检索结果-内蒙古大学图书馆

Twitter sentiment analysis using conditional generative adversarial network

International Journal of Cognitive computing in engineering 2024年第1期5卷 161-169页

作者： Mahalakshmi, V. Shenbagavalli, P. Raguvaran, S. Rajakumareswaran, V. Sivaraman, E. Department of Information Technology Sengunthar College of Engineering Tiruchengode Tiruchengode637205 India Assistant Professor Karunya Institute of Technology and Sciences Coimbatore India Assistant Professor Department of Computational Intelligence School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Kanchipuram Chennai Tamil Nadu 603203 India Assistant Professor Department of Computer Science and Design Erode Sengunthar Engineering College Tamil Nadu Thuduppathi India Department of Electrical and Computer Engineering Curtin University Miri Malaysia

Sentiment analysis, which aims to extract information from textual data indicating people's ideas or attitudes about a particular problem, has developed into one of the most exciting study issues in natural language processing (NLP) with the development of social media. Twitter is a social network with an extensive audience that expresses their thoughts and opinions clearly and readily. Due to the prevalence of slang phrases and incorrect spellings in short phrase styles, Twitter data analysis is more challenging than data analysis from other social networks. Automated feature selection still has several limitations, such as higher computing costs that rise with the number of characteristics. Deep learning, which is self-learned and more accurate at processing vast amounts of data, is utilized to overcome these challenges. This paper introduces a conditional generative adversarial network (GAN) for Twitter sentiment analysis, whereas a convolutional neural network (CNN) has been used to extract traits from Twitter data. Compared to existing works, the proposed work has outperformed in accuracy, recall, precision, and F1 score. The suggested method is the most accurate, with a classification accuracy of 93.33 %. © 2024

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An optimal group-wise non-rigid image registration technique based clinical decision support for dementia prediction

引用

Multimedia Tools and Applications 2025年 1-26页

作者： Mary, F. Sheeja Asanambigai, V. Fred, A. Lenin Assistant Professor Senior Grade School of Computing Dept. of CSE Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Chennai India Computer Science and Engineering Annamalai University Chidambaram India Dept. of CSE Mar Ephraem College of Engineering and Technology Marthandam India

The fundamental challenge in clinical practice is predicting whether patients with cognitive symptoms or impairment will improve or stay stable. Population ageing is a worldwide phenomena with various impacts. Among dementia, Alzheimer disease (AD) is common in the elderly which is the most common form of dementia and may contribute to 60–70% of cases. An early and precise AD diagnosis enhances patient quality of life. In this study, we propose an optimal group-wise non-rigid image registration technique for dementia (AD) prediction. We introduce an improved cuckoo search optimization (ICSO) algorithm to search optimal group-wise dense correspondence in large image sets in non-rigid image registration which reduce dimensionality of the search space. Then, we illustrate a teacher-student learning based optimization algorithm which cooperates with PLS regression to extract deformation which separates the relationship information suitable for each other from the raw relationship information. After that, we compute the distribution of morphologies of age by fitting smooth percentile curves to these scores using hybrid capsule neural network with least Median Square (hybrid CNN-LMS) curve fitting model. Finally, the simulation results of proposed hybrid CNN-LMS technique are compared to the existing methods to analyze the measures. We observed that the accuracy of our proposed hybrid CNN-LMS technique is 96.23% and 95.82% for RSS and ANDI datasets respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

A Novel Predictive Analysis and Classification of Land Subsidence Vulnerability Mapping based on GIS using Hybrid Optimized Machine Learning Techniques and Computer Vision

引用

Procedia Computer Science 2024年 233卷 343-352页

作者： Senthil G. A R. Prabha Arun M A. Sahaya Anselin Nisha S. Prabu Associate Professor Department of Information Technology Agni College of Technology Chennai India Associate Professor Department of Electronics and Communication Engineering Sri Sairam Institute of Technology Chennai India Assistant Professor Department of Electronics and Communication Engineering Panimalar Engineering College Chennai India Professor Department of Electronics and Communication Engineering Sathyabama Institute of Science and Technology Chennai India Assistant Professor Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India

