检索结果-内蒙古大学图书馆

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Turukmane, Anil v. Adhikari, Aviraj Das Chandini, Kollati School of Computer Science and Engineering VIT-AP University AP Vijaywada India

ISBN: (纸本)9798331300579

Recommender systems make individualized suggestions for users based on their actions and preferences by utilizing machine learning (ML) and artificial intelligence (AI).. These systems have evolved significantly, incorporating various AI techniques like fuzzy techniques, transfer learning, genetic algorithms, neural networks, deep learning, and more. The use of AI in recommender systems aims to enhance prediction accuracy and address data sparsity issues.1 Key methodologies in recommender systems include deep neural networks, transfer learning, active learning, fuzzy techniques, evolutionary algorithms, natural language processing, and computer vision.1 These techniques play crucial roles in knowledge representation, reasoning, planning, communication, perception, and image processing within recommender systems.1 Machine Learning plays a vital role in recommendation systems by utilizing algorithms like KNN clustering, Naive Bayes, collaborative filtering and content filtering to suggest products to users overwhelmed by information on e-commerce platforms.4 Additionally, Recommender systems (RSs) are widely used across various domains such as e-commerce, tourism, health, and e-learning to enhance user experience and increase sales through personalized recommendations based on user preferences.5 RSs have become integral in guiding decisions for users in online transactions and improving the quality of their interactions with platforms like Amazon, Netflix, YouTube, Spotify, Facebook, and Twitter5 used to pinpoint people who are most at risk for developing complications from an illness or who are most likely to have poor treatment outcomes. These data can be used to develop personalized treatment plans for patients. © Grenze Scientific Society, 2024.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

PEPPR-DWS on FPGA: Elevating Universal Parallelism and Precision Through Pulse-Enhanced Push-Relabel and Diffusion Wave Search

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND systems 2025年第1期44卷 157-171页

作者： Dong, Zehua Zhang, Boyu Jiang, Yucheng Yu, Yu Li, Han Mai, Songping Tsinghua Univ Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China Peng Cheng Lab Dept Circuit & Syst Shenzhen 518066 Peoples R China

The push-relabel algorithm is recognized as one of the efficient algorithms in the field of graph cut, finding widespread applications in computer vision. While its pixel-level parallel implementations are prevalent, existing methods predominantly rely on checkerboard scheduling, imposing inherent constraints on neighborhood size, limited to four. This limitation compromises both algorithm precision and efficiency, hindering real-time and high-precision applications. To address these issues, this article introduces a novel approach to accelerate push-relabel algorithm implementation on FPGA in a more universal and efficient manner, supporting variable-sized image block operations. First, by introducing the deferred update strategy, we realize the pulse-enhanced parallel push-relabel (PEPPR) algorithm to address data contention and conflict in parallel processing. Second, the simultaneous weighted push method is proposed, further enhancing parallel operations. Lastly, we introduce the efficient diffusion wave search (DWS) algorithm to expedite algorithm convergence and reduce redundancy. While achieving a modest $1.7\times $ acceleration compared to state-of-the-art implementations, the proposed algorithm (PEPPR-DWS) successfully overcomes the inherent limitations of checkerboard scheduling in full pixel-level parallelism. In the test based on Middlebury benchmark v3, the proposed 8-neighborhood implementation exhibits a reduction of error rate by over 1% compared to the typical 4-neighborhood implementation. It provides a versatile and efficient solution for high-precision and real-time applications, holding substantial potential for practical applications.

