检索结果-内蒙古大学图书馆

2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024

作者： Gelmez, Mustafa Kirmizi, Baki Altinel, Doğay Istanbul Medeniyet University Istanbul Turkey

ISBN: (纸本)9798350379433

In recent years, the automotive industry has entered a revolutionary new era with the rise of electric and autonomous vehicles. This development is expected to change not only the functioning of vehicles but also lifestyles and the overall dynamics of society. image processing and artificial intelligence applications used in autonomous vehicles can work together to ensure the safety of passengers and all traffic participants. In this study, the enabling technologies for autonomous vehicles to operate safely and efficiently are proposed and their performances are presented. In this context, the study presents a road lane detection algorithm that employs methods such as Gaussian blur, Canny edge detection, and Hough transform. This process enhances driving safety by allowing vehicles to recognize and follow lanes on the road. Additionally, this study implements a traffic sign detection and classification application using a deep learning model suitable for real life conditions. In order to improve the safety of driving experience by ensuring vehicles recognize traffic signs and react appropriately, an RF based communication system is also proposed and implemented. The results show that an accuracy value of 97.25% is achieved in our road lane detection application, and a recall value of 92.7% is obtained in the traffic sign detection model trained on our dataset. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Advancement in Sericulture Using image processing 2nd

Advancement in Sericulture Using Image Processing

引用

2nd International Conference on Computational Intelligence in Machine learning, ICCIML 2022

作者： Kumar, Kishor Pavan, N. Yashas, R. Rajesh, R. Rakshith, B.G. Department of Electronics and Communication Engineering Don Bosco Institute of Technology Mysore Road Kumbalagodu Bangalore India

ISBN: (纸本)9789819979530

The need for silk clothes is very high worldwide, and it is in high demand every year. To meet market demand, silkworm cocoons will be chosen much more often as the raw material for silk. The primary issue with the current scenario is that the identification procedure is ineffective. High-quality cocoons and faulty cocoons are now distinguished primarily by manual selection. To aid employees in choosing silkworm cocoons, automated optical equipment needs to be developed. deep learning, particularly the YOLO algorithm, has been increasingly popular in recent years and has steadily replaced other techniques for classifying images. We created a data collection of silkworm cocoons and created a machine learning model to categorize them in order to construct a model for silkworm cocoon categorization. For conventional convolutional neural networks, the fully connected layer frequently houses the majority of the parameters for the entire model, requiring a significant amount of processing time and resources during forward propagation. Due to the fact that our suggested solution is a live capturing system, computational time is reduced. The live image of the cocoon is captured using a mobile camera. The proposed architecture yields a higher accuracy, as shown by experimental findings, making it possible to utilize cocoon categorization in industry very soon. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Optical data processing

来源：评论

学校读者我要写书评

暂无评论

real-time Defect and Object Detection in Assembly Line: A Case for In-Line Quality Inspection 32nd

Real-Time Defect and Object Detection in Assembly Line: A Ca...

引用

32nd International Conference on Flexible Automation and Intelligent Manufacturing

作者： Ashourpour, Milad Azizpour, Ghazaleh Johansen, Kerstin Jonkoping Sch Engn S-55111 Jonkoping Sweden Husqvarna AB S-56182 Huskvarna Sweden

ISBN: (纸本)9783031382406;9783031382413

Identification of flawed assemblies and defective parts or products as early as possible is a daily struggle for manufacturing companies. With the ever-increasing complexity of assembly operations and manufacturing processes alongside the need for shorter cycle times and higher flexibility of productions, companies cannot afford to check for quality issues only at the end of the line. Inline quality inspection needs to be considered as a vital part of the process. This paper explores use of a real-time automated solution for detection of assembly defects through YOLOv8 (You Only Look Once) deep learning algorithm which is a class of convolutional neural networks (CNN). The use cases of the algorithm can be extended into detection of multiple objects within a single image to account for not only defects and missing parts in an assembly operation, but also quality assurance of the process both in manual and automatic cells. An analysis of YOLOv8 algorithm over an industrial case study for object detection shows the mean average precision (mAP) of the model on the test dataset and consequently its overall performance is extremely high. An implementation of this model would facilitate in-line quality inspection and streamline quality control tasks in complex assembly operations.

