检索结果-内蒙古大学图书馆

2024 IEEE international conference on Control Science and systems Engineering, ICCSSE 2024

作者： Li, Enshi Zhou, Li Zhu, Yan National Space Science Center of Chinese Academy of Sciences Bejing China

ISBN: (纸本)9798331517199

Due to the limitations of spacecraft data processing capabilities and the data transmission rate to the ground, the image compression system is essential for imaging payloads on satellites. JPEG2000, with its advantages of high compression ratio, high signal-to-noise ratio, support for progressive transmission, and absence of mosaic distortion, is a preferred algorithm for image compression in spaceborne cameras. In response to the complexity of the JPEG2000 algorithm and the challenges of hardware implementation, this paper presents an image compression system based on the ADV212 image compression chip for realizing JPEG2000 compression. The FPGA is utilized for image buffering and control of the compression system, while the ADV212 chip performs the compression functions. The experimental results validate the high performance and compatibility of the system. This system boasts advantages such as simple hardware and software implementation, high efficiency, superior performance, short development cycle, and low cost, which makes it suitable for aerospace applications, particularly in commercial space satellites. © 2024 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Detection Method for Loose Points in Transformer Iron Cores based on MTF and CNN

Detection Method for Loose Points in Transformer Iron Cores ...

引用

international conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Xu, Weijie Ding, De Zhang, Changgeng Environmental Protection Technique Center Co. Limited Shaanxi China Hebei University of Technology Tianjin China

ISBN: (纸本)9789819618552

The vibration signal of the transformer core is closely related to its mechanical state, and exploiting this characteristic enables the detection of loosening points in the transformer core. This paper proposes a method for detecting loosening points in the transformer core based on Markov Transition Field (MTF) and Convolutional Neural Network (CNN). Firstly, the initial vibration signal of the transformer core is decomposed using Ensemble Empirical Mode Decomposition (EEMD), and suitable components are selected for signal reconstruction to eliminate interference from the transformer itself and the external environment. Subsequently, the reconstructed signal’s MTF image is obtained through MTF transformation. Finally, the MTF image is utilized as the input for CNN to accomplish the detection of loosening points in the transformer core. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Research on the design and implementation of ultra-short baseline positioning algorithm based on a five-element array

Research on the design and implementation of ultra-short bas...

引用

2024 international conference on image, signal Processing, and Pattern Recognition, ISPP 2024

作者： Xu, Junshuai Zhang, Youwen Tu, Shumin Huang, Wei Ocean College Jiangsu University of Science and Technology Jiangsu Province Zhenjiang212100 China School of Underwater Acoustic Engineering Harbin Engineering University Heilongjiang Province Harbin150001 China Laboratory of Low Frequency Electromagnetic Communication Technology The WMCRI CSSC Hubei Province Wuhan430000 China

ISBN: (纸本)9781510680425

The ultra-short baseline (USBL) acoustic positioning systems, characterized by their compactness and ease of installation, are extensively employed to augment efficiency in marine engineering tasks. Nevertheless, the diminutive size of USBL systems inherently leads to escalated positioning inaccuracies as the operational range expands. Conventional positioning systems based on ternary and quaternary arrays are compromised by suboptimal positioning accuracy and inadequate robustness. While adopting more intricate array configurations, such as three-dimensional arrays, or an increased number of elements, such as octonary arrays, can enhance the system's accuracy and reliability, such measures inevitably raise the hardware requirements and computational demands. In response to the dichotomy between the need for precision and computational efficiency, this study introduces a novel five-element planar array USBL positioning approach. Executed on a low-power, fixed-point TI TMS320C6416T digital signal processor (DSP), this five-element array positioning algorithm adeptly mediates between the requisites for high positioning accuracy, manageable computational complexity, and affordability. Experimental outcomes from controlled pool tests affirm that the devised scheme attains a positioning accuracy of 0.6%, illustrating its efficacy and potential applicability in marine engineering endeavors. © 2024 SPIE.

