检索结果-内蒙古大学图书馆

Developing a Comprehensive Oil Spill Detection Model for Marine Environments

REMOTE SENSING 2024年第16期16卷 3080页

作者： Akhmedov, Farkhod Nasimov, Rashid Abdusalomov, Akmalbek Dept Comp Engn Dept Comp Engn Seongnam Si 461701 Gyeonggi Do South Korea Tashkent State Univ Econ Dept Informat Syst & Technol Tashkent 100066 Uzbekistan

Detecting oil spills in marine environments is crucial for avoiding environmental damage and facilitating rapid response efforts. In this study, we propose a robust method for oil spill detection leveraging state-of-the-art (SOTA) deep learning techniques. We constructed an extensive dataset comprising images and frames extracted from video sourced from Google, significantly augmenting the dataset through frame extraction techniques. Each image is meticulously labeled to ensure high-quality training data. Utilizing the Yolov8 segmentation model, we trained our oil spill detection model to accurately identify and segment oil spills in ocean environments. K-means and Truncated Linear Stretching algorithms are combined with trained model weight to increase model detection accuracy. The model demonstrated exceptional performance, yielding high detection accuracy and precise segmentation capabilities. Our results indicate that this approach is highly effective for real-time oil spill detection, offering a promising tool for environmental monitoring and disaster management. In training metrics, the model reached over 97% accuracy in 100 epochs. In evaluation, model achieved its best detection rates by 94% accuracy in F1, 93.9% accuracy in Precision, and 95.5% mAP@0.5 accuracy in Recall curves.

关键词： marine safety oil spill detection image segmentation object detection

来源：评论

学校读者我要写书评

暂无评论

Rootkit Detection using deep learning: A Comprehensive Survey 10

Rootkit Detection using Deep Learning: A Comprehensive Surve...

引用

10th International Conference on Communication and Signal processing, ICCSP 2024

作者： Suresh Kumar, S. Stephen, S. Suhainul Rumysia, M. Rajalakshmi Engineering College Department of Cse Chennai India

ISBN: (纸本)9798350353068

The 'Rootkit Detection using deep learning with Reinforcement learning' task addresses the important venture of detecting and mitigating rootkits, insidious types of malwares that frequently pass neglected within Personal Computer (PC) structures. Rootkits pose large threats to machine protection and their detection calls for innovative approaches. This task leverages the strength of deep s, especially reinforcement getting to know, to expand a dynamic and adaptable anomaly detection machine. The undertaking encompasses the collection of existing datasets regarded rootkits, ensuring information availability for training the reinforcement mastering agent. The dataset is created by logging actions, identifying subtleties, and classifying them based on malicious characteristics. It is meticulously annotated to describe rootkit types and behavior. The dataset is used for real-time monitoring and scanning by a reinforcement learning agent to distinguish between rootkit presence and normal system behavior. Reinforcement gaining knowledge of, a subset of deep mastering, allows the agent to analyze effective strategies to identify and reply to anomalies using a Generative Adversial Network (GAN), contributing to robust detection capabilities. The venture is structured into modules, inclusive of data collection, preprocessing, reinforcement studying, continuous model, and moral considerations. Evaluation metrics like precision, keep in mind, and F1-rating gauge the agent's detection accuracy. This research-pushed project targets to decorate the security of laptop structures by supplying a flexible and proactive method for rootkit detection. © 2024 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Using Convolutional Neural Networks (CNN) to realize deep Recognition Analysis of Power Technology Standard images 4

Using Convolutional Neural Networks (CNN) to Realize Deep Re...

引用

4th International Conference on Machine learning and Big Data Analytics for IoT Security and Privacy, SPIoT 2023

作者： Liu, Shan Zhao, Jin Wang, Haiqi Li, Rui Lu, Zhumao State Grid Shanxi Electric Power Research Institute Shanxi Taiyuan030001 China