Land subsidence is a natural disaster caused by the extraction of the earth's material strength on the surface that causes the earth's surface to settle and sink. Land subsidence can also result in significant financial losses since it causes structural damage and expensive maintenance costs for roads, trains, barriers, pipelines, ground water, oil, natural gas, mines, and buildings. The Geographic Information System (GIS) and Google Earth Platform (GEP) can be used to map this land subsidence. This provides a comprehensive view of land pattern subsidence and its interactions with other geographical elements. It applies to both progressive subsidence caused by fluid extraction (groundwater, oil, or natural gas) and rapid surface subsidence caused by the collapse of an underground mine. Risk mitigation is the most effective way to deal with the experimental model. This research study focuses on the use of Predictive Data Analysis (PDA), a powerful environment in data analytics that provides a set of tools that make it easier to evaluate optimal models. The proposed model makes use of a dataset that includes specific land subsidence circumstances as input. The prediction result is achieved using a hybrid machine learning technique that combines Stochastic Gradient Descent (SGD) with Long Short-Term Memory (LSTM) and is compared to K-Nearest Neighbor (KNN), Generative Adversarial Network (GAN), and Artificial Neural Network (ANN). The proposed system employs LSTM and SGD as optimizers, resulting in a hybrid model that improves accuracy. Among the four algorithms investigated the LSTM-SGD network has the highest accuracy (97%), followed by KNN (96%), GAN (90%), and ANN (89%). Due to their ability to capture complicated nonlinear correlations in data and manage temporal dependencies, optimized hybrid ML models LSTM-SGD and KNN models appear to be particularly well-suited for land subsidence prediction.

关键词： Land Subsidence Predictive Data Analysis (PDA) Geographic Information System Machine Learning Computer Cision Susceptibility Mapping Stochastic Gradient Descent (SGD) Generative Adversarial Network (GAN) Long Short-Term Memory (LSTM) K-Nearest Neighbor (KNN) Artificial Neural Network (ANN) Google Earth Platform

来源：评论

学校读者我要写书评

暂无评论

Satellite Image Classification using CNN with Particle Swarm Optimization Classifier

引用

Procedia Computer Science 2024年 233卷 979-987页

作者： Vidhya S Balaji M Kamaraj V Asst. Professor/Dept. of Computing Technologires School of Computing SRM Institute of Science and Technology Kattankulathur Chennai Asso. Professsor/Dept. of Electrical and Electronics Engineering Sri Sivasubramaniya Nadar College of Engineering Professor /Dept. of Electrical and Electronics Engineering Sri Sivasubramaniya Nadar College of Engineering Chennai

Disaster relief, police work, and environmental monitoring all benefit from satellite images. Objects and infrastructure in the images must be manually identified for these applications. Due to the large areas that need to be searched and the limited number of accessible analysts, automation is essential. However, the accuracy and dependability of existing object recognition and classification algorithms renders them inadequate for the task. One family of machine learning algorithms called "deep learning" has showed immense potential for automating these kinds of jobs. Convolutional neural networks have been successful in the area of image recognition. Here, convolutional neural networks (CNNs) and a particle swarm optimization classifier is utilized to develop efficient algorithms for classifying satellite images. The results of this classifier model are better than those of existing approaches.

关键词： Deep Learning Convolutional Neural Network Particle Swarm Optimization Satellite Image Classifier Satellite Images

来源：评论

学校读者我要写书评

暂无评论

Investigation of Security Attacks in IoMT Devices and Federated Learning as a Mitigation Strategy

引用

Procedia Computer Science 2025年 258卷 3426-3435页

作者： Kiruthika M T Poongodi Assistant Professor Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu 603203 India Professor Department of Computer Science and Engineering School of Engineering Dayananda Sagar University Bangalore Karnataka India

Internet of Medical Things (IoMT) is transforming the healthcare business with an increasing number of wearables, gadgets, and sensing devices. As a result, several patients are under daily monitoring for their cardio health, blood glucose level, blood pressure, etc. The data generated by these devices are very voluminous, and there is an increasing need for safeguarding these sensitive data in order to protect them from malicious attacks. This paper suggests to incorporate Federated learning model to IoMT as a mitigative measure. It is apt to induct FL into IoMT as it operates on a collaborative environment which do not allow transfer of the raw data. Patients’ data are stored at the client end itself and only model updates are shared to the server. In this way, the data and network attacks can be reduced to a great extent. This work proposes an integrated architecture where the layers of FL and IoMT can be knotted up for ensuring privacy and security. This proposed architecture model, further elaborates a distributed working environment. This paper illustrates how FL helps in securing the data produced by the different IoMT devices through the proposed architecture. The challenges involved in the deployment of FL in the framework of IoMT along with potential research directions are discussed further in this research.

