检索结果-内蒙古大学图书馆

30th ieee International Conference on image processing (ICIP)

作者： Manousis, Theodoros Passalis, Nikolaos Tefas, Anastasios Aristotle Univ Thessaloniki Computat Intelligence & Deep Learning Grp AIIA Lab Dept Informat Thessaloniki Greece

ISBN: (纸本)9781728198354

Deep Learning (DL) models have enabled very accurate pose estimation. However, most of the existing approaches require images of relatively high resolution, since locating body parts and joints accurately is challenging, which increases the computational cost of these approaches. To overcome this limitation in this paper we propose an active perception method for high-resolution pose estimation that enables efficiently selecting the most appropriate image region for analysis and then employing a bottom-up pose estimator on the corresponding region. This allows for significantly improving the efficiency of pose estimation by selectively analyzing in high resolution only the parts of the image that contain humans. To ensure the computational efficiency of the proposed method we propose using low-resolution heat maps extracted using the same pose estimation model in order to guide the active perception process. The proposed method is model agnostic since it can be combined with any bottom-up pose estimation model in order to enable high-resolution analysis. We have experimentally evaluated the proposed method using a well-known pose estimation model, Lightweight OpenPose, demonstrating its effectiveness on three high-resolution variants of the COCO2017 dataset.

关键词： pose estimation high resolution active perception deep learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Gradient Boosting Algorithm for Dynamic Pricing using a Custom dataset 5

A Hybrid Gradient Boosting Algorithm for Dynamic Pricing usi...

引用

5th International Conference on image processing and Capsule Networks, ICIPCN 2024

作者： Wadhwa, Jasmeet Singh Jagwani, Lavisha Pitchaimanickam, B. SRM Institute of Science and Technology School of Computing Department of Computational Intelligence Kattankulathur India School of Computing Department of Computational Intelligence Kattankulathur India

ISBN: (纸本)9798350367171

E-commerce platforms have experienced significant growth, especially during the COVID-19 pandemic, leading to an influx of sellers and buyers. However, pricing products accurately amidst this surge in online shopping presents a challenge due to various factors like seasonal trends and product specifications. To address this challenge, a novel approach is introduced in this study, combining XGBoost with NGBoost to predict product prices based on reviews and various features. The hybrid models are compared with the base models XGBoost and NGBoost, demonstrating superior performance over these existing algorithms. This offers business owners a competitive edge in pricing their products effectively. © 2024 ieee.

关键词： Ensemble algorithms Extreme Gradient Boost Hybrid model Natural Gradient Boost Stacking

来源：评论

学校读者我要写书评

暂无评论

The OCON model: an old but green solution for distributable supervised classification for acoustic monitoring in smart cities 5

The OCON model: an old but green solution for distributable ...

引用

5th ieee International symposium on the Internet of Sounds (ieee IS2)

作者： Giacomelli, Stefano Giordano, Marco Rinaldi, Claudia Univ LAquila DISIM Laquila Italy CNIT Consorzio Nazl Interuniv Telecomunicazio Laquila Italy

ISBN: (纸本)9798350366532;9798350366525

This paper explores a structured application of the One-Class approach and the One-Class-One-Network model for supervised classification tasks, focusing on vowel phonemes classification and speakers recognition for the Automatic Speech Recognition (ASR) domain. For our case-study, the ASR model runs on a proprietary sensing and lightning system, exploited to monitor acoustic and air pollution on urban streets. We formalize combinations of pseudo-Neural Architecture Search and Hyper-Parameters Tuning experiments, using an informed grid-search methodology, to achieve classification accuracy comparable to nowadays most complex architectures, delving into the speaker recognition and energy efficiency aspects. Despite its simplicity, our model proposal has a very good chance to generalize the language and speaker genders context for widespread applicability in computational constrained contexts, proved by relevant statistical and performance metrics. Our experiments code is openly accessible on our GitHub.

关键词： Artificial intelligence (AI) Deep Learning (DL) Neural Networks (NNs) Green-AI Digital Signal processing (DSP) speech communication phonetics phonology vowel phonemes

来源：评论

学校读者我要写书评

暂无评论

Enhancing image Super-Resolution with GANs Featuring Enhanced Deep Super-Resolution and Attention Mechanisms 4

Enhancing Image Super-Resolution with GANs Featuring Enhance...

引用

4th ieee International Conference on Emerging Techniques in computational intelligence, ICETCI 2024

作者： Kumar, G. Aditya Kativar, Aditi Kannan, A. Vellore Institute of Technology Computer Science and Engineering Vellore India School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350387063

Improving the quality and resolution of low- resolution digital images is an important task with far-reaching implications for a variety of applications, including medical imaging, surveillance, and content retrieval. To solve the high- resolution problem of a single image, this study proposes a new Generative Adversarial Network (GAN) model that includes an Enhanced Deep Super-Resolution (EDSR) generator. Our model includes a sensitivity function and a Squeeze-and- Excitation (SE) block in an EDSR design. These SE blocks directly model channel connections to optimize channel-specific performance responses and improve network capabilities without incurring significant computational costs. After extensive training using complex data processing methods such as rotation, rotation, and rotation, our model shows an impressive ability to enhance image details and traditional culture more accurately. Our strategy outperforms existing models both statistically and qualitatively with better signal-to- noise ratios (PSNRs) on the DIV2K dataset. These results, together with deep learning models, demonstrate the role of attentional processes in improving image resolution and lay the groundwork for further work in this field. © 2024 ieee.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Implementing Cultural image and Narrative in Jewelry Design with AHP and TRIZ 16

Implementing Cultural Image and Narrative in Jewelry Design ...

