检索结果-内蒙古大学图书馆

Enhanced Modified Contrast Enhancement and Exposure Fusion: a visionary dehazing approach for clarity in hazy imagery

引用

Multimedia Tools and Applications 2025年 1-24页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. EL-Rabaie, El-Sayed M. Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Prince Sultan University Riyadh11586 Saudi Arabia Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

In the field of image processing, haze is a type of atmospheric scattering that reduces contrast and clarity of images, frequently masking small details and far-off objects. It is mostly caused by microscopic airborne particles like smoke, dust, and water droplets that scatter incoming light. The scattered light, producing a hazy image, diminishes the direct light that reaches the camera sensor. Many image processing methods have been presened to solve this problem and lessen the impacts of haze. Usually, these methods work by determining how much haze is there in an image, and then using this information to get the image back to its assumed previous quality. In this work, we present the proposed Modified Contrast Enhancement and Exposure Fusion (MCEEF) technique. The MCEEF dehazing technique falls under the umbrella of enhancement-based dehazing techniques. In this technique, hazy frames or images undergo sharpening through a Smoothing-Sharpening Image Filter (SSIF) designed to accentuate the disparity between the haze and objects in images. Subsequently, Gamma Correction (GC) and Color Preserving Adaptive Histogram Equalization (CP-AHE) enhance the sharpened hazy images by augmenting their contrast. Dehazed images are then obtained by fusing the results of the CP-AHE- and GC-enhanced images. The MCEEF dehazing technique is aided with enhanced hazy images or frames as input for the dehazing process. Moreover, essential enhancement tools precede the MCEEF dehazing technique. These tools include homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE), which are instrumental in controlling the dynamic range before the dehazing phase. In the proposed approach, a hazy image or frame is initially subjected to homomorphic processing, followed by the application of CLAHE, and finally, the MCEEF dehazing technique is employed. To demonstrate the effectiveness of the proposed approach, we apply it on both visible and Near Infrared (NIR) frames. We

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

Risk identification method of dangerous driving behavior based on sliding window feature fusion

Advances in Transportation Studies

引用

Advances in Transportation Studies 2022年第Special issue期4卷 133-144页

作者： Chu, Y.X. Zhang, J. Yang, L. School of Electronics and Information Engineering Sias University Zhengzhou451150 China College of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou450001 China

It is of great significance to effectively identify the dangerous driving behaviors of drivers in real time. In order to improve the accuracy of driving behavior classification and the efficiency of risk identification, this paper proposes a risk identification method of road traffic dangerous driving behavior based on sliding window feature fusion. Firstly, the influencing factors of driving danger scenes are obtained, and the driving behavior characteristics are extracted according to the sliding window method;Then, the feature multiplication is used to calculate the time feature, and the spatial feature under each channel is calculated. The feature fusion method is used to achieve the spatio-temporal feature fusion;Finally, the risk identification function is constructed according to the ConvLSTM cascade method, and the risk identification result is obtained. The experimental results show that the classification accuracy of this method can reach 96.93%, the recognition accuracy is 93%, and the time consumption is less than 30s. The method of road traffic dangerous driving behavior risk identification based on sliding window feature fusion has better accuracy of driving behavior classification and better risk identification efficiency. © 2022, Aracne Editrice. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Sustainable AI Systems for Monitoring and Predicting Wildfires in Vulnerable Forest Regions

Sustainable AI Systems for Monitoring and Predicting Wildfir...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Raj, T. Selvin Retna Raj, J. Relin Francis Krishnan, R. Santhana Balamuralikrishnan, G. Vikkiramapandian, D. Jothi, J. Nirmal Dmi College of Engineering Department of Electronics and Communication Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Scad College of Engineering of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India Psna College of Engineering and Technology Department of Information Technology Dindigul India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Avadi Chennai India

