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： Kumar, Devesh V.V. Sreesankar, S. Dinesan, Krishnpriya Nair, Pranav B. Deepthi, L.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9798350370249

Graphs are effective models for illustrating complex connections in various contexts, including social networks, citation networks, and biological systems. In this study, the performance of Graph Neural Networks(GNN) for two main tasks is being explored: Node classification and Community detection. Community detection on complex networks is an emerging area that helps to understand the underlying structures and functions of interconnected systems across various domains. The structural and semantic information are captured using the various GNN models. This paper uses four GNN models for node classification: GCN, GAT, GraphSAGE, and Deep Graph Infomax. The embeddings of these models are clustered to detect the communities by using spectral clustering, k-means clustering, and the Louvain algorithm. The GNN model’s performance was assessed in terms of computational complexity, accuracy of clustering, and modularity. The results demonstrate that GNN models, particularly GCN, yield competitive performance in community detection tasks on citation networks. The effectiveness of each model varies across different datasets and community detection algorithms. ©2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Identifying Multiple Faces in Newspapers Using Textual Analysis 1

Identifying Multiple Faces in Newspapers Using Textual Analy...

引用

1st IEEE International Conference on computing and Data science, ICCDS 2024

作者： Bharath, Peruri Shakthi Udhaya Kumar, S. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350365337

The effectiveness, speed, wealth of documentation, community support, integration possibilities, platform freedom, integrated face detection models, and ongoing development make OpenCV the tool of choice for face detection and identification. It includes multiple face recognition methods and is compatible with real-time applications thanks to its streamlined Python code. Although there are competing frameworks, OpenCV is a well-liked option for computer vision applications due to its efficiency and versatility. An 87% accuracy rate is achieved when LSTM networks are integrated for text processing, demonstrating its potential for sequential input analysis. In comparison with previous methods such as LDA, PCA, EBGM, and AAM, the suggested method shows significant improvements. Empirical testing under ideal and real-world conditions confirms the effectiveness of joint identification of numerous faces by associating the corresponding text, even though it increases complexity. This method produces considerable benefits in retrieving information from news articles and resolves accuracy difficulties. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

AudioGuard: Deep Learning Based Telugu DeepFake Audio Detection 15

AudioGuard: Deep Learning Based Telugu DeepFake Audio Detect...

引用

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

作者： Karna, Siwani Haneesha, Samudrala Sai Santhoshi Jahanve, Poluru Reddy Pati, Peeta Basa Balakrishnan, Roshni M Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Recent advancements in deep fake audio technology have led to the creation of highly realistic synthetic voices that mimic human speech patterns. However, this technology raises ethical concerns due to its potential for misuse, including spreading misinformation, identity theft, and undermining trust in audio evidences. To address these issues, this research focuses on developing a method to detect deep fake audio specifically in the Telugu language. This research utilizes various Convolutional Neural Network (CNN) architectures like MobileNetV2, ResNet50, VGG16, and AlexNet to enhance accuracy and resilience. MobileNet achieved the highest accuracy of $\mathbf{9 9. 5 \%}$ and was chosen for deployment. The model is integrated into a user-friendly website using Flask, HTML, CSS, JavaScript, and MongoDB. This web application serves as a comprehensive solution for detecting Telugu deep fake audio, prioritizing user security, ease of use, and accuracy. © 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

Detect and Alleviate DDoS Attacks in Cloud Environment 1

引用

8th International Conference on Emerging Research in computing, Information, Communication and Applications, ERCICA 2023

作者： Kulwanth, Bandi Srinivasarengan, V. Anish, Peddinte Abirami, K. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9789819976331

ISBN: (纸本)9789819976324

The Internet is now a crucial aspect of our lives, and distributed computing has grown significantly in size, capability, and complexity, becoming an essential element of our daily lives. There are numerous vulnerabilities in distributed network computing, including viruses, worms, distributed denial of service (DDoS), DoS, and more. One of the more newsworthy attacks recently has been distributed denial-of-service attacks. Attacks that cause denials of service (DoS) have developed and had an influence on the Internet infrastructure. A DDoS attack aims to prevent the targeted users from accessing a computer resource. In this paper, we perform a comprehensive survey of detecting DDoS packets via couple of machine learning algorithms such as Random Forest, Gradient Descent, decision tree, Multi-layer Perceptron, and radial basis function using the CIC-DDoS2019 dataset. We also combine all our machine learning models into one hybrid model via an ensemble classifier. After that, we experiment with a DDoS attack on a local server via Ufonet and capture the data packets during the attack using the Wireshark tool. The captured data will be converted to a CSV file and can be given as input to machine learning models. The results show that each machine learning algorithm is predicting DDoS packets incoming into the server. The experimental results show that the proposed DDoS attack detection method based on machine learning has a good detection rate for the current popular DDoS attack. Finally, directions for future research work have been pointed out. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