关键词： : Federated Learning IoMT Security Internet of Medical Things IoMT Data Attacks Optimization

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Deep Learning Models in Alzheimer’s Disease Diagnosis

引用

Procedia Computer Science 2025年 258卷 2352-2361页

作者： Leena Arya Yogesh Kumar Sharma Smitha Nayak Janaki Sivakumar Assistant Professor Computing Department Muscat College Oman Associate Professor Programme leader Computer security and forensics Department of Computer Science and Creative Technologies Global College of Engineering and Technology Muscat Oman

Alzheimer’s Disease (AD) is an ever-evolving neurodegenerative confusion that influences the neurons of the mind in a manner that hinders the patients’ ability to solve problems and remember issues and that requires timely and proper identification to enable appropriate management and treatment. Based on MRI medical images, deep learning models have become one of the most effective approaches for analyzing the signs of the early stages of AD. This research, therefore, carries out a comparative analysis of five deep learning models such as Convolutional Neural Networks (CNNs) like AlexNet, VGGNet, and ResNet, as well as Long Short-Term Memory (LSTM) networks and 3D Convolutional Neural Networks (3D-CNNs) in the finding of Alzheimer’s Sickness from medical imaging data. Each model’s arrangement parameters, for example, layer configurations, learning rate, batch size, optimizer, number of epochs, loss function, applying techniques for regularization, activation functions, and the input dimensions, using pre-trained weights, were carefully initialized to yield a proper comparison between the models. Diagnostic performances were evaluated utilizing precision, responsiveness(recall), specificity, and region under the receiver operating characteristic curve (AUC-ROC). ResNet outperformed other profound learning models in diagnosing Alzheimer’s Disease from MRI scans with a precision of 0.91 and AUC-ROC of 0.95. At the same time, VGGNet, AlexNet, LSTM, and 3D-CNNs demonstrated varying strengths and limitations in balancing accuracy, computational efficiency, and feature extraction.

关键词： Artificial Intelligence (AI) Cognitive Impairment Data Augmentation Diagnosis Accuracy Medical Imaging

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-RNN Models for Multimodal Analysis of Autism Spectrum Disorder Neuroimaging

Hybrid CNN-RNN Models for Multimodal Analysis of Autism Spec...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Rajat Kishor Varshney Alok Katiyar Prashant Johri School of Computing Science & Engineering Research Scholar Galgotias University Greater Noida India School of Computing Science & Engineering Professor Galgotias University Greater Noida India School of Computer Application & Technology Professor Galgotias University Greater Noida India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

ASD is a developmental disorder in the neurological category and has numerous and diverse symptoms. Diagnosis is still problematic because symptoms of parkinsonism are diverse, and the dimensionality of the neuroimaging data is high. This paper presents a combination of CNN and RNN for classifying the ASD by analyzing multimodal neuroimaging data such as fMRI data, MRI data, and DTI data. The CNN component analyzes spatial characteristics of the neuroimaging data, and the RNN learns temporal patterns in fMRI series. Enhancements include a novel preprocessing step called 3D Brain Region Alignment (3D-BRA) as well as the 3D version of Adaptive Temporal, minimizing dimensionality through an innovative feature selection technique employing EN-CC. Predictive analysis with the hybrid model utilizes standard benchmark datasets such as ABIDE I, ABIDE II, HCP, and SFARI and records classification performances over 95 percentage. To enhance the interpretability of the model, the Grad-CAM algorithm is used, which marks specific regions of the brain important in the context of ASD. The proposed framework seems to possess considerable feasibility for enhancing the diagnosis of ASD and improving the understanding of its neural substrates, making the developed method highly advantageous for applications in neuroinformatics and clinical utility.

关键词： Neuroimaging Adaptation models Analytical models Three-dimensional displays Accuracy Functional magnetic resonance imaging Predictive models Brain modeling Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

A Robust Distributed Clustered Fault-Tolerant Scheduling for Wireless Sensor Networks (RDCFT) 1

引用

4th International Conference on Machine Intelligence and Signal Processing, MISP 2022

作者： Sahu, Sandeep Silakari, Sanjay Faculty School of Computing Science & Engineering VIT Bhopal University MP Sehore466114 India Professor University Institute of Technology Rajiv Gandhi Proudyogiki Vishwavidyalaya Madhya Pradesh Bhopal India