关键词： Precision engineering

来源：评论

学校读者我要写书评

暂无评论

Real-Time signal Processing in IoT-based Embedded systems Using Hybrid AI-Enhanced Edge Computing

Real-Time Signal Processing in IoT-Based Embedded Systems Us...

引用

2024 international conference on Artificial Intelligence and Quantum Computation-based Sensor Applications, ICAIQSA 2024

作者： Rajan, Chozha P. Ahmed, A. Sarfaraz Divya, Vyshnava Nagendar, Y. Mohan, Ashwala Atheeswaran, Athiraja Bannari Amman Institute of Technology Department of AIDS Tamilnadu Erode India Sri Eshwar College of Engineering Department of CSE Tamil Nadu Coimbatore India Malla Reddy College of Engineering Department of CSE Hyderabad India SR University Department of School of Computer Science and Artificial Intelligence Telangana Warangal India Guru Nanak Institutions Technical Campus Department of ECE Telangana Ranga Reddy India Hyderabad India

ISBN: (纸本)9798331517953

The rapid expansion of the internet of Things (IoT) has necessitated real-time signal processing capabilities in embedded systems, but traditional cloud-based models often fall short in meeting the low-latency demands of these applications. To address this, we propose a hybrid AI-enhanced edge computing framework that integrates machine learning with conventional signal processing techniques, optimizing real-time processing at the edge. Our framework was tested in a smart factory environment, where edge devices equipped with lightweight AI models were employed for signal classification and processing tasks. The results demonstrate a 40% reduction in latency, with processing times as low as 50 milliseconds per signal, and an accuracy improvement of 15% over traditional methods, achieving a 92% accuracy rate in signal classification. These findings underscore the potential of hybrid AI at the edge to significantly enhance both the speed and accuracy of real-time signal processing in IoT-based embedded systems. This approach not only meets the critical latency requirements of modern IoT applications but also improves overall system reliability, making it a promising solution for applications in smart manufacturing, healthcare, and autonomous systems. Future work should explore further optimization of AI models for edge deployment and scalability across broader IoT ecosystems. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Protecting the Privacy of Face by De-Identification Pipeline based on Deep Learning 16

Protecting the Privacy of Face by De-Identification Pipeline...

引用

16th international conference on signal-image technology and internet-based systems (SITIS)

作者： Parashar, Anubha Parashar, Apoorva Rida, Imad Aski, Vidyadhar Manipal Univ Jaipur Dept Comp Sci & Engn Jaipur India Mahindra Integrated Business Solut Emerging technol Mumbai India Univ Technol Compiegne Ctr Recherches Royallieu Compiegne France Emerging technol Mahindra & Mahindra Mumbai India

ISBN: (纸本)9781665464956

In this research, we offer a face de-identification process that is reversible and alters both the face's geometry and its texture. There are fourteen parameters that are employed for the change of the geometry. The usage of a fixed face texture template is required for texture change. We have explored how the capacity of people and robots to identify faces is affected when different geometrical and surface adjustments are made to components of the face such as the eyes, eyebrows, nose, and lips. The studies using crowdsourcing and machine face recognition were carried out on photographs of well-known persons that were obtained from the internet. The findings collected from both kinds of research indicated that alterations to a person's facial geometry (form) are less influential on the amount of privacy protection than changes to that person's face texture.

关键词： Face de-identification Face recognition Affine transformation Face geometry modification Face texture modification Psychological experiments

来源：评论

学校读者我要写书评

暂无评论

Ontology for Contextual Fake News Assessment based on Text and images 32

Ontology for Contextual Fake News Assessment based on Text a...

