检索结果-内蒙古大学图书馆

Advanced Cloud-Based Prediction Models for Cardiovascular Disease: Integrating Machine Learning and Feature Selection Techniques

引用

SN computer science 2024年第5期5卷 1-11页

作者： Dhiyanesh, B. Ammal, S. Ganapathi Saranya, K. Narayana, K.E. SRM Institute of Science and Technology Vadapalani Campus Tamil Nadu Chennai India Karpagam Institute of Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering Bannari Amman Institute of Technology Tamil Nadu Sathyamangalam India Rajalakshmi Engineering College Tamil Nadu Chennai India

Cardiovascular disease is a major cause of global mortality, and early detection and prevention are crucial for lessening the strain on the healthcare system. Over the past few years, cloud computing (CC) and Machine Learning methods have demonstrated significant promise in enhancing heart disease prediction precision and effectiveness. However, many commonly used methods are susceptible to feature omission, leading to reduced accuracy due to increased data variability. Furthermore, a heart disease prediction model can be developed using ANSIS classification and random forest feature selection implemented in a CC environment. This will solve that problem. By enhancing the power of Random Forest (RF) for feature selection and the adaptability of ANSIS for classification, we aim to improve the accuracy and robustness of the prediction model. This research could support more effective and scalable cardiac prediction systems, resulting in better patient outcomes and lower healthcare costs. The initial preprocessing involved Z-score normalization to reduce noise and verify the medical scaling factor, Heart Disease Prone Factor, which is estimated based on the entropy gain model to marginalize the disease rate. Feature selection was then applied to reduce non-relevant features and improve the disease impact finding rate. The dimensionality ratio was decreased, and the most significant characteristics were chosen using the RF approach. Finally, the Adaptive Neuro-Fuzzy Inference System method can be used to classify and generate predictions to achieve accuracy. Multiclass labels define the prediction class by referencing the disease impact rate. Heart disease prediction and patient outcomes could be improved through the use of this comprehensive approach. This research contributes to the field of predictive modelling for heart disease and provides valuable insights for improving performance in higher prediction rates, recall precision rates, F1 with redundant time complexi

关键词： Cardiovascular Classification Neuro-fuzzy Random forest Z-score normalization

来源：评论

学校读者我要写书评

暂无评论

Comparison of Tribological Behavior of Hard Faced Fe-Based Metallic Composite Coatings Sprayed Using HVOF

引用

Journal of Bio- and Tribo-Corrosion 2025年第1期11卷 1-18页

作者： Soni, Piyush Kumar Prasad, C. Durga Manjunath, H.R. Tiwari, Amit Raju, Vadali Pitchi Athithan, Senthil Deshmukh, Khemraj Kumar, Anjani Department of Mechanical Engineering New Horizon College of Engineering Karnataka Bengaluru India Department of Mechanical Engineering RV Institute of Technology and Management Karnataka Bengaluru India Department of Mechanical Engineering Ramaiah Institute of Technology Karnataka Bengaluru560054 India Department of Mechanical Engineering Suresh Gyan Vihar University Jaipur India Mechanical Engineering Department & amp Principal Indur Institute of Engineering and Technology Siddipet India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Biomedical Engineering Parul University Gujarat Vadodara India Mechanical Engineering Department Government Engineering College Arwal India

Fe-based alloys have recently become well-known for their ability to resist wear and corrosion. Iron, the primary component of alloys, is a cheaper option than alloys made from Co and Ni. There is a need for affordable and easily obtainable coatings based on iron. Coatings in the Fe–Ni–Cr system have demonstrated superior wear resistance compared to other commonly used Fe-based metallic coatings. The Fe-12Ni17Cr2.5Mo2.3Si0.03C based (Metco 41C) metallic coatings were applied onto boiler steel substrates using the High Velocity Oxy-Fuel (HVOF) spraying method. The coatings were examined using X-ray diffraction (XRD), a scanning electron microscope (SEM), and a microhardness tester to determine their density, porosity, microstructure, hardness, and surface roughness. The sliding wear behavior of the substrate and coatings was studied using the pin-on-disk tribometer. Figuring out the wear loss and coefficient of friction. Comparison was made of wear results between the substrate, coatings, and composite coatings. By combining these carbide powders with 30% SiC and WC-12Co particles, the coating’s wear resistance is enhanced in comparison to the Metco 41C coating. In comparison to boiler steel, the Metco 41C + SiC and Metco 41C + WC–Co coatings exhibited a roughly 70% and 40% reduction in volume loss compared with boiler steel respectively. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： HVOF thermal spraying

来源：评论

学校读者我要写书评

暂无评论

S5ELBP: Supervised SAR Image Classification using SVM from SSELBP Texture Features

S5ELBP: Supervised SAR Image Classification using SVM from S...