关键词： In-line Quality Inspection Computer Vision deep learning YOLOv8 Assembly Line

来源：评论

学校读者我要写书评

暂无评论

Ensemble Random Forest-based Gradient Optimization based Energy Efficient Video processing System for Smart Traffic Surveillance System

引用

IETE JOURNAL OF RESEARCH 2024年第9期70卷 7175-7191页

作者： Rajagopal, S. Devi, M. Uma Jones, G. Maria Nayagam, M. Gomathy Natl Engn Coll Dept Informat Technol Kovilpatti India SRM Inst Sci & Technol Dept Comp Technol Chennai India Sathyabama Inst Sci & Technol Dept Comp Sci & Engn Chennai India Ramco Inst Technol Dept Comp Sci & Business Syst Rajapalayam India

deep learning solutions in big data applications can benefit cloud centres and can also lead to network communication overhead. Typically, data collected from traffic are sent to the traffic management centre for analysis. However, this process can worsen the network route to the traffic management centre. A two-tier mechanism has been developed to address this issue, which performs vehicle speed estimation and traffic congestion detection for efficient traffic management. The real-time traffic video data are captured and the video frames are initially processed through a foreground extraction process, which extracts the temporarily stopped vehicles on the road by removing background pixels from the frames. The video frames are then wrapped in an up-down view to remove the influence of the observation angle. The traffic congestion is then detected accurately based on the traffic characteristics using the proposed Ensemble Random Forest-based Gradient Optimization (ERF-GO) algorithm. The generalization error occurs when learning complex features on frames is minimized using a gradient-based optimization (GO) algorithm. Finally, the learned information on traffic conditions is forwarded to the cloud and edge computing environments based on network connection speed. The efficiency of the proposed ERF-GO is investigated in terms of performance metrics, namely root mean square error, speed detection error, execution time, computational cost, accuracy, latency, workload balance, precision, recall, f-measure, and congestion detection error rate. The analytic result displays that the proposed ERF-GO algorithm attains a greater accuracy rate of about 98.65% in detecting traffic congestion which is comparably higher than state-of-the-art methods.

关键词： Edge computing Ensemble random forest Gradient-based optimization algorithm Traffic congestion Vehicle speed Video frames

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of visible infrared person re-identification from an application perspective

引用

Multimedia Tools and Applications 2024年第42期83卷 90243-90270页

作者： Chang, Hua Xu, Xin Liu, Wei Lu, Lingyi Li, Weigang School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China

Person re-identification (ReID) is a significant issue in computer vision, aiming to match the same pedestrian across various cameras. Recent research on this issue has successfully reached a satisfactory performance level in the daytime scenario. However, the performance of ReID in low illumination scenarios suffers a dramatic degradation due to the insufficient personal information captured by visible cameras in low or no light scenarios. To address this challenge, the adoption of novel camera technologies for more effective pedestrian data is imperative. Owing to the constraints of distance and usage scenarios in deploying depth cameras, practical infrared cameras are frequently utilized, spurring research in visible infrared person re-identification (VI-ReID). Significant progress has been made in the field of VI-ReID in recent years, but only a few reviews have categorized this problem based on methodology. This article offers a novel perspective by classifying VI-ReID according to application scenarios. Following our categorization scheme, the main advancements in deep learning for VI-ReID over the past five years have been grouped into three categories as follows: retrieval of infrared images using visible images (V→IR), retrieval of visible images using infrared images (IR→V), and joint retrieval of infrared and visible images (V→IR and IR→V). Next, this survey outlines the available datasets and evaluation metrics. After that, we categorize diverse methodologies under the proposed classification and assess their performance metrics across common datasets. Finally, we present two prospective avenues for future research in this domain, informed by the current state of advancement. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

On Site Personnel Access Monitoring and Early Warning in Photovoltaic Field Based on AI image Recognition 16

On Site Personnel Access Monitoring and Early Warning in Pho...