引用

32nd Euromicro international conference on Parallel, Distributed and Network-based Processing (PDP)

作者： Chandrasekaran, K. Kandasamy, A. Venkatesan, M. Prabhavathi, P. Gokuldhev, M. Aishwarya, C. NITK Surathkal CSE Dept Surathkal India NIT Puducherry CSE Dept Pondicherry India VIT Vellore CSE Dept Vellore India VelTech Univ CSE Dept Chennai India

ISBN: (纸本)9798350363074;9798350363081

The spread of false news on social networks is a major challenge in the digital age across various sectors, encompassing technology, politics, public health, and finance. This paper introduces an ontology-based method that combines text and image analysis to evaluate the accuracy of news stories in the context of social media. We investigate the role of social engineering tactics in crafting and dispersing fake news and advocate for a comprehensive multi-contextual perspective that covers content, source, social media, psychological, and impact aspects. Using OWL (Web Ontology Language), we present an ontology framework for assessing fake news, providing a structured approach to analyze text, visuals, audio, audience behavior, source credibility, and news propagation patterns. This framework serves as a foundation for advanced detection systems, contributing to the fight against digital misinformation.

关键词： Fake news Contextual Social Engineering OWL Ontology Data Analysis Audience Behavior Source Credibility Quantum Machine Learning Quantum Deep Learning

来源：评论

学校读者我要写书评

暂无评论

A presentation attack detection network based on dynamic convolution and multi-level feature fusion with security and reliability

引用

FUTURE GENERATION COMPUTER systems-THE international JOURNAL OF ESCIENCE 2023年第1期146卷 114-121页

作者： Cheng, Xin Zhou, Jingmei Zhao, Xiangmo Wang, Hongfei Li, Yuqi Changan Univ Sch Informat Engn Xian 710064 Peoples R China Minist Publ Secur Traff Management Res Inst Wuxi 214151 Peoples R China Changan Univ Sch Elect & Control Engn Xian 710064 Peoples R China Xian Technol Univ Sch Elect Informat Engn Xian 710021 Peoples R China

In the internet of Things environment, most facial recognition systems are highly susceptible to face spoofing attacks. To increase the security and reliability of such systems, this paper proposes an anti-spoofing method for facial recognition systems based on optical flow and texture features. The spoofing-detection algorithm first generates the optical flow field map of the face area using the optical flow method and a face-detection method, based on two consecutive frames of the captured face video. Then, the original RGB face area image and optical flow field map are input into a two-channel convolutional neural network to extract and fuse the features of the face. Finally, based on the optical flow and texture features, this method classifies real and fake faces. In addition, to better generate the optical flow field map containing liveness information, a motion amplification algorithm is applied to enhance the 0.04-0.4 Hz signal in the video frame by 20 times. For texture and optical flow presentation, we propose a lightweight network with dynamic convolution and multi-level feature fusion blocks. This paper used the Replay Attack spoofing dataset from IDIAP, consisting of 1300 videos, for model training, verification, and testing. Experiments showed that the algorithm proposed in the paper performed well on the Replay Attack data set and achieved a half total error rate of 0.66%.(c) 2023 Elsevier B.V. All rights reserved.

关键词： internet of Things Face fraud detection Deep learning Optical flow Dynamic convolution Featurefusion

来源：评论

学校读者我要写书评

暂无评论

Passive Location Model of UAV based on Geometric Derivation and Genetic Algorithm 24

Passive Location Model of UAV Based on Geometric Derivation ...

引用

2024 2nd international conference on internet of Things and Cloud Computing technology, IoTCCT 2024

作者： Liao, Shihao Zhou, Pinlin Marine Engineering College Dalian Maritime University Dalian China School of Maritime Economics and Management Dalian Maritime University Dalian China

ISBN: (纸本)9798400710148

In this paper, a location method of bearing-only UAV based on passive location principle is proposed. First of all, on the basis of establishing the relative plane Cartesian coordinate system, a threepoint positioning model is established by geometric derivation, so that the UAV can locate passively when only the angle information is received. The reliability of the model is verified by Monte Carlo simulation. Secondly, by analyzing the relationship between the polar diameter variation range of the signal receiver and the circumferential angle, the minimum number of UAV is determined. In addition, the genetic algorithm with uniform mutation factor is used to optimize the solution, and the root mean square error between the actual position and the standard position of the UAV is minimized as the fitness function. Finally, through the iterative optimization method, the specific position adjustment scheme of UAV is obtained, and the effective positioning of UAV is realized. This study provides a theoretical reference for the actual UAV formation. © 2024 Copyright held by the owner/author(s).

