检索结果-内蒙古大学图书馆

2023 International Telecommunications Conference, ITC-Egypt 2023

作者： Shehab, Mohamed Elghamrawy, Sally The British University in Egypt Department of Computer Engineering Cairo Egypt MISR Higher Institute for Engineering and Technology Computer Engineering Department Mansoura Egypt

ISBN: (纸本)9798350326062

Skin cancer is arguably known as one of the most prevalent cancers. However, it is also one of the most preventable and treatable types of cancer if caught early. An automated skin cancer detection system can help catch potential skin cancers early and prevent the disease from progressing to a more advanced and dangerous stage compared with manual detection methods, which are often prone to human error and may not always be accessible to people living in remote areas. Recently, convolutional neural networks (CNNs) have taken a front seat in today's technology as they automatically classify images based on their visual features. In this paper, deep learning was utilized as a tool to further enhance and increase accuracy in reference to skin cancer detection in its initial stages through CNN and transfer learning. Achieved results in classifying skin cancer into 7 classes comprise of 78% in regards to the basic CNN, however the transfer learning with VGG16 resulted in an accuracy rate of 84%. Another considered approach is to segregate the two main skin cancer types, melanoma and benign, and this resulted in an accuracy rate of 92% when tested on the basic CNN model. However, it did not improve from 92% when tested after adding the VGG16 pretrained model, so another approach has been considered, a combination of two pre-trained models has implemented subsequently in attempt to improve results. This approach acquired 95% accuracy rate when tested on unseen data classifying the skin lesions into two classes. © 2023 IEEE.

关键词： Convolutional neural networks

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

An Improved Deep Structure for Accurately Brain Tumor Recognition

引用

Computer Systems Science & engineering 2023年第8期46卷 1597-1616页

作者： Mohamed Maher Ata Reem N.Yousef Faten Khalid Karim Doaa Sami Khafaga Department of Communications and Electronics Engineering MISR Higher Institute for Engineering and TechnologyMansoura35516Egypt Department of Electronics and Communications Delta Higher Institute for Engineering and TechnologyMansoura35516Egypt Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

Brain neoplasms are recognized with a biopsy,which is not commonly done before decisive brain *** using Convolutional Neural Networks(CNNs)and textural features,the process of diagnosing brain tumors by radiologists would be a noninvasive *** paper proposes a features fusion model that can distinguish between no tumor and brain tumor types via a novel deep learning *** proposed model extracts Gray Level Co-occurrence Matrix(GLCM)textural features from MRI brain tumor ***,a deep neural network(DNN)model has been proposed to select the most salient features from the ***,it manipulates the extraction of the additional high levels of salient features from a proposed CNN ***,a fusion process has been utilized between these two types of features to form the input layer of additional proposed DNN model which is responsible for the recognition *** common datasets have been applied and tested,Br35H and FigShare *** first dataset contains binary labels,while the second one splits the brain tumor into four classes;glioma,meningioma,pituitary,and no ***,several performance metrics have been evaluated from both datasets,including,accuracy,sensitivity,specificity,F-score,and training *** results show that the proposed methodology has achieved superior performance compared with the current state of art *** proposed system has achieved about 98.22%accuracy value in the case of the Br35H dataset however,an accuracy of 98.01%has been achieved in the case of the FigShare dataset.

关键词： Brain tumor convolutional neural network gray level co-occurrence matrix noninvasive FigShare dataset Br35H dataset

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserved learning from non-i.i.d data in fog-assisted IoT:A federated learning approach

引用

Digital Communications and Networks 2024年第2期10卷 404-415页

作者： Mohamed Abdel-Basset Hossam Hawash Nour Moustafa Imran Razzak Mohamed Abd Elfattah Faculty of Computers and Informatics Zagazig UniversityZagazigSharqiyah44519Egypt School of Engineering and Information Technology University of New South Wales@ADFACanberraACT2600Australia Deakin University Geelong Waurn Ponds CampusAustralia Computer Science Department Misr Higher Institute for Commerce and ComputersMansoura35511Egypt

With the prevalence of the Internet of Things(IoT)systems,smart cities comprise complex networks,including sensors,actuators,appliances,and cyber *** complexity and heterogeneity of smart cities have become vulnerable to sophisticated cyber-attacks,especially privacy-related attacks such as inference and data poisoning *** Learning(FL)has been regarded as a hopeful method to enable distributed learning with privacypreserved intelligence in IoT *** though the significance of developing privacy-preserving FL has drawn as a great research interest,the current research only concentrates on FL with independent identically distributed(i.i.d)data and few studies have addressed the non-i.i.d *** is known to be vulnerable to Generative Adversarial Network(GAN)attacks,where an adversary can presume to act as a contributor participating in the training process to acquire the private data of other *** paper proposes an innovative Privacy Protection-based Federated Deep Learning(PP-FDL)framework,which accomplishes data protection against privacy-related GAN attacks,along with high classification rates from non-i.i.d ***-FDL is designed to enable fog nodes to cooperate to train the FDL model in a way that ensures contributors have no access to the data of each other,where class probabilities are protected utilizing a private identifier generated for each *** PP-FDL framework is evaluated for image classification using simple convolutional networks which are trained using MNIST and CIFAR-10 *** empirical results have revealed that PF-DFL can achieve data protection and the framework outperforms the other three state-of-the-art models with 3%–8%as accuracy improvements.

