual inference datasets and one knowledge-grounded question answering dataset. Experimental results demonstrate that (1) the proposed approach can improve the performance of knowledge selection by reducing the semantic drift;(2) the proposed approach produces outstanding results on the benchmark datasets. The code is available at https://***/hhhhzs666/KSIHER.

关键词： Knowledge selection Textual inference Semantic drift Coarse-to-Fine

来源：评论

学校读者我要写书评

暂无评论

A Way to Mark Attentance using Face Recognition using PL 3

A Way to Mark Attentance using Face Recognition using PL

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Vivek, V. Tr, Mahesh Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350399264

The computer system that is used to take attendance online is going to be upgraded as part of this project. This attendance tracking system is able to hold the technology known as facial recognition, which is a useful feature. This device helps students take attendance by utilizing both a biometric technology and artificial intelligence algorithms in one convenient package. When pupils enter the classroom, the face recognition software can identify them, making it useful for educational institutions of any kind. The existing system has a number of flaws that make it difficult to accurately record the attendance of both students and teachers. The approach makes it simpler to mark attendance and lowers the number of mistakes that might occur when doing *** students and teachers will gain a significant amount by utilizing these techniques. The ability to recognize people based on their faces is becoming increasingly significant in practically every industry. Face recognition techniques will be used to understand the faces. An attendance record is compared to the record that corresponds to it that was previously saved in the database. A student's photograph is used as a check point for this comparison. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Novel Anomaly Detection Scheme for Cyber Physical System using C-GAN in Fog assisted IoT Environment 2

Novel Anomaly Detection Scheme for Cyber Physical System usi...

引用

2nd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Mathur, Ashwini Babu, S. Anantha Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

An Internet of Things (IoT) appears to be an innovative technology with great potential for widespread development. There has been a rise in data security issues in recent years as a consequence of various technological developments. Despite the proliferation of security precautions, criminals have learned to circumvent them. We employ a Contingently Generative Adversarial Network in our research to detect harmful online behaviour (CC-GAN). Our proposed system employs CC-GAN, which can identify novel threats, to carry out intrusion detection based on anomalies. An Internet-of-Things layer, a fog layer, as well as a cloud layer make up the whole of our proposed fog-based infrastructure. The IoT layer consists of many connected devices, and it is here that the CC-GAN receives the training data it needs to learn to recognise potential security breaches. A convolutional neural network & encoder are trained on the cloud layer, where additional computing takes place. Adding a fog layer might help decrease the delay. Finally, the attack detection score is evaluated. For this exercise, we use the network simulator version 2.6. (NS 3.26). The simulation result shows that the proposed system achieves a higher detection rate than the state-of-the-art systems. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with a Novel Concoction Loss Function for Identification of Ophthalmic Disease

引用

computers, Materials & Continua 2023年第9期76卷 3763-3781页

作者： Sayyid Kamran Hussain Ali Haider Khan Malek Alrashidi Sajid Iqbal Qazi Mudassar Ilyas Kamran Shah Department of Computer Science TIMES InstituteMultan60000Pakistan Department of Software Engineering Faculty of Computer ScienceLahore Garrison UniversityLahore54000Pakistan Department of Computer Science Applied CollegeUniversity of TabukTabukSaudi Arabia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl Hofuf31982Saudi Arabia Department of Mechanical Engineering College of EngineeringKing Faisal UniversityAl HofufSaudi Arabia

As ocular computer-aided diagnostic(CAD)tools become more widely accessible,many researchers are developing deep learning(DL)methods to aid in ocular disease(OHD)*** eye diseases like cataracts(CATR),glaucoma(GLU),and age-related macular degeneration(AMD)are the focus of this study,which uses DL to examine their *** imbalance and outliers are widespread in fundus images,which can make it difficult to apply manyDL algorithms to accomplish this analytical *** creation of efficient and reliable DL algorithms is seen to be the key to further enhancing detection *** the analysis of images of the color of the retinal fundus,this study offers a DL model that is combined with a one-of-a-kind concoction loss function(CLF)for the automated identification of *** study presents a combination of focal loss(FL)and correntropy-induced loss functions(CILF)in the proposed DL model to improve the recognition performance of classifiers for biomedical *** is done because of the good generalization and robustness of these two types of losses in addressing complex datasets with class imbalance and *** classification performance of the DL model with our proposed loss function is compared to that of the baseline models using accuracy(ACU),recall(REC),specificity(SPF),Kappa,and area under the receiver operating characteristic curve(AUC)as the evaluation *** testing shows that the method is reliable and efficient.

