检索结果-内蒙古大学图书馆

By artificial intelligence algorithms and machine learning models to diagnosis cancer

Materials Today: Proceedings 2023年 80卷 2969-2975页

作者： Agarwal, Seema Yadav, Ajay Singh Dinesh, Vennapoosa Vatsav, Kolluru Sai Sri Prakash, Kolluru Sai Surya Jaiswal, Sushma Department of Mathematics SRM Institute of Science and Technology Delhi-NCR Campus U.P. Ghaziabad India Software Engineer Mechanical Engineering National Institute Of Technology Mizoram Aizwal Mizoram India Computer Science Engineering Gitam university Andhra Pradesh Visakhapatnam India Bilaspur India

Cancer is one of the world's most critical health issues. Many in the past decade More accurately, diagnostic tests and methodologies have been enhanced. Tests are categorised into imaging tests, endoscopic procedures Includes testing for biopsy and cytology. These diagnostic tests yield huge numbers. volumes of data that must be evaluated and differentiated by specialists Between tumours that are benign and malignant. Artificial intelligence now (AI) Large quantities of diagnostic imaging may be examined using applications Improved accuracy to enhance health system efficiency. New AI algorithms technical advances and computer enhancements Hardware may be used to train diagnostic neural artificial networks Experience with a wide range of scans. Already a thorough understanding and Machines can educate computers to compare and assess models Huge quantity of cancer scanning data. Highly diagnostic skills Software has been evaluated and compared to the conventional Cancer specialists' diagnostic tools. Their precision is much increased and regarded highly effective in early diagnosis and extended forecasting Different cancers. Scientists have become systems of artificial intelligence (AI). that may exceed human specialists in the prognosis of breast cancer and A great deal earlier diagnosis. Similarly, informatics developed an AI algorithm. and profound learning algorithms that may forecast to which persons Develop lung cancer using low dose CT analysis (computerized tomography) Lung scans. Lung scans. Use of the convolutionary neural network recently (CNNs) was employed in the invasion depth diagnosis of Gastric endoscopy-based gastric cancer. Studies have also been shown AI techniques paired with imagery may have a significant influence early diagnosis with algorithm-guided identification of oral cancer results Heterogeneity of the oral lesion. This review gathered some pretty interesting information Research publications on the topic. © 2021

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

Impact Analysis of Anthropogenic Activities on Coastal Vulnerability in Vishakhapatnam City on the Eastern Coast of India Using Remote Sensing

Impact Analysis of Anthropogenic Activities on Coastal Vulne...

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Challa S B Haranadh Naina Narang Department of Computer Science and Engineering GITAM School of Technology Visakhapatnam India

ISBN: (数字)9798350390346

ISBN: (纸本)9798350390353

Coastal locations are among the most vulnerable to the consequences of climate change and anthropogenic activities. Vishakhapatnam in India is one of the coastal cities susceptible to climate change’s effects, such as coastal erosion and extreme weather events. Currently, coastal land loss and its correlation with climate change are studied using the coastal vulnerability indices (CVI), primarily driven by physical and geological factors such as coastal features, change rate, sea level rise, coastal exposure, wave height, and tidal range. However, there is a need for multi-dimensional CVI to include more comprehensive parameters in the coastal vulnerability atlases, and better predictions and correlations can be deduced from the vulnerability study. The study aims to identify the shoreline change in Vishakhapatnam City that can be related to anthropogenic activities leading to coastal vulnerability. In the future, the results will be used to determine the multifaceted features driven by climate change, such as extreme weather events. A Google Earth Engine (GEE) application is developed to perform this study. The results show substantial coastal vulnerability.

关键词： Climate change Correlation Normalized difference water index Urban areas Sea measurements Landsat Sea level rise Indexes Remote sensing Meteorology

来源：评论

学校读者我要写书评

暂无评论

Recent advancements in Image Steganography using Generative Adversarial Networks methods

Recent advancements in Image Steganography using Generative ...

