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： Poojitha, D. Darak, Tanmay Samaddar, Ushnish Venugopal, Manju Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350370249

The ability to predict customer churn represents a critical component in the telecom industry's quest for enhanced customer retention and long-term viability. In this research, several standalone machine learning algorithms, including gradient boosting and decision trees, have been applied to a dataset comprised of customer demographics and service usage patterns. The application of rigorous hyperparameter tuning and cross-validation processes has significantly improved the performance metrics, such as accuracy, precision, recall, and F1 score, of these models. Furthermore, the study incorporates two advanced ensemble techniques to refine the prediction accuracy. The combination of Random Forest and Gradient Boost achieved an accuracy of 85.7%, while the integration of AdaBoost and CatBoost resulted in an accuracy of 87.3%. This approach provides telecom operators with a potent tool to proactively identify and engage customers at risk of churn, thus enabling timely and targeted retention strategies that enhance customer satisfaction and contribute to the sustainability of telecom enterprises. ©2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Octopus: A Latent Diffusion Model for Enhanced Text-Driven Manipulation in Image Synthesis

Octopus: A Latent Diffusion Model for Enhanced Text-Driven M...

引用

2024 IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2024

作者： Nithin Skantha, M. Meghadharsan, B. Sri Vignesh, C. Thiruselvan, J. Anuragi, Arti Coimbatore Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering India

ISBN: (纸本)9798350376876

By combining user interactivity and precise control over image attributes, the applications of text-based image synthesis can be vastly expanded. Thanks to recent advancements in developing state-of-the-art text-to-image models, we can now generate images with high fidelity and diversity. While a plethora of research focuses on improving the fidelity and diversity of images generated using text prompts, less focus is given to controlling the attributes or characteristics of the generated images. On the other hand, there have been advancements in image editing through text prompts, but most of these models lack the understanding of spatial knowledge and precise control over the objects present in the image, which makes the edited images lose much of their characteristics. To address these challenges, this study proposes a three-step methodology to introduce our text-driven image editing conditional diffusion model called 'Octopus,' which has precise control over image attributes. To bring in control over image attributes, this study uses a similar methodology proposed in a recent study, which uses rich text to control image attributes while exploring different formats, including bold, footnotes, font size, and font color. Then this model is used along with a fine-tuned Large Language Model (Gemma), to create a dataset of image editing examples to train Octopus, which, given an input image and edit instructions, generates the precise edited image during inference. This study demonstrates the potential of this approach with a variety of compelling results. © 2024 IEEE.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

DDSS: Driver decision support system based on the driver behaviour prediction to avoid accidents in intelligent transport system

引用

International Journal of Cognitive computing in engineering 2024年第1期5卷 1-13页

作者： S, Balasubramani D, John Aravindhar Renjith, P.N. Ramesh, K. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India

Accidents caused by drivers who exhibit unusual behavior are putting road safety at ever-greater risk. When one or more vehicle nodes behave in this way, it can put other nodes in danger and result in potentially catastrophic accidents. In order to anticipate and handle unusual driving behavior in Intelligent Transportation Systems (ITS), this research presents a unique Driver Decision Support System (DDSS). A reliable driving behavior prediction system is used by the suggested DDSS to categorize drivers as displaying normal or abnormal behavior. In order to prevent accidents in ITS scenarios, the system reliably detects anomalous driving patterns and advises nearby vehicles to change lanes or alter speed. The driver behavior prediction algorithm efficiently groups drivers into behavior categories using the K-Means clustering method. In order to evaluate the algorithm's efficacy, a comparative analysis is conducted by comparing its outcomes against those of Support Vector Machines (SVMs), Decision Trees, K-Nearest Neighbours (KNN), Logistic Regression, and Naïve Bayes. The integration of the Driver Decision Support System into the Intelligent Transportation System infrastructure serves to augment endeavours in accident prevention. Monitoring and analysis of driver behavior enable timely interventions, promoting safer driving practices and reducing accident risks. This research helps to create a more effective transportation system by reducing the number of accidents brought on by reckless driving. Because of its novel method to anticipating and controlling driver behavior, the proposed DDSS has promise for improving road safety and preventing accidents. The efficacy and the dependability of the driver behavior prediction algorithm are confirmed by the experimental assessment. © 2023