ISBN: (纸本)9798331509828

Wildfires pose significant threats to ecological systems, human safety, and economic stability, especially in vulnerable forest regions. To address this critical issue, a sustainable AI-driven framework, WiSEFire (Wildfire Surveillance and Estimation), is proposed for real-time monitoring and prediction of wildfires. The framework integrates a hybrid approach, utilizing Random Forest for feature analysis and Gated Recurrent Units (GRU) for temporal fire prediction. The system processes multi-source data, including satellite imagery, IoT sensors, and meteorological information, to enhance detection accuracy and prediction reliability. Simulation experiments were conducted using benchmark datasets to evaluate WiSEFire against state-of-the-art algorithms, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. Performance metrics such as accuracy, latency, and detection efficiency were analyzed. The results demonstrated that WiSE Fire outperformed existing methods, achieving superior detection precision and reduced latency while maintaining energy efficiency. This research highlights the potential of sustainable AI frameworks for mitigating wildfire risks and improving emergency response capabilities © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Keylogger Detection Systems Using Recurrent Neural Networks Enabled with Feature Selection Model 7th

An Enhanced Keylogger Detection Systems Using Recurrent Neur...

引用

7th International Conference on communication, Device and Networking, ICCDN 2024

作者： Awotunde, Joseph Bamidele Sur, Samarendra Nath Imoize, Agbotiname Lucky Rodríguez, Demóstenes Zegarra Akanji, Boluwatife Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara State Ilorin240003 Nigeria Department of Electronics and Communication Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos 100213 Nigeria Department of Electrical Engineering and Information Technology Institute of Digital Communication Ruhr University Bochum44801 Germany Department of Computer Science Federal University of Lavras Minas Gerais Lavras Brazil

ISBN: (纸本)9789819764648

Keyloggers are malicious software programs that record keystrokes of users without their consent or knowledge. They can steal sensitive information like credit card numbers and passwords. They pose a significant threat to users’ privacy and security since they capture keystroke data. Keylogger detection systems play a vital role in safeguarding users from cyberattacks and mitigating the potential harm caused by keyloggers. Keylogger detection systems employing deep learning have been widely used for identifying and mitigating cyber threats associated with keyloggers. However, they struggle to identify new or unfamiliar keylogger samples. This study aims to explore deep learning techniques with feature selection model to detect keylogger. This study employs Recurrent Neural Networks (RNNs) using a collection of known keylogger dataset. Furthermore, a correlation-based feature extraction method was applied to identify the most relevant features for the model, highlighting the importance of specific features, such as URG flag Count, ACK flag count, and Idle Mean, in differentiating between benign and keylog classes. The proposed model demonstrates superior accuracy of 0.8763 and precision of 0.8569 compared to a baseline model using Logistic Regression (LR) 0.7721 and 0.7407, respectively, indicating a better balance between accurate classification and minimizing false negatives and false positives. The findings from this study help to improve keylogger detection methods, making them more powerful and efficient. These results suggest that a keylogger-based detection system employing a deep learning approach can be a valuable tool for addressing the complex and evolving landscape of cyber threats related to keylogging. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Land Cover Segmentation for Agricultural Monitoring Using Synthetic Aperture Radar (SAR) Imagery with Convolutional Neural Networks and Attention-Based Transformer Models

Land Cover Segmentation for Agricultural Monitoring Using Sy...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Prakash, E.P. Sathiya, K.G. Manoranjitham, S. Sekar, G. Munaf, S. Santhia, R.K. Dr. N.G.P. Institute of Technology Department of Computer Science and Engineering Coimbatore641048 India Arunai Engineering College Department of Electronics and Communication Engineering Tiruvannamalai606604 India Agni college of Technology Department of Information Technology Chennai600130 India Vsb College Of Engineering Department of Electronics and Communication Engineering Technical Campus Coimbatore642109 India Sri Ramakrishna Institute of Technology Department of Electronics and Communication Engineering Coimbatore641010 India Pondicherry University Department of Computer Science and Engineering 605014 India

ISBN: (纸本)9798331509828

Automated classification of land cover types is one of the most crucial aspects within many remote sensing applications, including the monitoring of agricultural land and territories. This work proposes a novel approach for division of land covers using a hybrid of CNNs and Attention-based Transformer networks. CNNs are adopted to extract the spatial features from different levels of the SAR image, while Transformer Model Arch applies self-attention functions to explore the long-range dependency and contextual relation of the entire image. The model learning process is performed end-to-end from multi-temporal SAR data to differentiate different types of land covers, including crops, vegetation, water, and urban surfaces. In this case, we apply the proposed approach to different agricultural areas to show that it outperforms traditional methods, such as thresholding and other machine learning approaches. The results highlight the viability of this mixed form to solve the noise and changeable nature of SAR imagery, in terms of enhancing the use of the agricultural monitoring application. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Electricity Consumption Classification using Various Machine Learning Models