关键词： Parallel processing Field programmable gate arrays Convergence Graphics processing units Scheduling Optimization Design automation Diffusion wave search (DWS) field programmable gate array (FPGA) acceleration hardware-friendly pixel-level parallelism push-relabel simultaneous weighted push (SWP)

来源：评论

学校读者我要写书评

暂无评论

Geolocation estimation of target vehicles using image processing and geometric computation

引用

NEUROCOMPUTING 2022年 499卷 35-46页

作者： Namazi, Elnaz Mester, Rudolf Lu, Chaoru Li, Jingyue Norwegian Univ Sci & Technol NTNU Dept Comp Sci Trondheim Norway Oslo Metropolitan Univ OsloMet Dept Civil Engn & Energy Technol Oslo Norway

Estimating vehicles' locations is one of the key components in intelligent traffic management systems (ITMSs) for increasing traffic scene awareness. Traditionally, stationary sensors have been employed in this regard. The development of advanced sensing and communication technologies on modern vehicles (Mvs) makes it feasible to use such vehicles as mobile sensors to estimate the traffic data of observed vehicles. This study aims to explore the capabilities of a monocular camera mounted on an Mv in order to estimate the geolocation of the observed vehicle in a global positioning system (GPS) coordinate system. We proposed a new methodology by integrating deep learning, image processing, and geometric computation to address the observed-vehicle localization problem. To evaluate our proposed methodology, we developed new algorithms and tested them using real-world traffic data. The results indicated that our proposed methodology and algorithms could effectively estimate the observed vehicle's latitude and longitude dynamically. (c) 2022 The Author(s). Published by Elsevier B.v. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Target-vehicle localization vision-based localization Geometric computation GPS coordinate system Mixed traffic

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection using CT Scans: image processing through Deep Learning - A Review 8

Lung Cancer Detection using CT Scans: Image Processing throu...

引用

8th International Conference on Communication and Electronics systems, ICCES 2023

作者： Asha, v. Bhavanishankar, K. Rns Institute of Technology Dept of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350396638

Lung cancer being one of the catastrophic diseases is haunting mankind from past seven decades. Unfortunately, early detection of lung cancer is unlikely, hence leading to highest mortality rates. However, various imaging modalities including Computed Tomography (CT) helps in detecting the lung cancer possible at the earliest. processing such huge data of CT scans is highly time demanding and Computed Aided Diagnosis system (CAD)does a great job from image acquisition till the detection/classification of lung nodules through series of processing stages. This research study covers all the processing stages and major contributions in those stages. This study also summarizes various methods used in basic image processing through deep learning algorithms. A tabulation of various datasets and metrics descriptions is also discussed. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Spatio-Temporal video Denoising Co-Processor With Adaptive Codec

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems I-REGULAR PAPERS 2023年第11期70卷 4223-4234页

作者： Shi, Gang Wang, Xianglong Ouyang, Yichen Yao, Ruoheng Chen, Zhuoyu Zhang, Wei Chen, Lei An, Fengwei Southern Univ Sci & Technol Sch Microelect Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Sch Microelect Minist Educ Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Engn Res Ctr Integrated Circuits Next Generat Comm Minist Educ Shenzhen 518055 Peoples R China

With the increasing demand for high-resolution video and real-time processing, the limited efficiency of video-denoising algorithms has become a critical factor. This paper proposes a spatio-temporal video denoising co-processor to suppress an image sequence's spatial and temporal noise. Temporal denoising is achieved by merging the current and previous frames at the pixel level in which the current frame is processed by a spatial filter. After exploiting noise estimation and motion detection, the Wiener filter calculates the merge ratio. Rather than buffering the entire previous frame, the JPEG-like codec can dynamically adjust the compression ratio through a predefined quantization table to satisfy the designed on-chip storage. The experimental results demonstrate that the spatio-temporal denoising co-processor can effectively eliminate the fluctuation of the grayscale value of the noise in videos. Simultaneously, the adaptive codec can reduce the storage space consumption for the frame buffer by at least 80% of the original size. To the best of our knowledge, this is the first fully integrated spatio-temporal denoising co-processor without any external memory. Additionally, the grayscale, RGB, and RAW versions of the co-processor are also implemented on the Stratix v FPGA platform and synthesized in 28nm CMOS technology.

