检索结果-内蒙古大学图书馆

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Santushti Betgeri Piyush Lodha Aneesh Oak Aryan Parikh Ayush Lodha Dept. Of Computer Engineering Vishwakarma Institute of Technology Pune

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

With the rising incidents of harassment and violence in India, particularly against women, this paper presents a real-time violence detection system using YOLO image detection models (YOLOv7, YOLOv8, and YOLOv9). The models were trained on a carefully curated and manually annotated dataset using Roboflow, ensuring robust detection across diverse scenarios. Transfer learning and hyperparameter tuning were applied to improve accuracy. The system was evaluated using key performance metrics, including mean average precision (mAP), Intersection over Union (IoU), precision, and recall, achieving 80% precision and 50–60% recall. Extensive manual testing on real-world surveillance footage and additional video sources further validated its effectiveness. Results indicate that YOLOv8 outperforms other versions in balancing speed and accuracy. This system has strong potential for deployment in law enforcement, public surveillance, and safety-critical applications.

关键词： YOLO Accuracy Surveillance Scalability Transfer learning Real-time systems Safety Tuning Standards Testing

来源：评论

学校读者我要写书评

暂无评论

Full-Duplex Substrate Integrated Gap Waveguide Circulator Antenna System for Ka-Band Radars

Full-Duplex Substrate Integrated Gap Waveguide Circulator An...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Syed M. Sifat Yazan Al-Alem Marco A. Antoniades Dept. of Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto ON Canada Dept. of Electrical and Computer Engineering The Royal Military College of Canada Kingston ON Canada

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

This work uses an integration technique to design an antenna with a circulator forming a full-duplex communication system based on substrate-integrated gap waveguide (SIGW) technology. The SIGW circulator covers a wide frequency range from 27–33 GHz, with an excellent return loss and isolation level over the frequency range. The antenna considered for this work is a PCB-based dielectric resonator antenna (DRA) augmented with rings providing wide bandwidth and high gain.

关键词： Spaceborne radar Circulators Resonant frequency Gap waveguide Full-duplex system Radar antennas Dielectric resonator antennas

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Charging: A Distribution Network Perspective Highlighting the Technical Aspect 1

Electric Vehicle Charging: A Distribution Network Perspectiv...

引用

1st Renewable Energy Technologies and Modern Communications Systems: Future and Challenges Conference, RETMCS 2024

作者： Zaki, Mohamed El-Afifi, Magda I. Sedhom, Bishoy E. Osman, Samaa F. Eladl, Abdelfattah A. Hatata, Ahmed Y. Electrical Engineering Department Mansoura University Faculty of Engineering Mansoura Egypt Dept. of Elect. and Comm.Eng. Nile Higher Institute for Eng. and Technology Mansoura Egypt Electrical Engineering Department Faculty of Engineering Mansoura University El-Mansoura35516 Egypt

ISBN: (纸本)9798331519445

As the world transitions towards a more sustainable future, electric vehicles (EVs) have emerged as a promising solution to reduce environmental pollution and mitigate escalating energy consumption. The proliferation of EVs has significantly increased the demand for charging infrastructure, which faces several challenges. One of the primary concerns is the speed at which EV batteries can be recharged, hindering the practicality of long-distance travel. Additionally, the integration of EV charging stations into the existing power grid can strain the network, leading to potential issues such as increased peak loads, voltage instability, and reliability concerns. This paper presents the design of a comprehensive EV charging station integrated into the existing electricity distribution network. Simulations will evaluate the station's performance under various scenarios, including multiple simultaneous EV charging, focusing on factors such as charging speed, power quality, and network stability. ©2024 IEEE.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

Bangla Toxic Comment Classification and Severity Measure Using Deep Learning

Bangla Toxic Comment Classification and Severity Measure Usi...

引用

2022 International Conference on Recent Progresses in Science, engineering and technology, ICRPSET 2022

作者： Haque, Naimul Alam, Md. Bodrul Towfiq, Abdullah Ath Hossain, Mehorab Ahsanullah University of Science and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh Manarat International University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350332704

