检索结果-内蒙古大学图书馆

Optimal trained ensemble of classification model for satellite image classification

Multimedia Tools and Applications 2025年第7期84卷 3745-3766页

作者： Singh, Sarabjeet Kundra, Harish Kundra, Sheetal Pratima, P. Venkata Devi, M. V. Anjana Kumar, Sushil Hassan, Mariya Department of Computer Science and Engineering Chandigarh College of Engineering and Technology Chandigarh160019 India Department of Computer Science and Engineering Guru Nanak Institutions Technical Campus Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Artificial Intelligence and Data Science Guru Nanak Institute of Technology Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Computer Science and Engineering Central University of Haryana Jant-Pali Mahendergarh123031 India

Satellite image classification is the most significant remote sensing method for computerized analysis and pattern detection of satellite data. This method relies on the image's diversity structures and necessitates a thorough validation of the training data using the chosen classification algorithm. The classifying of remotely sensed images refers to the process of classifying pixels into a fixed set of distinct classes based on their data values. The pixel is categorized into that class if it complies with a specific set of requirements. A new SIC scheme is suggested in this work, where, Contrast limited adaptive histogram equalization (CLAHE) is deployed for pre-processing the image. Further, statistical features, Vegetation Indices (VI) and Improved Hybrid Vegetation Index (IHVI) are extracted from the preprocessed image. Then, we deploy 2 phase classification process for classifying the image. In the first phase, Bi-Directional Gated Recurrent Unit (BI-GRU), Convolutional Neural Network (CNN) and Deep Max Out (DMO) are used. In 2nd phase, optimized RNN is used for determining the final classification result. Also, the training of the model is done by the new Chaotic Opposition Behavior Improvised Coot Algorithm (COBI-CA) optimization via tuning the optimal weights. The COOT method has been enhanced and is now the suggested algorithm. Lastly, we conduct an analysis to compare the suggested Satellite Image Classification (SIC) model's performance to the traditional approaches in terms of statistical analysis, precision, accuracy, and error measure. In comparison to other conventional methods, the accuracy of the suggested model is 97%. © This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Cyberbullying detection based on the fusion of DistilBERT and SIMHASH Technique 2

Cyberbullying detection based on the fusion of DistilBERT an...

引用

2nd International Conference on Artificial Intelligence and Machine Learning Applications, AIMLA 2024

作者： Kumar, Chintoo Arun Kumar, K. Gupta, Suneet Sardar, Tanvir Habib GITAM Department of Computer Science and Engineering Bengaluru India ACED Alliance Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350349221

The advent of social network sites increases the bullying content in textual and visual formats. Bullying content disheartened a user or community to a great extent. Also detection of cyberbullying content is a challenging task, especially in online social networks where individuals can be harassed or harmed..Recently, using pre-trained language models has played a pivotal role in solving this problem reasonably. In this paper, we employed a fusion of a transformer-based model and the SIMHASH technique to solve this classification problem. We consider a readily available cyberbullying dataset. We conducted a comparative study among state-of-the-art models to check the proposed model's efficacy. The proposed model provides a promising result and outperforms. © 2024 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Real-Time Challenges and Opportunities for an Effective Resource Management in Multi-cloud Environment

引用

SN computer science 2024年第2期5卷 1-8页

作者： Basha, H. Anwar Anilkumar, B.H. Swetha, G. Reddy, Raghavendra Manoli, Sunil Department of Computer Science and Engineering Rajalakshmi Institute of Technology Tamilnadu Chennai India Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India R R Institute of Technology Bengaluru India School of Computer Science and Engineering REVA University Bengaluru India

As the usage of multi-cloud setups grows, resource management will become a major concern. Because of the dynamic nature of these environments, as well as fluctuating workloads and service-level targets, an effective algorithm for real-time resource allocation and optimisation is required. The Adaptive Multi-Cloud Resource Management Algorithm (AMCRMA) is proposed in this study to handle the obstacles and capitalise on the benefits of resource management in a multi-cloud context. To ensure optimal resource utilisation, cost effectiveness, and service performance, AMCRMA incorporates real-time monitoring, workload prediction, and intelligent resource allocation. Experiment results show that AMCRMA is successful in adapting to changing situations and managing resources in real time, resulting in enhanced resource utilisation and overall performance in multi-cloud systems. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： AMCRMA Cloud federation Cloud orchestration Data management Intelligent resource allocation Resource management

