检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Patil, Ranispoorti Ravindra Jayalaxmi, G.N. Choudapur, V.H. Baligar, Vishwanth P. Kle Technological University School of Computer Science & Engineering Karnataka Hubballi580031 India Kle Technological University School of Advanced Science Karnataka Hubballi580031 India Kle Technological University School of Computer Science Karnataka Hubballi580031 India

ISBN: (纸本)9798350370249

With an emphasis on Field-Emission Scanning Electron Microscope (FE-SEM) images, our goal is to enhance, classify, and segment 3D images acquired using a Scanning Electron Microscope (SEM). Based on the kind and concentration of doping present in the samples, these images are divided into three groups: Nd (Neodymium) doped cobalt chromite, La (Lanthanum) doped cobalt chromite and cobalt chromite in pure form. Our dataset includes ninety-three photos taken at different magnifications, offering a wide variety for additional processing and analysis. The effectiveness and appeal of the images are improved by the use of augmentation techniques. We use a new technique and pre-existing classical Deep Learning (DL) models to classify SEM pictures into different classes. While the 3D Residual Networks (3D ResNet) model achieves 40% average testing accuracy, the 3D Convolutional Neural Networks (CNN) model shows 50% accuracy. But the categorization procedure is complicated by the similarities and complexity seen in each class of images as well as the inclusion of different magnification levels. We provide a unique algorithm 'CompEx' (Integrated Image compression and Feature extraction), a approach based on modular arithmetic to to identify unique characteristics from the pictures and to overcome these difficulties. In addition, we evaluate Cobalt Chromite samples and assess factors like porosity, particle size, and distribution using a variety of computer vision and image processing techniques. © 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

Machine Learning Based Phishing Website Detection System - Natural Language Processing Approach 2

Machine Learning Based Phishing Website Detection System - N...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Patni, Jagdish Chandra Naik, S. Vinay Harika, K. Bahadure, Nilesh Bhaskarrao Verma, Kamal Kant Dept. of CSE Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Science and Engineering School of Technology GSFC University Gujarat Vadodara India School of Computer Science IILM University Greater Noida India

ISBN: (纸本)9798331530389

Natural language processing (NLP) methods can be used to identify phishing websites in addition to static and dynamic features. Phishing sites frequently include certain phrases, misspellings, or misleading text patterns in their material, as well as other visual cues and language that match those of authentic websites. Through the examination of textual components such anchor texts, meta-descriptions, and homepage titles. The proposed model is able to comprehend the linguistic traits that are frequently seen in phishing websites using NLP-based features like sentiment analysis, keyword matching, and phrase frequency to increase model's sensitivity. In addition, we use real-time URL parsing to detect possible dangers as users come across them, guaranteeing prompt notifications and lowering the possibility that phishing attempts would be successful. Our study emphasizes how crucial it is to keep improving and upgrading phishing detection models because attackers usually change their strategies. © 2025 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

High-Performance Intelligent System for Real-Time Medical Image Using Deep Learning and Augmented Reality 4th

High-Performance Intelligent System for Real-Time Medical Im...

引用

4th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2023

作者： Senthil, G.A. Prabha, R. Rajesh Kanna, R. Umadevi Venkat, G. Deepa, R. Department of Information Technology Agni College of Technology Chennai India Department of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Department of Computer Science and Engineering Agni College of Technology Chennai India Department of Computer Science and Engineering Vels Institute of Science and Technology and Advanced Studies Chennai India

ISBN: (纸本)9789819965854

Evolving new diseases demand the need for technology to identify the disease in an effective way. Medical imaging in the field of disease identification helps to identify the disease by scanning the human parts, thereby preventing the increased rate of deaths. Deep learning algorithms make it easier to identify and analyze disease efficiently through medical imaging. The high performance of these models is needed for the disease to be predicted with accurate results. The prediction rate of the disease can be increased by the efficient use of deep learning modules and algorithms. This research involves the use of deep learning models in identifying brain hemorrhage and retinopathy diseases through deep learning algorithms. The deep learning algorithms AlexNet and convolutional neural network (CNN) with the accuracy of 90% and 96%, respectively, are employed for the detection of brain hemorrhage, and ResNet-50 and CNN with accuracy of 70% and 92%, respectively, are used for the identification of retinopathy. The output of the model is displayed using augmented reality (AR), which makes it interactive for the user to analyze the results. The AR display is achieved using the unity engine along with the Vuforia package and using the barracuda package for importing the deep learning model into unity. Thus, by increasing the accuracy rate of the system, this research demonstrates the high performance of the intelligent system. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Cryptographically Secure Pseudo Random Number Generators for Post Quantum Era 7

Evaluation of Cryptographically Secure Pseudo Random Number ...

