检索结果-内蒙古大学图书馆

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Saragadam, Sneha Rohan, Gamidi Manideep, Thotapalli Sri Surya Jayan, Sarada Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Department of Mathematics Bengaluru India

ISBN: (纸本)9798331518592

In an effort to increase computing efficiency, this work presents an improved spectral clustering technique that approximates the affinity matrix using Toeplitz and Circulant matrices. To preserve the quality of the clustering, we take advantage of the spectral characteristics of the similarity graph's Laplacian matrix. The Iris flower, Wine Quality, and Mushroom datasets are used to assess the approach. The following six clustering methods are contrasted: PCA combined with either spectral or K-means clustering, K-means clustering (with and without matrix approximation), and spectral clustering (with and without matrix approximation). The Silhouette Score, Fl score, precision, recall, and Adj usted Rand Index (ARI) are used to evaluate performance. The suggested method produces similar results to traditional methods with a significant reduction in computational cost, according to the results. In order to fully investigate the advantages of these matrices, architectures in spectral clustering are explored. © 2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Telugu Language Analysis with XLM-RoBERTa: Enhancing Parts of Speech Tagging for Effective Natural Language Processing

引用

SN computer science 2025年第2期6卷 1-13页

作者： Bharathi Mohan, G. Prasanna Kumar, R. Krishna Jayanth, K. Doss, Srinath Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Faculty of Engineering and Technology Botho University Gaborone Botswana

This research investigates the efficacy of XLM-RoBERTa, a potent deep learning architecture rooted in transformer networks, for Part-of-Speech (POS) tagging—a foundational task in Natural Language Processing (NLP). The study narrows its focus to address the formidable UCD Telugu dataset, renowned for its intricate morphological characteristics that pose challenges to accurate tagging. Through meticulous fine-tuning of the pre-trained XLM-RoBERTa model. This study adeptly discerns and exploit intricate syntactic and semantic patterns underpinning the interplay between lexical elements and their respective POS tags. The rigorous evaluation regimen, complemented by a comprehensive statistical comparison with the Multilingual BERT model, conclusively establishes XLM-RoBERTa’s superiority. This advanced model attains a remarkable accuracy score of 91%, decisively surpassing the Multilingual BERT model, which achieves an accuracy of 88%. These findings not only underscore XLM-RoBERTa’s prowess in precise POS tagging, especially in the context of morphologically rich languages like Telugu, but also carry significant implications for the broader NLP community. This research unlocks valuable insights and positions XLM-RoBERTa as an exemplar of reliability and robustness in POS tagging. Furthermore, it extends an invitation for further exploration and innovation in deep learning architectures within the NLP domain. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bert Multilingual Bert NLP Parts-of-speech tagging Telugu XLM-RoBERTa

来源：评论

学校读者我要写书评

暂无评论

Investigation of Android Malware Using Deep Learning Approach

引用

Intelligent Automation & Soft computing 2023年第2期35卷 2413-2429页

作者： V.Joseph Raymond R.Jeberson Retna Raj Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyChennai600119TamilnaduIndia School of Computing SRM Institute of Science and TechnologyChennai603203TamilnaduIndia

In recent days the usage of android smartphones has increased exten-sively by *** are several applications in different categories bank-ing/ﬁnance,social engineering,education,sports andﬁtness,and many more *** android stack is more vulnerable compared to other mobile plat-forms like IOS,Windows,or Blackberry because of the open-source *** the Existing system,malware is written using vulnerable system calls to bypass signature detection important drawback is might not work with zero-day exploits and stealth *** attackers target the victim with various attacks like adware,backdoor,spyware,ransomware,and zero-day exploits and create threat hunts on the day-to-day *** the existing approach,there are various tradi-tional machine learning classiﬁers for building a decision support system with limitations such as low detection rate and less feature *** important contents taken for building model from android applications like Intent Filter,Per-mission Signature,API Calls,and System commands are taken from the manifestﬁ*** function parameters of various machine and deep learning classiﬁers like Nave Bayes,k-Nearest Neighbors(k-NN),Support Vector Machine(SVM),Ada Boost,and Multi-Layer Perceptron(MLP)are done for effective *** our pro-posed work,we have used an unsupervised learning multilayer perceptron with multiple target labels and built a model with a better accuracy rate compared to logistic regression,and rank the best features for detection of applications and clas-sify as malicious or benign can be used as threat model by online antivirus scanners.

