检索结果-内蒙古大学图书馆

Optimizing solar radiation prediction: a novel SVM approach for renewable energy systems

International Journal of Information Technology (Singapore) 2025年 1-13页

作者： Basha, S. Sharief Rao, A. Nagaraja Department of Mathematics School of Advanced Science Vellore Institute of Technology Tamil Nadu Vellore 632014 India Department of Computational Intelligence School of Computer Science & Engineering Vellore Institute of Technology Tamil Nadu Vellore 632014 India

The global transition toward renewable energy sources, driven by fossil fuel depletion and environmental imperatives, has positioned solar power as a crucial sustainable alternative. This study presents an advanced methodological framework for solar radiation (SR) prediction utilizing Support Vector Machine (SVM) techniques. The research analyzes comprehensive solar radiation data collected from India’s Vellore district throughout 2023, implementing a novel Support Vector Regression (SVR) approach with both polynomial and radial basis function (RBF) kernels. While conventional methodologies predominantly focus on minimizing training errors, our approach emphasizes reducing the generalization error bound to enhance predictive performance. The proposed model incorporates diverse meteorological parameters for SR prediction, demonstrating superior generalization capabilities compared to traditional approaches. Empirical results indicate that the SVR_rbf model significantly outperformed both SVR_poly and artificial neural network (ANN) models in SR prediction accuracy. The model's efficacy is validated through rigorous performance metrics: RMSE (10.3032), MAE (4.2728), MAPE (0.0152), and R² (0.9795). This research advances the understanding of machine learning applications in renewable energy forecasting, particularly for regions with limited meteorological data availability. Research findings enhance solar energy utilization and contribute to the transition towards sustainable energy. Future research directions may explore the integration of additional environmental parameters and the model’s adaptability across diverse geographical contexts. © Bharati Vidyapeeth's institute of Computer Applications and Management 2025.

关键词： Artificial neural network Predictive models Solar radiation Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Detecting Leaf Diseases Using Centralized CNN'S with Efficient R-CNN and Mask R-CNN

Detecting Leaf Diseases Using Centralized CNN'S with Efficie...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Pongiannan, R.K. Banerjee, Samudra Poornima, P.U. Brindha, R. Richard Pravin, A. Franklin, J. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur India Srm Institute of Science and Technology Department of Electrical and Electronics Engineering Kattankulathur India

ISBN: (纸本)9798331510022

Plant diseases have emerged as a significant concern, as they can drastically reduce both the quality and quantity of agricultural products. The research aims to identify plant leaf infections early on, enabling timely treatment to prevent the spread of diseases to other plants. The objective is to determine the severity of leaf diseases, allowing for targeted treatment based on the level of severity. Additionally, the severity of leaf diseases can help predict crop losses. This work is to improve the accuracy of leaf detection and measurement of morphological traits by Region Convolutional Neural Network (RCNN), Network namely state of the Mask region art. Experimental results verify that our automated approach effectively segments leaves from different plant families. Measured leaves of comparable size have an average relative error of about 4.6 percent for leaf length and approximately 5.7 percent for leaf width when compared to manual measurements by expert ecologists and botanists. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Diagnostic Tool for Retinal Disease Detection Using Convolutional Neural Networks 5

AI-Powered Diagnostic Tool for Retinal Disease Detection Usi...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Moovendran, Manikandan Kumar, K. K. Dhanush Sashanth, J.M. Srm Institute of Science and Technology Faculty of Engineering and Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai603203 India Chennai603203 India

ISBN: (纸本)9798350389609

Accurate and timely detection of retinal disease helps prevent severe vision impairment, although traditional diagnostics take plenty of time and are demanding to perform. This led to the design of the advanced diagnostic tool, in which AI and Convolutional Neural Networks (CNNs) will enhance the identification of retinal disorders. This system will analyze a retina image to detect among others, diabetic retinopathy and age-related macular degeneration, among others. Advanced deep learning algorithms enable the tool to rapidly identify the subtle patterns and anomalies in retinal scans, which even an astute human analyst might not identify, providing insightful and diagnostic support to healthcare experts. This AI-based approach leads to the acceleration of the diagnostic workflow and the minimization of errors, which elevates overall diagnostic accuracy and allows earlier intervention. This technology will contribute to making high-quality retinal care more accessible and efficient, finally arriving at the benefit of a patient at an earlier time of early detection and treatment. © 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

Deep Learning Video Streaming Web Application with AI Botsusing NLP

Deep Learning Video Streaming Web Application with AI Botsus...