引用

7th IEEE International conference for Convergence in Technology, I2CT 2022

作者： Kumar, Atul Mishra, Arun Defence Institute of Advanced Technology Computer Science and Engineering Pune India

ISBN: (纸本)9781665421683

The construction of a Pseudo-Random Number Generator (PRNG) is an extremely decisive task in the field of Cryptography, Gaming, Computational statistics, Simulation processes, Gambling, and other fields. But many of the PRNGs are not cryptographically secure so various kinds of models have been presented to generate Pseudo-Random numbers. As generators are used in the field of cryptography too therefore it is inescapable to assess it among scientists and researchers. In this study, we would evaluate different kinds of RNGs against quantum attacks including the one which is based on lattice-based cryptography. In the end, we would contrive to wind up how the lattice-based PRNGS are pragmatic for the Post Quantum Cryptography. © 2022 IEEE.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

advanced Medical Question and Answering Chatbot Powered by Llama-2 For Precis Health Answer 2

Advanced Medical Question and Answering Chatbot Powered by L...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Patni, Jagdish Chandra Anup, S.B. Swetha Chitra, K.S. Poornima, B.M. Raviprakash, B.P. Kant Verma, Kamal Dept. of CSE Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Science and Engineering School of Technology GSFC University Gujarat Vadodara India School of Computer Science IILM University Greater Noida India

ISBN: (纸本)9798331530389

LLaMA-2 model, which is known for having the best capabilities in natural language processing at the core of our system. With respect to symptom diagnosis, it ranked among the most accurate in being able to give the chances of as many conditions possible as per the information that it receives from the user. Creating custom responses to unique user queries all the time, which may potentially increase user satisfaction and engagement. We have tested and perfected our chatbot to ensure that the capabilities stood out at a level of accuracy as high as 85 percent-showing outstanding care in the matters of healthcare assistance issues under numerous medical topics. Our work adds advanced features with the improvement techniques to the conventional medical Q and A chatbot. The new deep learning chatbot is not only great for symptom diagnosis but also uses its capabilities to provide context-aware responses based on user health history, lifestyles, and preferences with adjustment of its advice for a more personal healthcare experience. © 2025 IEEE.

关键词： Chatbot LLaMA-2 model medical Question and Answers Natural language processing (NLP) symptom identification

来源：评论

学校读者我要写书评

暂无评论

Gastrointestinal Disease Classification And Analysis Using GI-Net Model

Gastrointestinal Disease Classification And Analysis Using G...

引用

2022 International Conference on Edge Computing and Applications, ICECAA 2022

作者： Malviya, Animesh Dutta, Malay Kishore Department of Computer Science and Engineering Center for Advanced Studies Lucknow India

ISBN: (数字)9781665482325

ISBN: (纸本)9781665482325

Detecting gastrointestinal illnesses accurately is crucial to early cancer detection and treatment. In spite of this, manual analysis is time-consuming, requiring the assistance of a gastrointestinal. A multi-class classification framework for screening gastrointestinal diseases is proposed that is efficient and robust. A neural network known as gastrointestinal GI-Net was developed to extract features that could differentiate between normal and diseased images taken by endoscopy device. In order to achieve the most optimal classification network, a variety of optimization techniques are used. For the classification network to be more effective, the framework can handle the challenges present in the dataset. It is 88% accurate in diagnosing using unseen endoscopy images. In comparison with other deep learning networks, the developed architecture is highly effective. Compared to other networks, in limited computation environments, the proposed network is likely to perform better. © 2022 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

High efficiency of Brillouin scattering behavior in single-mode Ge–As–Se–Te fibers at 2μm

引用

Chinese Physics B 2023年第5期32卷 449-456页

作者：付悦戴世勋徐路路方耀俊王莹莹焦凯王训四 Laboratory of Infrared Materials and Devices The Research Institute of Advanced TechnologiesNingbo UniversityNingbo 315211China Key Laboratory of Photoelectric Materials and Devices of Zhejiang Province Ningbo 315211China Engineering Research Center for Advanced Infrared Photoelectric Materials and Devices of Zhejiang Province Ningbo 315211China Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China

The Brillouin characteristics of step-index Ge–As–Se–Te(GAST)fibers at 2μm are designed and simulated on the basis of optical and acoustic *** refractive indexes of Ge_(20)As_(20)Se_(45)Te_(15)glass and Ge_(20)As_(20)Se_(43)Te_(17)glass serving as fiber core and cladding are 3.20 and 3.18 at 2μm,and their acoustic velocities are 2200 m/s and 2300 m/s,*** results indicate that the stimulated Brillouin scattering(SBS)efficiency is 248 m^(-1)·W^(-1),and the Brillouin threshold power is 66 m W when the core diameter of the 2-m-long GAST fiber is 4μm at 2-μm *** optic–acoustic coupling factor,the Brillouin frequency shift,and the Brillouin gain coefficient are 0.98,7.02 GHz,and 3.81×10^(-9)m/W,*** SBS effect of GAST fibers simulated for the first time provides a new promising approach to selecting gain medium based on 2-μm-wavelength fiber laser.

