检索结果-内蒙古大学图书馆

Curve-based lane estimation model with lightweight attention mechanism

SIGNAL image AND VIDEO processing 2023年第5期17卷 2637-2643页

作者： Zhang, Jindong Zhong, Haoting Jilin Univ Coll Comp Sci & Technol Qianjin St Changchun 130012 Jilin Peoples R China

One of the primary responsibilities of an autonomous driving system is lane detecting. We propose modeling lane markings using Catmull-Rom curves, as opposed to segmentation-based approaches and point detection-based methods, which input images captured by monocular cameras and output lane markings represented by Catmull-Rom segments. The Catmull-Rom segment fits the lane lines more closely than the cubic polynomial and is stable and simple to construct (tested on the TuSimple dataset). We also suggest a spatial attention module to take advantage of lane lines' nearly vertical distribution. Our suggested approach strikes a balance between accuracy and real-time. In the Tusimple dataset, our model's accuracy is 0.45% more accurate than the cubic polynomial model (PolyLaneNet). These results demonstrated the suitability of our approach for the lane detecting task.

关键词： Lane detection Autonomous driving deep learning Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A fiber optic sensing intrusion detection method based on WPD-EMD and improved ResNet

引用

OPTICAL FIBER TECHNOLOGY 2025年 90卷

作者： Hu, Xinmin Bai, Xinrui Li, Jingqi He, Yiting Li, Yingying Li, Liang Xiao, Han Liu, Cong Zhang, Fan Tang, Jing Hu, Sheng Hubei Univ Technol Sch Elect & Elect Engn Wuhan 430068 Peoples R China Hubei Univ Technol Hubei Key Lab High Efficiency Utilizat Solar Energ Wuhan 430068 Peoples R China Hubei Univ Technol Xiangyang Ind Inst Xiangyang 441000 Peoples R China

Perimeter security systems are essential for safeguarding critical locations from unauthorized intrusions and various security threats. Traditional video surveillance has limitations like coverage gaps, blind spots, and the need for extensive manual analysis. In contrast, fiber optic systems use distributed sensing technology for realtime, precise data acquisition and automatic anomaly detection, reducing the need for manual monitoring. The Phase-Sensitive Optical time-Domain Reflectometer (Phi-OTDR) is noted for its high sensitivity, large dynamic range, and robust interference resistance, making it ideal for extensive real-time monitoring. To enhance recognition accuracy, especially for high-threat events requiring zero false alarms, this study proposes a fiber optic sensing signal recognition method using Wavelet Packet Decomposition (WPD) combined with Empirical Mode Decomposition (EMD) and an improved ResNet architecture. Encoding one-dimensional signals into images using Recurrence Plots (RP) leverages advanced techniques from image processing and computer vision, enhancing signal recognition accuracy and application scope. Experimental results show that the WPD-EMD denoising method significantly improves the quality of the original signals, achieving an overall recognition rate of 93.83% for eight types of intrusion signals. For the most representative events (background noise, excavator digging, truck passing, stone knocking), the recognition rate reaches 99.69%. This method shows significant potential for advancing perimeter security monitoring.

关键词： Phase-sensitive optical time domain reflectometry (Phi-OTDR) Signal denoising deep learning Event recognition Perimeter security

来源：评论

学校读者我要写书评

暂无评论

deep learning Based Covid-19 Diagnosis and Severity Assessment Using Computed Tomography Imaging 2

Deep Learning Based Covid-19 Diagnosis and Severity Assessme...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Namratha, S. Hitha, K. Shetty, Gahana Thaskeen, Fathima Sannidhan, M.S. Martis, Jason Elroy Department of CSE NMAM Institute of Technology Nitte Deemed to be University Deralakatte India Department of ISE NMAM Institute of Technology Nitte Deemed to be University Deralakatte India

