检索结果-内蒙古大学图书馆

3rd International Conference on Innovative Mechanisms for Industry applications, ICIMIA 2023

作者： Jyostna, G. Goyal, Himanshu Rai Soudagar, Manzoore Elahi M. Parikh, Swapnil Patil, Harshal Alaskar, Kamal Potti Sriramulu Chalavadi Mallikarjuna Rao College of Engineering & Technology Department of CSE-DS Andhra Pradesh Vijayawada520 012 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of VLSI Microelectronics Tamil Nadu Chennai602105 India Parul Institute of Engineering and Technology Department of Computer Science and Engineering Parul University Post Limda Gujarat Waghodia391760 India Computer Science and Engineering Symbiosis Institute of Technology Maharashtra Pune412 115 India Department of Computer Application Institute of Management Maharashtra Kolhapur416003 India

ISBN: (纸本)9798350343632

Maternal health issues during pregnancy are a major global concern because they result in fetal death, which is more frequent in rising and poor countries. Cardiotocography (CTG) is the major non-invasive and cost-effective method for monitoring fetal health. CTG delivers critical parameters such as Fetal Heart Rate (FHR) and Uterine Contraction (UC), with a total of 21 features for accurate monitoring. These characteristics assist obstetricians in categorizing fetal health as normal, suspect, or pathological. However, differences in CTG interpretation among obstetricians frequently result in incorrect procedures. This work presents a unique way to detect deficient fetal states using a hybrid Machine Learning (ML) model that combines Support Vector Machine (SVM) and Random Forest (RF). The UCI repository dataset is pre-processed, which includes balancing, outlier reduction, and feature selection. The hybrid model's performance is then compared to that of classic ML models such as SVM, K-Nearest Neighbour (KNN), RF, and Decision Tree (DT). The hybrid model outperforms the other models in simulation, attaining the greatest accuracy rate of 98.83%. This novel ML-based technique has the potential to improve fetal health detection while reducing the influence of human CTG interpretation discrepancies across healthcare providers. © 2023 IEEE.

关键词： Cardiotocography Correlation Features Fetal Hybrid Machine Learning Outliers UCI Repository

来源：评论

学校读者我要写书评

暂无评论

FraudGuard Pro: An Ensemble-Based Feature Selection Algorithm for Credit Card Fraud Detection 15

FraudGuard Pro: An Ensemble-Based Feature Selection Algorith...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Bhardwaj, Shashank Baskar, S. Marakala, Vijaya Prasannan Gangodkar, Durgaprasad Dhole, Sumedh Vithalrao Dr. A.P.J. Abdul Kalam Technical University Department of Computer Application Lucknow India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Department of EE Tamil Nadu Chennai India University of Bisha College of Medicine Saudi Arabia Karpagam College of Engineering Department of Civil Engineering Tamilnadu Coimbatore India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India College of Engineering Department of Electronics & Communication Engineering Maharashtra Pune India

ISBN: (纸本)9798350370249

In recent years, the exponential growth in data volume and sample sizes across various domains, including finance and online transactions, has presented significant challenges for machine learning and data mining algorithms. High-dimensional and imbalanced datasets, often tainted with noise, have impeded the performance and interpretability of fraud detection models. Feature selection has emerged as a pivotal technique to address these challenges by identifying the most relevant features while discarding redundant or irrelevant *** research explores the landscape of feature selection methods and confronts the existing challenges in credit card fraud detection. We propose the 'FraudGuard Pro Ensemble Feature Selection Algorithm,' designed specifically for credit card fraud detection tasks. Notably, our proposed model achieves an impressive accuracy rate of 99%, outperforming traditional models such as Logistic Regression (95%), Random Forest (98%), and Support Vector Machine (94%). This substantial improvement underscores the effectiveness of our algorithm in mitigating fraud while minimizing false positives, offering a promising solution for enhanced security in online transactions. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Optimized Siamese Humboldt Squid Attention Network Architecture for Cyber-Attack Detection in IoT 4.0 4