关键词： Android application permissions multilayer perception relief scoring

来源：评论

学校读者我要写书评

暂无评论

Predictive Modelling of Diabetes Complications: Insights from Binary Classifier on Chronic Diabetic Mellitus

Predictive Modelling of Diabetes Complications: Insights fro...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Panigrahy, Smita Dash, Sachikanta Padhy, Sasmita Kumar, Naween Dash, Yajnaseni Computer Science And Engineering Giet University Odisha Gunupur India School Of Computing Science And Engineering Vit Bhopal University MP Bhopal India School Of Computer Science Engineering And Technology Bennett University Uttar Pradesh Greater Noida India School Of Computer Science Engineering And Technology Bennett University Uttar Pradesh India

ISBN: (纸本)9798350366846

Chronic diabetes Mellitus (DM) leads to severe consequences such as nephropathy, neuropathy, and retinopathy. Various learning algorithms are employed to forecast and categorize eight issues, encompassing metabolic syndrome and dyslipidemia. Machine learning is revolutionizing various domains by enabling algorithms to extract models from data. The main objective of this proposed study is to utilize binary classifiers to predict and categorize eight problems associated with DM. For this study we have used the dataset obtained from the Jeevandeep Hospital and Research Centre (JHRC) in Baripada, Mayurbhanj, Odisha, India. It includes 1296 records and has nine input variables and eight output categories that indicate different issues. Multiple models were constructed to address problems like Nephropathy, neuropathy, dyslipidemia, diabetic foot, metabolic syndrome, retinopathy, hypertension, and obesity. Different preprocessing operations on missing data, unbalanced data, and feature selection are employed. Binary classifiers were developed for each type of complication, with the number of records varied for each. Subsequently, an evaluation was conducted. The models achieved a maximum of 95.7% accuracy and 97.9% F1 score. The study demonstrates the effectiveness of using selected features to build accurate classifiers for predicting diabetes complications. © 2024 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Credit Card Fraud Detection Using Machine Learning- A Comprehensive Review 3

Credit Card Fraud Detection Using Machine Learning- A Compre...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Jaswant, T. Venkata Manoj, G. Sai Vamisdhar, V. Aravind, A. Reddy, S. Vasudeva Patni, Jagdish Chandra Bahadure, Nilesh Kumar, Rohit Alliance School of Advanced Computing Alliance University Dept. of Computer Science Engineering Bengaluru India School of Technology Gsfc University Department of Computer Science and Engineering Gujarat India

ISBN: (纸本)9798331518592

Credit card fraud is an omnipresent threat in the digital era that cannot be effectively managed without complex detection and prevention strategies. Machine learning has become instrumental for the industry, principally, due to providing tools to analyze transactional information and identify patterns of fraud. The article dwells on the methods, problems, and prospects of their future use. The algorithms are analyzed according to their potential applicability, scalability, and interpretability for fraud detection. This study includes convolutional neural networks and recurrent neural networks are used for utilization of anomaly exposure detection methods to detect unseen fraud with models. © 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

Enhancing Security: A Hybrid Encryption Algorithm for Effective Key Generation 2

Enhancing Security: A Hybrid Encryption Algorithm for Effect...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, computing, and Communications Systems, ICMACC 2024

作者： Jacob, Jeevan John Kiran, P.S. Shenoy, Jaigovind B Basavaraju, Sagar Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350366570

The abstract Data security is of most importance, in the present day- the introduction of high-level wireless communication channels has led to generation and transfer of massive amounts of data. Data security must keep up with it. Data breach may cause disastrous outcomes. Previously, hardware security modules (HSM) were used to perform cryptographic actions- storing keys and for authentication. This is no longer feasible as HSMs are physical devices and become inconvenient to carry around all the time. The unavailability of HSM poses a serious security threat (for cryptographic keys). This paper aims at a novel software solution that compensates for hardware. As the algorithm focuses on securing keys used for encryption. It may be referred to as key security scheme (KSS). The paper proposes a way to generate keys instead of storing it and assumes performing of cryptographic actions on the available hardware in the system. The proposed method can secure data, both in transit and while at rest. © 2024 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Hate Speech in Hindi using Supervised Learning Models

Automated Detection of Hate Speech in Hindi using Supervised...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Rajak, Nikhil Phulre, Ajay Kumar Chandra Patel, Subhash Patel, Narottam Das Khekare, Ganesh Vit Bhopal University School of Computing Science Engineering and Artificial Intelligence Sehore India Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350375442

This study addresses the pressing issue of hate speech on online platforms. Traditional text-based analysis is no longer adequate for identifying hate speech due to the growth of internet platform data. The project aims to create scalable automated methods for web platforms to detect hate speech in real-time. To find the best algorithms for recognizing hate speech, the study compares many machine learning models using a large dataset in Hindi from Twitter. Where the study matters is in the creation of advanced content filtering systems that offer a more secure and friendly online environment. Support Vector Machine (SVM) has the best performance, with outstanding precision (0.9468) and F1-score (0.944), showcasing the top-performing ones and talking about the difficulties and ways ahead in this field. The study recommends improving Hindi hate speech detection systems. With problems such as imbalanced data sets and the dynamic nature of online language, language research using hybrid models, constant model adjustments, and language trend monitoring are all necessary. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Robust Convolutional Neural Network Architecture for Automated Pneumonia Detection from Chest X-ray Images 3