ISBN: (纸本)9798331504960

The COVID-19 pandemic has highlighted the need for advanced diagnostic tools for early detection and management. This study presents a deep learning (DL) approach using CT scans to detect COVID-19 and assess lung involvement. A Convolutional Neural Network (CNN) achieves 94% accuracy in distinguishing COVID-positive from negative cases. image preprocessing, including Gaussian blurring and Otsu’s thresholding, enhances lung region clarity. Lung segmentation isolates critical areas, enabling severity classification (mild, moderate, severe) based on opacity-to-lung area ratio. Using the SARS-CoV-2 CT dataset, the CNN model with Transfer learning (TL) via ResNet reaches 96.74% accuracy. This method provides a valuable diagnostic tool for real-time healthcare decision-making during pandemics. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Harnessing the Power of deep learning in Brain Tumor Detection 2

Harnessing the Power of Deep Learning in Brain Tumor Detecti...

引用

2nd IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2024

作者： Srinivasarao, Narisetty Sri, Dasa Teja Reddy, Pandilla Sai Prakash Gopinadh, Singamsetty Department of Computer Science and Engineering Mylavaram India

ISBN: (纸本)9798350372847

Brain tumors represent a substantial source of morbidity and mortality on a global scale. Early Identification and precise diagnosis are crucial for successful treatment outcomes. Magnetic Resonance Imaging (MRI) has become a cornerstone in the diagnosis of brain tumors, but interpreting these scans is time-consuming and requires significant expertise. deep learning (DL) & image processing Techniques offer promising solutions to this problem. This project introduces a DL-based approach for identifying brain tumors from MRI scans. The proposed approach involves image preprocessing, feature extraction & classification using supervised ML Algorithms, such as Convolutional Neural Networks (CNN). The method involves preprocessing the MRI scans using various techniques, including filtering and segmentation, to remove noise and highlight potential tumor regions and extract features from the preprocessed images, such as texture, shape, and intensity using various image processing Techniques. These features are then used to train and test the DL models, which predict whether an MRI scan contains a tumor or not. Evaluation of the proposed approach on a large dataset of MRI scans collected from patients with brain tumors and healthy individuals substantiate the effectiveness of the proposed method in precisely identifying brain tumors. The CNN models demonstrate notable levels of accuracy & sensitivity, indicating their potential for use in Clinical settings. The project carries significant potential to advance the early detection and diagnosis of brain tumors, there by contributing to better patient outcomes and a reduction in mortality rates. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel deep learning Method for real-time Estimation of Lithium-Ion Battery Capacity

A Novel Deep Learning Method for Real-Time Estimation of Lit...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Zhang, Zihuan Fan, Zhong Ruiz, Cesar Arturo Angeles University of Exeter Centre for Smart Grid ExeterEX4 4QF United Kingdom

ISBN: (纸本)9789531842976

Accurate prediction of lithium-ion battery states in electric vehicles (EVs) is crucial for enhancing safety, economic efficiency, and environmental sustainability. However, current research on real-time, on-board estimation of battery states is limited. This paper aims to bridge this gap by introducing a method that employs an Auto-BiLSTM algorithm coupled with an innovative data preprocessing technique using a low pass filter (LPF) to accurately predict battery capacity. Initially, data from the NASA dataset were pre-processed with the LPF to mitigate measurement noise and smooth oscillations caused by capacity self-generation, thereby stabilizing the input for neural network processing. After optimizing the autoencoder settings, this refined data, and the encoder output were used to evaluate the most effective predictive model among four widely used architectures. The results indicate that an autoencoder with 50-dimensional hidden units paired with a BiLSTM model offers the highest accuracy and the smallest model size, making it suitable for hardware implementation. Finally, a comparative analysis with the latest deep learning-based prediction models demonstrates that our model achieves top-level accuracy currently available in the field. All the data and codes related to this work can be accessed at the GitHub repository: https://***/Kayaa1. © 2024 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Blurred Facial Recognition based on AdaFace 48

Blurred Facial Recognition based on AdaFace

引用

48th Annual IEEE International Computers, Software, and Applications Conference (COMPSAC) - Digital Development for a Better Future