ISBN: (数字)9789819900473

ISBN: (纸本)9789819900466

Numerous researchers have suggested numerous solutions based on routing and energy to overcome the prevalence of WSN faults in the current literature. Clustering is the most commonly used energy-efficient and fault-tolerant management technique in WSNs, grouping sensors to manage them and perform distributed activities such as resource management. Although clustering methods are most commonly used to reduce energy consumption, they can also achieve various quality-driven goals, such as network fault tolerance capability. As a result of WSN's unpredictable nature, developing fault tolerance mechanisms is essential. Redundancy and diversity methods are commonly used in networks to increase fault tolerance. As a network management challenge, clustering methods should tolerate malfunctioning sensors while maintaining the network's coverage and stability. Sensors are prone to failure due to their operation in hostile environments with limited battery power. The state of the deployed sensor or cluster head (CH) can be active, redundant, or dead/faulty for the same target region of interest (R). The network's overall lifetime and fault tolerance capability can also be extended by using these backup sensors. By putting redundant sensors into sleep mode, can extend the network lifetime without compromising the quality of service. Sensor networks are generally designed to endure far longer than individual sensors. It is commonly performed by putting sensors to sleep. We propose a robust distributed clustered fault tolerance scheduling (RDCFT) approach that efficiently checks the status of the deployed sensor periodically (based on a sweep-line redundancy check algorithm) in WSNs. Simulation results are based on analytical and experimental studies to validate the effectiveness and usefulness of the proposed work. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Heart Rate Anomaly Detection in Healthcare Using Elliptic Envelope and Local Forest

引用

Procedia Computer Science 2025年 258卷 1677-1687页

作者： Chandralekha E S. Vinodhini Kandasamy V Rama P Assistant Professor Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India-600062 Assistant Professor Department of Information Technology Velammal Engineering College Chennai Tamilnadu India-600062 Assistant Professor Panimalar Engineering College Chennai Tamilnadu India – 600123 Assistant Professor Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai Tamilnadu India-603203

Medical professionals use Anomaly Detection(AD) to identify patients with potential health problems in the heart rate data (HRD), an essential metric related to cardiovascular health. In this research, the most effective AD techniques were identified in detecting unusual variations of the heart rate pattern. Synthetic HRD data with anomalous rates of 15%, 20%, and 25% was generated and standardized it using min-max scaling for consistency among the datasets. Normal HR was based on function with a mean of 70 and a standard deviation of 5 while anomalous values were generated with a mean of 120 and a standard deviation of 10. Among the evaluated models (Elliptic Envelope, one-class SVM, Local Outlier Factor, and Isolation Forest), the Elliptic Envelope (EE) and Isolation Forest (IF) models obtain the best scores in terms of recall and precision – 0.92 and 0.89, respectively. Overall, the results of this research indicate that equally robust AD models should be implemented within clinical systems and wearable devices that serve as a digital space for early cardiac risk identification, prompting adequate intervention and, as a result, health improvement.

关键词： Anomaly Detection Heart Rate Data Isolation Forest Local Outlier Factor One-Class SVM Elliptic Envelope

来源：评论

学校读者我要写书评

暂无评论

Precaution Chatbot for Epilepsy Patients using Natural Language Processing and Deep Learning Sequential Model

引用

Procedia Computer Science 2024年 233卷 537-546页

作者： E Kasthuri S. Subbulakshmi Rajasree Sreedharan Research Scholar Department of Computer Science and Engineering Assistant Professor Department of Computer Science and Applications Amrita School of Computing Amritapuri India Associate Professor Division of Nephrology Department of Pediatrics Medical College of Wisconsin Milwaukee Wisconsin USA

Epilepsy is a brain disorder that can affect people of all ages which is one of the most common neurological disorders affecting around 50 million individuals. Healthcare Chatbots schedule appointments, respond to patient inquiries, and offer relevant information, freeing medical staff to handle life crises. This paper implements a chatbot for epilepsy patients to increase awareness about epilepsy. Patients may easily access this AI-based healthcare chatbot whenever they have queries regarding precautions to be taken by epilepsy patients. Chatbot uses a rich set of epilepsy-related datasets collected from trusted websites which are preprocessed with NLP techniques to prepare the data for model ***, LSTM, and RNN models are created and evaluated to produce answers to user queries related to possible precautions to avoid seizures, safety measures to be taken by patients with seizure history, etc. Evaluation of models shows that the RNN model generates more accurate answers with 94% accuracy. Finally, the epilepsy question answering Chatbot for precaution is concluded with the RNN model.

关键词： Epilepsy Seizure Chatbot Natutal Language Processing LSTM Long short-term memory Recurrent neural network Deep neural network

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：