检索结果-内蒙古大学图书馆

EPDTNet + -EM: Advanced Transfer Learning and SubNet Architecture for Medical Image Diagnosis

Cognitive Computation 2025年第2期17卷 1-22页

作者： K, Dhivya K, Sangamithrai S, Indra Priyadharshini M, Vedaraj Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & d Institute of Science and Technology Tamilnadu Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering R.M.D. Engineering College RSM Nagar Tamilnadu Kavaraipettai Thiruvallur601206 India

This paper presents a novel medical imaging framework, Efficient Parallel Deep Transfer SubNet+-based Explainable Model (EPDTNet + -EM), designed to improve the detection and classification of abnormalities in medical images. The model integrates Enhanced Exponential Transfer Learning (En-ETL) and the Parallel SubNet (PSNet +) architecture, addressing challenges like overfitting, high computational cost, and limited generalization across complex datasets. En-ETL accelerates learning and enhances precision, while PSNet + balances computational efficiency and performance through parallel convolutional layers and an axis attention mechanism. The proposed framework preprocesses medical images using resizing, noise removal, and contrast enhancement, ensuring high-quality inputs for analysis. For classification, the PSNet + model categorizes medical images into normal and abnormal cases. Explainable AI (XAI) is applied to highlight key features in classified images, improving interpretability and clinical decision-making. Experimental results validate the framework on various datasets, including MRI, CT, X-ray, and mammography images. The proposed model achieves a classification accuracy of 98.83%, a false positive rate of 2%, and an execution time of 5.3 ms. Comparative Analysis show superior performance over existing approaches in classification accuracy and efficiency. Ablation studies confirmed the significant contributions of the proposed model using each component in enhancing performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Sem-AI: A Unique Framework for Sentiment Analysis and Opinion Mining Using Social Network Data

引用

SN computer science 2025年第2期6卷 1-23页

作者： Maruthupandi, J. Sivakumar, S. Kumar, V. Senthil Srikaanth, P. Balaji Department of Computer Science and Engineering New Horizon College of Engineering Karnataka Bangalore India Department of Computer Science and Engineering SRM Institute of Science and Technology Tamilnadu Trichy India Department of Networks and Communication SRM Institute of Science and Technology Tamilnadu Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Chennai India

Social media has become an essential forum for people to share their thoughts and sentiments owing to the quick rise in mobile technology. Business and political organizations might benefit from understanding public sentiment when making strategic decisions. Challenges in the area include handling noisy and incomplete data, variation in language use across domains, and integration into existing systems of models developed for analysis. In these ways, they can seriously hamper the accuracy and generalizability of sentiment analysis models. In view of the challenges, this work has developed a new and innovative framework of AI-based semantic analysis for assessing and classifying user views from social data. In spite of this, sentiment analysis is crucial for determining the opposing perspectives of the general public's sentiments. This work constructed a new and innovative framework called Semantic analysis based on AI (SemAI) for assessing and categorizing user views from social data. With high efficiency, a collection of intelligence algorithms in the stages of feature extraction, optimization, and sentiment prediction are applied here. The Degree of Correlation Network Model (DCNM) is used in this work to extract the subset of dependable and most-required features from social network data. The most recent meta-heuristics model, Heap based Optimization (HbO), is used to reduce the dimensionality of retrieved features. Furthermore, the unique classification algorithm, Self-Attention based Deep Analyzing Network (SA-DAN), is used in this work to precisely identify and categorize attitudes into positive, neutral, and negative classifications. This present study used a variety of most recent social corpus data to investigate and evaluate the Sem-AI model's outputs. The SemAI model achieved impressive results, with accuracy, precision, and F1-scores of 99%, 98.9%, and 99%, respectively, across various social corpus datasets. © The Author(s), under exclusive licence to S

关键词： Classification Degree of correlation network model (DCNM) Heap based optimization (HbO) Opinion mining Self-attention based deep analyzing network (SA-DAN) Semantic analysis Social data

来源：评论

学校读者我要写书评

暂无评论

Multigraph-Based Curvilinear Regression Analysis of Two Novel Class of Drugs to Treat Cardiovascular Disease using Revan Indices

引用

IAENG International Journal of Applied Mathematics 2024年第11期54卷 2159-2175页

作者： Preetha, Ugasini P. Suresh, M. Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur603203 India