作者： Zhang, Quan-Bin Chi, Po-Yang Lin, Shang-Ze Wu, Chia-Xuan Hsieh, Yi-Zeng Natl Taiwan Univ Sci & Technol Taipei Taiwan

ISBN: (纸本)9798350376975;9798350376968

Many campuses in Taiwan feature open access, complicating the control and identification of individuals entering. This issue, along with emerging campus safety concerns, underscores the critical need for efficient security measures. The low resolution of surveillance cameras and the inefficiency of manual identification methods exacerbate this challenge. This study suggests the use of artificial intelligence, specifically the Adaface model with its unique Marginal-based loss functions, to enhance the identification process even with low-quality, blurred images. By automating the classification and processing of facial data-distinguishing between registered and unregistered faces-the system can perform real-time comparisons and logging. Our experiments with Adaface have demonstrated improved multi-face recognition capabilities and the ability to track unrecognized faces over time. Nonetheless, variations in scene context can still affect feature visibility and model stability.

关键词： blurred facial recognition deep learning low-resolution image

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Clinical Decision Support System (CDSS) by Using Recurrent Neural Network (RNN) Language Models for real-time Medical Query processing

引用

Computers, Materials & Continua 2024年第12期81卷 4787-4832页

作者： Israa Ibraheem Al Barazanchi Wahidah Hashim Reema Thabit Mashary Nawwaf Alrasheedy Abeer Aljohan Jongwoon Park Byoungchol Chang College of Computing and Informatics Universiti Tenaga Nasional(UNITEN)Kajang43000Malaysia College of Engineering University ofWarith Al-AnbiyaaKarbala56001Iraq Faculty of Information Science&Technology Universiti Kebangsaan MalaysiaBangi43600Malaysia Department of Computer Science Applied CollegeUniversity of HailHail55424Saudi Arabia Department of Computer Science and Informatics Taibah UniversityMedina42353Saudi Arabia Department of Computer Science Hanyang UniversitySeoul04763Republic of Korea

This research aims to enhance Clinical Decision Support Systems(CDSS)within Wireless Body Area Networks(WBANs)by leveraging advanced machine learning ***,we target the challenges of accurate diagnosis in medical imaging and sequential data analysis using Recurrent Neural Networks(RNNs)with Long Short-Term Memory(LSTM)layers and echo state *** models are tailored to improve diagnostic precision,particularly for conditions like rotator cuff tears in osteoporosis patients and gastrointestinal *** diagnostic methods and existing CDSS frameworks often fall short in managing complex,sequential medical data,struggling with long-term dependencies and data imbalances,resulting in suboptimal accuracy and delayed *** goal is to develop Artificial Intelligence(AI)models that address these shortcomings,offering robust,real-time diagnostic *** propose a hybrid RNN model that integrates SimpleRNN,LSTM layers,and echo state cells to manage long-term dependencies ***,we introduce CG-Net,a novel Convolutional Neural Network(CNN)framework for gastrointestinal disease classification,which outperforms traditional CNN *** further enhance model performance through data augmentation and transfer learning,improving generalization and robustness against data scarcity and *** validation,including 5-fold cross-validation and metrics such as accuracy,precision,recall,F1-score,and Area Under the Curve(AUC),confirms the models’***,SHapley Additive exPlanations(SHAP)and Local Interpretable Model-agnostic Explanations(LIME)are employed to improve model *** findings show that the proposed models significantly enhance diagnostic accuracy and efficiency,offering substantial advancements in WBANs and CDSS.

