检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Prakash, Harshitha Yadav, Ayush Ushashree, P. Jha, Chandranshu Sah, Gopi Kumar Naik, Archana Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350398465

This electronic Counterfeit currency is a major concern for governments, banks, and businesses around the world. The detection of counterfeit currency notes is a challenging task that requires sophisticated techniques to analyse various physical and security features on the notes. Traditional methods of detection are time-consuming and prone to human error. This paper proposes the use of deep learning approaches for the automated detection of counterfeit bank notes. The use of Convolutional neural networks (CNNs) to analyse currency note image features and Recurrent Neural Networks (RNNs) to analyse security features such as serial numbers is investigated. An ensemble of CNNs and RNNs is proposed to improve detection accuracy. The proposed method is tested on a dataset of genuine and counterfeit currency notes. This method outperforms traditional methods of detection in terms of accuracy and precision. Our proposed method can be integrated into existing systems to enhance the security of banknotes and protect against counterfeiting. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

The Voiceless Assistant for the Specially Abled 1

The Voiceless Assistant for the Specially Abled

引用

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Vijaya Shetty, S. Ram, Ajith Bhargav, Arjun Harshinee, A. Pathak, Kanchan Nitte Meenakshi Institute of Technology Department of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798350323795

A novel system aimed at bridging the communication gap between deaf and blind individuals and those who are not familiar with sign language or Braille is proposed. Google's Speech Recognition library is used to convert speech to text and the pyttsx3 library is used to convert text to speech. The system is designed to interconvert between Indian sign language, Braille, and English text, creating a unified platform for individuals with different disabilities to communicate effectively. The sign language recognition component of the system was trained with a training accuracy of 97.73 percent and test accuracy of 98 percent. The Braille recognition component was trained with a training accuracy of 97 percent and test accuracy of 95.5 percent. The integration of sign language and Braille into one platform is a unique feature that sets this system apart from existing solutions. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Implementing End to End Encryption to Communication Apps 7

Implementing End to End Encryption to Communication Apps

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Nalini, N. Harini, B. Nitte Meenakshi Institute of Technology Department of Computer Science & Engineering Bangalore India

ISBN: (纸本)9798350341485

This research study intends to continuously assess the security of cloud models against three types of passive attackers and one type of aggressive adversary. This study has demonstrated how some of the systems' security breaches result from the threat models and what steps are frequently taken to ensure these systems' confidentiality. This study also examines the most popular items on the market and demonstrate the degree of security. Online Social Networking (OSN) services allow users to publish "posts"that contain personal information, media, and news items. On OSN, users can create groups and send messages to one another in private conversations. A group of people can communicate privately with one another. Online discussion is another name for this. These show how these systems are open to inference attacks because of their unencrypted metadata and access patterns. And last, generic design principles for safely developing such systems. This research study defines and introduces the Virgil end-to-end encryption method, which makes use of a symmetric AES key encryption mechanism. There is now a fully functional human messaging service as a result. Instead of relying on outside programmers with questionable or undefined security standards, we created our prototype from the ground up in Java. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Jotter: An Approach to Summarize the Formal Online Meeting 1

Jotter: An Approach to Summarize the Formal Online Meeting

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Bhat, Sumedh S Ahmed Nawaz, Uzair Sujay, M. Tantri, Nameesha Vasudevan, Vani Nitte Meenakshi Institute of Technology Bengaluru Computer Science Engineering Karnataka India

ISBN: (纸本)9798350316469

This paper examines various meeting summarising techniques. It also presents a hybridised technique for meeting summarization that combines abstractive and extractive techniques. Text extraction from meetings is accomplished in two ways: audio during the meeting and text recognition from the screen. These extracted texts are then compiled to create a meeting summary. In contrast to extractive text summarising, which concatenates essential sentences from paragraphs, abstractive text summarization focuses on providing a coherent summary of the given content. The maj ority of recent progress on abstractive summarization has been using RNN or Recurrent Neural Networks, although RNN-based algorithms fail when dealing with long sequences. This paper proposes hybridizing these two methods sequentially for meeting summarization to create a better overall summary of the meeting. This research endeavour seeks to convert conference video and audio into text documents and then run our hybridised text summarizer model on them. The result is a summarised text document that the various stakeholders, whether present at the conference or not, could utilise for rapid and concise reference. It will help the people who are not been able to attend the meeting can get the main points discussed in the meeting through summary. © 2023 IEEE.

