检索结果-内蒙古大学图书馆

3TFL-XLnet-CP: A Novel Transformer-Based Crop Yield Prediction Framework with Weighted Loss Based 3-Tier Feature Learning Model

引用

SN computer science 2025年第3期6卷 1-17页

作者： Anoop, G.L. Nandini, C. Naresh, E. Department of Computer Science and Engineering Christ University Karnataka Bengaluru India Department of Computer Science and Engineering Dayananda Sagar Academy of Technology and Management Karnataka Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

The advancement of crop yield prediction through artificial intelligence (AI) has gained significant attention. However, the existing AI-based approaches for maximizing agricultural productivity, specifically in crop yield prediction, have not consistently delivered satisfactory results. In response to this challenge, we propose a novel framework named as Three Tier Feature Learning with XLnet based Crop Prediction (3TFL-XLnet-CP) that enhances agricultural productivity by accurately predicting crop yield. The 3TFL-XLnet-CP framework employs a three-tier feature learning approach in combination with the powerful XLnet transformer-based crop prediction model. The three-tier feature learning involves the integration of Spiking Neural Network (SNN), Graphical Neural Network (GNN), and Convolutional Neural Network (CNN) to extract distinct feature vectors from the preprocessed data. These feature vectors are then concatenated using Jaccard Similarity to measure their similarity score. Additionally, a weighted Loss function is introduced to optimize feature learning, further enhanced by a novel self-adaptive Spider Monkey Optimization algorithm (SASMO). The concatenated features are subsequently fed into the classification layer for making precise crop yield predictions. The proposed model is implemented using the Python platform and evaluated against existing models such as ANN, RNN, DNN, and BiLSTM. The comparison demonstrates the superiority of our proposed 3TFL-XLnet-CP framework in accurately predicting crop yield. © The Author(s) 2025.

关键词： 3TFL-XLnet-CP Convolutional neural network Crop yield prediction Graphical neural network Spiking neural network

来源：评论

学校读者我要写书评

暂无评论

Climate Geoscience–Based Disaster management in Healthcare Analysis by Markov Q-Transfer Adversarial with Cloud Computing

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 474-483页

作者： Srinivas, Jhade Rebecca, B. Bhargavi, Kovvuri N Swetha, Velma Reddy Spandana, S. Degala, Divya Priya Department of Computer Science and Engineering-Data Science KG Reddy College of Engineering and Technology Moinabad Telangana Hyderabad India Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Telangana Dundigal 500043 India Department of CSE Aditya University AP Surampalem India Department of Computer Science and Engineering (AI-ML) Malla Reddy Engineering College Hyderabad India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Bowrampet Telangana Hyderabad India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Analysis and reaction to natural disasters have made extensive use of deep learning methods using semantic segmentation networks. These implementations’ foundation is based on convolutional neural networks (CNNs), which are capable of precisely identifying and locating the relevant areas of interest within satellite imagery or other types of remote sensing data. This helps with rescue planning, restoration efforts, and disaster evaluation. Difficulties in the provision of healthcare services, due to natural disasters, are made worse by the existing problems prevalent in most healthcare systems. The aim of this research is to propose a novel technique in climate change–based disaster management with their public healthcare analysis using cloud computing with deep learning techniques. In this research, the cloud network has been used in LiDAR image collection for climate change–based disaster-struck regions and their public healthcare analysis. This collected image has been classified and optimized using a deep Markov Q-transfer adversarial neural network with binary grey whale swarm optimization. Experimental analysis has been carried out for various disaster management–based public healthcare datasets in terms of classification accuracy, specificity, NSE, sensitivity, and F-1 score. The proposed technique attained a classification accuracy of 97%, F-1 score of 94%, specificity of 96%, sensitivity of 95%, and NSE of 57%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Adversarial neural network Cloud computing Disaster management LiDAR image Whale swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Privacy Preservation in IoT Devices by Detecting Obfuscated Malware Using Wide Residual Network

引用

computers, Materials & Continua 2024年第11期81卷 2395-2436页

作者： Deema Alsekait Mohammed Zakariah Syed Umar Amin Zafar Iqbal Khan Jehad Saad Alqurni Applied College Department of Computer Science and Information TechnologyPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia College of Computer and Information Sciences King Saud UniversityRiyadh11362Saudi Arabia College of Computer and Information Sciences Prince Sultan UniversityRiyadh11586Saudi Arabia Department of Educational Technologies College of EducationImam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia

The widespread adoption of Internet of Things(IoT)devices has resulted in notable progress in different fields,improving operational effectiveness while also raising concerns about privacy due to their vulnerability to virus ***,the study suggests using an advanced approach that utilizes machine learning,specifically the Wide Residual Network(WRN),to identify hidden malware in IoT *** research intends to improve privacy protection by accurately identifying malicious software that undermines the security of IoT devices,using the MalMemAnalysis ***,thorough experimentation provides evidence for the effectiveness of the WRN-based strategy,resulting in exceptional performance measures such as accuracy,precision,F1-score,and *** study of the test data demonstrates highly impressive results,with a multiclass accuracy surpassing 99.97%and a binary class accuracy beyond 99.98%.The results emphasize the strength and dependability of using advanced deep learning methods such as WRN for identifying hidden malware risks in IoT ***,a comparison examination with the current body of literature emphasizes the originality and efficacy of the suggested *** research builds upon previous studies that have investigated several machine learning methods for detecting malware on IoT ***,it distinguishes itself by showcasing exceptional performance metrics and validating its findings through thorough experimentation with real-world *** WRN offers benefits in managing the intricacies of malware detection,emphasizing its capacity to enhance the security of IoT *** summarize,this work proposes an effective way to address privacy concerns on IoT devices by utilizing advanced machine learning *** research provides useful insights into the changing landscape of IoT cybersecurity by emphasizing methodological rigor and conducting comparative performance *** research co

关键词： Obfuscated malware detection IoT devices Wide Residual Network(WRN) malware detection machine learning

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing-Based Earth Climate Detection in Geoscience Model with Artificial Intelligence Application

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 569-581页

作者： Agarkar, Aarti Amod Karyakarte, Mandar S. Chavhan, Gajanan Ariffin, I.A. Patil, Milind Ushasree, Linginedi Priya, D. Divya Vishwakarma Institute of Technology Pune India Management and Science University Selangor Shah Alam Malaysia Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Remote sensing technology can offer exact information in an image format, it has permeated every sector related to natural resources. Right now, the source of geographic area data that is expanding the fastest is satellites used for remote sensing. Change detection is a highly valuable tool for monitoring environmental and human demands, given the constant changes in the earth’s surface and the extensive use of remote sensing. A significant capacity for estimating climate change has been made possible by combining machine learning (ML) models with remote sensing imagery. This methodology takes less data than traditional methods and relaxes a number of assumptions. Influential variables for estimating climate change using machine learning models are provided by satellite imagery. In this research, climate change detection has been analysed for geoscience modelling based on remote sensing data and ML models. Remote-sensed region images have been collected in which the pre-processing is carried out for noise removal, normalisation, and smoothening. This processed image’s features have been selected using a linear principal recurrent component neural network and classified using a random graph SqueezeNet perceptron neural network. The simulation results have been analysed for various remote-sensed region image data in terms of random accuracy, average precision, RMSE, recall, and F-measure. The proposed technique has a random accuracy of 96%, average precision of 97%, F-measure of 87%, RECALL of 85%, and RMSE of 61%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Climate change detection Geoscience modelling Random graph perceptron Recurrent component Remote sensing data

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based AI Solutions for Personal Finance management

Cloud-Based AI Solutions for Personal Finance Management

引用

2025 International Conference on Pervasive Computational technologies, ICPCT 2025

作者： Chhabra, Gurpreet Kaur Mishra, Ashutosh Kumar Tyagi, Varsha Mani, Chandra Tyagi, Vani Sagar, Pramod Kumar Management Education and Research Institute Department of Management Delhi India Srm Business School Department of Management UP Lucknow India Raj Kumar Goel Institute of Technology Computer Science & Engineering UP Ghaziabad India Mangalmay Institute of Engineering & Technology Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798331508685

Cloud-based AI answers for private finance control are out-of-the-field tools that leverage synthetic intelligence and cloud computing technologies to manage people's money higher. In this article, I have described various solutions with features ranging from budgeting to personalized financial planning and investment suggestions. Utilizing superior system learning algorithms and cloud-based AI solutions can help understand an individual's fiscal information, including expenses, profits, or savings transactions, for generating personalized insights and advice. This lets people learn about their spending habits and make more informed financial choices. Through the power of the cloud, these solutions can securely store and access financial data from multiple devices, which helps individuals, manage their finances on the go easily. It also enables the client to get real-time updates and notifications, which offers him more comprehensive knowledge regarding his existing financial scenario. These offerings also come with more automation features like reminders to pay payments and computerized enough transfers for a price range, keeping customers from spending further effort and time on their funds. They also offer financial advisors, tax planning tools, and wealth management. © 2025 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Smart Job Scheduling Model for Cloud Computing Network Application