来源：评论

学校读者我要写书评

暂无评论

Provably Secure Efficient Key-Exchange Protocol for Intelligent Supply Line Surveillance in Smart Grids

引用

IEEE Internet of Things Journal 2025年第12期12卷 21784-21792页

作者： Ayub, Muhammad Faizan Li, Xiong Mahmood, Khalid Alenazi, Mohammed J. F. Das, Ashok Kumar Wang, Guijuan University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh12311 Saudi Arabia International Institute of Information Technology Hyderabad Center for Security Theory and Algorithmic Research Hyderabad500032 India Korea University College of Informatics Department of Computer Science and Engineering Seoul02841 Korea Republic of Key Laboratory of Computing Power Network and Information Security Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Ministry of Education Shandong Computer Science Center Jinan250353 China

Intelligent supply line surveillance is critical for modern smart grids (SGs). Smart sensors and gateway nodes are strategically deployed along supply lines to achieve intelligent surveillance. They collect data continuously and transmit it to the control centre in real-time. It enables real-time monitoring, fault detection, and efficient energy management across distribution networks. This advanced surveillance system ensures continuous monitoring of supply lines, detecting anomalies, and optimizing operations to maintain the stability and reliability of the SG. However, the reliance of all participating nodes on public communication channels to transmit supply line surveillance data exposes these systems to critical cyber attacks. These cyber attacks include impersonation, physical tampering, ephemeral secret leakage (ESL), and desynchronization attacks. To address these issues, existing key-exchange protocols often fail to ensure robust security while imposing high computation and communication overheads, limiting their practicality for resource-constrained environments. Therefore, we propose a secure and efficient key exchange and tamper-resistant authentication protocol using elliptic curve cryptography (ECC) and physical unclonable functions (PUFs). The PUF mechanism provides robust resistance against physical tampering and cloning attacks, ensuring enhanced physical security for supply line devices. We validate the security robustness of the devised protocol using the random or real (ROR) model. Furthermore, informal security analysis demonstrates the protocol’s robustness in rigorously resisting various attacks, including physical tampering, impersonation, ESL and desynchronization. Moreover, we determine the performance evaluation that reveals the protocol’s superior efficiency compared to competing protocols, achieving significant reductions of 28.64% in computation overhead and 9.96% in communication overhead. © 2014 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

A machining center selection study using neural networks

引用

Neural Computing and Applications 2025年 1-38页

作者： Ic, Yusuf Tansel Yıldız, Burak Kececi, Barış Sert, Mustafa Department of Industrial Engineering Baskent University Ankara06970 Turkey Department of Computer Engineering Baskent University Ankara06970 Turkey Department of Electrical Engineering and Computer Science University of California IrvineCA92697 United States

Machining centers (MCs) are crucial high-technology machine tools that are widely used in the manufacturing industry. Since their high investment necessities, the selection of the appropriate MC for a company is an important task so that the company’s competitive advantages can be continued in the future. In the literature, there are many studies for MC selection using multi-criteria decision-making (MCDM) models and their fuzzy versions. This type of selection model must use selection criteria weighting procedures that are mainly based on subjective preferences. On the other hand, some attempts are provided in the literature to set objective decision-making models, such as the design of an experiment (DoE)-based Technique for Order Preferences by Similarity to the Ideal Solution (TOPSIS) model. In this study, we improved the DoE-based TOPSIS approach using neural network-based solutions and compared their capability of the MC selection studies against the classical MCDM and DoE-TOPSIS models. The proposed model can handle the newly generated scenarios using the Neural Networks. The feedforward neural network (FFNN)-based model utilizes machine learning techniques to overcome some of the challenges by modeling the complex relationships among various decision criteria without relying on human judgment for weighting. As a form of artificial neural network, FFNNs learned from large datasets and captured non-linear patterns, making them well-suited for the MC selection problem. Their capability to process high-dimensional inputs with numerous variables and interactions aligns effectively with the complexities of the MC selection problem. Therefore, the proposed FFNN model is very competitive against the DoE-TOPSIS and classical TOPSIS models. © The Author(s) 2025.

