检索结果-内蒙古大学图书馆

Computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Jie Chen Hongyan Han Library of Liaocheng University Liaocheng China School of Mathematical Sciences Liaocheng University Liaocheng China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

By effectively leveraging image periodicity during the denoising process, the non-local means filter has demonstrated superior performance over some conventional methods. However, its limited consideration of local image information may lead to the removal of useful non-periodic details during denoising. To address this limitation, this paper introduces a novel filter that integrates both local and non-local means. Furthermore, given the increasing prevalence of multimodal images in real-world applications, the proposed filter is extended to handle multimodal scenarios. Results from classic image experiments, including both subjective visual assessments and objective quantitative metrics, indicate that the proposed filter surpasses the original algorithm in denoising performance.

关键词： Hands Measurement Visualization Noise reduction filtering algorithms Big Data Information filters Reliability Kernel Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Tracking with Monocular Camera: Simple 2D Filter Springing From 3D Modeling

Pedestrian Tracking with Monocular Camera: Simple 2D Filter ...

引用

International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)

作者： Jan Krejčí Oliver Kost Ondřej Straka Jindřich Duník Department of Cybernetics University of West Bohemia Pilsen Czech Republic

ISBN: (数字)9798350368031

ISBN: (纸本)9798350368048

A simple and real-time 2D single-object visual tracker is derived based on first-principle modeling in 3D, which was introduced in previous work. An inverse of the nonlinear perspective projection is followed by a simple approximation assuming that the pedestrian moves with a fixed depth in front of the camera. The resulting 2D tracking algorithm appears to have a similar form as the state-of-the-art single-object tracker from BoT-SORT, is easy to implement, and its parameters have convenient meaning. Its performance is assessed statistically using the publicly available MOT17 dataset.

关键词： Visualization Solid modeling Three-dimensional displays Pedestrians Tracking filtering algorithms Cameras Approximation algorithms Real-time systems Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Design of $M$-Channel Uniform Linear-Phase Filter Banks with Partial Cosine Modulation

引用

Chinese Journal of Electronics 2023年第3期18卷 477-480页

作者： Wei Zhong Guangming Shi Xuemei Xie Xuyang Chen School of Electronic Engineering Xidian University Xi'an China

In this paper, a method of partial cosine modulation is proposed to maintain the Linear-phase (LP) property of $M$ -channel uniform filter banks. We design the lowpass analysis filter separately, getting the highpass by shifting it by $\pi$ , and obtain the bandpass via cosine modulation of a prototype filter, justifying the name “partial cosine modulation”. For the elimination of significant aliasing distortion, a necessary and sufficient condition is derived. With the proposed design criteria, the problem of uniform LP bank design becomes that of designing only two filters, one prototype and the lowpass filter, leading to a less design effort. By employing the Parks-McClellan algorithm, a global optimum solution in the minimax sense can be obtained. In addition, the proposed method is applicable to filter banks with arbitrary number of channels and offers more flexible in choosing the filter length.

关键词： Sufficient conditions Filter banks Modulation Prototypes filtering algorithms Distortion

来源：评论

学校读者我要写书评

暂无评论

Research on IMS Packet Service Triggering Algorithm Based on Double filtering Criterion

Research on IMS Packet Service Triggering Algorithm Based on...

引用

International Conference on Communication Technology (ICCT)

作者： Ning Ma Qing Miao Yuan Qin JinJin Li TangJie Yuan Unit 78167 of PLA ChengDu China Institute of Communication Engineering Army Engineering University of PLA NanJing China Unit 32554 of PLA KunMing China

The Service trigger algorithm is the core of the entire IMS system platform, which can affect the work efficiency and service quality of the entire system. In the early days, the service trigger algorithm officially defined by 3GPP can no longer meet the overall requirements of current big data and big user information services. In order to meet the Service needs of the multimedia network platform and the huge user group in the future, this paper conducts an in-depth study on the official Service trigger algorithm, and proposes an IMS packet Service trigger algorithm based on the double filter criteria. This algorithm achieves the goal of quickly processing multiple services by combining the packet Service trigger mechanism with the iFC+sFC dual service filter criteria. The simulation results show that the new service triggering algorithm can effectively reduce the overall session setup delay, improve the system throughput, and greatly improve the IMS system service triggering efficiency.

