检索结果-内蒙古大学图书馆

4th IEEE International Conference on data Engineering and Communication Systems, ICDECS 2024

作者： Sharanya, S. Rai, Arnav Vinod Vedanth, Sai Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems India

ISBN: (纸本)9798350393354

In this pivotal study, we delve into the imperative realm of Diabetic Retinopathy (DR), a sight-threatening eye disease, introducing a nuanced and comprehensive approach to its detection through cutting-edge deep learning techniques. Our focus centers on the meticulous comparison of four distinguished convolutional neural network (CNN) architectures: CNN, VGG16, ResNet50, and EfficientNetB5. The dataset comprises five meticulously curated image categories, delineating various DR stages. The discerning outcomes illuminate the consistent superiority of the CNN and VGG16 algorithms, showcasing a commendable edge in accuracy. To amplify DR detection precision, we introduce an innovative hybrid model amalgamating the robust attributes of both CNN and VGG16. This hybrid model triumphs with an extraordinary accuracy rate of 90.5%, surpassing individual performances of the four algorithms. In summation, our groundbreaking study unequivocally establishes the efficacy of a hybrid CNN-VGG16 model for Diabetic Retinopathy detection, underscoring its substantial superiority in accuracy when compared to each of the individual algorithms, advocating for the strategic integration of diverse deep learning models to fortify the accuracy and dependability of medical image analysis. The repercussions of our findings promise to revolutionize the landscape of early detection and holistic management of DR, fulfilling an unmet healthcare need. © 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

Adaptive sail fish optimizer based optimized region selection for robust video steganography

引用

International Journal of Information Technology (Singapore) 2025年第4期17卷 2417-2427页

作者： Babu, J. Suresh Niranjana, G. Ramana, Kadiyala Department of Computing Science & Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur Chengalpattu India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chengalpattu India Department of Artificial Intelligence and Data Science Chaitanya Bharathi Institute of Technology (Autonomous) Hyderabad India

Securing data transmission in a digital era is a difficult one due to the broad application of the Internet, personal computers, and mobile phones for communication. Traditional video steganography techniques sometimes fail to identify the best pixels for encoding hidden data, resulting in lowerquality and robustness. To solve this issue, this article proposes an innovative steganography technique that improves the security and quality of data hiding. The proposed method takes cover video and secret images as input. The Structural Similarity Index Measurement (SSIM) first collects key frames from the input video. The adaptive sailfish optimizer (ASFO) is then used to find the best regions within these keyframes to insert the secret data in. To improve security, the discrete wavelet transform (DWT) is applied to the specified region, and the LL band is used for the hiding process. The secret image is encrypted by Adaptive elliptical curve cryptography (AECC) and transformed to binary bits, which then get embedded in the chosen band. This method leads to the construction of a stego-video. The extraction procedure is repeated using the same approach, which ensures secure and robust data transmission. Performance metrics, including PSNR, BER, NAE, TAF, and NC are analyzed to compare each method's efficacy. © Bharati Vidyapeeth's institute of Computer Applications and Management 2025.

关键词： Adaptive elliptical curve cryptography And stego-video Discrete wavelet transform Structural similarity index measurement Video steganography

来源：评论

学校读者我要写书评

暂无评论

Two kinds of average approximation accuracy

引用

CAAI Transactions on Intelligence Technology 2024年第2期9卷 481-490页

作者： Qingzhao Kong Wanting Wang Dongxiao Zhang Wenbin Zhang Department of Science Jimei UniversityXiamenChina Digital Fujian Big Data Modeling and Intelligent Computing Institute Jimei UniversityXiamenChina Department of Computer Science Michigan Technological UniversityHoughtonMichiganUSA

Rough set theory places great importance on approximation accuracy,which is used to gauge how well a rough set model describes a target ***,traditional approximation accuracy has limitations since it varies with changes in the target concept and cannot evaluate the overall descriptive ability of a rough set *** overcome this,two types of average approximation accuracy that objectively assess a rough set model’s ability to approximate all information granules is *** first is the relative average approximation accuracy,which is based on all sets in the universe and has several basic *** second is the absolute average approximation accuracy,which is based on undefinable sets and has yielded significant *** also explore the relationship between these two types of average approximation ***,the average approximation accuracy has practical applications in addressing missing attribute values in incomplete information tables.