关键词： Cutting

来源：评论

学校读者我要写书评

暂无评论

Color Image Compression and Encryption Algorithm Based on 2D Compressed Sensing and Hyperchaotic System

引用

computers, Materials & Continua 2024年第2期78卷 1977-1993页

作者： Zhiqing Dong Zhao Zhang Hongyan Zhou Xuebo Chen School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China School of Electronic and Information Engineering University of Science and Technology LiaoningAnshan114051China

With the advent of the information security era,it is necessary to guarantee the privacy,accuracy,and dependable transfer of *** study presents a new approach to the encryption and compression of color *** is predicated on 2D compressed sensing(CS)and the hyperchaotic ***,an optimized Arnold scrambling algorithm is applied to the initial color images to ensure strong ***,the processed images are con-currently encrypted and compressed using 2D *** them,chaotic sequences replace traditional random measurement matrices to increase the system’s ***,the processed images are re-encrypted using a combination of permutation and diffusion *** addition,the 2D projected gradient with an embedding decryption(2DPG-ED)algorithm is used to reconstruct *** with the traditional reconstruction algorithm,the 2DPG-ED algorithm can improve security and reduce computational ***,it has better *** experimental outcome and the performance analysis indicate that this algorithm can withstand malicious attacks and prove the method is effective.

关键词： Image encryption image compression hyperchaotic system compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Strain modified nano-scale Ge/Ge0.98Sn0.02 exotic pin photo-sensor array for IR sensing: theoretical reliability and experimental feasibility studies

引用

Optical and Quantum Electronics 2024年第12期56卷 1-20页

作者： Bhadra, Bias Chinara, Suchismita Kundu, Abhijit Department of Computer Science and Engineering Chaibasa Engineering College Jharkhand Chaibasa India Department of Computer Science and Engineering NIT Rourkela Odisha Rourkela India Department of Electronics and Communication Engineering Chaibasa Engineering College Jharkhand Chaibasa India

In this paper, the superiority of Ge/Ge0.98Sn0.02asymmetrical supper lattice structure based vertically doped nano-scale pin photo-sensor under operating wavelength of 1200 nm to 2200 nm is reported. The authors have developed non-linear Strain Modified Quantum-Corrected Drift–Diffusion (SMQCDD) model for analyzing the electrical and optical characteristics of the photo-sensor. The inclusion of a small amount of Sn (2%) into the pure Ge material creates in-plane bi-axial strain in the intrinsic region (i-region) of the device. This results in increases in the value of the out-plane mobility of the charge particles. As a result, the overall performance of the photo-sensor enhances significantly. The authors have used in-plane induced bi-axial strain to accelerate the out-plane mobility of the charge particles by incorporation of the exotic asymmetrical supper lattice structure in the i-region of the photo-sensor. The validation of the non-linear SMQCDD model is performed through comparison of the simulated data obtained from SMQCDD model with the experimental results under a-like thermal/structural/electrical conditions. Additionally, the authors have designed 3X2 array of photo-sensors and studied the photo-electrical characteristics at the said operating wavelength. The proposed device offers better performance in terms of quantum efficiency (0.619: single-type photo-sensor;0.708: array-type photo) and photo-responsivity (0.056 A/W: single-type photo-sensor;0.808 A/W:for array-type photo-sensor)at 1600 nm wavelength compared to its conventional flat Si counterpart. The developed exotic pin photo-sensor can be used as a sensing device for applications in optical communication and bio-medical systems. As far as the authors are aware, this is the first report on nano-scale Ge/Ge0.98Sn0.02exotic pin photo-sensor. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Nanocrystals

