检索结果-内蒙古大学图书馆

A Fast and High-precision Ellipse detection Method Based on the Candy's Theorem

IEEE ACCESS 2023年 11卷 102971-102980页

作者： Fang, Xiujun Zhang, Enzheng Li, Bingchen Zhai, Bin Zhejiang Sci Tech Univ Sch Mat Sci & Engn Hangzhou 310018 Peoples R China

Ellipse detection is one of the important parts of intelligent manufacturing, and the efficient detection of elliptical contours corresponding to hole parts is the prerequisite before performing practical applications. Aiming at enhancing the efficiency in ellipse detection, a fast and high-precision ellipse detection method based on the Candy's theorem is proposed, in which the constrained simple polygon constraint and the Candy's theorem constraint are used to improve the efficiency of ellipse detection. The theory of the proposed ellipse detection method is described in detail. The comparison experiments with six popular ellipse detection methods are performed based on three public datasets, which are to verify the ellipse detection ability of the proposed method in improving detection speed and precision. And a small hole detection experiment is performed with the constructed experimental setup, which is to verify the effectiveness of the proposed method to detect small holes in practical applications. The proposed method can provide referenced methods and theories in the field of ellipse detection.

关键词： Turning Image edge detection Fitting Transforms Image segmentation Feature extraction Manufacturing detection algorithms The Candy's theorem ellipse detection detection speed detection precision

来源：评论

学校读者我要写书评

暂无评论

High precision and sensitivity detection of gas measurement by laser wavelength modulation spectroscopy implementing an optical fringe noise suppression method

引用

OPTICS AND LASERS IN ENGINEERING 2023年第1期166卷

作者： Cao, Yanan Cheng, Xin Xu, Zong Tiana, Xing Cheng, Gang Peng, Feiyan Wang, Jingjing Anhui Univ Sci & Technol Huainan 232001 Peoples R China West Anhui Univ Luan 237012 Peoples R China Fudan Univ Dept Atmospher & Ocean Sci Shanghai 200433 Peoples R China Shanghai QiZhi Inst Shanghai 200232 Peoples R China

In this work, a novel method to suppress optical fringe noise in the tunable diode laser absorption spectroscopy is proposed and applied to the CH4 gas sensor perturbed by optical fringes for higher detection precision and sensitivity. For the 2(nd) harmonic(2f) signal of 20 ppm CH4 spoiled by optical fringes and random noise, by the novel method, the signal-to-noise ratio (SNR) of the 2 f signal is improved about 6.5 times from 17 to 182 with an optimal averaging spectral range Delta lambda.A similar to 1.5 times improvement in the measurement precision of CH4 is achieved compared to unprocessed raw signal. The corresponding minimum detectable concentration can be improved from 3 ppb down to 0.78 ppb. The corresponding noise equivalent absorption sensitivity (NNEA) and the noise equivalent concentration (NEC) of the system is 6.13 x10 (- 11) cm(- 1) W H-z(- 1/2) and 0.181 ppm, respectively.

关键词： Tunable diode laser absorption spectroscopy Optical fringe noise Optimal averaging spectral range detection precision detection sensitivity

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable high-precision AC voltage detector for aerospace applications

引用

MEASUREMENT 2025年 248卷

作者： Jiang, Leijie Zhu, Lixun Liu, Chuande Hou, Qiankang Changzhou Univ Sch Mech Engn & Rail Transit Changzhou 213164 Peoples R China Changzhou Univ Jiangsu Key Lab Green Proc Equipment Changzhou 213164 Peoples R China Shanghai Maritime Univ Dept Elect Engn Shanghai 201306 Peoples R China Nanjing Univ Informat Sci & Technol Sch Automat Nanjing 210044 Peoples R China

In order to satisfy diversified AC voltage detection requirements in aerospace systems, a reconfigurable and high-precision detector is designed and implemented. The voltage transformation circuit is implemented to convert a high-level voltage signal into a low-level voltage signal. To match the analog input voltage range of the A/D converter, the voltage reference circuit and addition circuit are adopted for converting a lowlevel voltage signal into a non-negative pulsating voltage signal. The detection precision of the instantaneous value and root-mean-square value of the voltage is improved by using a reconfigurable strategy and an error calibration method. Moreover, the composite Simpson's approach is applied to decrease measurement error of the voltage root-mean-square value. The test results show that the detector detection precision can reach +/- 0.015 V for motor voltages at three different speeds. The proposed scheme can be extended to AC voltage acquisition systems for other industrial applications.

