检索结果-内蒙古大学图书馆

YOLO9tr: a lightweight model for pavement damage detection utilizing a generalized efficient layer aggregation network and attention mechanism

引用

JOURNAL OF real-time image processing 2024年第5期21卷 163页

作者： Youwai, Sompote Chaiyaphat, Achitaphon Chaipetch, Pawarotorn King Mongkuts Univ Technol Thonburi Dept Civil Engn AI Res Grp Bangkok Thailand Infraplus Co Ltd Bangkok Thailand

Maintaining road pavement integrity is crucial for ensuring safe and efficient transportation. Conventional methods for assessing pavement condition are often laborious and susceptible to human error. This paper proposes YOLO9tr, a novel lightweight object detection model for pavement damage detection, leveraging the advancements of deep learning. YOLO9tr is based on the YOLOv9 architecture, incorporating a partial attention block that enhances feature extraction and attention mechanisms, leading to improved detection performance in complex scenarios. The model is trained on a comprehensive dataset comprising road damage images from multiple countries. This dataset includes an expanded set of damage categories beyond the standard four types (longitudinal cracks, transverse cracks, alligator cracks, and potholes), providing a more nuanced classification of road damage. This broadened classification range allows for a more accurate and realistic assessment of pavement conditions. Comparative analysis demonstrates YOLO9tr's superior precision and inference speed compared to state-of-the-art models like YOLOv8, YOLOv9 and YOLOv10, achieving a balance between computational efficiency and detection accuracy. The model achieves a high frame rate of up to 136 FPS, making it suitable for real-time applications such as video surveillance and automated inspection systems. The research presents an ablation study to analyze the impact of architectural modifications and hyperparameter variations on model performance, further validating the effectiveness of the partial attention block. The results highlight YOLO9tr's potential for practical deployment in real-time pavement condition monitoring, contributing to the development of robust and efficient solutions for maintaining safe and functional road infrastructure.

关键词： YOLO Pavement damage Object detection deep learning

来源：评论

学校读者我要写书评

暂无评论

An Evaluation Method of Dental Treatment Quality Combined with deep learning and Multi-index Decomposition

引用

APPLIED ARTIFICIAL INTELLIGENCE 2024年第1期38卷

作者： Peng, Gang Liu, Jie Yan, Feng Liu, Beicun Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat 1037 Luoyu Rd Wuhan Hubei Peoples R China Minist Educ Key Lab Image Proc & Intelligent Control Wuhan Peoples R China Hubei Eya Med Investment Management Co Ltd Res Ctr Wuhan Peoples R China

Dentists judge that the quality of dental treatment for each patient is very time-consuming and inefficient, lacks quantitative evaluation criteria, and is easy to cause errors. At the same time, the traditional method of extracting tooth and root canal image features based on experience is difficult to accurately extract the tooth area and root canal filling area, resulting in low accuracy of tooth and root canal segmentation, which in turn affects the accuracy of tooth treatment quality evaluation. In this paper, a deep learning convolutional neural network is used to segment the root canal filling area, tooth boundary, and the boundary between tooth and soft tissue for the real patient 's root canal treatment and filling image. Finally, the segmented image is quantitatively evaluated according to the multi-evaluation index of professional doctors. The experimental results show that the intelligent evaluation method of dental treatment quality combined with deep learning and multi-index decomposition proposed in this paper not only unifies the evaluation criteria of dental treatment quality but also the therapeutic effect of quantitative scoring can effectively improve the work efficiency of doctors, which has reference significance for the application of artificial intelligence in the medical field.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

QARV: Quantization-Aware ResNet VAE for Lossy image Compression

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第1期46卷 436-450页

作者： Duan, Zhihao Lu, Ming Ma, Jack Huang, Yuning Ma, Zhan Zhu, Fengqing Purdue Univ Elmore Family Sch Elect & Comp Engn W Lafayette IN 47907 USA Nanjing Univ Sch Elect Sci & Engn Nanjing 210093 Jiangsu Peoples R China