关键词： Abstractive Technique Artificial Intelligence Deep Learning Extractive Technique Machine Learning Object Detection Text Summarization

来源：评论

学校读者我要写书评

暂无评论

A Collective Approach to SMS Spam Detection: Harnessing the Power of Multimodal Features, Machine Learning, and Advanced Classifiers 1

A Collective Approach to SMS Spam Detection: Harnessing the ...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Sandhya, B.R. Darshan, R.M. Anushree, L. Nitte Meenakshi Institute of Technology Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350316469

In the current of mobile communication, Short Message Service (SMS) remains a dominant means of interaction despite the proliferation of messaging apps. Unfortunately, this increase in SMS traffic has given rise to an increase in SMS spam. This unwelcome phenomenon has become a conduit for advertising and fraudulent activities, causing significant inconvenience and harm to users. Thus, achieving a better way of SMS spam filtering is a formidable challenge. In this research, a machine learning based approach to spam SMS detection is used. This approach uses a variety of machine learning algorithms, including Logistic Regression, Support Vector Machines (SVMs), Multinomial Naive Bayes (MNB), Voting Classifiers, Stacking Classifiers and many other ML models. The best model based on its performance, measured by accuracy and precision is found out to be Multinomial Naïve Bayes, this model is chosen and further used for spam and ham classification. This model resulted in accuracy of 97% and precision of 100%. This shows that multinomial naïve bayes is the most suitable model for this classification task. © 2023 IEEE.

关键词： Machine Learning Multinomial Naive Bayes Stacking Classifiers Support Vector Machines Voting Classifiers

来源：评论

学校读者我要写书评

暂无评论

REGAC: Multi-Class Offensive Content Identification Using Graphical Approach

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第4期52卷 931-952页

作者： Chinivar, Sneha Roopa, M.S. Arunalatha, J.S. Venugopal, K.R. Department of Computer Science and Engineering Bangalore University K R Circle Karnataka Bengaluru India Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Karnataka Bengaluru India Department of Computer Science and Engineering Bangalore University K R Circle Karnataka Bengaluru India Karnataka Bengaluru India

Online offensive behaviour continues to rise with the increasing popularity and use of social media. Various techniques have been used to address this issue. However, most existing studies consider offensive content identification as a binary or ternary problem, disregarding the potential for multi-class classification of derogatory content. In this work, we propose RoBERTa Embedding-based Graphical Approach Classifier (REGAC), which aims to designate the identified offensive content into varied classes,like age, gender, ethnicity, religion, and others to understand what exact qualities the bully usually targets in their victim so that pertinent measures can be taken to battle them. Additionally, the models’ efficiency is evaluated using an unbalanced dataset to identify types of offensive content. The word embeddings are generated for a balanced dataset using RoBERTa embedding model to bring out the best-fitting vectors. These vectors are then input into traditional Machine Learning algorithms (SVM, KNN, Logistic Regression, Random Forest, and XGBoost) and graph-based algorithms (Graph Convolution Network (GCN), GraphSAGE, and Graph Attention Network (GAT)) for fine-grained categorization of offensive textual content. The experimental results demonstrate the efficiency of combating social media’s offensive content of the proposed work with higher Precision, Recall, F1-Score, and Accuracy compared with most state-of-art approaches. © (2025.0), (International Association of Engineers). All Rights Reserved.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time series Forecasting for Cloud Machine Utilization 3

Multivariate Time series Forecasting for Cloud Machine Utili...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Naik, Archana Sooda, Kavitha Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bangalore India Department of Computer Science and Engineering B.M.S. College of Engineering Bangalore India

ISBN: (纸本)9798331527549

The cloud machine utilization prediction using a multivariate time series model is explored in this study. The cloud machine usage data set samples are selected with varied patterns. The long sequence forecasting model Informer is investigated for the forecasting. The model results are benchmarked against LSTM, GRU, Prophet, and XGBoost across the diverse datasets. The performance is evaluated using RMSE. Experimental results show that the Prophet model performs best overall due to its ability to capture both seasonal and irregular patterns accurately. The RMSE value for Informer is 0.13, Prophet is 0.097, XGBoost is 0.096, LSTM is 0.1725, and GRU is 0.1547. © 2025 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection using CNN 15

