检索结果-内蒙古大学图书馆

Telecommunications Conference (ITC-Egypt), International

作者： Waleed Abd-Elshafi Ali Hatem Abdelhamid Saleh Haneen Salah Eid Ahmed Mohamed Fathi Abd-El Rahman Amr Mohamed Department of Communications and Computer Engineering Higher Institute of Engineering EL- Shorouk Academy Cairo Egypt Department of Electronics and Communications Engineering Misr University for Science and Technology Giza Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

Advanced Driver Assistance Systems (ADAS) are a pivotal advancement in automotive technology, enhancing vehicle safety and driving experience. In our project, we have successfully designed and built a robotic prototype car. We have implemented a comprehensive control system for the car's movement, and the following features of ADAS systems: Bump Detection, Precise Lane Tracking, Adaptive Cruise Control, Traffic Sign Recognition, and Blind Spot Detection. Bump detection systems are equipped to detect and alert drivers of speed bumps and other road irregularities, in which we use NVIDIA Jetson Nano, Astra Pro Plus Depth camera as RGB and Depth sensor and use Custom AI Model based on YOLOv5 to detect different Bumps on the road and we use Python, TensorRT, and OpenCV. Lane Departure Warning (LDW) alerts drivers when their vehicle unintentionally drifts out of their lane, we use NVIDIA Jetson Nano as our main microcontroller unit (MCU) responsible for our Machine learning and Astra Pro Plus Depth camera as our RGB sensor, we use Python, Python's libraries such as OpenCV, and NumPy to implement LDW. Adaptive Cruise Control (ACC) adjusts the vehicle's speed automatically to maintain a safe distance from the vehicle ahead, we use NVIDIA Jetson Nano, Astra Pro Plus Depth camera as RGB and Depth sensor and use Custom AI Model based on YOLOv5 to detect different vehicles on the road, we use Python, TensorRT, and OpenCV. Traffic Sign Recognition can interpret and display traffic signs to keep drivers informed about speed limits, no-entry signs, and more, we use NVIDIA Jetson Nano, and Astra Pro Plus Depth camera as our RGB sensor and use Custom AI Model based on YOLOv5 to detect different Traffic Signs on the road, we use Python, TensorRT, and OpenCV. Blind Spot Detection (BSD) technology helps drivers identify vehicles in their blind spots and alerts them to avoid dangerous maneuvers, we use ESP32 as an MCU and Ultrasonic sensor, and use C++ to program the BSD feature.

关键词： YOLO Microcontrollers Robot sensing systems Cameras Feature extraction Automobiles Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Technique for early diagnosis of Skin Cancer disease using Biomedical data

A Deep Learning Technique for early diagnosis of Skin Cancer...

引用

Telecommunications Conference (ITC-Egypt), International

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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supervised Acute Lymphocytic Leukemia Detection and Classification Based - Empirical Mode Decomposition

Supervised Acute Lymphocytic Leukemia Detection and Classifi...

引用

2022 International Telecommunications Conference, ITC-Egypt 2022

作者： Elrefaie, Reem Magdy Marzouk, Elsaid Mohamed, Mohamed Ata, Mohamed Maher Researcher in Mansoura University Department of Electronics and Communications Engineering Mansoura Egypt Mansoura University Department of Electronics and Communications Engineering Faculty of Engineering Mansoura Egypt MISR Higher institute for Engineering and Technology Department of Communications and Electronics Engineering Mansoura Egypt

ISBN: (数字)9781665488082

ISBN: (纸本)9781665488082

Acute lymphocytic leukemia (ALL) is a potentially fatal disease that affects both children and adults. ALL spreads quickly in the human body and kills within weeks. Hematologists examine the blood and bone marrow to see if ALL is present. Manual blood testing methods, which have been used for a long time, might be slow. This study provided an advanced computerized mechanism for classifying leukemia into two types: normal cell leukemia and blast cell leukemia. To begin, advanced image preprocessing algorithms were used and applied to acquire data augmentation, enhancement, and transformation. Furthermore, the K-means clustering technique was used to accurately segment the appropriate nuclei from the background. Moreover, most salient features have been extract via an empirical mode decomposition (EMD) based Hilbert Hung Transform (HHT). The extracted features have been fed toward supervised classifiers in order to the classify the nuclei. A neural networks (NNs) classifier with the Bayesian regularization (BR) method have been implemented. Moreover, support vector machine (SVM), KNN, Random forest, Nave Bayes, Logistic regression, and Decision trees classifiers have been utilized, tested, and compared with NNs. Experimental results show that NNs outperformed a classification accuracy of 98.7%, sensitivity of 99.3%, and specificity of 98.1%. © 2022 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection using Artificial Intelligence techniques for Agricultural productivity enhancement in Egypt