关键词： Circuit design Reconfigurable strategy Composite Simpson's approach detection precision BLDC motor

来源：评论

学校读者我要写书评

暂无评论

Supersensitive Novel Detector using Surface Plasmon Resonance Nanostructure Based on Black Phosphorus/Graphene for the Discovery of Various Pathogens in Drinking Water

引用

PLASMONICS 2024年 1-9页

作者： Daher, Malek G. Taya, Sofyan A. Faragallah, Osama S. Alzain, Mohammed A. Almawgani, Abdulkarem H. M. Alzahrani, Ahmad Prajapati, Yogenra Kumar Armghan, Ammar Zyoud, Samer H. Islamic Univ Gaza Phys Dept POB 108 Gaza Palestine Al Aqsa Univ Fac Sci Phys Dept Palestinian Author Gaza Palestine Taif Univ Coll Comp & Informat Technol Dept Informat Technol POB 11099 Taif 21944 Saudi Arabia Najran Univ Coll Engn Elect Engn Dept Najran Saudi Arabia Motilal Nehru Natl Inst Technol MNNIT Allahabad Dept Elect & Commun Engn Prayagraj India Jouf Univ Coll Engn Dept Elect Engn Sakaka 72388 Saudi Arabia Ajman Univ Dept Math & Sci Ajman U Arab Emirates Ajman Univ Nonlinear Dynam Res Ctr NDRC Ajman U Arab Emirates Univ Sains Malaysia Sch Phys George Town 11800 Malaysia

This study assesses a surface plasmon resonance (SPR) sensor using bismuth ferrite and black phosphorus (BPP) to detect pathogens in drinking water. The investigations collected at 632.8 nm, employing angular interrogation and the transfer matrix approach. Tested pathogens include Escherichia coli, Shigella flexneri, Vibrio cholera, and Salmonella flagellin. The sensor's effectiveness depends type on the prism used. Various layer thicknesses are tested, with optimal thicknesses identified as 60 nm for Ag, 9 nm for BiFeO3, and 4 BPP layers. Pathogen detection capabilities vary, with the highest sensitivity achieved against Salmonella flagellin due to its higher RI. Comparatively, using graphene instead of BPP resulted in lower sensitivity, which attributed to graphene's high imaginary part of RI. This sensor stands out against recent SPR sensors, offering superior performance, its easy construction and the properties of its constituent materials. The SPR sensor offers a simple, adjustable configuration with nanoscale dimensions, enhancing its efficacy as a biological sample detector.

关键词： Plasmonic surface resonance Microbial agents Matrix transfer approach Biological sensor detection precision

来源：评论

学校读者我要写书评

暂无评论

Human elbow flexion behaviour recognition based on posture estimation in complex scenes

引用

IET IMAGE PROCESSING 2023年第1期17卷 178-192页

作者： Gong, Faming Li, Yunjing Yuan, Xiangbing Liu, Xin Gao, Yating China Univ Petr East China Coll Comp Sci & Technol Qingdao 266580 Peoples R China Sinopec Gtp Offshore Oil Prod Plant Dongying Peoples R China

Aiming at the difficulty of recognising the smoking and making phone calls behaviours of people in the complex background of construction sites, a method of recognising human elbow flexion behaviour based on posture estimation is proposed. The human upper body key points needed are retrained based on AlphaPose to achieve human object localization and key points detection. Then, a mathematical model for human elbow flexion behaviour discrimination (HEFBD model) is proposed based on human key points, as well as locating the region of interest for small object detection and reducing the interference of complex background. A super-resolution image reconstruction method is used for pre-processing some blurred images. In addition, YOLOv5s is improved by adding a small object detection layer and integrating a convolutional block attention model to improve the detection performance. The detection precision of this method is improved by 5.6%, and the false detection rate caused by complex background is reduced by 13%, which outperforms other state-of-the-art detection methods and meets the requirement of real-time performance.

