检索结果-内蒙古大学图书馆

Advancement in Data Science, E-learning and Information systems (ICADEIS), international conference on

作者： Ahmad Hunain Indrabayu Amil Ahmad Ilham Department of Informatics Hasanuddin University Makassar Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

This study develops a real-time vehicle detection, tracking, and counting system by integrating the You Only Look Once (YOLO) algorithm with the Kalman Filter. The system is designed to detect multiple types of vehicles, track their movements across frames, and count the number of vehicles crossing a detection line in traffic videos. YOLO is employed for vehicle detection by generating bounding boxes and class labels, while the Kalman Filter ensures robust and stable tracking, even in scenarios with interrupted detections or occlusions. The system was evaluated on real-world traffic videos and demonstrated high accuracy in vehicle detection, achieving a Mean Average Precision (mAP) of 96.7% after 200 training epochs. The system effectively counts vehicles with minimal errors, particularly for larger vehicles like cars and trucks. With an average processing speed of 25 frames per second (FPS), the system is capable of meeting real-time application demands. Additionally, dense traffic conditions with significant vehicle overlaps can impact detection and tracking accuracy. To address these limitations, future work is suggested, including retraining the model using localized datasets to improve performance under specific conditions, integrating complementary sensors such as LIDAR for better spatial awareness, and optimizing the system for deployment on embedded devices. This system has substantial potential for implementation in intelligent transportation applications, such as traffic flow analysis, violation detection, and data-driven transportation management, contributing to advancements in smart city infrastructure.

关键词： YOLO Accuracy Tracking Vehicle detection Transportation Radar tracking real-time systems Kalman filters Videos Meteorology

来源：评论

学校读者我要写书评

暂无评论

Perceptual Learning Technology Based on Computer Vision and Machine Learning Algorithms

Perceptual Learning Technology Based on Computer Vision and ...

引用

international conference on Communication systems and Network Technologies (CSNT)

作者： Tianjian Wang School of Computer Science and Technology Wuhan Qingchuan University Wuhan China

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

To address the issue of low accuracy and poor robustness of perceptual learning in complex scenarios, a new method integrating computer vision and machine learning is adopted, that is, by applying deep neural networks, transfer learning and self-supervised learning, combined with multimodal data fusion strategy, to improve target recognition efficiency and learning ability. First, based on the preprocessing algorithm of improved Gaussian filtering and image segmentation, the quality of image features is improved. Data enhancement methods such as random rotation, flipping, and blurring are used to expand data distribution and improve model adaptability. Secondly, a convolutional neural network (CNN) is utilized in combination with an attention mechanism to extract multi-scale target features, and transfer learning is applied to transfer common features from pre-trained models to reduce dependence on large-scale labeled data. Finally, a contrastive learning framework is constructed to mine the correlation of unlabeled data. Transformer is used to realize the fusion of multimodal data of images and texts, and the model performance is optimized through multi-task learning. The mAP (Mean Average Precision) of the traditional method in dynamic occlusion scenarios is 60.5%, which is relatively weak. This may be because the traditional method cannot fully extract the effective features of the target under the occlusion of complex moving targets. The mAP of the method in this paper is 72.8%, which is higher than that of the traditional method. The perceptual learning method adopted in this paper effectively improves the accuracy and robustness in complex scenarios, and provides reliable technical support for intelligent applications. In the future, it can be combined with edge computing to further optimize the real-time processing capability and promote its application in the fields of unmanned driving and intelligent security.

关键词： Adaptation models Computer vision Image segmentation Machine learning algorithms Computational modeling Transfer learning Feature extraction Data models Robustness real-time systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Modeling and Low Complexity Implementation of Rate Estimation in Versatile Video Coding

Efficient Modeling and Low Complexity Implementation of Rate...