Plant Disease Detection using Artificial Intelligence techni...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Aya Osman Ibrahim Sally Elghamrawy Computer Engineering Department The British university in Egypt Cairo Egypt Computer Engineering Department MISR Higher Institute for Engineering and Technology Mansoura Egypt

In the past few years, the use of artificial intelligence and especially Convolution Neural networks (CNN) for different computer vision tasks has been taking over. One of these tasks is detecting diseases in plants since plant diseases is now a topic of interest as it highly affects the crop yield production. Egypt in fact is one of the main countries that should consider plant disease detection for a productive crop yield since Egypt heavily relies on agriculture as it’s income. Moreover, other countries also rely on the crops exported from Egypt such as oranges, as Egypt is considered one of the largest orange exporters in the world. Therefore, deep learning was stated as the current effective approach in smart agriculture to help tackle the crop yield reduction crisis that are caused due to the neglection of plant diseases and the standard visual inspecting techniques used for detecting plant diseases. In this paper different deep learning Convolution Neural Network approaches are proposed using the new plant diseases dataset which consists of 38 classes of 14 types of healthy and diseased crop leaf images to help detect diseases in plants effectively and efficiently. The first proposed approach is a Convolution Neural Network model consisting of four convolution and pooling layers in addition to two fully connected layers and an output layer with 38 neurons for each of the 38 classes which resulted in an accuracy of 98.36%, loss of 0.0972, 98.35% F1 score, 98.36% recall, 98.39% precision, model size of 12.25mb, training time of 22.82 seconds, and total parameters of 668, 134. While the second approach is a Hybrid ResNet50-InceptionV3 model with an accuracy of 96.20%, a precision of 96.16%, and F1-score of 96.45%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Optimized Eco-Friendly High Strength Geopolymer Concrete Incorporating Clay Brick Wastes

SSRN

引用

SSRN 2023年

作者： Elemam, Walid E. Tahwia, Ahmed M. Ellatief, Mohamed Abd Kandil, Mohamed A. Structural Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Civil Engineering Department Misr Higher Institute of Engineering and Technology Mansoura Egypt

The utilization of clay brick waste (CBW) in construction industry has a great importance toward sustainability. In this study, GGBFS and fine aggregate were partially replaced by clay brick powder (CBP) and fine clay brick (FCB), respectively, to produce high strength geopolymer concrete (HSGPC) mixtures. Fly ash (FA) was also used as a partial replacement of GGBFS. HSGPC mixtures were designed using response surface methodology (RSM) with three factors including CBP (0-25%), FA (0-25%), and FCB (0-50%). The tests included slump, compressive strength, flexural strength, splitting tensile strength, and concrete microstructure. The results indicated that the incorporation of FA is essential parameter to eliminate the negative impacts of CBP and FCB addition on slump results. The higher mechanical properties could be obtained at low levels of CBP and FA as a partial replacement of GGBFS and high ratios of FCB up to 40% as a partial substitution of sand. The incorporation of CBP by minimal percentage up to 5% could significantly contribute to the hydration kinetics and the development of unreacted GGBFS and FA particles. The mixture composed of 487.5 kg/m3 GGBFS, 27 kg/m3 FA, 30.7 kg/m3 CBP, 345 kg/m3 sand, 170 kg/m3 FCB, 955 kg/m3 dolomite, 208 kg/m3 SS, 32.5 kg/m3 SH, 50.7 kg/m3 water, and 13 kg/m3 superplasticizer achieved 70.3 MPa compressive strength, 8.1 MPa splitting tensile strength, and 9.95 MPa flexural strength at age 28-days with percent increase of 30.4%, 32.8%, and 17.05%, respectively in comparison to the control mixture. A significant correlation between input parameters and output responses in predicting properties of HSGPC mixtures was obtained. © 2023, The Authors. All rights reserved.