关键词： Deep learning multi-classification focal loss CNN eye disease

来源：评论

学校读者我要写书评

暂无评论

Smart irrigation system using IoT and machine learning methods 5

Smart irrigation system using IoT and machine learning metho...

引用

5th International IEEE Novel Intelligent and Leading Emerging sciences Conference, NILES 2023

作者： Esmail, Ahmed A. Ibrahim, Manar A. Abdallah, Sayed M. Radwan, Ahmed E. Elsonbaty, Haya K. Elsayed, Mohamed A. Elnakeib, Noure A. Dawoud, Merit Samir El-Ghamry, Amir Fouad, Khaled M. Moawad, Ibrahim F. New Mansoura University Artificial Intelligence Science Faculty of Computer Science and Engineering Dakhlia Egypt Mansoura University Faculty of Computer Science and Engineering New Mansoura University Information Technology Faculty of Computer and Information Sciences Egypt Mansoura University Faculty of Computer Science and Engineering New Mansoura University Faculty of Computer and Information Sciences Egypt University of Hertfordshire Hosted by Global Academic Foundation School of Engineering and Computer Science Egypt Benha University Information Systems Faculty of Computers and Artificial Intelligence Egypt New Mansoura University Faculty of Computer Science and Engineering Dakhlia Egypt Ain Shams University Cairo Information Systems Faculty of Computer and Information Sciences Egypt

ISBN: (纸本)9798350381030

Water loss and improper scheduling are problems with traditional irrigation techniques, making it difficult to meet the growing demand for food production while also preserving precious water resources. To address these challenges, this paper introduces a cutting-edge smart irrigation system that leverages the power of the Internet of Things (IoT), data analysis, and machine learning to determine the most efficient way to apply and schedule water for irrigation. The cornerstone of this innovative system is the utilization of a carefully curated dataset, "Crop Irrigation Scheduling,"sourced from Kaggle. This dataset comprises six crucial attributes: Crop Type, Crop Days, Soil Moisture, Temperature, Humidity, and Irrigation. These attributes, described in detail in the dataset's metadata, provide the foundational information required for precise irrigation management. The system operates seamlessly by deploying IoT sensors to collect real-time data from the field. This data is then preprocessed to ensure its quality and consistency. Subsequently, a machine learning model is trained using this dataset to make intelligent irrigation decisions in real time. The model's predictions are seamlessly integrated with control mechanisms that govern the irrigation process. Moreover, the system offers an intuitive API for easy data access and management, allowing agricultural professionals to monitor and adjust irrigation strategies effortlessly. Experimental findings validate the system's utility, with particular emphasis on the decision tree model, which demonstrates the best balance of accuracy, precision, recall, and F1 score. This system maximizes crop yield and minimizes water waste, contributing to a more sustainable and productive agricultural ecosystem. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Interpretable Arabic Hate Speech Detection using Large Language Model 2

Interpretable Arabic Hate Speech Detection using Large Langu...

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Alwateer, Majed Gad, Ibrahim Elmarhomy, Mahmoud Elmarhomy, Ghada Hashim, Hasan Almaliki, Malik Atlam, El-Sayed College of Computer Science and Engineering Taibah University Department of Computer Science Saudi Arabia Tanta University Faculty of Science Computer Science Department Tanta31527 Egypt College of Applied Taibah University Computer Science and Information Saudi Arabia College of Computer Science and Engineering Taibah University Department of Information Systems Saudi Arabia