This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of variational autoencoders (VAEs), a powerful class of generative probabilistic models that has a deep connection to lossy compression. Based on VAEs, we develop a new scheme for lossy image compression, which we name quantization-aware ResNet VAE (QARV). Our method incorporates a hierarchical VAE architecture integrated with test-time quantization and quantization-aware training, without which efficient entropy coding would not be possible. In addition, we design the neural network architecture of QARV specifically for fast decoding and propose an adaptive normalization operation for variable-rate compression. Extensive experiments are conducted, and results show that QARV achieves variable-rate compression, high-speed decoding, and better rate-distortion performance than existing baseline methods.

关键词： Lossy image compression learned image compression variational autoencoder deep learning

来源：评论

学校读者我要写书评

暂无评论

deep Convolution Neural Networks for image-Based Android Malware Classification

引用

Computers, Materials & Continua 2025年第3期82卷 4093-4116页

作者： Amel Ksibi Mohammed Zakariah Latifah Almuqren Ala Saleh Alluhaidan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia College of Computer and Information Sciences King Saud UniversityRiyadhP.O.Box 11442Saudi Arabia

The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of *** resolve this problem,efficient and flexible malware detection tools are *** work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data ***,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:***,***,***,***,*** network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained *** addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional *** success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.

关键词： Android malware detection deep convolutional neural network(DCNN) image processing CIC-AndMal2017 dataset exploratory data analysis VGG16 model

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Task Scheduling Technique in Fog Computing Using Fuzzy Logic and deep Reinforcement learning

引用

IEEE ACCESS 2024年 12卷 176363-176388页

作者： Choppara, Prashanth Mangalampalli, S. Sudheer VIT AP Univ Sch Comp Sci & Engn Amaravati 522237 Andhra Pradesh India Manipal Acad Higher Educ Manipal Inst Technol Bengaluru Dept Comp Sci & Engn Manipal 576104 Karnataka India

This work presents an innovative method for scheduling tasks in a fog computing environments by combining the fuzzy logic with deep reinforcement learning. In Internet of Things there has been a significant raising the amount of data produced by different devices. This has created a need for more effective methods of processing and managing this data. Conventional cloud computing often fails to fulfill the need of IoT usage in terms of high bandwidth, low makespan, and real-time processing. Fog computing presents available solution by placing the processing resources near the data source but the issue of efficient task scheduling remains a major obstacle. We proposed a technique that combines an Hybrid task scheduling technique in fog computing using fuzzy logic and deep reinforcement learning (HTSFFDRL) algorithm with a Takagi-Sugeno fuzzy inference system. By continuously interacting with the environment, this hybrid technique allows for the dynamic prioritization of tasks and the real-time change of scheduling rules. The technique seeks to maximize many crucial performance measures, such as makespan, energy consumption, cost, and fault tolerance. Simulations extensively validate the suggested strategy, demonstrating significant enhancements compared to current approaches like LSTM, DQN, and A2C. The results indicate that combining fuzzy logic with reinforcement learning may greatly improve the effectiveness and dependability of task scheduling in fog computing, opening up possibilities for more resilient IoT applications.

关键词： Processor scheduling Scheduling Internet of Things Edge computing Dynamic scheduling Resource management Job shop scheduling Costs real-time systems Optimization Task scheduling reinforcement learning fuzzy fog computing makespan cost energy consumption fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Enhancing Public Safety through real-time Weapon Detection: A deep learning Approach 3

Enhancing Public Safety through Real-time Weapon Detection: ...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Dass, J. Maria Arockia Suresh, A. Swathi, K. Shalini, Paidimuddala Sinha, N A Yaswanth Kotholla Uday Kiran, U. Siddharth Institute of Engineering & Technology Department of Computer Science and Engineering Andhra Pradesh Chittoor India