关键词： Streaming media Wiener filters image coding Hardware Estimation Real-time systems Low-pass filters Noise reduction FPGA image compression motion estimation

来源：评论

学校读者我要写书评

暂无评论

Smart and Quick Parking Spot Detection 15

Smart and Quick Parking Spot Detection

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： veeramalla, Santhosh Kumar Gali, Rama Lakshmi Ranjeeth, M. Tara, Saikumar Hindumathi, v. Bhargava Kumar, L. Bvrit Hyderabad College of Engineering for Women Department of Ece Hyderabad India

ISBN: (纸本)9798350370249

The rapid expansion of urban areas has intensified the challenge of finding parking spaces for drivers. Intelligent parking systems emerge as a crucial solution by providing real-time detection of available spaces. While various methods exist, from basic magnetic sensors to advanced computer vision algorithms, their effectiveness can be hindered by environmental factors. Recognizing the importance of automated systems, this paper focuses on implementing an image processing approach for parking space detection. By strategically placing cameras in parking lots, the system identifies vacant spaces and transforms images to determine availability. Integrating these techniques into mobile applications could further aid drivers in locating parking spots, improving their overall experience. Ultimately, accurate and efficient parking space identification is vital for reducing congestion, enhancing air quality, and improving urban environments. © 2024 IEEE.

关键词： CCTv Computer vision image processing Parking availability Parking guidance Smart parking Sustainable cities

来源：评论

学校读者我要写书评

暂无评论

DeepAID: a design of smart animal intrusion detection and classification using deep hybrid neural networks

引用

SOFT COMPUTING 2023年 1-12页

作者： varun, S. Sajithra Nagarajan, G. MVJ Coll Engn Dept IIoT Bengaluru Karnataka India Sathyabama Inst Sci & Technol Dept Comp Sci & Engn Chennai India

Animal incursion is a significant problem in many locations, including roads, rural communities, and base camps for different camps. This has an influence on food security since the primer of animals will decrease agricultural land output and reduce farmers' profits. There must be a means to identify animals before they enter locations they should not be, so that appropriate measures may be taken to stop their incursion and its effects. Since a few decades ago, the study of detecting wild animals has been active. In this paper, a method for detecting animals is proposed utilizing developments in Deep Learning algorithm approaches. With the help of this deep learning technology, it is possible to identify animals in advance and take the proper security measures to prevent harm from animal entry. This study includes image processing and artificial intelligence for animal detection, species categorization, and automatic animal identification using CNN, an alarm unit, and an animal repellent circuit design. The proposed system experiments on the Amur Tiger Re-identification in the Wild datasets, Animals Detection images Dataset, and Using Google Open images v6+, the dataset for detecting animals (objects) was retrieved. Deep Convolutional Neural Network is used to extract these characteristics from cluttered photos. Hybrid CNN models were employed in the system's implementation, which was done on a regular camera trap database. Finally, CNN features were supplied to the top categorization deep learning algorithms. Our results show that our proposed method is better than other systems that have been mentioned in the literature.

关键词： Animal Intrusion CNN Hybrid CNN Artificial Intelligence image processing Animal repellent

来源：评论

学校读者我要写书评

暂无评论

image Pre-processing Effects on Attention Modules in Facial Emotion Recognition 12

Image Pre-processing Effects on Attention Modules in Facial ...

引用

12th IFAC Symposium on Biological and Medical systems (BMS)

作者： Arabian, H. Wagner-Hartl, v Moeller, K. Furtwangen Univ Inst Tech Med ITeM D-78054 Villingen Schwenningen Germany Furtwangen Univ Campus Tuttlingen D-78532 Tuttlingen Germany