In this research, two distinct categories of medications for treating cardiovascular conditions, specifically fibrates and calcium channel blockers were analyzed. QSPR analysis of curvilinear regression models was used to establish a relationship between these degree-based indices and the physicochemical properties of some novel drugs used in the treatment of heart disease. The results show that quadratic regression outperformed linear regression for both drug classes. Additionally, comparing multigraph and simple graph modeling revealed that multigraph modeling provides a more detailed understanding of drug structures, enhancing the accuracy of estimating physicochemical properties. Specifically, eight Revan indices showed a strong correlation (R=1) in quadratic regression for fibrate drugs with the first Revan index (R1) serving as the most accurate estimator for molar refractivity and polarizability. Meanwhile, the Geometric-Arithmetic Revan index (GAR) emerged as the best estimator for polar surface area in quadratic regression equations for calcium channel blockers. These studies highlight the potential of topological indices in estimating physicochemical properties of drugs, which could be useful in the development of new drugs and therapies. © (2024), (International Association of Engineers). All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Switched coupled inductor inverter-based interline dynamic voltage restorer with discrete wavelet transform-artificial neural network technique

引用

International Journal of Electrical engineering and Education 2024年第2期61卷 143-160页

作者： Sivaperumal, P. Dash, Subranhsu Sekhar Mohanraj, K. Balaji, C. Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Chennai India

An educational studies and understanding about theoretical and practical laboratory in power quality issues. Interline dynamic voltage restorer is used in the proposed system for mitigating voltage sag, swell, harmonics, and interruptions. The conventional topology of dynamic voltage restorer possessing voltage source inverter is modified into a switched coupled inductor inverter which has the clear edge in power transfer over the former one. The versatility of the controller is enhanced in this work by deploying an artificial neural network combined discrete wavelet transform. The artificial neural network and discrete wavelet transform aided pulse width modulation generation enhances the controller performance by mitigating the harmonics considerably. The simulation and experimental results reveal that interline dynamic voltage restorer renders solution for major power quality issues like voltage sag and swell. Interline dynamic voltage restorer-based SCII is implemented with field programmable gate array Spartan 6 controller and signal processing technique such as discrete wavelet transform that mitigates voltage sag and harmonics. Paper is constructed such that the students in Bachelor’s and Master’s program of Electrical engineering can understand the power quality, various issues, and mitigating the total harmonic distortion value. The equations related to real power transfer are derived which enable the students to clearly understand about the power exchange between the feeders. Further, it is applied in practical laboratory setup facility for understanding about power quality issues to students of both undergraduate and postgraduate courses. © The Author(s) 2019.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Anti-Wear Characteristics of Karanja Oil Using Tribological Testing and Quantum Chemical Calculations

引用

Journal of Bio- and Tribo-Corrosion 2025年第2期11卷 1-9页

作者： Menon, Krishnaprasad S Ambigai, R. Department of Mechanical Engineering SRM Institute of Science and Technology Chennai Kattankulathur603203 India

The potential depletion of oil resources, combined with the limited biodegradability of mineral oil-based lubricants, has highlighted the importance of developing bio-based lubricants. As a result, vegetable oils have gained social attention and are widely recognised as an environmentally friendly alternative to petroleum and mineral-based lubricants due to their admirable properties such as biodegradability, low toxicity, and renewable nature. Since, the vegetable oils are composed of long chain unsaturated fatty acids, the antiwear performance of vegetable oils can be predicted by considering the structural relationship between their anti-wear properties and the chemical structures. This study utilises quantum chemical calculations to analyse the tribological properties of the various fatty acid components found in Karanja oil, rather than studying their triglyceride ester molecules. The acquired results are rigorously verified using published data’s and compared with experimental tribological test outcomes obtained from four-ball tester. The addition of 2 wt% ZDDP in Karanja oil showed an improvement in wear scar diameter by 40% and about 29% of coefficient of friction from the base oil. The tribological test showed that the presence of ZDDP additive enhances the antiwear property of Karanja oil. A strong correlation was also observed between the experimental results and the chosen quantum chemical descriptors. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Unsaturated fatty acids