This article mainly studies the method of deep recognition analysis of power technology standard images using Convolutional Neural Network (CNN). In this study, an efficient CNN model was constructed to quickly and accurately classify and recognize common technical standard images in the power industry. The experimental results indicate that the research method has high accuracy and good practicality in the recognition of power technology standard images. In the experimental stage, this study designed four experiments to explore the application of CNN models in power technology standard image recognition, with a focus on evaluating the impact of different network designs and data processing strategies on model performance. In the benchmark model comparison experiment, the AUC (Area Under the ROC Curve) value of the CNN model in the power technology standard image recognition task was 0.96, the AUC value of the Support Vector Machine (SVM) was 0.88, and the AUC value of the decision tree model was 0.82. In experiments on the impact of different data augmentation strategies, the CNN model using scaling augmentation strategy achieved an accuracy of 90%. In the experiment on the impact of network depth on performance, the accuracy of the CNN model was highest improved to 95%. In real-time recognition capability testing, although the CNN model has the highest accuracy, the average processing time for each image is also relatively long. In the above data conclusion, the effectiveness of the CNN model in power technology standard image recognition tasks has been demonstrated, and possible paths for optimizing model performance in practical applications have also been revealed. © 2024 The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Coal Gangue Sorting Based on deep learning

Coal Gangue Sorting Based on Deep Learning

引用

2023 International Conference on Algorithm, Imaging processing, and Machine Vision, AIPMV 2023

作者： Yang, Panliang Zhu, Bin Ji, Lianquan Nie, Peng Nanjing Yehengda Intelligent Solutions Co. Ltd. Nanjing China CCTEG Nanjing Design & Research Institute Co. Ltd. Nanjing China

ISBN: (纸本)9781510672444

Coal gangue sorting is an important link in the process of coal mining and processing, which can effectively reduce the difficulty and cost of coal post-processing. Aiming at the problems of complicated sorting process and low sorting efficiency of coal gangue, a coal gangue sorting method based on deep learning was proposed. The method is based on the YOLO v7 deep learning algorithm, and it achieves real-time detection of coal gangue by creating a coal gangue dataset and training the detection model. By constructing a coal gangue sorting platform, the capture of target gangue has been achieved. The experimental results show that the mAP of YOLO v7 model is 96.70%, and the detection speed is 69fps, which has significant advantages compared to YOLO v5, SSD and Faster RCNN algorithms. © 2024 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Using LSTM-Based deep learning on Natural Gas Pipeline Operational Data 12

Anomaly Detection Using LSTM-Based Deep Learning on Natural ...

引用

12th International Conference on Information and Communication Technology, ICoICT 2024

作者： Rieza Fachrezi, Muhammad Firman Ihsan, Aditya Astuti, Widi School of Computing Telkom University Bandung Indonesia

ISBN: (纸本)9798350363432

The oil and natural gas industry is a crucial sector in our daily lives. Unwanted incidents in this sector can significantly impact the household sector. Therefore, an automatic early warning system is necessary to detect errors in the pipeline network connecting production and processing points. Anomaly detection methods can be used to overcome these problems. One model suitable for unsupervised anomaly detection is the deep learning Long Short-Term Memory (LSTM) model. This research aims to implement an LSTM-based deep learning anomaly detection model on time-series operational data from an observation point situated within the sink, which consists of 17 usable features and 8,736 data points, representing a year's worth of data. Model selection involves optimizing hyperparameters (e.g., dropouts, regularizers, layers, and batch sizes) using the Mean Squared Error (MSE) through 3-fold cross-validation, resulting in 10 model candidates. The best-performing model is then trained using the training data. After training, the LSTM model reconstructs the original time-series data to calculate anomaly scores based on the Euclidean distance metric. These scores determine anomalies using a set threshold derived from the distribution of anomaly scores. Human interpretation validates the model's capability to accurately identify anomalies within the dataset. Infrastructure requirements for real-world applications are also discussed, focusing on the use of edge computing methods to enhance real-time anomaly detection capabilities. © 2024 IEEE.

关键词： Gas industry

来源：评论

学校读者我要写书评

暂无评论

Learned lensless 3D camera

引用

OPTICS EXPRESS 2022年第19期30卷 34479-34496页

作者： Tian, Feng Yang, Weijian Univ Calif Davis Dept Elect & Comp Engn Davis CA 95616 USA

Single-shot three-dimensional (3D) imaging with compact device footprint, high imaging quality, and fast processing speed is challenging in computational imaging. Mask-based lensless imagers, which replace the bulky optics with customized thin optical masks, are portable and lightweight, and can recover 3D object from a snap-shot image. Existing lensless imaging typically requires extensive calibration of its point spread function and heavy computational resources to reconstruct the object. Here we overcome these challenges and demonstrate a compact and learnable lensless 3D camera for real-time photorealistic imaging. We custom designed and fabricated the optical phase mask with an optimized spatial frequency support and axial resolving ability. We developed a simple and robust physics-aware deep learning model with adversarial learning module for real-time depth-resolved photorealistic reconstructions. Our lensless imager does not require calibrating the point spread function and has the capability to resolve depth and "see-through" opaque obstacles to image features being blocked, enabling broad applications in computational imaging.(c) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Computational imaging image processing image resolution Light transmission Spatial frequency Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Joint Optimization of Acquisition and Reconstruction of Quantitative MRI

Data-Driven Joint Optimization of Acquisition and Reconstruc...

