检索结果-内蒙古大学图书馆

1st International Conference on Pioneering Developments in computer science and Digital Technologies, IC2SDT 2024

作者： Chaturvedi, Sushil Ahirwal, Mitul Kumar Maulana Azad National Institute of Technology Dept. of Computer Science and Engineering Bhopal India

ISBN: (纸本)9798350365016

Mental workload (MWL) can be explained as the ratio of a participant's mental effort to their brain capability when performing activities. A significant challenge in the field of MWL classification for brain-computer interfaces (BCIs) based on electroencephalograms (EEGs) is the variability among individuals. It commonly takes unnecessary time to retrain the classification model from starting for a new subject. To address the individual variations among different subjects, a one-dimensional convolutional neural network along with transfer learning (1D CNN-TL) is proposed in this work. The end-to-end 1D-CNN learns the common features of EEG signals and, to tackle the problem of difference in EEG for individuals, a transfer learning technique is used that does fine-tuning on fully connected (FC) layers for a new participant having less training data. The average test accuracy (mean±stdv) of 65.18± 8.37 is achieved over the Cross-session mental workload dataset. The suggested method can achieve satisfying results for new unknown data with less time and fewer training data. © 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

Enhancing WSNs Lifetime Through GOA based Clustering and Routing 1

Enhancing WSNs Lifetime Through GOA based Clustering and Rou...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Kaushik, Neeraj Singhal, Amit Pandey, Ashish Monad University Dept. of Computer Science and Engineering UP Hapur India GCET Dept. of Electronics and Communication Engineering UP Greater Noida India

ISBN: (纸本)9798350356816

WSNs are regularly battery-powered and it is not continually feasible to recharge or replace them due to a variation of applications. Hence, in this work, a Grasshopper Optimization Algorithm based on routing and power restriction optimization has been proposed for improving the battery lifetime in wireless sensor network. The proposed approach aims to enhance the effective longevity of individual sensor nodes within the network by accomplishing energy-efficient clustering along with energy-aware routing. The outcomes of the suggested method are compared with the several existing optimization methods in WSNs. It is observed that the proposed Grasshopper Optimization Algorithm (GOA) based technique outperforms all the other existing methods in terms of lifetime achieved under various power constraints. For checking robustness of approach, two different locations of base station and various populations of sensing nodes and gateways are also considered. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Blockchain Unleashed: Exploring its Multifaceted Applications and the Dynamics of Proof-of-Work

Blockchain Unleashed: Exploring its Multifaceted Application...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Hassan, Inzimam Ul Ahmad Lone, Zeeshan Kaur, Inderdeep Kaur, Gaganjot Siya, Siya Priya, Simran Chandigarh University Dept. of Computer Science and Engineering Mohali India Vivekananda Global University Dept. of Computer Science and Engineering Jaipur India Chandigarh University Dept. of Cse Mohali India

ISBN: (纸本)9798350308167

In a range of sectors, such as banking, healthcare, and the Internet of Things, we have seen several data security and confidentiality issues. So, it is revealed that blockchain can provide a solution to the security problem. Thanks to the distributed database technology known as a blockchain, a trusted third party are not required for secure and transparent transactions between parties. The integrity of the chain is ensured by the cryptographic hash of each block in the chain, which makes each one tamper-proof. Blockchain technology has the potential to revolutionize a wide range of industries, from finance to healthcare, by providing a secure, efficient, and transparent method of storing and transmitting data and value. After reading the research on blockchain applications in different fields, we will highlight some of the major advantages we understand © 2023 IEEE.

关键词： banking finance Blockchain security integrity tamper-proof

来源：评论

学校读者我要写书评

暂无评论

Late Breaking Results: A real-time diffusion-based filter for human pose estimation on edge devices 24

Late Breaking Results: A real-time diffusion-based filter fo...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Bozzini, Chiara Boldo, Michele Martini, Enrico Bombieri, Nicola Dept. of Engineering for Innovation Medicine University of Verona Verona Italy Dept. of Computer Science University of Verona Verona Italy

ISBN: (纸本)9798400706011

Human Pose Estimation (HPE) is increasingly being adopted in a wide range of applications, from healthcare to Industry 5.0. To address the intrinsic inaccuracy of such CNN-based software, the current trend involves applying filtering models to refine and improve the inference results. However, state-of-the-art filtering models are computationally intensive, limiting their use in resource-constrained devices. To overcome this limitation, we propose a real-time filtering technique based on diffusion models designed specifically for edge devices. Through a micro-benchmarking phase, we analyze how the model responds to various levels of noise and select the optimal setup for specific application scenarios. Using a widely available edge device, we evaluated the model's performance on both synthetic and real noise generated by a state-of-the-art HPE system. Preliminary results demonstrate a significant improvement in real-time filtering performance with minimal computational overhead. © 2024 Copyright held by the owner/author(s).