ISBN: (纸本)9798350354171

Date In response to the imperative need for mitigating criminal activities and ensuring public safety, this research proposes a novel approach leveraging deep learning techniques for real-time weapon detection. In contemporary society, criminal acts pose significant threats to both individuals and the broader community, necessitating proactive measures to counter such offenses swiftly. By harnessing advanced technologies, particularly deep learning algorithms like YOLOv7-tiny, this study intend to create a robust system capable of identifying weapons in surveillance footage captured by CCTV cameras. The project begins with the meticulous collection of datasets from reputable research sources, ensuring diverse and comprehensive samples for training the deep learning model. Subsequently, these datasets undergo rigorous pre-processing steps to optimize them for training, including resizing images to the required format. To facilitate accurate annotation and labelling of the dataset, advanced tools like Robo flow software are employed, streamlining the process and enhancing efficiency. Upon completion of the pre-processing phase, the YOLOv7-tiny algorithm is deployed for training the model on the annotated datasets. Through iterative training and validation processes, the model is fine-tuned to achieve optimal performance in weapon detection tasks. Once trained, the model is capable of swiftly and accurately identifying weapons in real-time surveillance footage. This project presents an effective solution for real-time weapon detection in public spaces, leveraging deep learning algorithms and advanced software tools. © 2024 IEEE.

关键词： image annotation

来源：评论

学校读者我要写书评

暂无评论

Improved Unsupervised deep Boltzmann learning Approach for Accurate Hand Vein Recognition

引用

IEEE ACCESS 2024年 12卷 18488-18507页

作者： Nour, Rana Moustafa, Hossam El-Din Abdelhay, Ehab H. Ata, Mohamed Maher Mansoura Higher Inst Engn & Technol Dept Elect & Commun Engn Mansoura 35516 Egypt Mansoura Univ Fac Engn Dept Commun & Elect Engn Mansoura 35516 Egypt Zewail City Sci & Technol Sch Computat Sci & Artificial Intelligence CSAI Giza 12578 Egypt Misr Higher Inst Engn & Technol Dept Commun & Elect Engn Mansoura 35511 Egypt

Dorsal hand vein (DHV) recognition is a burgeoning biometric technology that has recently garnered considerable attention. This article uses image processing and deep learning to present a novel DHV recognition approach. It involves detecting and identifying the unique patterns present in the DHV. The proposed system begins with the preprocessing mechanism that is applied to enhance the quality of the acquired images, including contrast enhancement and noise reduction, by using some filters such as Median and Contrast Limited Adaptive Histogram Equalization (CLAHE). Next, a deep learning model, such as a convolutional neural network (CNN), is employed to automatically abstract discriminative features from the preprocessed vein images. The empirical outcomes prove the influence and reliability of the proposed technique for vein recognition, making it a promising solution for biometric authentication systems. Compared with traditional CNN, the proposed approach shows good accuracy and classification rate results. The suggested model achieved a high recognition rate accuracy, recall, precious, and f-score of 99.7%,97%,96%, and 96%, respectively, and a recognition time of about 1283.45 s. To enrich the model's capability for feature recognition and reduce recognition time, decrease the intricacy of learning and the connectivity CNN structure, an alternative approach based on Restricted Boltzmann Machines (RBM) was assessed. This strategy exhibits superior accuracy in comparison to other contemporary algorithms. The proposed RBM achieved a high recognition rate accuracy, recall, precious, and f-score of 99.9%,99%,99%, and 99%, respectively, and a recognition time of about 137.235s.