关键词： Fly ash

来源：评论

学校读者我要写书评

暂无评论

Physical and Mechanical Properties of Lime and Wood Ash Plastering Mortars 1

引用

1st Belt and Road Webinar Series on Geotechnics, Energy, and Environment, BRWSG 2021

作者： Ashour, Ayat Gamal Shaban, Wafaa Mohamed Elbaz, Khalid Department of Civil and Environmental Engineering College of Engineering University of Sharjah Sharjah27272 United Arab Emirates Department of Civil Engineering Misr Higher Institute of Engineering and Technology El Mansoura Egypt MOE Key Laboratory of Intelligent Manufacturing Technology Department of Civil Engineering College of Engineering Shantou University Guangdong Shantou515063 China Department of Civil Engineering Higher Future Institute of Engineering and Technology El Mansoura Egypt

ISBN: (数字)9789811699634

ISBN: (纸本)9789811699627

Cement industry is one of the causes of increasing carbon dioxide in the world. Using sustainable cementitious materials as a full or partial replacement of cement is become vital to reduce the massive amount of carbon dioxide emission and encourage the use of waste materials. This study aims to build a database for the characteristics of different types of plastering mortars using waste materials, mainly, lime and wood ash as a partial replacement for cement. Four different cement types (CEM I 32.5R, CEM I 42.5R, CEM II B-S 32.5N, and CEM II B-LL 42.5N) were used with two types of lime and wood ash with different proportions were studied. To investigate the different properties of mortar, flow table test, compressive strength, flexural strength, and drying shrinkage strain were carried out. Results showed that the mortars with CEM II B-LL 42.5N have the highest values in flexure and compressive strength. However, CEM II B-S 32.5N showed the least value of dry shrinkage strain. Wood ash decreased the flexure and compressive strength of all mortars except for CEM I 32.5R which had the same value when using lime and cement. Moreover, fly ash increased the drying shrinkage for all mortars while the dry shrinkage value of mortar with CEM I 42.5R decreased. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cements

来源：评论

学校读者我要写书评

暂无评论

Audio Signal Processing and Musical Instrument Detection using Deep Learning Techniques 9

Audio Signal Processing and Musical Instrument Detection usi...

引用

9th International Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2021

作者： Elghamrawy, Sally M. Edin Ibrahim, Shehab Misr Higher Institute for Engineering and Technology Computer Engineering Department Mansoura Egypt British University in Egypt Computer Engineering Department Cairo Egypt

ISBN: (纸本)9781665482929

The advance of deep learning and audio signal processing techniques has led to serious development on Musical Information retrieval (MIR). Effective audio processing can improve speed, reduce errors, and sometimes increase the accuracy of detecting musical instrument. Spectrographic data is also necessary for many mathematical tools common across Musical Information retrieval. A major aspect of MIR is the categorization of pieces of music. One of the main tools used for categorization tasks in recent years is deep learning, which has led to many advancements in MIR. One such categorization task that deep learning is useful for is the recognition of instruments in a piece of music. In this paper, a new architecture is proposed for audio processing and musical instrument detection using Multilayer Perceptron (MLPs), Convolution Neural Networks (CNN), and Recurrent Neural Networks - Long Short Term Memory (RNN-LSTM). In addition, a number of experiments are implemented using real dataset that contains 20, 000 recording. The three deep learning techniques are implemented and compared to present potential new solutions. The usage of processing techniques unique to the field of deep learning is also discussed. © 2021 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Classification of Dermoscopy Images for Early Detection of Skin Cancer

Classification of Dermoscopy Images for Early Detection of S...

引用

2021 International Telecommunications Conference, ITC-Egypt 2021

作者： Galal, Amal Fayez, Nehal El-Seddek, Mervat Misr Higher Institute for Engineering and Technology Department of Communications and Electronics Engineering Mansoura Egypt Mansoura University Faculty of Engineering Department of Electronics and Communications Engineering Mansoura Egypt

ISBN: (纸本)9781665445733

Malignant melanoma, with a high mortality rate, is a deadly form of skin disease and its spread has risen quite significantly in recent years. Early prosopoeia of skin cancer is important for the patient's health requirements and a vital mission for the dermatologist. The factual belief is that if diagnosed early, the chance of patient survival is high. In this paper, a skin malignancy recognition system is evolved to early diagnose cutaneous lesions such as melanomas of dermoscopy images and describe its steps. First, to remove unwanted objects, such as hair, the images are processed, and then automatically the skin lesion are segmented. Features just like asymmetry, boundary irregularity, color and diameter (ABCD) have been extracted. An ABCD rule is used to detect the presence of cancer. Using an artificial neural network, the images have been graded. The findings obtained suggest the viability of the proposed method of diagnosis of skin cancer. Using this technique, encouraging results are obtained with BR algorithms which results in an accuracy of approximately 98 %, sensitivity of approximately 100% and specificity of approximately 96.2%, which is effective in detecting the presence or absence of melanoma. This technique is resistant to noise and image conditions and can be utilized for complicated skin lesions efficiently. This methodology is so comprehensive that it can be tailored to different medical image segmentations and predict skin cancer accurately. © 2021 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Electrochemical, Gravimetric, Quantum Chemical and Computational Investigations on an Effective Synthetic Chlorinated Cyclic Imide Derivative as a Corrosion Inhibitor for Carbon Steel in Sulfuric Acid Solution