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Fortifying Digital Security: A Machine Learning and Explainable AI Framework for Password Strength Assessment 8

Fortifying Digital Security: A Machine Learning and Explaina...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Shreya, Kuthati Divakarla, Lasya Priya Kumar, Kanderi Johith Vishwas, H.N. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350367904

In the current era where almost anything is accessible over the internet, passwords have become most important to ensure security and authentication. To provide authentication many other mechanisms exist like smart locks, biometrics, voice recognition, face recognition, etc. but still, passwords exist as the widely preferred method for authentication because of its ease of use and as many people are familiar with passwords. With the ease of use that it comes with there is a possible threat of guessing the passwords that exists. Usually, the passwords are some patterns, names, important years, etc. These are sometimes repetitive or easily guessed by the attacker because of their simplicity, and having common and weak passwords. The proposed model is a machine-learning algorithms that classifies the passwords as weak, medium, and strong based on their strength. Machine learning models like Random Forest (RF) classifier, Logistic Regression, XGBoost (XGB), and Gradient Boosting Machines (GBM). © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Convolutional Neural Network Architectures for Pneumonia Diagnosis from Chest X-ray Images 15

Comparative Analysis of Convolutional Neural Network Archite...

引用

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

作者： Padmavathi, A. Kavyasree, Nagireddy Sanjana, N. Devi, Mareddy Gayathri Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350370249

Various viruses, bacteria, etc., are responsible for an infection called pneumonia which can be discovered by X-rays. This study will present some Convolutional Neural Network models for diagnosing pneumonia with the help of X-ray images. The dataset used contains 5856 X-ray images, which were used for training and validation. Various CNN architectures were trained to classify X-ray images into two groups: pneumonia and non-pneumonia. Some models were fine-tuned by altering parameters, hyperparameters or several convolutional layers. Four pretrained models were used: EfflcientNetB0, ResNet50, DenseNet121 and AlexNet. Among them all, the EfficientNetB6 model achieved the best validation accuracy of 84%. ResNet50 came after that at 76% while DenseNet121 had 82%. Lastly, with an accuracy score equating to 62% AlexNet performed worst among these four models. The chest X-ray dataset, comprising of 5856 images, was used for training and evaluation. © 2024 IEEE.

关键词： Convolutional neural network Deep learning Image Classification Pneumonia Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Gunshot Sound Detection using AlexNet and XGBoost from Fourier Spectrograms 4

Enhanced Gunshot Sound Detection using AlexNet and XGBoost f...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Priya, M.Yagnasri Shendre, Sanjivani P. Pati, Peeta Basa Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350349900

Gunshot detection and classification are pivotal for ensuring public safety, law enforcement, defense, and forensic investigations. This paper presents a comparitive study into the effectiveness of deep learning and traditional machine learning models in classifying gunshot sounds through Short-Term Fourier Transform (STFT) spectograms is presented. The study involves integrating Convolutional Neural Networks (CNNs) with standard machine learning techniques to extract and analyze features, particularly focusing on the penultimate layer of CNNs. By leveraging these features, this paper aims to enhance the system's ability to accurately identify complex sound patterns associated with gunshots. This analysis provides insights into the strengths and weaknesses of deep learning and machine learning approaches in gunshot classification, particularly achieving a perfect accuracy score with AlexNet and XGBoost. These findings pave the way for more effective gunshot detection systems in a variety of operational scenarios, thereby significantly contributing to public safety measures. © 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

Premature Birth Prediction Using Machine Learning Algorithms - A Comparative Analysis 7

Premature Birth Prediction Using Machine Learning Algorithms...

引用

7th International Conference on Contemporary computing and Informatics, IC3I 2024

作者： Padmavathi, A. Maurya, Laxmi Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350350067

Premature birth (PB) presents a significant global health challenge, often leading to enduring developmental issues and neonatal mortality. Approximately 4-16% of new-born worldwide is born prematurely. Leveraging machine learning, a predictive model has been developed to anticipate preterm birth risk. This model evaluates maternal characteristics and other pertinent factors to provide timely alerts to healthcare providers. Through the analysis of extensive datasets, the system offers valuable insights for forecasting and classifying preterm birth risks. First and foremost, this study aims to enhance prenatal care and outcomes for high-risk pregnancies by harnessing artificial intelligence to refine the accuracy and promptness of preterm birth prediction. Employing machine learning algorithms, our study achieves a remarkable 99% accuracy rate throughout all the techniques. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Accent-Enhanced Automatic Speech Recognition for Multilingual Classrooms 15

Accent-Enhanced Automatic Speech Recognition for Multilingua...