来源：评论

学校读者我要写书评

暂无评论

Structure Property Modeling of Physicochemical Properties of Antipsychotic Drugs via Topological Descriptors, Multigraph Modeling with the Specific Treatment of Heteroatoms and Chemometric Methods

引用

IAENG International Journal of Applied Mathematics 2024年第11期54卷 2388-2403页

The physicochemical properties for thirteen antipsychotic drugs: Chlorpromazine, Trifluoperazine, Thioridazine, Thiothixene, Haloperidol, Ziprasidone, Loxapine, Quetiapine, Aripprazole, Clozapine, Risperidone, Olanzapine and Sertindole were studied using some distance and degree based topological descriptors. The heterocyclic antipsychotic drugs are modeled as hydrogen suppressed molecular multigraph with the specific treatment for the heteroatoms using valence delta values δv. In the literature, the molecular connectivity index, originally for hydrocarbons, has been extended to molecules with heteroatoms. The delta value for the heteroatom considers its valence electrons (Zv) minus the number of bonded hydrogen atoms (h), expressed as Zv − h. This modification accommodates heteroatoms in the index calculation on the recently introduced certain set of distance based leap Zagreb indices and degree-based indices. This research uses statistical techniques like quadratic, stepwise regression to link topological descriptors with QSPR models, improving the estimation of drug properties such as boiling point, melting point, enthalpy, flash point, molar refractivity, refractive index, complexity, molecular weight and refractivity. Validation involves comparing estimated values with actual drug properties. This study demonstrates both the similarities and distinctions among the chosen antipsychotic drugs by employing chemometric methods like principal component analysis (PCA) and cluster analysis (CA). These methods help in understanding the shared characteristics and variations present within the drugs being investigated. © (2024), (International Association of Engineers). All rights reserved.

关键词： Hydrogen bonds

来源：评论

学校读者我要写书评

暂无评论

Study of Evolving Young Wind Waves under Steady Wind Forcing

引用

Journal of Offshore Mechanics and Arctic engineering 2025年第5期147卷 051201页

作者： Soman, Sachu S. Singh, Santosh Kumar Department of Mechanical Engineering SRM Institute of Science and Technology Kattankulathur Chennai603203 India

In this work, a comprehensive experiment is conducted to investigate the spatio-temporal variability of young wind waves under steady wind forcing. The experimental setup included a wave tank equipped with a wind blower capable of generating a wide range of wind velocities. Wave elevation was measured at various airflow rates and fetches using a capacitance-type wave gauge. The spatial growth rates of young waves at different frequencies were assessed by analyzing wave gauge records taken at multiple fetches. In every case of wind blowing, the growing wave field exhibited strong nonhomogeneity, with an increase in wave energy along the wave channel accompanied by a decrease in frequency. Notably, the findings from the experiments reveal that young wind waves lose their temporal coherence within three local dominant wave periods, regardless of wind velocity and fetch. The limited temporal and spatial coherence of gravity-capillary and short wind waves has significant implications for radar remote sensing of the ocean surface. Copyright © 2025 by ASME.

关键词： Coastal engineering

来源：评论

学校读者我要写书评

暂无评论

DeepGAN: Utilizing generative adversarial networks for improved deep learning

引用

International Journal of Knowledge-Based and Intelligent engineering Systems 2024年第4期28卷 732-748页

作者： V, Edward Naveen A, Jenefa T.M, Thiyagu A, Lincy Taurshia, Antony Department of Computer Science and Engineering Sri Shakthi Institute of Engineering and Technology India Department of Computer Science and Engineering Karunya Institute of Technology and Sciences India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences India Department of Computer Science and Engineering National Engineering College India

