检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Artificial Intelligence, ICAI 2023

作者： Ali, Muhammad Shahroze Hassan, Ali Rahim, Aqsa Ashraf, Muhammad Hashir Rahim, Amna Saghir, Shayaan CEME Department of Computer & Software Engineering Islamabad Pakistan

ISBN: (纸本)9798350322125

This work proposes a new way to apply the deep convolutional EfficientN etB0 model for the classification to learn various electroencephalogram (EEG) signal properties on BCI competition IV dataset 2b. Several deep convolutional neural networks (DCNN)-based techniques have been applied to enhance the accuracy of motor imagery-based brain-computer interfaces (BCIs). The time-varying nature of various frequency bands makes extracting informative features from EEG signals difficult, causing the loss of DCNN classification accuracy. The EfficientNetB0 baseline model's feature extraction capability is used to overcome these limitations by first transforming EEG 1D signals into 2D images using the feature extraction technique of the Short-Time Fourier Transform (STFT) algorithm to train and evaluate the EfficientNetB0 model. The transfer learning approach is used to expand the initial feature sets for efficient model training in a short period. After learning from the dataset, the entire model is retrained and fine-tuned to work with the proposed layers. Our evaluated results demonstrated that the highest average Accuracy, Precision, Recall, F1-Score and MCC with the STFT method is 86.46%,88.2%, 91.2%,89.78% and 0.815 respectively over 10 epochs. According to the results, the proposed methodology outperforms other state-of-the-art DCNN models for feature extraction and classification of two-class motor imagery, namely right-hand and left-hand movements for the given dataset. © 2023 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Towards Enhancing Aviation Safety Through Advanced Incident Analysis Using Large Language Models 34

Towards Enhancing Aviation Safety Through Advanced Incident ...

引用

34th Annual International Conference on Collaborative Advances in software and Computing, CASCON 2024

作者： Siddeshwar, Vaishali Azim, Akramul Alwidian, Sanaa Makrehchi, Masoud University of Ontario Institute of Technology Department of Electrical Computer and Software Engineering Canada

ISBN: (纸本)9798331504830

Aerospace incident reports, crucial for identifying abnormal aircraft occurrences, are submitted to regulatory authorities like FAA or EASA. These reports, often in natural language, offer clarity and context. Existing literature proposes incident-analysis tools utilizing manual rules and NLP techniques like Part-of-Speech Tagging and dependency parsers to extract entities from logs. However, these approaches may miss nuances, leading to incomplete or inaccurate extractions and potential mis-interpretations. This study aims to automate initial extraction using Large Language Models, extracting Aircraft Number/Model, contributing and human factors, primary root cause, and incident summaries. Automating this phase can expedite investigations and improve expert efficiency during review processes. © 2024 IEEE.

关键词： Aircraft accidents

来源：评论

学校读者我要写书评

暂无评论

Adventures in data analysis: a systematic review of Deep Learning techniques for pattern recognition in cyber-physical-social systems

引用

Multimedia Tools and Applications 2024年第8期83卷 22909-22973页

作者： Amiri, Zahra Heidari, Arash Navimipour, Nima Jafari Unal, Mehmet Mousavi, Ali Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Department of Software Engineering Haliç University Istanbul34060 Turkey Department of Computer Engineering Kadir Has Universitesi Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Douliou64002 Taiwan Department of Computer Engineering Nisantasi Universitesi Istanbul Turkey Islamic Azad University Sanandaj Branch Sanandaj Iran

Machine Learning (ML) and Deep Learning (DL) have achieved high success in many textual, auditory, medical imaging, and visual recognition patterns. Concerning the importance of ML/DL in recognizing patterns due to its high accuracy, many researchers argued for many solutions for improving pattern recognition performance using ML/DL methods. Due to the importance of the required intelligent pattern recognition of machines needed in image processing and the outstanding role of big data in generating state-of-the-art modern and classical approaches to pattern recognition, we conducted a thorough Systematic Literature Review (SLR) about DL approaches for big data pattern recognition. Therefore, we have discussed different research issues and possible paths in which the abovementioned techniques might help materialize the pattern recognition notion. Similarly, we have classified 60 of the most cutting-edge articles put forward pattern recognition issues into ten categories based on the DL/ML method used: Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Generative Adversarial Network (GAN), Autoencoder (AE), Ensemble Learning (EL), Reinforcement Learning (RL), Random Forest (RF), Multilayer Perception (MLP), Long-Short Term Memory (LSTM), and hybrid methods. SLR method has been used to investigate each one in terms of influential properties such as the main idea, advantages, disadvantages, strategies, simulation environment, datasets, and security issues. The results indicate most of the articles were published in 2021. Moreover, some important parameters such as accuracy, adaptability, fault tolerance, security, scalability, and flexibility were involved in these investigations. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Real-time CAN Data Acquisition and Visualization: Synerging Physical-to-Virtual (P2V) Twinning of Automotive Battery Management Systems 50

