检索结果-内蒙古大学图书馆

Mobile Networks and Wireless communications (ICMNWC), IEEE International Conference on

作者： Laith H. Alzubaidi Priyadharshini. C Vasanthakumar G U Srinivas Samala S. Ananthi Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Electronics and Communication Engineering Bharathiyar Institute of Engineering for Women Salem India Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru India Department of Electronics and Communication Engineering SR University Warangal India Department of Electrical and Electronics Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai India

ISBN: (数字)9798331528348

ISBN: (纸本)9798331528355

In recent days, the information about electrical activity is obtained in the form of Electro-Cardo-Diograms (ECG) which is become a typical way of monitoring heart rhythm and function of patients. In existing, the Convolutional Neural Networks (CNN) is utilized for the effective detection of Cardiac Disease (CD). However, the CNN model may not extract the spatial features from the signals effectively. To overcome this issue, Graph Convolutional Network (GCN) is proposed to extract the spatial features from signal effectively. Initially, the data is taken from Massachusetts Institute of Technology and Beth Israel Hospital (MIT-BIH) dataset. Then, min-max normalization is utilized to preprocess the data and the high frequency noise is removed with Butterworth Frequency Filter (BFF). After that, the preprocessed data is further processed into classification with proposed GCN model. In the classification, the convolutional layers are utilized to extract the spatial features by using graph-based structure. Finally, the fully connected layer with softmax activation function is utilized to classify the CD into normal or abnormal labels. From the results, the proposed GCN model established better results than existing CNN including precision (99.75%), recall (98.60%), F1-score (98.20%) and Area Under Curve (99.70%) respectively.

关键词： Wireless communication Convolution Heart beat Graph convolutional networks Noise Cardiac disease Electrocardiography Feature extraction High frequency Resilience

来源：评论

学校读者我要写书评

暂无评论

ECG Based Early Heart Attack Prediction Using Neural Networks 3

ECG Based Early Heart Attack Prediction Using Neural Network...

引用

3rd International Conference on electronics and Sustainable communication Systems, ICESC 2022

作者： Kumar, Ashish Rathor, Ketan Vaddi, Snehit Patel, Devanshi Vanjarapu, Preethi Maddi, Manichandra Delhi Technological University Department of Information Technology Delhi India Solution Architect Birla Carbon Mumbai India Gitam University Dept of Computer Science and Engineering Vishakhapatnam India K. J. Somaiya College of Engineering Department of Information Technology Mumbai India Cmr Engineering College Department of Computer Science Engineering Telengana India Vaagdevi College of Engineering Department of Electronics and Communication Engineering Telengana India

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479714

In today's world, a large amount of data is being collected every minute. This data came from different sources: health care, social media, business applications, manufacturing industries, and many more. The healthcare industry gives a large amount of data. Especially heart disease, which stops the flow of blood from vessels, resulting in chest pain and heart attack. Heart diagnosis at starting stage of the disease can lead to a successful cure of the disease. The classifications that are used to prevent the diagnosis are: - Naive Byes classification, the Support Vector Machine classification, and the k-NN classification. Hence, some deep learning techniques need to be tested on the dataset which has been taken and needs to be tested on it. The primary goal of this paper is to identify novel deep learning accuracy and a better neural network between convolutional neural networks and artificial neural networks.. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

IoT based ECG Signal Feature Extraction and Analysis for Heart Disease Risk Assessment

IoT based ECG Signal Feature Extraction and Analysis for Hea...

引用

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： S. Satheeskumaran K. Sasikala Kumar Neeraj A. SenthilKumar N. Sharath Babu Department of Electronics and Communication Engineering Anurag Univerity Hyderabad India Department of Electrical and Electronics Engineering Vels Univerity Chennai India Department of Computer Science and Engineering Sri Vishnu Engineering College for Women India

Digital healthcare solutions are being created to meet the demands of the healthcare industry. Advances in IoT and cloud computing have led to the development of numerous smart healthcare solutions for elderly people and people with chronic diseases. Healthcare centres and physicians get the opportunity to assess the health of patients from anywhere through the developed smart systems. In this work, an IoT and cloud-based healthcare system is developed for ECG signal parameter extraction and machine learning-based analysis that will be helpful in heart disease risk assessment. The minimal local signal processing required by IoT-based healthcare equipment is made possible by cloud computing. However, there are certain concerns related to service quality issues while employing a cloud framework for real-time monitoring and signal processing. This work proposes ECG beat rate detection and machine learning-based analysis in an IoT-based framework. Finding the precise location of the QRS complex during ECG data processing facilitates the detection of heart rate variability (HRV) parameters, which will play a crucial role in the risk assessment of heart diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition in Visual Art on Color and Texture Analysis using Improved Vision Transformer