关键词： Privacy preservation Federated learning Deep learning Fog computing Smart cities

来源：评论

学校读者我要写书评

暂无评论

Waste Allocation Load Lifter Model for Trash Detection Based on Deep Learning and Wireless Localization Techniques

Waste Allocation Load Lifter Model for Trash Detection Based...

引用

作者： Mohsen, Layla Talaat, Abdulrahman Elghamrawy, Sally Computer Science Department The American University in Cairo Cairo Egypt Computer Engineering Department MISR Higher Institute for Engineering and Technology Mansoura Egypt Cairo Egypt

The progressive contamination of lands, oceans, and rivers by garbage is a growing concern. The pollution imposed by garbage accumulation can lead to serious health hazards as well as economic and environmental repercussions;this accumulation derives from irresponsible waste disposal. To counter the surplus of garbage pollution, this paper proposes an accurate, low-energy consuming system for a trash allocation robot, namely, Wall-E. Wall-E is a Waste Allocation Load Lifter Model for trash detection based on deep learning and wireless localization techniques. It is based on the integration of the deep learning models for trash detection and classification as well as a navigation system that is more accurate and energy-efficient than the commonly used global position system (GPS). The paper tests and analyses the neural network algorithms YOLOv7 and YOLOv8 conducted on a trash dataset and concludes that YOLOv7 is of higher performance in trash detection and classification. To implement this algorithm on a real-time robotic system, image frames will be sent from a Pi camera at a high frequency to a Raspberry Pi board that has YOLOv7 installed. In order to conceptually determine a suitable navigation system for our robot, the paper discusses the common challenges faced in traditional navigation systems, including proposed systems in related works and their limitations to our proposed system. In our conducted experiments, the proposed Wall-E achieved the highest accuracy in object detection using YOLOv7, which will be utilized in our robot to detect trash items sent through image frames from a Pi camera. The Dejavu navigation system was concluded as the most appropriate for our system’s requirements. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Artificial Intelligent-Based System for Crop Yield Prediction Using Climate Change Data and Sensor Fusion

An Artificial Intelligent-Based System for Crop Yield Predic...

引用

作者： Sameh, Salma Elghamrawy, Sally Electrical and Computer Engineering The British University in Egypt Al Sherouk City Cairo Egypt Computer Engineering Department MISR Higher Institute for Engineering and Technology Mansoura Egypt Cairo Egypt

The world’s food security is in danger as climate change keeps reducing the annual corps-growth rate and the world’s population grows exponentially. Predicting crop-yield has been a common practice since the beginning of time;farmers would decide where and when to plant different types of plants based on their basic knowledge of weather and soil properties and what are the suitable conditions for every crop. Improving our forecasting skills of crop-yields is crucial for feeding the growing population while reducing the negative impacts of the agriculture industry on the environment. The fluctuating climatic features pose a threat that is increasing day-by-day and affecting our crops. Not only do the fluctuating weather conditions reduce agricultural productivity, but it also reduces the nutritious value and health benefits gained from the plants. That’s because of the increase in the tonnes of pesticides used on the fields and farms as a way of coping with climate change and pollution effects and increasing the plants’ growth rate. Predicting crop-yield using Machine Learning (ML) and Deep Learning (DL) has been widely adopted by the AI community in the past few decades;however, some obstacles and bottleneck challenges that affect its accuracy remains. This paper aims to propose a forecasting framework that is easy to use, inexpensive, and reliable enough to be used and certified by governments, companies, or individuals who depend on harvest for living. The proposed framework shows how Sensor Fusion can be beneficial to the agriculture industry specifically and artificial intelligence field in general. The framework demonstrates how Sensor Fusion can be incorporated as part of the data-processing. To accommodate for the crops that require specific soil quality to ensure maximum yield, an NPK sensor and a PH level sensor will be added to measure the acidity of the soil along with the levels of nitrogen, phosphorus, and potassium. Four supervised regression machine l

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

Optimized Cooperative Caching Scheme for Mobile Ad-Hoc Networks Over IoT Systems

Optimized Cooperative Caching Scheme for Mobile Ad-Hoc Netwo...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Elmahdy M. Ameen Department of Communication and Compuer Engineering MISR Higher Institute for Engineering and Technology Mansoura Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

Mobile Ad-hoc Networks over the Internet of Things (MANET-IoT) systems combine Wireless Sensor Networks (WSNs) and Mobile Ad-hoc Networks (MANET)s with the Internet of Things (IoT) to enhance user mobility and reduce network deployment costs. This paper introduces an Optimized Cooperative Caching Scheme (OCCS) for caching in MANET-IoT systems. OCCS partitions the MANET-IoT into regions, where each region acting as a fog region managed by a Master Server (MS). The MS monitors and manages data objects, applying cache replacement policies to sink node (SN) in the region. Unlike traditional cache schemes, OCCS proactively manages cache without waiting for requests from SN nodes. By continuously monitoring data object status and exchanging this information among SNs. Experimental results show that OCCS efficiently utilizes memory capabilities and improves MANET-IoT performance in terms of network throughput, latency, and cache hit ratio.