引用

16th IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2024

作者： Zheng, Wenjin Wang, Yajun Xu, Xiaochen Chu, Hao Jin, Danyang Fang, Shibiao Powerchina Huadong Engineering Corporation Limited Hangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798350386127

The study aims to enhance the management and monitoring of photovoltaic (PV) construction sites, which are often located in remote areas with challenging conditions. Traditional monitoring methods are inefficient, costly, and prone to errors, necessitating the integration of advanced image recognition technology to improve site management. The research introduces image recognition technology, a core aspect of artificial intelligence (AI) and computer vision (CV), to automate the detection and monitoring of equipment, personnel behavior, materials, and construction progress at PV sites. The process involves real-time data collection via high-definition cameras, automated anomaly detection, reporting, and historical data analysis using advanced deep learning models like YOLO. The study developed an efficient and adaptive image recognition model tailored to the complexities of PV construction sites. The model successfully improves the accuracy of detecting safety hazards, optimizes resource utilization, and enhances the overall safety and efficiency of the construction process. The findings highlight the potential of image recognition technology to significantly improve the management of PV construction sites. As the technology advances and becomes more cost-effective, its application is expected to drive higher levels of efficiency, reliability, and safety in the renewable energy sector, supporting the industry's sustainable growth. © 2024 IEEE.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image Analysis Using Cloud-Based Support Vector Machines

引用

SN Computer Science 2024年第6期5卷 719页

作者： Haut, Juan M. Franco-Valiente, Jose M. Paoletti, Mercedes E. Moreno-Álvarez, Sergio Pardo-Diaz, Alfonso Department of Technology of Computers and Communications Universidad de Extremadura CETA-CIEMAT Center of Extremadura for Advanced Technologies Department of Computer Systems and Languages National University of Distance Education

Hyperspectral image processing techniques involve time-consuming calculations due to the large volume and complexity of the data. Indeed, hyperspectral scenes contain a wealth of spatial and spectral information thanks to the hundreds of narrow and continuous bands collected across the electromagnetic spectrum. Predictive models, particularly supervised machine learning classifiers, take advantage of this information to predict the pixel categories of images through a training set of real observations. Most notably, the Support Vector Machine (SVM) has demonstrate impressive accuracy results for image classification. Notwithstanding the performance offered by SVMs, dealing with such a large volume of data is computationally challenging. In this paper, a scalable and high-performance cloud-based approach for distributed training of SVM is proposed. The proposal address the overwhelming amount of remote sensing (RS) data information through a parallel training allocation. The implementation is performed over a memory-efficient Apache Spark distributed environment. Experiments are performed on a benchmark of real hyperspectral scenes to show the robustness of the proposal. Obtained results demonstrate efficient classification whilst optimising data processing in terms of training times. © The Author(s) 2024.

关键词： Cloud computing (CC) Hyperspectral imaging (HSIs) Machine learning (ML) Remote sensing (RS) Support vector machines (SVMs)

来源：评论

学校读者我要写书评

暂无评论

real-time Non-Invasive Imaging and Detection of Spreading Depolarizations through EEG: An Ultra-Light Explainable deep learning Approach

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第10期28卷 5780-5791页

作者： Wu, Yinzhe Jewell, Sharon Xing, Xiaodan Nan, Yang Strong, Anthony J. Yang, Guang Boutelle, Martyn G. Imperial Coll London Dept Bioengn London SW7 2AZ England Royal Brompton Hosp Cardiovasc Res Ctr London SW3 6NP England Kings Coll London Acad Neurosci Ctr Inst Psychiat Psychol & Neurosci Dept Basic & Clin Neurosci London SE5 8AF England Imperial Coll London Dept Bioengn London W12 7SL England Imperial Coll London Imperial X London W12 7SL England Imperial Coll London Natl Heart & Lung Inst London SW7 2AZ England Royal Brompton Hosp Cardiovasc Res Ctr London SW3 6NP England Kings Coll London Sch Biomed Engn & Imaging Sci London WC2R 2LS England

A core aim of neurocritical care is to prevent secondary brain injury. Spreading depolarizations (SDs) have been identified as an important independent cause of secondary brain injury. SDs are usually detected using invasive electrocorticography recorded at high sampling frequency. Recent pilot studies suggest a possible utility of scalp electrodes generated electroencephalogram (EEG) for non-invasive SD detection. However, noise and attenuation of EEG signals makes this detection task extremely challenging. Previous methods focus on detecting temporal power change of EEG over a fixed high-density map of scalp electrodes, which is not always clinically feasible. Having a specialized spectrogram as an input to the automatic SD detection model, this study is the first to transform SD identification problem from a detection task on a 1-D time-series wave to a task on a sequential 2-D rendered imaging. This study presented a novel ultra-light-weight multi-modal deep-learning network to fuse EEG spectrogram imaging and temporal power vectors to enhance SD identification accuracy over each single electrode, allowing flexible EEG map and paving the way for SD detection on ultra-low-density EEG with variable electrode positioning. Our proposed model has an ultra-fast processing speed (<0.3 sec). Compared to the conventional methods (2 hours), this is a huge advancement towards early SD detection and to facilitate instant brain injury prognosis. Seeing SDs with a new dimension - frequency on spectrograms, we demonstrated that such additional dimension could improve SD detection accuracy, providing preliminary evidence to support the hypothesis that SDs may show implicit features over the frequency profile.