关键词： Biometrics (access control) Convolutional neural networks deep learning Biological system modeling Feature extraction Authentication image recognition Biometrics image processing DHV CNN deep learning RBM

来源：评论

学校读者我要写书评

暂无评论

A one-shot face detection and recognition using deep learning method for access control system

引用

SIGNAL image AND VIDEO processing 2023年第4期17卷 1571-1579页

作者： Tsai, Tsung-Han Tsai, Chi-En Chi, Po-Ting Natl Cent Univ Dept Elect Engn 300 Jung Da Rd Zhongli 320 Taiwan

In this paper, we propose a face detection and recognition system using deep learning method. It can be used as an access control system that performs face detection and recognition in real-time processing. Our goal is to achieve a one-shot recognition instead of traditional two-step methods. We use SSD as the main model for face detection and VGG-Face as the main model for face recognition. We perform the deep learning method through the collection of datasets. Moreover, we use some techniques, such as data augmentation, preprocessing of the image, and post-processing of the image to train the robust face detection and recognition subsystems. We use continuous frames as input to avoid false-positive cases and make the system output without wrong results. A real demonstration system is constructed to determine the identification of the laboratory members. We use 1280 x 960 resolution video for experimental testing and achieve about 30 fps speed under GPU acceleration.

关键词： Face detection Face recognition deep neural network Machine learning Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

deep learning-based hyperspectral image reconstruction for quality assessment of agro-product

引用

JOURNAL OF FOOD ENGINEERING 2024年 382卷

作者： Ahmed, Md. Toukir Monjur, Ocean Kamruzzaman, Mohammed Univ Illinois Dept Agr & Biol Engn Urbana IL 61801 USA

Hyperspectral imaging (HSI) has recently emerged as a promising tool for many agricultural applications;however, the technology cannot be directly used in real-time for immediate decision-making and actions due to the extensive time needed to capture, process, and analyze large volumes of data. Consequently, the development of a simple, compact, and cost-effective imaging system is not possible with the current HSI systems. Therefore, the overall goal of this study was to reconstruct hyperspectral images from RGB images through deep learning for agricultural applications. Specifically, this study used Hyperspectral Convolutional Neural Network - Dense (HSCNN-D) to reconstruct hyperspectral images from RGB images for predicting soluble solid content (SSC) in sweet potatoes. The algorithm reconstructed the hyperspectral images from RGB images, with the resulting spectra closely matching the ground-truth. The partial least squares regression (PLSR) model based on reconstructed spectra outperformed the model using the full spectral range, demonstrating its potential for SSC prediction in sweet potatoes. These findings highlight the potential of deep learning-based hyperspectral image reconstruction as a low-cost, efficient tool for various agricultural uses.

关键词： Hyperspectral imaging RGB Genetic algorithm PLSR image reconstruction deep learning

来源：评论

学校读者我要写书评

暂无评论

deep-learning for Objective Quality Assessment of Tone Mapped images

引用

APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION processing 2024年第1期13卷

作者： Khan, Ishtiaq Rasool Imtiaz, Romil Abu Dhabi Sch Management Abu Dhabi U Arab Emirates Univ Jeddah Coll Comp Sci & Engn Jeddah Saudi Arabia Pakistan Inst Engn & Technol Multan Pakistan

High dynamic range (HDR) images capture real-world luminance values which cannot be directly displayed on the screen and require tone mapping to be shown on low dynamic range (LDR) hardware. During this transformation, tone mapping algorithms are expected to preserve the naturalness and structural details of the image. In this regard, the performance of atone mapping algorithm can be evaluated through a subjective study where participants rank or score tone mapped images based on their preferences. However, such subjective evaluations can be time-consuming and cannot be repeated for every tone mapped image. To address this issue, numerous quantitative metrics have been proposed for objective evaluation. This paper presents a robust objective metric based on deep learning to quantify image quality. We assess the performance of our proposed metric by comparing it to 20 existing state-of-theart metrics using two subjective datasets, including one benchmark dataset and a novel proposed dataset of 666 tone mapped images comprising a variety of scenes and labeled by 20 users. Our approach exhibits the highest correlation with subjective scores in both evaluations, confirming its effectiveness and potential to be a reliable alternative to laborious subjective studies.

关键词： image quality assessment deep learning image datasets tone mapping high dynamic range

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：