Online users nowadays leave a lot of comments on various social networks, news websites, and forums. Certain comments are harmful or abusive. Since it is impractical to manually monitor so many comments, the majority of systems employ some form of a machine learning model to automatically identify harmful content. Much of the work has been done for the English language. However, only a few approaches have been taken to classify toxic comments in the Bangla language. A multi-label classification technique for Bangla comments is offered in the study that follows to classify the numerous toxic comments into six categories: Toxic, severe toxic, obscene, threat, insult, and identity hate, and also measure the severity of these comments. For the experiment, we compiled a dataset of 12634 comments from TikTok and other sources. By incorporating knowledge from earlier proposed studies, the proposed classification model was developed utilizing deep learning techniques, specifically Long Short-Term Memory (LSTM) and Long Short-Term Memory-Convolutional Neural Networks (LSTM-CNNs), as well as word embeddings and obtained a maximum accuracy of 83.66% and 1.61 MSE loss for the severity measure.11https://***/imbodrulalam/Toxic-Comment-Detection-BN © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Decomposition Algorithm for Security-Constrained Unit Commitment with AC Optimal Power Flows

Decomposition Algorithm for Security-Constrained Unit Commit...

引用

IEEE Texas Power and Energy Conference (TPEC)

作者： Weihang Ren Mingze Li Lei Fan Yongpei Guan Dept. of Industrial and Systems Engineering University of Florida FL USA Dept. of Electrical and Computer Engineering University of Houston TX USA Engineering Technology University of Houston TX USA

ISBN: (数字)9798331541125

ISBN: (纸本)9798331541132

This paper presents a comprehensive approach to solving the security-constrained unit commitment with alternating current power flows (SCUC-ACPF) problem in contemporary power systems. We introduce algorithms that decompose the problem into subproblems suitable for specialized solvers, so that the large-scale mixed-integer nonlinear program-ming SCUC-ACPF problem can be solved. In case studies, we validate the efficiency and effectiveness of our algorithms on synthetic and industry-scale power system networks.

关键词： Runtime Scalability Power systems Planning Security Optimization AC power transmission Load flow

来源：评论

学校读者我要写书评

暂无评论

Bi-Directional LSTM Classification of Emotions in EEG Signals

Bi-Directional LSTM Classification of Emotions in EEG Signal...

引用

2022 International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2022

作者： Nand, Ashley Jebadurai, Immanuel Johnraja Jeremiah, Ocheni Leelipushpam Paulraj, Getzi Jeba Jebadurai, Jebaveerasingh Karunya Institue of Technology and Science Dept. of Computer Science and Engineering Coimbatore India Government Polytechnique College Dept. of Computer Science and Engineering Tanjore India

ISBN: (纸本)9781665489621

In the field of neuroscience research, the analysis of EEG signals is crucial for comprehending both human behavior and the workings of the brain. The majority of research is being done to find out how EEG signals are usually used to distinguish between various psychological states and emotions. The proposed study has applied the Bi-LSTM approach for emotion categorization, which significantly raises the accuracy of emotion categorization based on the brain waves obtained from EEG. The results show that the system is reliable as the data has been trained by using a variety of classifiers but with the DEAP dataset, the proposed method obtains a higher and quicker accuracy rate with a training period of about 5ms and an average accuracy rate of 94.12%, and is working to classify the emotion such as valence, arousal, and dominance with single electrode channel with the highest accuracy. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

FusedMAC Framework Analysis for Enhanced Animal Condition Monitoring

FusedMAC Framework Analysis for Enhanced Animal Condition Mo...

引用

International Conference on electrical, computer and Communication engineering (ECCE)

作者： Al Rafi Aurnob M D Rokon Islam Emon Tonmoy Mohajan Dipta Barua Rupom Razzaque Kamruddin Nur Dept. of Computer Science American International University-Bangladesh Dhaka Bangladesh Dept. of Electrical and Electronic Engineering Chittagong University of Engineering and Technology Chittagong Bangladesh Dept. of Computer Science & Engineering International Islamic University Chittagong Chittagong Bangladesh School of Electrical Engineering and Computer Science Queen Mary University of London London United Kingdom

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

The integration of advanced technologies especially with machine learning has the potential to revolutionize animal condition monitoring by improving animal welfare and health status through comprehensive condition monitoring across the agricultural and veterinary domains as well as wildlife conservation. This study focuses on Multiple Additive Regression Trees (MART) and CatBoost as well as the fusion techniques. The proposed FusedMAC framework analyzes complex and high-dimensional data. Stacking fusion techniques aim to provide a comprehensive understanding of animal conditions by integrating diverse data modalities. Also, the use of the explainable artificial intelligence (XAI) methods, called SHAP (Shapley Additive Explanations). This technique ensures the transparency and interpretability of the model’s predictions. Our proposed approach addresses key gaps in previous research, including the need for advanced machine learning integration, robust data fusion and real-world validation. This study contributes to more effective animal management practices by enhancing predictive accuracy and interpretability. Ultimately, improving animal welfare and health outcomes.