引用

作者： Zou, Jiaren University of Michigan

学位级别：Ph.D., Doctor of Philosophy

Quantitative magnetic resonance imaging (qMRI) measures physical, physiological or biological properties of tissues and thus provides reproducible imaging biomarkers for disease diagnosis and therapy response monitoring. However, long scanning and reconstruction time, low reproducibility, spatial resolution, and volume of coverage limit the clinical translation of *** overall goal of this dissertation is to improve qMRI by exploiting its sparsity by data-driven deep learning methods. Such methods can provide more accurate and precise tissue parameters from highly undersampled or accelerated scans using a fraction of reconstruction time of conventional methods. Sampling patterns, image reconstruction and parameter estimation could be jointly optimized to directly minimize parameter quantification error under the same scan *** sparsity in dynamic contrast enhanced magnetic resonance imaging (DCE MRI) was exploited by a long short-term memory (LSTM) neural network-based approach to provide more robust tissue parameter estimation. The network was trained on simulated DCE signals and tested on both simulated and real data. Compared to a conventional linear least squares (LLSQ) fitting method, the LSTM-based approach had higher accuracy for the data with temporally subsampling, total acquisition time truncation, or high noise level. Also, the LSTM-based method reduced the inference time by ~14 times compared to the LLSQ fitting. Validation of the method on real data demonstrated its clinical feasibility to provide high-quality tissue parameter *** temporal sparsity, the spatiotemporal sparsity of DCE MRI was further exploited by convolutional recurrent neural network. 2D Cartesian phase encoding k-space subsampling patterns were jointly optimized with image reconstruction to identify the most informative k-space data to acquire beyond the learned population prior knowledge. Both reconstruction image quality and parameter estimation accuracy were use

关键词： Magnetic resonance imaging image reconstruction deep learning End-to-end optimization

来源：评论

学校读者我要写书评

暂无评论

HYBRID deep learning ALGORITHM FOR FRACTAL HUMAN ACTIVITY RECOGNITION USING SMART IOT-EDGE-CLOUD CONTINUUM

引用

FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY 2025年第2期33卷

作者： Allafi, Randa Alrowais, Fadwa Aljebreen, Mohammed Negm, Noha Salama, Ahmed s. Marzouk, Radwa Northern Border Univ Coll Sci Dept Comp Sci Ar Ar Saudi Arabia Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Comp Sci POB 84428 Riyadh 11671 Saudi Arabia King Saud Univ Community Coll Dept Comp Sci POB 28095 Riyadh 11437 Saudi Arabia King Khalid Univ Appl Coll Mahayil Dept Comp Sci Abha Saudi Arabia Future Univ Egypt Fac Engn & Technol Dept Elect Engn New Cairo 11845 Egypt Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst Riyadh Saudi Arabia

Human activity recognition (HAR) employs a broad range of sensors that generate massive volumes of data. Traditional server-based and cloud computing methods require all sensor data to be sent to servers or clouds for processing, which leads to high latency and bandwidth costs. The long-term data transfer between servers and sensors maximizes the cost of latency and bandwidth. real-time processing is, nevertheless, highly required for human action identification. By bringing processing and quick data storage to the sensors instead of depending on a central database, edge computing is rapidly emerging as a solution to this issue. Artificial intelligence is responsible for most HAR, which demands a lot of processing power and calculation. Artificial intelligence (AI) needs more computation which is not allowed by edge computing. So Edge intelligence, which allows AI to operate at the network edge for actual-time applications, has been made possible by the advent of binarized neural networks. To provide less latency and less memory for human activity identification at the edge network, we construct a hybrid deep learning-based binarized neural network (HDL-Binary Dilated DenseNet) in this research. Fractal HAR optimization algorithms could be applied to these algorithms. For example, fractal-HAR optimization techniques might be used to provide less latency and less memory human activity identification at the edge network. Using three sensors-based human activity detection datasets such as Radar HAR dataset, UCI HAR dataset and UniMib-SHAR dataset, we implemented the Hybrid Binary Dilated Dense Net. It is then assessed using four criteria. Comparatively, the Hybrid Binary Dilated DenseNet performs better with 99.6% radar HAR dataset which is highest than other models like CNN-BiLSTM and GoogLeNet.