A Robust Convolutional Neural Network Architecture for Autom...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Babu, Tina Naik, Pramod Kumar Nair, Rekha R Pallavi, K. Alliance University Alliance School of Advanced Computing Department of Computer Science and Engineering Bengaluru India Dayananda Sagar University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350354171

Pneumonia is a significant global health concern, especially for vulnerable populations such as children under five. Timely and accurate diagnosis is critical for effective treatment and improved patient outcomes. This project proposes a robust solution leveraging Convolutional Neural Networks (CNNs) for automated pneumonia detection from chest X-ray images. The model, trained on a meticulously preprocessed dataset of 5,216 chest X-ray images, demonstrated exceptional performance, achieving a training accuracy of 98.16% and a validation accuracy of 98.45% after 50 epochs. The architecture comprises five Conv2D layers with ReLU activation, followed by max-pooling layers, and a fully connected artificial neural network for classification. The model's success in distinguishing between normal and pneumonia-infected cases underscores its potential as a valuable tool for healthcare professionals, offering a reliable and efficient means of pneumonia identification. The model's high accuracy and efficiency make it a valuable asset, potentially reducing the workload on radiologists and enabling quicker diagnoses, ultimately leading to more timely interventions and improved patient outcomes. Comprehensive evaluation, including testing on a separate dataset and real-world image inferences, validates the robustness of the proposed solution. © 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

Regularized Hybrid Deep Learning for DDoS Attack Prediction in Software Defined Internet of Things (SD-IoT) 3

Regularized Hybrid Deep Learning for DDoS Attack Prediction ...

引用

3rd International Conference on Power, Control and computing Technologies, ICPC2T 2024

作者： Deepthy, J. Radhika, N. Denny, Alosh Department of Electronics & Communication Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham India School of Engineering Ernakulam Cochin University of Science and Technology Division of Computer Science and Engineering India

ISBN: (纸本)9798350349207

The availability of online resource is seriously threatened by the fatal DDoS (Distributed Denial of Service) attacks, which can earnestly break up a targeted network or website by flooding it with traffic. DDoS attacks can use a variety of tactics and can be launched from different points around the world, making it difficult to predict when they will occur. In order to improve accuracy by minimizing overfitting of data in CNN, this work proposes an efficient method by combining CNN with Bi-LSTM for predicting DDoS attacks based on a modified loss function with regularization. We test our method on the CICDDOS2019 dataset of network traffic and demonstrate that it can accurately and successfully predict DDoS attacks with an accuracy of 99.8% and an F-score of 97.29%. © 2024 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

D^(2)PAM:Epileptic seizures prediction using adversarial deep dual patch attention mechanism

引用

CAAI Transactions on Intelligence Technology 2023年第3期8卷 755-769页

作者： Arfat Ahmad Khan Rakesh Kumar Madendran Usharani Thirunavukkarasu Muhammad Faheem Department of Computer Science College of ComputingKhon Kaen UniversityKhon KaenThailand Department of Computer Science and Engineering Rajalakshmi Engineering CollegeChennaiIndia Department of Biomedical Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical Sciences(Deemed to be University)ChennaiIndia School of Technology and Innovations University of VaasaVaasaFinland

Epilepsy is considered as a serious brain disorder in which patients frequently experience *** seizures are defined as the unexpected electrical changes in brain neural activity,which leads to *** researches made an intense effort for predicting the epileptic seizures using brain signal ***,they faced difficulty in obtaining the patients'characteristics because the model's distribution turned to fake predictions,affecting the model's *** addition,the existing prediction models have severe issues,such as overfitting and false positive *** overcome these existing issues,we propose a deep learning approach known as Deep dual‐patch attention mechanism(D^(2)PAM)for classifying the pre‐ictal signals of people with Epilepsy based on the brain *** neural network is integrated with D^(2)PAM,and it lowers the effect of differences between patients to predict *** multi‐network design enhances the trained model's generalisability and stability ***,the proposed model for processing the brain signal is designed to transform the signals into data blocks,which is appropriate for pre‐ictal *** earlier warning of epilepsy with the proposed model obtains the auxiliary *** data of real patients for the experiments provides the improved accuracy by D2PAM approximation compared to the existing *** be more distinctive,the authors have analysed the performance of their work with five patients,and the accuracy comes out to be 95%,97%,99%,99%,and 99%***,the numerical results unveil that the proposed work outperforms the existing models.

关键词： artificial intelligence techniques classification learning(artificial intelligence)

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：