MBTI Based Personality Prediction using Social Media Data 15

MBTI Based Personality Prediction using Social Media Data

引用

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

作者： Prasanna Kumar, R. Bharathi Mohan, G. Rithani, M. Pallavi, Gundala Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350370249

Existing methods for assessing an individual's personality are very cumbersome due to those tests being very monotonous and erroneous due to a self-report bias. Whereas data-driven, automatic personality deduction raises privacy concern due to them needing external personal information. In our model, a person's personality can be classified based on the 16 categories of Myers-Briggs personality types. With the availability of a huge amount of data on human behavior and personality traits, a machine learning model can be trained, and it can predict the personality trait of a person. A MBTI dataset is used to analyze and train the model. Upon analyzing the dataset, we found out that the classes are not balanced. To overcome this problem, we used binary classification. Next, we used the NLTK library to pre-process the data. We selected four machine learning models and trained our data in those models. Furthermore, we compared the results of four different machine learning models and chose the most accurate model. This research can be used to personalize advertisements, coaching for students and companies can use this research to attract specific types of audience. © 2024 IEEE.

关键词： Logistic regression Myers-Briggs personality types Naïve Bayes NLTK Personality prediction Random Forest SVM

来源：评论

学校读者我要写书评

暂无评论

Enhancing Credit Card Fraud Detection with Deep Learning and Graph Neural Networks 15

Enhancing Credit Card Fraud Detection with Deep Learning and...

引用

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

作者： Sherwin Akshay, J.G. Vinusha, T. Sharon Bianca, R. Sarath Krishna, C.K. Radhika, G. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350370249

Financial fraud poses a major threat to financial service institutions and clients, facilitating anomaly detection capabilities. This paper dives into deep learning models which can be implemented to detect and distinguish fraudulent transactions from normal transactions and flag anomalies. Further, conversion of tabular data to graphs have been implemented for keen understanding and improved pattern analysis of fraudulent transactions, challenges include evolving attack strategies, class imbalance and model interpretability. The proposed methods utilize a synergistic combination of ensemble learning techniques and unsupervised deep neural networks, like Auto-Encoders and Recurrent Neural Networks. In the graphical representation, this study focuses on implementing Louvain Modularity, Girvan-Newman and Label Propagation Algorithm for effectiveness in community detection. The outcomes exhibit consistently reliable results on credit card transaction datasets. A comprehensive comparative analysis follows to compare the proposed approach to traditional fraud detection methods, demonstrating its superiority in accurately identifying fraudulent transactions, adapting to emerging threats, handling high-dimensional data, and mitigating class imbalances with respect to data privacy and security. © 2024 IEEE.

关键词： Auto-Encoders CatBoost GAN GNN GRU RNN Unsupervised learning XG-Boost

来源：评论

学校读者我要写书评

暂无评论

Prognostic Modeling of Diabetes Mellitus in Women: A comparitive analysis of Machine Learning algorithms integrating Clinical and Genetic Data

Prognostic Modeling of Diabetes Mellitus in Women: A compari...

引用

2024 IEEE International Conference on Emerging Technologies in Computer science for Interdisciplinary Applications, ICETCS 2024

作者： Prashanth, M. Venkat Jose, Nikhil Tom Verma, Konda Hemesh Sreevidya, B. Rajesh, M. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350372502

Diabetes is considered as one of the most commonly observed medical condition among human beings. Millions of people worldwide are affected by a chronic condition that goes by the name of diabetes. There are 3 sorts of diabetes and they comprise of Type 1, Type 2 and Gestational diabetes. Early prediction of diabetes helps to avoid complications like diabetic retinopathy which leads to blindness. There is a 13% higher risk of death among people with diabetes, especially in women, cardiovascular disease caused by diabetes attributes to 50% higher risk of death, coronary heart disease caused by diabetes contributes to a 58% higher risk of death. The proposed research work aims in predicting diabetes from the symptoms a patient exhibit. The proposed system is a healthcare assisting system which is accessible to patients as well as medical practitioners. The system is developed as a web application using the features of Django python framework along with suitable database management system. The system is powered with gradient boosting machine learning algorithm for predictions. By using the web application along with a blood test to find out the insulin levels and glucose levels in blood, any user can predict whether he/she would be affected by diabetes in future and can avoid the complications caused by diabetes. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Infield disease detection in citrus plants: integrating semantic segmentation and dynamic deep learning object detection model for enhanced agricultural yield

