检索结果-内蒙古大学图书馆

A Novel Mixed Precision Distributed TPU GAN for Accelerated Learning Curve

computer Systems science & engineering 2023年第7期46卷 563-578页

作者： Aswathy Ravikumar Harini Sriraman School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India

Deep neural networks are gaining importance and popularity in applications and *** to the enormous number of learnable parameters and datasets,the training of neural networks is computationally *** and distributed computation-based strategies are used to accelerate this training *** Adversarial Networks(GAN)are a recent technological achievement in deep *** generative models are computationally expensive because a GAN consists of two neural networks and trains on enormous ***,a GAN is trained on a single *** deep learning accelerator designs are challenged by the unique properties of GAN,like the enormous computation stages with non-traditional convolution *** work addresses the issue of distributing GANs so that they can train on datasets distributed over many TPUs(Tensor Processing Unit).Distributed learning training accelerates the learning process and decreases computation *** this paper,the Generative Adversarial Network is accelerated using the distributed multi-core TPU in distributed data-parallel synchronous *** adequate acceleration of the GAN network,the data parallel SGD(Stochastic Gradient Descent)model is implemented in multi-core TPU using distributed TensorFlow with mixed precision,bfloat16,and XLA(Accelerated Linear Algebra).The study was conducted on the MNIST dataset for varying batch sizes from 64 to 512 for 30 epochs in distributed SGD in TPU v3 with 128×128 systolic *** extensive batch technique is implemented in bfloat16 to decrease the storage cost and speed up floating-point *** accelerated learning curve for the generator and discriminator network is *** training time was reduced by 79%by varying the batch size from 64 to 512 in multi-core TPU.

关键词： Data parallel distributed model generative model learning curve mixed precision

来源：评论

学校读者我要写书评

暂无评论

From Clusters to Scores: Unsupervised Acne Detection and Severity Assessment with Deep Learning 4

From Clusters to Scores: Unsupervised Acne Detection and Sev...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Khandelwal, Animan Santhi, H. Wagh, Devdatta School of Computer Science and Engineering Vellore Institute Of Technology Vellore India

ISBN: (纸本)9798331540364

Acne detection and severity scoring remain challenging due to the scarcity of labeled data and inconsistencies caused by varying skin tones and lighting conditions. While recent advancements using deep learning models like CNNs have shown promise, they often rely heavily on large labeled datasets. This dependency limits their applicability, particularly in real-world settings where such data is scarce. Moreover, ensuring accurate classification across diverse image conditions continues to be a significant hurdle. To address these challenges, an unsupervised learning framework is proposed, utilizing the Kaggle Acne dataset of 680 unlabeled images. Our approach combines image normalization through NumPy and OpenCV with feature extraction using a pretrained ResNet model. The extracted features are clustered into five severity levels using K-Means, and clusters are labeled based on acne-related characteristics like redness intensity. This method bypasses the need for labeled data, offering a scalable solution for acne severity scoring that can support further dermatological research and clinical applications. © 2024 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Predictive Maintenance of Aircraft Engines: Machine Learning Approaches for Remaining Useful Life Estimation 6

Predictive Maintenance of Aircraft Engines: Machine Learning...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Deepika, J. Reddy, Pappuru Manikanta Murari, Kothaluri Rahul, Boyana School of Computer Science and Engineering Vellore Institute of Technology Vellore Tamil Nadu Vellore India