关键词： rough sets rough set theory

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based gene expression biomarkers to distinguish Zika and Dengue virus infections: implications for diagnosis

引用

VirusDisease 2024年第3期35卷 446-461页

作者： Zeba, Ayesha Rajalingam, Aruna Sekar, Kanagaraj Ganjiwale, Anjali Department of Life Science Bangalore University Laboratory for Structural Biology and Bio-Computing Department of Computational and Data Sciences Indian Institute of Science

Zika virus (ZIKV) and Dengue virus (DENV) infections cause severe disease in humans and are significant socio-economic burden worldwide. These flavivirus infections are difficult to diagnose serologically due to antigenic overlap. The phylogenetic analysis shows that ZIKV clusters with DENVs at a higher node of the phylogenetic tree with significant genomic and structural similarity. Our study aims to identify gene biomarkers for the classification of Dengue and Zika viral infections using machine learning algorithms and bioinformatics analysis. The gene expression count matrix for single-cell RNA sequencing dataset GSE110496 was analyzed using binary classifiers, namely Logistic regression, Support Vector Machines, Random Forest, and Decision trees. The GSE110496 dataset represents a unique study of the transcriptional and translational dynamics of DENV and ZIKV infections at 4-, 12-, 24-, and 48-h time points for human hepatoma (Huh7) cells. Out of which 24-h time point has been analyzed in this study, at the optimal threshold of viral molecules. Feature selection was performed using two different approaches Random Forest Classifier (RFC) for gene ranking and Recursive Feature Elimination (RFE). Out of which RFE, showed more accuracy and precision. The classification accuracy of 89.4% and the precision of 90% were obtained using selected 10 gene features. SCY1 Like Pseudokinase 3 (SCYL3), Chromosome 1 Open Reading Frame 112 (C1orf112), Complement factor H (CFH), Heme-binding protein 1 (HEBP1), Cadherin 1 (CDH1), Nibrin (NBN), Histone deacetylase 5 (HDAC5), nuclear receptor subfamily 0, group B, member 2 (NR0B2), Annexin A9 (ANXA9) and Alcohol dehydrogenase 6 (ADH6) are the proposed gene biomarkers in this study. The functional analysis of the reported biomarkers was performed using KEGG and GO with the WEB-based Gene SeT AnaLysis Toolkit (WebGestalt). The relationship of the selected biomarkers with DENV and ZIKV infections analyzed using a gene–gene interaction n

关键词： Biomarkers Dengue Machine learning Single cell RNA sequencing Zika

来源：评论

学校读者我要写书评

暂无评论

Large Graphs with Small Burning Numbers

Large Graphs with Small Burning Numbers

引用

International Conference on Computational Engineering, ICCE 2023

作者： Rajasingh, Angelin Jemima Parthiban, N. Department of Data Science and Business System School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India

In this paper, we have determined the burning number of graphs with universal vertices and graphs that are generated using the graph operation namely ‘join of graphs’. © The Author(s), under exclusive license t... 详细信息

ISBN: (纸本)9783031777639

关键词： Burning number Join of graphs Universal vertex

来源：评论

学校读者我要写书评

暂无评论

Predictive Stress Management for Working Women in Educational Institutions using Federated Learning and Wearable Technology 8

Predictive Stress Management for Working Women in Educationa...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Devi, D. Sudha Sujithra, M. Velvadivu, P. Kavya, V.V. Jhunandhini, S. Data Science Coimbatore Institute of Technology Department of Computing Tamil Nadu Coimbatore India

ISBN: (纸本)9798350376425

The proposed methodology uses Artificial Neural Networks (ANN) to predict stress levels of women working in educational institutions by analyzing physiological and demographic data collected through wearable technology. TensorFlow Federated framework is used here to ensure the data privacy by enabling secure and decentralized training of the proposed model. The approach integrates various steps, including data preprocessing, feature selection, and model training with federated learning. Based on predicted stress levels, the platform provides personalized recommendations to manage stress and improve mental well-being, while keeping user data private. The process involves collecting data from surveys and wearable devices, optimizing the model through techniques like hyperparameter tuning and regularization, and deploying the system via a web interface for real-time stress management. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Polycystic Ovary Syndrome Prediction through CNN based Image Analysis: A Deep Learning Based Approach 8

Polycystic Ovary Syndrome Prediction through CNN based Image...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Karthik, Yazhini Sruthi, R. Sujithra, M. Coimbatore Institute of Technology Department of Computing - Data Science Tamil Nadu Coimbatore India