关键词： Radar Sensors Wearable Sensors Edge Computing Edge Intelligence Neural Networks Fractal HAR

来源：评论

学校读者我要写书评

暂无评论

Insight into Automatic image Diagnosis of Ear Conditions Based on Optimized deep learning Approach

引用

ANNALS OF BIOMEDICAL ENGINEERING 2024年第4期52卷 865-876页

作者： Afify, Heba M. Mohammed, Kamel K. Hassanien, Aboul Ella Shorouk Acad Syst & Biomed Engn Dept Higher Inst Engn Al Shorouk City Cairo Egypt Al Azhar Univ Ctr Virus Res & Studies Cairo Egypt Kuwait Univ Coll Business Adm Kuwait Kuwait Sci Res Grp Egypt SRGE Cairo Egypt Cairo Univ Fac Comp & Informat Giza Egypt

Examining otoscopic images for ear diseases is necessary when the clinical diagnosis of ear diseases extracted from the knowledge of otolaryngologists is limited. Improved diagnosis approaches based on otoscopic image processing are urgently needed. Recently, convolutional neural networks (CNNs) have been carried out for medical diagnosis to obtain higher accuracy than standard machine learning algorithms and specialists' expertise. Therefore, the proposed approach involves using the Bayesian hyperparameter optimization with the CNN architecture for automatic diagnosis of ear imagery database including four classes: normal, myringosclerosis, earwax plug, and chronic otitis media (COM). The suggested approach was trained using 616 otoscopic images, and the performance of this approach was assessed using 264 testing images. In this paper, the performance of ear disease classification was compared in terms of accuracy, sensitivity, specificity, and positive predictive value (PPV). The results produced a classification accuracy of 98.10%, a sensitivity of 98.11%, a specificity of 99.36%, and a PPV of 98.10%. Finally, the suggested approach demonstrates how to locate optimal CNN hyperparameters for accurate diagnosis of ear diseases while taking time into account. As a result, the usefulness and dependability of the suggested approach will lead to the establishment of an automated tool for better categorization and prediction of different ear diseases.

关键词： Ear imagery database Convolutional neural networks (CNNs) Hyperparameters Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

An overview of violence detection techniques: current challenges and future directions

引用

ARTIFICIAL INTELLIGENCE REVIEW 2023年第5期56卷 4641-4666页

作者： Mumtaz, Nadia Ejaz, Naveed Habib, Shabana Mohsin, Syed Muhammad Tiwari, Prayag Band, Shahab S. Kumar, Neeraj Iqra Univ Dept Comp Sci Islamabad Campus Islamabad Pakistan Qassim Univ Coll Comp Dept Informat Technol Buraydah 52571 Saudi Arabia COMSATS Univ Dept Comp Sci Islamabad 45550 Pakistan Halmstad Univ Sch Informat Technol Halmstad Sweden Natl Yunlin Univ Sci & Technol Future Technol Res Ctr 123 Univ RdSect 3 Touliu 64002 Yunlin Taiwan Thapar Inst Engn & Technol Deemed Univ Dept Comp Sci & Engn Patiala Punjab India Lebanese Amer Univ Dept Elect & Comp Engn Beirut Lebanon Univ Petr & Energy Studies Sch Comp Sci Dehra Dun Uttarakhand India King Abdulaziz Univ Jeddah Saudi Arabia

The Big Video Data generated in today's smart cities has raised concerns from its purposeful usage perspective, where surveillance cameras, among many others are the most prominent resources to contribute to the huge volumes of data, making its automated analysis a difficult task in terms of computation and preciseness. Violence detection (VD), broadly plunging under action and activity recognition domain, is used to analyze Big Video data for anomalous actions incurred due to humans. The VD literature is traditionally based on manually engineered features, though advancements to deep learning based standalone models are developed for real-time VD analysis. This paper focuses on overview of deep sequence learning approaches along with localization strategies of the detected violence. This overview also dives into the initial image processing and machine learning-based VD literature and their possible advantages such as efficiency against the current complex models. Furthermore,the datasets are discussed, to provide an analysis of the current models, explaining their pros and cons with future directions in VD domain derived from an in-depth analysis of the previous methods.

关键词： Violence detection Action and activity recognition Anomaly detection deep learning for VD

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：