关键词： human upper body key points feature extraction posture estimation detection performance human key points video signal processing human elbow flexion behaviour discrimination complex background key points detection Neural nets HEFBD model mathematical model super-resolution image reconstruction method Optical, image and video signal processing Computer vision and image processing techniques convolutional block attention model construction sites convolutional neural nets smoking human object localization object detection state-of-the-art detection methods Image recognition making phone calls pose estimation object detection layer human elbow flexion behaviour recognition Video signal processing biomechanics image motion analysis image reconstruction image resolution complex scenes false detection rate detection precision

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based substation remote construction management and AI automatic violation detection system

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2022年第9期16卷 1714-1726页

作者： Yan, Kai Li, Quanjing Li, Hao Wang, Haifeng Fang, Yuping Xing, Lin Yang, Yang Bai, Haicheng Zhou, Chengjiang Yunnan Normal Univ Sch Informat Sci & Technol Kunming 650500 Yunnan Peoples R China Yunnan Normal Univ Lab Pattern Recognit & Artificial Intelligence Kunming 650500 Yunnan Peoples R China Yunnan Normal Univ Sch Phys & Elect Informat Kunming 650500 Yunnan Peoples R China Yunnan Normal Univ Sch Vocat & Tech Educ Kunming 650500 Yunnan Peoples R China

Workplace video surveillance and timely response to operational violations are critical to avoid operator injuries at power construction sites. Here, a system that combines remote substation construction management and artificial intelligence object detection techniques to intellectualize the power construction management process and identify violations during construction in real time is proposed. To improve the detection accuracy, a data augmentation method, including three operations: (1) object segmentation and background fusion;(2) partial erasing;and (3) other basic transformations, is also proposed. Six variants of the You Only Look Once (YOLO) model are trained as detectors for comparative experiments on a dataset collected at the practical construction site. The experimental results show that the detection precision and recall of the YOLOv5-s model are 0.852 and 0.922, with high accuracy and low miss rate, which meet the requirements of robustness and accuracy in detecting realistic power construction violations.

关键词： object detection image segmentation data augmentation power construction sites artificial intelligence object detection techniques video surveillance detection accuracy operator injuries substations realistic power construction violations timely response workplace video surveillance power construction management process remote substation construction management data augmentation method operational violations AI automatic violation detection system background fusion deep learning-based substation remote construction management deep learning (artificial intelligence) practical construction site detection precision artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

CT2-MDS: Cooperative trust-aware tolerant misbehaviour detection system for connected and automated vehicles

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2022年第2期16卷 218-231页

作者： Liu, Ying Xue, Hongwei Zhuang, Weichao Wang, Fa'an Xu, Liwei Yin, Guodong Southeast Univ Sch Cyber Sci & Engn Nanjing 211189 Peoples R China Southeast Univ Sch Mech Engn Nanjing 211189 Peoples R China

Connected and automated vehicles (CAVs) are recognized as a promising solution to improve road safety. Before deploying CAVs, securing the communication environment is a critical challenge. To secure the exchanged sensitive messages between CAVs, a novel cooperative trust-aware tolerant misbehaviour detection system (CT2-MDS) is proposed in this paper. The vehicle-to-everything (V2X) network model in real complex scenarios is built first, and several typical types of attacks are simulated. The cooperative trust factor is then defined to evaluate the received message packet's plausibility instead of the node. And the measuring uncertainty of sensors is considered to improve the overall detection precision. At last, a multi-model fusion misbehaviour detection method is presented based on the idea of cross-validation. In this mechanism, different from the binary classification, the misbehaviour messages are categorized into particular misbehaving classes. To verify the proposed system's performance, the simulation is conducted, and the results showed that the proposed method outperformed existing single classifiers and provided good prediction accuracy in different attack density.

关键词： multimodel fusion misbehaviour detection method exchanged sensitive messages road vehicles vehicle-to-everything network model computer network security intelligent transportation systems received message packet trust-aware tolerant misbehaviour detection system communication environment V2X road safety trusted computing vehicular ad hoc networks novel cooperative trust-aware CT2-MDS detection precision trust factor pattern classification misbehaviour messages traffic engineering computing connected automated vehicles

来源：评论

学校读者我要写书评

暂无评论

Automatic detection and Classification System of Domestic Waste via Multimodel Cascaded Convolutional Neural Network

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第1期18卷 163-173页

作者： Li, Jiajia Chen, Jie Sheng, Bin Li, Ping Yang, Po Feng, David Dagan Qi, Jun Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China Samsung Elect China R&D Ctr Nanjing 210012 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Univ Sheffield Dept Comp Sci Sheffield S1 4DP S Yorkshire England Univ Sydney Sch Informat Technol Biomed & Multimedia Informat Technol Res Grp Sydney NSW 2006 Australia Xian Jiaotong Liverpool Univ Dept Comp Sci & Software Engn Suzhou 215123 Peoples R China