引用

2023 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Bandi, Sudheer Reddy Anbarasan, M. Merlin Linda, G. Panimalar Engineering College Department of Artificial Intelligence and Data Science Chennai India Swarna Bharathi Institute of Science and Technology Department of Computer Science and Engineering Khammam India

ISBN: (纸本)9798350348910

Synthetic Aperture Radar (SAR) and Optical sensors are very popular depending on their strengths and application needs. The ocean surface will be covered with clouds most of the time and optical sensors cannot capture the information as they cannot operate in dust and cloudy conditions. So, SAR sensors come into existence to capture the atmospheric phenomena in those regions. There is a wide range of texture extraction techniques such as traditional-based wavelet analysis, statistical analysis, local pixel-based approaches, and dimensional reduction approaches. However, these approaches have limitations in boundary extraction, high-dimensional feature extraction, and uniformity representation. In recent times, deep learning (DL) approaches to extract features which varies based on the applications, image interpretation, and so on. At the same time, DL approaches are limited in transparency, computation requirements, and hyperparameter tuning. In contrast, the proposed S5ELBP i.e., Supervised SAR image classification using the integration of Support Vector Machine (SVM) and Scale Selective Extended Local Binary Pattern (SSELBP) extraction techniques shall overcome various challenges of existing traditional and DL approaches such as adaptive thresholding, less computational resources, and noise robustness. Hence, the objective of the proposed methodology is to extract the image features from the Scale Selective Extended Local Binary Pattern (SSELBP). Also, the SSELBP features are integrated with SVM to show the strength of the proposed approach in SAR image classification. Additionally, the performance of the present work is enhanced by comparing the extracted results with various classifiers. Finally, the work is concluded by recommending the scope of future work. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

VICTOR: Video Content-aware Partially Reliable Transmission over Multipath QUIC

VICTOR: Video Content-aware Partially Reliable Transmission ...

引用

2023 IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2023

作者： Li, Yahui Han, Biao Han, Xueqiang Ji, Xiaolan Song, Congxi Chen, Guo National University of Defense Technology School of Computer Changsha China Hunan University College of Computer Science and Electronic Engineering Changsha China

ISBN: (纸本)9798350333336

Over the past few years, video streaming has been dominating the internet traffic. The Quick UDP Internet Connections (QUIC) protocol and its support for both reliable and un-reliable transmission may exhibit attractive advantages for video streaming. Multipath transport techniques like Multi-Path QUIC (MPQUIC) are introduced to aggregate the bandwidth of multiple links and to provide reliable transmission in poor network conditions. However, how to leverage unreliable transmission for video streaming over MPQUIC has not been explored yet. Motivated by extensive experimental observations, we propose VICTOR, video content-aware partially reliable transmission over multipath QUIC. Specifically, VICTOR exploits both reliable and unreliable transmission to improve the quality of experience (QoE) perceived by users. Besides, the scheduling mechanism of MPQUIC is examined and VICTOR split video frames over multiple paths with the perception of QoE. We evaluate VICTOR experimentally in both simulations and a lab testbed. The results reveal that VICTOR can achieve better performance compared with the latest MPTCP and MPQUIC protocols. © 2023 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Classification using Ensemble Models with MFCC

Speech Emotion Classification using Ensemble Models with MFC...

