检索结果-内蒙古大学图书馆

Deep Learning Based Camera Switching for Sports Broadcasting 1

5th International Conference on Machine Learning for Networking, MLN 2022

作者： Tohidypour, Hamid Reza Wang, Yixiao Pourazad, Mahsa T. Nasiopoulos, Panos Heir, Gurpreet Ibikunle, Derinsola Li, Anthony Saleem, Fawaz Ahmed Luo, Zhaobang Department of Electrical and Computer Engineering University of British Columbia Vancouver Canada

ISBN: (数字)9783031361838

ISBN: (纸本)9783031361821

Switching camera views when broadcasting sport games is essential for improved quality of viewing experience. Traditionally, expensive equipment and a broadcast director are employed to choose the optimal camera view during the game. In this study, we propose a novel deep learning based method to automatically switch between cameras based on importance of the scene detected in each view. Here, in order to show the validity of our approach, we chose to train our network for ice hockey, as the network needs to be retrained for each sport, using a dataset that corresponds to the specific game. Our method uses a YOLOv4 model that accurately detects the important objects for ice hockey, namely players, puck, net, goalie, and referee. Our novel camera switching view scheme uses the confidence values of the detected objects and temporal tracking to choose the most important camera view for that instance. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Millimeter- Wave Vehicle-to-Infrastructure Communications for Autonomous Vehicles: Location-Aided Beam Forecasting in 6G 16

Millimeter- Wave Vehicle-to-Infrastructure Communications fo...

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Makadia, Omikumar B. Patel, Dhaval K. Shah, Kashish D. Raval, Mehul S. Zaveri, Mukesh Merchant, S.N. School of Engineering and Applied Science Ahmedabad University India Svnit Department of Computer Science and Engineering Gujarat Surat India Iit Bombay Department of Electrical Engineering Mumbai Powai India

ISBN: (纸本)9798350383119

The rise of autonomous vehicles has generated substantial interest due to their potential to transform transportation, enhance safety, and reduce traffic congestion in urban areas. This research investigates strategies to facilitate communication among various elements in driving environments, such as vehicles, pedestrians, and emergency responders, primarily focusing on vehicle-to-infrastructure (V2I) communication. Furthermore, advancements in wireless technology, including 6G and millimetre waves, offer improved connectivity but face challenges in signal propagation. The study emphasizes the importance of beam-forming as a solution, exploring alternative, resource-efficient methods to predict optimal signal directions using user positions. Positive simulation results suggest real-world applicability, and the study addresses critical questions about utilizing future positions and their impact on overhead complexity. This research provides valuable insights into position-based approaches for enhancing wireless communication in autonomous driving scenarios. © 2024 IEEE.

关键词： 6G Autonomous vehicles beam prediction overhead complexity training overhead

来源：评论

学校读者我要写书评

暂无评论

Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task 8

Quantized and Interpretable Learning Scheme for Deep Neural ...

引用

8th IEEE International Conference on Information and Communication Technology, CICT 2024

作者： Maleki, Alireza Lavaei, Mahsa Bagheritabar, Mohsen Beigzad, Salar Abadi, Zahra University of Tehran Department of Technology Management Tehran Iran Electrical and Computer Engineering University of Tehran Tehran Iran University of Cincinnati Electrical Engineering Department Ohio United States Software and Engineering University of St. Thomas Minnesota MN United States Tehran University Electrical Engineering Department Tehran Iran

ISBN: (纸本)9798331531539

Deep learning techniques have proven highly effective in image classification, but their deployment in resource-constrained environments remains challenging due to high computational demands. Furthermore, their interpretability is of high importance which demands even more available resources. In this work, we introduce an approach that combines saliency-guided training with quantization techniques to create an interpretable and resource-efficient model without compromising accuracy. We utilize Parameterized Clipping Activation (PACT) to perform quantization-aware training, specifically targeting activations and weights to optimize precision while minimizing resource usage. Concurrently, saliency-guided training is employed to enhance interpretability by iteratively masking features with low gradient values, leading to more focused and meaningful saliency maps. This training procedure helps in mitigating noisy gradients and yields models that provide clearer, more interpretable insights into their decision-making processes. To evaluate the impact of our approach, we conduct experiments using famous Convo-lutional Neural Networks (CNN) architecture on the MNIST and CIFAR-10 benchmark datasets as two popular datasets. We compare the saliency maps generated by standard and quantized models to assess the influence of quantization on both interpretability and classification accuracy. Our results demonstrate that the combined use of saliency-guided training and PACT-based quantization not only maintains classification performance but also produces models that are significantly more efficient and interpretable, making them suitable for deployment in resource-limited settings. © 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