引用

2023 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Ponmalar, P. Sridevi Singh, Shivam Agrahari, Rahul Kumar SRM Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computational Intelligence Chennai603203 India

ISBN: (纸本)9798350319200

In this digital age, online learning has become increasingly prevalent, but learners often struggle with asking questions and getting immediate clarification. To address this issue, this research paper proposes a solution in the form of a web application that uses deep learning, AI bots, and NLP to generate keywords and provide real-time responses to user queries during video playback. The title of the paper is "Deep Learning Video Streaming Web Application with AI Bots using NLP". It highlights the application's key features and technologies used, including deep learning, AI bots, and natural language processing (NLP). The problem addressed in this paper is the difficulty learners face when seeking real-time answers to their questions during online video tutorials. The proposed solution aims to address this issue by providing a platform that allows users to add questions and answers to a database, which can then be accessed during video playback. The solution presented in this paper uses a combination of deep learning, AI bots, and NLP to generate relevant keywords and provide real-time responses to user queries. The paper outlines the methodology used to develop the application and discusses the results obtained from testing the platform. The analysis output shows that the proposed solution can effectively address the issue of real-time question answering during online video tutorials. The application's use of deep learning, AI bots, and NLP allows for a more personalized and interactive learning experience. The merits of this work lie in the potential to revolutionize the online learning experience by enabling learners to ask questions and get immediate answers. Possible applications of this research include the development of similar web applications for other domains, such as customer service or technical support. Additionally, the findings of this study may inspire further research on the use of deep learning, AI bots, and NLP in online learning and other fiel

关键词： AI bots Deep-Learning NLTK (Natural Language Toolkit)

来源：评论

学校读者我要写书评

暂无评论

Gaussian weighting—based random walk segmentation and DCNN method for brain tumor detection and classification

引用

Multimedia Tools and Applications 2025年第8期84卷 4675-4702页

作者： Rani, K. Vijila Sumathy, G. Shoba, L.K. Sivalakshmi, P. Department of ECE Udaya School of Engineering Tamil Nadu Nagercoil India Department of Computational Intelligence SRM Institute Of Science and Technology Kattankulathur CampusChengalpattu Dt Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Chennai India Department of ECE R.M.K College of Engineering and Technology Tamil Nadu Chennai India

Cancer is a disease that develops when cells divide abnormally. Cancerous cells can spread to surrounding organ tissues, the bloodstream, and the lymphatic system. This process is known as metastasis, and it shortens the patients' lives. Brain cancer is a type of cancer that develops in the brain and nervous system. Typically, MR (Magnetic Resonance) scan images are used by doctors to assess the condition of tissues that have grown abnormally within the human body. A novel segmentation method with classification is specifically suggested here for assessing the tumor site. To improve the quality of an image, it first uses top hat filtering to perform the morphological process. The brain tumor region is subsequently extracted from the morphologically filtered output using the Gaussian Weighted-Based Random Walk (GWBRW) segmentation technique. Lastly, a classification operation is carried out by the Deep Convolutional Neural Network (DCNN) classifier. Five performance measures are then used to compare the segmented output with the original images. The segmentation-based assessment estimations show that the segmentation achieves higher results, with average values of 22.8160, 0.2133, and 0.9704 for PSNR, Dice, and SSIM, respectively, and lower results, with average values of 19.3997 and 422.0844 for RMSE and MSE. The segmentation results show that the suggested computation enhances the tumor region's characteristics. Eventually, the Deep Convolutional Neural Network classifier successfully classifies 96.1% of the predictions. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Graph Theory Based Self-Learning Honeypot to Detect Persistent Threats