引用

international conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yanze Wang Tianyi Sun Hui Zhao Jun Sun Wangxuan Institute of Computer Technology Peking University Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In Versatile Video Coding (VVC), Rate-Distortion Optimized Quantization (RDOQ) is a widely adopted technique to strike a balance between bit rate and distortion. However, the computational complexity introduced by RDOQ poses significant challenges for real-time applications. To address this issue, we propose a low-complexity rate estimation model to accelerate the conventional RDOQ approach. Through comprehensive analysis, we have identified the generalized Gaussian distribution (GGD) as an efficient model for simulating the distribution of transform coefficients. Leveraging this insight, we developed a GGD-based rate estimator to expedite the selection of quantization levels. Experimental results demonstrate that the proposed model achieves an average encoding time reduction of 13.15%, with only a minimal impact on BD-Rate.

关键词： Video coding Quantization (signal) Computational modeling Rate-distortion Estimation Transforms Gaussian distribution Streaming media real-time systems Speech processing

来源：评论

学校读者我要写书评

暂无评论

Blockchain for Data Traceability: Ensuring Integrity in Digital Ecosystems

Blockchain for Data Traceability: Ensuring Integrity in Digi...

引用

Computational Intelligence Approaches and applications (ICCIAA), international conference on

作者： Ali Al Maqousi Enrique Arias Jose Antonio Mateo Department of Information Security University of Petra Amman Jordan Department of Information Systems University of Castilla-La Mancha Campus Universitario Albacete Spain

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

In the modern world, where digital ecosystems are shifting towards data-oriented, data must be traceable and highly integrity. This paper aims to define the possibilities of blockchain technology to improve data tracking, emphasizing the supply chain, healthcare, and finance sectors. We explore how blockchain can be embedded in current digital environments, review the literature, and assess real-life examples and potential issues and benefits of blockchain regarding scalability, energy usage, and legal concerns. The study reveals that blockchain can offer a clear, secure, and tamper-proof record of data but at the same time examines the technological and managerial challenges associated with this technology's use.

关键词： Supply chain management Reviews Data integrity Scalability Ecosystems Supply chains Medical services Proof of Work Consensus protocol Security

来源：评论

学校读者我要写书评

暂无评论

Lightweight Deep Learning Model for Airborne Object Classification

Lightweight Deep Learning Model for Airborne Object Classifi...

引用

international conference on Communication systems and Network Technologies (CSNT)

作者： Vamsi Krishna Puduru Bethi Pardhasaradhi Sagar Koorapati Linga Reddy Cenkeramaddi ICT Dept. University of Agder Norway CSE Dept. Indian Institute Of Information Technology Design & Manufacturing Kurnool India CPU Design Group Qualcomm Technologies Austin TX

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

Airborne object detection and classification play an important role in applications like military surveillance, border security, and public safety. The ability to accurately distinguish between airplanes, helicopters, drones, and birds is essential for monitoring and responding to potential aerial threats in real-time. This study leverages the AOD 4 dataset, which contains a comprehensive collection of 22,516 images spanning diverse environmental conditions. After organizing the dataset into four distinct classes, a custom lightweight Convolutional Neural Network (CNN) was developed to classify airborne objects. The proposed lightweight CNN achieves a remarkable accuracy of 97.12% and is able to outperform state-of-the-art pre-trained models in terms of accuracy and model size. On top of it, the model is also targeted at the various processors to unleash its potential to run in a real-time environment. The proposed model infers in 2.9 milliseconds on intel core i7 processor, which is a fourfold improvement compared to the MobileNetv3Small model. The findings from this study contribute to advancing the field of airborne object classification and pave the way for more robust real-world implementations.