关键词： Computer science clinical decision support system(CDSS) medical queries healthcare deep learning recurrent neural network(RNN) long short-term memory(LSTM)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Traffic Control Using Machine learning Algorithm 15

Adaptive Traffic Control Using Machine Learning Algorithm

引用

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

作者： Gowri, P. Sivapriya, G. Venkateswaran, K. Sridhar, N. Indhumathi, N. Sathya, M. Kongu Engineering College Department of Ece Erode Perundurai India Cmr Institute of Technology Department of Ece Bengaluru India

ISBN: (纸本)9798350370249

The adaptive traffic light control using edge computing project leverages AI-driven techniques to enhance the efficiency of traffic management at critical road junctions. By employing image processing methods, it captures real-time data on vehicular density and traffic patterns at the junction. These images enable the system to identify vehicle types and count their numbers in different lanes. This information feeds into a pre-trained machine learning model, which generates recommendations for optimal traffic signal durations. These recommendations are then communicated to the traffic light controller, which dynamically adjusts signal timings based on current conditions. The adaptive traffic control system continuously monitors and adapts to changing traffic patterns, leading to reduced congestion and minimized delays. This innovative approach ensures a more efficient use of road infrastructure and smoother traffic flow at important junctions. © 2024 IEEE.

关键词： Edge computing Machine learning real-time data Traffic light controller Traffic patterns

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of deep learning Based Filtering Algorithm in Separation of Human Objects from images 14th

Effectiveness of Deep Learning Based Filtering Algorithm in ...

引用

14th International Conference on Intelligent Human Computer Interaction, IHCI 2022

作者： Khalilov, S.P. Yusupov, I. Mannapova, M.G. Nasrullayev, N.B. Botirov, F. Tashkent University of Information Technologies Named After Muhammad al Khwarizmi Tashkent Uzbekistan Nurafshan Branch of Tashkent University of Information Technologies Named After Muhammad Al Khwarizmi Tashkent Uzbekistan

ISBN: (纸本)9783031271984

This article focuses on the use of filtering algorithms based on noise deep learning in high-efficiency detection of moving human objects in real-time video frames. The frame separation method developed for the detection of moving human objects has been modified to provide real-time image processing. In the first method, an efficient frame splitting method was used to detect the moving object from the original image. In this method, it is possible to detect moving objects in the image at a high speed, but the disadvantage is that the efficiency index is lower due to the fact that the image noise filtering tools are not used. To increase the efficiency of the algorithm, the use of the LBF-algorithm - (Machine learning Approach for Filtering), which reduces the additional quality of the noise, was proposed. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine learning Enhanced Framework for Big Data Modeling with Application in Industry 4.0

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第3期15卷 308-318页

作者： Kazbekova, Gulnur Ismagulova, Zhuldyz Zhussipbek, Botagoz Abdrazakh, Yntymak Iskendirova, Gulzipa Toilybayeva, Nurgul Turkish Univ Khoja Akhmet Yassawi Int Kazakh Turkistan Kazakhstan Korkyt Ata Kyzylorda Univ Kyzylorda Kazakhstan

In the dynamic milieu of Industry 4.0, characterized by the deluge of big data, this research promulgates a groundbreaking framework that harnesses machine learning (ML) to optimize big data modeling processes, addressing the intricate requirements and challenges of contemporary industrial domains. Traditional data processing mechanisms falter in the face of the sheer volume, velocity, and variety of big data, necessitating more robust, intelligent solutions. This paper delineates the development and application of an innovative ML-augmented framework, engineered to interpret and model complex, multifaceted data structures more efficiently and accurately than has been feasible with conventional methodologies. Central to our approach is the integration of advanced ML strategies-including but not limited to deep learning and neural networks-with sophisticated analytics tools, collectively capable of automated decision-making, predictive analysis, and trend identification in real-time scenarios. Beyond theoretical formulation, our research rigorously evaluates the framework through empirical analysis and industrial case studies, demonstrating tangible enhancements in data utility, predictive accuracy, operational efficiency, and scalability within various Industry 4.0 contexts. The results signify a marked improvement over existing models, particularly in handling high-dimensional data and facilitating actionable insights, thereby empowering industrial entities to navigate the complexities of digital transformation. This exploration underscores the potential of machine learning as a pivotal ally in evolving data strategies, setting a new precedent for data-driven decision- making paradigms in the era of Industry 4.0.

关键词： Industry 4.0 machine learning big data application management

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：