引用

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

作者： Syeda Imrana Fatima Yugandhar Garapati Department of Computer Science & Engineering GITAM (Deemed to be University) Hyderabad India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

Generative Adversarial Networks are employed by GAN-based models in image steganography to efficiently conceal information from images while preserving their visual integrity. These models are made up of two primary parts: the discriminator which determines if an image is a real image or a stego-image, and the generator which embeds the hidden data into images. The generator learns how to embed data in a way that minimizes obvious distortions through adversarial training, where the discriminator and generator fight to make the hidden data less noticeable to detection algorithms and human observers. High data capacity and versatility are strengths of GAN-based steganography models, which enable efficient data concealment across a variety of image formats and steganographic techniques. They dynamically adjust the embedding procedure to strike a compromise between image quality and data capacity. They do, however, come with certain drawbacks such as the need for sophisticated model training, high processing overhead and hyperparameter sensitivity. Notwithstanding these drawbacks, GAN-based techniques mark a substantial breakthrough in the development of delicate and reliable image steganography techniques.

关键词： Training Image quality Steganography Visualization Sensitivity Observers Generative adversarial networks Generators Data models Reliability

来源：评论

学校读者我要写书评

暂无评论

Integrating Dropout and Kullback-Leibler Regularization in Bayesian Neural Networks for Improved Uncertainty Estimation in Regression

SSRN

引用

SSRN 2024年

作者： Devadas, Raghavendra M. Hiremani, Vani Department of Computer Science and Engineering Gitam School of Technology GITAM Bengaluru India Pune Lavale India

The objective of the study is to enhance uncertainty prediction in regression problems by introducing a revolutionary Bayesian Neural Network (BNN) model. Experimental results reveal significant improvements in uncertainty prediction and point forecasts with the integrated BNN model compared to the plain BNN. Performance metrics, including mean squared error (MSE), mean absolute error (MAE), and R-squared (R²), demonstrate superior results for the proposed BNN. The experimental results show that for plain BNN, MSE is 87.3, MAE is 6.62 and R2 is -0.0492, whereas for the proposed BNN model MSE was found to be 44.64, MAE is 4.4 and R2 is 0.46. This research brings a fresh approach to Bayesian Neural Networks by incorporating both dropout and KL regularization techniques, resulting in a powerful tool for handling regression tasks with certainty. By combining these techniques, the study enhances model stability, avoids overfitting, and achieve more reliable uncertainty estimation. This study adds to our knowledge of uncertainty-aware machine learning models and offers a valuable solution for accurately assessing uncertainty in various applications. The innovative BNN model merges the power of Bayesian principles with the effectiveness of dropout and KL *** test and refine our model, the study utilizes the Boston Housing dataset for both training and evaluation purposes. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and MRI Improve Carotid Arterial Tree Reconstruction

Deep Learning and MRI Improve Carotid Arterial Tree Reconstr...

引用

2023 International Conference on Data science and Network Security, ICDSNS 2023

作者： Murthy M S, Narasimha Spandan, Gunti Aswani, Inakollu Nayak Bhukya, Shankar Ramachandra, A.C. Bms Institute of Technology and Management Department of Information Science and Engineering Bengaluru India Gst Gitam University Department of Computer Science Bengaluru India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh India Hyderabad India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350301595

This study suggests using magnetic resonance imaging (MRI) scan data to segment and rebuild the carotid artery tree using a deep learning-based method. In the proposed method, the UNET architecture is used to divide an image into parts, and then a 3D level set method is used to make the parts even better. The method was compared to seven different approaches to segmentation and reconstruction, and it outperformed all but one of them. It had a 94% accuracy rate and took 12 hours to process. Deep learning's capacity to reliably segment and categorise pictures, the UNET architecture's ability to maintain spatial information through skip connections, and the level set approach's ability to improve segmentation further all contribute to the proposed method's effectiveness. The proposed approach has the potential to be a useful tool for clinicians in evaluating the status of the carotid artery and finding any irregularities. Stroke is one of the most devastating symptoms of cardiovascular disease, and recognising and treating carotid artery stenosis in its early stages can help avoid or reduce the risk of having a stroke. The success of the proposed method shows that deep learning techniques have the potential to improve the accuracy of carotid arterial tree reconstruction from MRI data. Better identification and treatment of carotid artery stenosis may increase the overall effectiveness of the proposed technique, ultimately leading to better patient outcomes. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Task Scheduling Using a Novel Metaheuristics Approach in Cloud Data Centers

Energy-Efficient Task Scheduling Using a Novel Metaheuristic...