Optimized Siamese Humboldt Squid Attention Network Architect...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Mohamed, M. Varusai Nainwal, Ankita Ayshwarya, B. Kumar, H.S. Rabadiya, Dhaval Taqui, Syed Noeman Department of Computer Application Tamil Nadu Chennai600048 India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun248 002 India Kristu Jayanti College Department of Computer science Karnataka Bengaluru560043 India Department of Mechanical Engineering Karnataka Nitte India Parul University Faculty of Management studies P.O. Limda Ta. Waghodia Gujarat Vadodara391760 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India

ISBN: (纸本)9798331540364

The rapid expansion of IoT within Industry 4.0 has heightened the risk of cyber-attacks, underscoring the need for advanced detection mechanisms. Existing cyber-attack detection systems in this context often struggle with reduced accuracy, high computational time, complexity, and elevated error rates. This study addresses these challenges by proposing an Optimized Siamese Humboldt Squid Attention Network (OSH-SqAtNet) architecture for cyber-attack detection in IoT Industry 4.0 environments. The input data, sourced from datasets like CSE-CIC-IDS2018, undergoes preprocessing via a Mixture of Conventional Fast Bilateral Filter (MC2FB) to enhance data quality. A Gold Rush Optimizer (GRO) is then employed for feature selection, isolating the most significant features to optimize classification performance. The preprocessed and optimized data are classified using the OSH-SqAtN et architecture for accurate cyber-attack detection. For secure data transmission, Rabin Fuzzy Cryptosystem assisted Elliptic Curve Cryptography (RFC-ECC) is utilized. Experimental simulations conducted on the Python platform reveal that the proposed method outperforms existing techniques, achieving higher accuracy (98%) and recall (0.993%). These results demonstrate the approach's superior efficacy and potential for advancing cybersecurity in IoT Industry 4.0. © 2024 IEEE.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Aided Intelligent Framework for Condition Monitoring of Electrical Machinery 5

A Deep Learning Aided Intelligent Framework for Condition Mo...

引用

5th International Conference on Devices for Integrated Circuit, DevIC 2023

作者： Ganguly, Biswarup Ray, Radha Kumari Chatterjee, Arunava Paul, Subho Meghnad Saha Institute of Technology Electrical Engineering Department Kolkata India Application Development Associate Accenture Kolkata India Raghunathpur Govt. Polytechnic Electrical Engineering Department Purulia India Washington State University School of Electrical Engineering and Computer Science PullmanWA United States

ISBN: (纸本)9798350347265

Single-phase induction motors (SPIM) are fairly efficiently employed in household devices and possess wide applications in the industrial system. Typically, current signature-Analysis (CSA) based methods have been used for fault diagnosis, but not always been an efficient solution, especially for fractional kW SPIMs that may be replaced entirely iffaulty. This paper presents a deep learning (DL) based fault detection scheme of a SPIM which is in-service in household devices. The fault detection is done employing a wavelet based deep dense convolutional neural network (W-D2CNN), where several wavelets are used as convolutional filters for convolution operation. The convoluted feature maps are further passed through a proposed nonlinearity, i.e., SLReLU, for richer feature extraction. The uniqueness of the proposed method lies in the feature learning ability, where upper-And lower-layer features of the dense block fuse via concatenation operation. Also, the SL-ReLU has been designed to combine logarithmic function, softsign, and ReLU operation. The designed SL-ReLU minimizes the probability of convoluted output and gradient explosion, due to which training has been improved along with feature learning ability. Comprehensive results reveal the efficacy of the proposed work in terms of performance metrics with state-of-The-Art DL frameworks using the same dataset. The proposed work can also be extendable to multiphase-induction machines or any other electrical device working in any environment for fault identification. © 2023 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Research on elephant flow detection method based on information entropy and improved random forest

Research on elephant flow detection method based on informat...