ISBN: (纸本)9798350376425

Polycystic Ovary Syndrome (PCOS) is a prevalent hormonal disorder affecting women during their reproductive years. It is characterized by irregular menstrual cycles, excessive hair growth, and the presence of cysts in the ovaries. The diagnosis of PCOS typically involves a combination of clinical evaluations and laboratory tests. The paper proposes a novel approach using Convolutional Neural Networks (CNNs) for predicting PCOS through the analysis of ultrasound images. The dataset comprises images obtained from ovarian ultrasound scans of both PCOS-positive and PCOS-negative individuals. These images undergo preprocessing and augmentation techniques such as rescaling, shearing, zooming, flipping, and rotation to enhance the diversity of the training data. Multiple CNN-based models with varying architectures are constructed, altering parameters such as the number of convolutional and pooling layers, activation functions, and other hyperparameters. The models are trained and validated using a split of the dataset into training and validation sets, with metrics like loss and accuracy monitored during training to assess model performance. Upon completion of training, the models are tested using unseen data to evaluate their predictive capabilities. The results demonstrate that deep learning models trained on ultrasound images can accurately predict the presence or absence of PCOS. Such models hold promise in aiding healthcare professionals with early diagnosis and management of PCOS, ultimately improving patient care and outcomes. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Classification of Fetal Health on Cardiotocograph data using Machine Learning Techniques 15

Classification of Fetal Health on Cardiotocograph Data using...

引用

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

作者： Deepa, M.S. Sujithra, M. Department of Computing-Data Science Coimbatore Institute of Technology Tamil Nadu Coimbatore India

ISBN: (纸本)9798331300579

Pregnancy and fetus development is an incredibly intricate biological process that can go wrong when the health of fetus or the mother gets ***, India has the highest number of stillbirths, with an estimated 5,92,100 deaths per year, and a WHO estimated rate of 22 per 1000 total *** is one procedure used to check whether the fetus is growing as *** diagnostic procedure measures the mother's uterine contractions and the fetus' heartbeat, usually in the third trimester of pregnancy when the fetus heart is fully *** paper aims to classify the results into one of three states (physiological, suspicious or abnormal) based on cardiotocographic data using machine learning algorithms and compare the accuracies of different ML classification models such as logistic regression, k-nearest neighbor, decision tree, random forest classifier and support vector machine. © Grenze Scientific Society, 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Xgboost Optimized Ensemble Model for Remaining useful Life Prediction of Aircraft Turbofan Engines 6

A Xgboost Optimized Ensemble Model for Remaining useful Life...

引用

6th IEEE International Conference on Emerging Smart computing and Informatics, ESCI 2024

作者： Sharma, Vaasudev Dagar, Riyansh Sharanya, S. School of Computing SRM Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur India

ISBN: (纸本)9798350306613

Proactive maintenance for the optimized lifecycle of equipment is now effortless via condition monitoring and fault diagnosis. Recognition and avoidance of a state of failure help to achieve solidity and reliability. Artificial Intelligence and Machine Learning (ML) forecast such situations and aid in the prevention of economic and safety emergencies. This work reviews such ML algorithms and ML models that help diagnose faults in Turbofan engines via measurement of the Remaining Useful Life parameter. This proposed an ensemble machine-learning model optimized by Extreme Gradient Boosting. The approach is then evaluated via different metrics and their performance is measured to current innovative methods. The system is useful for all processes that require high reliability quality and efficiency and reduces unplanned downtime, maintenance costs and asset quality. © 2024 IEEE.

关键词： CMAPSS Ensemble Model Machine Learning Predictive Maintenance Remaining useful life (RUL) Turbofan Engine

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Current Trends in Unsupervised Machine learning Algorithms and Challenges in Real World Applications 14

A Comprehensive Study on Current Trends in Unsupervised Mach...

引用

14th International Conference on Advances in computing, Control, and Telecommunication Technologies, ACT 2023

作者： Velvadivu, P. Sujithra, M. Priyadharshini, R. Department of Computing - Data Science Coimbatore Institute of Technology India

In this technology fueled world, everyone is using smart devices, electronic gadgets, wireless products etc. and huge amounts of data are being generated, collected, and stored in the databases. To efficiently process and intelligently analyze the huge amount of data, the knowledge about subfield of Artificial Intelligence that is, Particularly Machine learning (ML) is required. There are various types of machine learning and its algorithms have been introduced to handle real world scenarios. This paper discusses the Comprehensive survey based on methodologies, techniques, algorithms, applications, and challenges faced by unsupervised machine learning and how unsupervised learning techniques can be helpful in real world business and environment. Thus, this study’s key contribution is explaining the principles of different unsupervised machine learning techniques and their applicability in various real-world application domains, such as cybersecurity systems, smart cities, healthcare, e-commerce, agriculture, and many more. © Grenze Scientific Society, 2023.

关键词： Unsupervised learning

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：