Emotion Recognition in Visual Art on Color and Texture Analy...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： K G Suma Zaed Balasm N. Sasirekha Veera Manikandan P K. Sandhya Department of AI & ML School of Computer Science and Engineering Vellore Institute of Technology Andhra Pradesh India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Electronics and Communication Engineering Sona College of Technology Salem India Department of Electrical and Electronics Engineering Dhanalakshmi Srinivasan College of Engineering and Technology India Department of Computer Science and Engineering (AI&ML) Mohan Babu University Tirupati India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Nowadays, Emotion Recognition plays a key role in social communication interaction in which human emotions are interpreted from facial expressions and speech. Several challenges occur in emotion recognition such as capturing context of any emotion also facial attributes make the recognition process complex. To overcome these drawbacks Improved Vision Transformer (IViT) classifier is proposed for emotion recognition. Initially, the input data is collected from the Japanese Female Facial Expression (JAFFE) to collect color features and visual features. Then, the input data is processed using min max scaling method which normalizes pixel values. After that, colour and texture-based features are extracted by utilizing Rotation Invariant Local Binary Patterns (RI-LBP) with Hue Saturation and Value (HSV) and Red Green Blue (RGB). Finally, classification is performed by IViT, which processes images as sequences of patches. Hence, the proposed IViT model achieved better output when compared to existing Visual–Audio Attention Network (VAANet) in terms of accuracy by obtaining 96.6% respectively.

关键词： Emotion recognition Visualization computer vision Art Accuracy Image color analysis Face recognition Speech recognition Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

Beam Selection Approach in Millimeter Wave communication using Multi-Objective Prairie Dog Optimization

Beam Selection Approach in Millimeter Wave Communication usi...

引用

2023 International Conference on Integrated Intelligence and communication Systems, ICIICS 2023

作者： Reddy, R. Archana Alzubaidi, Laith H. Hussein, Abbas Hameed Abdul Pradeep Kumar, S. Rajaram, J. SR University School of Computer Science and Artificial Intelligence Warangal India The Islamic University Najaf Iraq Ahl Al Bayt University College of Pharmacy Karbala Iraq Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India Malla Reddy Engineering College for Women Hyderabad India

ISBN: (纸本)9798350315455

The selection of beam relies as a major conflict in wireless communication systems. The beam selection has been widely utilized in millimeter wave bands which helps to mitigate the path loss and minimize the energy consumption. The existing beam selection approaches results in high computational and communication costs and hinders the widespread deployment of mm Wave communications. Moreover, the existing approaches faced issues related to select the users for multiple radio frequencies and this suffers the users to face computational burden and results in beam optimization problem. So, this research utilized a Multi-Objective Prairie Dog Optimization (MOPDO) algorithm to perform an effective beam selection for multiple users in a single iteration. MOPDO considers the multiobjective functionalities such as beam power, energy efficiency, spectral efficiency and computational time. The experimental evaluation of proposed approach is evaluated with Alternative Grey Wolf with Beetle Swarm Optimization (AGW-BSO). For example, computational time of the proposed MOPDO is 320.87 seconds whereas the existing AGW-BSO is 355.72 seconds. © 2023 IEEE.

关键词： Beam selection Computational time Energy efficiency Millimeter wave communication Multi-Objective Prairie Dog Optimization

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Prediction and Classification Using Decision Tree and VGG16 Convolutional Neural Networks

引用

Open Biomedical engineering Journal 2024年 18卷

作者： Krishna, S. Udit Lakshman, A. N. Barath Archana, T. Raja, K. Ayyadurai, M. Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Ramapuram Chennai India

Introduction: A malignant abnormal growth that starts in the tissues of the lungs is called Lung Cancer. It ranks among the most common and lethal cancers globally. Lung Cancer is particularly dangerous because of its aggressive nature and how quickly it can extend to other areas of the body. We propose a two-step verification architecture to check the presence of Lung Cancer. The model proposed by this paper first assesses the patient based on a few questions about the patient's symptoms and medical background. Then, the algorithm determines whether the patient has a low, medium, or high risk of developing lung cancer by diagnosing the response using the “Decision Tree” classification at an accuracy of 99.67%. If the patient has a medium or high risk, we further validate the finding by examining the patient's CT scan image using the “VGG16” CNN model at an accuracy of 92.53%. Background: One of the key areas of research on Lung Cancer prediction is to identify patients based on symptoms and medical history. Its subjective nature makes it challenging to apply in real-world scenarios. Another research area in this field involves forecasting the presence of cancer cells using CT scan imagery, providing high accuracy. However, it requires physician intervention and is not appropriate for early-stage prediction. Objective: This research aims to forecast the severity of Lung Cancer by analyzing the patient with a few questions regarding the symptoms and past medical conditions. If the patient has a medium or a high risk, we further examine their CT scan, validate the result and also predict the type of Lung Cancer. Methodology: This paper uses the “Decision Tree” algorithm and the Customised “VGG16” model of CNN for the implementation. The “Decision Tree” algorithm is used to analyze the answers given by the patient to distinguish the severity of Lung Cancer. We further use Convolution Neural Networks with a Customised “VGG16” model to examine the patient's CT scan image