BAMTGAN: A Balanced Augmentation Technique for Tabular Data 9

BAMTGAN: A Balanced Augmentation Technique for Tabular Data

引用

9th International Conference on Applied System Innovation, ICASI 2023

作者： Jeong, Jueun Jeong, Hanseok Kim, Han-Joon University of Seoul Department of Electrical and Computer Engineering Seoul Korea Republic of

ISBN: (纸本)9798350398380

This paper presents BAMTGAN, a novel data augmentation technique that addresses the class imbalance problem and prevents mode collapse by utilizing a modified DCGAN model and a new similarity loss to generate diverse and realistic tabular data. BAMTGAN encodes each column to produce a feature map for each record, which is then converted back to its original tabular form an intermediate image format. Experimental results demonstrate that BAMTGAN provides a more substantial improvement in developing high-quality predictive models than existing augmentation methods. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Explainable Machine Learning Method for Open Fault Detection of NPC Inverter Using SHAP and LIME 6

Explainable Machine Learning Method for Open Fault Detection...

引用

6th IEEE Conference on Energy Conversion, CENCON 2023

作者： Gamal Al-Kaf, Hasan Ali Lee, Kyo-Beum Ajou University Department of Electrical and Computer Engineering Suwon Korea Republic of

ISBN: (纸本)9798350325096

Machine learning methods (ML) have been widely used for fault detection of NPC inverters. However, ML methods such as deep neural networks or ensemble models often act as black boxes, making it challenging to identify critical factors that significantly affect the performance of these models. The lack of interpretability in these models can be a drawback, especially when there is a need to understand the underlying factors driving their predictions for fault detection of NPC inverter. To address this challenge, there is a need for more reliable and trustworthy ML model. Therefore, this study focuses on analyzing the importance of features for open fault detection using Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive explanations (SHAP). SHAP and LIME are popular techniques used to provide interpretability and explainability in machine learning models. The simulation results show that SHAP and LIME methods can identify and analyze the most important features of the open fault of the NPC inverter. © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Wideband Fat Dipole Antenna Integrated with Solar Cells for Internet of Things Applications

A Wideband Fat Dipole Antenna Integrated with Solar Cells fo...

引用

2023 IEEE International Symposium on Antennas and Propagation, ISAP 2023

作者： Wang, Heesu Ali, Ahmed Park, Ikmo Department of Electrical and Computer Engineering Ajou University Suwon Korea Republic of

ISBN: (纸本)9798350341140

This paper presents a solar cell–integrated wideband fat dipole antenna. Implementing a dipole antenna with a solar cell provides dual functionality that simultaneously enables energy harvesting and wireless communication. RF decoupler circuits are used to operate the antenna and the solar cell independently. The proposed design uses a fat dipole structure incorporating a wide dipole arm and a pair of open stubs. These features make the antenna have wideband characteristics and a high-form factor. The proposed solar cell integrated antenna has overall dimensions of 102 mm × 52 mm × 0.571 mm (0.333 λo × 0.170 λo × 0.0019 λo at 0.98 GHz). It exhibits a –10 dB impedance bandwidth of 105% (ranging from 0.98 to 3.18 GHz), a form factor of 96%, and an optical transparency of 100%. © 2023 IEEE.