ISBN: (纸本)9798331506995

Social media platforms serve as significant spaces for users to have conversations, discussions and express their opinions. However, anonymity provided to users on these platforms allows the spread of hate speech and other offensive material. Due to the wide-ranging nature of these platforms, there is a critical need to automatically detect and report occurrences of hate speech. There are various detection methods, but many of them operate as black boxes, lacking interpretability and explainability by design. To address the lack of interpretability, this study explores the development of an interpretable framework to detect hate speech in Arabic using large language models (LLMs). The proposed approach combines advanced natural language processing techniques with interpretable machine learning methods to enhance understanding of model decisions. The experimental results demonstrate that the model achieves high accuracy while maintaining interpretability, enabling users to understand the reasoning behind the detections. The proposed method achieves an accuracy of 0.846%, with a precision of 0.843% and a recall of 0.846%, outperforming existing Arabic hate speech detection models. These results show the effectiveness of combining LLM with interpretability for this critical task, providing a reliable and transparent solution for automated moderation of harmful content. © 2025 IEEE.

关键词： Arabic Hate Speech Detection Large Language Mode XAI

来源：评论

学校读者我要写书评

暂无评论

YOLOV9 Driven Internet of Things Enabled Sustainable Solution for Intelligent Traffic Light Management System for Emergency Vehicles in Large Scale Urban Traffic 2

YOLOV9 Driven Internet of Things Enabled Sustainable Solutio...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Vijay Ganesh, P. Sam Joshua, V. Saro Murugan, L. Mahalakshmi, S. Karpagam Academy of Higher Education Deemed to be University Department of Computer Science and Engineering Coimbatore India Karpagam Academy of Higher Education Deemed to be University Faculty of Engineering Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331505745

Due to densely populated urban environment leads to huge traffic in peak hours, Intelligent traffic light management system becomes paramount for emergency vehicle transportation on leveraging the sensor technologies. However sensor data acquired from densely populated urban environment helps to process the traffic congestion based traffic density. Many researches has been carried out to enable intelligent transportation system using internet of things, artificial intelligence and communication technologies but still it requires sustainable solutions for intelligent transportation., traffic congestion management, traffic light controlling with respect to the detection of emergency vehicles like ambulance as it saves the life of the human being. In this paper, AI driven Intelligent of Things enabled sustainable solutions for intelligent traffic light management system for emergency vehicles in the large scale urban traffic. Initially sensor or camera deployed in the smart cities monitors the roads and its surroundings environments. Those acquired information is transmitted to the base station containing IoT servers. In IoT Server., video data is transformed into image frames and processed using YoloV9 based AI model. YoloV9 Model uses multiple component like backbone., neck and head for processing the image frame to recognize and tack the objects in each frame. Especially Backbone model employs convolution neural network for multi scale feature extraction and feature map generation on inclusion of the Generalized Efficient aggregation Network while neck component uses the path aggregation network for future fusion process and head component uses anchor box bounding box prediction method to detect and recognize the object of interest. On detect of the object of interest, distance and speed of the object is computed using gradient flow. Further model incorporates prediction approaches to detected emergency vehicle to estimate its speed and distance from traffic signal

关键词： Ambulances

来源：评论

学校读者我要写书评

暂无评论

The New Development of Steganography Technique for Problem Solving of Gaussian Blur

The New Development of Steganography Technique for Problem S...

引用

2023 International Conference on Networking, Electrical engineering, computer science, and Technology, IConNECT 2023

作者： Darwis, Dedi Putri, Chintya Veronica Mehta, Abhishek R. Permata Setiawansyah Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandar Lampung Indonesia Parul University Faculty of It and Computer Science Gujarat India

ISBN: (纸本)9798350331172

Cybercrimes are increasingly invading the privacy of individuals, organizations, and governments. Personal data is increasingly insecure because of illegal data collected by unauthorized person. This study aims to develop a data embedding technique in image whose data robustness is tested when attacked by Gaussian Blur. The development of this technique uses the python programming language and the LSB (Least Significant Bit) method. By testing the gaussian blur attack using imperceptibility, fidelity, and robustness tests. The test results that have been carried out for imperceptibility testing use 25 respondents with 10 images and get a 80 percentage. The results of the fidelity test using 10 images found that an average MSE value is 0.001623 and an average PSNR value is 77.642 dB. The results of the robustness test using a blur radius of 0 to 1 on 10 stego-images obtained the message that 8 out of 10 stego-images could be extracted. © 2023 IEEE.

关键词： Steganography

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：