检索结果-内蒙古大学图书馆

International Baltic Electronics Conference, BEC

作者： Junyi Gu Mauro Bellone Artjom Lind Dep. of Mechanical and Industrial Engineering Tallinn University of Technology Tallinn Estonia FinEst Centre for Smart Cities Tallinn University of Technology Tallinn Estonia Institute of Computer Science University of Tartu Tartu Estonia

ISBN: (数字)9798350365115

ISBN: (纸本)9798350365122

This paper presents the results of a series of machine learning experiments that focus on the domain adaption between different training datasets for autonomous driving. The experiments use a neural network model obtained through transfer learning from the Waymo Open Dataset and then tested with our custom dataset, which was recorded at the TalTech campus in different weather conditions. In this work, we developed a set of tools to extract and process the sensory data from the iseAuto shuttle. The camera and LiDAR sensors of the iseAuto shuttle were calibrated, and the point clouds data of the LiDAR sensor was projected onto the camera plane. We present, here, our publicly available iseAuto dataset which was used for a classification task under adverse weather and low illumination conditions. The iseAuto dataset contains 8000 frames of camera and LiDAR data for traffic object detection and segmentation. We provide ground truth annotations of 2400 frames, in which the object contours were manually labeled out. In addition, we provided the manual-labeled ground-truth segmentations of cars and humans in images, which can be used by the community to test the accuracy of the segmentation of their models. An additional focus of this paper is to demonstrate that with a few custom annotated data, using transfer learning and semi-supervised learning, it is possible to obtain reasonable accuracy on noisy real-world data. The current performance in vehicle segmentation ranges from 65% to 85% in intersection over union (IoU) and between 43% and 60% IoU for pedestrian segmentation in challenging scenarios such as nighttime and rainy weather.

关键词： Point cloud compression Laser radar Accuracy Transfer learning Object segmentation Semisupervised learning Cameras Sensors Autonomous vehicles Meteorology

来源：评论

学校读者我要写书评

暂无评论

Fine modelling and control of three-phase PWM inverter based on average model method 4

Fine modelling and control of three-phase PWM inverter based...

引用

4th International Symposium on Power Electronics and Control engineering, ISPECE 2021

作者： Guo, Yu Dong, Dong Guo, YouGui The Bradley Dep. of Electrical and Computer Engineering Virginia Tech BlacksburgVA24061 United States Automation and Electronic Information College Xiangtan University Xiangtan411105 China

ISBN: (数字)9781510650374

ISBN: (纸本)9781510650367

This paper discusses the fine modelling and control of three-phase PWM inverter by means of average model method. First, the average model method is used step by step to make it easier to read in the power stage design. The second part is the controller design which has the inner current controller and the outer voltage controller to help controlling accurately. Finally, the linear and nonlinear loads were tested respectively on the basis of fine modelling, being meaningful to do the research of nonlinear loads. The simulation results have shown that the average model method is an effective research solution of three-phase PWM inverters, which can be easily generalized to modelling and control of any other PWM inverters. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

Review of Cloud AI for Real-Time Fraud Detection

Review of Cloud AI for Real-Time Fraud Detection

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Gulnara A.Abitova Miras Abalkanov Gulnara A. Abitova Gulnur Shuteyeva Elvira Aitmukhanbetova Korlan Kulniyazova Dep. Computer Engineeering Astana IT University Astana Kazakhstan Dept. Electical Engineering and Computer Science State Univerity of New York at Binghamton Binghamton USA Dept. System Anslysis and Managemnt Eurasian National University Astana Kazakhstan

ISBN: (数字)9798350394245

ISBN: (纸本)9798350394252

The paper presents a comprehensive analysis of the integration of Cloud AI in real-time fraud detection, highlighting significant advancements and practical applications. It is identifying a key challenge such as data privacy and the need for scalable solutions, while also exploring the potential of innovative AI algorithms and strategic partnerships to enhance fraud detection capabilities. Through detailed case studies, the work is demonstrated the effective application of Cloud AI across various sectors. The study concludes that Cloud AI, despite not being a complete solution, plays a crucial role in strengthening fraud detection systems. Our findings suggest that strategic implementation of Cloud AI can lead to more adaptive and efficient systems, thereby significantly contributing to the economic sector's resilience against fraudulent activities. This paper underscores the transformative impact of Cloud AI in fraud detection, offering insights into its future potential and laying the groundwork for further advancements in this field.

关键词： Economics Training Data privacy Technological innovation Scalability Real-time systems Fraud

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Classification by Large-Margin Distance Learning 10

Zero-Shot Classification by Large-Margin Distance Learning

引用

10th International Conference on computer and Knowledge engineering, ICCKE 2020

作者： Reza Zarei, Mohammad Taheri, Mohammad Shiraz University Dep. of Computer Science and Engineering Shiraz Iran

ISBN: (纸本)9781728185668

Zero-Shot Learning (ZSL) has increasingly attained a lot of attentions due to the scalability it provides to recognition models for classifying instances from new classes of which no training data have been seen before. This scalability is achieved by providing semantic information about new classes, which could be obtained remarkably easier, with a lower cost, in comparison with gathering a new training set. In other words, ZSL can be seen as a subset of transfer learning. In this paper, a distance function is learnt in order to discriminate the classes with a customized large-margin loss function. We also propose a nonlinear prototype learning approach by defining a theoretical-based, but simple mapping function to generate the class prototypes from associated semantic information. The instances are compared with the generated prototypes for classification considering the learnt distance function. The evaluations on five widely-used ZSL datasets, illustrate the effectiveness and superiority of the proposed method in comparison with the state-of-the-art ZSL approaches, despite of its simplicity. © 2020 IEEE.