Real-time CAN Data Acquisition and Visualization: Synerging ...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Sharma, Mohit Samanta, Akash Chetri, Chandan Williamson, Sheldon Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

ISBN: (纸本)9781665464543

Controller area network (CAN) is widely used in automotive applications and has become the standard communication protocol to enable efficient communication primarily between electronic control units (ECUs) to reduce the complexity and cost of electrical wiring in automobiles through multiplexing. Towards developing the cloud-based electric vehicle battery data monitoring and digital-twinning of a battery management system (BMS), this paper introduced an online CAN data acquisition and visualization technique from an automotive grade BMS of NXP®®. Python-based CAN data processing tool is developed to process the raw data from the NXP® BMS and an open-source platform Grafana® is utilized together with the InfluxDB for visualization of the time-series data in real-time from a battery module containing 14 SAMSUNG 21700 lithium-ion battery cells. Each of those elements is implemented through the Docker container platform to become a standardized unit called a container. Besides presenting the detailed architecture of the data acquisition and visualization platform and the python-based data processing tool, this paper demonstrated the capability of the proposed architecture through examples of visualizing individual cell voltage, current, and temperature in real-time and their applications and utility in implementing cloud-based BMS. © 2024 IEEE.

关键词： Problem oriented languages

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Behavior of Solid State Protection System for Dual Active Bridge in Solid State Transformers Under Short Circuit Faults

Analyzing the Behavior of Solid State Protection System for ...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Lulbadda, Kushan Tharuka De Seram, Ruvini Sidhu, Tarlochan Williamson, Sheldon S. Ontario Tech University Department of Electrical Computer and Software Engineering Oshawa Canada

ISBN: (纸本)9798350376067

DC microgrids equipped with solid-state transformers (SST) offer a contemporary alternative to traditional low-frequency transformers (LFT) by increasing the system's power density. The SST consists of a front-end AC/DC converter and a Dual Active Bridge (DAB) as the two major components. However, the protection of the SSTs is still under minor development as they need a fast and reliable protection system. Solid-state circuit breakers (SSCBs) are becoming more popular in DC power systems due to the need for protection at ultrafast speed. The main objective of this article is to analyze the performance of the SSCB-based protection system for DAB during short circuit faults. PLECS simulation environment has been used to simulate and analyze the protection system's reaction to short circuit failures. A 1kW SSCB integrated DAB has been implemented in testing with actual hardware to validate the simulation results. The SSCB-based protection system achieves a remarkably high speed tripping time of 340μs. For a better understanding of the system, the behavior of the SSCB during a short circuit has been demonstrated at 50V by achieving a response time of 55.4μs. Moreover, the system is tested for different voltage levels to demonstrate the response time. This illustrates how the SSCB can safeguard SST quickly and effectively, improving safety and reliability. © 2024 IEEE.

关键词： Transformer protection

来源：评论

学校读者我要写书评

暂无评论

A Quad-Active Bridge (QAB)-Based Solid-State Transformer for Fast Charging of Light/Medium and Heavy Electric Vehicles 25

A Quad-Active Bridge (QAB)-Based Solid-State Transformer for...

引用

25th IEEE International Conference on Industrial Technology, ICIT 2024

作者： De Seram, Ruvini Lulbadda, Kushan Tharuka Sidhu, Tarlochan Williamson, Sheldon S. Ontario Tech University Department Of Electrical Computer And Software Engineering Oshawa Canada

ISBN: (纸本)9798350340266

Integrating electric vehicle (EV) fast charging stations with the medium voltage (MV) grid using a solid-state transformer (SST) has attracted more interest from researchers due to the reduced size and the smart functionalities it offers for maintaining the stability and power quality of the grid. However, the modular structure of SST requires many power converters and high-frequency transformers in the isolated DC/DC converter stage which again increases the space of the charging station. This paper proposes a design of an SST-based EV charging station using a quadruple-active-bridge (QAB) as the isolated DC/DC converter and investigates the power density enhancement compared to the dual-active-bridge (DAB)-based system. The proposed charging station can charge different EVs with different battery voltages (800V, 400V, and 200V) and capacities. The performance is validated by simulating a 1MVA, 10kV EV charging station using MATLAB. The control architecture and a detailed analysis of the system are included in the paper. © 2024 IEEE.

关键词： Bridges

来源：评论

学校读者我要写书评

暂无评论

SAC and DAC Approach for Load Frequency Controller with Multi-Battery Energy Storage

SAC and DAC Approach for Load Frequency Controller with Mult...