关键词： Condition monitoring Additives Animals High dimensional data Prevention and mitigation Wildlife Stacking Data integration Predictive models Regression tree analysis

来源：评论

学校读者我要写书评

暂无评论

Characterization and Control of a Superconducting Homopolar Motor with Cryogenic GaN Inverter for Electric Aircrafts

Characterization and Control of a Superconducting Homopolar ...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Gliese, Felix Pearce, Matthew G. S. Wadsworth, Aaron Siamaki, Mohammad Storey, James Lumsden, Grant Thrimawithana, Duleepa J. Badcock, Rod Roth-Stielow, Joerg Neuburger, Martin Esslingen University Faculty of Mobility and Technology Germany The University of Auckland Dept. of Electrical Computer and Software Engineering New Zealand OpenStar Technologies New Zealand Victoria University of Wellington Robinson Research Institute New Zealand University of Stuttgart Institute for Power Electronics and Electrical Drives Germany

ISBN: (纸本)9798350376067

In the quest for a zero-emissions future, the aviation sector is facing the challenge of reducing its carbon footprint. This paper presents a characterization of a superconducting homopolar motor designed to meet the stringent power and efficiency requirements of all-electric aircraft. The control system, which features field-oriented control and a multi-layer architecture, ensures precise operation of the motor under various load conditions. The motor uses a stationary cryogenic superconducting DC coil to generate the rotor's magnetic field. Utilizing superconducting materials helps produce the high power densities critical for aviation. The characterization of the key parameters of the motor, such as inductances, stator resistance and flux, are presented. A description of the cryogenic GaN power electronic inverter power stage immersed in liquid nitrogen is provided. This design enables future integration next to the motor, and improved power density and efficiency. This paper outlines the design, implementation, and initial testing of the superconducting homopolar motor and its power electronics, highlighting its potential for electric propulsion in aviation by providing a viable solution for long-range flights. © 2024 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

A Preprocessing Method for Security-Constrained Unit Commitment with AC Power Flows

A Preprocessing Method for Security-Constrained Unit Commitm...

引用

IEEE Texas Power and Energy Conference (TPEC)

作者： Mingze Li Weihang Ren Lei Fan Yongpei Guan Dept. of Electrical and Computer Engineering University of Houston TX USA Engineering Technology University of Houston TX USA Dept. of Industrial and Systems Engineering University of Florida FL USA

ISBN: (数字)9798331541125

ISBN: (纸本)9798331541132

This paper presents a preprocessing method to solve the security-constrained unit commitment with AC power flows (SCUC-ACPF), which is a large scale mixed-integer non-convex, nonlinear optimization problem. We introduce clustering algorithms and local search to reduce problem complexity, and obtain local optimal solutions within limited solving time and computational capacity. The clustering algorithms group buses into manageable clusters centered around core buses, creating smaller sub-grids for efficient optimization. The local search algorithms iteratively explore and improve solution quality. Our method ensures balanced clusters that respect physical and operational constraints, significantly enhancing optimization efficiency and contributing to more effective grid management and operation.

关键词： Heuristic algorithms Clustering methods Clustering algorithms Search problems Boundary conditions Power grids Complexity theory Optimization AC power transmission

来源：评论

学校读者我要写书评

暂无评论

Study on ESS maximum capacity calculation and operation algorithm based on load pattern of substations in urban railway

引用

Transactions of the Korean Institute of electrical Engineers 2021年第9期70卷 1405-1412页

作者： Yun, Chi-Myeong Cho, Gyu-Jung Kim, Hyungchul Kim, Chul-Hwan Jung, Hosung Smart Electrical & Signaling Division Korea Railroad Research Institute Korea Republic of Dept. of Transportation Engineering Korea University of Science and Technology Korea Republic of Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In this paper, we introduce the method of reducing only the morning peak of the ESS and the method of calculating the maximum ESS capacity according to the method of reducing the entire day by using the characteristic that the load of the urban railway substation shows a different load pattern depending on weekdays, weekends, and holidays. Furthermore, an operation method suitable for urban railroad is introduced using the operation algorithm for each of the five points of time of the ESS according to the load pattern. To verify the introduced maximum capacity calculation method and ESS operation algorithm, power analysis program, PSCAD/EMTDC was used. Copyright © The Korean Institute of electrical Engineers.

关键词： Cost reduction

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：