关键词： Distance education

来源：评论

学校读者我要写书评

暂无评论

Discrete cosine transform as universal sentence encoder

arXiv

引用

arXiv 2021年

作者： Almarwani, Nada Diab, Mona Dep. of Computer Science The George Washington University Dep. of Computer Science College of Computer Science and Engineering Taibah University Facebook AI Research

Modern sentence encoders are used to generate dense vector representations that capture the underlying linguistic characteristics for a sequence of words, including phrases, sentences, or paragraphs. These kinds of representations are ideal for training a classifier for an end task such as sentiment analysis, question answering and text classification. Different models have been proposed to efficiently generate general purpose sentence representations to be used in pretraining protocols. While averaging is the most commonly used efficient sentence encoder, Discrete Cosine Transform (DCT) was recently proposed as an alternative that captures the underlying syntactic characteristics of a given text without compromising practical efficiency compared to averaging. However, as with most other sentence encoders, the DCT sentence encoder was only evaluated in English. To this end, we utilize DCT encoder to generate universal sentence representation for different languages such as German, French, Spanish and Russian. The experimental results clearly show the superior effectiveness of DCT encoding in which consistent performance improvements are achieved over strong baselines on multiple standardized datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Sorting Red and Green Chilies by Digital Image Processing

Sorting Red and Green Chilies by Digital Image Processing

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Narumol Chumuang Mahasak Ketcham Thittaporn Ganokratanaa Patiyuth Pramkeaw Jiratha Chongsri Worawut Yimyam Dep. of Digital Media Technology Muban Chombueng Rajabhat University (MCRU) Thailand Dep. of Information Technology Management King Mongkut's University of Technology North Bangkok Thailand Applied Computer Science Program King Mongkut's University of Technology Thonburi Bangkok Thailand Media Technology Program King Mongkut's University of Technology Thonburi Bangkok Thailand Dep. of Business Information Management Phetchaburi Rajabhat University Thailand

The purpose of this research is to help save electricity within organizations and workplaces that use computers. Due to the behavior of general users today, they do not give importance to saving electricity. This work has developed an automatic computer shutdown system. with image processing via a webcam by using image processing techniques (image processing) applied to a webcam by using a webcam to capture the user on the computer screen. Then the images are analyzed and examined with the principles of image processing with the face detection technique using the algorithm of Haar -like features to detect human faces and ROI. define a specific area of interest. The system will then check the amount of inactivity on the screen. or does not show the face image within 10 minutes, the system will automatically turn off the computer. with image processing. This work can make it easier to turn off computers when not in use. and helps to save electricity for the organization or agencies as well.

关键词： computers Technological innovation Webcams Digital images Employment Organizations Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Usage of Blockchain Technology for Improving computer Security

Usage of Blockchain Technology for Improving Computer Securi...

引用

information Technology (ACIT)

作者： Adai Almomani Al Refai Mohammed N Ahmad Aburomman Omar Khair Alla Alidmat Qotadeh Saber Fuad Alshariedeh Mohammed Khouj Department of Computer Science Zarqa University Zarqa Jordan Software Engineering Dep. Zarqa University Zarqa Jordan Department of Data Science and A Zarqa University Zarqa Jordan Department of Electronic Enginnering Univeristy of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Cyber threats have grown increasingly sophisticated, surpassing the capabilities of traditional security measures. Blockchain technology, with its decentralized and immutable structure, offers a potential solution to these challenges. This study examines the role of blockchain tools such as smart contracts, decentralized identity management, and secure data sharing in enhancing cybersecurity. A review of key literature and analysis of survey data from cybersecurity professionals demonstrate blockchain's effectiveness in improving data integrity, access control, and secure communications. The results show significant correlations between the adoption of blockchain technologies and the mitigation of threats like data breaches and unauthorized access. While blockchain presents promising advancements, scalability, regulatory barriers, and energy consumption remain challenges. The study provides valuable insights for researchers, practitioners, and policymakers on how blockchain can be integrated into modern cybersecurity strategies to create more secure digital environments.