Lung Cancer Detection using CNN

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Shobhar Aswin, R.B. Gupta, Rohan Sharma, Varun N. Nalini, N. Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology- Affiliated to Visvesvaraya Technological University Bangalore India

ISBN: (纸本)9798331300579

Lung cancer remains a sizable global health concern, challenging beforehand detection for improved treatment outcomes. This paper explores the transformative potential of Deep Learning techniques, exclusively convolutional neural networks (CNNs), in the accurate identification and classification of lung cancer using computed tomography (CT) scans. A comprehensive literature survey outlines diverse methodologies, including CNNs, support vector machines (SVMs), and feature extraction, employed in the pursuit of precise lung cancer diagnosis. Our proposed methodology involves preprocessing CT scan images, feature extraction, and the application of a CNN model trained on a dataset of lung CT scans. The CNN model aims to categorize images into distinct types of lung cancer, proposing a promising avenue for enhanced diagnostic accuracy. Results and analysis showcase the proficiency of our CNN model, supported by key performance indicators. As we delve into the future of cancer diagnostics, the integration of advanced machine learning with medical imaging emerges as a beacon of hope for quick and personalized lung cancer detection, surfacing the way for improved patient outcomes. © Grenze Scientific Society, 2024.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Virtual Medical Assistant in English and Kannada Languages 1

Virtual Medical Assistant in English and Kannada Languages

引用

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Mamatha Bai, B.G. Prerana, Preethi Benki, Akash A Rakesh, R. Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350323795

Health care and medicine are two crucial facets of human existence. This guarantees patients the right to accurate and timely clarification of any questions they may have about their health state. A virtual assistant built with the help of Natural Language Processing [NLP] makes it simpler for consumers to consult the medical personnel in the pandemic situation from the comfort of their homes without any direct contact. This work discusses various methods for building virtual medical assistants that may interact with people to answer simple questions about health characteristics and recommend necessary actions to the user. A unique inclusion in this paper is the support to a regional language which is kannada in this case. In order to identify the ailment, the system extracts essential keywords from the chat and applies predictive analysis. The user is advised to see a doctor, take medication, or visit the hospital, depending on the severity of the symptoms. The Kannada voice-bot has a higher processing time when compared to the English voice-bot due to change in dialects. The real goal of this job is to address the user's symptoms and offer appropriate medical advice in order to shorten the process's time and expense requirements. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Co-expression and Data Fusion Analysis of Omics Data for Liver Related Metabolic Diseases

引用

SN computer science 2024年第6期5卷 670页

作者： Shobha, P. Nalini, N. Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology (Affiliated to Visvesvaraya Technological University - Belagavi) Karnataka Bengaluru 560064 India

In the proposed work co expression technique is applied to perform data fusion techniques to integrate omics data, understand gene and protein relationships, explore protein expression in human tissues, and identify drug targets. The need to comprehensively analyze diverse omics data—transcriptomics, proteomics, metabolomics using co-expression analysis and data *** obtaining and processing data from the Protein Atlas website to extract information about protein subcellular location and gene expression in various cell lines. The fusion process combines these datasets based on a common "Gene” property, facilitating analysis to identify potential therapeutic targets, specifically for liver-related metabolic diseases. This approach utilizes feature-level fusion and leverages resources for research purposes, offering insights into protein functions, cellular processes, and potential drug targets. The integration of data sources and feature-level fusion, illuminating the intricate interplay between protein subcellular localization and gene expression across cell types and tissues. This fusion technique uncovers potential therapeutic targets for liver-related metabolic disorders. The Protein Atlas database, a valuable resource, aids researchers and clinicians. The correlation matrix offers insights into variable interactions and potential biomarkers. PCA provides dimensionality reduction and trend visualization, while WGCNA explores co-expression patterns in-depth. These techniques offer varying levels of complexity and insight, catering to different analytical goals. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Co expression Data fusion Gene Medical Protein Sub cellular

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：