ISBN: (纸本)9798331522667

In the realm of predictive maintenance for aircraft engines, ensuring precise and timely predictions of Remaining Useful Life (RUL) is paramount to enhancing safety, reducing costs, and minimizing downtime. While deep learning models dominate this field, their complexity, high computational demand, and lack of interpretability can hinder practical deployment in real-world scenarios. This study demonstrates the potential of machine learning models as an efficient and interpretable alternative for RUL prediction, leveraging the publicly available C-MAPSS dataset from NASA. Using C-MAPSS dataset, we integrated PostgreSQL for scalable data storage and Flask for interactive real-time visualization, creating a seamless pipeline from data ingestion to result interpretation. Preprocessing steps, including normalization, noise removal via box plots, and feature engineering, ensured a clean and reliable dataset. Among the models evaluated—XGBoost, Random Forest, SVM, KNN, and Linear Regression—XGBoost emerged as the best performer, achieving an RMSE of 23.8 and an R2 score of 0.67. These results nearly matches the accuracy typically associated with deep learning models while maintaining computational efficiency. Feature importance analysis through Explainable AI (XAI) further revealed critical insights into sensor contributions, enhancing interpretability and trust in the predictions. This work underscores the practicality and effectiveness of machine learning in predictive maintenance, offering a robust, transparent, and resource-efficient approach to RUL prediction. The findings highlight its potential to meet industry needs where simplicity, accuracy, and interpretability are critical for decision-making and operational efficiency. © 2025 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Healthcare: Blockchain's Transformative Applications for Data Security, Privacy, and Interoperability 9

Revolutionizing Healthcare: Blockchain's Transformative Appl...

引用

9th IEEE International Conference for Convergence in technology, I2CT 2024

作者： Raj, Riya Raja, S.P. Vellore Institute of Technology School of Computer Science And Engineering Vellore India

ISBN: (纸本)9798350394474

In a rapidly evolving digital era, the convergence of blockchain technology and healthcare is poised to revolutionize the industry in unprecedented ways. This research paper presents an innovative exploration of the transformative potential of blockchain within healthcare, unveiling a new paradigm of patient-centric, secure, and interoperable healthcare systems. Blockchain, renowned for its decentralized architecture and cryptographic security, addresses the perennial challenges of data integrity, patient privacy, and healthcare system interoperability. In this paper, we embark on a journey to unveil the diverse applications of blockchain technology in healthcare, ranging from enhancing medical records management (MRMs) to enabling groundbreaking advances in telemedicine, drug traceability, clinical trials and organ transplantation. Our research deploys a multidimensional analysis, we delve into blockchain's ability to empower patients with unprecedented control over their health data, fostering transparency and trust within the healthcare ecosystem. As we navigate the landscape of blockchain in healthcare, we also confront the formidable challenges that lie ahead, such as regulatory compliance, scalability, and the need for industry-wide adoption. In conclusion, this research paper is an innovative exploration into the fusion of blockchain technology and healthcare, reimagining the possibilities of a digitally transformed healthcare landscape. By unveiling novel applications, addressing challenges, and presenting practical solutions, this work inspires a new wave of research and innovation in the intersection of blockchain and healthcare, paving the way for a healthier, more secure, and patient-centric future. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

CE-EEN-B0:Contour Extraction Based Extended EfficientNet-B0 for Brain Tumor Classification Using MRI Images

引用

computers, Materials & Continua 2023年第3期74卷 5967-5982页

作者： Abishek Mahesh Deeptimaan Banerjee Ahona Saha Manas Ranjan Prusty A.Balasundaram School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India Centre for Cyber-Physical Systems Vellore Institute of TechnologyChennai600127India

A brain tumor is the uncharacteristic progression of tissues in the *** are very deadly,and if it is not diagnosed at an early stage,it might shorten the affected patient’s life ***,their classification and detection play a critical role in *** Brain tumor detection is done by biopsy which is quite *** is usually not preferred at an early stage of the *** detection involvesMagneticResonance Imaging(MRI),which is essential for evaluating the *** paper aims to identify and detect brain tumors based on their location in the *** order to achieve this,the paper proposes a model that uses an extended deep Convolutional Neural Network(CNN)named Contour Extraction based Extended EfficientNet-B0(CE-EEN-B0)which is a feed-forward neural network with the efficient net layers;three convolutional layers and max-pooling layers;and finally,the global average pooling *** site of tumors in the brain is one feature that determines its effect on the functioning of an ***,this CNN architecture classifies brain tumors into four categories:No tumor,Pituitary tumor,Meningioma tumor,andGlioma *** network provides an accuracy of 97.24%,a precision of 96.65%,and an F1 score of 96.86%which is better than already existing pre-trained networks and aims to help health professionals to cross-diagnose an MRI *** model will undoubtedly reduce the complications in detection and aid radiologists without taking invasive steps.