引用

2022 International Conference on Algorithms, Microchips and Network applications

作者： Hu, Xiaohong Miao, Xianghua Yuan, Meiyu Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Computer Technology Application Kunming University of Science and Technology Kunming650500 China

ISBN: (纸本)9781510653290

In the increasingly complex network environment, various attacks emerge one after another. Being able to accurately detect elephant flow and mouse flow plays an extremely important role in defending against large-scale network attacks. Aiming at some shortcomings of current methods for detecting elephant flow and mouse flow, this paper proposes a detection method based on information entropy and improved random forest. After preprocessing the data, first calculate the data feature score with information entropy, screen out the truly valuable features according to the score, then put them into the improved random forest classifier, and finally get the detection results. In this paper, the grid search algorithm is used to optimize the tree and depth of random forest tree, so that the detection results can be obtained quickly and accurately. Experiments show that due to the significant difference between the data characteristics of elephant flow and mouse flow, this method can effectively identify elephant flow and mouse flow. The accuracy rate is 97.93%, the precision rate is 99.99%, the recall rate is 97.91%, and the F1-score is 98.94%, which is improved compared with other algorithms. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Weather Prediction

Deep Learning Techniques for Weather Prediction

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： R Dhanalakshmi Tushar Paul Centre for Cyber Physical Systems School of Computer Science and Engineering Vellore Institute of Technology Chennai Masters of Computer Application Vellore Institute of Technology Chennai India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510039

Human activities are directly impacted by weather occurrences. Forest fires, high air temperatures that lead to drought, and extreme weather events caused by global warming all make life more difficult for humans. Precautions against such climatic calamities require weather forecast models that are both accurate and effective. As a result, creating models that accurately forecast the weather is crucial. The creation of effective models of deep learning-based weather forecasting was greatly aided by technological advancements. This study suggested a hybrid weather prediction model based on convolutional and recurrent neural networks, which had a decent success rate. The dataset named Jena, which comprises 14 parameters, extensive meteorological information that has not been used for predicting the weather, was subjected to the suggested hybrid model. The experimental findings were compared using well-known machine learning, deep learning, and statistical techniques such CNN, Integrated Moving Average with Auto-Regression, LSTM, RNN, Random Forest, Multilayer Perceptrons and SVM. These comparisons showed that the suggested hybrid model had the best prediction outcome across the board. For instance, the suggested hybrid model produced the following findings based on the weather forecast data for Jena.

关键词： Deep learning Temperature distribution Recurrent neural networks Accuracy Atmospheric modeling Weather forecasting Predictive models Data models Convolutional neural networks Meteorology

来源：评论

学校读者我要写书评

暂无评论

Neural Network Implementation for Battery Failure Detection in Electric Vehicles

Neural Network Implementation for Battery Failure Detection ...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Vijitha, S. Hebri, Dheeraj Singh, Sangeeta Manohara, M. Ishrat, Mohammad Joseph, D Raja Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Tamil Nadu Chennai600117 India Srinivas Institute of Technology Department of Master of Computer Application Karnataka Mangaluru574143 India JSS Academy of Technical Education Department of Electrical Engineering Uttar Pradesh Noida201301 India Mohan Babu University School of Engineering Andhra Pradesh Tirupati517102 India KoneruLakshmaiah Education Foundation Department of Computer Science and Engineering Guntur Andhra Pradesh Vaddeswaram522502 India Hindustan Institute of Technology and Science School of Aeronautical Sciences Tamil Nadu Chennai603103 India

ISBN: (纸本)9798350319200

Soil destruction and global warming have recently come to the forefront of discussion in industrialised nations as governments strive to accommodate the rising demands of their citizens. The demand for zero-emission electric cars has increased as a result of international competitiveness and technological advancements (EVs). Concerns about the high voltage of increasing numbers of electric cars are shared by an increasing number of individuals. Since the system of batteries may be at responsible for over 30% of EV accidents, it is vital to investigate how problems with LIBs are recognized. Many different kinds of problems make it hard to fix EV's LIB. Fast and precise diagnosis of battery pack problems is crucial for the immediate and ongoing safety of EV operation. Utilizing models of neural networks like multiple hidden layers (MLP) or nonlinear activation functions, this research provides a mechanism for identifying and fixing problems with electric vehicle batteries (RBF). To generate information for the BFD system, battery simulations are done in MATLAB. Accuracy may be improved by performing pre-processing steps on the information once it has been generated. After training, the two models are put to the test to see how well they perform. There are both positive and negative measures that may be used to determine which model is the best. © 2023 IEEE.