SSRN

引用

SSRN 2024年

作者： Toghan, Arafat Alduaij, O.K. Farag, Ahmed A. Elabbasy, H.M. Dardeer, Hemat M. Fawzy, Ahmed Gadow, H.S. Riyadh11623 Saudi Arabia Chemistry Department Faculty of Science South Valley University Qena83523 Egypt Nasr City Cairo11727 Egypt Misr Higher Institute for Engineering and Technology Mansoura Egypt Chemistry Department Faculty of Science Assiut University Assiut71516 Egypt High institute of engineering and technology New Damietta Egypt

Although many different human activities such as the oil and gas sector, mineral production, utilities, transportation, etc. depend on the utilization of steel and its alloys, they are highly susceptible to corrosion, especially in acidic media. Hence, processing entails substantial material expenditures due to metal losses. In this regard, the inhibitory characteristics of the synthetic heterocyclic derivative (3aR,7S,7aS)-4,5,6,7,8,8-hexachloro-1,3-dioxo-1,3,3a,4,7,7a-hexahydro-2H-4,7-methanoisoindol-2-yl)benzenesulfonamide (MBSI) was studied against corrosion of C-steel in 0.5 M H2SO4 at 25-550 °C. The structure of the synthesized molecule was confirmed by FTIR, 1H-NMR, 13C-NMR, and MS. Weight-loss, potentiodynamic polarization, electrochemical impedance spectroscopy, electrochemical frequency modulation measurements as well as theoretical analyses were employed in this investigation. The results showed that the investigated MBSI compound functions as an efficient inhibitor with a physical adsorption nature on the surface of carbon steel. MBSI concentration causes the inhibition efficiency to rise, reaching a maximum of 94% for the steel alloy corrosion at 37 × 10-6 M and 25 °C. The synthesized compound was suggested to act a mixed-type inhibitor. SEM surface analysis showed construction of a protective layer at the carbon steel surface. DFT-based quantum chemical indices provided more insight into the inhibitory mechanism. Molecular dynamics (MD) simulations were also applied to predict the conformational adsorption change of the inhibitor on the iron surface. In addition, thermodynamic and kinetic parameters were calculated. The experimental results are largely consistent with the theoretical results. © 2024, The Authors. All rights reserved.

关键词： Corrosion inhibitors

来源：评论

学校读者我要写书评

暂无评论

Audio Signal Processing and Musical Instrument Detection using Deep Learning Techniques

Audio Signal Processing and Musical Instrument Detection usi...

引用

Japan-Egypt International Conference on Electronics, Communications and Computers (JEC-ECC)

作者： Sally M. Elghamrawy Shehab Edin Ibrahim Misr Higher Institute for Engineering and Technology Mansoura Egypt British University in Egypt Cairo Egypt

ISBN: (纸本)9781665482936

The advance of deep learning and audio signal processing techniques has led to serious development on Musical Information retrieval (MIR). Effective audio processing can improve speed, reduce errors, and sometimes increase the accuracy of detecting musical instrument. Spectrographic data is also necessary for many mathematical tools common across Musical Information retrieval. A major aspect of MIR is the categorization of pieces of music. One of the main tools used for categorization tasks in recent years is deep learning, which has led to many advancements in MIR. One such categorization task that deep learning is useful for is the recognition of instruments in a piece of music. In this paper, a new architecture is proposed for audio processing and musical instrument detection using Multilayer Perceptron (MLPs), Convolution Neural Networks (CNN), and Recurrent Neural Networks - Long Short Term Memory (RNN-LSTM). In addition, a number of experiments are implemented using real dataset that contains 20,000 recording. The three deep learning techniques are implemented and compared to present potential new solutions. The usage of processing techniques unique to the field of deep learning is also discussed.

关键词： Deep learning Recurrent neural networks Instruments Music Computer architecture Network architecture Multilayer perceptrons

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：