EAI Endorsed Transactions on Energy Web

引用

EAI Endorsed Transactions on Energy Web 2024年 11卷 1-6页

作者： Paikaray, Bijay Kumar Jena, Swarna Prabha Mondal, Jayanta Van Thuan, Nguyen Tung, Nguyen Trong Mallick, Chandrakant Bhubaneswar India Department of Electronics and Communication Engineering Centurion of University of Technology and Management Odisha India School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Faculty of Engineering Technology Hung Vuong University Viet Nam Quality Assurance Dong A University Viet Nam Department of Computer Science & Information Technology GITA Autonomous College Odisha Bhubaneswar India

INTRODUCTION: As population has increased over successive generations, human dependency on electricity has increased to the point where it has become a norm and indispensable, and the idea of living without it has become unthinkable. OBJECTIVES: Machine learning is emerging as a fundamental method for performing tasks autonomously without human intervention. Forecasting electricity consumption is challenging due to the many factors that influence it;embracing modern technology with its heavy focus on machine learning and artificial intelligence is a potential solution. METHODS: This study employs various machine learning algorithms to forecast power usage and determine which method performs best in predicting the dataset based on different variables. RESULTS: Eight models were tested, including Linear Regression, DT Classifier, RF Classifier, KNN, DT Regression, SVM, Logistic Regression, and GNB Classifier. The Decision Tree model had the greatest accuracy of 98.3%. CONCLUSION: The Decision Tree model’s accuracy can facilitate efficient use of electricity, leading to both conservation of electricity and cost savings, and be a guiding light in future planning. Copyright © 2024 Paikaray, B.K. et al., licensed to EAI. This open-access article is distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transforming, and building upon the material in any medium so long as the original work is properly cited.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Detection of Malaria by Using a CNN Model 4th

Detection of Malaria by Using a CNN Model

引用

4th International Conference on Machine Intelligence and Signal Processing, MISP 2022

作者： Choubey, Dilip Kumar Raj, Sandeep Aman, Arju Deoli, Rajat Hanselia, Rishabh Department of Computer Science and Engineering Indian Institute of Information Technology Bhagalpur Bihar India Department of Electronics and Communication Engineering Indian Institute of Information Technology Bhagalpur Bihar India

ISBN: (纸本)9789819900848

Malaria is a dangerous and potentially fatal disease caused by Plasmodium parasites that are transferred to humans through the bites of infected Anopheles mosquitos. The most common and accepted technique of diagnosing malaria is for a competent technician to visually analyze a blood smear under a microscope for parasitized red blood cells. The individual conducting the inspection’s experience and knowledge is used to make a diagnosis. It’s also time-consuming and, in rare situations, prone to human mistakes. The research work has been processed into two stages: Stage one deals with dataset summarization, whereas Stage two deals with the proposed algorithm. We present a completely automated CNN-based model for identifying malaria in blood smear micrographs in this study. Our proposed algorithm has a ninety-six percent accuracy rate in detecting malarial parasites from microscopic images, which can be improved further when trained and tested on larger datasets. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

IoT ML Driven Holistic Health Monitoring and Fitness Assessment Empowering Proactive Wellbeing Management

IoT ML Driven Holistic Health Monitoring and Fitness Assessm...

引用

2024 IEEE Students Conference on engineering and Systems, SCES 2024

作者： Mishra, Sachin Singh, Anurag Dept. of Computer Science and Engineering Government Engineering College Raipur Chhattisgarh Raipur India International Institute of Information Technology Dept. of Electronics & Communication Engineering Chhattisgarh Naya Raipur India