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Integration of Q-Learning with Maximal Ratio Combining to Enhance IoT Communications in Dynamic Fading Environments 12

Integration of Q-Learning with Maximal Ratio Combining to En...

引用

12th International Conference on Internet of Everything, Microwave, Embedded, Communication and Networks, IEMECON 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Sharma, Rashmi Upadhyay, Abhay Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India Nagpur Campus Pune India

ISBN: (纸本)9798350387315

This paper serves to show how Q-learning can be used in complement with Maximal Ratio Combining to better IoT communication systems under dynamic fading, high-density networks, and severe interference sources. The ML-enhanced MRC demonstrated promising improvements in signal strength and quality, allowing for performance that was either above or at least equal to the regular MRC. The ML-enhanced presented the added benefit of dynamic adaptation, modifying its performance to meet real-life needs by adapting to issues such as increased density and interference. These results support that integrating Q-learning into MRC-based frameworks significantly increases the reliability and efficiency of IoT communication protocols. Future investigations will aim to improve ML algorithms more appropriate for devices with few resources and evaluate their potential with state-of-the-art technology to foster future applications across intelligent IoT networks. These approaches have the potential to support more efficient operations and increased connectivity in IoT systems. © 2024 IEEE.

关键词： Fading MRC Q-Learning Wireless

来源：评论

学校读者我要写书评

暂无评论

Weighted butterfly optimization algorithm with intuitionistic fuzzy Gaussian function based adaptive-neuro fuzzy inference system for covid-19 prediction

引用

Materials Today: Proceedings 2022年 56卷 3317-3324页

作者： Sundaravadivel, T. Mahalakshmi, V. Dept. of Computer Science and Engineering Annamalai University Tamil Nadu India

Covid-19 cases are increasing each day, however none of the countries successfully came up with a proper approved vaccine. Studies suggest that the virus enters the body causing a respiratory infection post contact with a disease. Measures like screening and early diagnosis contribute towards the management of COVID- 19 thereby reducing the load of health care systems. Recent studies have provided promising methods that will be applicable for the current pandemic situation. The previous system designed a various Machine Learning (ML) algorithms such as Decision Tree (DT), Random Forest (RF), XGBoost, Gradient Boosting Machine (GBM) and Support Vector Machine (SVM) for predicting COVID-19 disease with symptoms. However, it does not produce satisfactory results in terms of true positive rate. And also, better optimization methods are required to enhance the precision rate with minimum execution time. To solve this problem the proposed system designed a Weighted Butterfly Optimization Algorithm (WBOA) with Intuitionistic fuzzy Gaussian function based Adaptive-Neuro Fuzzy Inference System (IFGF-ANFIS) classifier for predicting the magnitude of COVID- 19 disease. The principle aim of this method is to design an algorithm that could predict and assess the COVID-19 parameters. Initially, the dataset regarding COVID-19 is taken as an input and preprocessed. The parameters included are age, sex, history of fever, travel history, presence of cough and lung infection. Then the optimal features are selected by using Weighted Butterfly Optimization Algorithm (WBOA) to improve the classification accuracy. Based on the selected features, an Intuitionistic fuzzy Gaussian function based Adaptive-Neuro Fuzzy Inference System (IFGF-ANFIS) classifier is utilized for classifying the people having infection possibility. The studies conducted on this proposed system indicates that it is capable of producing better results than the other systems especially in terms of accuracy, precision,

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Modular Design of Solid-State Transformer with High Flexibility

Modular Design of Solid-State Transformer with High Flexibil...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Ma, Zhuxuan Cao, Hui Zhao, Yue University of Arkansas Dept. of Electrical Engineering and Computer Science FayettevilleAR United States

ISBN: (纸本)9798350376067

This paper presents a modular solid state transformer (SST) design incorporating dual active bridge and cascaded H-Bridge topologies to enhance electric vehicle (EV) charging infrastructure. By using modular design concept for the power cell hardware, the proposed SST can be suitable for industrial usage with low manufacturing cost, and low maintenance complexity. With various combinations of the power cells, the whole SST converter has high flexibility for the power scale and circuit topology. This guarantees the fast installation and high transportability of the SST, suitable for the high-demanded EV charging applications. The design detail of the busbar used for the SST has been presented, which shows how to reduce the stray inductance of the busbar while keeping its high current conduction ability and high insulation. To validate the high current conduction ability of the busbar, finite element analysis is conducted to assess busbar current density and temperature. Finally, an advanced control strategy is introduced to effectively reduce DC link ripple, eliminating the need for bulky components. © 2024 IEEE.