关键词： Deep learning Accuracy Program processors Atmospheric modeling Surveillance Computational modeling real-time systems Public security Convolutional neural networks Security

来源：评论

学校读者我要写书评

暂无评论

Hierarchical embedded System Based on FPGA for Classification of Respiratory Diseases

引用

ieee Access 2025年 13卷 93017-93032页

作者： Trong-Thanh Han Kien Le Trung Phuong Nguyen Anh Anh Do Trung School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Vietnam Department of Science and Technology Management and International Cooperation Posts and Telecommunications Institute of Technology Hanoi Vietnam

Objectives: This research aims to design and develop a hierarchical embedded system that utilizes respiratory sound features for diagnosing COPD and other respiratory disorders. The system is engineered to achieve high accuracy and efficiency while minimizing energy consumption, making it suitable for deployment in mobile devices or embedded systems. Methods: Lung sounds are segmented into individual breathing cycles. Thirty-nine main respiratory features in the time and frequency domains are extracted and organized into four layers. The Random Forest algorithm and Artificial Neural Network are fine-tuned with the dataset and applied to disease classification. The first layer contains recorded information, while the second and third layers contain features extracted from fixed-length sound segments classified via Random Forest. The fourth layer utilizes Wavelet Transform to convert breathing patterns into Spectrogram images, which the Artificial Neural Network processes for disease diagnosis. The system is implemented on the Xilinx PYNQ-Ultra96-V2 FPGA development board. Results: The system achieves the highest accuracy of 98.81% for five disease classes: COPD, Healthy, URTI, Bronchitis, and Pneumonia, and saves 52.5% of energy consumption compared to CPU-GPU-based traditional methods. Conclusion: This study demonstrates the effectiveness of the proposed method in diagnosing COPD and other respiratory disorders. The hierarchical embedded system is designed with high accuracy and energy efficiency, with potential real-world applications to support clinical diagnosis.

关键词： Feature extraction Mel frequency cepstral coefficient Chronic obstructive pulmonary disease Accuracy Lungs Field programmable gate arrays Support vector machines Convolutional neural networks Classification algorithms Machine learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Optimal Control for Continuous-time Quantized systems via Adaptive Dynamic Programming

Reinforcement Learning-Based Optimal Control for Continuous-...

引用

ieee SSD international Multi-conference on systems, Signals and Devices

作者： Omar Qasem Weinan Gao Omar R. Daoud Electrical and Computer Engineering Department School of Engineering and Computing American International University Al-Jahra Kuwait State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang Lianning China

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

Ahstract- This paper presents a comprehensive investigation into the stability analysis and design conditions for quantizers to ensure the closed-loop stability of continuous-time linear quantized systems, under the conditions derived by the small-gain theorem. The study begins by deriving explicit bounds on the quantizer parameters required for maintaining system stability. Building on this foundation, an optimal controller is designed using the linear quadratic regulator (LQR) framework, providing an efficient data-driven control strategy. To further enhance the system's performance, an adaptive dynamic programming (ADP) algorithm, referred to as the hybrid iteration (HI) method, is developed. This algorithm effectively learns the optimal control policy by leveraging the trajectories of the quantized states and inputs, thereby addressing the challenges posed by quantization constraints. The proposed HI approach combines the advantages of adaptive learning and optimization, making it well-suited for continuous-time systems with limited information. The simulation results confirm that the ADP approach with the provided conditions not only stabilizes the quantized system but also achieves optimal control performance under the specified quantization conditions. This study offers valuable insights and a robust methodological framework for addressing stability and control challenges, with insights to be expanded to continuous-time nonlinear quantized systems, with potential applications in various engineering domains, such as networked systems, robotics and autonomous systems.

关键词： Quantization (signal) Adaptive systems Regulators Simulation Heuristic algorithms Optimal control Stability analysis Dynamic programming Trajectory Thermal stability

来源：评论

学校读者我要写书评

暂无评论

PosturalNet, an Advanced Architecture to Detect Shoplifting at Megastores

PosturalNet, an Advanced Architecture to Detect Shoplifting ...

