检索结果-内蒙古大学图书馆

Application of Computer Vision for Efficient Maintenance of Cleanliness and Order in Commercial Areas: An Invention Approach for Automated Management in Commercial Zones 8

Application of Computer Vision for Efficient Maintenance of ...

引用

8th International Conference on Communication and Information Systems, ICCIS 2024

作者： Llacta, Jesus David Villon Simeon, Wiler Yosef Hurtado Rosales, Jorge Martin Vega Universidad Continental Facultad de Ingeniería Huancayo Peru Universidad Continental Faculty of Engineering Huancayo Peru

ISBN: (纸本)9798331531171

This study explores the application of computer vision technology to improve the efficiency of maintaining cleanliness and order in high-traffic commercial areas. Given the growing importance of automation in managing commercial spaces, this paper proposes a technological model that utilizes strategically placed cameras and image processing algorithms to detect disorganized or dirty tables, sending real-time alerts to cleaning staff via a mobile application. The goal is to optimize resource use, reduce response times, and enhance customer experience. To validate the model, an experiment was conducted with a sample of 30 customers, measuring their satisfaction levels before and after the system's implementation. The results, analyzed through statistical tests, show a significant improvement in customer satisfaction. Additionally, the study discusses its limitations and proposes future research directions, including an evaluation of the costs associated with the automated system compared to traditional methods. © 2024 IEEE.

关键词： automation cleaning management commercial areas Computer vision customer experience detection algorithms image processing operational efficiency

来源：评论

学校读者我要写书评

暂无评论

Processing and Recognition of Two-Coordinate Reference Marks Images in Scanning Probe Microscopy

引用

OPTICS AND SPECTROSCOPY 2022年第9期130卷 527-531页

作者： Gulyaev, P. V. Tyurikov, A. V. Ermolin, K. S. Shelkovnikova, T. E. Russian Acad Sci Udmurt Fed Res Ctr Ural Branch Izhevsk 426067 Russia

The article is devoted to the problem of automatic positioning of a scanning probe microscope to a studied region after probe replacement, sample surface treatment, etc. As an auxiliary tool for positioning, it is proposed to use reference marks indicating directions of the probe displacement to the investigated region. The considered pattern of reference marks is a cross. A method of detection of reference marks in the image by analyzing the surface curvature is described. An algorithm of recognition of reference marks based on the structural analysis of positions of singular points (local extrema of curvature) is proposed. Analysis is performed for selected pairs of singular points with specific length and angle of inclination. For selected pairs, parallel transfer parameters are calculated. If reference marks are present in the frame, these parameters are ordered along a straight line, which is a qualitative criterion of recognition of reference marks.

关键词： reference marks scanning tunnel microscope filtering of STM images nanoobjects detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Mapping the unmappable—Rapid high-density contact mapping in hemodynamically unstable ventricular tachycardia using a novel star-shaped multipolar catheter

引用

HeartRhythm Case Reports 2023年第10期9卷 749-754页

作者： Tonko, Johanna B. Sporton, Simon Sawhney, Vinit Dhinoja, Mehul St Bartholomew's Hospital London United Kingdom Institute for Cardiovascular Science University College London London United Kingdom

来源：评论

学校读者我要写书评

暂无评论

Underwater Multitarget Tracking With Sonar Images Using Thresholded Sequential Monte Carlo Probability Hypothesis Density Algorithm

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷

作者： Zhou, Tian Wang, Yuqian Chen, Baowei Zhu, Jianjun Yu, Xiaoyang Harbin Engn Univ Acoust Sci & Technol Lab Harbin 150001 Peoples R China Harbin Engn Univ Key Lab Marine Informat Acquisit & Secur Minist Ind & Informat Technol Harbin 150001 Peoples R China Harbin Engn Univ Coll Underwater Acoust Engn Harbin 150001 Peoples R China

This letter presents a multitarget tracking algorithm-thresholded sequential Monte Carlo probability hypothesis density (TH-SMC-PHD) algorithm. The TH-SMC-PHD aims to overcome the problem that underwater multitarget tracking is prone to missing tracking on sonar images, resulting in the breakage of trajectories. First, cell average (CA)-constant false alarm rate (CFAR) and K-means are employed to detect potential underwater targets from sonar images, respectively. Then, the TH-SMC-PHD is applied to the detection results for tracking, using a continuously lost frame threshold to reduce the missing tracking rate (MR) and the minimum-sampling-variance (MSV) resampling to improve tracking accuracy. An actual underwater multitarget tracking experiment using a forward-looking sonar was contracted in a water tank to evaluate the tracking performance. Compared with the other two PHD tracking algorithms, the results demonstrate that the proposed algorithm achieves high-precision, non-fracture, non-missing tracking of three targets. In addition, the TH-SMC-PHD is more stable and less affected by different detection algorithms, which has the potential for practical applications.