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Content based image Retrieval System Using CNN based Deep Learning Models 2

Content Based Image Retrieval System Using CNN based Deep Le...

引用

2nd international conference on Machine Learning and Data Engineering, ICMLDE 2023

作者： Gautam, Giriraj Khanna, Anita Dept. of Electronics and Communication Engineering Guru Ghasidas Vishwavidyalaya Koni Bilaspur495009 India

Digital information search archives on the internet and other platforms have been an essential part of our daily lives. With the use of huge amounts of digital images, it is paramount to develop efficient solutions to retrieve images seamlessly. Due to inadequate textual description, the task of automated image retrieval is quite complicated. Therefore, retrieval of images by analysing their visual content is an exciting task and research-worthy. Text based image Search (TIBR) is time consuming as initially, every image has to be linked with a keyword or text to be extracted on query search. In the proposed system, an efficient algorithm for Content based image Retrieval (CBIR) using pre-trained CNN-based Deep Learning models to extract deep features of an image has been developed, which significantly increases the performance of the image retrieval process. Convolutional Neural Networks (CNN) has evolved as an efficient deep learning solution for the CBIR systems that work in image recognition applications. The results of retrieval are evaluated in terms of precision performance parameters. Emphasis has been given to the comparison of the efficiency of the system using two different pre-trained CNN-based Deep Learning models based on VGG16 and ResNet-50 architecture. Transfer learning enables us to develop robust and efficient working systems using pre-trained models. In the proposed system, pre-trained models have been used to derive features using a deep learning CNN network trained for a large image classification dataset imageNet. This approach outperforms many contemporary CBIR systems. As most CBIR systems depend on query images and as most users of such systems are non-professional, we have developed a user interface for the built prototype systems. The efficiency of the CBIR systems with pre-trained models VGG16, and ResNet-50 are compared for better image retrieval and reliability. The proposed system has addressed a few existing problems in CBIR system de

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of rhubarb processing control system based on internet of Things 4

Design of rhubarb processing control system based on Interne...

引用

4th international conference on Telecommunications, Optics, and Computer Science, TOCS 2023

作者： Sun, Lijuan Wei, Jiansheng Li, Xiangwei Zhao, Xiaoqiang Tang, Jiawei School of Computer Science and Artificial Intelligence Lanzhou Institute of Technology Lanzhou730000 China Li County Rhubarb technology Co. LTD Gansu province Li County Industrial Park Longnan Longnan730000 China

ISBN: (数字)9781510679849

ISBN: (纸本)9781510679832

In order to improve the processing quality of traditional Chinese medicine rhubarb and control the processing process of rhubarb in real time, a programmable logic control system with Ethernet and internet of things remote communication function was designed, and the corresponding programming software and configuration software were developed, which had important engineering application value for the transformation and upgrading of traditional processing equipment of rhubarb. In this paper, based on 5G Narrowband internet of Things (NBiot) technology and industrial Ethernet technology, a programmable logic control system with remote wireless communication function is designed, and the supporting programming software platform is developed to connect to the cloud wireless network. The research results were tested in Li County Rhuai technology Co., LTD. The rhuai production yield was increased by 30%, the processing quality was effectively improved, and the effectiveness of the rhuai processing process control was guaranteed. In addition, the results can provide reference for the research and development of intelligent control systems in traditional Chinese medicine preparation industry, and realize the large-scale and industrialized development of traditional Chinese medicine processing equipment. © 2024 SPIE.

关键词： internet of things

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：