引用

Intelligent Automation & Soft computing 2023年第3期35卷 3331-3348页

作者： R.T.Pavendan K.Sankar K.A.Varun Kumar Department of Mathematics College of EngineeringAnna UniversityChennai600025India Department of Networking and Communications School of ComputingSRM Institute of Science and TechnologyKattankulathur602203India

Attacks on the cyber space is getting exponential in recent *** penetrations and breaches are real threats to the individuals and *** security systems are good enough to detect the known threats but when it comes to Advanced Persistent Threats(APTs)they *** APTs are targeted,more sophisticated and very persistent and incorporates lot of evasive techniques to bypass the existing ***,there is a need for an effective defense system that can achieve a complete reliance of *** address the above-mentioned issues,this paper proposes a novel honeypot system that tracks the anonymous behavior of the APT *** key idea of honeypot leverages the concepts of graph theory to detect such targeted *** proposed honey-pot is self-realizing,strategic assisted which withholds the APTs actionable tech-niques and observes the behavior for analysis and *** proposed graph theory based self learning honeypot using the resultsγ(C(n,1)),γc(C(n,1)),γsc(C(n,1))outperforms traditional techniques by detecting APTs behavioral with detection rate of 96%.

关键词： Graph theory Domination Connected Domination Secure Connected Domination honeypot self learning ransomware

来源：评论

学校读者我要写书评

暂无评论

Three-Stage Transfer Learning with AlexNet50 for MRI Image Multi-Class Classification with Optimal Learning Rate

引用

Computer Modeling in engineering & sciences 2025年第1期142卷 155-183页

作者： Suganya Athisayamani A.Robert Singh Gyanendra Prasad Joshi Woong Cho School of Computing Sastra Deemed to be UniversityThanjavur613401India Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203India Department of AI and Software Engineering Kangwon National UniversitySamcheok25913Republic of Korea Department of Electronics Information and Communication EngineeringKangwon National UniversitySamcheok25913Republic of Korea

In radiology,magnetic resonance imaging(MRI)is an essential diagnostic tool that provides detailed images of a patient’s anatomical and physiological *** is particularly effective for detecting soft tissue ***,radiologists manually interpret these images,which can be labor-intensive and time-consuming due to the vast amount of *** address this challenge,machine learning,and deep learning approaches can be utilized to improve the accuracy and efficiency of anomaly detection in MRI *** manuscript presents the use of the Deep AlexNet50 model for MRI classification with discriminative learning *** are three stages for learning;in the first stage,the whole dataset is used to learn the *** the second stage,some layers of AlexNet50 are frozen with an augmented dataset,and in the third stage,AlexNet50 with an augmented dataset with the augmented *** method used three publicly available MRI classification datasets:Harvard whole brain atlas(HWBA-dataset),the School of Biomedical engineering of Southern Medical University(SMU-dataset),and The National institute of Neuroscience and Hospitals brain MRI dataset(NINS-dataset)for *** hyperparameter optimizers like Adam,stochastic gradient descent(SGD),Root mean square propagation(RMS prop),Adamax,and AdamW have been used to compare the performance of the learning ***-dataset registers maximum classification *** evaluated the performance of the proposed classification model using several quantitative metrics,achieving an average accuracy of 98%.

关键词： MRI tumors classification AlexNet50 transfer learning hyperparameter tuning optimizer

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Face Detection: VisionaryNet's Breakthrough in Unraveling Facial Camplexity 2

Revolutionizing Face Detection: VisionaryNet's Breakthrough ...

引用

2nd International Conference on Computer, Communication and Control, IC4 2024

作者： Nallarasan, V. Arivazhagan, N. Lakshminarayanan, R. Sharmila, D. Sangolgi, Nagaveni B Anand, M. Srm Institute of Science and Technology School of Computing Department of Networking and Communications Chengalpattu Kattankulathur India Srm Institute of Science and Technology School of Computing Department of Computational Intelligence Chengalpattu Kattankulathur India Kpr Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India Sharnbasva University Department of Electronics and Communication Engineering Kalaburagi India Srm Institute of Science and Technology Department of Computing Technologies Chengalpattu Kattankulathur India