引用

SN computer science 2024年第1期5卷 39页

作者： Onyema, Edeh Michael Gude, Venkataramaiah Bhatt, Ashutosh Aggarwal, Ambika Kumar, Sunil Benson-Emenike, Mercy Eberechi Nwobodo, Lois Onyejere Department of Vocational and Technical Education Faculty of Education Alex Ekwueme Federal University Ndufu-Alike Abakaliki Nigeria Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India GP Technologies LLC Texas United States Department of Computer Science and Engineering Shivalik College of Engineering Dehradun India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Computer Science Federal University of Technology Owerri Nigeria Department of Computer Engineering Enugu State University of Science and Technology Enugu Nigeria

Task scheduling is one of the significant factors for heterogeneous type of elements in multi-cloud computing environment. It is to delegate activities to most adequate resources to raise the performance with respect to some dynamic parameters. The suggested model of scheduling was designed to run applications of cloud computing which applied in three steps (classifying, execution, minimization, and rating) and is assumed to be completion time, average waiting and turnaround time, and render duration as output parameters. The tasks’ execution time in cloud computing applications was created in the task scheduling model by exponential and normal distribution. The task ranking depends on the shortest strategy for First Job and the results are compared with other “Largest Processing Time” and “First Come First Serve” ranking method. Scheduling model proposed provides significant output than per performance parameters specified. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cloud computing Directed acyclic graph (DAG) Smart scheduling

来源：评论

学校读者我要写书评

暂无评论

The Most Important Factors Chosen in Medical Clinical Data by Using Multi-Facet Clustering Variational Autoencoders (MFCVAE) 24

The Most Important Factors Chosen in Medical Clinical Data b...

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： Zeng, Zhihong Chang, Dong-Meau Hsu, Tse-Chuan Liang, Zhou College of Mathematics and Information Engineering Longyan University China School of Computer Science and Intelligence Education Lingnan Normal University China Soochow University Department of Computer Science & Information Management Taipei111 Taiwan

ISBN: (纸本)9798350365658

In medical practice, doctors often need the support of various medical measuring data to diagnose diseases. In clinical observation, doctors will sort out various factors related to the cause of the disease based on the patient's condition. MFCVAE is a principled, probabilistic clustering model which finds multiple partitions of data simultaneously through its multiple Mixtures-of-Gaussians (MoG) prior. Our model lies in the framework of variational autoencoders, and is trained fully unsupervised. MFCVAE discovers a disentangled multi-facet structure in an exploratory setting, allows to compose representations of inputs in the latent space, perform generative classification, and generate diverse, synthetic samples. This article used the patient data of hospital patients and the MFCVAE method be used to find the most relevant factors and provide them as a reference for doctors in disease diagnosis. The research results was shown that the top 10 important factors could be found from 186 clinical factors using the MFCVAE method. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Hybrid RNN Based Text Classification Model for Unstructured Data

引用

SN computer science 2024年第6期5卷 726页

作者： Sunagar, Pramod Sowmya, B.J. Pruthviraja, Dayananda Supreeth, S. Mathew, Jimpson Rohith, S. Shruthi, G. Cloudthat Technologies Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education School of Computer Science and Engineering REVA University Department of Computer Science and Engineering Indian Institute of Technology Patna Department of ECE Nagarjuna College of Engineering and Technology

The volume of social media posts is on the rise as the number of social media users expands. It is imperative that these data be analyzed using cutting-edge algorithms. This goal is handled by the many techniques used in text categorization. There are a variety of text categorization techniques available, ranging from machine learning to deep learning. Numerical crunching has become easier with less processing time since the emergence of high-end computer facilities. This has led to the development of sophisticated network architectures that can be trained to achieve higher precision and recall. The performance of neural network models which was evaluated by the F1 score is affected by cumulative performance in precision and recall. The current study intends to analyze and compare the performance of the neural network proposed, A Hybrid RNN model that has two layers of BiLSTM and two layers of GRU to that of previous hybrid models. GloVE dataset is used to train the models and their accuracy, precision, recall, and F1 score are used to assess performance. Except for the RNN + GRU model, the RNN + BILSTM + GRU model has a precision of 0.767, a recall of 0.759, and an F1-score of 0.7585. This hybrid model outperforms the others. © The Author(s) 2024.