关键词： Wireless sensor networks Cooperative caching Memory management Throughput Ad hoc networks Telecommunications Servers

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Technique for Multi-Classification of Acute Lymphocytic Leukemia

A Deep Learning Technique for Multi-Classification of Acute ...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Mervat El-Seddek Department of Communications and Electronics Engineering Misr Higher Institute for Engineering and Technology Mansoura Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

Early detection, diagnosis, prognosis, and treatment of blood cancers are challenging healthcare problems. Leukemia is a very fatal blood cancer. Leukemia can be categorized into acute leukemia and chronic leukemia. In childhood, acute lymphocytic leukemia (ALL) is responsible for about 25% of all childhood cancers. Because the microscopic images of acute leukemic b-lymphoblasts are very similar to those of benign cells under the microscope, it is very hard to stage cancer and differentiate them from benign cells. The present work proposes a computer-aided detection system to classify ALL into four classes, based on convolutional neural network (CNN) models, namely VGG16 and DenseNet201. These classes include normal cells, early lymphoid precursor (ELP), pro-B cells, and pre-B cells. The classification accuracy of the suggested approach had reached 99.66% and 99.9% for ALL multi-classification using VGG-16 and DensNet-201 respectively. The suggested system potentially improves the accuracy and speed of diagnosis to help pathologists and specialists analyze images and make the most appropriate decision to identify clinical cases of patients and start an early treatment approach.

关键词： Deep learning Pediatrics Accuracy Statistical analysis Microscopy Medical services Telecommunications

来源：评论

学校读者我要写书评

暂无评论

A new systematic firefly algorithm for forecasting the durability of reinforced recycled aggregate concrete

引用

Frontiers of Structural and Civil engineering 2022年第3期16卷 329-346页

作者： Wafaa Mohamed SHABAN Khalid ELBAZ Mohamed AMIN Ayat gamal ASHOUR Department of Civil and Environmental Engineering College of EngineeringShantou UniversityShantou 515063China Department of Civil Engineering Misr Higher Institute of Engineering and TechnologyMansouraEgypt Department of Civil Engineering Higher Future Institute of Engineering and TechnologyMansouraEgypt Guangdong Engineering Center for Structure Safety and Health Monitoring Shantou UniversityShantou 515063China Civil and Architectural Construction Department Faculty of Technology and EducationSuez UniversityIsmailiaEgypt Department of Civil and Environmental Engineering Collage of EngineeringUniversity of SharjahSharjah 27272UAE

This study presents a new systematic algorithm to optimize the durability of reinforced recycled aggregate *** proposed algorithm integrates machine learning with a new version of the firefly algorithm called chaotic based firefly algorithm(CFA)to evolve a rational and efficient predictive *** CFA optimizer is augmented with chaotic maps and Levy flight to improve the firefly performance in forecasting the chloride penetrability of strengthened recycled aggregate concrete(RAC).A comprehensive and credible database of distinctive chloride migration coefficient results is used to establish the developed algorithm.A dataset composite of nine effective parameters,including concrete components and fundamental characteristics of recycled aggregate(RA),is used as input to predict the migration coefficient of strengthened RAC as output,k-fold cross validation algorithm is utilized to validate the hybrid *** numerical benchmark analyses are applied to prove the superiority and applicability of the CFA algorithm in predicting chloride *** show that the developed CFA approach significantly outperforms the firefly algorithm on almost tested functions and demonstrates powerful *** addition,the proposed strategy can be an active tool to recognize the contradictions in the experimental results and can be especially beneficial for assessing the chloride resistance of RAC.

关键词： chloride penetrability recycled aggregate concrete machine learning concrete components durability

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Soliton Pulse Propagation Using Modified Differential Transform Methods

引用

Journal of Applied Mathematics and Physics 2024年第12期12卷 4183-4197页

作者： Entsar El-Shazly Ahmed Abo-Elenin Ibrahim El-Kalla Basic Science Department Misr Higher Institute for Engineering and Technology Mansoura Egypt Physics & Engineering Mathematics Department Faculty of Engineering Mansoura University Mansoura Egypt

In this article, a modified version of the Differential Transform Method (DTM) is employed to examine soliton pulse propagation in a weakly non-local parabolic law medium and wave propagation in optical fibers. This semi-analytic method has the advantage of overcoming the obstacle of the hardest nonlinear terms and is used to explain the origin of the bright and dark soliton solutions through the Schrödinger equation in its non-local form and the Radhakrishnan-Kundu-Laksmannan (RKL) equation. Numerical examples demonstrate the effectiveness of this method.

关键词： Soliton Pulse Parabolic Law Medium Differential Transform Method Bright Solution Dark Solution Schrödinger Equation Radhakrishnan-Kundu-Laksmannan

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：