检索结果-内蒙古大学图书馆

Employing of machine learning and wearable devices in healthcare system: tasks and challenges

Neural Computing and Applications 2024年第29期36卷 17829-17849页

作者： Saad, Hend S. Zaki, John F. W. Abdelsalam, Mohamed M. Computers Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

Disease outbreaks are nowadays a critical issue despite the development and rapid growth of technology. One of the major challenges facing healthcare professionals and healthcare industries is disease prevention and control by technology. Due to busy work schedules, maintaining a healthy lifestyle has become impossible, so the solution to these previous challenges is the intelligent health monitoring system. Over the past few years, a lot of research has been done on the use of Machine learning (ML) techniques in healthcare applications. With wearable devices, ML greatly helps in tracking human activities and vital signs as well as helping to monitor and diagnose patients’ health so it plays a huge role in elderly care. Research and development of more applications for wearable devices has been underway in the past five years, due to significant technological advances in medical sensors. Despite the widespread use of wearable devices, there is little research on machine learning applications of these devices. This paper presents a review of the different areas of recent ML research for healthcare wearable devices. It also discusses the different challenges facing ML applications on wearable devices. © The Author(s) 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MCHIAO: a modified coronavirus herd immunity-Aquila optimization algorithm based on chaotic behavior for solving engineering problems

引用

Neural Computing and Applications 2024年第22期36卷 13381-13465页

作者： Selim, Heba Haikal, Amira Y. Labib, Labib M. Saafan, Mahmoud M. Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt

This paper proposes a hybrid Modified Coronavirus Herd Immunity Aquila Optimization Algorithm (MCHIAO) that compiles the Enhanced Coronavirus Herd Immunity Optimizer (ECHIO) algorithm and Aquila Optimizer (AO). As one of the competitive human-based optimization algorithms, the Coronavirus Herd Immunity Optimizer (CHIO) exceeds some other biological-inspired algorithms. Compared to other optimization algorithms, CHIO showed good results. However, CHIO gets confined to local optima, and the accuracy of large-scale global optimization problems is decreased. On the other hand, although AO has significant local exploitation capabilities, its global exploration capabilities are insufficient. Subsequently, a novel metaheuristic optimizer, Modified Coronavirus Herd Immunity Aquila Optimizer (MCHIAO), is presented to overcome these restrictions and adapt it to solve feature selection challenges. In this paper, MCHIAO is proposed with three main enhancements to overcome these issues and reach higher optimal results which are cases categorizing, enhancing the new genes’ value equation using the chaotic system as inspired by the chaotic behavior of the coronavirus and generating a new formula to switch between expanded and narrowed exploitation. MCHIAO demonstrates it’s worth contra ten well-known state-of-the-art optimization algorithms (GOA, MFO, MPA, GWO, HHO, SSA, WOA, IAO, NOA, NGO) in addition to AO and CHIO. Friedman average rank and Wilcoxon statistical analysis (p-value) are conducted on all state-of-the-art algorithms testing 23 benchmark functions. Wilcoxon test and Friedman are conducted as well on the 29 CEC2017 functions. Moreover, some statistical tests are conducted on the 10 CEC2019 benchmark functions. Six real-world problems are used to validate the proposed MCHIAO against the same twelve state-of-the-art algorithms. On classical functions, including 24 unimodal and 44 multimodal functions, respectively, the exploitative and explorative behavior of the hybrid

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

IHHO: an improved Harris Hawks optimization algorithm for solving engineering problems

引用

Neural Computing and Applications 2024年第20期36卷 12185-12298页

作者： Akl, Dalia T. Saafan, Mahmoud M. Haikal, Amira Y. El-Gendy, Eman M. Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt

Harris Hawks optimization (HHO) algorithm was a powerful metaheuristic algorithm for solving complex problems. However, HHO could easily fall within the local minimum. In this paper, we proposed an improved Harris Hawks optimization (IHHO) algorithm for solving different engineering tasks. The proposed algorithm focused on random location-based habitats during the exploration phase and on strategies 1, 3, and 4 during the exploitation phase. The proposed modified Harris hawks in the wild would change their perch strategy and chasing pattern according to updates in both the exploration and exploitation phases. To avoid being stuck in a local solution, random values were generated using logarithms and exponentials to explore new regions more quickly and locations. To evaluate the performance of the proposed algorithm, IHHO was compared to other five recent algorithms [grey wolf optimization, BAT algorithm, teaching–learning-based optimization, moth-flame optimization, and whale optimization algorithm] as well as three other modifications of HHO (BHHO, LogHHO, and MHHO). These optimizers had been applied to different benchmarks, namely standard benchmarks, CEC2017, CEC2019, CEC2020, and other 52 standard benchmark functions. Moreover, six classical real-world engineering problems were tested against the IHHO to prove the efficiency of the proposed algorithm. The numerical results showed the superiority of the proposed algorithm IHHO against other algorithms, which was proved visually using different convergence curves. Friedman's mean rank statistical test was also inducted to calculate the rank of IHHO against other algorithms. The results of the Friedman test indicated that the proposed algorithm was ranked first as compared to the other algorithms as well as three other modifications of HHO. © The Author(s) 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Economically optimized heat exchanger design: a synergistic approach using differential evolution and equilibrium optimizer within an evolutionary algorithm framework