关键词： Bidirectional long-short-term memory (BiLSTM) Gated recurrent units (GRU) Recurrent neural networks (RNN) Region-based convolutional neural networks (RCNN) Text classification

来源：评论

学校读者我要写书评

暂无评论

An Operative Expectation of Parkinson’s Ailment Using a Hybrid Machine Learning and Artificial Intelligence Systems

引用

SN computer science 2024年第8期5卷 1146页

作者： Athithan, Senthil Sachi, Savya Singh, Ajay Kumar Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of information technology Lalit Narayan Mishra College of Business Management Bihar Muzaffarpur 842001 India Computer Science and Engineering Department Chandigarh University Uttar Pradesh Unnao India

Human biosignals can be used to detect early signs of Parkinson’s disease (PD). Electroencephalography (EEG) measures brain signals, while electromyography (EMG) measures muscle signals, both of which are useful in studying functional and neuronal changes in Parkinson’s patients. Researchers extracted various time and frequency domain features from EEG and EMG signals of early-stage PD patients and control subjects (CS) to identify motor symptoms. A diagnostic tool based on a mathematical model utilizing an artificial neural network (ANN) and a graphical user interface was developed. The ANN-based classifier, using the EEG and EMG features as inputs, accurately identified early-stage PD patients from control subjects with a classification rate of approximately 100%. The combination of EEG and EMG characteristics resulted in the highest recognition rate of 99.1%. This model demonstrated near-perfect accuracy, with an R-value of 0.9976, indicating its precision. Additionally, it achieved a low validation mean square error of 0.0068 and an elapsed time of 1.32 s. Studies show that combining EEG and EMG features as input parameters effectively distinguishes PD patients from control subjects. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： EEG Frontal Brain Neurological Disorder Parkinson’s Disease Temporal Brain

来源：评论

学校读者我要写书评

暂无评论

Enhanced Emotion Recognition Using a Hybrid Autoencoder-LSTM Model Optimized with a Hybrid ACO-WOA Algorithm for Hyperparameter Tuning

引用

International Journal of Advanced computer science and Applications 2025年第4期16卷 861-876页

作者： Waiker, Vinod Ramesh, Janjhyam Venkata Naga Bala, Ms Kiran Krishnaiah, V.V. Jaya Rama Jackulin, T. Muniyandy, Elangovan Shahin, Osama R. Datta Meghe Institute of Management Studies Maharashtra Nagpur India Department of CSE Graphic Era Hill University Dehradun248002 India Department of CSE Graphic Era Deemed To Be University Uttarakhand Dehradun248002 India Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of CSE Panimalar Engineering College Tamil Nadu Chennai India Department of Biosciences-Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602 105 India Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Science College of Computer and Information Sciences Jouf University Saudi Arabia Physics and Mathematics Department Faculty of Engineering Helwan University Helwan Egypt

Emotion recognition is vital in the human computer interaction because it improves interaction. Therefore, this paper proposes an improved method for emotion recognition regarding the Hybrid Autoencoder-Long Short-Term Memory (LSTM) model and the newly developed hybrid approach of the Ant Colony Optimization (ACO) and Whale Optimization Algorithm (WOA) for hyperparameters tuning. In this case, Autoencoder can reduce input data dimensionality for input data and find the features relevant for the model’s work. In addition, LSTM is able to work with temporal structures of sequential inputs like speech and videos. The contribution of this research lies in the novel combination method of ACO-WOA which aims at tweaking hyperparameters of Autoencoder-LSTM model. Global aspect of ACO and WOA thereby improve the search efficiency and the accuracy of the proposed emotion recognition system and its generalization capacity. In context with the benchmark dataset for the experimentations of emotion recognition, it has established the efficiency of the proposed model in terms of the conventional methods. Recall rates in recognitive intended various emotions and different modalities were also higher in the hybrid Autoencoder-LSTM model. The optimization algorithms like the ACO-WOA also supported in reducing the computational cost which arose due to hyperparameters tuning. The implementation of this paper is done through Python Software. This implementation shows a high accuracy of 94.12% and 95.94% for audio datasets and image datasets respectively when compared with other deep learning models of Conv LSTM and VGG16. Therefore, the research shows that the presented hybrid approach can be a useful solution for successfully employing emotion recognition for enhancing the creation of the empathetic AI systems and for improving user interactions within various fields including healthcare, entertainment, and customer support. © (2025), (science and Information Organization). All rights

关键词： Ant colony optimization

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：