引用

2024 IEEE Green Technologies Conference, GreenTech 2024

作者： Gamage, Don Wanigasekara, Chathura Ukil, Abhisek Swain, Akshya University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand

ISBN: (纸本)9798350308587

This research introduces a static average consensus (SAC) and dynamic average consensus (DAC) based Load Fre-quency Controller (LFC) designed for a distributed multi-battery energy storage system (MBESS). The proposed control strategy leverages the active power delivery or absorption capability of battery storage units to manage system frequency during power deficits or surpluses. The controller adopts a consensus-based distributed frequency control approach, wherein each node engages in information exchange with its neighboring nodes, sharing main parameters like battery energy and power. It is also noted that our proposed controller approach will keep the State of Charge (SoC) in safe range which achieve a consensus in a finite time. The simulation results through MATLAB/Simulink indicate that the proposed system exhibits better characteristics. © 2024 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Protection Schemes of Solid State Transformers for Different Fault Conditions 4

Protection Schemes of Solid State Transformers for Different...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： Lulbadda, Kushan Tharuka Seram, Ruvini De Sidhu, Tarlochan Williamson, Sheldon S. Ontario Tech University Department of Electrical Computer and Software Engineering Oshawa Canada

ISBN: (纸本)9798350306262

The idea of a Solid-State Transformer (SST) has received much interest recently and is being thoroughly explored for use in the electrical system by replacing the traditional low-frequency transformer (LFT) using high-frequency isolated ACAC conversion. The SSTs are able to offer several additional functions than the traditional LFT. As the SST concept becomes popular among the power system, the safety of the system becomes vulnerable. The SST is made of a collection of several power electronic switches which has less reliability in general. Several kinds of faults can be caused by this issue like overcurrent, overvoltage, and overtemperature. These main issues are generally discussed in this paper to give a better idea of the faults that can happen in the system due to the integration of SSTs. In order to protect the SST a specific protection scheme must be needed. Further, it must have the ability to protect the system from disturbances coursed by the integration of SST. There are several protection schemes are available in the literature for the purpose of protecting the SST. Most of them are designed based on traditional power systems which are equipped with the LFTs. A few of them are discussed in this paper with their schematic diagrams to give a better understanding. The main focus of these protection systems is the protection of power electronic switches which will discussed in detail in this paper. Therefore, this paper will be a huge benefit for the researchers who are working on designing the protection systems for SST. Further, this paper will highlight the research areas that need more focus from a protection perspective. © 2024 IEEE.

关键词： Electric power system protection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Threat Intelligence Coalitions for Improved Cyber Defense Capabilities 13

Dynamic Threat Intelligence Coalitions for Improved Cyber De...

引用

13th IEEE International Conference on Cloud Networking, CloudNet 2024

作者： Wahab, Omar Abdel Polytechnique Montréal Department of Computer and Software Engineering Montréal Canada

ISBN: (纸本)9798350376562

In the dynamic landscape of cybersecu-rity and cyber warfares, Cyber Threat Intelligence (CTI) is increasingly relied on for gathering and sharing the latest information about threats and their trends. Current CTI sharing methods (e.g., ISACs, automated STIX/TAXII platforms), face challenges in terms of scalability, trust, and data quality issues. This is because they often lack systematic metrics for evaluating the quality and relevance of the threat data that are being shared. Moreover, they do not offer any mechanism to enable participating organizations to autonomously make decisions as to what Threat Intelligence providers to request and share data from/to. To address these limitations, we propose a novel Threat Intelligence sharing approach based on coalitional game theory. We first propose a set of metrics that enable organizations to assess the effectiveness of the shared Threat Intelligence data. Based on these metrics, we propose a preference function and a coalition formation algorithm that enable organizations to autonomously join and leave Threat Intelligence coalitions until reaching a Nash-Stable situation wherein no organization has incentive to leave its current coalition and join another one. Experiments suggest that our solution significantly improves the Mean Time to Detect (MTTD), Mean Time to Respond (MTTR) and Containment Rate. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Advanced Battery Aging Prediction through Impedance Spectroscopy Including Thermal Behavior and Degradation Analysis

Advanced Battery Aging Prediction through Impedance Spectros...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Anekal, Latha Williamson, Sheldon Ontario Tech University Department of Electrical Computer and Software Engineering Oshawa Canada

ISBN: (纸本)9798350376067

Understanding the thermal behaviour of lithiumion batteries (LIBs) with aging and degradation is crucial for developing an effective thermal management system and state-of-temperature estimation technique ensuring higher levels of accuracy over the entire battery cycle. The aging and degradation of LIBs are greatly affected by operating temperatures and battery degradation in turn increases the battery reversible and irreversible heat generation. This study deduces the relationship between aging parameters and temperature rise through cycling under normal operating temperatures using the electrochemical impedance spectroscopy (EIS) method. The critical analysis of the temperature and EIS data shows that the equilibrium temperature has increased by 6°C with cycling due to the associated impedance rise. © 2024 IEEE.

关键词： Battery management systems

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：