关键词： Brain tumor image preprocessing contour extraction disease classification transfer learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Malware Image Classification through Ensemble model 3

Enhanced Malware Image Classification through Ensemble model

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Kotha, Eshwar Palivela, Lakshmi Harika Begum, Afruza Vellore Institute of Technology School of Computer Science and Engineering Chennai India Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350375190

Classification of malwares and viruses is a very important work in the cyber security field to protect the computers and systems from threats and attacks. In this paper, we proposed a novel approach for the classification of the malwares by combining 2 models EfficientNet B0 and EffiCBNet models. Here we have used Malimg dataset which is available in Kaggle and it contains around 9,339 malware images and these malwares are from 25 different families, for evaluating the models. EffcientNetB0 is a Convolution Neural Network (CNN) model, which showed great and high results on various image classification works. We used transfer learning to fine tune the EfficientNet model;whereas the proposed EffiCBNet model is a deep learning model which contains of convolution layers and batch normalization layers. The results have shown that the proposed model has given the highest accuracy of 99.70 on the dataset we have used, exceeding all other models. The proposed model is the combination of EfficientNet and EffiCBNet, which showed great results for the classification. The proposed model can also be used in real time applications for detecting malware attacks and threats © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Leveraging Artificial Neural Networks for Breast Cancer Detection and Prognosis

Leveraging Artificial Neural Networks for Breast Cancer Dete...

引用

2025 IEEE International Conference on Computational, Communication and Information technology, ICCCIT 2025

作者： Goel, Aadya Mishra, Pallavi Bhatia, Rachna School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Advanced Sciences Vellore Institute of Technology Vellore India

ISBN: (纸本)9798331512965

Breast cancer remains one of the leading causes of mortality among women worldwide, making early detection and accurate classification critical for improving patient out-comes. This study explores the application of Artificial Neural Networks (ANN) for breast cancer multiclass classification and prediction using the CBIS-DDSM: Breast Cancer Image Dataset. The model was trained to classify mammographic images into three categories: benign, malignant, and benign without callback, achieving an impressive accuracy of 99.6%. The choice of ANN was driven by its proven capability to model complex, nonlinear relationships within data, offering a significant improvement over traditional machine learning technique. Despite the challenges posed by the limited size and heterogeneity of the dataset, the ANN demonstrated robust performance, highlighting its potential for clinical applications. The high accuracy of the model underscores its value as a reliable tool for aiding radiologists in the early detection and prognosis of breast cancer, which could lead to more effective treatment planning and better patient outcomes. This study lays the foundation for integrating advanced AI technologies into clinical settings, offering promise for more precise, timely breast cancer diagnoses. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Recognition and Anticipation of Diabetic Foot Ulcer in Type Ⅱ Diabetic Patients using Multi-layered Fuzzy Model

引用

Journal of Harbin institute of technology(New Series) 2024年第4期31卷 13-23页

作者： Sai Surya Varshith Nukala Jayashree Jayaraman Vijayashree Jayaraman Rishi Raghu School of Computer Science and Engineering Vellore Institute of TechnologyVellore 632014Tamil NaduIndia

Diabetes mellitus is associated with foot ulcers,which frequently pave the way to lower-extremity ***,trauma,deformity,high plantar pressures,and peripheral vascular disease are the most common underlying *** 15%of diabetic patients are affected by diabetic foot ulcer in their lifetime.64 million people are affected by diabetics in India and 40000 amputations are done every *** ulcers are evaluated and classified in a systematic and thorough manner to assist in determining the best course of *** paper proposes a novel model which predicts the threat of diabetic foot ulcer using independent agents for various input values and a combination of fuzzy expert *** proposed model uses a classification system to distinguish between each fuzzy framework and its *** on the severity levels necessary prevention,treatment,and medication are *** the results of all the fuzzy frameworks derived from its constituent parameters,a risk-specific medication is *** work also has higher accuracy when compared to other related models.