Domestic waste classification was incorporated into legal provisions recently in China. However, relying on manpower to detect and classify domestic waste is highly inefficient. To that end, in this article, we propose a multimodel cascaded convolutional neural network (MCCNN) for domestic waste image detection and classification. MCCNN combined three subnetworks (DSSD, YOLOv4, and Faster-RCNN) to obtain the detections. Moreover, to suppress the false-positive predicts, we utilized a classification model cascaded with the detection part to judge whether the detection results are correct. To train and evaluate MCCNN, we designed a large-scale waste image dataset (LSWID), containing 30 000 domestic waste multilabeled images with 52 categories. To the best of our knowledge, the LSWID is the largest dataset on domestic waste images. Furthermore, a smart trash can is designed and applied to a Shanghai community, which helped to make waste recycling more efficient. Experimental results showed a state-of-the-art performance, with an average improvement of 10% in detection precision.

关键词： Convolutional neural networks Object detection Informatics Predictive models Training Shape Recycling detection precision domestic waste detection and classification multimodel cascaded convolutional neural network (MCCNN) smart trash can (STC)

来源：评论

学校读者我要写书评

暂无评论

Preserving Visual Authenticity: Block chain-Augmented AI Frameworks for Advanced Digital Deception Recognition and Mitigation 5

Preserving Visual Authenticity: Block chain-Augmented AI Fra...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Priya, M. Murugesan, J. Bhuvaneswari, P. Rubigha, M. Lalithambikai, S. Mohanraj, B. Knowledge Institute of Technology Department of Information Technology Salem India Sona College of Technology Department of Computer Science and Engineering Salem India Sona College of Technology Department of Information Technology Salem India

ISBN: (纸本)9798331504403

The rapid advancements in deep learning have given rise to sophisticated DeepFake technologies, posing significant threats to visual integrity and authenticity in digital media. This paper presents an innovative approach to DeepFake detection and mitigation by integrating blockchain technology with artificial intelligence frameworks. The proposed Blockchain-Augmented AI (BAAI) framework utilizes the immutability and decentralized nature of block chain to enhance the security and reliability of the detection process. Our method involves the development of advanced AI models for detecting DeepFakes, which are then integrated with a blockchain-based ledger to ensure the verifiability and traceability of detection results. In this proposed work, a novel integration of blockchain technology and AI designed to enhance DeepFake detection capabilities. The framework achieves a 97% accuracy rate, ensuring reliable identification of manipulated media, while maintaining a low false positive rate of 3%. These results highlight the BAAI framework's effectiveness in minimizing erroneous detections and its robustness in safeguarding digital visual content. In the face of increasingly sophisticated DeepFake technologies, this framework offers a crucial advancement in combating digital deception. © 2024 IEEE.

关键词： Blockchain-Augmented AI (BAAI) DeepFake detection detection Accuracy detection precision False Positives Media Authenticity Visual Integrity

来源：评论

学校读者我要写书评

暂无评论

DESIGN AND EXPERIMENTAL STUDY OF MOISTURE CONTENT detection DEVICE BASED ON CAPACITIVE METHOD

引用

INMATEH-AGRICULTURAL ENGINEERING 2022年第3期68卷 156-166页

作者： Huang, Chao Chen, Shu Jiang, Qing Xu, Liang-yuan Anhui Agr Univ Coll Engn Hefei Anhui Peoples R China Anhui Prov Engn Lab Intelligent Agr Machinery & E Hefei Anhui Peoples R China

To enable the accurate detection of grain moisture content and improve the efficiency of the drying process, a parallel-plate moisture content detection device (PPMCDD) was developed in this study. Firstly, the detection principle and influencing factors of this device are analyzed. Then the effects of three key factors as distance, thickness, relative area on the accuracy of the device were determined through simulation, and the optimal combination of parameters was obtained through analysis of variance of a regression model and response surface methodology. Finally, a simple test bench is built to verify the effectiveness of PPMCDD by comparative experiment. Through simulation and response surface analysis, the optimal combination parameters are as follows: thickness =1 mm, pacing =19.54 mm, relative area =4023.17 mm2, corresponding to the measured capacitance value of 37.676 pF. By comparative experimental analysis, it is found that the maximal relative error of the moisture content detection device evaluated in this study was 1.58%. The detection error is small, and the device exhibits high accuracy and stability and meets the design requirement.

关键词： Capacitance method detection precision Moisture detection Parallel-plate moisture content detection device (PPMCDD)

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：