来源：评论

学校读者我要写书评

暂无评论

Registration of CT Images of Lung Using Fireworks Algorithm 1

引用

2nd International Conference on Human-Centric Smart Computing, ICHCSC 2023

作者： Nayak, Somen Mondal, Subhodip Obaid, Ahmed J. Department of Computer Application University of Engineering and Management Rajasthan Jaipur India Department of Computer Science and Engineering University of Engineering and Management Rajasthan Jaipur India Department of Computer Science and Mathematics Department of Computer Science University of Kufa Najaf Iraq

ISBN: (数字)9789819977116

ISBN: (纸本)9789819977109

The acquisition of medical images from various modalities can provide a number of practical challenges that can be addressed through medical image registration. Intensity-based registration methods, which are used in multi-modal registration, merge multiple images with the same content into a single representation by applying image transformation. It is essential to edit photographs as best as you can. It is highly important to improve the similarity measure between the various photographs. We introduce a new method for registering lung’s CT image affected with COVID-19 in this work since the image registration process is fundamentally an improvement problem. Lung computed tomography image registration is a technique for aligning pre- and post-contrast images for analysis the effect of COVID-19 virus in the lung. A meta-heuristics-based optimization technique called FWA-IATF was explored for registering lung CT images. Following that, the FWA-IATF algorithm successfully registers the images. The results of registration based on the FWA-IATF method and PSO approach are compared. The results indicate that the FWA-IATF-based registration methods outperform the PSO-based registration approach while registering lung CT images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An Experimentation for generating Text-based Medical Report from Chest X-Ray images using Attention based Deep Learning Models 3

An Experimentation for generating Text-based Medical Report ...

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Rana, Jainil Thakkar, Amit Shah, Bela Department of Computer Science & Engineering CSPIT CHARUSAT Gujarat India Department of Computer Science & Engineering PIET Parul University Gujarat India

This study investigates the efficacy of attention-based deep learning models for generating text-based medical reports from chest X-ray images. Four distinct models were developed and evaluated: a basic encoder-decoder model (Model 1), an encoder-decoder architecture using an attention mechanism (Model 2), a model incorporating spatial feature preservation (Model 3), and a model with a bidirectional GRU in the decoder (Model 4). We trained and evaluated these models using the Indiana University Chest X-ray dataset (Open-i), employing the BLEU score as the primary performance metric. Model 1, using a greedy search decoding strategy, achieved an average BLEU score of 0.619. Incorporating an attention mechanism in Model 2 resulted in a modest improvement, reaching a BLEU score of 0.667 with beam search decoding. Model 3, preserving spatial information during feature extraction, further enhanced performance, achieving a BLEU score of 0.718. Finally, Model 4, integrating a bidirectional GRU, yielded the highest performance with a BLEU score of 0.745. Our results highlight the significant impact of attention mechanisms and spatial feature preservation in generating more accurate and detailed medical reports. The study highlights the potential of deep learning models for automating medical report generation, paving the way for further research and development in this domain. © 2025 The Author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Job Candidate Eligibility Prediction using Convolutional Neural Network 4

Job Candidate Eligibility Prediction using Convolutional Neu...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Shaw, Mayank Kumar Dey, Prianka Chowdhury, Sagarika Ghosh, Tanmoy University of Calcutta Department of Computer Science and Engineering India Narula Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350349900

The foundation of the applicant selection process is the candidate eligibility criteria. All applications must go through some evaluation process to get selected for a job. Without the use of a machine learning algorithm, the traditional method can require a great deal of time and work from the recruiter and force candidates to wait weeks or months for their results, depending on how many applications there are. It can be completed in a couple of minutes or even seconds with the help of machine learning algorithms. For employees who need this data to decide whether the applicants qualify, this enhancement may prove to be a significant benefit even though there are additional factors to take into account, such as fraud prevention and background checks. Applying convolution neural network to these kinds of challenges has produced quite encouraging outcomes. In this work, we attempt to apply Convolutional Neural Network integration to candidate eligibility cases using a probabilistic technique. The result shows that this technique is suitable for the scenario that requires only two states - approved or rejected-because it could generate binary classified output. Our project aims to implement Convolutional Neural Network and iterate on the approach by adjusting the approach of the network. © 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

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：