ISBN: (纸本)9798350374711

In recent years, significant advancements in the area of non-invasive and wearable technology have paved the way for widespread applications of personalized and remote health monitoring. Health monitoring enables proactive management of one's well-being, and enhances overall health outcomes. With the advent of such technologies there are lots of platforms developed. But such platforms are not successful in providing the followings: 1) the ability to monitor all major health vitals in one unified application, & 2) the provision of a holistic health score derived from these non-invasive vitals for fitness measurement. In response, this paper presents a novel solution featuring: 1) An IoT-ML enabled platform for self-monitoring of important health vitals, and 2) A fitness assessment score derived through ML algorithm using the health vitals of a person. By integrating data on various health parameters including heart rate, blood oxygen levels, and sleep patterns, advanced machine learning models are developed to analyze this data and predict the fitness score that accurately reflects an individual's overall health and fitness level. The performance of the proposed estimation model is evaluated using R2 and mean square error (MSE) and the best value is achieved using the XGBoost regressor of values 0.967 and 0.0033. This solution empowers individuals to take control of their well-being and improve their overall quality of life. Overall, the integration of non-invasive methods and IoT sensors for health vitals monitoring and fitness assessment presents a novel approach with significant potential to revolutionize health care. By empowering individuals with real-time insights and a comprehensive fitness score, this solution facilitates informed decision-making and enables individuals to proactively manage their health and well-being, ultimately enhancing their overall quality of life. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Comparative Study between KNN and CNN's Techniques for Kidney Stone Detection

Comparative Study between KNN and CNN's Techniques for Kidne...

引用

2023 International Conference on Smart Computing and Application, ICSCA 2023

作者： Al-Tbenawey, Fahdah M. Alotaibi, Shoayee Salem, Marwa Mir, Shamaila Mir, Zahida Computer Science and Engineering College University of Ha'il Department of Computer Science and Information Hail Saudi Arabia Faculty of Engineering Department of Electrical Communication and Electronics Systems Engineering Cairo Egypt

ISBN: (纸本)9798350347050

This paper aims to determine the better technique for kidney stone detection between K-Nearest Neighbor (KNN) and Convolutional Neural Networks (CNNs). As well known, the presence of kidney stones is an important topic that deserves discussion regarding expected medical outcomes. Most of the detection measures comprise CT scans, ultrasounds, and abdominal X-rays. These measures have varying effectiveness levels, hence used in the detection to prepare patients for specific treatment options. Patients' treatment options comprise percutaneous nephrolithotomy (PCNL), extracorporeal shockwave lithotripsy (ESWL), and ureteroscopy. The different detection techniques carried out for the patients are essential to test whether the patient has small or large kidney stones. One essential technique is using conventional neural networks (CNNs) technology. In this paper kidney, stone detection will be carried out using both of K-Nearest Neighbor (KNN) and CNN's techniques. A comparison between both techniques will be carried out to figure out the better. All of the simulations are carried out using MATLAB. © 2023 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Methods for Enhancing Parkinson's Disease Early Detection 4

Hybrid Deep Learning Methods for Enhancing Parkinson's Disea...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Devi, S. Vijaya Amala Vijayalakshmi, K. Krishnan, R. Santhana Raj, J. Relin Francis Umesh, R. Soundiraraj, N. Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Velammal College of Engineering and Technology Department of Information Technology Madurai India Psna College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul India

ISBN: (纸本)9798331523923

Parkinson's Disease (PD) is a progressive neurodegenerative disorder that significantly impacts motor function. Early detection is critical for effective intervention, yet traditional diagnostic methods often face limitations in accuracy and timeliness. This paper proposes a hybrid deep learning model combining EfficientNet, BiLSTM, and GANs to improve PD detection accuracy using medical images and sequential data. EfficientNet is employed for extracting features from MRI scans, while BiLSTM is used to analyze temporal data, such as gait and speech patterns, to capture the progressive changes associated with PD. Additionally, GANs are utilized to augment the dataset, addressing the challenges of data scarcity and imbalance. The fusion of spatial and temporal features enables a more comprehensive understanding of PD, improving diagnostic performance. Bayesian optimization is applied for hyperparameter tuning, and K-fold cross-validation ensures robust model evaluation. The results demonstrate that the hybrid model outperforms single-modal approaches in both classification and regression tasks, offering enhanced accuracy in detecting PD and predicting disease severity. Furthermore, interpretability techniques like Grad-CAM and attention mechanisms are incorporated to provide insights into the model's decision-making process. This work presents a promising approach for automating PD diagnosis and lays the groundwork for further research in multi-modal deep learning for disease detection. © 2025 IEEE.

关键词： Deep learning

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：