关键词： diabetic ulcer typeⅡdiabetic fuzzy model

来源：评论

学校读者我要写书评

暂无评论

Novel Darknet traffic data synthesis using Generative Adversarial Networks enhanced with oscillatory Growing Cosine Unit activated convolution layers

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 58-65页

作者： Pradeep C, Antony Amali D, Geraldine Bessie Noel, Mathew Mithra Ghalib, Muhammad Rukunuddin Subramaniam, Prabhakar Rontala Venugopal, Chitra School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Electrical Engineering Vellore Institute of Technology Vellore India School of Computing De Montfort University Dubai United Arab Emirates Information Systems and Technology Westville South Africa Electrical Engineering & Renewable Energy Oregon Institute of Technology United States

The Darknet is an anonymous, encrypted collection of websites, with a passive listening nature - accepting incoming packets, while not supporting outgoing packets. Thus, it can potentially host criminal or malicious activity and software, becoming a cyber security threat. Network Detection Systems are effective in identifying dark net traffic and mitigating its ill effects. However, capturing and extracting data from raw network traffic for training these systems can be time-intensive and costly. Using the CIC-Darknet 2020 dataset, this paper proposes using a Novel Generative Adversarial Networks (GAN) Architecture generating the required training and testing data for these systems. This uses a combination of Growing Cosine Unit (GCU) activated convolution layers and Dense layers for the Generator. Feature selection with statistical correlation methods is used to select the most relevant features. An independently trained Evaluator network is used to evaluate the generated data. The proposed system is compared to other established Tabular data GANs like Conditional Tabular GAN (CTGAN) and Copula GAN with similar parameters and on the same data. The Proposed GAN architecture outperforms CTGAN and CopulaGAN by 20 % and 10 % in ters of accuracy while also taking 90 % and 30 % less time to train respectively. Results from measuring similarity of data using the Inverted Kolmogorov - Smirnov D statistic also show significantly better results for the Proposed GAN Architecture. This shows significant promise in using Generative models to reduce the time and effort costs associated with collecting and formatting data to use in research and for training detection systems. © 2024

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

DDSS: Driver decision support system based on the driver behaviour prediction to avoid accidents in intelligent transport system

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 1-13页

作者： S, Balasubramani D, John Aravindhar Renjith, P.N. Ramesh, K. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India

Accidents caused by drivers who exhibit unusual behavior are putting road safety at ever-greater risk. When one or more vehicle nodes behave in this way, it can put other nodes in danger and result in potentially catastrophic accidents. In order to anticipate and handle unusual driving behavior in Intelligent Transportation Systems (ITS), this research presents a unique Driver Decision Support System (DDSS). A reliable driving behavior prediction system is used by the suggested DDSS to categorize drivers as displaying normal or abnormal behavior. In order to prevent accidents in ITS scenarios, the system reliably detects anomalous driving patterns and advises nearby vehicles to change lanes or alter speed. The driver behavior prediction algorithm efficiently groups drivers into behavior categories using the K-Means clustering method. In order to evaluate the algorithm's efficacy, a comparative analysis is conducted by comparing its outcomes against those of Support Vector Machines (SVMs), Decision Trees, K-Nearest Neighbours (KNN), Logistic Regression, and Naïve Bayes. The integration of the Driver Decision Support System into the Intelligent Transportation System infrastructure serves to augment endeavours in accident prevention. Monitoring and analysis of driver behavior enable timely interventions, promoting safer driving practices and reducing accident risks. This research helps to create a more effective transportation system by reducing the number of accidents brought on by reckless driving. Because of its novel method to anticipating and controlling driver behavior, the proposed DDSS has promise for improving road safety and preventing accidents. The efficacy and the dependability of the driver behavior prediction algorithm are confirmed by the experimental assessment. © 2023

关键词： K-means clustering

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：