关键词： Electroencephalogram (EEG) deep learning spreading depolarization (SD) spreading depolarization (SD) traumatic brain injury (TBI) traumatic brain injury (TBI) spreading depolarization (SD) traumatic brain injury (TBI)

来源：评论

学校读者我要写书评

暂无评论

Harnessing Generative AI for IoT Enhanced Education

Harnessing Generative AI for IoT Enhanced Education

引用

2024 IEEE International Conference on Signal processing, Informatics, Communication and Energy Systems, SPICES 2024

作者： Priya, K.M. Soundarya, P. Kungumaraj, E. Bhagyarathi, P. Subathra, P. Varghese, Susmi Mariam Sri Eshwar College of Engineering Department of Science and Humanities Coimbatore India Akshaya College of Engineering and Technology Department of Science and Humanities Coimbatore India Nehru Institute of Engineering and Technology Department of Science and Humanities Coimbatore India Karpagam College of Engineering Salome Department of Science and Humanities Coimbatore India Sri Krishna College of Engineering and Technology Department of Science and Humanities Coimbatore India

ISBN: (纸本)9798350376135

This paper explores the integration of Generative Artificial Intelligence (AI) techniques with the Internet of Things (IoT) to revolutionize educational paradigms. Leveraging Generative AI, such as deep learning models, alongside IoT devices opens up new avenues for personalized and immersive learning experiences. Through the analysis of real-time data collected by IoT sensors, coupled with Generative AI's ability to synthesize content, educational environments can be dynamically adapted to individual learning styles and preferences. This abstract presents a framework for the synergy between Generative AI and IoT, emphasizing their combined potential to create interactive educational platforms. By harnessing Generative AI for content generation and IoT for data collection and analysis, educational systems can be tailored to cater to diverse learners, fostering engagement, retention, and comprehension. The integration of these technologies promises to reshape the landscape of education, offering adaptive, interactive, and enriched learning experiences for students across various disciplines and demographics. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

deep Neural Labeling: Hybrid Hand Pose Estimation Using Unlabeled Motion Capture Data With Color Gloves in Context of German Sign Language 6

Deep Neural Labeling: Hybrid Hand Pose Estimation Using Unla...

引用

6th IEEE International Conference on Artificial Intelligence and eXtended and Virtual reality, AIxVR 2024

作者： Waldow, Kristoffer Fuhrmann, Arnulph Roth, Daniel Computer Graphics Group Th Köln Cologne Germany Technical University of Munich Klinikum Rechts der Isar Orthopedics and Sports Orthopedics Munich Germany

ISBN: (纸本)9798350372021

Hands are fundamental to conveying emotions and ideas, especially in sign language. In the context of virtual reality, motion capture is becoming essential for mapping real human movements to avatars in immersive environments. While current hand motion capture methods feature partly great usability, accuracy, and real-time performance, they have limitations. Industry-standard motion capture methods with sensor gloves lead to acceptable results, but still produce occasional errors due to proximity of the fingers and sensor drifts. This, in turn, requires time-consuming correction and manual labeling of optical markers during post-processing for offline use cases and prohibits the use in real-time scenarios as VR communication. To overcome these limitations, we introduce a novel hybrid hand pose estimation method that leverages both an optical motion capture system and a color-coded fabric glove. This approach merges the strengths of both techniques, enabling the automated labeling of 3D marker positions through a data-driven machine-learning approach. Using a spherical capture rig and a deep learning algorithm, we improve efficiency and accuracy. The labeled markers then drive a robust optimization procedure for solving hand posture, accounting for limitations in finger movements and validation checks. We evaluate our system in the context of German sign language where we achieve an accuracy of 97% correct marker assignments. Our approach aims to enhance the accuracy and immersion of sign language communication in VR, making it more inclusive for both deaf and hearing people. © 2024 IEEE.

关键词： Virtual reality

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：