In the realm of deep learning, Generative Adversarial Networks (GANs) have emerged as a topic of significant interest for their potential to enhance model performance and enable effective data augmentation. This paper addresses the existing challenges in synthesizing high-quality data and harnessing the capabilities of GANs for improved deep learning outcomes. Unlike traditional approaches that heavily rely on manually engineered data augmentation techniques, our work introduces a novel framework that leverages DeepGANs to autonomously generate diverse and high-fidelity data. Our experiments encompass a diverse spectrum of datasets, including images, text, and time series data. In the context of image classification tasks, we conduct experiments on the widely recognized CIFAR-10 dataset, which consists of 50,000 image samples. Our results demonstrate the remarkable efficacy of DeepGANs in enhancing model performance across various data domains. Notably, in image classification using the CIFAR-10 dataset, our innovative approach achieves an impressive accuracy of 97.2%. This represents a substantial advancement beyond conventional CNN models, underscoring the profound impact of DeepGANs in the realm of deep learning. In summary, this research sheds light on DeepGANs as a fundamental component in the pursuit of enhanced deep learning performance. Our framework not only overcomes existing limitations but also heralds a new era of data augmentation, with generative adversarial networks leading the way. The attainment of an accuracy rate of 97.2% on CIFAR-10 serves as a compelling testament to the transformative potential of DeepGANs, solidifying their pivotal role in the future of deep learning. This promises the development of more robust, adaptive, and accurate models across a myriad of applications, marking a significant contribution to the field. © 2024 – IOS Press. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Classification of Photovoltaic Panels Based on Convolutional Neural Network

引用

computers, Materials & Continua 2023年第1期74卷 1437-1455页

作者： S.Prabhakaran R.Annie Uthra J.Preetharoselyn Department of Computational Intelligence SRM Institute of Science and TechnologyChengalpattu603203India Department of Electrical Engineering SRM Institute of Science and TechnologyChengalpattu603203India

Photovoltaic(PV)boards are a perfect way to create eco-friendly power from *** defects in the PV panels are caused by various conditions;such defective PV panels need continuous *** recent development of PV panel monitoring systems provides a modest and viable approach to monitoring and managing the condition of the PV *** general,conventional procedures are used to identify the faulty modules earlier and to avoid declines in power *** existing deep learning architectures provide the required output to predict the faulty PV panels with less accuracy and a more time-consuming *** increase the accuracy and to reduce the processing time,a new Convolutional Neural Network(CNN)architecture is ***,in the present work,a new Real-time Multi Variant Deep learning Model(RMVDM)architecture is proposed,and it extracts the image features and classifies the defects in PV panels quickly with high *** defects that arise in the PV panels are identified by the CNN based RMVDM using RGB *** biggest difference between CNN and its predecessors is that CNN automatically extracts the image features without any help from a *** technique is quantitatively assessed and compared with existing faulty PV board identification approaches on the large real-time *** results show that 98%of the accuracy and recall values in the fault detection and classification process.

关键词： Photovoltaic panels deep learning defect feature extraction RMVDM

来源：评论

学校读者我要写书评

暂无评论

Novel Multimodal Biometric Feature Extraction for Precise Human Identification

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 1349-1363页

作者： J.Vasavi M.S.Abirami Department of Computer Science and Engineering SRM Institute of Science and TechnologyKattankulathur603203Tamil NaduIndia Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203Tamil NaduIndia

In recent years,biometric sensors are applicable for identifying impor-tant individual information and accessing the control using various identiﬁers by including the characteristics like aﬁngerprint,palm print,iris recognition,and so ***,the precise identiﬁcation of human features is still physically chal-lenging in humans during their lifetime resulting in a variance in their appearance or *** response to these challenges,a novel Multimodal Biometric Feature Extraction(MBFE)model is proposed to extract the features from the noisy sen-sor data using a modiﬁed Ranking-based Deep Convolution Neural Network(RDCNN).The proposed MBFE model enables the feature extraction from differ-ent biometric images that includes iris,palm print,and lip,where the images are preprocessed initially for further *** extracted features are validated after optimal extraction by the RDCNN by splitting the datasets to train the fea-ture extraction model and then testing the model with different sets of input *** simulation is performed in matlab to test the efﬁcacy of the modal over multi-modal datasets and the simulation result shows that the proposed meth-od achieves increased accuracy,precision,recall,and F1 score than the existing deep learning feature extraction *** performance improvement of the MBFE Algorithm technique in terms of accuracy,precision,recall,and F1 score is attained by 0.126%,0.152%,0.184%,and 0.38%with existing Back Propaga-tion Neural Network(BPNN),Human Identiﬁcation Using Wavelet Transform(HIUWT),Segmentation Methodology for Non-cooperative Recognition(SMNR),Daugman Iris Localization Algorithm(DILA)feature extraction techni-ques respectively.

关键词： Multimodalbiometric feature extraction ranking-baseddeepconvolution neural network noisy sensor data palm prints lip biometric iris recognition

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：