引用

2022 International Conference on Machine Learning and Data engineering, ICMLDE 2022

作者： Mohan, Meera Dhanalakshmi, P. Kumar, R. Satheesh Department of Computer Science and Engineering Annamalai University India Department of Computer Science and Engineering Sahrdaya College of Engineering and Technology India

Speech is one of the most promising features that reflects the underlying emotion of a human being. There are some measurable parameters in speech signals that reveal a persons affective state. Speech Emotion Recognition (SER) is a process of identifying the emotional elements in communication regardless of contextual relevance. Leveraging studies have taken place in this area. This paper proposes an ensemble model to automatically classify emotion from speech signals to one among the seven emotional classes neutral, calm, angry, sad, happy, fear, disgust, and surprised. In this work, speech spectral features have been extracted using Mel Frequency Cepstral Coefficient (MFCC). An emotion classification model based on 2-Dimensional Convolutional Neural Networks (2D-CNN) and eXtreme Gradient Boosting (XG-Boost) is proposed in this paper. This work also compares the performance of the proposed ensemble model with baseline models and other ensemble models. The accuracy of each model on the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset is computed and the proposed model shows maximum accuracy in classifying emotions. © 2022 Elsevier B.V.. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

DDoS Detection and Prediction Techniques-A Survey

DDoS Detection and Prediction Techniques-A Survey

引用

2023 International Conference on Computational Intelligence and Sustainable engineering Solution, CISES 2023

作者： Goyal, Ashtha Matta, Priya Gautam, Pratiksha Graphic Era Deemed to Be University Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Hindustan College of Science and Technology Department of Computer Science and Engineering Mathura India

ISBN: (纸本)9798350323917

The Distributed Denial of service (D-DoS) attack continues to attract excess of assiduity in the cyber security world, owing to the tremendous damage it may bring to an organization's assets. Consequently, as internet consumer traffic and device access speeds rise substantially, it confronts a serious issue In Spite of having often bottlenecks, however, some approaches have devised mitigating strategies. Earlier, SDN was shown in order to protect enterprises against D-DoS cyber-attacks. D-DoS cyberattacks create server disruptions and monetary loss as a result of shutdowns as a result achieving Service level agreement (SLA) with customers continues to be a difficulty. This paper contains a complete literature study and a comprehensive study of the DDoS effect. Furthermore, it investigates the shortcomings of conventional DDoS detection and prediction systems in order to assist scientific and corporate researchers in building prominent DDoS detection and prediction methods. This review identified and referenced all journals with information related to the domain from multiple digital libraries, along with appropriate search strategies. However, it only involved a small number of journal papers and conference proceedings. These papers were cited in many studies and referred by the industry for real-time projects. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Retinal Disease Diagnosis Reimagined: A Deep Transfer Learning and Multi-Scale Attention Network Algorithm for Precision Ophthalmology

Retinal Disease Diagnosis Reimagined: A Deep Transfer Learni...

引用

2023 International Conference on Energy, Materials and Communication engineering, ICEMCE 2023

作者： Ramanathan, S. Arun Kumar, M. Susmanth Srinivas, A. Shanmukha Naveen, K. Senthil Kumar, C. Thiagarajar College of Engineering Department of Computer Science and Engineering Tamil Nadu Madurai India Ssn College of Engineering Department of Information Technology Tamil Nadu Chennai India

ISBN: (纸本)9798350393378

Retinal diseases are critical in nature as they progress quite quickly and lead to catastrophic damages in retina and therefore leading to loss of vision. The availability of proper healthcare systems to all sections of the society remains uncertain. A retinal disease detection model is created to solve these issues. The Fundus dataset used here consists of 1548 exhaustive collection of images in 3 different classes. InceptionV3 was among the other pre-trained model that the VGG16 substantially surpassed with a recognition accuracy of 93.4%. The Custom Multi-Scale Attention Network model yielded a competent 91% accuracy score. © 2023 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Models for Understanding Audience Sentiments in Movie Tweets 5

Deep Learning Models for Understanding Audience Sentiments i...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Prasath, S. Ram Jeevitha, J.K. Margret, S. Krishnan, R. Santhana Raj, J. Relin Francis Nithila, Ezhil E Scad College of Engineering and Technology Department of Computer Science and Engineering Cheranmahadevi India Psna College of Engineering and Technology Department of Information Technology Dindigul India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai Avadi India