关键词： Accuracy Battery Electric Vehicle Fault Model Neural Network

来源：评论

学校读者我要写书评

暂无评论

FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysis

arXiv

引用

arXiv 2025年

作者： Che, Haoxuan Wu, Yifei Jin, Haibo Xia, Yong Chen, Hao Department of Computer Science and Engineering Hong Kong University of Science and Technology University Hong Kong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Department of Computer Science and Engineering Department of Chemical and Biological Engineering Division of Life Science Hong Kong University of Science and Technology Hong Kong

Federated domain generalization aims to train a global model from multiple source domains and ensure its generalization ability to unseen target domains. Due to the target domain being with unknown domain shifts, attempting to approximate these gaps by source domains may be the key to improving model generalization capability. Existing works mainly focus on sharing and recombining local domain-specific attributes to increase data diversity and simulate potential domain shifts. However, these methods may be insufficient since only the local attribute recombination can be hard to touch the out-of-distribution of global data. In this paper, we propose a simple-yet-efficient framework named Federated Domain Adversarial Generation (FedDAG). It aims to simulate the domain shift and improve the model generalization by adversarially generating novel domains different from local and global source domains. Specifically, it generates novel-style images by maximizing the instance-level feature discrepancy between original and generated images and trains a generalizable task model by minimizing their feature discrepancy. Further, we observed that FedDAG could cause different performance improvements for local models. It may be due to inherent data isolation and heterogeneity among clients, exacerbating the imbalance in their generalization contributions to the global model. Ignoring this imbalance can lead the global model’s generalization ability to be sub-optimal, further limiting the novel domain generation procedure. Thus, to mitigate this imbalance, FedDAG hierarchically aggregates local models at the within-client and across-client levels by using the sharpness concept to evaluate client model generalization contributions. Extensive experiments across four medical benchmarks demonstrate FedDAG’s ability to enhance generalization in federated medical scenarios. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Decentralized and Network-Aware UAV Service Deployment for Dependency-Driven applications

Decentralized and Network-Aware UAV Service Deployment for D...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Sari, Talip Tolga Quadri, Christian Seçinti, Gökhan Trotta, Angelo University of Bologna Department of Computer Science and Engineering Italy Istanbul Technical University Department of Computer Engineering Turkey Università degli Studi di Milano Department of Computer Science Italy Bts - Digital Twin Application and Research Center Istanbul Technical University Turkey

ISBN: (纸本)9798350368369

Unmanned Aerial Vehicle (UAV) swarms enable the rapid deployment of IoT services in dynamic and challenging environments. While these swarms offer flexibility and close proximity to sensing and actuation points, efficiently deploying interdependent services at scale remains a core challenge. Traditional centralized methods struggle to handle the complexity of large UAV networks, leading to increased latency and limited reliability. In this paper, we propose a decentralized approach to service deployment in UAV swarms. Our method relies on local information at each node, allowing UAVs to make their own assignment decisions. Over time, these decisions are iteratively refined as nodes exchange status updates and adapt to network changes. This process avoids the bottlenecks of centralized coordination and enables more responsive resource allocation. Simulation results show that our approach supports the successful deployment of a high number of tasks while maintaining low latency. These findings indicate that decentralized methods with local resource knowledge, improves both scalability and responsiveness in UAV-based IoT systems. © 2025 IEEE.

关键词： Target drones

来源：评论

学校读者我要写书评

暂无评论

Decentralized and Network-Aware UAV Service Deployment for Dependency-Driven applications

Decentralized and Network-Aware UAV Service Deployment for D...

引用

IEEE Conference on Wireless Communications and Networking

作者： Talip Tolga Sarı Christian Quadri Gökhan Seçinti Angelo Trotta Department of Computer Science and Engineering University of Bologna Italy Department of Computer Engineering Istanbul Technical University Turkey Department of Computer Science Università degli Studi di Milano Italy BTS - Digital Twin Application and Research Center Istanbul Technical University Turkey

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

关键词： Simulation Scalability Autonomous aerial vehicles Robustness Sensors Internet of Things Resource management Vehicle dynamics Optimization Testing

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：