引用

Neural Computing and Applications 2024年第24期36卷 14999-15026页

作者： Moharam, Amal Haikal, Amira Y. Elhosseini, Mostafa Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

This study introduces the CP-EODE algorithm, a novel hybrid of the Equilibrium Optimizer (EO), and the Differential Evolution (DE) algorithm. It addresses EO’s tendency toward premature convergence by enhancing its exploration capabilities. The motivation for this research stems from the need for more efficient and economically viable designs in engineering, particularly in the optimization of shell-and-tube heat exchangers (STHEs) and photovoltaic module parameters. The CP-EODE algorithm leverages DE's exploration strengths to enhance EO’s performance adopting a cooperative parallel approach that divides the population into EO and DE sub-populations for a more effective search space exploration. The validation of CP-EODE’s effectiveness commenced with its application to 29 benchmark functions, where a Friedman test yielded an Fr value of 22.19, significantly surpassing the critical value of 7.81, and a Wilcoxon signed rank test confirmed statistical improvements with a z-score beyond − 1.96. Four quality metrics were discussed to provide a detailed assessment of CP-EODE’s performance highlighting its robust exploration and exploitation capabilities. In practical applications, CP-EODE demonstrated significant advancements in STHE design achieving up to 19.706% reduction in heat exchanger surface area compared to traditional and other algorithmic designs, showcasing its potential to enhance engineering design efficiency and cost-effectiveness. A critical examination of the algorithm's convergence rate revealed its swift optimization capability, with rapid attainment of optimal solutions in various test cases, further establishing CP-EODE’s advantage in handling complex optimization challenges. Through rigorous statistical analysis and performance metrics, CP-EODE emerges as a superior solution for complex optimization challenges, underscoring the value of hybrid algorithmic strategies in engineering optimizations. © The Author(s), under exclusive licence to Springer-

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

A comprehensive framework towards segmenting and classifying breast cancer patients using deep learning and Aquila optimizer

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第6期14卷 7897-7917页

作者： Balaha, Hossam Magdy Antar, Esraa Raffik Saafan, Mahmoud M. El-Gendy, Eman M. Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt

Breast cancer is among the major frequent types of cancer worldwide, causing a significant death rate every year. It is the second most prevalent malignancy in Egypt. With the increasing number of new cases, it is vital to diagnose breast cancer in its early phases to avoid serious complications and deaths. Therefore, routine screening is important. With the current evolution of deep learning, medical imaging became one of the interesting fields. The purpose of the current work is to suggest a hybrid framework for both the classification and segmentation of breast scans. The framework consists of two phases, namely the classification phase and the segmentation phase. In the classification phase, five different CNN architectures via transfer learning, namely MobileNet, MobileNetV2, NasNetMobile, VGG16, and VGG19, are applied. Aquila optimizer is used for the calculation of the optimal hyperparameters of the different TL architectures. Four different datasets representing four different modalities (i.e., MRI, Mammographic, Ultrasound images, and Histopathology slides) are used for training purposes. The framework can perform both binary- and multi-class classification. In the segmentation phase, five different structures, namely U-Net, Swin U-Net, Attention U-Net, U-Net++, and V-Net, are applied to identify the region of interest in the ultrasound breast images. The reported results prove the efficiency of the suggested framework against current state-of-the-art studies. © 2023, The Author(s).

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Real-time drone detection framework based on advanced texture feature extraction and pattern recognition model using GUI

引用

Neural Computing and Applications 2025年第5期37卷 3435-3454页

作者： Hussen, Noha Salem, Mofreh Eldesouky, Ali I. Sakr, Noha Elghamrawy, Sally Computers and Control Systems Engineering Department Mansoura University Mansoura Egypt Computer Engineering Department Misr Higher Institute for Engineering and Technology Mansoura Egypt