关键词： stimulated Brillouin scattering chalcogenide fiber nonlinear effect optical–acoustic coupling

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer

High-Fidelity Document Stain Removal via A Large-Scale Real-...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Li, Mingxian Sun, Hao Lei, Yingtie Zhang, Xiaofeng Dong, Yihang Zhou, Yilin Li, Zimeng Chen, Xuhang School of Computer Science and Engineering Huizhou University China The Ohio State University Department of Computer Science and Engineering United States School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China School of Electronic and Communication Engineering Shenzhen Polytechnic University China

ISBN: (纸本)9798331510831

Document images are often degraded by various stains, significantly impacting their readability and hindering downstream applications such as document digitization and analysis. The absence of a comprehensive stained document dataset has limited the effectiveness of existing document enhancement methods in removing stains while preserving fine-grained details. To address this challenge, we construct StainDoc, the first large-scale, high-resolution (2145 x 2245) dataset specifically designed for document stain removal. StainDoc comprises over 5,000 pairs of stained and clean document images across multiple scenes. This dataset encompasses a diverse range of stain types, severities, and document backgrounds, facilitating robust training and evaluation of document stain removal algorithms. Furthermore, we propose StainRestorer, a Transformer-based document stain removal approach. StainRestorer employs a memory-augmented Transformer architecture that captures hierarchical stain representations at part, instance, and semantic levels via the DocMemory module. The Stain Removal Transformer (SRTransformer) leverages these feature representations through a dual attention mechanism: an enhanced spatial attention with an expanded receptive field, and a channel attention captures channel-wise feature importance. This combination enables precise stain removal while preserving document content integrity. Extensive experiments demonstrate StainRestorer's superior performance over state-of-the-art methods on the Stain-Doc dataset and its variants *** and ***, establishing a new benchmark for document stain removal. Our work highlights the potential of memory-augmented Transformers for this task and contributes a valuable dataset to advance future research. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A flexible capacitive photoreceptor for the biomimetic retina

引用

Light(science & Applications) 2022年第1期11卷 38-49页

作者： Mani Teja Vijjapu Mohammed E.Fouda Agamyrat Agambayev Chun Hong Kang Chun-Ho Lin Boon S.Ooi Jr-Hau He Ahmed M.Eltawil Khaled N.Salama Sensors lab Advanced Membranes and Porous Materials CenterComputerElectrical and Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia Communication and Computing Systems Lab ComputerElectrical and Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia Department of Electrical Engineering and Computer Science University of California-IrvineIrvineCA 92612USA Department of Electrical Computer and Energy EngineeringArizona State UniversityTempeAZUSA Computer Electrical and Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia Department of Materials Science and Engineering City University of Hong KongHong Kong SARChina

Neuromorphic vision sensors have been extremely beneficial in developing energy-efficient intelligent systems for robotics and privacy-preserving security *** is a dire need for devices to mimic the retina's photoreceptors that encode the light illumination into a sequence of spikes to develop such ***,we develop a hybrid perovskite-based flexible photoreceptor whose capacitance changes proportionally to the light intensity mimicking the retina's rod cells,paving the way for developing an efficient artificial retina *** proposed device constitutes a hybrid nanocomposite of perovskites(methyl-ammonium lead bromide)and the ferroelectric terpolymer(polyvinylidene fluoride trifluoroethylene-chlorofluoroethylene).A metal-insulator-metal type capacitor with the prepared composite exhibits the unique and photosensitive capacitive behavior at various light intensities in the visible light *** proposed photoreceptor mimics the spectral sensitivity curve of human photopic *** hybrid nanocomposite is stable in ambient air for 129 weeks,with no observable degradation of the composite due to the encapsulation of hybrid perovskites in the hydrophobic *** functionality of the proposed photoreceptor to recognize handwritten digits(MNIST)dataset using an unsupervised trained spiking neural network with 72.05%recognition accuracy is *** demonstration proves the potential of the proposed sensor for neuromorphic vision applications.

关键词： perovskite illumination preserving

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：