关键词： Simulation Information services filtering algorithms Big Data Throughput Information filters Communications technology

来源：评论

学校读者我要写书评

暂无评论

User preference Based Personalized Collaborative filtering for Large Scale Recommender Systems

User preference Based Personalized Collaborative Filtering f...

引用

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Priya V Keerthika J L.R Sujithra Department of Artificial Intelligence and Data Science Dr NGP Institute of Technology Coimbatore India Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore India Department of Computer Science and Engineering Dr NGP Institute of Technology Coimbatore India

The Indian market for internet shopping has already been penetrated by E-Commerce. People are increasingly attracted to shop online, which has altered the market landscape. Amazon, Snap deal, Flipkart, and more companies offer online shopping sites that are gaining traction. As the number of online buyers and dealers grows, smart business approaches are required to deal with the massive amounts of data generated every day. Recommendation systems play a crucial role in sifting this data and giving consumers with relevant information. Various strategies for recommender systems have been used, such as Collaborative filtering, Content-based, and Demographic, but these techniques have a number of flaws that make them ineffective. Among these collaborative filtering approach is widely popular because of its simplicity and accuracy. But still these systems can be improved in their accuracy when used for multiple domains. As a result, more distinguishing traits must be identified in order to optimize these procedures. This can be accomplished by combining the benefits of multiple strategies in a hybrid approach. This paper describes a hybrid approach that identifies the users with shared preferences (semantic users) and their dynamic interests with parallel training to improve recommendation efficiency. Results were compared with other state of art techniques and the accuracy of our system is found to be improved by 2% and seems to give promising results for multiple domains.

关键词： Training filtering Collaborative filtering Semantics Collaboration Companies filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

SCIHYPO - A Deep Learning Framework for Data-Driven Scientific Hypothesis Generation from Extensive Literature Analysis

SCIHYPO - A Deep Learning Framework for Data-Driven Scientif...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： Mothilal Tadiparthi Sindhu Pasupuleti Sita Venkata Sathwika Talluri Subramanyam Raju Sangaraju Manikanta Mogili Dept. of AI&DS SR Gudlavalleru Engineering College Gudlavalleru India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

Scientific progress relies heavily on hypothesis generation, yet conventional methods often rely on expert intuition, limiting exploration of new ideas. To address this, we introduce SciHypo, a deep learning framework leveraging scientific literature to generate fresh hypotheses across diverse fields. SciHypo employs advanced natural language processing, including Generative Pre-trained Transformer to analyze patterns, relationships, and gaps in research. This allows the model to uncover latent connections and propose novel research trajectories. Filter search algorithms ensure the production of relevant hypotheses. A key strength is SciHypo's adaptability across scientific disciplines, enabling transdisciplinary hypothesis generation. Results demonstrate its ability to propose hypotheses resonating with experts, advancing scientific frontiers.

关键词： Deep learning Bridges Limiting Navigation Production filtering algorithms Transformers

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fixed-time Backstepping SMC for Gear Transmission System with Backlash

Adaptive Fixed-time Backstepping SMC for Gear Transmission S...

引用

International Conference on Power Electronics and Motion Control (IPEMC)

作者： Zheng Yu Yong Chen Hui Tang Shenggang Wang Hongru Wang School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Sichuan Province Engineering Technology Research Center for Electric Vehicle Driving System and Safety Chengdu China Sichuan Aucu Technology Co. ltd Mianyang China

ISBN: (数字)9798350351330

ISBN: (纸本)9798350351347

In this paper, an adaptive fixed-time backstepping sliding mode control (AFTBSMC) method is proposed for gear transmission system with gear backlash and mismatched disturbances. First, an adaptive fixed-time sliding mode surface and an adaptive fixed-time reaching law are proposed so that the system state converges to a domain near the origin in a fixed time. Second, a backstepping control scheme is designed to solve the higher-order state equations of the gear transmission system. Meanwhile, the adaptive estimation is used to deal with the problem of mismatched disturbances, and through the advantage of fixed-time stability, AFBSMC makes it possible to make the closed-loop system can be guaranteed to be rapid and robust without being affected by the initial state of the system. Finally, the effectiveness of AFBSMC is verified on the dSPACE gearbox physical platform.

关键词： Backstepping Adaptive systems Gears filtering algorithms Power electronics Explosions Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Target Detection and Visualization Using Low Cost SONAR Technology

Dynamic Target Detection and Visualization Using Low Cost SO...