Neural Networks have achieved a reputation for their ability to outperform traditional machine learning algorithms. The robustness of network models to unseen data is important. In this study the implementation of an attention module to an existing network architecture is studied for robustness improvement with extensive image pre-processing for facial emotion recognition, a component in a closed loop feedback system being developed for the emotional training of people with autism spectrum disorder. The squeeze and excitation (SE) attention module was selected and combined with the network architecture of vGG16. The performance of the model, trained with the OULU-CASIA dataset, was based on statistical data generated from validation accuracies with a 10-fold partition, while the robustness analysis was based on data generated from cross database prediction accuracies. The visualization technique of Grad-CAM was used to observe the regions of impact on classification. validation accuracies of up to 98.39% were achieved and generalization performance was 52.43% on the FACES, and 26.10% on the JAFFE datasets. The improvements of the SE over the base model were observed in the visualizations of the validation datasets. Data analyzed showed that extensive image pre-processing diminished effects of SE in relation to model robustness. Copyright (C) 2024 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： Attention modules Autism spectrum disorder Deep learning Model robustness Prediction visualizations

来源：评论

学校读者我要写书评

暂无评论

A WEB APPLICATION FOR ULTRASONIC NONDESTRUCTIvE TESTING ANALYSIS 51

A WEB APPLICATION FOR ULTRASONIC NONDESTRUCTIVE TESTING ANAL...

引用

51st Annual Review of Progress in Quantitative Nondestructive Evaluation (QNDE)

作者： Guarneri, Giovanni A. Pegorini, vinicius Pipa, Daniel R. Pires, Gustavo P. Nunes, Maria Isabela S. Forlini, Felipe Passarin, Thiago A. R. Univ Tecnol Fed Parana Pato Branco Brazil Univ Tecnol Fed Parana Curitiba Parana Brazil Petrobras SA Rio De Janeiro Brazil

ISBN: (纸本)9780791888162

Identifying and mapping corrosion represents a significant challenge in maintaining oil production systems. Mechanical and chemical phenomena, such as abrasion and hydrogen attack, cause corrosion on the internal surface of pipes. Knowing the dimensions of corrosion enables technicians to make decisions about the structural stability of pipelines under operating conditions. Using ultrasound imaging is a non-destructive approach to assessing the state of internal surfaces. We present a web application for processing ultrasound signals and image reconstruction. However, it can be used in any non-destructive ultrasound inspection application. The software is developed mainly in Python and Typescript, using a different approach than conventional web applications. Instead of using a standard structure, with the front-end running in the browser and the back-end running the data processing on a remote server, our application runs entirely on the browser through Pyodide, a Python distribution for the browser and *** based on WebAssembly whilst the server side only hosts the web application files. The application is divided into modules for (i) graphical interface, (ii) reading inspection files, (iii) signal preprocessing, (iv) estimation of inspection parameters, (v) external surface detection (for inspection by immersion), and (vi) image reconstruction. The web application allows Python script execution and offers a user-friendly interface for running image reconstruction algorithms. This paper describes the development of critical features and indicates the chosen implementation of algorithms. The current state of development is presented, and the next steps toward the ultimate goal of corrosion mapping are defined.

关键词： Ultrasonic NDT image reconstruction Web application

来源：评论

学校读者我要写书评

暂无评论

Building Structures image Matching Using Convolutional Neural Network

Building Structures Image Matching Using Convolutional Neura...

引用

2024 systems of Signals Generating and processing in the Field of on Board Communications, SOSG 2024

作者： Andriyanov, N.A. Magdeev, R.G. Dementyiev, v.E. Financial University under the Government of the Russian Federation Moscow Russia Ulyanovsk State Technical University Ulyanovsk Russia National Research Mordovia State University Saransk Russia

ISBN: (纸本)9798350383614

The paper examines the features of combining multi-temporal and multi-angle images of building structures in order to identify critical changes. It is proposed to carry out such a combination on the basis of high-speed pseudogradient algorithms. The focus of the work is the problem of identifying areas of attention that are the source of combined points. It is proposed to perform such selection using convolutional neural networks of the YOLO family. The consistency of this approach is shown and estimates of the resulting gains are also calculated. It is also suggested to use different optimization methods for improving the processing speed. So the YOLO detector will be very high performance and efficient real time detector. ©2024 IEEE.

关键词： Object detection

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：