关键词： dipole antenna integrated antenna solar cell antenna wideband antenna

来源：评论

学校读者我要写书评

暂无评论

EDI-Driven Multi-Dimensional Resource Allocation for Inclusive 6G Communications

IEEE Networking Letters

引用

IEEE Networking Letters 2023年第2期5卷 110-114页

作者： Han, Wudan Wang, Xianbin Mei, Jie Western University Department of Electrical and Computer Engineering LondonONN6A 5B9 Canada

This letter proposes a novel inclusive multi-dimensional resource allocation scheme for diverse 6G communications driven by the principle of Equity, Diversity, and Inclusion (EDI). In coping with challenges of ever-increasing device diversity and application Quality-of-Service (QoS) heterogeneity, the proposed scheme can inclusively support all users with equitable service provisioning satisfaction level and flexible multiple access. By jointly considering user-specific communication requirements and scenario-dependent resource utilization cost, we aim to maximize the average user utility while minimizing its distribution variance. Simulation demonstrates the proposed scheme can inclusively provide equitable user QoS satisfactions by higher average utility with smaller disparity and inequality. © 2019 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Obfuscated Malware Detection Using Artificial Neural Network (ANN) 5

Obfuscated Malware Detection Using Artificial Neural Network...

引用

5th IEEE International Conference on electrical, computer and Communication Technologies, ICECCT 2023

作者： Khan, Lamia Parven North South University Department of Electrical and Computer Engineering Dhaka Bangladesh

ISBN: (纸本)9781665493604

Thinking about life without using the internet is impossible. Internet and network have become a part of our daily life. Sharing confidential information through internet and doing lots of important and confidential official work is done easily by using internet. One side internet has made life easy and another side is it cheap and fast compare to other methods such as letter or fax. With the growing technology some third party cybercriminals and hackers are trying to use the internet for their personal gain and harm the users or organizations. Malware is one of those malicious software whose sole purpose is to harm the user, system or organization and steal information and sent it to third party for harmful use. It is necessary to find this malicious software and prevent them from harming through the internet. The proposed model detects the harmful malware lurking on the internet and prevent the user and system from any potential harmful effect. The model is very simple and cost effective yet very efficient. the accuracy of the model is 99.72%. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Debugging approach for IEC 61499 control applications in FBME 32

Debugging approach for IEC 61499 control applications in FBM...

引用

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Akifev, Daniil Liakh, Tatiana Ovsiannikova, Polina Sorokin, Radimir Vyatkin, Valeriy Lulea Tekniska Universitet Department of Computer Science Computer and Space Engineering Sweden Aalto University Department of Electrical Engineering and Automation Espoo Finland

ISBN: (纸本)9798350399714

With the increase in the use of distributed control systems in industrial automation, it is becoming more challenging to analyze the behavior of the system to evaluate its quality. The lack of data coming from the system during operation also complicates debugging and error finding in the system software. The paper presents a quality control method of IEC 61499 industrial control software. The proposed method is based on a combination of several techniques: monitoring of the system behavior, recovering missing data with a simulator, and explanation of the recovered traces by highlighting a sequence of events that led to the explored state of the system. The paper integrates the method into modular IDE for IEC 61499 applications FBME. We also demonstrate the method on a simple example. © 2023 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Vessel Segmentation Technique Using LTP and PCA 4

Unsupervised Vessel Segmentation Technique Using LTP and PCA

引用

4th International Conference on Communication Technologies, ComTech 2023

作者： Faridoon, Fatima Khan, Khurram Umair, Mir Yasir Mahmood, Zahid COMSATS University Department of Electrical and Computer Engineering Abbottabad Islamabad Pakistan GIK Institute of Engineering Sciences and Technology Faculty of Computer Science and Engineering KPK Topi Pakistan National University of Sciences and Technology Department of Electrical Engineering Islamabad Pakistan

ISBN: (纸本)9798350337211

This paper presents a retinal vessels segmentation method than can be used by the ophthalmologists to diagnose different retinal diseases, such as thickening, thinning, or splitting. The proposed method consists of various interconnected steps. Initially, the G-channel is isolated from the input colored RGB image. Later, the Principal Component Analysis (PCA) is applied on the Green channel. Next, the Local Ternary Pattern (LTP) is used that feeds the processed image to the Morphological Filter Bank (MFB). The MFB uses various filters, such as spur, majority, and opening operations to segment the vessels image. Simulations are performed on the DRIVE and the STARE datasets. The proposed method yields mean accuracy of 94.07% and 93.45% on DRIVE and STARE datasets, respectively. Moreover, the proposed method is computationally less complex as compared to the few published methods. © 2023 IEEE.

关键词： Principal component analysis

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：