关键词： Busbars

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach for Parkinson' s disease Prediction through Quantum Computing Techniques 2

Machine Learning Approach for Parkinson' s disease Predictio...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Arpitha, K. Lohith, H.R. Nemmadi, H.K. Sujan, K. Yashwanth, C.L. Dept. of Computer Science Engineering BGS Institute of Technology Adichunchanagiri University Mandya India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383867

One of the most serious illnesses that may impact the neurological system in humans is dementia, of which Parkinson' s disease is a major subtype. Patients with Parkinson' s disease have significant behavioural changes. The suggested system uses quantum computing and machine learning to build a speech signal-based method for Parkinson' s disease prediction. Four main machine learning methods are used in this prediction: Artificial Neural Networks, KNN, Decision Trees, and Naïve Bayes. Furthermore, different ensemble learning models are used to combine numerous models and improve the accuracy. An industry standard dataset from the UCI Machine Learning Repository is used to assess the model' s performance. Ensemble models have proven to outperform extremely efficient techniques like neural networks in terms of accuracy. A multi-layer perceptron, a very significant machine learning optimization technique, is incorporated into the suggested system. © 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

An Effective Way to Detect Phishing Website Using Machine Learning 6

An Effective Way to Detect Phishing Website Using Machine Le...

引用

6th International Conference on Electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Toyeer-E-Ferdoush Shorab, Mst. Sumaiya Ritu, Saima Akter International University of Business Agriculture and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385779

In today's interconnected digital landscape, phishing represents a significant threat to both individuals and organizations. Phishers cleverly utilize deceptive techniques to extract sensitive information from unsuspecting users, posing a risk to critical account details. Despite various proposed methods to detect phishing websites, the adaptability of phishers continually challenges the efficacy of existing approaches. Recognizing the vital role of Machine Learning (ML) in combating these evolving threats, this research investigates the application of ML techniques. Common characteristics in phishing attacks can be identified through accurate ML analysis. This research employs a range of ML models and transformer models, including Catboost (Cat), XGBoost (XGB), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), TabNet, K-nearest neighbor (KNN), and Logistic Regression (LR) with grid-search. Among these models, the Catboost classifier achieved a remarkable accuracy of 97%. This study shows dedication to utilizing diverse methodologies to advance the field of phishing website detection. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

DriveQ: A Dedicated Vehicle-to-Vehicle Communication System for Enhancing Road Safety and Traffic Management

DriveQ: A Dedicated Vehicle-to-Vehicle Communication System ...

引用

2024 International Conference on E-Mobility, Power Control and Smart Systems, ICEMPS 2024

作者： Sunil, K.S. Biju, Alan Aiswarya Arun, G. Joy, Prince V. Rathul Krishnan, R. Government Engineering College Dept. of Computer Science & Engg. Kerala Idukki India

ISBN: (纸本)9798350394399

Modern urban transportation systems confront significant challenges, including escalating traffic congestion, accidents, and inefficient traffic management. One critical aspect contributing to these issues is the limited means of communication between vehicles, which represents a missed opportunity to en-hance road safety and traffic efficiency. To address these concerns and facilitate smarter transportation solutions, there's a need for an efficient, standardized, and secure Vehicle-to-Vehicle (V2V) communication system capable of seamlessly sharing real-time data between vehicles. DriveQ mainly focuses on implementing a dedicated V2V communication system that enhances road safety and traffic management. V2V communication technology is a revolutionary development that depends on Dedicated Short-Range Communication (DSRC), a specialized communication method enabling vehicles to exchange critical information such as location, speed, and status in real-time. In addition to providing exceptionally low latency communication, DSRC is essential for broadcasting messages that improve road safety by facilitating quick and easy communication between vehicles. The system allows users to view and share real-time data and allows us to connect with nearby vehicles within a specific range. With the help of this function, drivers can take preventative measures to keep themselves safe. DriveQ has a broad range of applications including Stop Sign Movement Assistance, Forward Collision Warning, Pre-Crash Warning, and Curve Speed Warning. © 2024 IEEE.

关键词： Vehicle to vehicle communications

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：