引用

16th International symposium on computational intelligence and Design, ISCID 2023

作者： Wei, Siteng Department of Art and Design Guangzhou College of Commerce Guangzhou China

ISBN: (纸本)9798350317459

This paper presents a quantitative design approach for integrating cultural image and narrative into jewelry design using the Analytical Hierarchy Process (AHP) and the Theory of Inventive Problem Solving (TRIZ) methods, with Lingnan culture as example. By incorporating AHP and TRIZ, this study offers a systematic and data-driven method to guide the creative process in cultural and creative jewelry design. The paper highlights the significance of quantitative design methods in cultural and creative jewelry design, offering valuable insights for designers seeking to create culturally meaningful and marketable jewelry pieces. By integrating Lingnan culture with the AHP and TRIZ design method, this study contributes to the expanding field of cultural and creative product development, fostering a deeper appreciation and understanding of cultural heritage through contemporary jewelry design. ©2023 ieee.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Research on Real-time image Stitching for Wafer Defect Inspection

Research on Real-time Image Stitching for Wafer Defect Inspe...

引用

International Conference on computational Science and computational intelligence (CSCI)

作者： Kwon, So -Young Kim, Young -Hying Jung, Dong-Soo Lee, Yong-Hwan Kumoh Natl Inst Technol Dept Elect Engn Gumi South Korea Kumoh Natl Inst Technol Dept IT Convergence Gumi South Korea Syisolution Cheongju South Korea Kumoh Natl Inst Technol Sch Elect Engn Gumi South Korea

ISBN: (纸本)9798350361513;9798350372304

Recently, with the development of the 4th industrial revolution technology, the importance and demand for memory semiconductors have increased rapidly, and the semiconductor market is expected to continue to expand in the future. One of the important processes in the semiconductor industry is wafer production, and since wafer yield is directly related to a company's competitiveness, improving wafer yield is a very important issue. Therefore, it is important to accurately detect and analyze wafer defects during semiconductor production. A predictive system is used to determine the cause of defects, in which vision camera and scope equipment is used. The prediction system currently in use perform manually when combining multiple photographic images into one image, which increases the time required to analyze defects and has the potential to result in production disruption. In this paper, we discuss an algorithm that automatically combining multiple photographic images and a method of implementing it with FPGA for real-time processing.

关键词： wafer image stitching defect inspection FPGA vision system

来源：评论

学校读者我要写书评

暂无评论

3D Cloud of Points AI-Based Analysis to Wheels Detection in the Free-Flow Tolling Context 19

3D Cloud of Points AI-Based Analysis to Wheels Detection in ...

引用

ieee 19th Conference on Industrial Electronics and Applications (ICIEA)

作者： dos Santos Oliveira, Erick Lemmy Schitz da Rocha, Luiz Gustavo Rudek, Marcelo Pontifical Catholic Univ Parana PUCPR Dept Comp Engn Curitiba Parana Brazil Pumatronix Curitiba Parana Brazil Pontifical Catholic Univ Parana PUCPR Ind & Syst Engn Grad Programme PPGEPS Curitiba Parana Brazil

ISBN: (纸本)9798350360875;9798350360868

This work addresses the challenge of vehicle parameters' identification for the automation of efficient traffic management from vehicle classification, speed measurement, and axles counting by proposing a method based on computer vision and artificial intelligence. Once a vehicle is classified the research problem investigation is to differentiate the number of wheels that can be identified for each vehicle class as trucks, buses, cars pulling trailers due to the different price policies according to the roads' characteristics. We explore wheels and tires' identification by the 3D cloud of points analysis by artificial intelligence and computational vision technologies. The proposal aims to overcome the limitations of current 2D image systems. Also, we discuss the integration approach based on the integration of a variety of technologies for classifying and tracking and by exploring the main libraries for image processing and 3D data analysis. Additionally, the text describes a virtual testing environment as a digital twin for different scenarios and climate conditions involved in the process. As a result, the research brings the comparative study between the real and simulated virtual data.