关键词： Target tracking Sonar detection Object detection detection algorithms Prediction algorithms Particle measurements Atmospheric measurements Sonar images thresholded sequential Monte Carlo probability hypothesis density (TH-SMC-PHD) algorithm underwater multitarget tracking

来源：评论

学校读者我要写书评

暂无评论

Video Manipulations Beyond Faces: A Dataset with Human-Machine Analysis

Video Manipulations Beyond Faces: A Dataset with Human-Machi...

引用

23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Mittal, Trisha Sinha, Ritwik Swaminathan, Viswanathan Collomosse, John Manocha, Dinesh Univ Maryland Baltimore MD 21201 USA Adobe Res San Jose CA USA

ISBN: (纸本)9798350320565

As tools for content editing mature, and artificial intelligence (AI) based algorithms for synthesizing media grow, the presence of manipulated content across online media is increasing. This phenomenon causes the spread of misinformation, creating a greater need to distinguish between "real" and "manipulated" content. To this end, we present VIDEOSHAM, a dataset consisting of 826 videos (413 real and 413 manipulated). Many of the existing deepfake datasets focus exclusively on two types of facial manipulations-swapping with a different subject's face or altering the existing face. VIDEOSHAM, on the other hand, contains more diverse, context-rich, and human-centric, high-resolution videos manipulated using a combination of 6 different spatial and temporal attacks. Our analysis shows that state-of-the-art manipulation detection algorithms only work for a few specific attacks and do not scale well on VIDEOSHAM. We performed a user study on Amazon Mechanical Turk with 1200 participants to understand if they can differentiate between the real and manipulated videos in VIDEOSHAM. Finally, we dig deeper into the strengths and weaknesses of performances by humans and SOTA-algorithms to identify gaps that need to be filled with better AI algorithms. We present the dataset here(1).

关键词： Deepfakes Computer vision Conferences Artificial intelligence detection algorithms Faces Man-machine systems

来源：评论

学校读者我要写书评

暂无评论

Technologies for Risk Mitigation and Support of Impaired Drivers

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第5期23卷 4736-4738页

作者： Ahlstrom, Christer Diederichs, Frederik Teichmann, Daniel Swedish Natl Rd & Transport Res Inst S-58195 Linkoping Sweden Linkooping Univ Dept Biomed Engn S-58183 Linkoping Sweden Fraunhofer Inst Optron Syst Technol & Image Exploitat D-76131 Karlsruhe Germany Univ Southern Denmark SDU Hlth Informat & Technol DK-5230 Odense Denmark MIT Inst Med Engn & Sci Cambridge MA 02139 USA

This editorial serves as an extended introduction to the Special Issue on Technologies for Risk Mitigation and Support of Impaired Drivers. It gives the context to recent advances in assisted and automated driving and the new challenges that arise when modern technology meets human users. The Special Issue focuses on the development of robust sensors and detection algorithms for driver state monitoring of fatigue, stress, and inattention, and on the development of personalized multimodal, user-oriented, and adaptive information, warning, actuation, and handover strategies. A summary of more recent developments serves as a motivation for each article that follows.

关键词： Special issues and sections Risk management Biomedical monitoring Human factors Human computer interaction Automation detection algorithms Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of Automatic Wheeze detection Algorithm for Children With Asthma

引用

IEEE ACCESS 2021年 9卷 126882-126890页

作者： Kuo, Ho-Chang Lin, Bor-Shing Wang, Yan-Di Lin, Bor-Shyh Kaohsiung Chang Gung Mem Hosp Dept Pediat Kaohsiung 83301 Taiwan Kaohsiung Chang Gung Mem Hosp Kawasaki Dis Ctr Kaohsiung 83301 Taiwan Chang Gung Univ Coll Med Taoyuan 33302 Taiwan Natl Taipei Univ Dept Comp Sci & Informat Engn New Taipei 237303 Taiwan Natl Yang Ming Chiao Tung Univ Inst Imaging & Biomed Photon Tainan 71150 Taiwan Chi Mei Med Ctr Dept Med Res Tainan 71004 Taiwan

Asthma is a symptom of tracheal obstruction caused by bronchospasm, and it is among the most prevalent chronic obstructive pulmonary diseases. Auscultation is the most commonly used approach for the clinical diagnosis of asthma. However, recognizing wheezes through auscultation requires experienced physicians, and this approach is not sufficiently objective. Therefore, developing a method for recognizing wheezes objectively is crucial. Most studies have used the spectral features of lung sounds to detect wheezes;however, they have not achieved sufficiently high performance owing to the poor discrimination of spectral features. Several studies have attempted to extract wheezing features from lung sound spectrograms;however, their approaches were easily affected by variations in the wheezing frequency and background noise. The present study proposes a novel automatic wheeze detection algorithm for extracting lung sound features in the time-frequency domain and automatically detecting wheezes. The proposed algorithm applies canonical correlation analysis to successfully detect wheezing features in a lung sound spectrogram. Moreover, a neural network technique is used to effectively classify healthy and wheezing sounds. The experimental results indicated that the proposed algorithm showed excellent performance in detecting wheezing.