ISBN: (纸本)9798350387933

The initial step in facial recognition and analysis systems often involves facial detection. Traditional methods like Haar cascades and directed gradient histograms relied on manually designed features, limiting their effectiveness in diverse image environments. However, the emergence of deep learning in computer vision has accelerated the development of face detection frameworks, significantly improving accuracy. Detecting small-scale faces, varying positions, occlusions, blurs, and partially obscured faces in uncontrolled settings remains a persistent challenge in face identification. To address this, we propose a new approach called 'Visionary Net.' This single-stage face detector has undergone refinements, boosting both detection speed and accuracy. We tested Visionary Net on two well-known datasets: Mega Face and CelebA. Notably, on the Mega Face benchmark, our method achieved an impressive AP of 48.5 at a speed of 15.2 FPS using single-scale inference and an exceptional AP of 52.7 with multi-scale inference. Implementing it with the PyTorch framework resulted in a remarkable 97.3% accuracy in successfully detecting faces. Our comprehensive experiments show that Visionary Net surpasses existing models, demonstrating superior detection and recognition capabilities across various evaluation metrics. This innovative algorithm holds significant promise for robust face detection in challenging real-world scenarios. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Riemannian Exponential Augmented Lagrangian Method for computing the Projection Robust Wasserstein Distance 37

A Riemannian Exponential Augmented Lagrangian Method for Com...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Jiang, Bo Liu, Ya-Feng Ministry of Education Key Laboratory of NSLSCS School of Mathematical Sciences Nanjing Normal University Nanjing210023 China State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781713899921

Projection robust Wasserstein (PRW) distance is recently proposed to efficiently mitigate the curse of dimensionality in the classical Wasserstein distance. In this paper, by equivalently reformulating the computation of the PRW distance as an optimization problem over the Cartesian product of the Stiefel manifold and the Euclidean space with additional nonlinear inequality constraints, we propose a Riemannian exponential augmented Lagrangian method (REALM) for solving this problem. Compared with the existing Riemannian exponential penalty-based approaches, REALM can potentially avoid too small penalty parameters and exhibit more stable numerical performance. To solve the subproblems in REALM efficiently, we design an inexact Riemannian Barzilai-Borwein method with Sinkhorn iteration (iRBBS), which selects the stepsizes adaptively rather than tuning the stepsizes in efforts as done in the existing methods. We show that iRBBS can return an Ε-stationary point of the original PRW distance problem within O(Ε-3) iterations, which matches the best known iteration complexity result. Extensive numerical results demonstrate that our proposed methods outperform the state-of-the-art solvers for computing the PRW distance. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

A Fertilizer Recommendation System for Rice Leaf Plant 9

A Fertilizer Recommendation System for Rice Leaf Plant

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Murugan, Subhiksha Manikandan, A. Hariprasad, S. College of Engineering and Technology Srm Institute of Science and Technology Department of Electronics and Communication Engineering Kattankulathur Chennai603203 India School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur Chennai603203 India

ISBN: (纸本)9798350377972

The secret to increasing crop productivity and sustainability is precision farming. Optimizing fertilizer use is essential in rice cultivation to satisfy the unique nutrient requirements of crops while reducing environmental effect. Conventional techniques focus on general principles, which frequently result in reduced yields, deteriorated soil, and inefficient nutrient usage. The AI-based fertilizer recommendation system RiceFert, created for rice leaf plants, is presented in this work. The system examines crop-specific information, soil characteristics (such as type and nutrient levels), and environmental data (temperature, humidity, and wetness) using a Random Forest (RF) model and deep learning techniques. Data preparation, feature extraction, and model training are all part of the process, which compares classifiers such as Random Forest, SVM, Gradient Boosting, and Naive Bayes. The Random Forest model is superior at recommending fertilizer based on performance criteria like accuracy, precision, recall, and F1-score. This focused strategy reduces excessive or inadequate fertilizer use, increasing rice output and promoting sustainable farming. RiceFert demonstrates the potential of AI in precision agriculture by offering farmers personalized guidance that improves crop output, lowers costs, encourages environmental conservation, and helps farmers make better decisions. © 2024 IEEE.

关键词： Deep Learning Fertilizer Recommendation Precision Agriculture Rice Crop

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：