关键词： Computer Vision Artificial intelligence Vehicle Detection Traffic Flow 3D Cloud of Points image Classification Digital Twin

来源：评论

学校读者我要写书评

暂无评论

A Novel Practical Decisive Row-Class Entropy-Based Technique for Multilevel Threshold Selection Using Opposition Flow Directional Algorithm

引用

ieee ACCESS 2022年 10卷 110473-110484页

作者： Panda, Rutuparna Swain, Monorama Naik, Manoj Kumar Agrawal, Sanjay Abraham, Ajith VSS Univ Technol Dept Elect & Telecommun Engn Burla 768018 India Silicon Inst Technol Dept Elect & Commun Engn Bhubaneswar 751024 India Siksha O Anusandhan Fac Engn & Technol Bhubaneswar 751030 India Machine Intelligence Res Labs Auburn WA 98071 USA Innopolis Univ Ctr Artificial Intelligence Innopolis 420500 Russia

One of today's inspiring issues is the 2D histogram-based multilevel threshold selection which is used for segmenting images into several regions. The image analysis warrants exploration of multiclass thresholding techniques using various entropy-based objective functions. In this context, the Shannon type of entropic function without inherent decision making capacity has been widely used for threshold selection in the last decade. Furthermore, a 2D histogram was constructed using local average intensity values resulting in loss of some edge information. To address these problems, this study proposes a new methodology using a novel practical decisive row-class entropy (PDRCE) based fitness function for multilevel thresholding. The PDRCE values are computed using the newly constructed 2D histogram-based on normal local variance. Further, an opposition flow directional algorithm (OFDA) is proposed to maximize the fitness function. The performance of the proposed technique is compared with five state-of-the-art 2D histogram-based entropic fitness functions. Moreover, the performance of OFDA is investigated through comparison with other global optimizers namely the genetic algorithm, particle swarm optimization and artificial bee colony. An image segmentation evaluation dataset (BSDS500) is used in this experiment. It is witnessed that the proposal is more efficient than state-of-the-art methods. Our fitness function would be useful for registration, segmentation, fusion, etc.

关键词： Entropy image segmentation Histograms Linear programming Thresholding (Imaging) Decision making Probability distribution image processing Machine learning computational intelligence image processing multilevel thresholding entropy computational intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

Surface-PMSM Sensorless Control Strategy Based on Reduced-Order Linear Kalman Filter Cooperating With Prediction Error Rolling Compensation

引用

ieee Transactions on Power Electronics 2025年第8期40卷 10804-10815页

作者： Xu, Sang Shen, Anwen Tang, Qipeng Wang, Miaomiao Luo, Pan Luo, Xin Xu, Jinbang National Key Laboratory of Science and Technology on Multispectral Information Processing Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Wuhan430074 China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China

Kalman filter (KF) is increasingly attracted for sensorless control of surface permanent magnet synchronous motors due to its strong robustness against measurement and system noise. However, the conventional method suffers from poor position and speed estimation accuracy under dynamic conditions and high computational cost. In order to solve these problems, an enhanced sensorless control strategy based on reduced-order linear Kalman filter (RLKF) cooperating with prediction error rolling compensation is introduced in this article. Differing from conventional methods, a reduced-order linear state equation encompassing rotor position, speed, and torque disturbance is constructed. Then, by obtaining the prediction error of system output using the motor current equation in the predictive reference frame, the optimal estimation of rotor position and speed in the KF algorithm is achieved based on the reduced-order model. This not only simplifies the calculation process but also enhances the position and speed estimation accuracy under dynamic conditions. Meanwhile, a prediction error rolling compensation algorithm is developed to minimize the estimation deviations caused by motor parameter variations. In addition, the system's dynamic performance is further improved with an adopted speed controller based on torque disturbance feedforward and acceleration feedback. Finally, experimental results verify the effectiveness and feasibility of the proposed strategy. © 1986-2012 ieee.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Using Quantum Resistant Variants of NIST IR 8454 Lightweight Encryption Algorithms in image Encryption 8

Using Quantum Resistant Variants of NIST IR 8454 Lightweight...

引用

8th International Artificial intelligence and Data processing symposium, IDAP 2024

作者： Kaya, Muhammed Saadetdin Iince, Kenan Ankara University Cyber Security Vocational School Ankara Turkey Inonu University Software Engineering Malatya Turkey

ISBN: (纸本)9798331531492

This work examines the potential of quantum resistant variants of NIST IR 8454 lightweight encryption algorithms in the field of image encryption. Selected algorithms from ASCON, TinyJAMBU and SPARKLE families were analyzed using various performance metrics. The research includes entropy analysis, correlation analysis, histogram analysis, NPCR and UACI tests, PSNR and SSIM tests, and calculation speed analysis. The results show that all tested algorithms meet the basic security requirements for image encryption. In particular, an increase in entropy of approximately 13 % in encrypted images, significant reduction in pixel correlations, and high sensitivity to small changes in the input image are observed. While ASCON80pq shows the fastest performance, all algorithms provide basic resistance to quantum attacks. This work reveals that quantumresistant lightweight encryption algorithms are promising for image security, especially in resource-constrained environments such as IoT. However, it is emphasized that these algorithms need to be further investigated in different image types, specific attack scenarios and real-world applications. © 2024 ieee.

关键词： Encryption algorithms

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：