关键词： Lung Feature extraction Spectrogram Correlation detection algorithms Time-frequency analysis Neural networks Asthma wheezes canonical correlation analysis neural network

来源：评论

学校读者我要写书评

暂无评论

Data-Driven False Data Injection Attack: A Low-Rank Approach

引用

IEEE TRANSACTIONS ON SMART GRID 2022年第3期13卷 2479-2482页

作者： Mukherjee, Debottam Indian Inst Technol BHU Varanasi Dept Elect Engn Varanasi 221005 Uttar Pradesh India

False data injection attack on the state estimation algorithms have already showcased its detrimental effects for modern grid operation. This letter promotes a novel attack vector formulation policy for the linear state estimation algorithm by exploring the low-rank subspace of the mapping matrix. An extensive analysis on the IEEE 14 bus test bench promotes the aforementioned propositions.

关键词： Sparse matrices Matrix decomposition State estimation Approximation algorithms Detectors Singular value decomposition detection algorithms Cyber security false data injection attack smart grid state estimation

来源：评论

学校读者我要写书评

暂无评论

Load Voltage Control Operation Method for Hybrid Distribution Transformers Based on Improved Voltage detection Algorithm

Load Voltage Control Operation Method for Hybrid Distributio...

引用

Smart Grid and Artificial Intelligence (SGAI), International Conference on

作者： Zixia Sang Xu Zheng Jiaqi Huang Jiong Yan Junyao Liu Qixin Wang State Grid HBEPC Economic & Technology Research Institute Wuhan China

ISBN: (数字)9798331518806

ISBN: (纸本)9798331518813

The changes in the distribution network load will affect the distribution network voltage, so the hybrid distribution transformer (HDT) needs to start or stop the load voltage compensation equipment according to the specific load situation. Due to the disadvantage of commonly used voltage rise and fall detection algorithms, this paper proposes a novel dq0 transformation detection algorithm, which takes the derivative of each phase voltage to construct a virtual three-phase voltage, and then performs dq0 transformation on three sets of virtual three-phase voltages. Finally, through simple logical judgment, the detection of single-phase power supply voltage drops and other conditions can be achieved. The advantage of this algorithm is that it only requires the addition of a filter with a smaller time constant to filter out higher-order harmonics, effectively avoiding the delay caused by the larger filter time constant in traditional detection algorithms, thereby improving the real-time and accuracy of detection. The simulation verification of the improved detection algorithm is implemented with the Saber simulation platform about the start and stop of the load voltage compensation device based on the detection signal.

关键词： Low-pass filters Distribution networks Filtering algorithms Transformers Real-time systems Delays Time factors detection algorithms Voltage control Power harmonic filters

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Community detection and Network Analysis: A 2-Level Approach for Social Media Networks

Hierarchical Community Detection and Network Analysis: A 2-L...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Vishakha Shelke Priyan Parmar Darshit Adhiya Department of Computer Science and Engineering (ICB) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

As social networking site users and their relationships generate enormous amounts of data, these networks become complicated, requiring sophisticated research approaches to extract valuable information. This research presents an innovative 2-level hierarchical method for community discovery. Greedy Modularity and Label Propagation community detection algorithms applied in the first level to find communities. Next, node similarity is assessed using similarity metrics such Jaccard, Cosine, Katz, and Adamic-Adar. These nodes are grouped utilizing K-Nearest Neighbors (KNN) using common neighbors and vicinity to centroids once initial communities are identified, which refines the neighborhood framework to form a 2-tiered hierarchy. NetworkX visualizations for link prediction techniques used to highlight additional network topology insights. The proposed method improves on conventional community detection by identifying intricate hierarchical patterns, providing a more thorough comprehension of the dynamics of social media networks. The effectiveness of the presented hierarchical community detection methodology is assessed using quantitative indicators, such as F1 score, precision, and recall. The outcomes show the reliability of our approach in accurate community detection.

关键词： Social networking (online) Scalability Network analyzers Nearest neighbor methods Network architecture Gain measurement Real-time systems Reliability detection algorithms Informatics

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：