关键词： Convolutional neural networks Decision tree classification Deep learning Image processing Lung cancer Machine learning VGG16

来源：评论

学校读者我要写书评

暂无评论

Sensors for Bone Mineral Density Measurement to Identify the Level of Osteoporosis: A Study 4

Sensors for Bone Mineral Density Measurement to Identify the...

引用

4th International Conference on Smart Systems and Inventive Technology, ICSSIT 2022

作者： Ramaraj, Kottaimalai Amiya, Gautam Murugan, Pallikonda Rajasekaran Govindaraj, Vishnuvarthanan Vasudevan, Muneeswaran Thiyagarajan, Arunprasath Department of Electronics and Communication Engineering Kalasalingam Academy of Research and Education Tamilnadu Krishnankoil India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamilnadu Krishnankoil India Department of Biomedical Engineering Kalasalingam Academy of Research and Education Tamilnadu Krishnankoil India

ISBN: (纸本)9781665401180

Osteoporosis (OP) is a skeletal system-wide metabolic disorder marked by degradation of bone microarchitecture (BMA), reduced bone mineral density (BMD), and change in protein level. As a result, a diagnostic approach can completely examine bone strength and is convenient to adopt that should be established for OP screening and early identification. The majority of currently offered clinical diagnostic methods rely on the utilization of X-rays or ultrasonography. Dual-energy X-ray absorptiometry (DXA/DEXA) that provides BMD information, is now considered the "gold standard" for OP diagnosis. The metrics obtained by this approach, on the other hand, can only describe variations in BMD and unable to assess BMA, or further significant characteristics that influence fracture risk. The broadband ultrasonic attenuation (BUA) and speed of sound (SOS) are the main features of the quantitative ultrasound (QUS) bone evaluation approach. Early detection of indications and diagnosis of bone illnesses are becoming critical in order to avert significant consequences. The development of diverse monitoring systems for bone strength and estimating methodologies used by investigators and healthcare corporations have been addressed as a result of this motivation. This research highlights the numerous sensors widely available and their features for measuring BMD. © 2022 IEEE

关键词： Ultrasonic applications

来源：评论

学校读者我要写书评

暂无评论

A Novel Orientation Approach in Artificial Intelligence for Mounting Robots Utilizing a Three-Dimensional Framework of the Broadcast Tower

A Novel Orientation Approach in Artificial Intelligence for ...

引用

Artificial Intelligence and Knowledge Discovery in Concurrent engineering (ICECONF), International Conference on

作者： S. Niranjana I. Chandra G. Charulatha S. Leopauline Ch Prathima T. Geetha Department of Electronics and Communication Engineering Jeppiaar Institute of Technology Chennai Department of Computer and Communication Engineering Rajalakshmi Institute of Technology Chennai Department of Electronics and Communication Engineering PERI Institute of Technology Chennai Department of Electronics and Communication Engineering Veltech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai School of Co mputing(IT) Mohan Babu University Tirupati Department of Computer Science Engineering Vinayaka Missions KirupanandaVariyar Engineering College Salem

Machines with adaptable behavior and certain humanlike physical traits have been designed for industry, but they do not resemble humans in any way. The study of specialized robots for certain difficult working conditions has steadily become a hot issue as robot technology has advanced and their use has spread. When deployed to transmission towers, the climbing robot serves as a replacement for people doing bolt tightening, detection, and other operations at dangerous heights, thereby enhancing the effectiveness of transmission tower maintenance while also protecting workers' lives. Yet, the transmission tower climbing robot's limited commercial uses may be largely attributed to its inability to independently find itself inside the transmission tower's complicated model. In order to ensure the operating precision of climbing robots, this study provides an Artificial intelligent placement strategy that combines the transmission tower with optical sensor information. Experiments have shown that the approach can pinpoint a location to within 2 cm.

关键词： Solid modeling Three-dimensional displays Service robots Poles and towers Maintenance engineering Robot sensing systems Climbing robots

来源：评论

学校读者我要写书评

暂无评论

Enhancing VANET Efficiency with ACRR Technique for Improved Traffic Management and Network Scalability

Enhancing VANET Efficiency with ACRR Technique for Improved ...