The increasing prevalence of drones has raised significant concerns regarding their potential for misuse in activities such as smuggling, terrorism, and unauthorized access to restricted airspace. Consequently, the development of robust and efficient drone detection systems has become paramount. Traditional detection methods such as radar and acoustic sensors have limitations in detecting small drones and can be costly to implement. This can lead to lower detection rates and increased security breaches and safety concerns. However, prevailing methodologies often falter in achieving real-time detection with requisite precision and efficacy, particularly within complex operational environments. Motivated by the imperative to surmount these challenges, our research endeavors to introduce a pioneering real-time drone detection framework. Our study encapsulates several seminal advancements. Firstly, we proffer a groundbreaking framework that synergizes advanced integration technique based on texture feature extraction and pattern recognition techniques for real-time drone detection to increase accuracy to detect drones in different conditions such as bad weather and low resolution. Secondly, we introduce an intuitive graphical user interface, enhancing the usability and accessibility of the system in real-time scenario. Lastly, through exhaustive evaluation and comparative analysis, we substantiate the superior performance of our framework in terms of accuracy, precision, and real-time detection capabilities compared to conventional DDS methodologies. Its stability and effectiveness render it a compelling solution for security-focused entities, notably those within air force and military systems. Our experimental results reveal a commendable accuracy rate of 97%, affirming the reliability and precision 98% and recall parameter 98% of our framework in accurately identifying and detecting drones, thus surpassing recent models in the field. © The Author(s), under exclusive

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

ELCD-NSC2: a novel early lung cancer detection and non-small cell classification framework

引用

Neural Computing and Applications 2024年第24期36卷 15149-15164页

作者： Helaly, Hadeer A. Badawy, Mahmoud El-Gendy, Eman M. Haikal, Amira Y. Electrical Engineering Department Faculty of Engineering Damietta University Damietta Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Department of Computer Science and Informatics Taibah University Medina Saudi Arabia

The survival rate of lung cancer relies significantly on how far the disease has spread when it is detected, how it reacts to the treatment, the patient’s overall health, and other factors. Therefore, the earlier the lung cancer diagnosis, the higher the survival rate. For radiologists, recognizing malignant lung nodules from computed tomography (CT) scans is a challenging and time-consuming process. As a result, computer-aided diagnosis (CAD) systems have been suggested to alleviate these burdens. Deep-learning approaches have demonstrated remarkable results in recent years, surpassing traditional methods in different fields. Researchers are currently experimenting with several deep-learning strategies to increase the effectiveness of CAD systems in lung cancer detection with CT. This work proposes a deep-learning framework for detecting and diagnosing lung cancer. The proposed framework used recent deep-learning techniques in all its layers. The autoencoder technique structure is tuned and used in the preprocessing stage to denoise and reconstruct the medical lung cancer dataset. Besides, it depends on the transfer learning pre-trained models to make multi-classification among different lung cancer cases such as benign, adenocarcinoma, and squamous cell carcinoma. The proposed model provides high performance while recognizing and differentiating between two types of datasets, including biopsy and CT scans. The Cancer Imaging Archive and Kaggle datasets are utilized to train and test the proposed model. The empirical results show that the proposed framework performs well according to various performance metrics. According to accuracy, precision, recall, F1-score, and AUC metrics, it achieves 99.60, 99.61, 99.62, 99.70, and 99.75%, respectively. Also, it depicts 0.0028, 0.0026, and 0.0507 in mean absolute error, mean squared error, and root mean square error metrics. Furthermore, it helps physicians effectively diagnose lung cancer in its early stages and allows spe

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Novel Framework of Segmentation 3D MRI of Brain Tumors

引用

computers, Materials & Continua 2023年第2期74卷 3489-3502页

作者： Ibrahim Mahmoud El-Henawy Mostafa Elbaz Zainab H.Ali Noha Sakr Department of Computer Science Faculty of Computers and InformaticsZagazig UniversityZagazigEgypt Department of Computer Science Faculty of Computers and InformaticsKafrelsheikh UniversityKafrelsheikhEgypt Department of Embedded Network Sys.and Tec. Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikhEgypt Computers Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansouraEgypt

Medical image segmentation is a crucial process for computer-aided diagnosis and *** image segmentation refers to portioning the images into small,disjointed parts for simplifying the processes of analysis and *** and speckle noise are different types of noise in magnetic resonance imaging(MRI)that affect the accuracy of the segmentation process ***,image enhancement has a significant role in MRI *** paper proposes a novel framework that uses 3D MRI images from Kaggle and applies different diverse models to remove Rician and speckle noise using the best possible noise-free *** proposed techniques consider the values of Peak Signal to Noise Ratio(PSNR)and the level of noise as inputs to the attention-U-Net model for segmentation of the *** framework has been divided into three stages:removing speckle and Rician noise,the segmentation stage,and the feature extraction *** framework presents solutions for each problem at a different stage of the *** the first stage,the framework uses Vibrational Mode Decomposition(VMD)along with Block-matching and 3D filtering(Bm3D)algorithms to remove the ***,the most significant Rician noise-free images are passed to the three different methods:Deep Residual Network(DeRNet),Dilated Convolution Auto-encoder Denoising Network(Di-Conv-AE-Net),andDenoising Generative Adversarial Network(DGAN-Net)for removing the speckle *** Bm3D have achieved PSNR values for levels of noise(0,0.25,0.5,0.75)for reducing the Rician noise by(35.243,32.135,28.214,24.124)and(36.11,31.212,26.215,24.123)*** framework also achieved PSNR values for removing the speckle noise process for each level as follows:(34.146,30.313,28.125,24.001),(33.112,29.103,27.110,24.194),and(32.113,28.017,26.193,23.121)forDeRNet,Di-Conv-AE-Net,and DGAN-Net,*** experiments that have been conducted have proved the efficiency of the proposed framework a