引用

International Conference on Computer and Information Technology (ICCIT)

作者： Mohammad Mashhunur Rahman Mehedi Hassan Asiba Tasnim Jarin Subha Parsha Nee Nee Sun S. M. Abrar Abid Department of Aeronautical Engineering Military Institute of Science and Technology Dhaka Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

In autopilot and small surveillance systems, the potentialities of Sound Navigation and Ranging (SONAR) sensors can be harnessed to augment safety, and efficiency, and enhance the overall efficacy. The authors propose using the HC-SR04 sensor, which utilizes SONAR technology, to develop a low-cost Internet of Things (IoT) system that identifies, locates, and measures the velocity of stationary and moving targets. However, the sensor readings were susceptible to a plethora of noise factors, including acoustic disturbances, environmental conditions, and physical obstructions. Hence, a discrete Kalman filter (KF) algorithm was developed which improved the sensor's performance by 35.24%. Concurrently, DHT11 sensor was used to account for temperature effect on ultrasound. Subsequent to target detection, their spatial coordinates were visualized in a Graphical User Interface (GUI). The proposed system detected targets within a range of 2 cm to 4 meters within a 180-degree arc. The novelty added to this study was the development of an algorithm to detect dynamic targets and real-time monitoring through a GUI, which was developed using the Qt platform. The system successfully detected both stationary and moving targets, providing real-time information about their location, speed, and direction. This data can significantly improve safety, security, and operational efficiency.

关键词： Temperature sensors Sonar filtering algorithms Sonar navigation Distance measurement Sensors Autopilot Kalman filters Security Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Heart and Respiratory Rate Extraction from a Single Audio-based Monitoring System using Wavelet and Hilbert Transforms

Heart and Respiratory Rate Extraction from a Single Audio-ba...

引用

IEEE Region 10 International Conference TENCON

作者： Gabriel Monasterial Ned Tilos Daniel Vicho Paul Jason Co Marc Rosales Carl Timothy Tolentino John Richard Hizon UP Center for Air Research in Urban Environments Research Group Electrical and Electronics Engineering Institute University of the Philippines Diliman Quezon City Philippines

ISBN: (数字)9798350350821

ISBN: (纸本)9798350350838

Audio-based health monitoring systems have gained traction for its capability in capturing different physiological target signals and holding features relevant in diagnosis and treatment, making it a feasible form of data acquisition in biomedical signal processing and feature extraction. Acquiring audio for both heart and respiratory sounds for rate estimation was accomplished using the bottom microphone of the Google Pixel 6A from the trachea and anterior left. A direct comparison of the filter-Hilbert and wavelet-Shannon algorithms based on literature with modifications catering to the application of this study was done to measure their performance and reliability against the KardiaMobile 6L EKG. Tests done were able to show good accuracy for both algorithms on heart rate calculations on both the trachea and anterior left, satisfying having less than ± 10 BPM difference from control. Tests for respiratory rate only provided promising results of less than ± 5 CPM difference from control for tracheal recordings,

关键词： Heart rate Wavelet transforms Databases Signal processing algorithms filtering algorithms Wavelet analysis Recording Biomedical monitoring Trachea Monitoring

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of PSO and GWO algorithms in Fractional-Order Low Pass Filter Design

Comparative Study of PSO and GWO Algorithms in Fractional-Or...

引用

Intelligent Computing and Sustainable Innovations in Technology (IC-SIT), International Conference on

作者： A.Konda Babu B.T. Krishna Department of ECE JNTUK Kakinada A.P India

ISBN: (数字)9798350369175

ISBN: (纸本)9798350369182

This work, in an effort to improve the functionality and adaptability of electronic filters, is exploring the design of a Fractional Order Lowpass Filter by means of evolving algorithms. Filters’ fractional order transfer functions provide a more fluid representation of system dynamics than traditional integer order filter. Evolutionary algorithms are employed in the design phase to enhance the fractional-order filter’s parameters. Among the frequency response parameters that are optimized for are cut-off frequency, roll-off, and attenuation. Evolutionary algorithms are a useful tool for efficiently solving the difficult parameter space problems of fractional-order filters by swiftly identifying the optimal solutions. Through the examination of various filter configurations made possible by the algorithmic framework, designs that balance filter complexity and performance are found.

关键词： Technological innovation Fluids System dynamics Heuristic algorithms Low-pass filters Transfer functions filtering algorithms Frequency response Particle swarm optimization Optimization

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：