引用

Neural computing and Applications 2024年第35期36卷 22485-22510页

作者： Rani, N. Shobha Krishna, Arun Sri Sunag, M. Sangamesha, M.A. Pushpa, B.R. University Bengaluru India Department of Computer Science School of Computing Amrita Vishwa Vidyapeetham Mysuru India Department of Chemistry The National Institute of Engineering Mysuru India

Simultaneous and dynamic detection of diseases from infield images of citrus plants is the primary objective of this investigation. Refraining from discarding the disease-related issues would reduce agricultural yield and production, resulting in significant crop loss and economic instability. Computer Vision offers an inexpensive and efficient solution for detecting and predicting multiple diseases from infield images of citrus plants in various stages of plant growth. This study aims to perform simultaneous detection and prediction of cankers, mites, and nutritional deficiencies from infield images of citrus plants. For this purpose, over 4914 samples are annotated that are obtained from 441 image samples collected from orchards of citrus plants. Initially, the input image is subject to preprocessing followed by segmentation of prominent leaf regions and disease prediction. Contributions investigated in this work are two-fold: a deep semantic segmentation model named Dynamic U-Net is employed to extract prominent regions of interest, and a dynamic, lightweight object detection deep learning model for predicting diseases. From experimental outcomes, the segmentation efficiency is found to be 89.07% foreground accuracy, 0.7881 of IoU, and 0.9188 of the Dice coefficient. The object detection performance is quantified using the mapped metric, resulting in 0.85, 0.71, 0.64, and 0.27 efficiency concerning plant diseases, cankers, mites, and nutritional deficiency. As per the findings, the proposed approach is an effective solution to perform automated detection and prediction from infield images of citrus plants. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

Empowering Linguistic Diversity: Bridging Cultures through Neural Machine Translation from Dzongkha to Hindi 15

Empowering Linguistic Diversity: Bridging Cultures through N...

引用

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

作者： Ganguly, Tania Santhanalakshmi, S. Pati, Peeta Basa Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350370249

Bhutan and India have enjoyed longstanding friendly relations, fostering significant travel between the two nations. However, linguistic differences often impede visitors' comprehension of cultural beliefs, particularly between Dzongkha, Bhutan's native language, and Hindi, widely spoken in India. This paper presents an innovative language translation solution leveraging Neural Machine Translation (NMT) models which is the first and only solution to overcome these barriers. The goal is to enrich tourists' experiences by providing comprehensive insights into the cultural intricacies of both countries. Through extensive testing, the proposed methodology achieves a promising BLEU score of 0.416, offering an effective means to bridge the linguistic gap and foster cross-cultural understanding. © 2024 IEEE.

关键词： Long Short Term Memory (LSTM) Low Resource Language (LRL) Neural Machine Translation (NMT) Sentence Length Analysis (SLA)

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Telugu News Articles Decoding Textual Nuances 2

Sentiment Analysis of Telugu News Articles Decoding Textual ...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Viswanadh, V Balaji Eswar Prasad, K. Bharathi Mohan, G. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350328202

In the field of Natural Language Processing, analyzing sentiment in Telugu presents distinctive challenges owing to the limited availability of annotated datasets. This paper presents a sophisticated method utilizing BERT (Bidirectional Encoder Representations from Transformers) for Telugu sentiment analysis, complemented by Part-of-Speech (POS) and Named Entity Recognition (NER) algorithms. The proposed system follows a multi-step process, leveraging BERT's bidirectional context understanding during pretraining, and subsequently fine-tuning the model with a focus on sentiment analysis. Additionally, the integration of POS and NER algorithms enhances the language model's capabilities by capturing grammatical components and identifying named entities in Telugu text. The model is evaluated on a diverse Telugu dataset, specifically the Telugu Sentiment Analysis Dataset (TSAD), demonstrating its proficiency in predicting sentiment labels. The study addresses the problem of limited annotated data in Telugu sentiment analysis and show-cases significant improvements in accuracy, precision, and recall compared to previous approaches. The proposed system achieves a notable accuracy of 92.07 %, illustrating its effectiveness in capturing the nuances of sentiment expression in Telugu. © 2024 IEEE.

关键词： Sentiment analysis

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：