引用

international conference on Communication systems and Network Technologies (CSNT)

作者： Mohd Aquib Ansari Shahnawaz Ahmad Arvind Mewada Sushil Kumar Maurya SCSET Bennett University Greater Noida India ITER Siksha ’O’ Anusandhan University Bhubaneswar Odisha

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

Human activity recognition (HAR) requires a full understanding of postural dynamics to create sophisticated surveillance systems that specifically detect shoplifting activities. PosturalNet represents a new architectural framework that uses human postural analytics to detect shoplifting incidents in large retail spaces. The proposed method uses a 2D body joint detection algorithm named OpenPose to extract postural information. Subsequently, these postures are pre-processed, and then features such as joint velocities, normalized body joints, magnitudes and angles are extracted. A combination of feature encoding techniques together with dimension reduction strategies maintains vital information while improving system computational efficiency. Testing PosturalNet on synthetic shoplifting data yielded an accurate detection rate of 96.87%. The method demonstrates robust performance in real-time applications which handle occluded environments when applied to practical store surveillance footage.

关键词： Deep learning Accuracy Thermal sensors Feature extraction Video surveillance real-time systems Data models Human activity recognition Reliability Testing

来源：评论

学校读者我要写书评

暂无评论

Generalizable real-time Accelerated Dynamic MRI

Generalizable Real-time Accelerated Dynamic MRI

引用

international conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Silpa Babu Wahidul Alam Rushdi Zahid Rusho Sajan Goud Lingala Namrata Vaswani ECE Dept Iowa State University USA BME Dept University of Iowa USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We introduce a real-time undersampled dynamic MRI algorithm, termed FewShot-AltGDmin-MRI, that is generalizable: works for many different applications and sampling trajectories without any application-specific parameter tuning. FS-AGM-MRI operates in real-time after processing the first short mini-batch, i.e., it can provide a reconstruction of each new image frame as soon as the MRI scan data for that frame arrives. It also provides a second set of improved quality reconstructions after a short delay. We compare our algorithm against many state of the art batch MRI algorithms, including Deep Learning (DL) based ones, on 17 different retrospectively undersampled datasets and two prospective datasets. FS-AGM-MRI is the only approach that provides accurate recovery for all datasets while also being one of the fastest.

关键词： Magnetic resonance imaging Heuristic algorithms Signal processing algorithms Signal processing real-time systems Trajectory Delays Speech processing Image reconstruction Tuning

来源：评论

学校读者我要写书评

暂无评论

EdgeMLBalancer: A Self-Adaptive Approach for Dynamic Model Switching on Resource-Constrained Edge Devices

EdgeMLBalancer: A Self-Adaptive Approach for Dynamic Model S...

引用

ieee international conference on Software Architecture Workshops (ICSAW)

作者： Akhila Matathammal Kriti Gupta Larissa Lavanya Ananya Vishal Halgatti Priyanshi Gupta Karthik Vaidhyanathan Software Engineering Research Center IIIT Hyderabad India IIIT Hyderabad India

ISBN: (数字)9798331533366

ISBN: (纸本)9798331533373

The widespread adoption of machine learning (ML) on edge devices, such as mobile phones, laptops, IoT devices, etc. has enabled real-time AI applications in resource-constrained environments. Existing solutions for managing computational resources often focus narrowly on accuracy or energy efficiency, failing to adapt dynamically to varying workloads. Furthermore, the existing system lack robust mechanisms to adaptively balance CPU utilization, leading to inefficiencies in resource-constrained scenarios such as real-time traffic monitoring. To address these limitations, we propose a Self-Adaptive approach that optimizes CPU utilization and resource management on edge devices. Our approach EdgeMLBalancer balances between models through dynamic switching, guided by real-time CPU usage monitoring across processor cores. Tested on real-time traffic data, the approach adapts object detection models based on CPU usage, ensuring efficient resource utilization. The approach leverages epsilon-greedy strategy which promotes fairness and prevents resource starvation, maintaining system robustness. The results of our evaluation demonstrate significant improvements by balancing computational efficiency and accuracy, highlighting the approach's ability to adapt seamlessly to varying workloads. This work lays the groundwork for further advancements in self-adaptation for resource-constrained environments.

关键词： Adaptation models Image edge detection Computational modeling Switches Dynamic scheduling real-time systems Energy efficiency Computational efficiency Resource management Monitoring

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：