引用

Cognitive, Green and Ubiquitous Computing (IC-CGU), International Conference on

作者： Chaitanya Udatha Gondi Lakshmeeswari Department of Computer Science and Engineering GITAM (Deemed to be University) Visakhapatnam India

ISBN: (数字)9798350361780

ISBN: (纸本)9798350361797

Cloud computing operates under a centralized computing framework and employs a distributed computing paradigm that revolutionizes delivering computing services. With this transformative technology, users can access virtualized and elastic resources, including computation, platforms, and applications software, which can be provisioned and released instantaneously according to demand. The cloud infrastructure, comprising numerous data centers, requires substantial power consumption to efficiently deliver services to users on demand. The increased power consumption of these resources translates to higher costs for service provision. Current task scheduling methods predominantly focus on objectives like load balancing or makespan, but most of these approaches neglect to optimize power consumption for heterogeneous cloud platforms. The proposed EETSJMSPSO is a new novel metaheuristic approach known as Energy Efficient Task Scheduling using JAYA and Multi-Swarm Particle Swarm Optimization. The primary goal of EETSJMSPSO is to address the persistent challenge of high-power consumption when virtual machines are not subject to migration. The proposed algorithm allocates tasks intending to optimize energy consumption and makespan by implementing load balancing. It also aims to outperform existing schemes dynamically by optimizing other quality of service (QoS) parameters.

关键词： Data centers Cloud computing Energy consumption Power demand Metaheuristics Quality of service Load management

来源：评论

学校读者我要写书评

暂无评论

Medical Images Analysis for Segmentation and Classification Using DNN 10th

Medical Images Analysis for Segmentation and Classification ...

引用

10th International Conference on Innovations in computer science and engineering, ICICSE 2022

作者： Mehbodniya, Abolfazl Narayanasami, Satheesh Webber, Julian L. Kothalanka, Amarendra Sengan, Sudhakar Rangasamy, Rajasekar Stalin David, D. Doha Kuwait Department of Computer Science and Engineering St. Martin’s Engineering College Telangana Secunderabad500100 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh Vaddeswaram522302 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India Department of Computer Science and Engineering GITAM School of Technology GITAM University Karnataka Bengaluru561203 India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Tamil Nadu Chennai600072 India

ISBN: (纸本)9789811974540

The healthcare business is unique in comparison to other fields. It is a high-priority area, and people have high expectations about the quality of treatment and services regardless of the cost. Despite accounting for a significant portion of the total cost, it did not meet the public’s expectations. Most of the time, medical experts are responsible for providing their interpretations of medical data. The interpretation of an image by a human expert is relatively restricted because of its subjectivity, the complexity of the image, the wide variances that occur between various interpreters, and the fact that interpreters might get tired. Many other real-world applications have succeeded with Deep Learning (DL), and now it provides exciting results for Medical Imaging (MI) with a high degree of accuracy. One of the essential methods for the future development of health-related applications is being hailed. We spoke about the most recent developments in DL architecture and how to optimise it so that it may be utilised for the segmentation and classification of MI. In the last part, we spoke about the difficulties associated with using DL-based approaches for MI and the open research question. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Model for Prediction of Heart Failure with Enhanced Self-Supervised Learning Algorithm

An Intelligent Model for Prediction of Heart Failure with En...