引用

science, Technology, engineering and Management (ICSTEM), International Conference on

作者： K Karthick Praveen Talari Nishadevi V R Krishna Prakash R. Asokan Velusamy A Dept. of Computer Science and Engineering Kongunadu College of Engineering and Technology Trichy Tamilnadu Dept. of Computer Science and Engineering Vignan Bharathi institute of technology Hyderabad Telangana Dept. of Computer Science and Engineering Mahendra College of Engineering Salem Tamilnadu Dept. of Information Technology Sona College of Technology Salem India Dept. of Electronics and Communication Engineering Kongunadu College of Engineering and Technology Trichy Tamilnadu

ISBN: (数字)9798350376913

ISBN: (纸本)9798350388473

The role of Vehicular Ad Hoc Networks (VANETs) is crucial in enabling Intelligent Transportation System (ITS) technologies such as safe financial transactions, media applications, and effective traffic control. As traffic increases, the topology of vehicular networks is in constant flux, and the sparse distribution of vehicles, particularly on highways, presents challenges for network scalability. This situation makes it difficult for cars to keep consistent routes inside the network, which affects the stability of the network. To address these challenges, the developed Adaptive-ant Colony based Randomized Recommendation (ACRR) technique emerges as a unique solution for enhancing VANETs by reducing travel time. In instances of high traffic density on busy roads, the ACRR algorithm is effectively utilized to group vehicles. Leveraging data collected from these densely populated road segments, the system identifies congestion-prone areas and formulates optimal vehicle routes based on customized vehicle groupings. The framework's performance evaluation encompasses various parameters, including packet loss, message transmission rate, energy consumption, and average cluster growth. The proposed VANET framework, empowered by the ACRR algorithm, achieves an impressive message transmission rate of approximately 80%. In comparison, alternative methods like Re-RouTE exhibit a limited transmission rate of 70%, while others such as Net Run Rate (NRR), DIVERT 30, and DIVERT-60 demonstrate rates below 20%. Furthermore, the framework's parcel loss is significantly reduced to only 33% of that observed in the standard VANET framework. As a result, the ACRR algorithm integrated into the VANET framework demonstrates notable efficiency when compared to other approaches. It is crucial to recognize that, even with a refined technique, managing traffic congestion remains challenging if drivers disregard the recommended routing suggestions. Overall, this research offers insights into the p

关键词： Performance evaluation Roads Scalability Vehicular ad hoc networks Clustering algorithms Packet loss Routing

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Method for Predicting Skin Disease Using OM-Extreme Learning Machine 4

An Intelligent Method for Predicting Skin Disease Using OM-E...

引用

4th International Conference on Smart electronics and communication, ICOSEC 2023

作者： Suja, G.P. Akshaya, M. Salim, Abu Sarfaraz, Mohd Kathiravan, Mathur Nadarajan Singh Pundir, Aditya Kumar Muslim Arts College Research Centre of Computer Science Tamilnadu Kanyakumari India Department of Cse Tamilnadu Coimbatore India College of Computer Science and Information Technology Jazan University Department of Computer Science Jazan Saudi Arabia College of Computer Science and Information Technology Jazan University Department of Information Technology and Security Jazan Saudi Arabia Dr N. G. P Arts and Science College Department of Biotechnology Tamil Nadu Coimbatore India Arya College of Engineering and Information Technology Department of Electronics and Communication Engineering Rajasthan Jaipur India

ISBN: (纸本)9798350300888

In terms of prevalence, skin disorders rank towards the top. Various organisms, including fungi, bacteria, allergens, viruses, and so on, can trigger skin illnesses. Improved speed and accuracy in the diagnosis of skin diseases has resulted from the development of lasers and Photonics-based medical technology. However, there is now a severe lack of affordable options for such diagnostics. Therefore, at the outset, image processing techniques aid in constructing an automated screening system for dermatology. To aid in the categorization of skin disorders, feature extraction is essential. Several methods exist where computer vision can aid in the diagnosis of skin disorders. Skin infections are frequent in Saudi Arabia because of the country's scorching, desert climate. This proposed method adds to the literature on the early diagnosis of skin diseases. To help diagnose skin conditions, to recommended using image processing. This technique uses digital images of the affected skin to determine the disease kind through the application of image analysis. The method to offer straightforward, quick, and can be done with just a camera and a ***, feature extraction for segmentation, and model performance evaluation make up the suggested method. Preprocessing makes use of a histogram and an RGB to Grayscale conversion. Segmentation is performed with the help of adaptive thresholding. The GLCM, IQA, and complete reference methods are all utilized for feature extraction. Finally, OM-ELM is utilized to assess the model's performance. Comparing the suggested method to ELM and AE-ELM, it fares quite well. © 2023 IEEE.

关键词： Mean square error

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：