引用

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

作者： Jagadeeshvaran, M. Sarah Michelle, H. Shruti Bala, S. Srinivasa Vinayak, M. Deepika, T. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350370249

In an increasingly interconnected world, universities face the challenge of hosting diverse students from different backgrounds. The biggest obstacle to effective communication and learning in multicultural classrooms is teacher and student diversity. To overcome this challenge, we propose the development of noise-enhanced automatic speech recognition (ASR), specifically for multilingual classrooms. The system is designed to provide instant feedback on lessons while preserving the subtleties of speech, thus improving understanding and creating a learning environment. Using the advanced capabilities of the Transformer model together with the convolutional neural network (CNN) highlight classifier, the proposed system provides powerful and accurate transcription capabilities. This article provides an overview of the design, implementation, and evaluation of voice-enhanced ASR, demonstrating its potential to transform communication and learning in a variety of educational settings. © 2024 IEEE.

关键词： Accent Enhancement Accent Nullification Automatic Speech Recognition Inclusive Learning Multilingual Classrooms Speech Transcription

来源：评论

学校读者我要写书评

暂无评论

Enhanced prediction of agricultural CO2 emission using ensemble machine learning-based imputation approach

引用

Neural computing and Applications 2024年第36期36卷 22867-22887页

作者： Thendral, M. Sathya Abinaya, S. Devi, M. K. Kavitha Department of Computer Science and Engineering Thiagarajar College of Engineering Madurai625015 India School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India

The agricultural sector contributes significantly to greenhouse gas emissions, which cause global warming and climate change. Numerous mathematical models have been developed to predict the greenhouse gas emissions from agriculture. However, the database utilized for prediction has thousands of missing values and imbalanced data records due to various factors, such as environmental disasters, sensor failure, maintenance issues, and budgetary constraints. Many researchers have either completely discarded records with missing values or have only partially addressed the issue, leading to less precise predictions. This study proposes a machine learning-based ensemble approach that uses multiple imputation by chained equations (MICE), K-nearest neighbors (KNN), and MissForest techniques to impute the missing values by reducing uncertainties and improves robustness in predictions. Furthermore, Synthetic Minority Oversampling Technique (SMOTE R) addresses data imbalance in CO2 emissions prediction by generating synthetic data to balance the target variable's distribution in the regression problem. Thereby the proposed SMOTE R and ensemble imputation approach aims to improve prediction accuracy and reliability by tackling data completeness and distribution issues simultaneously. The experiments are conducted on the GRACEnet database shows that the proposed approach outperforms the existing work in measure of R2, MAE, and RMSE metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Greenhouse gas emissions

来源：评论

学校读者我要写书评

暂无评论

Discernment and Enumeration of Security Vulnerabilities Present in Docker Images 15

Discernment and Enumeration of Security Vulnerabilities Pres...

引用

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

作者： Chopra, Shraddha Sreedevi, A.G. Shanmugam, Udhayakumar Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9798331300579

Docker containers have emerged pivotal in the packaging, distributing and deployment of applications ushering into a new era of flexibility and scalability across diverse computing environments. Consequently, this widespread integration has led to formidable challenges in the security domain. These are primarily concerned with the detection and remediation of vulnerabilities inherently present within the Docker images. This study presents an automated pipeline for Docker image analysis, focusing on vulnerability detection and severity assessment. Employing a methodical research framework, the study undertakes a systematic scrutiny of Docker images sourced from the most comprehensive antecedent, DockerHub. The images are then examined using a blend of manual inspection and automated vulnerability scanning methodologies, aiming to enhance the security posture by identifying and categorizing vulnerabilities based on severity, and to provide insights into the image composition. The threats are then cross-referenced with the common vulnerabilities and exposures (CVE) database to ascertain their presence in known security advisories and to facilitate accurate risk assessment and mitigation strategies. © Grenze Scientific Society, 2024.

关键词： Risk assessment

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：