ISBN: (纸本)9798350379945

This study explores the application of deep learning models for analyzing audience sentiments in movie tweets, aiming to provide a comprehensive understanding of audience reception. Leveraging Twitter data collected using Tweepy and supplemented with web-scraped content via BeautifulSoup, the study employs advanced Natural Language Processing (NLP) techniques. Text preprocessing using SpaCy ensures standardized input for subsequent analysis. Sentiment analysis utilizes RoBERTa, an advanced deep learning transformer model known for its robust performance in NLP tasks. RoBERTa effectively classifies tweets into positive, negative, or neutral sentiments, leveraging its contextual understanding to interpret nuanced language expressions prevalent in social media discourse. Simultaneously, RoBERTa is employed for emotion detection, identifying emotional states such as joy, anger, sadness, and more, crucial for gauging audience emotional responses to various aspects of movies. This dual-analysis framework provides detailed insights into audience reactions, facilitating a nuanced evaluation of movie reception across diverse demographic segments. Additionally, the study explores aspect-based sentiment analysis to delve deeper into specific movie attributes like plot, acting, and special effects. Visualizations using Plotly enhance the interpretability of sentiment and emotion distributions over time, supporting informed decision-making in the entertainment industry. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Impact of Preprocessing Thermographs on Effective Classification of Potatoes 4

Impact of Preprocessing Thermographs on Effective Classifica...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Nandhitha, N.M. Emalda Roslin, S. Shivasreetha, S. Muthiah, M.A. Rajasekar, B. Sathyabama Institute of Science and Technology Department of ECE Chennai600119 India St.Joseph's College of Engineering Computer Science and Engineering Chennai600119 India Sathyabama Institute of Science and Technology Dept. of ECE Chennai600119 India

ISBN: (纸本)9798331515720

InfraRed Thermography can be used for assessing the quality of potatoes. Thermographs acquired using IR camera is processed for identifying the presence/absence of diseases in potatoes. Raw pseudocolor images as acquired from thermographs for four different classes (holes, fungus, badly affected potatoes and normal potatoes) are fed as input to ALEXNET and the performance was studied. Performance metrics cannot be improved as the background intensity and the Region of Interest (RoI) intensity are nearly equal (low contrast images). In this paper, prior to feeding thermographs as inputs to ALEXNET, thermographs were enhanced and the performance was studied. Secondly, only potato region was identified and the background intensities are made as lowest (zero) to improve the contrast. These images are then fed to ALEXNET and the performance is studied. Also, in order to reduce the computational complexity of ALEXNET, the convolution layer and ReLu layer above the fully connected network are removed and a modified ALEXNET architecture is obtained. After training, modified ALEXNET is then used for the above three sets of thermographs and the performance is studied. It is found that modified ALEXNET not only reduces the computational complexity but also has an accuracy of 75% for RoI separated thermographs much greater than that of ALEXNET and that of enhanced thermographs. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Modelling of 7-Segment Hex Decoder using Silicon Microring Resonator

Modelling of 7-Segment Hex Decoder using Silicon Microring R...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Raju, Kommisetti Murthy Nirmala Bai, K.S. Mondal, Bikas Roy, Bhaskar Banerjee, Sudipta Kundu, Sumanta Electronics and Communication Engineering Shri Vishnu Engineering College for Women Bhimavaram India Electronics and Communication Engineering Jntua College of Engineering Kalikiri Kalikiri India Electronics and Computer Science Narula Institute of Technology Kolkata India Asansol Engineering College Asansol India Pune India Electrical Engineering Narula Institute of Technology Kolkata India

ISBN: (纸本)9798331540821

A creative design for a 7-segment hex decoder that makes use of an optical microring Resonator (OMRR). Digital devices called decoders are used to transform binary input into the required output format. The hexadecimal is widely used in programming languages, memory addressing, error codes, etc. The main advantage of 'Hexadecimal' numerals is that they require less memory to store more numbers. After processing the binary code, the decoder accepts it and converts it back into a format that output devices can understand. The entire design has been simulated step-by-step in MATLAB. An all-optical decoder with a quick response time can significantly enhance various aspects of digital data communication and processing. The microring resonator is modulated utilizing an optical pump signal, which is the powerful optical laser beam. This microring resonator-based optical decoder can be applied to optical communication and networking, as well as optical secure coding circuits, as a basic building block. © 2024 IEEE.

关键词： Laser beams

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：