关键词： Access control Industries Proof of stake Scalability Smart contracts Data protection Blockchains computer security Identity management systems Business

来源：评论

学校读者我要写书评

暂无评论

Stabilization of THz waves using chaos supremacy

Stabilization of THz waves using chaos supremacy

引用

2023 International Conference on Smart-Green Technology in Electrical and information Systems, ICSGTEIS 2023

作者： Kuwashima, Fumiyoshi Jarrahi, Mona Cakmakyapan, Semih Wada, Kenji Haraguchi, Masanobu Kawakami, Yuki Moriyasu, Takeshi Morikawa, Osamu Kurihara, Kazuyoshi Kitahara, Hideaki Furuya, Takashi Nakajima, Makoto Tani, Masahiko Fukui University of Technology Dep. of Electr. and Electron. Eng. Fukui Japan Ucla Electrical and Computer Eng. Los AngelesCA90095 United States Osaka Metropolitan University Dep. of Physics and Electronics Osaka Japan Tokushima Univ. Industrial and Social Science Grad. Sch. of Tech. Tokushima Japan Fukui Col. Natl. Inst. of Tech. Dep. of Elec. and Inf. Eng. Fukui Japan University of Fukui Faculty of Engineering Fukui Japan Japan Coast Guard Academy Liberal Arts Kure Japan University. of Fukui School of Education Fukui Japan FIR-UF University of Fukui Fukui Japan Osaka Univ. Inst. of Laser Engineering Osaka Japan

ISBN: (纸本)9798350382822

We apply the chaos supremacy of laser chaos system to the high stabilization of THz waves. Stability was demonstrated by down converting the optical beats between laser longitudinal modes in the THz domain to the radio frequency domain and comparing a conventional free running CW laser diode to a chaotically oscillating laser diode. Because of their exceptional stability, chaotically oscillating lasers are attractive options for optical pump sources in terahertz time-domain spectroscopy systems. © 2023 IEEE.

关键词： Stabilization

来源：评论

学校读者我要写书评

暂无评论

Studying of Initial Weight Vector Selection Impact on Transient Performance of Coherent Sidelobe Cancellation System with Gradient Adaptation Algorithm

Studying of Initial Weight Vector Selection Impact on Transi...

引用

2020 IEEE International Conference on Problems of Infocommunications science and Technology, PIC S and T 2020

作者： Pliushch, Oleksandr Toliupa, Serhii Vyshnivskyi, Viktor Rybydajlo, Anatolii State University of Telecommunications Dep. of Mobile and Videoinformational Technologies Kyiv Ukraine Taras Shevchenko National University Dep. of Cyber Security and Information Protection Kyiv Ukraine Ukraine State University of Telecommunications Dep. of Computer Science Kyiv Ukraine Ukraine Center for Military and Strategic Studies of the National Defence University of Ukraine Named after Ivan Cherniakhovskyi Kyiv Ukraine

ISBN: (纸本)9781728191775

Coherent sidelobe canceller is considered as a special case of adaptive antenna arrays. Utilization of the steepest descent algorithm in such a system is studied. It is shown that eigenvectors of the auxiliary channels correlation matrix create two subspaces with so-called primed coordinates, which comprise the principal axes of the quadratic performance surface. The first subspace is formed by the eigenvectors corresponding to the singular eigenvalues, which equal channels' internal noise power, while the second is created by those corresponding to the distinct eigenvalues. Dimension of the second subspace equals the number of the jamming sources. It is proven that, if the initial weight vector is chosen zero, the trajectory of the transient process totally belongs to the second subspace. In this case, transient performance is good. If, for whatever reason, initial weight vector finds itself in the first subspace, the transient performance can be compromised. computer simulation of the adaptive coherent sidelobe canceller has shown that this transient performance degradation can be substantial. Still, it lessens greatly if the number of the auxiliary antennas is much higher than that of the jammers. As a measure to improve performance, it is proposed to set to zero the initial weight vector in the systems with the small number of the auxiliary channels any time interference environment changes. © 2020 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Automatic computer Shutdown with Image Processing via Webcam to Save Energy

Automatic Computer Shutdown with Image Processing via Webcam...

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Narumol Chumuang Mahasak Ketcham Thittaporn Ganokratanaa Patiyuth Pramkeaw Worawut Yimyam Chuamoo Dep. of Digital Media Technology Muban Chombueng Rajabhat University (MCRU) Thailand Dep. of Information Technology Management King Mongkut's University of Technology North Bangkok Thailand Applied Computer Science Program King Mongkut's University of Technology Thonburi Bangkok Thailand Media Technology Program King Mongkut's University of Technology Thonburi Bangkok Thailand Dep. of Business Information Management Phetchaburi Rajabhat University Thailand

The purpose of this research is to help save electricity within organizations and workplaces that use computers. Due to the behavior of general users today, they do not give importance to saving electricity. The researcher has developed an automatic computer shutdown system. with image processing via a webcam By using image processing techniques (Image Processing) applied to a webcam. By using a webcam to capture the user on the computer screen. Then the images are analyzed and examined with the principles of image processing with the Face Detection technique using the algorithm of Haar-like Features to detect human faces and ROI. Define a specific area of interest The system will then check the amount of inactivity on the screen. or does not show the face image within 10 minutes, the system will automatically turn off the computer. with image processing This research can make it easier to turn off computers when not in use. and helps to save electricity for the organization or agencies as well.

关键词： computers Performance evaluation Technological innovation Webcams Organizations Inspection Feature extraction

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：