引用

2024 International Conference on Intelligent and Innovative Practices in engineering and Management, IIPEM 2024

作者： Tamizh Arasi, G.S. Arjun, K.P. Balamurugan, B. Rakesh, Nitin Gernal, Liza Macasukit Bangalore India GITAM University Department of Computer Science and Engineering Karnataka India Shiv Nadar University Delhi India SIT CSE Nagpur India University of Science and Technology of Fujairah United Arab Emirates

ISBN: (纸本)9798350390049

In recent times the role artificial intelligence across healthcare has become more significant. The effective convergence of this technique helps in earlier diagnosis and treatment of various harmful diseases. Congestive heart failure mainly caused due to unhealthy life style and various other cardiac factors is a serious healthcare concern among humans that impacts several individuals every year. On the other hand, there are many numbers of researches that attempt to prevent the harmful impacts of the heart failure in human. The major concern with these approaches are that it lacks in sufficient labeled data. In this context, the proposed approach presents an enhanced self-supervised learning algorithm for prediction of heart failure in humans. The major contribution of this approach is to compare the significant factors that contribute to heart failure and to predict the possibility of person's risk to heart disease in an accurate manner. The accuracy measures are compared with other conventional models based on supervised and unsupervised learning. The simulation results of the proposed approach is found to be comparatively better than the conventional approaches. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Music Genre Classification Using Long Short-Term Memory with Gated Recurrent Unit 2

Music Genre Classification Using Long Short-Term Memory with...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Sumalatha, K. Nagendar, Y. Sharma, Jaya Padma, C.R. Alsalami, Zaid Department of Ece Telangana Hyderabad India School of Computer Science and Engineering Sr University Telangana Warangal India Gitam University Department of Cse Hyderabad India Dayananda College of Engineering Department of Medical Electronics Engineering Karnataka India The Islamic University Najaf Iraq

ISBN: (纸本)9798350382952

The music genre classification is an important part in data retrieval for the association of increasing music collections. It is one of the challenging tasks for classifying music with reliable accuracy. Numerous methods are utilized as handcrafted features for identifying individual patterns which are unable to define the actual characteristics of music. To overcome these issues, this paper proposed a Deep Learning (DL) based technique for classifying music genre. The Long Short-Term Memory with Gated Recurrent Unit (LSTM+GRU) is used to classifying the music genre. The GTZAN dataset is used in this paper which collects 1000 clips from 10 balanced genres music data. It is preprocessed by clip splitting procedure which is utilized to convert 30s music clip into 3s which helps to enhance the classification performance. Then, the Mel Frequency Cepstral Coefficients (MFCC) is used for extracting relevant features from input signal and LSTM+GRU is used for classifying the music genres. The accuracy, recall, precision and f1-score are used for calculating model performance. The LSTM+GRU attains accuracy 93.65%, recall 92.38%, precision 92.57% and 92.18% f1-score when compared to existing techniques like ResNet50 and Convolutional Neural Network with Bidirectional GRU (CNN+BiGRU). © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Personalized Walking Speed Prediction: Cloud-Enabled Long Short-Term Memory Networks for Health Monitoring 2

Personalized Walking Speed Prediction: Cloud-Enabled Long Sh...

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Reddy, Chilukala Mahender Juliet, P. Sudha Ravinder, Bathini Ashfaqul Hasan, M.D. Ramesh, N. Sujatha, S. Gitam University Department of Computer Science and Engineering Telangana Hyderabad India Meenakshi College of Engineering Department of Electronics and Instrumentation Engineering Tamil Nadu Chennai India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Guntur India Malla Reddy Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India Mother Theresa Institute of Engineering and Technology Department of Electronics and Communication Engineering Andhra Pradesh Palamaner India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350387933

Cloud-Enabled Long Short-Term Memory (LSTM) Networks for individualized walking speed prediction in health monitoring applications are discussed in the research paper. Walking speed is important for mobility and health assessment. Traditional approaches for forecasting walking speed are frequently generic. It uses Cloud-Enabled LSTM Networks to record individual walking patterns and change predictions using real-time data. The proposed approach uses cloud computing to train and update LSTM models. This allows the model to learn and improve over time, keeping it relevant and accurate for each user. Personalization takes into consideration age, fitness, and health to predict walking speed more accurately. Extensive tests on different datasets show that the proposed strategy outperforms current approaches in accuracy and flexibility. The cloud-enabled system integrates with wearable devices, making it suitable for real-world health monitoring. It provides an effective and scalable strategy for predicting walking pace, an important parameter in measuring and maintaining individual well-being, to develop customized health monitoring systems. © 2024 IEEE.

关键词： Long short-term memory

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：