关键词： MRI Rician noise speckle noise segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Model for Segmentation of the Skin Lesion Based on Residual Attention U-Net

引用

computers, Materials & Continua 2023年第6期75卷 5177-5192页

作者： Saleh Naif Almuayqil Reham Arnous Noha Sakr Magdy M.Fadel Department of Information Systems College of Computer and Information SciencesJouf UniversitySakakaSaudi Arabia Department of Communications and Electronics Delta Higher Institute for Engineering and Technology(DHIET)MansouraEgypt Computers Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansouraEgypt

Skin segmentation participates significantly in various biomedical applications,such as skin cancer identification and skin lesion *** paper presents a novel framework for segmenting the *** framework contains two main stages:The first stage is for removing different types of noises from the dermoscopic images,such as hair,speckle,and impulse noise,and the second stage is for segmentation of the dermoscopic images using an attention residual U-shaped Network(U-Net).The framework uses variational Autoencoders(VAEs)for removing the hair noises,the Generative Adversarial Denoising Network(DGAN-Net),the Denoising U-shaped U-Net(D-U-NET),and Batch Renormalization U-Net(Br-U-NET)for remov-ing the speckle noise,and the Laplacian Vector Median Filter(MLVMF)for removing the impulse *** the second main stage,the residual attention u-net was used for *** framework achieves(35.11,31.26,27.01,and 26.16),(36.34,33.23,31.32,and 28.65),and(36.33,32.21,28.54,and 27.11)for removing hair,speckle,and impulse noise,respectively,based on Peak Signal Noise Ratio(PSNR)at the level of(0.1,0.25,0.5,and 0.75)of *** framework also achieves an accuracy of nearly 94.26 in the dice score in the process of segmentation before removing noise and 95.22 after removing different types of *** experiments have shown the efficiency of the used model in removing noise according to the structural similarity index measure(SSIM)and PSNR and in the segmentation process as well.

关键词： Skin tumor speckle noise impulse noise hair noise deep learning segmentation

来源：评论

学校读者我要写书评

暂无评论

Collision avoidance and routing based on location access (CARLA) of mobile robots

引用

Neural Computing and Applications 2025年第9期37卷 6401-6430页

作者： ElSayyad, Shimaa Ezzat Saleh, Ahmed I. Ali, Hesham A. Saraya, M.S. Rabie, Asmaa H. Abdelsalam, Mohamed M. Computers Engineering Department MISR Higher Institute for Engineering and Technology Mansoura Round Road Mansoura City35516 Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt Dean of Faculty of Artificial Intelligence Delta University for Science and Technology Gamasa Mansoura Egypt Faculty of Engineering Mansoura National University Gamasa Mansoura Egypt

The paper introduces a new path-planning robotic system methodology called Collision Avoidance and Routing based on Location Access (CARLA) for use in critical environments such as hospitals and crises where quick action and saving human lives are vital. The main focus of our framework is on accuracy and fast responses, such as delivering tools or items in a specific area while avoiding collisions with other robots and obstacles. CARLA is designed to provide quick responses during emergencies, unlike most existing algorithms that are integrated into site control units or distributed among mobile robots on-site. By being loaded onto a remote server node rather than individual robots, CARLA helps to conserve the robots' capabilities, hardware resources, and power consumption. Additionally, our system utilizes cloud computing and Fog servers technology to improve data transmission times between the cloud and smart devices, especially for applications with strict timing requirements like emergency response. The Fog platform is also leveraged to enhance on-site access to real-time interaction and location-based services by bringing processing power closer to the robots from far-off Cloud servers. CARLA has various applications, such as in factories and warehouses, where mobile robots need to be selected and directed by a central control system remotely. The proposed framework consists of three main modules: Robot Knowledge Module, Robot Selection Module, and Route Reservation Module, which will all be discussed in detail in this paper. The results of simulations using this framework show that the robots have improved flexibility and efficiency in terms of computing paths and successfully fulfiling requests without colliding, compared to traditional methods used in similar scenarios. © The Author(s) 2025.

关键词： Mobile robots

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：